text
stringlengths 296
254k
|
---|
<s>[INST] Thank you for listening to this conversation with scott Aaronson and thank you to our presenting sponsor, cash app, Download it used collects podcast, you'll get $10.10 will go to first an organization that inspires and educates young minds to become science to technology innovators of tomorrow. You enjoy this podcast. Subscribe on Youtube, give it five stars on apple podcast, support on Patreon or simply connect with me on twitter Elex Friedman. Now let me leave you with some words from a funny and insightful blog post scott wrote over 10 years ago on the ever present malthusian. ISMs in our daily lives, quote again and again. I've undergone the humbling experience of first lamenting how badly something sucks. Then only much later having a crucial insight that it's not sucking wouldn't have been a nash equilibrium. Thank you for listening. I hope to see you next time [/INST] </s> |
<s>[INST] So they they grow up around fighting in all forms, yep. Um There are also, I mean their technique is exceptionally good [/INST] because they grow up in </s><s>[INST] it. They grow up [/INST] they don't they don't understand anything else </s><s>[INST] so you don't have to, it's almost like you were the way cutting, it's not like a big dramatic thing for them to fight. It's like this is just part of life. [/INST] Yes. And when you're I don't want to say bread into it but when you've done it For you know I want to say like 90% of your life by the time. Like could be probably has right from the time he could crawl he's probably been grappling in some fashion. Their of right. Um You know when you as grapplers like you can look at a wrestler having never seen this person before and go you wrestled. Yeah. Why is that? It's because he's probably wrestled since he was like six. So the way he carries himself, the way his body is built, the way he grew into it was framed around wrestling. Right? So the people in that culture are framed around fighting and grappling. </s><s>[INST] You're right, it's like first of all philosophically psychologically but also just like the way you move your body. That means like when you're young the people you admire move their body in a certain kind of way [/INST] and then genetically it just as they keep doing that they're just going to get better and better every generation. Yeah it's just going to keep improving because they just keep building into that system of turning them out. </s><s>[INST] And part of it there's like cultural stuff where, I mean it's such an interesting approach to wrestling. I really want to travel to Dagestan and just talk to them because it happened to be able to speak Russian because because there's um less value for this kind of materialistic success that I think sometimes can get in the way of greatness. It seems like it makes coaching more difficult. It makes like following orders as an athlete more difficult. I [/INST] don't struggle with that and usa judo </s><s>[INST] because you want more money but then more money if not applied correctly can corrupt the system somehow. It can split people up. [/INST] It's just the same thing with the prestige around certain metals over others because athletes start chasing fame instead of development. Yeah. </s><s>[INST] Yeah, that's I mean uh it's your brothers are famous for this, like ignoring ignoring fame, ignoring all of this. Like focus on the art itself, not even not. So it's not even the medals. Exactly. You're saying just the purity of like when you're in it and let everybody else figure out their stupid medals and money and all that because it comes, it comes [/INST] exactly as a result. </s><s>[INST] Exactly like it's not that you don't appreciate it, but you know that it comes if you focus on the art, [/INST] there's a distinction when you're talking about your athletic career or really any endeavor, right? The problem with goal setting is nobody teaches the athletes or the people how to transition from the goal to reality, right? So When you look at my career as a whole, like when I was getting ready for 2008, I actually forgot to train for it. I was so happy at such a young age that I became an Olympian that that in and of itself was a goal that I thought had to be admired, had to be celebrated that you know, the games are right around the corner. I I didn't really come down off that high, </s><s>[INST] you're the local optimum of, of just winning the trials. That was [/INST] a big thing. </s><s>[INST] It's a huge thing. But then you're just focusing on the accomplishment. Not the [/INST] correct, but at some point, right. When I, when I went into London, I actually went into London going with, I'm going to prove I'm the best in the world because I believe I'm the best in the world and I believe it from like the bottom of my soul that I'm winning this. And then you're almost like trying to tell the universe like I'm accomplishing this thing because it's a goal. But when I went into RIO, I just accepted the fact that I was winning. It's not a goal like this is happening. </s><s>[INST] You visualize [/INST] it, but I felt it. You felt it right? Like this is no longer a goal anymore. Mm Like I anticipate like this is happening. I can see this coming down the path because I'm anticipating that the games is happening and I'm gonna win. It's not a goal to anticipation and there's a distinct distinction there between the two. </s><s>[INST] Okay, so for people who are just watching the video of this, there should be an overlay of uh, Young Travis. This is uh, you still have to make 81. This is still a tough cut here. [/INST] No, this one was relatively easy. This is going all the way back to 2008. So this is the summer before the games. This probably happened in june I would say. </s><s>[INST] So this is the olympic trials. So in the United States you have to mean similar to like wrestling, you have to win the trials to qualify for that particular division to represent the United States. So this is you said june before in august olympics. Yeah. So here I just wanted to show this match because uh, what was there? There's another one, I think you do a pin, you just sign this groundwork and the other one. But in this one [/INST] fighting a teammate, </s><s>[INST] finding a teammate, [/INST] former teammate, Oh, there's an old school double leg, I forgot about that. And it's weird to see. </s> |
<s>[INST] Yeah, I kind of like the metric, that sort of the Alexa prize has proposed. I mean maybe it's obvious to you. It wasn't to me of setting sort of a length Of a conversation like you want the boat to be sufficiently interesting that you would want to keep talking to it for like 20 minutes. And that's a, that's a surprisingly uh effective in aggregate metric because really like nobody has the patience to be able to talk to about. That's not interesting and intelligent and witty and is able to go on the different tangents. Jump domains, be able to you know, say something interesting to maintain your attention. [/INST] Maybe many humans groups also failed this test. </s><s>[INST] Unfortunately we set just like with autonomous vehicles with chatbots. We also set a bar that's way too hard hide to reach. [/INST] I said, you know, the turing test is not as bad as some people believe, but what is really not useful about the turing test, it gives us no guidance how to develop these systems in the first place of course. You know, we can develop then by trial and error and you know, do whatever entered and run the test and see whether it works or not. But um a mathematical definition of intelligence gives us um you know an objective which we can then analyze by, you know, theoretical tools or computational um and you know, maybe improve how close we are and we will come back to that later. Um there's the ICSI model. So I mentioned the compression right? So in in that language processing and they have chief amazing results. And one way to test this of course, you know, take the system, you train it and then you you know, see how well it performs on the task but a lot of um performance measurement is done by so called perplexity. This is essentially the same as a complexity or compression length. So the LP community develops new systems and then they measure the compression length and then they have ranking um and leaks because there's a strong correlation between compressing well. And then these systems performing well at the task at hand. It's not perfect but it's good enough for them as as an intermediate aim. </s><s>[INST] So you mean measure? So this is kind of almost returning to the common growth complexity. So you're saying good compression usually means good intelligence. Yes. So you mentioned you're one of the, one of the only people who dared boldly to try to formalize our the idea of artificial general intelligence to to have a and mathematical framework for intelligence just like as we mentioned termed I X C A I X. I. So let me ask the basic question, What is I X. E. [/INST] Okay, so let me first say what it stands for </s><s>[INST] because what it stands for, actually, that's probably the more basic questions. The [/INST] first question is usually how, how it's pronounced. But finally I put it on the website how it's pronounced. You figured it out. The name comes from A. I. Artificial intelligence and the X. I. Is the greek letter Qusai which are used for Solomon's distribution for quite stupid reasons which I'm not willing to repeat here in front of the camera. So that just happened to be a more or less arbitrary chose the side but it also has nice other interpretations. So um their actions and perceptions in this model right? An agent has actions and perceptions and over time. So this is a index I X. Index I. So there's action at time I and then followed by perception at that time I </s><s>[INST] will go with that, I'll edit out the first [/INST] Part, I'm just kidding, I have some more interpretations. So at some point maybe five years ago or 10 years ago I discovered in in Barcelona, it wasn't a big church, there was a stone engraved some text and the word ICSI appeared a couple of times. It was very surprised and and uh happy about it and I looked it up. So it is a Catalan language and it means with some interpretation of that's it, that's the right thing to do. Yeah, America </s><s>[INST] Oh so it's almost like destined. Uh somehow it came came like I came to you in a dream so [/INST] similar. There's a chinese word I she also written like Alex, see if you can transcribe the tape engine and the final one is there is a I crossed with induction because that is and it's going more to the content now. Um so a good old fashioned ai is more about planning and non deterministic world and induction is more about often, you know, I a d data and inferring models and essentially what this ICSI model does is combining these two </s><s>[INST] and I actually also recently I think heard that in japanese ai means love. So so if you can combine X I somehow with that, I think we can uh there might be some interesting ideas there. So I said let's then take the next step, can you maybe um talk at the big level of what is this mathematical framework? [/INST] So it consists essentially of two parts, one is the learning And induction and prediction part and the other one is the planning part. So let's come first to the learning induction prediction part, which essentially explained already before. So what we need for any agent to act well is that it can somehow predict what happens if you have no idea what your actions do, how can you decide which acts are good or not? So you need to have some model of what your actions effect. So what you do is you have some experience, you build models like scientists, you know, of your experience then you hope these models are roughly correct. And then you use these models for prediction </s> |
<s>[INST] so you know, a lot of writers talk about, you know basically suffering the writing process is having, you know, it's extremely difficult and I think of programming especially the or technical writing that you're doing can be like that. Do you find yourself method a logically? How do you every day sit down to do the work? Is it a challenge you kind of say it's you know, it's fun but it would be interesting to hear if if there are non fun parts that you really struggle with. [/INST] So the fun comes when when I'm able to put together ideas of 2-2 people who didn't know about each other. And and so it might be the first person that saw both of their ideas. And so then you know, then then I get to make the synthesis and that gives me a chance to be creative. But the drudge work is where I I've got to chase everything down to its root. This leads me into really interesting stuff. I mean I I learned about Sanskrit night and you know, I try to give credit to all the authors and so I write, so I write to people who know the people authors if they're dead, I I communicate this way I and uh, I got to get the math right. And I got to tackle my programs, try to find holes in them. And I rewrite the program's over after I get a better idea. </s><s>[INST] Is there ever dead ends [/INST] that end? So yeah, I throw stuff out. Yeah. One of the things that I I spent a lot of time preparing a major example based on the game of baseball and I know a lot of people who, for whom baseball is the most important thing in the world, you know. But, but I also know a lot of people from cricket is the most important in the world or suck or something. And and I realized that if if I had a big temple and he was going to have a foldout illustration and everything I was saying, well, what, what am I really teaching about algorithms here? Where I had this, this, this this baseball example. And if I was a person who who knew on a cricket, wouldn't they, what would they think about this? And so I ripped the whole thing out. But you know, I had something that would have really appealed to people who grew up with baseball as a, as a major theme in their </s><s>[INST] life, which is a lot of people. But [/INST] just yeah, </s><s>[INST] still a minority. [/INST] Small minority. I took out bowling too. Uh, </s><s>[INST] even a smaller minority. What's the art in the art of programming? Why why is there of the few words in the title? Why is Art one of them? [/INST] Yeah. Well that's that's what I wrote my touring lecture about. And uh and so when people talk about are really, I mean, what the word means is something that's not in nature. So when you have artificial intelligence, that art comes from the same root saying that this is something that was created by by human beings. And then it's gotten a further meaning, often a fine art which has this beauty to the to the mix and says, you know, we have things that are artistically done and and this means not only done by humans but also done in a way that's elegant and uh brings joy and and has has uh I guess that Tolstoy dostoyevsky. </s><s>[INST] Uh [/INST] but anyway, it it's that part that that says that it's done well as well as not only different from nature in general, then uh art is what human beings are specifically good at. And when they say artificial intelligence, well, they're trying to mimic human beings, </s><s>[INST] but there's an element of fine art and beauty. You are one. That's [/INST] what I that's what I tried to also say that you can write a a program and make a work of art. </s><s>[INST] So now in terms of surprising, you know, what ideas in in writing from sort and search to the combinatorial algorithms. What ideas have you come across that were particularly surprising to you. That changed the way you see a space of problems. [/INST] I get a surprise every time I have a bug in my program obviously. But but but that isn't really what you're more </s><s>[INST] transformation for [/INST] Example in Volume four A. I was </s><s>[INST] especially surprised when I learned about [/INST] data structure called B. B. D. D. But bullying decision diagram because I sort of had the feeling that uh as an old timer. Uh and you know I've been programming since the since the fifties And uh b. d. d. s weren't invented until 1986. And here comes a brand new idea that revolutionizes the way to represent a boolean function. And boolean functions are so basic to all kinds of things in, you know, I mean logic underlies it. Everything we can describe all of what we know in terms of logic somehow and and and and uh proposition in logic. Uh I thought uh that was cut and dried and everything was known. But but but but here comes uh uh randy Bryant and uh and discovers that bds are incredibly powerful Then then. So so I uh that mean it means I have a whole whole new section to the book that I never would have thought of until 1986, 19 until 1990s when I went when people started to uh to use it for for you know a billion dollars of applications. Uh and it was it was the standard way to design computers for a long time until until sat solvers came along when in the year 2000. So that's another great big surprise. So a lot of these things have have totally changed the structure of my book. and the middle 3rd of volume for bees is about that summers. And that's 300 plus pages which is uh which was all about material mostly about material that was discovered in this century. Um and I had to start from scratch and you meet all the people in the field. Right. I have 15 different sets of words that I wrote while preparing that seven of them are described in the book. Others who are from my own experience. </s> |
<s>[INST] I mean you mentioned this gets slower and slower with age, but it's there like I've I think I've read and spoken offline even on this podcast with uh developmental neurobiologist, I guess would be the right terminology is like looking at the very early, like from from embryonic stem cells to like to the creation of the brain and like that's like what that's mind blowing, how much stuff happens there. So it's very malleable at that stage. Uh it's and then but after that, at which point does it stop being malleable. [/INST] So that's the interesting thing is that it remains valuable your whole life. So even when you're old person, you'll be able to remember new faces and names, you'll be able to learn new sorts of tasks and thank goodness because the world is changing rapidly in terms of technology and so on. I just sent my mother and Alexa and she, you know, figured out how to go in the settings and do the thing and I was really, I was really impressed by that, she was able to do it. So there are parts of the brain that remain malleable your whole life. The interesting part is that really your goal is to make an internal model of the world. Your goal is to say, okay, the brain is trapped in silence and darkness and it's trying to understand how the world works out there, right? </s><s>[INST] I love that image. Yeah, I guess it is you forget you forget it's like this, this lonely thing is sitting in its own container and trying to actually throw a few censors, figure out what the what the hell is going on. [/INST] You know, what I sometimes think about is um that movie, the martian with Matt Damon, the I mean he's written a book of course, but the movie poster shows Matt Damon all alone on the red planet, and I think God, that's actually what it's like to be inside your head, in my head, in anybody's head is that you're essentially on your own planet in there. And I'm essentially on my own plan and everyone's got their own world where you're, you've absorbed all of your experiences up to this moment in your life that made you exactly who you are and the same for me and everyone and and we've got this very thin bandwidth of communication and I'll say something like, oh yeah, that tastes just like peaches and you'll say, oh I know what you mean, but the experience of course might be might be vastly different for us. Um but anyway, yes, so the brain is trapped in silence and darkness, each one of us and what it's trying to do this is the important part is trying to make an internal model of what's going on out there. As in how do I function in the world? How do I, how do I interact with other people? Do I say something nice and polite, addressing something aggressive and mean, do I, you know, all these things that is putting together about the world? And I think what happens when people get older and older, it may not be that plasticity is diminishing, it may be that their internal model essentially has set itself up in a way where it says, okay, I've pretty much got a really good understanding of the world now and I don't really need to change. Right? So when old, when, when, when much older people find themselves in a situation where they need to change, they can actually are able to do it. It's just that I think this notion that we all have that plasticity diminishes as we grow older is in part because the motivation isn't there. Um, but if you were 80 and you get fired from your job and suddenly had to figure out how to program a wordpress site or something, you'd figure it out. </s><s>[INST] Got it. So the capability, the possibility of changes is there. But let me ask the highest challenge. The interesting challenge to this plasticity to this live wire system. Uh if we could talk about brain computer interfaces and neural link, uh what are your thoughts about the efforts of Elon musk and your link Bc. I in general in this regard, which is adding a machine, a computer. Uh the capability of a computer to communicate with the brain and the brain to communicate with the computer at the very basic applications. And then like the futuristic kind of thoughts. [/INST] Yeah. First of all, it's terrific that people are jumping and doing that because it's clearly the future. The interesting part is our brains have pretty good methods of interacting with technology. So maybe it's your fat thumbs on a cell phone or something. But um or maybe it's watching a Youtube video getting into your eye that way. But we have pretty rapid ways of communicating with technology and getting data. So if you actually crack open the skull and go into the inner sanctum of the brain, um you might be able to get a little bit faster. But I'll tell you. Yeah, yeah, I'm I'm not so sanguine on the future of that as a business. And I'll tell you why it's because there are various ways of getting data in and out. And an open head surgery is a big deal neurosurgeons don't want to do it because there's always risk of death and infection on the table. Um, and also it's not clear how many people would say I'm going to volunteer to get something in my head So that I can text faster, you know, 20% faster. So I think it's you know, mother nature surrounds the brain with this armored, you know, bunker of the skull because it's a very delicate material and there's an expression in neurosurgery um, about the brain is, you know, the person is never the same after you open up their school now, whether or not that's true or whatever, who cares. But it's a big deal to do an open head surgery. So what I'm interested in is how can we get information in and out of the brain without having to crack the skull open. </s> |
<s>[INST] Another thing that actually happened? I just have a million questions I wanna ask you is fascinating to me, uh, is there's a bird strike on the plane. Does that happen [/INST] often </s><s>[INST] damaged the engine? And they made it seem like it's a serious, exactly, serious [/INST] issue. I've hit birds. Um, I know someone that took a turkey vulture to the face through the cockpit, right, shattered the cockpit, knocked him out. Um, I think that actually, I don't know him personally, but the store I know from the command I was at, and I believe the back seater had to punch out and punch them both out because he was unconscious, you know, in the front seat from the bird. Um, it can kill you from hitting you. It's, you know, it's like a bowling ball going 250 miles an hour. Um, it can take out an engine, uh, very easily. Uh, every airport I've flown at in the navy, I've had to check the bird condition if you will to see how many birds we've had to cancel flights because, because there's too many of them around the airport, some airports even have bird radars. Airport, </s><s>[INST] there are systems that monitor the bird condition. [/INST] There's, yeah, there's actual radar systems and you can go in the certain bases, you have to call up and they'll tell you what it is for the day or for that hour and other ones have it in like their, their weather report that goes out over the radio. </s><s>[INST] What are some technological solutions to this? Or is this just uh because it's a low probability event? There's no real solution for it? [/INST] I would say it's not a little probably about event. I mean this is happening a lot. I mean although the hits themselves aren't necessarily that common or I'll say a catastrophic hit, either a near miss or hit or the pilot having to actively maneuver to avoid. It is pretty common and in fact it </s><s>[INST] seems stressful. [/INST] It is, it's so common in fact that we know that you never want to try to go over or you never want to go under a bird. If you see it in front of you, you always want to try to go over it because what they'll do immediately if they see you is and you startled and they'll bring their wings in and just drop straight down to try to get out of the path. It's interesting. I didn't know they did that, but so if you immediately, if you try to go under them will be dropping into you. So you typically want to try to go above them. </s><s>[INST] Is this something you can train for or no. [/INST] Um, is </s><s>[INST] this one of those things you have to really experience? It's [/INST] a skill set that um, you somewhat trained for in the duties of being a fighter pilot descent, right? Being able to react to your environment very quickly and make make decisions quickly. So is </s><s>[INST] that one of the more absurd things challenges you have to deal with. And flying. Is there other things sort of maybe weather conditions like harsh weather conditions? Is there something that we maybe don't often think about in terms of the challenges of flying [/INST] birds in a way aren't a ridiculous threat for us. It's it's a safety threat that, you know, anything physical in the air is, it's something that we really have to be careful about whether we're flying formation off of the aircraft right next to us or whether it's a turkey vulture at 2000 ft or a flock of 5000 birds like at the runway, we have to wave off, You know, and although there are low probability, a lot of bases will have like actual environmental protecting agency employees that are responsible for safely removing migratory birds or different animals um, that maybe in the runways or flying about, </s><s>[INST] wow, I didn't know what a turkey vulture is and it really does look like a mix between a vulture and a [/INST] turkey </s><s>[INST] and look kind of dumb. No offense to turkey vultures. Um, in that movie. Who was the enemy nation? Was it? Uh, I mean, I think, I guess they were implying as Iran or was it Russia? [/INST] I didn't think they were implying any particular nation state, frankly, I think they did a somewhat decent job of having some Ambiguous 5th generation fighters the location and and the stockpile like I get like how the story kind of insinuates certain things. But they seemed a good job of not having anything directly pointing to another nation, which I thought was, you know, the good move. I I enjoy these type of movies as an aviator and you know, as an american, right? Cause it's a feel good movie. But um you know, we we shouldn't be celebrating going to war with any particular country, you know, china Russia, whoever may have these weapons. It's it's fun to watch but it would be an incredibly serious event to be employing these weapons. </s><s>[INST] Yeah, well we'll talk about war in general because yeah, it's the movies kind of celebrating the human side of things and also the incredible technology involved. But there's also the cost of, of war and the seriousness of war and the suffering involved with war not just in the fighting but in the death of civilians and all those kinds of things. Um Well you wore a Navy pilot, let's let's talk a little bit more uh seriously about this And you were twice deployed in the Middle East flying the F a 18 F super hornet. Can you briefly tell the story of your career as a navy pilot? [/INST] Sure. So I joined the Navy in 2009. Right after college, I went to officer essentially officer bootcamp officer candidate school I applied as a pilot and I got into the pilot that was advantage of going that way is that essentially choose what I wanted and if I got in great if not I didn't get stuck doing something else. So </s> |
<s>[INST] And hopefully, I mean, you can assume that is uniformly distributed. [/INST] Hopefully, we can assume and there's evidence that it's uniformly distributed. Yes. So then the next so all of these factors so far number of stars accessible to whatever telescope you're thinking about how many stars are quiet fraction of stars that are quiet fraction that are observable in this case for the geometric factor. Those are all things we can measure. And there's one more term in the seeker equation, we can measure. I call it fraction of planets in the habitable zone because, believe it or not, we have a handle on that for a certain set of stars we know from our the kepler space telescope that operated for a number of years. We have estimates for how many planets in the so called habitable zone of the host star for a certain type of star. So all those we have measurable and then like the drake equation itself, there's some terms we can not measure and those ones, I call them fl fraction of all those planets that have life on them because we don't know what that is. And F. S. I. Called for spectroscopy. The fraction that have, we can use our telescope and instrument tools to look for light actually, Fs was the ones that the planets that that have life that actually gives off a gas, useful gas that might accumulate in the atmosphere so we could eventually observe it. </s><s>[INST] How do the F. L. N. F. S. Interplay? So these are separate terms, [/INST] separate terms. </s><s>[INST] And so [/INST] so for example, you can imagine so for example, you can imagine life like us, humans, we breathe out carbon dioxide, but our planet Earth, we already have a lot of carbon dioxide on it. Well, we have hundreds of parts per million, but it has a really strong signal. So as humans breathing out carbon dioxide, it's not helpful for any intelligent beings that are looking back at Earth because there's already a lot of there's already enough carbon dioxide, we're not adding to it. So if there is life on the planet and it's about putting a boring gas that's not helpful for us to uniquely identify as being made by life versus just being there anyway, then it's not helpful. So, I separated those two terms out soon. I think we'll have evidence that planets that can support life at least are common. </s><s>[INST] So, okay, this is such an awesome topic of a million questions. What? Okay, I know there's a little bit of speculation. But what's your sense about that? Uh I think FS which is like that life would produce interesting gasses that would be able to detect. Like is there one, Is there scientific evidence? And and second is there some intuition around life producing gasses, detectable hints in terms of chemistry [/INST] so interestingly and have that entire question relates to, I'm going to say almost my life's work. The work I'm doing now and the work I'm doing for the next 20 years. And I wish I could give you a concrete number. Like 1%. Like on the worst days, it's 1%. Let's say in my mind, you know, the best days, it's like 80% and I could actually go into a lot of detail here, but I'll just give you the simplest things. So, first of all, we make an assumption that, like us and our life here on earth, life uses chemistry. So we use chemistry because we eat food, we breathe air and we have metabolism that to break down food to get energy, to store energy and then ultimately to use it. And all life here has some kind of byproduct in doing all that, some kind of waste product that goes into the atmosphere. So, I like to think that life everywhere uses chemistry. Some people have imagined like, let's imagine like a windmill, like mechanical energy, just getting energy and using it without storing it. And if there was life like that, it might not need to output, I guess. So, we make this basic assumption of chemistry. That's the first thing. The second more complicated thing that I and my team work on is what happens to the gas. Once it is produced by life it goes into the atmosphere and a lot of gas is just destroyed immediately actually by ultraviolet radiation or by oxygen. Oxygen is incredibly destructive to a lot of gasses. So the gas can be produced by life, but it could be just completely destroyed by its environment. </s><s>[INST] I guess we should pause on that. That you mentioned your life's work and this is just a beautiful idea that it's kind of paralyzing, when you look out there and you wonder, is there life out there. Uh, it's the first paralyzing actually before I encountered your work. I feel like an idiot. But you know, uh, it feels like there's no tool to answer that question. And then you kind of provided is this cool idea that it might be possible to answer that by looking at the gas is, I mean, that's a really interesting. That's a beautiful idea. And uh, yeah, so we can just pause on like just that's as a powerful tool. I think that to build the intuition wrong cause I was totally clueless about it and I was is kind of exciting. I mean, I'm sure there's a folks probably early on in your life who were very skeptical about this notion. Maybe. I'm not sure, but it's generally, you would want to be skeptical of like, well all these kinds of other things could generate gasses, you know, all [/INST] those. That's so true. And that's a big part of this growing field is how to make sure that this gas isn't produced by another effect. But do you want to again, pausing on that and going back a bit, it's incredible to think, but like at least almost 100 years ago, there's a record of someone talking about the idea of a gas being an indicator of life elsewhere </s> |
<s>[INST] It's [/INST] been very useful, reductionism has been useful but it's over. And it's time for us to go beyond. </s><s>[INST] When you say space time is doomed. Is it the space is that is that the time is that the very hard coded specification of four dimensions um or are you specifically referring to the kind of perceptual domain that humans operate in which is spacetime? You think like there's a three D. Um like our world is three dimensional and time progresses forward. Therefore three dimensions +14 D. What what exactly do you mean by space time. What do you mean by space time is doomed. [/INST] Great. Great. So this is by the way, not my quote. This is from for example, Nima Hamed at the Institute for Advanced study at Princeton Ed witten. Also there David Gross Nobel prize winner. So this is not just something the cognitive scientists and this is what the physicists are saying. </s><s>[INST] Yeah, the physicists are spacetime uh skeptics. [/INST] Well, they're saying that, I can say exactly why they think it's doomed. But what they're saying is that because your question was what what aspect of space time? What are we talking about here? It's both space and time, their union into space time as in Einstein's theory that's doomed. And they're they're basically saying that even quantum theory, this is the Marconi Hamad especially. So Hilbert spaces will not be fundamental either. So that that the notion of Hilbert space, which is really critical to quantum field theory, quantum information theory, uh that's not going to figure in the fundamental new laws of physics. So what they're looking for is some new mathematical structures beyond space time beyond Einstein's four dimensional spacetime or supersymmetric version, geometric algebra signature to come before kind of, there are different ways that you can represent it, but they're finding new structures and then by the way they're succeeding now they're finding they found something called the amplitude Hedren. This is nemo and his colleagues, the the cosmological polito. These are so there are these like politics. These policy dra in multi dimensions? Generalizations of simplicities that our coding for, for example, the scattering amplitudes of of processes in the large Hadron collider and other other colliders. So they're finding that if they let go of spacetime completely, they're finding new ways of computing these scattering amplitudes that turn literally billions of terms into one term when you do it in space and time, because it's the wrong framework. It's it's it's just a user interface from that's not from the evolutionary point of view, just user interface, it's not a deep insight into the nature of reality. So it's missing. Deep symmetry is something called a dual can formal symmetry, which turns out to be true of the scattering data, but you can't see it in space time and is making the the computations way too complicated cause you're trying to compute all the loops and Feinman diagrams and all the fine men integral. So see the fine men approach to the scattering amplitudes, is trying to enforce two critical properties of space time locality and unitary T. And so by when you enforce those, you get all these loops and multiple different levels of loops. And for each of those you have to add new terms to your computation. But when you do it outside of space time you don't have the notion of unitary T. You don't have the notion of locality, you have something deeper and is capturing some symmetries that are actually true of the data. And but then when you look at the geometry of the facets of these polito hopes then certain of them will code for unitary T and locality. So it actually comes out of the structure of these deep politics. So what we're finding is there's this whole new world now beyond space time that is making explicit symmetries that are true of the data, that cannot be seen in space time, and that is turning the computations from billions of terms to one or two or a handful of terms. So we're getting insights into symmetries and we're all of a sudden the math is becoming simple because we're not doing something silly. We're not adding up all these loops in spacetime, we're doing something far deeper. But they don't know what this world is about. Also, you know, they're in an interesting position where we know that space time is doomed and I should probably tell you why it's doomed. What they're saying about why it's doomed. But but they need a flashlight to look beyond space time. What what flashlight are we going to use to look into the dark beyond space time? Because Einstein's theory and quantum theory can't tell us what's beyond them all they can do is tell us that when you put us together, spacetime is doomed at 10 to the -33 cm, 10 to the -43 seconds beyond that space time doesn't even make sense, It just has no operational definition. So, but it doesn't tell you what's beyond. And so they're they're just looking for deep structures like guessing it's really fun. So these really brilliant guys, generic brilliant men and women who are doing this work, physicists are making guesses about these structures informed guesses because they're trying to ask, okay, what deeper structure could give us the stuff that we're seeing in spacetime, but without certain commitments that we have to make in spacetime like locality unit. So they make these brilliant guesses. And of course, most of the time you're gonna be wrong, But once you get one or two that start to pay off and then you get some lucky breaks. So they got a lucky break back in 1986, a couple of mathematicians named Park and Taylor took the scattering amplitude for two gluons coming in and high energy and four glue ons going out at low energy. So that kind of scattering thing. So apparently for people who are into this, that's sort of something that happens so often you need to be able to find it and get rid of those because you already know about that. You need to so you needed to compute them. It was billions of terms and they couldn't do it even though for the supercomputers couldn't do that for the many billions or millions of times per second they need to do it. So they begged the experimentalists begged the theorist please can you gotta. So Park and Taylor took the billions of terms, hundreds of pages and Miraculous, Miraculous. They turned it into nine. And then a little bit later they guessed one term expression that turned out to be equivalent. So billions of terms reduced to one term that so called famous park Taylor formula 1986. And that was like, okay, where did that come from? What? This is a pointer into a deep realm beyond space and time, But but no one, I mean, what can you do with it? And they thought maybe it was a one off. But then other formulas started coming up and then eventually Neymar Connie Hamed and his team found this thing called the amplitude which really sort of captures the whole a big part of the whole ball of wax. I'm sure they would say no, there's plenty more to do. So I won't say they did it all by any means. They're looking at the cosmological polito as well. So what's remarkable to me is that two Pillars of modern science, quantum field theory with gravity on the one hand, And evolution by natural selection on the other, just in the last 20 years have very clearly said, space time has had a good run reductionism has been a fantastic methodology. So we had a great ontology of spacetime, a great methodology of reductionism. Now it's time for a new trick, </s> |
<s>[INST] thought of so eric drives towards the fundamental and new draft towards the emergent, the physics and biology, [/INST] right, opposite ends of the continuum. And as eric would be quick to point out if he was sitting here, I treat the emergent layer, I seek the fundamentals in it, which is sort of an echo of eric style of thinking but applied to the very far complexity. </s><s>[INST] He's uh overpowering, lee argues for the importance of physics the fundamental of the fundamental, he's not here to defend himself. Is there an argument to be made against that or Biology? The emergent, the study of the thing that emerged when the fundamental acts at the universal at the cosmic scale and builds the beautiful thing that is us is much more important. Like uh psychology, Biology. The systems that we're actually interacting within this human world are much more important to understand than um low level uh theories of quantum mechanics and general relativity. [/INST] Yeah, I can't say that one is more important. I think there's probably a different time scale. I think understanding the emergent layer is more often useful but the bang for the buck at the far fundamental layer may be much greater. So for example the fourth frontier, I'm pretty sure it's going to have to be fusion powered. I don't think anything else will do it. But once you had fusion power, assuming we didn't just dump fusion power on the market the way we would be likely to if it was invented usefully tomorrow. But if we had fusion power and we had a little bit more wisdom than we have, you could do an awful lot. And that's not going to come from people like me who you know, look at dynamics. </s><s>[INST] Can I argue against that, please? I think the way to unlock fusion power is through artificial intelligence is so I think most of the breakthrough ideas in the futures of science will be developed by ai systems and I think in order to build intelligent Ai systems, you have to be a scholar of the fundamental of the emergent of biology, of the neuroscience, of the way the brain works of intelligence, of consciousness and those things at least directly don't have anything to do with physics. [/INST] Well, you're making me a little bit sad because my addiction to the ah ha moment thing is incompatible with, you know, outsourcing that job. I don't want to outsource that thing to the moment. Um You know, and actually I've seen this happen before because some of the people who trained Heather and me, we're from the genetic systemic pistes, Arnold clergy in particular. And the problem with systematics is that to do it right, when your technology is primitive, you have to be deeply embedded in the philosophical and the logical, right? Your method has to be based in the highest level of rigor. Once you can sequence genes, genes can spit so much data at you that you can overwhelm high quality work with just lots and lots and lots of automated work. And so in any, in some sense, there's like a generation of genetic systemic ists who are the last of the greats because what's replacing them as sequencers. Um So anyway, I maybe you're right about the Ai and I guess I'm just said I like figuring stuff out, </s><s>[INST] is there something that you disagree with the american? They've been trying to convince them, you failed so far, but you will eventually succeed. [/INST] You know, that is a very long list eric and I have have tensions over certain things that recur all the time. And I'm trying to think what would be, you know, the </s><s>[INST] idea in the space of science in the space of philosophy, politics, family, love robots. [/INST] Well, all right, let me, I'm just going to use your podcast to make a bit of cryptic war and just say there are many places in which I believe I have butted heads with erIC over the course of decades and I have seen him move in my direction substantially over. You've </s><s>[INST] been winning. He might, he wouldn't battle here there, but you've been winning the [/INST] war. I would not say that it's quite possible. He could say the same thing about me. And in fact, I know that it's true. There are places where he's absolutely convinced me. But in any case, I do believe it's at least it may not be a totally even fight, but it's more even than some will imagine. Um, but yeah, we have, you know, there are things I say that drive him nuts. Right? Like when </s><s>[INST] something, [/INST] you know, like you heard me talk about the, what was it? It was the autopilot that seems to be putting a great many humans in needless medical jeopardy over the COVID-19 pandemic. And my feeling is we can say this almost for sure any time you have the appearance of some captured gigantic entity that is censoring you on, youtube and, you know, handing down dictates from the who and all of that. It is sure that there will be a certain amount of collusion, right. There's gonna be some embarrassing emails in some places that are going to reveal some shocking connections. And then there's going to be an awful lot of emergence that didn't involve collusion right in which people were doing their little part of a job and something was emerging and you never know what the admixture is. How much are we looking at actual collusion and how much are we looking at an emergent process? But you should always walk in with the sense that it's going to be a ratio. And the question is, what is the ratio in this case? I think this drives eric nuts because he is very focused on the people. I think he's focused on the people who have a choice and make the wrong one. And anyway, he made </s> |
<s>[INST] Singularity squared, that's singularity squared. That's already beyond the first singularity. But can we just? Yeah, let's go back to open cog. No, no. Yeah, and the hypergraph and open cog. [/INST] No, no, open cog. That's the software framework, right? So then the next thing is our cognitive architecture tells us particular algorithms to put there. </s><s>[INST] Got it. Can we backtrack on the kind of, is this graph designed, is it in general supposed to be sparse and the operations constantly grow and change the graph? Yeah, the graph is sparse. But is it constantly adding links and so on to graph? [/INST] Yeah, the graph is sparse. Links and so on? </s><s>[INST] It's a self-modifying hypergraph. So it's not the right and read operations you're referring to. This isn't just a fixed graph to which you change the way. No, no, no. [/INST] It's a disgusted growing graph. No, no, no. similar disgusted growing graph. Yeah, that's true. But it is different model than say current deep neural nets, and they have a fixed neural architecture, and you're updating the weights, although there have been cascade correlational neural that architectures that grow new nodes and links. But the most common neural architectures now have a fixed neural architecture. You're updating the weights. And in OpenCog, you can update the weights. And that certainly happens a lot. But adding new nodes, adding new links, Removing nodes and links is an equally critical part of the systems operations. </s><s>[INST] Got it, got it. So now when you start to add these cognitive algorithms on top of this open cog architecture, what does that look like? [/INST] So what? Yeah, so within this framework then, creating a cognitive architecture is basically two things. It's choosing what type system you wanna put on the nodes and links in the hypergraph, what types of nodes and links you want. And then it's choosing what collection of agents, what collection of AI algorithms or processes are gonna run to operate on this hypergraph. And of course those two decisions are closely connected to each other. So in terms of the type system, there are some links that are more neural net like, they're just like have weights to get updated by heavy and learning and activation spreads along them. They're other links that are more logic like and nodes that are more logic like. So you could have a variable node and you can have a node representing a universal or existential quantifier as in predicate logic or term logic. So you can have logic like nodes and links or you can have neural like nodes and links. You can also have procedure like nodes and links as in say a combinatorial logic or Lambda calculus representing programs. So you can have nodes and links representing many different types of semantics, which means you could make a horrible ugly mess, or you could make a system where these different types of knowledge all interpenetrate and synergize </s><s>[INST] with each other beautifully, right? [/INST] So the hypergraph can contain programs? Yeah, it can contain programs. Although in the current version, it is a very inefficient way to guide the execution of programs, which is one thing that we are aiming to resolve </s><s>[INST] with our rewrite of the system now. So what to you is the most beautiful aspect of OpenCog? Just to you personally, some aspect that captivates your imagination from beauty or power? [/INST] What fascinates me is finding a common representation that underlies abstract declarative knowledge and sensory knowledge and movement knowledge and procedural knowledge and episodic knowledge, finding the right level of representation where all these types of knowledge are stored in a sort of universal and interconvertible, yet practically manipulable way, right? So to me, that's the core. Because once you've done that, then the different learning algorithms can help each other out. Like what you want is if you have a logic engine that helps with declarative knowledge and you have a deep neural net that gathers perceptual knowledge and you have, say, an evolutionary learning system that learns procedures, you want these to not only interact on the level of sharing results and passing inputs and outputs to each other, you want the logic engine, when it gets stuck, to be able to share its intermediate state with the neural net and with the evolutionary learning algorithm so that they can help each other out of bottlenecks and help each other solve combinatorial explosions by intervening inside each other's cognitive processes. But that can only be done if the intermediate state of a logic engine, the evolutionary learning engine and a deep neural net are represented in the same form. And that's what we figured out how to do by putting the right type system </s><s>[INST] on top of this weighted labeled hypergraph. So is there, can you maybe elaborate on what are the different characteristics of a type system that can coexist amongst all these different kinds of knowledge that needs to be represented? And is, I mean, like, is it hierarchical? Just any kind of insights you can give on that kind of type system? [/INST] Yeah, yeah, yeah, yeah. So this gets very nitty gritty and mathematical, of course. But one key part is switching from predicate logic to term logic. </s><s>[INST] What is predicate logic? What is term logic? [/INST] So term logic was invented by Aristotle, or at least that's the oldest recollection we have of it. But term logic breaks down basic logic into basically simple links between nodes, like an inheritance link between node A and node B. Node A and node B. So in term logic, the basic deduction operation is A implies B, B implies C, therefore A implies C. Whereas in predicate logic, the basic operation is modus ponens. It's like A, A implies B, therefore B. So it's a slightly different way of breaking down logic. But by breaking down logic into term logic, you get a nice way of breaking logic down into nodes and links. So your concepts can become nodes, the logical relations become links. And so then inference is like, so if this link is A implies B, this link is B implies C, then deduction builds a link A implies C. And your probabilistic algorithm can assign a certain weight there. Now, you may also have a heavy and neural link from A to C, which is the degree to which A being the focus of attention should make B the focus of attention. So you could have then a neural link, and you could have a symbolic logical inheritance link in your term logic. And they have separate meaning, but they could be used to guide each other as well. If there is a large amount of neural weight on the link between A and B, that may direct your logic engine to think about, well, what is the relation? Are they similar? Is there an inheritance relation? Are they similar in some context? On the other hand, if there's a logical relation between A and B, that may direct your neural component to think, well, when I'm thinking about A, should I be directing some attention to B also? Because there's a logical relation. So in terms of logic, there's a lot of thought that went into how do you break down logic relations, including basic sort of propositional logic relations, as Aristotelian term logic deals with, and then quantifier logic relations also. How do you break those down elegantly into a hypergraph? Because I mean, you can boil logic expression into a graph in many different ways. Many of them are very ugly, right? We tried to find elegant ways of sort of hierarchically breaking down complex logic expression into nodes and links so that if you have, say, different nodes representing Ben, AI, Lex, interview, or whatever, the logic relations between those things are compact in the node and link representation. So that when you have a neural net acting on those same nodes and links, the neural net </s> |
<s>[INST] Listen, you're frustrated and I could see it over a few years of just having dealt [/INST] with the humongous influx of charlatans. I wouldn't say frustrated, I'm amused. </s><s>[INST] And it's no, it's water off my back. No, but a man they use this in a community, they use the word shit coin is a little bit, you have, you call it amusement. And I think amusement is a way to deal with the frustration, it's a channeling of frustration. Like sometimes when you have to deal with bullshit, the best way is just to laugh at the absurdity of it all. And that's what you mean by amusement. But the fact is like, there's things like artificial intelligence for what is it? How many decades, seven decades, has been off and on promising to change everything. And it has failed time and time again to deliver to the promise. But that doesn't mean there's something fundamental and really powerful about both the small and the big things going on within the actual research and development within those communities. There's a lot of exciting developments and the scale at which those developments might actually have a transformative impact, the time scale is unclear. It seems like we certainly over promise it. We dream too big and too aggressively in the AI community [/INST] but a lot of them- Yeah and I'm happy to give people the benefit of the doubt when they're overpromising but not when they're making their own money. When you start making your own currency then you don't get the benefit of the doubt. Because if your idea needs you to have a new currency that you print when Bitcoin is out there, then I'm gonna go ahead and assume that you're doing this for the money- </s><s>[INST] Good time to mention that I am actually launching my coin called Lex coin. You mean shit coin. Yes. Oh, God. I'm gonna have to block you with love. Okay, one thing I wanted to ask you about is the Feds, this paper they released in January 20th on the potential central bank digital currency, CBDC. What are your thoughts about that? Is it just another, like, is there pros and cons to this? Is it all interesting to you [/INST] that they're even considering this kind of thing? Oh, God. I used to think that it's just basically waffle. It's meaningless. Because as it exists, the dollar is a central bank digital currency. The vast majority of dollars are digital. But I think the way that over the last couple of years I've changed my mind on this, I think there's some serious substance behind these ideas. And what they mean effectively is the disintermediation of the banking system. And giving everybody an account at the Federal Reserve. This is kind of the really dangerous idea. And I think this is enormously significant. Effectively, as somebody who's lived in the Soviet Union, what this is, is the return of the Goss Bank on a global scale with modern technology. So under the Soviet Union, there was something called the Goss Bank or People's Bank. And that was the only bank in the country. And you had an account with the National Bank. And if you said something wrong, your money got terminated from the Goss Bank. Now, imagine that combined with the power of digital technology, and you can see that this could be an enormously powerful technology really. Because if banks are out of the picture, then we changed the fundamental reality of fiat as being the creation of money through lending. And then it becomes the creation of money truly by fiat, by government fiat. So we moved to a system in which money is just basically it's like we have money that is pieces of paper. And every time we've had money, we've had fiat money that was just pieces of paper, it collapsed very quickly. With the current system, money is credit. And the creation of credit is restricted to some point. And the creation of credit is self-correcting. I discussed this in the fiat standard. If the central bank allows banks to create too much credit, that creates a bubble and then, there's a collapse in the money supply, which prevents hyperinflation from happening because the money creation is self-destructive, it's self-correcting. So you end up with an average of like 7% per year increase because you have 10% for five years and then you get negative 20% for one year and it's correcting. But now if you get rid of the credit creation mechanism and it's just assigning money directly, we're likely gonna get much faster inflation. And I think that's obviously a huge problem and perhaps an even bigger problem is the enormous amount of power that it gives to governments. It allows them to create an awful dystopia where you've got your money on your phone and anything you do is completely supervised and controlled through your spending. So they wanna introduce a new lockdown, then they'll just make your money not work. Your money's broken today, you can't spend money or you can only spend money in your local supermarket for the next three months because you can't leave your neighborhood, your money stops working outside of your neighborhood. This Chinese social credit score system is an example of this. And I think, I don't know, I don't have a crystal ball, so I don't know what the likelihood is of implementing something like this in the US. I've discussed it with Michael Saylor, he thinks it's highly unlikely, he thinks the people who've been pushing this are very far from the position of power and the traditional monetary and financial system is going to survive intact. I certainly hope so. I think this would be a terrible thing if it comes to pass. But I don't think, many people think that it is something that would undermine Bitcoin. Like a lot of common objection to Bitcoin is, well, governments are just gonna launch their own digital currencies and then Bitcoin is gonna die. And I think this is completely missing the point. People think Bitcoin is important because it's digital, it's not, national currencies can be digital. Bitcoin is important because it's not inflationary and because nobody controls it. Central bank digital currencies are likely to be very inflationary and they're likely to have very strong control at the top. So if anything, they are an advertisement for Bitcoin, rather than a replacement for it. </s> |
<s>[INST] toughness to technique to the art, to the science. [/INST] Yeah, all that stuff. And that's why I even talking to you and you're sitting over there you love M. I. T. And you're bragging about it over Harvard you know uh you know it's because it's true in your eyes and and and that's and that's great and it might be but but it's the same type of thing that you know there's something that you're probably stealing from Harvard but but you won't give them credit. </s><s>[INST] Well then in the interest of time I've read that you're pretty serious, you're pretty seriously into fishing. So what's the biggest fish you ever caught? What are we talking about here? Are you talking about? [/INST] No I don't think I've ever caught a big ocean fish. I'm not I'm a river lake fishermen. I have uh you know probably uh Probably northern, I probably caught a northern net weighed 20 some pounds. Uh You know my fish I like to catch his Wall eyes and that the reason why I like to catch them because they're really good eating fish and the best eating fish are not the real big ones. Uh You know it's kind of kind of interesting. They got people hunting deer right on my land and they're looking for the big bucks but they're not the best eaters if you want if you want to eat them but they're the best trophy so you know I I do have a couple of trophy wall is on the wall but but most time I throw the big ones back and put them back in there so </s><s>[INST] I don't know if you know there's a book by Hemingway called old man in the sea, uh [/INST] huh </s><s>[INST] Ernest Hemingway Yeah, and he uh there's a, there's an old man that basically uh catches an 18 footer but it can't pull it in, doesn't have the strength. So they together spend while the sharks eat away at it. I mean this is very powerful story. I think one of the Nobel prize, but he says it's better to be lucky. The old man says it's better to be lucky, but I would rather be exact that that that way when luck comes, you're ready. So let me ask, uh what do you think about luck? Do you believe in free will, that we have actions that control the direction destination of our life? Or does luck and some other outside forces really land you where you end up [/INST] for me. I'm not about luck, but I do think there is luck is involved, but I think it's mostly created uh just how lucky you are through preparations and things have things have happened in my life forever. A lot of good things and a lot of people could say, hey, you've been pretty lucky to win all these awards. I don't know if you analyze my life. I don't think it was involved with luck, you know, I think it was more involved with preparation and you know, and again, science had you been smarter, had you understood that you could do some things and be just as lucky, that'd be great, but I'm only as smart as today. So when I was training in my life and me even training people in my life as of that moment, that's how lucky I am to be able to uh, have whatever is available to me. And that's what you call that a lot of science. So for me, I, I think that, you know, like right now, if I look back, I do a lot of things different just because things are proven differently. Like I give people water during practice and I did and I would let them change their running wrestling shoes into running shoes to run sprints on the concrete or I would actually, maybe, Maybe I had a guy climbed 12 ropes after practice, one after another and then maybe the next day I'd do it again. Uh, you know, I might not make him do it the next day, I might let him recover a little bit more and uh, you gotta learn, keep adding to your philosophy and your philosophy may have been great at that time, but it's at that time. And what is really important is where you at with this time today. And so there's better ways to do things now. If you ever take attitude out of it and just depend on total science, then, you know, you're not going to be as, as, uh, you know, I think as I listened to a couple people that are really pretty famous people, uh, one of those john Irving, he was a writer and he told me, he says, you think I really learned how to be a great writer and writing school. I said yeah, I learned a lot there. But really what gave me the ability to stay focused to work extra hours to be more disciplined was wrestling practices </s><s>[INST] that he was a wrestler. [/INST] Yeah, he goes I go back to that, that's what gave me that chance. You know, and and there's a guy in Iowa that uh guy named norman Borlaug's, he he learned he he invented a process to feed the underprivileged countries of the world and he was a wrestler and he said the same thing and he he worked extremely hard and he said uh I give a lot of credit to the sport of wrestling. Uh and even though I was, I'm known for this and I got a statue and in Washington D. C. Because I saved a billion lives. Plus I'm going to give wrestling a lot of credit. So you know, I think some of these mm a. Stars and some of these guys that maybe weren't wrestlers that had to Russell russell had to fight wrestling guys and stuff missed a little bit there. But I think the ones that did have rustling probably have a really good chance and can adapt to the other ones. But I think every martial art or every activity is good and you probably can't skip any, But I don't think they're ever gonna overlook and say that rustling pretty not are not valuable because it is however, that doesn't mean you're gonna make it, you still got to take the values and apply it whatever area you're gonna be in. And and some people forget that some people can't get over the highness of getting your arm raised in a wrestling match and you know what's even greater than me getting my arm raised is that if I'm a coach or if I wasn't belong with you that you get your arm raised and even if you don't get your arm raises what you walk away with and how and how you learn two handle that as well because there's gonna be some losses but you don't want many because you don't want to get used to losing. I can tell you that </s> |
<s>[INST] of what we're doing on this planet. It's interesting, the thing about the Big Bang is basically from our current perspective of what we're able to detect, [/INST] it's the time when things were forgotten. </s><s>[INST] Yes. It's the time of the reset, from our limited perspective. And so the question is, is it useful to ever study the thing that was forgotten? Or should we focus just on the memories [/INST] that are still there? Well, the point I was trying to make about the experiment is I was trying to say both things. And I think perhaps yes from the following point of view, if you could then imagine what was forgotten and then work forwards, you will have different consequences. So then it becomes testable. So as long as we can find tests, then it's definitely worth thinking about. What I don't like is when physicists say what happened before the Big Bang and before, before, before, without giving me any credible conjecture about what we would, how would we know the difference? But the way you framed it is quite nice. I like that. </s><s>[INST] It's like, what have we forgotten? Is there a room for God in assembly theory? [/INST] Who's God? I like arguments for a necessary being better than God. Well, I think I said it earlier. What's a necessary- Like something that has to exist. Well, I think I said it earlier. </s><s>[INST] What's a necessary- Oh, so you like, I mean, you like the shortest path. [/INST] Like does God need- No, no, no. I mean, I, well, you can go back to like Thomas Aquinas and arguments for the existence of God. But I think, I think most of the interesting theological arguments are always about whether something has to exist or there was a first thing that had to exist. But I think there's a lot of logical loopholes </s><s>[INST] in those kinds of arguments. Well, so God here, meaning the machine [/INST] that creates, that generates the stuff. But God- So what I was trying to say earlier is- Isn't that just the universe. That's what I was trying to say earlier is- Isn't that just the universe? </s><s>[INST] Yeah, yeah, yeah. Yeah. Yeah, well, yeah. Yeah, yeah. Well, yeah. Well, yeah. Well, but I, there's a difference between... Should I imagine like a black box, like a machine? Yeah. That's then I would be more comfortable [/INST] calling that God. </s><s>[INST] Yeah. That because it's a machine. [/INST] You go into a room and there's a thing with a button. Yeah. I don't like the great programmer in the sky version. </s><s>[INST] Can I? You know? Yeah, but if it's more kind of, Like to don't like to think of, if you look at a cellulared autonomous, If it's the cells and the rules, that doesn't feel like God that generates a bunch of stuff. But if there's a machine that runs the cellular automata and set the rules, then that feels like God, in terms of terminology. So I wonder if there's a machine that's required to generate this universe. [/INST] That's very important for running this in the lab. So as I said earlier, I think I said this earlier, that I can't remember the phrase, but something like, I mean, does God exist in our universe? Yes. Where does God exist? God at least exists in the abstraction in our minds, particularly of people who have religious faith they believe in. But let's then take your, but you're talking a little bit more about generic, say, well, is there a mechanism beyond the universe you're calling God? I would say God did not exist at the beginning, but he or she does now, because I'm saying the mechanism. </s><s>[INST] Well, you don't know if he didn't exist in the beginning. So this could be us in our minds trying to just listen to gravitational waves, detecting gravitational waves. It's the same thing. It's us trying to go back further and further into our memories to try to understand the machines that make up, that make up us. And so it's possible that we're trying to grasp at possible kind of what kind of machines could create. There's always a tweet. There's always a tweet. If the universe is a computer, then God must have built it because computers need creators. There you go. And then Joachim Bach replied, since there's something rather than nothing, perhaps existence is the default. If existence is the default, then many computers exist. Creator gods are necessary computers, unnecessarily computers too. I'm very confused by that. [/INST] But that's an interesting idea that existence is the default versus non-existence. </s><s>[INST] I agree with that, but the rest is not. And then Lee responds, perhaps this reasoning is incomplete. That's how scientists talk trash each other on Twitter, apparently. [/INST] Which part don't you agree with? And he said, if existence is the default, then many computers exist. This comes back to the inventor and discovery argument. I would say the universe at the beginning wasn't capable of computation because there wasn't enough technology, enough states. So what you're saying is if God is a mechanism. So I might actually agree, but then the thing is lots of people see God is more than a mechanism. For me, God could be the causal graph in assembly theory that creates all the stuff and memories we know. And the fact that we can even relate to each other is because we have the same, we share that heritage. And why we love each other or we like to see God in each other is it's just we know we </s> |
<s>[INST] Yeah I would I would I would I would really love to um to visit now. We returned back. I don't know how we ended up in. Iran but let us, let us stroll back to uh Stalin taking power. What role did the suppression of speech, the censorship, the suppression of the freedom of the press have in um Stalin taking hold taking power in Lenin and Trotsky in Stalin having power. [/INST] Well it was a very useful mechanism to direct public opinion and inform public perspectives and everything. So first of all there was a lot of news about how um great things were. You have a bumper crop here, you know, grains never better you have. There's this great, there's another anecdote where President Clinton is talking about how um </s><s>[INST] on [/INST] Karl Marx street in Kharkiv there's all sorts of new skyscrapers being built and it's just absolutely amazing and some of the audience gets up and goes comrade, I work on Karl Marx street, I walk there every day, there's none of these skyscrapers goes see that's your problem, you're trusting your eyes instead of reading something and learning what's in the papers. So there was this kind of disconnect between you know, I forgot you probably know the joke like Pravda. Pravda is like probably means truth but there's no truth to be had in probably is like kind of Russian line. The point is it very much. And the other thing this is, you know, my mom wasn't particularly politically motivated but she talked about how you didn't have to be smart to realize how dishonest it was because one day someone is the great hero of the soviet people. and the next week he's been a traitor and ACL class enemy and the worst. And then sometimes they reverted and it's like, okay, like they couldn't even keep their stories straight. And in fact at a certain point when they, you know, Gorbachev liberalized, they had to cancel tests because the history books had to be rewritten so quickly. Um so and the thing that also with these newspapers is there was a lot of it was very monotonous because, you know, you had the same message over and over. Uh a lot of these papers were about kind of speaking to the lowest common denominator, Stalin's great, everything's great overseas bad. So it it very much was about not informing but creating uh a certain perspective in the public at large. And also it you you were educated as a citizen on what you're supposed to think and say. So you have a lot of this was this kind of um private truths, public lies situation. So you could read the paper and at your at your factory, you could be like, oh my God, this this guy, Karl radek is great. He's like, oh my God, yeah, he's amazing. You know, you know what to talk about and you knew how to look at it as well. And then when you get home you could just kind of be more honest with family, </s><s>[INST] but the question is to what degree does this propaganda and this ideology infiltrate, your actual thinking? Um, you give examples of scientists infiltrated science. [/INST] Oh yeah, So basically, you know, Lutsenko is the textbook example of heroism in biology. So because Marxism is materialist, uh, they didn't like the idea that genes pass on, um, you know, from one generation to the next. So Lysenko ism kind of was a rejection of Mendel and that kind of genetics. And if you reject jeans, you're really going in a bad direction in terms of biology, the soviet Union's biological biological program became an international laughing stock. At one point, Lutsenko claimed he crossed the tomato and potato. Um you had things where they said they had nuclear, which is what we have fish in. But they said they invented fusion or hard or heavy water or hard water? It was point being in cultures like this, your way to achieve status wasn't necessarily about your accomplishments but about your loyalty to orthodoxy. So if you were saying things that got to a result that was congruent with the broader ideology as a whole, that was much better as a means of furthering yourself in the arts or in the scientists in the sciences than if you had something that was innovative because if you're innovative, it's like, well, how do I fit this in with the broader ruling ideology? The problem, totalitarianism. One of the many problems is everything, literally everything has to be perceived through the lens of ideology. So, and that is, you know, there were um scientists who were arrested, or at least fired because of their theories about sunspot developments, because it was regarded as a Marxist. There was just there was there was an epidemic and all these horses got sick. And because the vaccine didn't work on the horses, the bacteriologist were arrested because they regard as records, it's like we gave you a job, you didn't do it, you're undermining the Socialist State. So it's kind of a backwards series of incentives. Um, and it's designed to maintain at all costs the ruling ideological superstructure. </s><s>[INST] But you draw a small distinction between the ideology and the ideological superstructure and the propaganda. Aren't those kind of intermixed together? [/INST] Well, the ideological, like in the sciences and what's true and genetics or what's true in astronomy, that doesn't really percolate out to the masses. Right? So the problem is not, is maybe covering this scientist is great or these discoveries are great, but it's not necessarily the same as day to day or glorifying political leaders, </s><s>[INST] but probably as a manifestation of the idea that truth can be conjured [/INST] up. Yes, it can be </s> |
<s>[INST] is there anecdotal stuff like with steve jobs? I think their stories right, in your exploration of the is there something a little bit more than just stories? Is there like a little bit more of a solid data points, even if they're just experiential like anecdotes? Is there something that you draw inspiration from? Like in your intuition, because we'll talk about your trying to construct studies that are more rigorous around these questions? But is there something you draw inspiration from from the past from the 80s and the 90s and Silicon Valley that kind of space? Or is it just like you have a sense based on everything you've learned and these kind of loose stories that there's something worth digging at. [/INST] I am influenced by the gosh, the the just incredible number of, of anecdotes surrounding these. I mean, um uh Carrie Mullis, he he invented pcr I mean absolutely revolutionized biological sciences. He says he wouldn't have won the Nobel prize for him and said he wouldn't have come up with that, had he not had psychedelic experiences. Um you know, now he's an interesting character. People should read his autobiography because you could point to other things he was into, but I think that speaks to the casting your nets wide and this mental flex more of these general these general mechanisms where sometimes if you cast your nets really wide and it's going to depend on the person and their influences, but sometimes you come up with false positives, you know, um you know, you connect the dots where maybe you shouldn't have connected those dots, but I think that can be constrained and so much of our not only a personal psychological suffering but our our limitations um academically and in terms of technology are because of the self imposed limitations and and heuristics, these entrance ways of thinking, you know, like, you know, those examples throughout the history of science where someone has come up with a rat, the paradigm Kuhn's paradigm shifts, it's like, here's something completely different, you know, this doesn't make sense by any of the previous models and like, we need more of those, you know, and then you need the right balance between that because so many of the, you know, novel crazy ideas are just bunk and you you need, that's what science is about separating them from from the valid paradigm shifting ideas. But we need more paradigm shifting ideas, like in a big way. And I think we could, I think you could argue that we've because of the structure of academia and science in modern times, it heavily biases against those </s><s>[INST] right? There's all kinds of mechanisms in our human nature that resists paradigm shift quite sort of obviously so and uh psychedelics, there could be a lot of other tools, but it seems like psychedelics could be one set of tools that encourage paradigm shifting thinking. So like the first principle is kind of thinking, so it's a kind of uh you're at the forefront of research here, There's just kind of anecdotal stories, there's uh early studies, there's a sense that we don't understand very much, but there's a lot of depth here. How do we get from there to where Ellen and I can regularly, like I wake up every morning, I have deep work sessions where it's well understood uh like what dose to take, Like if I want to explore something where it's all legal, where it's all understood and safe, all that kind of stuff. How do we get from where we are today to they're not speaking in terms of legality in the sense like policy making all that like laws and stuff meaning like how do we scientifically understand this stuff well enough to get to a place where I can just take it safely in order to expand my uh thinking like this kind of first principles thinking, which I'm in my personal life currently doing? Like how do I have revolutionized particular? Several things like it seems like the only tools I have right now. It's just just but my mind going doing the first principles like, wait, wait, wait, okay. Why has this been done this way? Can we do completely differently? It seems like I'm still tethered to the prior that I bring to the table and I keep trying to untether myself. Maybe there's tools that can systematically help me on to other. [/INST] Yeah, well we need experiments, you know, and that's that's tied to kind of the policy level stuff. Um, and I should be clear. I would never encourage anyone to do anything um illicitly. But yeah, you know, uh in the future we could see these these, you know, compounds used for the for for technical and scientific innovation. What we need are studies that are digging into that right now. Most of what the funding, which is largely fun from philanthropy, um, not from the government. Um, largely what it's for is treatment of mental disorders like addiction and depression, et cetera. Um, but we need studies, you know, one of the early initial stabs on this question decades ago was they took some architects and engineers and said, what what problems have you been working on? Where you've been stuck for months like working on this damn thing and you're not getting anywhere like your heads butting up against the wall. It's like come in here taken. I think it was 100 micrograms of LSD so not a big session and a little bit different model where they were actually working. It was a moderate enough dose where they could work on the problem during the session. I think probably I'm an empiricist. So I'd I'd like to see all the studies done. But the first thing I would do is like a really high dose session where you're not necessarily in front of your computer. You know what you can't really do on a really high dose. And </s> |
<s>[INST] So if you skip please still check out the sponsors by clicking the links in the description. It is in fact the best way to support this podcast. This episode is sponsored by the jordans. Harbinger show. Go [/INST] to Jordan's </s><s>[INST] harbinger dot com slash lex. Subscribe to it. Listen, you won't regret it. I've been binging on this podcast for the entirety of 2020, Jordan's a great interviewer, he gets the best out of his guests dives deep, calls them out when it's needed and makes the whole thing fun to listen to. He has interviewed Kobe Bryant, Mark Cuban, the other grasse Tyson, Garry, Kasparov and many more. Perhaps more importantly, he is unafraid of addressing challenging even controversial topics with thought and grace, especially like his feedback friday's episodes where his combination of fearlessness and thoughtfulness is especially on display, touching topics of sex corruption, mental disorders. Hey love and everything in between. Again, go to Jordan harbinger dot com slash lex is how he knows I sent you On that page, there's links to subscribe to the show on everywhere you listen to podcasts including apple podcast. Spotify. If you're listening to this, I'm sure you know how this works. Oh, and if you like it, probably go give five stars to show, leave a nice review. Tell him I sent you this show is also sponsored by the thing had currently really need, which is coffee for stigmatic, the maker of delicious mushroom. Coffee and plant based protein. I enjoyed both. The coffee has lines, mane mushroom for productivity and Chicago mushroom for immune support. The plant based protein has immune support as well and tastes delicious, which I think honestly at least for me is the most important quality of both protein and coffee supporting your immune system is one of the best things you can do now to stay healthy And this difficult time for the human species. Not only does for stigmatic, always have 100% money back guarantee, but right now you can try their amazing products for up to 50% off and on top of that you get extra discounts for just the listeners of this podcast. If you go to four stigmatic dot com slash lex, that's four stigmatic dot com slash lex. This episode is sponsored by better help spelled h E L p help. I always think about the movie castaway when I spell out the word help. Okay, they figured out what you need and match you with a licensed professional therapist under 48 hours. I chat with a person on there and enjoy it. Of course. I also have been talking to over the stretch of 2020 and looks like 20, as well to David Goggins who is definitely not a licensed professional or some would say saying, but he does help me meet his and my demons and become comfortable to exist in their presence. This is just my view, but I think mental struggle is essential for creation, but I think you can struggle in a way that's controlled and done beautifully as opposed to in a way that destroys you. I think therapy can help in this and better help us a good option for that. There are easy, private, affordable available worldwide. You can communicate by text any time and schedule weekly audio and video session to give a shout out to the to O G. S. My two favorite psychiatrist, Sigmund Freud and Carl Young when I was younger. Their work was important in my intellectual development anyway, check out better health dot com slash lex. That's better help dot com slash lex. The show is also sponsored by Express VPN. It provides privacy in your digital life. Without VPN, your internet service provider can see every sight you've ever visited, keeping a log of every single thing you did online. So your internet provider, like A T and T or Comcast is allowed to store those logs and sell this data to anyone. That's why you should use Express VPN as much as possible. I do it. You should consider doing it as well. They don't keep any logs, they audit their attack by external companies. These guys are legit. I think this topic and VPN certainly are especially relevant now when the power of social media firms and SPS was made a parent with a wave of deplatforming actions, we need to use tools that lessen the power of the centralized entities. I use Express VPN is just one example of such a tool. Go to Express VPN dot com slash lacks pod to get an extra three months free on a one year package as a big red button if you enjoy those kinds of things. I certainly do. Okay, that's express VPN dot com slash flex pod. Sign up for the privacy and the big red button that's expressive BN dot com slash flex pod. And now here's my conversation with max tag mark. So people might not know this, but you were actually episode number one of this podcast just a couple of years ago and now we're back. And it so happens that a lot of exciting things happened in both physics and artificial intelligence both feels that you're super passionate about. Can we try to catch up to some of the exciting things happening and artificial intelligence especially in the context of the way it's cracking open the different problems of the sciences. [/INST] Yeah, I'd love to. Especially now, as we start 2021 here, it's a really fun time to think about what were the biggest breakthroughs in aI, not the ones necessarily the media wrote about, but that really matter. And and what does that mean for our ability to do better science? What does it mean for our ability to help people around the world? And what does it mean for new problems that they could cause if we're not smart enough to avoid them? So, you know, what do we learn basically from this? </s> |
<s>[INST] can you explain a little little further what is the chemical here? That what are we talking about? So how I I don't understand how it's possible to have a physical pad that does the encryption without any computing. How does it [/INST] so so no no it doesn't it doesn't do any work you know so and the uh the communication that the encrypted communication was was a a set of Uh groups of five five digits and another five. And there's always a gap in between. Um and so let's say if I get this radio transmission I write them all down and then I then I use my developed my algorithm and then I do mathematics. Either addition or subtraction. The resulting set of digits had then had a 1-1 correlation to letters. And </s><s>[INST] this is an easy way to then do the correlation. Yes I guess that's cool that you're saying the algorithm was not efficient it was not [/INST] the manual that took a long time and and you can't make an arrow right </s><s>[INST] Would you know where can you? It's easy to debug. No you know [/INST] you do it twice. </s><s>[INST] You do it twice and that's how you check [/INST] it's identical then you know </s><s>[INST] it's not [/INST] then then one is right and the other is wrong. You gotta </s><s>[INST] don't make mistakes. [/INST] No that's right and I really didn't. But anyway um so I was I was learning that I was also told that I was required to become proficient in another language and they gave me a choice and I picked english. What </s><s>[INST] Was the other 1? Oh [/INST] no they gave him pick one friend, you know whatever is spoken in the west. What </s><s>[INST] was what was what would be second to you? Would you would you think french because of paris? What would you why English [/INST] english was a no brainer because I was a straight a student in english without studying like it came so easily to me. So that's why I chose it. Right? </s><s>[INST] Uh [/INST] So that was that then um I was taught the basics of counter surveillance, you know some trickery and and and uh surveillance detection routes where you wander around in the city for three hours and determine whether you're being followed or not. That requires you to plan the route very well. I give you one example that that will illustrate that as my my favorite spot when when when I was in Moscow. I did a lot of that also. And my favorite spot was it wasn't not well traveled road, it went down the hill and and curved and at the bottom of the hill there was a telephone booth and when you opened the door and pick up the telephone you have to look back so it wasn't like this right? It wasn't a giveaway. This was normal, it was natural so you could see if somebody would come walking after me. You know these kinds of things or you would uh you know use um public transportation, big buildings where you needed to use an elevator and see who's because surveillance the object of surveillance is to never lose sight of the individual who you're surveilling because at that point you may miss the window where he does something that you're looking for. So somebody always has to come close. Right. </s><s>[INST] Did you have to also study surveillance [/INST] counter surveillance and what helped me? And in all my training, you know I would be would have a competition with folks that were coming, they were following me and me and I beat them every time they were at a disadvantage because one of them always had to be close and and if you saw the same face twice, you know that we were being followed and I had a very very good memory for faces. So </s><s>[INST] basically figure out a fixed [/INST] route </s><s>[INST] and then a fixed route that allows you to uh survey the area and then record the faces you've seen inside your mind and if you see multiple times a single face that's that's a bad sign. [/INST] And and they could they could uh you use different clothes uh but they didn't have was facemasks the C. I. A. Does nowadays they can give you a different face with within seconds. Yeah. </s><s>[INST] So how I mean again you talk about paranoia. Uh huh. Is that part of the is that a big part of the job counter surveillance? Like being constant paranoid that you're being watched? [/INST] Yeah, I was supposed </s><s>[INST] to isn't that quite stressful? So is that is that one of the is that actually an effective way to operate? [/INST] Nobody? It sort of becomes a routine, I was told to do it while in the US once a month and uh </s><s>[INST] it's [/INST] not every day. No no no no no once a month or before, I would say mail a letter with secret writing. So I was sure that you know, nobody saw me put an envelope into a post box. </s><s>[INST] So this is one of the tools in your toolbox. There's morse code, there's the decryption and encryption, there's the counter surveillance, [/INST] photography, making making micro dots, you know what a microdot is? Well that's uh that's uh you use you take a photograph and you use a microscope in reverse and make that photograph really small so small that it's like the head of a pin that can be used to hide under a postage stamp. Huh. In reality I knew how to make him but in reality then they never asked me to make use of that technique. </s><s>[INST] It's a sort of an encryption mechanism for photographs. [/INST] Yeah. So what we do nowadays in embed code and and PDFs and stuff like that. Right. Yeah. </s> |
<s>[INST] viewers. How do you tackle that problem? What was the uh you're just freaking out behind a computer? There's word are there other other folks working on this problem that we're behind a white board where you doing [/INST] uh a little pair coding? He has a little lonely because there's four of us working on the company and only two people really wrote code and Emmett wrote the website in the chat system and I wrote the software for this video streaming device and video server. And so, you know, it's my sole responsibility to figure that out. And I think I think it's those, you know, setting, setting deadlines trying to move quickly and everything where you're in that moment of intense pressure that sometimes people do their best. And most interesting work. And so even though it was a terrible moment, I look back on it fondly because that's like, you know, that's one of those character defining moments, I think. </s><s>[INST] So in uh 2013 October you found a cruise automation, so progressing forward. Another exception, successful company was acquired by GM in 16 for $1 billion. But uh in October 2013, what was on your mind? What was the plan? How does one seriously start to tackle one of the hardest robotics most important, impact robotics problems of our age [/INST] after going through twitch, twitch was was and is today pretty successful. But the the work was the result was entertainment mostly like the better the product was, the more we would entertain people and then, you know, make money on the ad revenues and other things. And that was that was a good thing. It felt it felt good to entertain people. But I figured like, you know what is really the point of becoming a really good engineer and developing these skills other than, you know, my own enjoyment. And I realized I wanted something that scratched more of an existential itch, like something that truly matters. And so I basically made this list of requirements for a new, if I was going to do another company. And the one thing I knew in the back of my head that twitch took like eight years to become successful. And so whatever I do, I better be willing to commit, You know, at least 10 years to something. And when you think about things from that perspective, you certainly, I think raise the bar on what you choose to work on. So for me, the three things where it had to be something where the technology itself determines the success of the product, like hard, really juicy technology problems because that's what motivates me. And then it had to have a direct and positive impact on society in some way. So example would be like healthcare, self driving cars because they save lives, other things where there's a clear connection to somehow improving other people's lives and the last one is it had to be a big business because for the positive impact to matter, it's got to be a large scale and I was thinking about that for a while and I made like tried writing a gmail clone and looked at some other ideas and then it just sort of light bulb went off like self driving cars, like that was the most fun I had ever had in college working on that and like, well what's the state of the technology has been 10 years, maybe, maybe times have changed and maybe now is the time to make this work. And I poked around and looked at the only other thing out there really, at the time was the google self driving car project and I thought surely there's a way to, you know, have an entrepreneur mindset and sort of solve the minimum viable product here. And so I just took the plunge right then and there and said this, this is something I know I can commit 10 years to. It's the probably the greatest applied ai problem of our generation and if it works, it's going to be both a huge business and therefore like probably the most positive impact I can possibly have on the world. So after that light bulb went off, I I went all in on cruise immediately and got to work. </s><s>[INST] Did you have an idea how to solve this problem? Which aspect of the problem to solve? You know, slow like we just had the Oliver for voyage here, slow moving retirement communities, urban driving, highway driving. Did you have like did you have a vision of the city of the future or you know, uh, transportation is largely automated, that kind of thing or was it sort of uh more fuzzy and gray area than that. [/INST] My analysis of the situation is that google is putting a lot, had been putting a lot of money into that project, had a lot more resources and so, And they still hadn't cracked the fully driverless car, you know, this is 20, I guess. So I thought, what, what can I do to sort of go from zero to, you know, significant scale so I can actually solve the real problem, which is the driverless cars. And I thought here's the strategy will start by doing a really simple problem or solving a really simple problem that creates value for people. So eventually ended up deciding on automating highway driving, which is relatively more straightforward as long as there's a backup driver there. And uh, you know, the go to market will be able to retrofit people's cars and just sell these products directly. And the idea was we'll take all the revenue and profits from that and use it to do the this is sort of reinvest that in research for doing fully driverless cars. And that was the plan. The only thing that really changed along the way between then and now is we never really launched the first product. We had enough interest from investors and enough of a signal that this was something that we should be working on that. Um after about a year of working on the highway autopilot, we had it working, you know, at the prototype stage, but we just completely abandoned that and said we're going to go all in on driverless cars now is the time. Um, I can't think of anything that's more exciting and if it works more impactful, so we're just gonna go for it. </s> |
<s>[INST] Let's return back to human institutions and talk about history of human civilization and politics. So one question to ask is, was America founded as a christian nation in your view, what if we look at the declaration of Independence? What do the words mean? We hold these truths to be self evident that all men are created equal, that they are endowed by their creator with certain inalienable rights that among these are life, liberty and the pursuit of happiness. It seems like God is breathing through those words to [/INST] yeah, I think so, yeah. The founders will be some kind of combination of deism. Um, certainly Christianity is, is coming up through them, enlightenment, rationalism all in kind of a mix, you know, So you're not going to find our founding fathers simply thomas Aquinas or like a purely, you know, classically christian understanding, it's Christianity in those various expressions because actually, I would see the enlightenment as a sort of um child of Christianity. We could talk about that. But having said all that, yes, I think they are expressing at least the residue of a once deeply integrated christian sense of things that our rights are not created by the government. They're not uh, doled out by the government. They come from God. And the other thing I find really interesting is equality because um look in classical philosophy, political philosophy, plato Aristotle cicero, it's not equality for them. It's our inequality. That's really interesting. So plato divides us into the three classes. And aerosols has only a tiny little coterie of property. Males of sufficient education should be in the political life. The rest should all be in private life, you know? And then some are suited for slavery. So I mean, he divides us dramatically. Same with cicero and so on. Um where did this come from? This weird idea that we're all equal. I mean, how we're not equal in beauty, not equal in strength, not equal in moral attainment were not equal and intelligence. So what is it? And I think the residue especially comes through in that little word that all men are created equal? That's our equality, that we're all equally Children of God. So take God out of the picture, I think we are going to slide rapidly into an embrace of inequality now in the classical world. Yes. But heck, look at the 20th century, I mean, when God is excluded in a very systematic way, I think you saw the suspension of rights and the suspension of equality like mad. So, no, I think it's very important that God is in the picture and that we're a nation under God. It matters enormously. That's not pious boilerplate. That's at the at the rational foundations of our democracy. </s><s>[INST] So, do you think Nietzsche was onto something with the idea Looking into the 20th century that God is dead? That there is uh, a cultural distancing from a belief in God? [/INST] Yeah. You know, I I'd be somewhat sympathetic to Jordan Peterson's reading of Nietzsche there, namely, it's not Nietzsche crowing from the mountaintop, hey God is dead. You know, it's more of a lament, You know, God is dead and we've killed them. And what will happen in the wake of that? And I think, yeah, much of the totalitarianism in the 20th century follows from that, that questioning of God and the dismissal of God from, from public life. So I would be sympathetic with that. Um, when we're beyond good and evil? You know, and all that's left is the will to power. And then why are we surprised that the powerful rise and that they use the power less for their purposes? When we forget ideas like equality and rights which are grounded in God? Why are we surprised that that death camps follow? So I think there's a correlation there for sure. </s><s>[INST] I don't know. I believe that there's a capacity to do good in all of us and a capacity to do evil and there's something that tends towards good, whatever that is. I tend to think that if that community that love that we talked about, they find each other, they find the good. If you don't constrain the resources, if you don't push them, if you um don't artificially create conflict through power centers and evil charismatic leaders, then people would be good to each other. And whether that's God or some other source of deep um moral meaning that seems to be essential for functioning civilization. And it's hard. I mean, that's what humans are. We're searching for. What that God is what that means. [/INST] You know, that triggers in my mind. I wonder if you agree with this, that the modern sciences drew their strength from their narrowness. What I mean there is is they almost completely bracketed formal and final causality in the aristotelian sense and they focused on efficient and material causality. And that gave, as I say, great strength. But from the narrowness of focus. But for Aristotle the more important causes are the final and the formal causes and so final causality there. What's drawing us? So for air style, he'd look at someone like me and say, okay, you're you have an intelligible structure and that leads you to seek certain things for the perfection of that structure, you know? And fair enough. And that's right. So I seek the good. Right now, I'm seeking the good of being with you. I said, yeah, I'll sit down with lex Friedman and we'll talk about deep and important things. That's the good. I saw it this morning when I woke up now, why am I seeking that? Well, for a higher reason to hire good, you know, because it's part of my work, my ministry is to, you know, the the church reaching out beyond itself to the wider culture and okay, well, why do you want that? Because I want to bring more and more people into into the what I think is beautiful and true and good in the church? Well, how come you want that? Well, because a long time ago, I was kind of myself brought into that realm and find it very compelling. Yeah. But then why do you want that? Because ultimately I want to be, I want to be friends with God. Now I've given you one example there, but but any act of the will. It seems to me has to be analyzed that way. The will seek something. It seeks the good right by definition but the good always nest like a Russian doll in a higher good right. Which then nesting is still higher good until you come. This is acquainted to some in this sense uncalled cause an an caused final cause there has to be some some um bonham right some supreme good that you're looking for and that's God by the way, that's another I think rational path to God is is every single moment every day we are implicitly seeking God. </s> |
<s>[INST] Well. So you also discuss effective altruism, which is a mechanism for going around government for putting the power in the hands of the people to donate money towards causes to help, you know, do you know, remove the middle man and give it directly to the to the causes they care about, sort of Maybe this is a good time to ask you 10 years ago wrote the life you can save. That's now think available for free online. [/INST] That's right. You can download either the e book or the audio book free from the life you can save dot org. </s><s>[INST] And what are the key ideas that you present in in the book? [/INST] The main thing I want to do in the book is to make people realize that is not difficult to help people in extreme poverty, that there are highly effective organizations now that are doing this, that they've been independently assessed and verified by research teams that are expert in this area and that it's a fulfilling thing to do to, for at least part of your life. You know, we can't all be saints, but at least one of your goals should be to really make a positive contribution to the world and to do something to help people who through no fault of their own are in very dire circumstances and living a life that is barely, or perhaps not at all a decent life for a human being to live. </s><s>[INST] So you describe a uh, a minimum ethical standard of giving, what, what advice would you give to people that want to be effectively altruistic in their life, like live and effective altruism life. [/INST] There are many different kinds of ways of living as an effective altruist. And if you're at the point where you're thinking about your long term career, I'd recommend you take a look at a website called 80,000 hours, 80,000 hours dot org, which looks at ethical career choices. And they range from, for example, going to work on Wall Street so that you can earn a huge amount of money and then donate most of it to effective charities to going to work for a really good nonprofit organizations so that you can directly use your skills and ability and hard work to further a good cause or perhaps going into politics, maybe small chances, but big payoffs in politics, go to work in the public service where if you're talented, you might rise to a high level where you can influence decisions, do research in an area where the payoff could be great. There are a lot of different opportunities. But too few people are even thinking about those questions. They're just going along in some sort of preordained rut, two particular careers, maybe they think they'll earn a lot of money and have a comfortable life, but they may not find that as fulfilling as actually knowing that they're making a positive difference in the world. </s><s>[INST] What about in terms of, so that's like long term, 80,000 hours, shorter term giving part of, well actually it's a part of that and go to work at Wall Street. If you would like to give a percentage of your income, you talk about life, you can save that. I mean it was looking through, it's quite a compelling um, it's, I mean I'm I'm just a dumb engineer. So I like the simple rules. [/INST] Okay, so I do actually set out suggested levels of giving because people often ask me about this um a popular answer is give 10% the traditional Thai that's recommended in Christianity and also Judaism, but You know, why should it be the same percentage irrespective your income tax scales reflect the idea that the more income you have, the more you can pay tax and I think the same is true in what you can give. So uh I do set out a progressive donor scale which starts at 1% for people on modest incomes And rises to 33 and a 3rd% for people who are really learning a lot. And my idea is that I don't think any of these amounts really impose real hardship on people because they are progressive and get to income. So I think anybody can do this and can know that they're doing something significant to play their part in reducing the huge gap between people in extreme poverty in the world and people living affluent lives. </s><s>[INST] And aside from it being an ethical life, it's one that you find more fulfilling because like there's something about our human nature that or some of our human nature's maybe most of our human nature that enjoys doing the the ethical thing. [/INST] Yes, I make both those arguments that </s><s>[INST] it is an [/INST] ethical requirement and the kind of world we live in today to help people in great need when we can easily do so, but also that it is a rewarding thing. And there's good psychological research showing that people who give more tend to be more satisfied with their lives. And I think this has something to do with having a purpose that's larger than yourself. Um and therefore never being, if you like, never, never being bored sitting around or you know what will I do next? I've got nothing to do in a world like this. There are many good things that you can do and enjoy doing them, plus you're working with other people in the effective altruism movement who are forming a community of other people with similar ideas and they tend to be interesting, thoughtful and good people as well and having friends of that sort is another big contribution to having a good life. </s> |
<s>[INST] Through any of this. The pain you have to go through with Leukemia. But also the days of 9:11 and after did your faith get challenged? [/INST] You know, like, it was strange. It was times, it was so angry, you know, is that range of emotions, the anger, the denial, the depression of this or that. And this is the weirdest thing. It was, it was mostly I knew my career was over and uh, they retired me out of the job that I got sick in august and that october they told me I was out and by the time I was processed and you know, used up my, my leaves and whatever you want to say, it was, I was, I was officially retired in january of 02 And less than six months And I'm there walking my dog one day, my rescue greyhound to I miss, she was such a soul. God, she lived to be almost 13, Katie. And uh, we're walking in the snow and I got the call, I was retired and I looked at her, I'm like, Katie, what am I gonna do? And she just looked up. So we're gonna go on a lot more walks, you know? And I was so sad. I was so sad. I was so angry because I lost my priesthood. I loved helping people. I really like, I would have done it for free. I would never tell Mayor Bloomberg that right. It's all about the book, right? But like, you know, honestly, I would've, I would've been in New york city fireman, I would have paid them to do it, you know? And uh I wasn't allowed anymore. That's it. You have over 20 years and you have cancer, you know, back when my dad got sick, they let you hang around for 10, 12 years in an office, but not now now, it's all about the bottom line and uh but I was more depressed about losing a job than almost losing my life, like as crazy as that sounds, you know, and it just uh </s><s>[INST] it was more than a job. I mean it's uh it's a way of life, man. It's also is your family, your father, you're carrying torture. Your father's [/INST] Oh my friend, I love my friends, I love we work 24 hour shifts. Yeah, you cook, you clean your breaking jobs relentlessly. I mean it was I love those guys so much. I mean I I hope that my kids and anyone that I know and care about, I hope they can experience the bond of that brotherhood that I experienced in my life, it was so God, I would give anything to have it back. Just yeah, </s><s>[INST] can see about new york. So when I I've unfortunately never lived in new york, I visit, I've always wanted to live there for a bit, obviously it's a very different experience to have really lived in new york for many, many years, but there's a few friends of mine that are firm, they got similar accent is yours that uh that are a little bit saddened. Perhaps it's temporary, but perhaps not. They don't seem to think so of what new york has become, especially with Covid, it's losing some of the spirit of new york. Um Do you have that sense? Do you, do you have a hope for this city that has been so defining to what is America? [/INST] You know, my heart is broken. I had moved to New Jersey many years ago and but I still have a close attachment to new york. My my parents were still there many, many family members. Um and I've since now moved to Tennessee, I needed to go somewhere quiet. I wanted to heal my fractured soul and I'm I'm in the middle of a beautiful farming rural area in middle Tennessee and so they probably call me a sellout back in new york for leaving, but it's not the same city and it's sad um you know, I'll refrain from the politics and the uh finger point, but it's a mess compared to what it was and um you know, I did broadway theater security for many years and I started to see it slide like, like with stuff that was happening like, you know, public urination and defecation and just like, you know, tourists don't want to see that, right? And and um I, I had an unfortunate incident um two years ago, I was jumped by four teenagers coming off the subway and they were pissed off because I was wearing american flag hat. And I uh, I don't know, I'm not really sure why, but it left me. I got out of it. Um, okay, but I was taken back. They were literally videoing it and the kid was just throwing shadow punches at my face, wanting to beat me up. And I finally looked at many eyes and I was like, oh boy, a little too old for this Bodies a little broken down for chemo. And I finally just said, all right, all right, I just had enough. I wanted to go home, just worked a 17 hour shift as a stagehand and I was so taken back. I was so insulted. I'm saying, you know, I spent my life protecting this city and now I'm getting attacked like for nothing. And I just, I gave up and I maybe I should have given it a little more time. But it's um, I don't know, it's turned into an angry place. It's turned into, I think there's a lot of people that aren't getting the resources they need in a sense, there's a lot of mental illness, there's a lot of homelessness, There's a lot of violent people just roaming around the streets and it's not good. It's not safe and tourists are not, I'm gonna come back. Even just leading up to the Covid, I had some tourists amy, I won't be back and now I can only imagine that it's just gotten exponentially worse. But I hope there's a chance it will swing back because it is, it's the gateway to the world. I mean my grandfather came, you know from Denmark, he landed in Ellis Island in the 20s, You know American success story, $25 in his pocket, didn't speak the language, had a sponsor family in Bay Ridge Brooklyn and he made it, you know, he ended up dying on in a bakery at one point and then an apartment building and he did pretty well for himself for for an immigrant. He was poor. And my mom, my Irish mother landed in the same neighborhood. Bay Ridge Brooklyn. uh 16 years old worked as a cashier 50 60 hours a week in the supermarket and finished school at night married my father the fireman. And you know lived the american dream and it was all, it was all from new york. And my my father's mom was from irish immigrants and they all landed in Ellis Island. Well my mom didn't because it was closed at that point, but it's it's there's people breaking down the doors to come to this country right there. There's no one breaking down the doors to leave and this is, this is a problem I have with people that are grateful for being here and and this again is not political, just straight down the ball, straight down the middle fastball if you don't like it here, I'll show you the door, I'll get you the plane ticket. I mean, would you want to live back in Russia compared to here? Would you, you might because of family ties, but I mean if you had no ties to Russia or would you want to go to china right now and possibly end up in a labor camp or right there's people busting down the doors to get to this place. It's not perfect, it's got its flaws, it's got its blemishes, you know, um but it's a damn great place, it's the best country in the world. </s> |
<s>[INST] there, can we just like linger on that? So is part of it like the ambiguity in the [/INST] language </s><s>[INST] if it was like very strict, if you narrow the set of possible sentences you could do with that simplify the game significantly. [/INST] The real difficulty is the breadth of things that you can talk about. Um you can have natural language and other games like settlers of Catan for example, like you could have a natural language, settlers of Catan ai but the things that you're going to talk about are basically like, am I trading you to sheep for wood or three sheep for wood? Um whereas in a game like diplomacy, the breadth of conversations that you're going to have our like, you know, am I going to support you? Are you going to support me in return, which units are, are gonna do what um what did this other person promise you? Uh they're lying because they told this other person that they're going to do this instead. Um, if you help me out this turn then in the future I'll do these things that will help you out. Um the depth and breadth of these conversations is really complicated and it's all being done in natural language. Um now you could approach it and we actually consider doing this like you, you know, having a simplified language to make this complexity smaller. But ultimately we thought the most impactful way of doing this research would be to address the natural language component. Head on and just try to go for the full game up front. </s><s>[INST] Just looking at sample games and what the conversations look like greetings. England. This should prove to be a fun game. Since all the private press is going to be made public at the end at the least. It will be interesting to see if the press changes because of that. Anyway. Good. Okay, so there's like uh [/INST] yeah, that's just kind of like the generic greetings at the beginning of the game. I think that the meat comes a little bit later when you're starting to talk about like specific strategy and stuff. I </s><s>[INST] agree there are a lot of advantages to the two of us keeping in touch and our nation's make strong natural allies in the middle game. So that kind of stuff. Making friends, making enemies. [/INST] Yeah, like if you look at the next line, So the person saying like I've heard bits about the Lepanto and an octopus opening and basically telling Austria like, hey, just a heads up. You know, I've heard these whispers about like what might be going on behind your back. </s><s>[INST] Yeah. So there's all kinds of complexities in that in the in the language of that, right? Like to interpret what the what the heck that means. It's hard for us humans, but it's even harder because you have to understand like at every level the semantics of that. [/INST] Right? I mean there's the there's the complexity and understanding when somebody is saying this to me, what does that mean? And then there's also the complexity of like should I be telling this person this? Like I've overheard these these whispers, should I be telling this person that like, hey you might be getting attacked by by this other power? </s><s>[INST] Okay, so what how we're supposed to think about. Okay, so that's the natural language. How do you even begin trying to solve this game? It seems like it seems like the touring test on steroids. [/INST] Yeah. And I mean there's there's the natural language aspect and then even besides the natural language aspect, you also have the the cooperative elements of the game and I think this is actually um something that I find really interesting if you look at all the previous game ai breakthroughs, they've all happened in these purely adversarial games where you don't actually need to understand how humans play the game. It's all just A. I. Versus Ai right? Like you look at uh checkers chess go poker Starcraft Dota two like in some of those cases they leveraged human data but they never needed to they were always just trying to have a scalable algorithm that then they could throw a lot of computational resources at a lot of memory at and then eventually it would converge to an approximation of a nash equilibrium. This perfect strategy that in the two player zero sum game guarantees that they're going to be able to not lose to any opponents. So </s><s>[INST] you can't leverage self play to solve this game. [/INST] You you can leverage self play but it's no longer sufficient to beat humans. </s><s>[INST] So how do you integrate the human into the loop of this? [/INST] So what you have to do is incorporate human data. Um And to kind of give you some intuition for why this is the case. Like imagine you're playing a negotiation game like like diplomacy. Um But your training completely from scratch without any human data that the Ai is not going to suddenly like figure out how to communicate in english it's going to figure out some weird robot language that only it will understand. And then when you stick that in a game with six other humans, they're gonna think this person's talking gibberish and they're just gonna ally with each other and team up against the bot. Or not even team up against the wall but just not work with the bot. And so in order to be able to play this game with humans, it has to understand the human way of playing the game, not this machine way of playing the game. </s><s>[INST] Yeah. Yeah. That's fascinating. So right. That's a that's a nuance thing to understand because the [/INST] a </s> |
<s>[INST] If you own a business, try them out, schedule your free product tour at net suite dot com slash lex. That's N E T S U [/INST] I T E dot </s><s>[INST] com slash lex. This show is sponsored by Graham Early, a writing assistant tool, the check, spelling, grammar, sentence structure and readability grandma, lee premium the version you pay for offers a bunch of extra features. My favorite is the clarity check which helps detect rambling, overcomplicated chaos that many of us can descend into like this very thing that I wrote for myself. Most of these reeds, I go off the top of my head but some of them are right down. The parts I write down are even worse than the parts that go off the top of my head. I wish I had something like real time Graham early for spoken word. But in the medium of the written word, I truly value simplicity. I find simplicity to be just beautiful and so Graham early is a kind of nudge towards simplicity and clarity with the tools that their premium service provides. I recommended highly even if you don't agree with the suggestion makes Ultimately I think the debate with a suggested change will create a better written piece. Anyway, Graham Early is available on basically any platform in major sites and apps like gmail and twitter and so on. Do more than just spell check, say what you really mean with grandma lee premium get 20% off Graham early premium by signing up at Graham early dot com slash lux. That's 20% off at grandma lee dot com slash lex. This show is also sponsored by Express VPN. They put a layer of protection between you and powerful technology companies that control much of what we do online. The suggested talking points that Express VPN keeps sending me really make these like big tech companies into the enemy. I think we should definitely be skeptical, especially skeptical of the surveillance state, but I think these companies bring a lot of good too. But yes, it is good to have a layer of protection in terms of your data that said, I do think there's a lot of money to be made by companies to actually be transparent and actually give you control over your data. I think it's a win win and I have no idea why facebook is doing what it's doing, I have no idea why twitter is doing what he's doing. I think it was just the momentum of the past and hopefully we're going to see a pivot towards companies giving individual users more control over their data anyway, go to express VPN dot com slash flex pod to get an extra three months free. That's express VPN dot com slash like spot. This is the lex Friedman podcast and here is my conversation with brian johnson. [/INST] You ready lacks? Yes, I'm ready. I just want to come in and put the interfaces on our heads and then I will proceed to tell you a few jokes. </s><s>[INST] So we uh, we have two incredible pieces of technology and A machine running bond to 2004 in front of us. What are we doing? Alright. Are these going on our [/INST] heads? They're going on our heads. Yeah and they will place it on our heads for proper alignment. </s><s>[INST] Does this support giant heads because I kind of have a giant head is [/INST] as like an eagle or you staying physically both. Can we drop it on? Really? </s><s>[INST] It's a nice massage. Okay, how does it feel if you if it's okay to move around it feels Oh yeah, this feels awesome. [/INST] Thank you. That feels good. </s><s>[INST] So this is big head friendly [/INST] suits you well lex </s><s>[INST] thank you. I feel like I need to uh I feel like when I wear this and you just sound like Sam Harris, calm collected. Eloquent. I feel smarter actually. I don't think I've ever felt quite as much like I'm part of the future. Is now [/INST] have you ever worn a brain interface </s><s>[INST] or had your brain image? Oh, never had my brain imaged. The only way of analyzing my brain is by talking to myself and thinking no direct data. [/INST] Yeah, yeah, that is that is definitely a brain interface </s><s>[INST] that [/INST] has a lot of blind spots, </s><s>[INST] some blind spots. Yeah, psychotherapy, [/INST] that's right. All right. Are we recording? Forget. All right, select the objective of this. I'm going to tell you some jokes and your objective is to not smile, which has a Russian. You should have an edge. </s><s>[INST] Make the mother. I'm proud. I got you. Okay, let's hear the jokes [/INST] lex. And this is from the Colonel crew. We've been working on a device that can read your mind and we would love to see your thoughts. </s><s>[INST] Is that the joke? [/INST] That's the opening. Okay. If I'm if I'm seeing the muscle activation correctly on your, on your lips you're not going to do well on this. Let's see. Alright, here, here comes the first screwed. Here comes the first one </s><s>[INST] is going to break the device. Is it resilient to uh to laughter [/INST] lex what goes through a potatoes brain? </s><s>[INST] I already failed. That's the hilarious opener. Okay, what [/INST] tater thoughts. What kind of fish performed brain surgery? I don't know, a neurosurgeon. </s><s>[INST] Mhm. And so we're getting data of everything that's [/INST] happening in my brain right now. Lifetime. Yeah. We're getting activation patterns of your entire cortex. </s><s>[INST] I want to try to do better. I'll let it out all the parts where I left in Photoshop. You a serious [/INST] face over me, you can recover. Yeah. All right. Lex What do scholars eat when they're hungry? </s><s>[INST] I don't know what [/INST] academia nuts. </s><s>[INST] That was pretty good wine. [/INST] So what we'll do is so you're wearing Colonel Flow, which is an interface built using technology called spectroscopy. So it's similar to what we wear wearables on the wrist using light. So using light are as you know, and we're using that to image. It's a functional imaging of brain activity. And so as your neurons fire electrically and chemically. It creates blood oxygenation levels were measuring that. And so you'll see in the reconstructions we do for you. You'll see your activation patterns in your brain as throughout this entire time we were wearing it. So in the reaction to the jokes and as we were sitting here talking. So it's a we're moving towards a real time feed of your cortical brain activity. </s><s>[INST] So there's a bunch of things that are in contact with my skull right now. How many of them are there? And so how many of them are? What are they what are the actual sensors? [/INST] There's 52 modules and each module has one laser and six sensors. And they're the sensors fire uh about 100 PICO seconds and then the photons scatter and absorb in your brain. And if you go in if you come back out a bunch go in and if you come back out and we since those photons and then we do the reconstruction for the activity overall. There's about 1000 plus channels that are sampling your activity. </s><s>[INST] How difficult is it to make it as comfortable as it is because it's surprisingly comfortable. I would not think it would be comfortable. Something that's measuring brain activity. I would not think it would be comfortable. But it is. I agree. In fact I want to [/INST] take this home. Yeah. Yeah that's right. So people are accustomed to being in big systems like Fmri where there's 100 20 decibel sounds and you're in a and a claustrophobic encasement or E. G. Which is just painful or surgery. And so yes I agree that this is a convenient option to be able to just put on your head, it measures your brain activity in the contextual environment you choose. So if we want to have it during the podcast that we want to be at home in a business setting. So we its freedom to be where to record your brain activity in the setting that you choose. </s><s>[INST] Yeah, but sort of from an engineering perspective are these uh what is it? There's a bunch of different modular parts and they're kind of, there's like a rubber band thing where they mold to the shape of your head. [/INST] That's right. So we built this this version of the mechanical design to accommodate most adult heads, </s><s>[INST] but I have a giant head and if it's fine it feels fits well actually. So I don't think I have an average head. Okay, maybe I feel I feel much better about my head now, maybe I'm are more average than I thought. Okay, so what else is there interesting that you could say, well it's while it's on our heads, I can keep this on the whole time. This is kind of awesome. And it's amazing for me as a fan of avanti, I use a bunch of matt. You guys use that too, but it's amazing to have code running to the side measuring stuff and collecting data. I mean I just, I feel like much more important now that my data is being recorded, like somebody like you know when you have a good friend that listens to you that actually like listens like actually is listening to you, this is what I feel like I'm like a much better friend because it's like accurately listening to me do ponto. [/INST] What a cool perspective I hadn't thought about that of feeling understood, heard you heard deeply by the mechanical system that is recording your brain activity versus the human that you're engaging with. That your mind immediately goes to that there's this dimensionality and depth of understanding of this software system which you're intimately familiar with and now you're able to communicate with this system in ways that you couldn't before. </s><s>[INST] Yeah, I feel hard. I [/INST] mean I guess what's interesting about this is your intuitions are spot on. Most people have intuitions about brainer faces that they've grown up with this idea of people moving cursor on the screen or typing or changing the channel or skipping a song. It's primarily been anchored on control. And I think the more relevant understanding to bring interfaces and neural imaging is that it's a measurement system and once you have numbers for a given thing, a seemingly endless number of possibilities emerge around that of what to do with those numbers. </s><s>[INST] So before you tell me about the possibilities, this was an incredible experience, I can keep this on for another two hours but I'm being told that for a bunch of reasons just because we probably want to keep the data small and visualize it nicely for the final product, we want to cut this off and take this take this amazing helmet away from me. So brian thank you so much for this experience and let's uh let's continue without helmet lys. Alright, so that was an incredible experience. Uh Can you maybe speak to what kind of opportunities that opens up that stream of data? That rich stream of data from the brain [/INST] 1st? I'm curious what is your reaction? What what comes to mind when you put it on your head? What does it mean to you and what possibilities emerge and what significance might have. I'm curious where your orientation is at. </s><s>[INST] Well for me, I'm really excited by the possibility of various information about my body about my mind being converted into data. Such that data can be used to create products that make my life better. So that that to me is really exciting possibility. Even just like a Fitbit that measures I don't know some very basic measurements about your body is really cool but it's the bandwidth of information. The resolution of that information is very crude so it's not very interesting. The possibility of recording. I was just building a data set coming in a clean way and a high bandwidth way from my brain opens up all kinds of you know at the very I was kind of joking where we're talking but it's not really is like I feel heard in a sense that it feels like the full richness of the information coming from my mind is actually being recorded by the machine. I mean there's a I can't I can't quite put it into words, but there is genuinely for me there's not some kind of joke about me being a robot. It's just genuinely feels like I'm being heard in a way that that's going to improve my life as long as the thing that's on the other end can do something useful with that data. But even the recording itself is like once you record, it's like taking a picture that moment is forever saved in time. Now picture cannot allow you to step back into that world. But perhaps recording your brain is a much higher resolution thing, Much more personal recording of the information that a picture that would allow you to step back into that uh where you were in that particular moment in history and then map out a certain trajectory to tell you certain things about uh about yourself. That could open up all kinds of applications. Of course there's health that I consider. But honestly to me, the exciting thing is just being heard. My state of mind, the level of focus, all those kinds of things being heard. [/INST] What I heard you say is you have an entirety of lived experience, some of which you can communicate in words and in body language, some of which you feel internally, which cannot be captured in those communication modalities and that this measurement system Captures both. The things you can try to articulate in words maybe in a lower dimensional space. Using one word for example, to communicate focus when it really may be represented in a 20 dimensional space of this particular kind of focus and that this information is being captured. So it's a closer representation to the entirety of your experience captured in a dynamic fashion. That is not just a static image of your conscious experience. </s><s>[INST] Yeah, that's that's that's the promise. That's the hope. That was the feeling and it felt like the future. So it's a pretty cool experience and from the sort of mechanical perspective it was cool to have an actual device that feels pretty good. That doesn't uh doesn't require me to go into the lab. And also the other thing I was I was feeling there's a guy named danger Huberman is a friend of mine, amazing podcast. People should uh should listen to a human lab podcast. We're working on a paper together about eye movement and so on and we're kind of, he's a neuroscientist and I'm a data person when she learning person or we're both excited by how much the that how much the data measurements of the human mind and the brain and all the different metrics that come from that could be used to understand human beings and in a rigorous scientific way. So the other thing I was thinking about is how this could be turned into a tool for science sort of not just personal science not just like Fitbit style. Like how am I doing my personal metrics of health but doing larger scale studies of human behavior and so on. So like data not at the scale of an individual but day to the scale of many individuals with a large number of individuals. So so it's personal being heard was exciting. And also just for science is exciting. It's very easy like like that there's a very powerful thing to it being so easy to just put on that. You can scale much easier [/INST] if you think about that second thing you said about the science of the brain most we've done a pretty good job like we the human race has done a pretty good job figuring out how to quantify the things around us from distant stars to calories and steps and our genome so we can measure and quantify pretty much everything in the known universe except for our minds and we can do these one offs if we're going to get enough MRI scan or uh huh do something with the low rez E. G system but we haven't done this at population scale. And so if you think about human thought or human cognition is probably the single law largest raw input material into society at any given moment. It's our conversations with our with ourselves and with other people and we have this this raw input that we can't I haven't been able to measure yet and if you when I think about it through that frame it's remarkable. It's almost like we live in this wild Wild West oven quantified communications within ourselves and between each other when everything else has been grounded me. For example, I know if I buy an appliance at the at the store or on a website I don't need to look at the measurements on the appliance and make sure it can fit through my door. That's an engineered system of appliance, manufacturing and construction. Everyone's agreed upon engineering standards and we don't have engineering standards around cognition is not has not entered as a formal engineering discipline that enables us to scaffold in society with everything else we're doing including consuming news, our relationships, politics, economics, education all the above. And so to me that the most significant contribution that Colonel technology has to offer would be the formal scott the introduction of the formal engineering of cognition as it relates to everything else in society. </s><s>[INST] I love that idea that you kind of think that there is just this ocean of data that's coming from people's brains as being in a crude way of reduced down to like tweets and texts and so on. It's a very hard core, many scale compression of actual the raw data but maybe you can comment because you usually work cognition? I think the first step is to get the brain data but is there a leap to be taking to sort of interpreting that data in terms of cognition. So is your is your idea is basically you need to start collecting data at scale from the brain and then we start to really be able to take little steps along the path to actually measuring some deep sense of cognition because it's, you know, as I'm sure, you know, we don't, we understand a few things but we don't understand most of what makes up cognition. [/INST] This has been one of the most significant challenges of building Colonel and Colonel wouldn't exist if I wasn't able to fund it initially about myself because when I engage in conversations with investors, the immediate thought is what is the killer app. And of course I understand that heuristic, that's what they're looking at is they're looking to de risk is the product solve? Is there a customer base? Are people willing to pay for it? How does it compare to competing options? And in the case with Brainer faces, when I started the company, there was no known path to even build a technology that could potentially become mainstream. And then once we figure out the technology, We could even, we could commence having conversations with investors and it became what is the killer app. And so what has been uh, so I I funded the 1st $53 million 228 investors. One said yes, it was remarkable and it was mostly around this concept around what is a killer app. And so internally the way we think about it is we think of the </s><s>[INST] the go to market strategy much more [/INST] like the drake equation where if we can build technology that has the characteristics of it has the data quality is high enough. It meets some certain threshold cost, accessibility, comfort, it can be worn in contextual environments. If it meets the criteria of being a mass market device, then the responsibility that we have is to figure out how to create the algorithm that enables the human to enable humans to find value with it. So it's so the analogy is like brainer faces are like early 90s of the Internet is you you want to populate an ecosystem with a certain number of devices. You want a certain number of people who play around with them who do experiments of certain data collection parameters. You want to encourage certain mistakes from experts and non experts. These are all critical elements that ignite. Discovery. And so you we believe we've accomplished the first objective of building technology that reaches those thresholds. And now it's the drake equation component of how do we try to generate 20 years of value discovery in a two or three year time period. How do we compress that? </s><s>[INST] So just to clarify? So when you mean the drake equation which for people who don't know, I don't know why you, if you listen to this, I bring up aliens every single conversation, so I don't know how you wouldn't know what the drake equation is. But you mean like the killer app, it would be one alien civilization that equation. So meaning like this is in search of an application that impact transformative, by the way it should be. We need to come up with a better term than killer app as a it's also [/INST] violent, right? </s><s>[INST] You can go like viral app. That's horrible to write some very uh inspiring lee impactful application. How about that? Okay, so let's stick with killer app. That's fine. Nobody's I concur [/INST] with you. I dislike the chosen words in capturing the concept. </s><s>[INST] You know, it's one of those sticky things that is as effective to use in the tech world. But when you now become a communicator outside of the tech world, especially when you're talking about software and hardware and artificial intelligence applications, it sounds for, [/INST] you know, it's interesting. I actually regret now having called attention cause I regret having used that word in this conversation because it's something I would not normally do. I used it in order to create a bridge of shared understanding of how others would, what terminology others would use. </s><s>[INST] Yeah, but yeah, I concur let's go with impactful application [/INST] or the value creation? </s><s>[INST] Value creation something people love using? There we go, that's it love app. Okay, so what do you have any idea? So you're basically creating a framework where there's a the possibility of a discovery of uh an application that people love using is they have ideas. [/INST] We began to play a fun game internally where when we have these discussions we begin sir circling around this concept of does anybody have an idea? Does anyone have intuitions? And if we see the conversation starting to veer in that direction we flag it and say human intuition alert, stop it. And so we really want to focus on the algorithm of there's a natural process of human discovery that that when you populate a system with devices and you give people the opportunity to play around with it and expected and unexpected ways we are thinking that is a much better system of discovery than us, exercising tuitions And it's interesting we're also seeing a funeral scientists who have been, have been talking to us while speaking just one young associate professor and I approached a conversation and said hey we have these five data streams that were pulling off when you hear that, what weighted value do you add each data source? Like which one do you think is going to be valuable for your objectives and which ones not. And he said I don't care, just give me the data. All I care about is my machine learning model but importantly he did not have a theory of mind, he did not come to the table and say I think the brain operates, you know, in this way and these reasons we have these functions, he didn't care, he just wanted the data and we're seeing that more and more that certain people are devaluing human intuitions for good reasons as we've seen in machine learning over over the past couple years and we're doing the same in our value creation market </s><s>[INST] charging, so more collect more data, clean data, make the products such that the collection of data is easy and and and fun and then the rest will just spring to life through humans. Playing around with [/INST] the objective is to create the most valuable data collection system of the brain ever and with that then applying all the best tools of machine learning and other techniques to extract out, you know, to try to find insight. But yes, our objective is really to systematize the discovery process because we we can't put definite timeframes on discovery, the brain is complicated and science is not a business strategy and so we really need to figure out how to, this is the difficulty of bringing bringing you know technology like this to market, that's why most of time, it just link it languishes in academic academic for quite some time, but we hope that we will over cross over and make this mainstream in the coming years? </s><s>[INST] The thing was cool to wear but what are you chasing a good reason for millions of people to put this on their head and keep on their head regularly? Is there like who's going to discover that reason? Is it going to be people just kind of organically or is there going to be uh angry birds style application? That's just too exciting to not use [/INST] if I think through the things that have changed my life most significantly over the past few years when I started wearing a wearable in my wrist, that would give me data about my heart rate, heart rate, variability, respiration rate, ah metabolic approximations etcetera. For the first time in my life I had access to information sleep patterns that were highly impactful. They told me for example, if I eat close to bedtime, I'm not going to get deep sleep and not getting deep sleep means you have all these following consequences in life. And so it opened up this window of understanding of myself that I cannot self introspect and deduce these things. This is information that was available to be acquired. But it just wasn't, I would have to get expensive sleep study that it's an end like one night and that's not good enough to run all my trials. And so if you look just at the information that one can acquire on their wrist and now you're planning to the entire cortex in the brain and you say, what kind of information could we acquire? It opens up a whole new universe of possibilities. For example, we did this internal study at Colonel where I wore a prototype device and we were measuring the cognitive effects of sleep. So I had a device measuring my sleep. I performed with 13 of my coworkers. We perform four cognitive tasks over 13 sessions and we focused on reaction time, impulse control, uh short term memory and then arresting state task. And we with mine, we found for example, that my impulse control, it was independently correlated with my sleep outside of behavioral measures of my ability to play the game. The point of the study was I had the brain study eidetic. Colonel confirmed my life experience that if I my deep sleep determined whether or not I would be able to resist temptation the following day. And my brain didn't show that as one example. And so if you start thinking, if you actually have data on yourself on your entire cortex, you can control the settings. I think there's probably an a large number of things that we could discover about ourselves. Very, very small and very, very big. Just for example, like when you read news, what's going on? </s><s>[INST] Like when you use social media, when you use news, like uh all the ways we allocate attention. That's right with the computer. I mean that seems like a compelling place to where you would want to put on uh Colonel, whether what is it called Colonel flux Colonel, Like what [/INST] flow? We have two technologies, you're flow flow. </s><s>[INST] Okay, so when you when you put on the kernel flow, it is seems like to be um compelling time and place to do. It is when you're behind the desk behind a computer, you could probably work for prolonged periods of time as you're as you're taking in content and there could a lot of, because some of our so much of our lives happens in the digital world. Now, that kind of coupling the information about the human mind with the consumption and the behaviors in the digital world might give us a lot of information about the effects of the way we behave and navigate the digital world to the actual physical meet space, uh effects on our body. It's interesting to think in terms of both. Like for work, I'm a big fan of uh cal Newport has ideas of deep work that I spent uh with few exceptions, I try to spend the first two hours of every day. Usually if I'm like at home and have nothing on my schedule is going to be up to eight hours of deep work of focus, zero distraction. And for me to analyze the I mean I'm very aware of the uh the waning of that. The ups and downs of that and it's almost like you're surfing the ups and downs of that as you're doing programming as you're doing. Thinking about particular problems, you're trying to visualize things in your mind. You're trying to stitch them together. You're trying to uh when there's a dead end about an idea, you have to kind of calmly like walk back and start again all those kinds of processes. It would be interesting to get data on my mind is actually doing. And also recently started doing um I just talked to Sam Harris a few days ago and been building up to that. I started using started meditating using his app. Waking up very much recommend it and be interesting to get data on that because it's you're very it's like you're removing all the noise from your head and you very much it's an active process of active noise removal, active noise canceling headphones. And it would be interesting to see what is going on in the mind before the meditation during it and after all those kinds of things [/INST] and all of your examples. It's interesting that everyone who has designed an experience for you. So whether it be the meditation app or the deep work or all the things you mentioned, they constructed this product with a certain number of knowns. Yeah. Now what if we expanded the number of knowns by 10 X or 20 x 30 X. They would reconstruct their product, we'll incorporate those known. So it be and so this is the dimensionality that I think is the promising aspect is people will be able to use this quantification. Use this information to build more effective products. And this is I'm not talking about better products to advertise to you or manipulate you. I'm talking about our focus is helping people individuals have this contextual awareness and quantification and then to engage with others who are seeking to improve people's lives that the objective is, its betterment across ourselves, individually and also with each other. </s><s>[INST] So it's a nice data stream to have. If you're building an app, like if you're building a podcast listening app, it would be nice to know data about the listener so that like if you're bored or you fell asleep, maybe pause the podcast. It's like really dumb, just very simple applications that could just improve the quality of the experience of using the app. [/INST] I'm imagining if you have you have your neural um this is lex and you there's a statistical representation of you and you engage with the app and it says lex your best to engage with this meditation exercise in the following settings at this time of day after eating this kind of food or not eating fasting with this level of blood glucose and this kind of night sleep. But all these data combined to give you this contextually relevant experience, just like we do with our sleep, you've optimized your entire life based upon what information you can acquire and know about yourself. And so the question is, how much do we really know of the things going around us and I would venture to guess in my own my life life experience. I capture my self awareness, captures an extremely small percent of the things that actually influenced my conscious and unconscious experience. </s><s>[INST] Well in some sense, the data would help encourage you to be more self aware, not just because you trust everything the data saying, but is it will give you a prod to start investigating. Like I would love to get a like a rating like a ranking of all the things I do and what are the things It's probably important to do without the data, but the data will certainly help is like rank all the things you do in life and which ones make you feel shitty, which must make you feel good. Like you're talking about evening brian like this. It's a good example of somebody like I do pig out at night as well and uh never [/INST] make like you're in a safe </s><s>[INST] space. Is this is the same. It's never no, I I definitely have much less self control at night. It's interesting and the same. You know, people might criticize this, but I know my own body, I know when I eat carnivore, just eat meat, I feel much better uh than if I eat more more carbs, the more carbs I eat the worse I feel. I don't know why that is, I don't, there is science supporting, but I'm not leading on science. I'm leaning on personal experience that's really important. I don't need to read. I'm not gonna go in the whole rant about nutrition science. But many of those studies are very flawed. They're doing their best. But nutrition science is a very difficult field of the study because humans are so different and the mind has so much impact on the way your body behaves and it's so difficult from a scientific perspective to conduct really strong studies that you have to be almost like a scientist of an inch of one have to do these studies and yourself. That's the best way to understand what works for you or not. And I don't understand why because it sounds unhealthy but eating only meat always makes me feel good. Just mean that's it. And uh I don't have any allergies and you know that kind of stuff. I'm not full like Jordan Peterson where like if he like deviates a little bit that he goes off like deviate a little bit from the carnivore diet. He goes off like the cliff. No, I can I can have like chuck, I can I can go off the diet. I feel fine. It's a it's a gradual uh it's a gradual worsening of how I feel. But what he only meet, I feel great and it'll be nice to be reminded of that. There's a very simple fact that I feel good when I eat carnivore and I think that repeats itself in all kinds of experiences, like I feel really good uh when I exercise not, I hate exercise okay. But in the rest of the day the the impact it has on my mind and the clarity of mind and the experiences and the happiness and all those kinds of things. I feel really good. And to be able to concretely expressed that through data would be nice. It would be a nice reminder. Almost like a statement like remember what feels good and what not. And there could be things like uh that I'm not many things like you're suggesting that I could not be aware of, there might be sitting right in front of me. That makes me feel really good and makes me feel not good. And the data would show that [/INST] I agree with you. I've actually Employed the same strategy. I fired my mind entirely from being responsible for constructing my diet. So I started doing a program where I now track over 200 biomarkers every 90 days and it captures of course the things you would expect that cholesterol, but also DNA methylation and all kinds of things about my body, all the processes that make up me. And then I let that data generate the shopping list. Uh huh. And so I never actually ask my mind what it wants. It's entirely what my body is reporting that it wants. And so I call this goal alignment within Brian and there's 200 plus actors that I'm currently asking their opinion of. And so I'm asking my liver, how are you doing? And it's expressing via the biomarkers. And so then I construct that diet and I only eat those foods until my next testing round. And that has changed my life more than I think anything else because in the demotion of my conscious mind that I gave primacy to my entire life, it led me astray because like you're saying the mind then goes out into the world and it navigates the dozens of different dietary regimens people put together in books and it all has there. I'll have their supporting science in certain contextual settings, but it's not the end of one. And like you're saying this dietary really is an end of one. These what people have published scientifically of course can be used for nice groundings, but it changes when you should end up one level. And so that's what gets me excited about brainer faces is if you if I could do the same thing for my brain where I can stop asking my conscious mind for its advice or for its decision making, which is flawed. And I'd rather just look at this data that and I've never had better health markers in my life than when I stopped actually asking myself to be in charge of it and </s><s>[INST] the idea of demotion of the conscious mind is uh it's such a sort of engineering way of phrasing like meditation with what that's what we're doing, right? Yeah, that's beautiful. That means really beautifully put. Uh by the way testing round what does that look like? What's that? Well you mentioned uh [/INST] yeah that the very the test I do so includes a complete blood panel, do a microbiome test, I do a food inflammation, a diet induced inflammation. So I look for saddle kind expressions. So foods that produce inflammatory reactions. I look at my neuro endocrine systems. I look at all my neurotransmitters. Uh I do yeah there's several micronutrient test to see how I'm looking at the various nutrients. </s><s>[INST] What about like self report of like how you feel, you know almost like uh you can't demote your you still exist within your conscious mind, right? So that that lived experience of is a lot of values. You measure [/INST] that, do a temporal sampling over some duration of time. So I'll think through how I feel over a week, over a month over three months. I don't do a temporal sampling of if I'm at the grocery store in front of a cereal box and be like you know what Captain crunch is probably the right thing for me today because I'm feeling like I need a little fun in my life. And so it's a temporal sampling. If the data sets large enough then I smooth out the function of my natural oscillations of how I feel about life where some days I maybe feel upset or depressed or down or whatever and I don't want those moments to then rule my decision making. That's why The demotion happens. And it says really if you're looking at health of a 90 day period of time, All my 200 voices speak up on that interval and they're all given voice to say this is how I'm doing and this is what I want. And so it really is an accounting system for everybody. So that's why I think that if you think about the future of being human, there's two things I think that are really going on. one is the design manufacturing and distribution of intelligence Is heading towards zero gonna cost curve over over a certain design over a certain time frame. But our ability to, you know, evolution produced us an intelligent, the form of intelligence. We are now designing our own intelligence systems And the design, manufacturing distribution of that intelligence over a certain time frame is going to go to a cost of zero </s><s>[INST] design manufacture, distribution of intelligent cost is going to zero again, just give me a second. That's brilliant. Okay, an evolution is doing the design manufacturing distribution of intelligence and now we are doing the design manufacturing distribution of intelligence and the cost of that is going to zero. That's a very uh nice way of looking at life on earth. [/INST] So if that that's going on. And then now in parallel to that, then you say, okay, what what then happens if when that cost curve is heading 20, our existence becomes a goal alignment problem ago alignment function. And so the same thing I'm doing where I'm doing go alignment within myself of these 200 biomarkers where I'm saying when when brian exists on a daily basis and this entity is deciding what to eat what to do and etcetera, it's not just my conscious mind which is opening its 200 biological processes and there's a whole bunch of more voices involved. So in that equation we're going to increasingly automate the things that we spend high energy on today. It's easier. And now we're going to then negotiate the terms and conditions of intelligent life. Now we say conscious existence because we're biased because that's what we have. But it will be the largest computational exercise in history because you're now doing go alignment with planet Earth, within yourself, with each other. Within all the intelligence agents were building boats and other voice assistants. You basically have to have a trillions and trillions of agents working on the negotiation of goal alignment. </s><s>[INST] Yeah, this this is in fact true. Uh What was the second thing [/INST] that was it? So the cost design, manufacturing distribution of intelligence going to zero, which then means what's really going on? What are we really doing? We're negotiating the terms and conditions of existence. </s><s>[INST] Do you worry about the survival of this process? Mhm. That life as we know what on earth comes to an end or at least intelligent life. That as the cost goes to zero. Uh Something happens where all of that intelligence is thrown in the trash by something like nuclear war or development of AGI systems that are very dumb. Not A G I guess, but a isIS, that's the paperclip thing, what unmasked is dumb but has unintended consequences to where destroys human civilization. Do you worry about those kinds of things? I [/INST] mean it's it's unsurprising that a new thing comes into the sphere of human consciousness. Humans identify the foreign object in this case artificial intelligence, our amygdala fires up and says scary foreign, we should be apprehensive about this. And so it makes sense from a biological perspective of humans. For the the knee jerk reaction is fear. What I don't think has been properly weighted with that is that we are the first generation of intelligent beings on this earth that has been able to look out over their expected lifetime and see there is a real possibility of evolving into entirely novel forms of consciousness. Yeah, so different that it would be totally unrecognizable to us today. We don't have words for it, we can't hint at it, we can't point at it, we can't you can't look in the sky and to see that thing that is shining? We're gonna go up there. You you cannot even create an aspirational statement about it. And instead we've had this knee jerk reaction of fear about everything that could go wrong. But in my estimation, this should be the defining aspiration of all intelligent life on earth that that we would aspire that basically every generation surveys the landscape of possibilities that afforded given the technological, cultural and other contextual situation that they're in. We're in this context. We haven't yet identified this and said, this is unbelievable. We should carefully think this thing through not just of mitigating the things will wipe us out like we have this potential. And so we just haven't given voice to it even though it's within the realm of possibilities. </s><s>[INST] So you're excited about the possibility of super intelligence systems and what the opportunities that bring. I mean, these parallels to this. You think about people before the internet as the internet was coming to life. I mean there's kind of a fog through what you can't see, what does the future look like predicting collective intelligence, which I don't think we're understanding that we're living through that now is that there is now with with in some sense stopped being individual intelligences and become much more like collective intelligences because ideas travel much much faster now and they can in a viral way, like sweep across the populations. And so it's almost I mean it almost feels like a thought is had by many people know thousands or millions of people as opposed to an individual person. And that's changed everything. But to me, I think we're realizing how much that actually changed people or societies, but like to predict that before the internet would have been very difficult. And in that same way we're sitting here with the fog before us thinking what is uh super intelligence systems, how is that going to change the world? What is uh, increasing the band with like, um, plugging our brains into this whole thing? How is that going to change the world? And it seems like, uh, it's a fog, you don't know? And it could be, it could, uh, whatever comes to be, could destroy the world that we could be the last generation. But it also could transform in in ways that creates a, an incredibly fulfilling life experience that's unlike anything we've ever experienced, it might involve dissolution of ego and consciousness and so on. You're no longer one individual, it might be more, you know, that might be a certain kind of death and ego, death. But the experience might be really exciting and enriching maybe we'll live in a virtually like, it's like, it's funny to think about a bunch of sort of hypothetical questions of, would it be more fulfilling to live in a virtual world? Like if you were able to plug your brain in a very dense way into a video game, which world would you want to live in in the video game or in the physical world. For most of us, we kind of touring with the idea of the video game, but we still want to live in the physical world, have friendships and relationships in the physical world, but we don't know that again, it's a fog and maybe maybe in 100 years we're all living inside a video game, Hopefully not Call of Duty, hopefully more like, like Sims five, which which version is it on for you individually though? Does it make you sad that your brain ends That you die one day very soon? That the whole thing that that that that data source just goes offline sooner than you would like. [/INST] That's a complicated question, I would have answered it differently In different times in my life, I, you know, had chronic depression for 10 years. And so in that 10 year time period I desperately wanted lights to be off. And the thing that made it even worse is I was in a religious, I was born into a religion. It was the only reality I ever understood. And it's difficult to articulate to people when you're born into that kind of reality. And it's the only reality you're exposed to. You are literally blinded to the existence of other realities because it's so much the in group out group thing. And so in that situation, it was not only that I desperately wanted lights out forever, it was that I couldn't have lights out forever. It was there was an afterlife and this afterlife. Had this system that would either penalize or or reward you for your behaviors. And so it's almost like this is indescribable hopelessness of not only being in hopeless despair of not wanting to exist, but they're also being forced to be to exist. And so there was the duration of my time of the creation of life and say, yes, I have no remorse for lights being out and actually wanted more than anything in the entire world. There are other times where I'm looking out at the future and I say, this is an opportunity for future evolving, human conscious experience that is beyond my ability, understand. And, and I jump out of bed and I raced to work and I can't think about anything else. But I I think the the reality for me is I don't know what it's like to be in your head, but in my head when I wake up in the morning, I don't say Good morning Brian, I'm so happy to see you. Like, I'm sure you're just going to be beautiful to me today. You're not going to make a huge long list of everything you should be anxious about. You're not gonna repeat that list to me 400 times. You're not going to have me relive all the regrets I've made in life. I'm sure you're not doing any of that. You're just going to just help me along all day long. I mean, it's a brutal environment in my brain and we've just become normalized to this environment that we just accept that this is what it means to be human. But if we look at it, if we try to muster as much soberness as we can about the realities of being human, it's brutal if it is for me. And so am I sad that the brain may be off one day? You know, it depends on the contextual setting like how am I, what moment are you asking me that? And that's it's my mind is so fickle and this is why again, I don't trust my conscious mind. I have been given realities. I was given a religious reality that was a video game. And then I figured out it was not a real reality. And then I lived in a depressive reality which delivered this terrible hopelessness. That wasn't a real reality that I discovered Behavoural psychology. And I figured out how biased 188 chronicle biases and how my brain is distorting reality at the time. I have gone from one reality to another. I don't trust reality. I don't trust realities are given to me. And so to make try to make a decision on what I value or not value that future state. I don't trust my response. </s><s>[INST] So not fully, not fully listening to the conscious mind at any one moment as the ultimate truth, but allowing you to go up and down as it does. It's kind of being observing it. [/INST] Yes, I assume that whatever my conscious mind delivers up to my awareness is wrong on upon landing, and I just need to figure out where it's wrong, how it's wrong, how wrong it is, and then try to correct for it as best I can. But I assume that on impact, it's mistaken in some critical ways. </s><s>[INST] Is there something you can say by way of advice when the mind is depressive, when the conscious mind serves up something that uh you know, the dark thoughts, how you deal with that by calling your own life, you've overcome that, and others who are experiencing that you can overcome it. [/INST] Two things one that those depressive states are biochemical states, it's not you. And the suggestions that these things that the state delivers to you about suggestion of the hopelessness of lives or or the meaninglessness of it, or that you should hit the eject button. That's a false reality. Yeah. And that it's when I I completely understand the rational decision to commit suicide there, it is not lost on me at all, that that is and that is an international situation. But the key is when you're in that situation of those thoughts are landing to be able to say, thank you, you're not real. I know you're not real. And so I'm in a situation where, for whatever reason, I'm having this this uh neurochemical state, but that state can be altered. And so it again, it goes back to the realities of the difficulties of being human. And like when I was trying to solve my depression, I tried literally, if you name it, I tried it systematically and nothing would fix it. And so this is what gives me hope with brainer faces. For example. Like could I have numbers on my brain, Can I see what's going on? Because I go to the doctor, it's like how do you feel? I don't know, terrible. Like on a scale of 1 to 10 to have that you want to commit suicide 10? Like, </s><s>[INST] okay, at [/INST] this moment here, here's his bottle how much I take. I don't know, like just </s><s>[INST] yeah, it's very, very crude. And this data opens up the the yeah, it opens up the possibility of really helping in those dark moments to first understand the ways of the ups and downs the most document was on the complete flip side of that. Yeah, I am very conscious in my own brain and deeply, deeply grateful that what they're it's it's almost like a chemistry thing, a biochemistry thing that I go many times throughout the day. I'll look at like this cup and I'll be overcome with joy how amazing it is to be alive. Like I actually think I'm my biochemistry is such that it's not as common. Like I've talked to people and I don't think that's that common. Like it's a it's not a rational thing at all. It's like I feel like I'm on drugs and I'll just be like whoa a lot of people talk about like the meditative experience will allow you to sort of, you know, look at some basic things like the movement of your hand as deeply joyful because it's like that's life. But I get that from just looking at a cup, like I'm waiting for the coffee to brew and I'll just be like fuck life is awesome and I'll sometimes tweet that, but then I'll regret it later. Like goddammit, you're so ridiculous. But yeah, so but that is purely chemistry, like there's no rational, it doesn't fit with the rest of my life. I have all this ship, I'm always late to stuff, I'm always like there's all stuff, you know, I'm super self critical, like really self critical about everything I do almost. To the point I almost hate everything I do. But there's this engine of joy for life outside of all that and that has to be chemistry and the flip side of that is what depression probably is is the opposite of that feeling of like because I I bet you that feeling of the cup being amazing, it would save anybody in a state of depression like that that would be like fresh, you're in a desert and it's a, it's a drink of water Ah shit man, the brain is a, it would be nice to understand where that's coming from, to be able to, to understand how you hit those lows and those highs that have nothing to do with the actual reality. It has to do with some very specific aspects of how you maybe see the world. Maybe it could be just like basic habits you engage in and then how to walk along the line to find those experiences of joy. [/INST] And this goes back to the discussion we're having of human cognition is in volume the largest input of raw material into society. Yeah, and it's not quantified, we have no bearings on it. And so we just, you wonder we both articulated some of the challenges we have in our own mind and it's likely that others would say I have something similar and you wonder when you look at society, what how does that contribute to all the other compounded problems that we're experiencing? How does that blind us to the opportunities we could be looking at. And so it really it has this potential distortion effect on reality that just makes everything worse. And I hope if we can put some, if we can assign some numbers to these things just to get our bearings. So we're aware of what's going on, if we could find greater stabilization in how we conduct our lives and how we build society. It might be the thing that enables us to scaffold because we've really again we've done a human have done a fantastic job systematically scaffolding technology and science institutions. It's human these are our own selves which we have not been able to scaffold. It's it's we are the we are the one part of this intelligence infrastructure that remains unchanged. </s><s>[INST] Is there something you can say about coupling this brain data with not just the basic human experience but say an experience you mentioned sleep but the wildest experience which is psychedelics. Is there uh And there's been quite a few studies now that are being um approved and run which is exciting from a scientific perspective on psychedelics. Do you think? What do you think happens to the brain and psychedelics and how can data about this help us understand it? And uh when you're on D. M. T. D. C. L. S. And can we get can we convert into uh into data? Um [/INST] Can you add aliens in there? </s><s>[INST] Yeah aliens definitely. Do you actually meet aliens? And elves are elves aliens? I'm asking for uh for a few Austin friends yet that they are convinced that they've actually met the elves? [/INST] What it was like are they friendly? </s><s>[INST] Are they are they [/INST] like the smurfs are like they're like they're industrious and they have different skill sets and </s><s>[INST] the. Yeah I think they're very uh they're very critical as friends. It's the [/INST] trolls troll. </s><s>[INST] No but they care about you. So there's a bunch of different version of trolls. There's a loving trolls that are harsh on you but they want you to be better. And there's trolls that just enjoy the your destruction. And I think they're the ones that care for you. Like I I think their criticism from I. C. I'm talking I haven't met him directly. I'm it's like a friend of a friend [/INST] and I'm a telephone. </s><s>[INST] Yeah a bit of and and the whole point is that on psychedelics and certainly I D. M. T. Were this is where the brain data versus war data fails which is you know words can't convey the experience most people that you can be poetic and so on but it really does not convey the experience of what it actually means to meet the two meet the house. [/INST] I mean to me what baselines this conversation is imagine if you if we were interested in the health of your heart. And we started and said okay lex self introspect. Tell me how's the health of your heart and you sit there and you close your eyes and you think it feels all right like the same things feel okay. And then you went to the cardiologist and the cardiologist complex. You know tell me how you feel. Actually. What I really like you to do is do an E. K. G. And a blood panel and look at arterial plaques and let's look at my cholesterol and there's like 5-10 studies you would do. They give you this report and say here's the quantified health of your heart. Now with this data I'm going to prescribe the following regime of exercise and maybe I'll put you on a statin like uh etcetera. But the protocol is based upon this data. You would think the cardiologist is out of their mind if they just gave you a bottle of statins based upon you're like well I think something's kind of wrong and they're just just kind of experiment and see what happens. That's what we do with our mental health today. So you're it's it's kind of absurd. And so if you look at psychedelics uh to have begin to be able to measure the brain and get a baseline state and then to measure during a psychedelic experience and post the psychedelic experience and then do it longitudinal e you now have a quantification of what's going on. And so you could then pose questions what molecule is appropriate at what dosage is at what frequency in what contextual environment. What happens when I have this diet with this molecule of this experience, all the experimentation you do when you have good sleep data or HIV. And so that's what I think happens. What we could potentially do with psychedelics is we could add this level of sophistication that is not in the industry currently and it may improve the outcomes. People experience it may improve the safety and efficacy. And so that's why I hope we are able to achieve. And it would transform mental health because we would finally have numbers to work with the based on ourselves. And then if you think about it, we when we talk about things related to the mind, we talk about the modality. We use words like meditation or psychedelics or or something else because we can't talk about a marker in the brain. We can't use a word to say. We can talk about cholesterol, we don't talk about plaque in the arteries, we don't talk about HIV and so if we have numbers, then the solutions get mapped to numbers instead of the modalities being the thing we talked about meditation just does good things in a crude fashion. </s><s>[INST] So in your blog post, zero principle thinking good title, you partner. How do people come up with a truly original ideas? What what's your thoughts on this as a human and as a person who is measuring brain data. [/INST] zero Principles are building blocks. 1st principles. Our understanding of system laws. So if you take for example, I can Sherlock Holmes, he's a first principle stinker. So he says, once you've eliminated the impossible, anything that remains, however improbable, it's true. Mhm Whereas dirk gently the holistic detective by Douglas Adams says, I don't like eliminating the impossible. So when someone says from a first principles perspective and they they're trying to assume the fewest number of things within a given timeframe. And so when I after braintree Venmo, I set my mind to the question of what single thing can I do that would maximally increase the probability that the human race thrives beyond what we can even imagine. And I found that in my conversations with others in the books I read in my own deliberations, I had a missing piece of the puzzle because I didn't feel like over Yeah, I didn't feel like the future could be deduced from first Principles thinking. And that's when I read the book zero, a biography of a dangerous idea. And </s><s>[INST] I had a really good [/INST] book by the way, I think it's my favorite book I've ever read, </s><s>[INST] It's also a really interesting number zero [/INST] and I I wasn't aware that the numbers zero had to be discovered, I didn't realize that it caused a revolution in philosophy and and just tore up math and it tore up. I mean it builds modern society, but it it wrecked everything in its way. It was an unbelievable disruptor and it it was so difficult for society to get their heads around it. And so zero advocates of course the a representation of the zeroth principal thinking, which is, it's the caliber and consequential nature of an idea. And so when you talk about what kind of ideas have civilization transforming properties. Oftentimes they fall in the zeroth category. And so in thinking this through, I I was wanting to find a quantitative structure on how to think about the zero principles and so I came up with that to be a coupler with first principles thinking. And so now it's a staple is part of how I think about the world in the future. </s><s>[INST] So it emphasizes trying to identify the lands on that word impossible. Like what is impossible, essentially trying to identify what is impossible, what is possible and being as um how do you I mean this, this is the thing is most of society tells you the range of things they say is impossible is very wide. So you need to be shrinking that. I mean that's the whole process of of this kind of thinking is you need to be very rigorous in in uh trying to be trying to draw the lines of what is actually impossible because very few things are actually impossible. I don't know what is actually impossible. Huh? Like its joe Rogan is entirely possible. I like that approach to ah to science, to engineering to entrepreneurship. It's entirely possible, basically shrink the impossible to zero two very small set [/INST] your life constraints favor first principles thinking because it it enables faster action with higher probability of success pursuing zero of principle optionality is expensive and uncertain. And so in a society constrained by resources, time and money and a desire for social status, accomplishment, etcetera. It minimizes zero principle thinking about it. But the reason why I think zero principle thinking should be a staple of our shared cognitive infrastructure is If you look at the history of the past couple of 1000 years and let's just say we arbitrarily we subjectively try to assess what is a zero level zero level idea and we say how many have occurred on what time scales and what were the contractual settings for it. I would argue that if you look at Alpha go when it played, go from another dimension with the human go players, when it saw Alpha goes moves, it attributed to playing with an alien playing go with uh with Alphago beating from another dimension. And so if you say computational intelligence has an attribute of introducing zero like insights, then if you say what is going to be the occurrence of zeros in society going forward and you could recently say probably a lot more than have occurred and probably more at a faster pace. So then if you say what happens if you have this computational intelligence throughout society, that manufacturing design and distribution of intelligence is now going to heading towards zero. You have an increased number of zeros being produced with a tight connection between humans and computers. That's when I got to a point and said, we cannot predict the future with first principles thinking we can't that cannot be our imagination set, It can't be Our sole anchor in the situation that basically the future of our conscious existence, 2030, 40, 50 years is probably zero. </s><s>[INST] So just to clarify when you say zero, you're referring to basically truly revolutionary idea. [/INST] Yeah, it's something that is currently not a building block of our shared conscious existence either in the form of knowledge. Uh yeah, it's currently not manifest in what we've acknowledged. </s><s>[INST] zero principles, thinking is playing with ideas that are so revolutionary that we can't even clearly reason about the consequences once those ideas come to [/INST] be. Or for example, like Einstein, that was a zero, I would categorize it zeroes principal insight. </s><s>[INST] You mean general spacetime? Of course, yeah, [/INST] basically the building upon what Newton had done and said yes also, and it just changed the fabric of our understanding of reality. And so that was unexpected. It existed. We just it became became part of our awareness and the moves Alphago made existed, It just came into our awareness. And so it to your point, there's this question of what do we know and what don't we know? Do we think we know 99% of all things or do we think we know .001% of all things. And that goes back to no known unknowns and unknown unknowns and first principles and zero principle thinking gives us a quantitative framework to say there's no way for us to mathematically try to create probabilities for these things. Therefore it would be helpful if they were just part of our standard thought processes because it may encourage different behaviors and what we do individually collectively as a society, what we aspire to, what we talked about, the possibility sets we imagine. </s><s>[INST] Yeah, I've been engaged in that kind of thinking uh quite a bit and thinking about engineering of consciousness. I think it's feasible. I think it's possible in the language that we're using here. It's very difficult to reason about the world when inklings of consciousness can be engineered into uh artificial systems, not from a philosophical perspective, but from an engineering perspective, I believe a good step towards engineering consciousness is is creating engineering the illusion of consciousness. I'm captivated by our natural predisposition to anthropomorphize things. And I think that's what we Yeah, I don't want to hear from the philosophers, but I think that's what we kind of do to each other. [/INST] Okay, </s><s>[INST] that consciousness is created socially that like much of the power of consciousness is in the social interaction, I create your consciousness. No, I create my consciousness by having interacted with you. And that that's the display of consciousness. It's the same as like the display of emotion. Emotion is created through communication. Language is created through its use and then we somehow humans kind of, especially philosophers, you know, the hard problem of consciousness really want to believe that we possess this thing that's like there's a there's a there's a there's an elf sitting there with the hat or like name taxes consciousness and they're like feeding this subjective experience to us as opposed to like it actually being an illusion that would construct to make social communication more effective. And so I think if you focus on creating the illusion of consciousness, you can create some very fulfilling experiences in in software and so that to me is a compelling space of ideas to explore. [/INST] I agree with you and I think going back to our experience together with interfaces on you could imagine if we get to a certain level of maturity. So first let's take the university so you and I text back and forth and we're sending each other emojis that has a certain amount of information transfer rate as we communicate with each other. And so in our communication with people of the via email and text whatnot. We've taken the bandwidth of human interaction, the information transfer rate and we produced it. We have less social cues. We have less information to work with. There's a lot, a lot more opportunity for misunderstanding. So that is altering the conscious experience between two individuals. And if we add brainer faces to the equation, let's imagine now we amplify the dimensionality of our communications. That to me is what you're talking about which is consciousness engineering. Perhaps I understand you with dimensions. So maybe I understand your when you look at the cup and you experience that happiness, you can tell me you're happy and I then do theory of mind and say I can imagine what it might be like to be lex and feel happy about seeing this cup. But if the interface could then quantify and give me a 50 50 vector space model and say this is the version of happiness that lex is experiencing as you look at this cup, then it would allow me potentially to have much greater empathy for you and understand you as a human. And this is how you experience joy, which is entirely unique from how I experience joy even though we assumed ahead of time that we have, we're having some kind of similar experience. But I agree with you that the we do consciousness engineering today and everything we do when we talk to each other when we're building products and that we're entering into a a stage where it will be much more methodical and quantitative base in computational and how we go about doing it. Which to me I find encouraging because I think it creates better guard rails for to create uh ethical systems on versus right now. I feel like it's really wild Wild West on how these interactions are happening. </s><s>[INST] Yeah. And it's funny you focus on human to human but that this kind of data enables human to machine [/INST] Yes interaction </s><s>[INST] which is what we're kind of talking about when we say engineering consciousness [/INST] and that will happen. Of course let's flip that on its head. Let's right now we're putting humans as the central node. What if we gave gpt three a bunch of human brains said, Hey, GPT three learn some manners when you speak and run your algorithms on humans brains and see how they respond. So you can be polite and so that you can be friendly and so that you can be conversationally appropriate but to inverse it to give our machines a training set in real time with closed loop feedback so that our machines were better equipped to find their way through our society in polite and kind in appropriate ways. </s><s>[INST] I love the idea or better yet teach it some uh uh have it uh read the finding documents and have a visit austin in texas. And so that when you ask, when you tell it, why don't you learn some manners? DPT three learns to say no, it learns what it means to be free and the sovereign individual. So that it depends. So it depends what kind of a version of GPT three you want one that's free, one that behaves well with social revolution. You want, you want to like you want a socialist GPT three, You want an anarchist GPC three, you want a polite like you take it home with me to visit mom and dad. GPT three and you want like partying like Vegas to a strip club. GPT three, you want all flavors [/INST] and then you've got to have good alignment between all those. </s><s>[INST] Yeah, they don't want to manipulate each other for sure. Uh that's what I mean. You kind of spoke to ethics the one of the concerns that people have in this modern world, the digital data is that of privacy and security. But privacy, you know, they're concerned that when they share data it's the same thing we feel when we're trust other human beings uh in being fragile and revealing something that we're vulnerable, vulnerable about. There's a there's a leap of faith. There is a leap of trust that that's going to be just between us. There's a privacy to it. And then the challenge is when you're in the digital space and sharing your data with companies that use that data for advertisement, all those kinds of things. There's a hesitancy to share that much data to share a lot of deep personal data and if you look at brain data that feels a whole lot like it's richly deeply personal data. So how do you think about privacy with this kind of ocean of data. [/INST] I think we got off to a wrong start with the internet where the basic rules of play for the for the company that B was if your company you can go out and get as much information on a person as you can find without their approval and you can also do things to induce them to give you as much information and you don't need to tell them what you're doing with it. You can do anything on the back side, you can make money on it but the game is who can acquire the most information and devised the most clever schemes to do it. That was a bad starting place. And so we are in this period where we need to directly to correct for that and we need to say first of all, the individual always has control over their data. It's not a free for all. It's not like a game of hungry hippo but they can just go out and grab as much as they want. So for example when your brain data was recorded today, the first thing we did in the kernel app was you have control over your data. And so it's individual consent. It's individual control. And then you can build up on top of that but it has to be based upon some clear rules of play. If everyone knows what's being collected they know what's being done with it and the person has control over it. </s><s>[INST] The transparency and control. So everybody knows what does control look like. My ability to delete the data [/INST] if you want to delete it and to know who is being shared with under what you know what under what terms and conditions we haven't reached that level of sophistication with our products of if if you say for example hey Spotify please give me a customized playlist according to mine. you're um you know, you could say you can have access to this vector space model but only for this duration of time and uh and then you've got to delete it. We haven't gotten there at that level of sophistication, but these are ideas we need to start talking about of how do you, how would you actually structure permissions? And I think it creates a much more stable set for society to build where we understand the rules of play and people aren't vulnerable to being taken event. It's not fair for an individual to be taken advantage of without their awareness with some other practice that some companies doing for their sole benefit. And so hopefully we are going through a process now we're correcting for these things and that it can be an economy wide shift that because really these are these are fundamentals we need to have in place. </s><s>[INST] It's kind of fun to think about like in chrome when you install an extension or like install an app, it's ask you like what permissions you're willing to give and be cool if in the future it is like uh you can have access to my brain data. I [/INST] mean it's not unimaginable in the future. The big technology companies have built a business based upon acquiring data about you that they can then create a model of you and sell that predictability. And so it's not unimaginable that you will create with Colonel device for example, a more reliable predictor of you than they could and that they're asking you for permission to complete their objectives and you're the one that gets to negotiate that with them and say sure, but it's not unimaginable, that might be the case. </s><s>[INST] So there's a guy named Elon musk and he has a company in one of the many companies called neuralink that has uh that's also excited about the brain. So be interesting to hear your kind of opinions about a very different approach that's invasive that requires surgery implants a data collection device in the brain. How do you think about the difference in kernel and your link in the approaches of uh getting that stream of brain data. [/INST] Ellen and I spoke about this a lot early on we we met up, I had started Colonel and he had an interest in pre interfaces as well and we explored doing something together, him joining Colonel. And ultimately it wasn't the right move. And so he started, not only can I continue building Colonel, but it was interesting because we were both at this very early time where it wasn't certain what if there was a path to pursue if now was the right time to do something and then the technological choice of doing that. And so we were both our starting point was looking at invasive technologies and I was building to invasive technology at the time that's ultimately where he's gone ah a little less than a year after uh you and I were engaged, I shifted Colonel to do non invasive And we had this neuroscientists come to colonel, we were talking about he had been doing a neurosurgeon for 30 years, one of the most respected neuroscientists in the us. And we brought him to colonel to figure out the ins and outs of his profession. And at the very end of our three hour conversation, he said, you know, Every 15 or so years a new technology comes along. That changes everything. He said. It's probably already here. You just can't see it yet. And my jaw dropped. I thought because I I had spoken to bob Greenberg who had built uh second sight first on the optical nerve and then he did court up an array on the optical um cortex. And then I also became friendly with um no pace. Who does, who does the implants, first, seizure detection and remediation. And I saw in their eyes, What it was like to take something through an implantable device through for her for a 15 year run. They initially thought was seven years, Ended up being 15 years and they thought would be 100 million is, you know, 300, million. And I really didn't want to build invasive technology. It was the only thing that appeared to be possible. But then once I spun up an internal effort to start looking at non invasive options, we said, is there something here? Is there anything here that, again, has the characteristics of it has a high quality data, it could be low cost that could be accessible, couldn't make brain or faces mainstream. And so I did a bet the company move, we shifted from non invasive to invasive to non invasive. </s><s>[INST] So the answer is yes to that there's something there. It's possible. [/INST] The answers will see we've now built both technologies and they're now you experience one of them today. We or playing. We're now deploying it. So we're trying to figure out what values really there. But I'd say it's it's really too early to express confidence whether it's true. I think it's too early to assess which technological choice is The right one on what timescales, </s><s>[INST] timescales are really important. Very [/INST] important because if you look at the only invasive side, there's so much activity going on right now of less invasive techniques to get at The neuron firings, which would what neuralink is building. It's possible that in 10, 15 years when they're scaling the technology, other things have come along, you'd much rather do that. That thing starts the clock again. It may not be the case. It may be the case that neuralink has property, chosen the right technology and that that's exactly what they want to be totally possible. And it's also possible that the path we've chosen noninvasive fall short for a variety of reasons. It's just it's unknown. And so right now the two technologies we chose the analogy of Gift Give you to create a baseline of understanding is If you think of it like the Internet in the 90s, the internet became useful when people could do a dial up connection and then the paid and then as bandwidth increased. So did the utility of that connection and sort of ecosystem approved. And so if you say what Colonel Flow is going to give you a full screen on the picture of information but you're gonna be watching a movie but the image is going to be blurred and the audio is going to be muffled so it has a lower resolution of coverage. Colonel flux R M E G. Technology is going to give you the full movie and 10 80 P. And neuralink is going to give you a circle on the screen four K. Yeah. And so each one has their pros and cons and it's give and take. And so the decision I made. But Colonel was that these two technologies flux and Flow were basically the answer for the next seven years and that they would give rise to the ecosystem which would become much more valuable than the hardware itself and that we would just continue to improve on the hard way over time and you know, it's early days. So it's </s><s>[INST] kind of fascinating to think about that you don't it's very true that you don't know both paths are very problem are promising And it's like 50 years from now, we'll we will look back and maybe not even remember one of them and the other one might change the world. It's so cool how technology is. I mean, that's that's what entrepreneurship is, is like markets the zeroth principle is like you're marching ahead into the darkness, into the fog not knowing. [/INST] It's wonderful to have someone else out there with us doing this. Because if you if you look at Brainer faces, anything that's off the shelf right now is inadequate. It's had its run for a couple decades. It's still in hacker communities. It hasn't gone to the mainstream. The room size machines are on their own path, but there is no answer right now. We're bringing brainer faces mainstream. And so it both both they and us, we've both spent over $100 million dollars and that's kind of what it takes to have a go at this because you need to build full stack, I mean, Colonel, we are from the photon and the atom, through the machine learning. We have just under 100 people. I think it's something like 36 37 phds in these specialties, these areas that there's only a few people in the world who have these abilities and that's what it takes to build next generation have to make an attempt Breaking into brainer faces and so we'll see you in a couple years whether it's the right time or whether we were both too early or whether something else comes along in 7 to 10 years which is the right thing that brings it mainstream. </s><s>[INST] So you see Ellen as a kind of competitor or a fellow traveler along the path of uncertainty or both. [/INST] It's a fellow traveler it's like at the beginning of the internet is how many companies are going to be invited to this new ecosystem like an endless number because if you think that the hardware just starts the process and so okay back to your initial example if you take the Fitbit for example you say okay now I can get measurements on the body and what do we think the ultimate value this device is going to be? What is the information transfer rate? And they were in the market for a certain duration of time and google bought them for $2.5 billion. They didn't have ancillary value add. There weren't people building on top of the Fitbit device, they also didn't have increased insight with additional data streams. So he's really just the device. If you look for example at Apple and the device they sell you have value in the device that someone buys but also you have everyone who's building on top of it. You have this additional ecosystem value and then you have additional data streams that come in which increased the value of the product and so if you say if you look at the hardware as the Ingigator of value creation, you know over time what we've built may constitute five or 10% of the value of the overall ecosystem and that's what we really really care about. What we're trying to do is kick start the mainstream adoption of quantifying the brain and the hardware just opens the door to say what kind of ecosystem could exist. Mhm And that's why we're the examples are so relevant of the things you've outlined in your life. We hope, I hope those things the books, people write the experiences, people build the conversations, you have your relationship with your AI systems. I hope those all are feeding on the insights built upon this ecosystem, we've created to better your life and so that's the thinking behind it again with the drake equation being the underlying driver of value and the people that colonel have joined, not because we have certainty of success, but because we find it to be the most exhilarating opportunity we could ever pursue in this time to be alive, </s><s>[INST] You founded the payment system Braintree in 2007 That acquired Venmo in 2012 in that in that same year was acquired by paypal, which is now ebay, can you tell me the story of the vision and the challenge of building an online payment system and just building a large, successful business in general, [/INST] I discovered payments by accident As I was when I was 21. I I just returned from Ecuador living in extreme poverty for two years and I came back to the U. S. And I was shocked by the opulence and of the United States and I just thought this is, I couldn't believe it and I decided I wanted to try to spend my life helping others. Like that was the that was the life objective that I thought was worthwhile to pursue versus making money and whatever the case may be for its own right. And so I decided that moment that I was going to try to make Enough money by the age of 32, never have to work again. And then with some abundance of money, I could then choose to do things that might be beneficial to others but may not meet the criteria of being a standalone business. And so in that process I started a few companies, had some small successes, had some failures. In one of the endeavors, I was up to my eyeballs in debt. Things were not going well and I needed a part time job to pay my bills. And so I one day I saw in the paper in Utah where I was living the 50 richest people in Utah and I e mailed each one of the assistants and said, you know, I'm young, I'm resourceful, I'll do anything. I just want to, I'm entrepreneurial. I try to get a job that would be flexible and no one responded and then I interviewed at a few dozen places, nobody would even give the time of day like you wouldn't want to take me seriously. And so finally I it was a monster dot com that I saw this job posting for credit card sales, door to door commissioner, I did not know this story, This is great. I love the head drop. That's exactly right. So it was </s><s>[INST] the low points to which we go and [/INST] like so I I responded and you know the person made an attempt at suggesting that they had some kind of standards that they would consider hiring, but it's kind of like if you could fog a mirror, Like come and do this because 100% Commission. And so I started walking up and down the street in my community selling credit card processing. And so what you learn immediately and doing that is if you, you walk into a business first of all, the business owner is typically there and you walk in the door and they can tell by how your address or how you walk whatever their pattern recognition is and they just hate you immediately. It's like stop wasting my time. I really am trying to get stuff done. I don't want to do a sales pitch. So you have to overcome the initial get out and then once you engage when you say there were credit card processing, the person's like I already hate you because I have been taking advantage of dozens of times because you all are weasels. And so I had to figure out an algorithm to get past all those different conditions because I'm still working on my other startup for the majority of my time doing this part time. And so I figured out that the industry really was built on people uh on the seat basically people promising things that were not reality. And so I walk into a business and say look I will give you $100. I put $100 bill and say I'll give you $100 for three minutes of your time. If you don't say yes to what I'm saying, I'll give you $100. And then he usually crack a smile and say ok what you got for me son. And so I sit down, I just opened my book and I'd say here's the credit card industry, here's how it works. Here are the players, here's what they do here is how they deceive you. Here's what I am. I'm no different than anyone else. It's like you're going to process your credit card, you get the money in the account, you're just going to get a clean statement, you can have someone who answers the call when someone asked and you know just like the basic like you're okay and people started saying yes and then of course I went to next business and be like, you know joe and susie and whoever said yes to and so I built the social proof structure and I became the number one sales person out of 400 people nationwide doing this and I have worked half time still doing so their startup and </s><s>[INST] that's a brilliant strategy by the way, it's very well, very well strategized and executed. [/INST] He did it for nine months. And at the time my customer base was making was generating around I think was sick, if I remember correctly, $62,500 a month where the overall revenues, I thought, Wow, that's amazing. If I Built that as my own company, I would just make $62,000 a month of income passively with these merchants processing credit cards set up. And so uh, that's when I thought I'm going to create a company. And so then I started Braintree and the idea was the online world was broken because Paypal had had been acquired by Ebay around I think 19 2099 or 2000. And Ebay had not innovative much with Paypal. So it basically sat still for seven years as the software world moved along and then authorize dot net was also accompanied with relatively stagnant. So you basically had software engineers who wanted modern payment tools, but there were none available for them. And so they just dealt with software they didn't like. And so with Braintree, I thought the entry point is to build software that engineers will love. And if we can find the entry point via software, make it easy and beautiful and just a magical experience and then provide customer service on top of that. It was easy. That would be great. What was really going after for that was it was Paypal. They were the only company and payments making money because they, because they had the relationship with the bay early on, People created a Paypal account. They fund their account with their checking account versus their credit cards. And then when they use Paypal to pay a merchant, Paypal, how the cost of payment of zero versus if you have coming from a credit card, you have to pay the bank the fees. So Paypal's margins were 3% on a transaction versus a typical payments company, which may be a nickel or a penny or a dime or something like that. And so I, a new Paypal really was the model to replicate. But a bunch of companies had tried to do that. They tried to come in and build a two sided marketplace. So get consumers to fund the checking account, the merchants to accept it. But they all failed because building a two sided marketplaces very hard at the same time. So my plan was, I'm going to build a company and get the best merchants in the whole world to use our service Then in year five, I'm going to have, I'm going to acquire a consumer payments company and I'm going to bring the two together and </s><s>[INST] so focus on the merchant side. Exactly and then get the payments company, does the customer, the whatever the other side of [/INST] this is the planet presented when I was at University of Chicago. And weirdly it happened exactly like that. So for four years in our customer base included, Uber Airbnb, get hub 37 signals, not base camp. We had a fantastic collection of companies that represented the fastest growing, some of the fastest growing tech companies in the world. And then we met up with Venmo and they had done a remarkable job in building products then something very counterintuitive, which is make public your private financial transactions, which people previously thought were something that should be hidden from others. And we acquired Venmo and at that point we now had, we replicated the model because people could fund their Venmo account, but the checking account, keep money in the account and then you could just plug Venmo as a form of payment. And so I think people saw that, that we were getting the best merchants in the world. We had people using Venmo, they were both the up and coming millennials at the time who had so much influence online and so they came in and offered us uh an attractive number and my goal was not to build the biggest payments company in the world. It wasn't to try to climb the Forbes billionaire list. It was the objective was I want to earn enough money so that I can basically dedicate my attention to doing something that could potentially be useful on a society wide scale. And more importantly that could be considered to be valuable from the vantage point of 2050, 12,500. So thinking about on a a few 100 year time scale and there was a certain amount of money I needed to do that. So I didn't require the permission of anybody to do that. And so that what people offered was sufficient for me to get that amount of money to basically have a go. And that's when I set off to survey everything I could identify existence to say of anything in the entire world. I could do what one thing could I do that would actually have the highest value potential for the species. And so it took me a little while to arrive at Brainerd faces. But </s><s>[INST] you know, payments in themselves, our revolutionary technologies that can change the world. Like it's not, let's not sort of um let's not forget that too easily. I mean obviously, you know this, but there's uh quite a few lovely folks who are now fascinated with the space of Cryptocurrency and uh where payments are very much connected to this, but in general just money and many of the folks that I've spoken with, they also kind of connect that to not just purely financial discussions but philosophical and political discussions. And uh, they see Bitcoin as a way almost as activism, Almost as a way to resist the corruption of centralized the centers of power and sort of basically in the 21st century decentralizing control, whether that's Bitcoin or other cryptocurrencies, they see that's one possible way to give power to those that live in regimes that are corrupt or are not respectful of human rights and all those kinds of things. What's your sense? Just all your expertise with payments and seeing how that changed the world. What's your sense about the lay of the land for the future of Bitcoin or other cryptocurrencies in the positive impact you may have in the world? [/INST] Yeah, to be clear, my communication wasn't suggest wasn't meant to minimize payments or to denigrate in any way. It was a an attempted communication that when I was surveying the world, it was an algorithm of what could I individually do. So there's there are things that exist that have a lot of potential that can be done and then there's a filtering of how many people are qualified to do this given thing. And then there's a further characterization that can be done of, okay, given the number of qualified people will somebody be a unique out performer of that group to make something truly impossible to be something done that otherwise couldn't get done. So there's there's a process of assessing where can you add unique value in the world? </s><s>[INST] And some of that has to do with you being very uh very formal and calculated here. But some of that is just like what you sense. Like part of that equation is how much passion you sense within yourself to be able to drive that through, to discover the impossibility to make them possible. [/INST] That's right. And so we we were a braintree. I think we were the first company to integrate coin base into our uh, I think we're the first payments company to formally incorporate crypto if I'm not mistaken </s><s>[INST] for people who are not familiar, coin base is a place we can trade cryptocurrencies. [/INST] Yeah. Which was one of the only places you could. So we were early uh in doing that. And of course this was in the Air 2013. So an attorney to go in Cryptocurrency land, I concur with the the statement you made of the potential of the principles underlying cryptocurrencies and that many of the things that they're building in the name of money and end of of moving value is equally applicable to the brain and equally applicable to how the brain interacts with the rest of world and how we would imagine doing goal alignment with people. So it's to me it's a continuous spectrum of possibility. And we're talking your question is isolated on the money and I think it just is basically a scaffolding later for all of society. So you don't see </s><s>[INST] that this money is particularly distinct. I [/INST] don't it's I think we well colonel, we will benefit greatly from the progress being made in Cryptocurrency because it will be a similar technology stack we will want to use for many things we want to accomplish. And so I'm bullish on what's going on and I think it could greatly enhance brain our faces and the value of the brain face ecosystem. </s><s>[INST] I mean, is there something you can say about, first of all, bullish on Cryptocurrency versus fiat money? Do you have a sense that in 21st century Cryptocurrency will be embraced by governments and changed the the face of governments, the structural government. [/INST] It's the it's the same way I think about my diet where previously it was conscious brian looking at foods in certain biochemical states on my hungry. Am I irritated and depressed? And then I choose based upon those momentary windows do I eat at night when I'm fatigued and I have no willpower. Am I going to pig out on something? And the current monetary system is based upon human conscious decision making and politics and power and this whole mess of things. And what I like about the building blocks of cryptocurrencies, It's methodical, it's structured, it is accountable is transparent. So it introduces this scaffolding, which I think again it's the right starting point for how we think about building next generation institutions for society and that's why I think it's much broader and much broader than money. </s><s>[INST] So I guess what you're saying is Bitcoin is the demotion of the conscious mind as well. In the same way you were talking about diet, it's like giving less priority to the the ups and downs of any one particular human mind in this case your own and giving more power to the sort of data driven. [/INST] Yes. Yeah. I I think that is accurate. That Cryptocurrency is a version of what I would call my autonomous self that I'm trying to build. It is an introduction of an autonomous system of value, exchange and value and the process Yeah. Value creation in society. Yes, their similarities. </s><s>[INST] So I guess what you're saying is Bitcoin will somehow help me not pig out at night or the equivalent of speaking of diet if we could just linger on that topic a little bit. We already talked about your your blog post of I I fired myself. I fired brian the evening brian who's too willing to uh not not making good decisions for the long term well being and happiness of the entirety of the organism, basically you were like pigging out at night. And it was interesting because I do this, I do the same. In fact I often eat one meal a day and uh like I have been this this week actually, especially when I travel. And it's funny that uh it never occurred to me to just basically look at the fact that I'm able to be much smarter about my eating decisions in the morning and the afternoon than I am at night. So if I eat one meal a day, why not eat that one meal a day in the morning, Like I'm not, it never occurred to me this revolutionary until until you've uh you've outlined that. So maybe can you give some details and what this is just you? This is one person brian arrived at a particular thing that they do. But it's fascinating to kind of look at this one particular case study. So what works for you diet wise? What's your actual diet? What do you eat often do you eat? [/INST] My current protocol is basically the result of thousands of experiments and decision making. So I've I do this every 90 days. I do the tests, I do the cycle through that. I measure again and then I'm measuring all the time. And so what I I of course I'm optimizing for my biomarkers. I want perfect cholesterol and I brought perfect blood glucose levels and perfect DNA methylation. Uh you know, processes. Uh I also want perfect sleep. And so for example, recently, the past two weeks my resting heart rate Has been at 42 when I sleep and when my resting heart rate at 42, my HR V is at its highest. And I wake up in the morning filling More energized than any other configuration. And so I know from all these processes that eating roughly 8:30 AM, right after I work out on an empty stomach creates enough distance between that completed eating and bedtime where I have no almost no digestive processes going on in my body. Therefore my resting heart rate goes very low. And when my resting heart rate is very low, I sleep with high quality. And so basically I've been trying to optimize the entirety of what I eat to my sleep quality and sleep quality. Then of course feeds into my willpower, so creases virtuous cycle. So what at 8 30 what I do is I eat what I call super veggie, which is, it's a pudding of 250 g of broccoli, 150 g of cauliflower and hoping to other vegetables that I eat what I call nutty pudding, which is </s><s>[INST] make the putting yourself like, like like the what you call it, like a veggie mix, whatever thing that like a blender. [/INST] Yeah. How people can be made in a high speed blender. But basically the same thing every day veggie bowl as in the form of pudding, and then bowl in the form of nuts. And then I have </s><s>[INST] vegan vegan vegan. So that's fat and that's like uh that's fat and carbs and fats and protein and so on. But it tastes good. [/INST] I love it. I I love it so much I dream about it. </s><s>[INST] Yeah, that's awesome. This is uh [/INST] and then I have a third dish which is, it changes every day today, it was Callum spinach and sweet potato. And then I take about 20 supplements that hopefully make constitute a perfect nutritional profile. So what I'm trying to do is create the perfect diet for my body every single day we're </s><s>[INST] asleep as part of the optimization. You're like one of the things that really tracking me, Can you? Well I have a million questions but 20 supplements like what kind are like would you say are essential? Because I only take I only take uh athletic athletic greens dot com slash that's like the multivitamin essentially. That's like the lazy man, you know, like like if you don't actually want to think about ship, that's what you take and then uh fish oil and that's it, that's all I take [/INST] you. Alfred North Whitehead said advanced civilization advances as that extends the number of important operations that can do without thinking about them. And so my objective on this is I want an algorithm for perfect health that I never have to think about. And then I want that system to be scalable to anybody so that they don't even think about it. And right now it's expensive for me to do it. It's time consuming for me to do it and I have the infrastructure to do it. But the future of being human is not going to the grocery store and deciding what to eat. It's also not reading scientific papers trying to decide this thing or that thing, it's all end of one. So it's it's devices on the outside and inside your body assessing real time what your body needs and then creating closed loop systems for that to happen. </s><s>[INST] So right now you're doing the data collection and you're being the scientist, It would be much better if you're doing just that if you just did the data clock or it was being essentially done for you and you can outsource that to another scientist that's doing the N1 study of you. [/INST] That's right because every time I spend time thinking about this or executing spending time I'm spending less time thinking about building kernel or or future of being human and so it's we just all have these the budget of our capacity on on everyday basis and we will scaffold our way up out of this. And so yeah, hopefully what I'm doing is really it serves as a model that others can also build on why that's why I wrote about it is hopefully people can take and improve upon it. Uh I hold nothing sacred, I changed my diet almost every day based upon some new test results or science or something like that but </s><s>[INST] can you maybe elaborate on the sleep thing, why is sleep so important and why presumably like what does good sleep mean to you? [/INST] I think sleep is a contender for being the most powerful health intervention in existence. Yeah, it's a contender. I mean it's uh it's magical what it does if you're well rested and what your body can do. And I mean for example, I know when when I eat close to my bedtime and I've done a systematic study Four years looking at like 15 minute increments on time of day and where I eat my last meal, my willpower is directly correlated to my to the amount of deep sleep I get. So my ability to not binge eat at night when rascal brian's out about is based upon how much deep sleep I got the night </s><s>[INST] before. And so there's some, there's a lot to that. Yeah, [/INST] and so I just I've seen it manifest itself and so that I think the way it summarized this is in society, we've had this myth of we tell stories, for example, of entrepreneurship, where this person was so amazing, they stayed at the office for three days and slip into their desk and we say, wow, that's amazing, that's amazing. And now I think we're headed towards a state where we say that's primitive and really not a good idea if on every level. And so the new mythology is going to be the exact opposite. </s><s>[INST] Yeah, by the way, just sort of maybe push back a little bit on that idea. [/INST] Did you sleep under your desk collects </s><s>[INST] well? Yeah, I lied. I'm a big believer in that actually. I'm a big believer in, in chaos and not giving, giving into your passion and sometimes doing things that are out of the ordinary there, like not trying to optimize health for certain periods of time in, uh, in lieu of your passions is a signal to yourself that you're throwing everything away. So I think what you're referring to is how to have good performance for prolonged periods of time. I think there's, there's moments in life, we need to throw all that away, all the plans away, all the structure away. So the, I don't just, I'm not sure I have an eloquent way describe exactly what I'm talking about, but it all depends on different people on people, people are different, but there's a danger of over optimization to where you don't just give in to the madness of the way your brain flows. I mean, to push back on my pushback is like, it's nice to have like where the, where the foundations of your brain are not messed with. So you have a fixed foundation where the diet is fixed, where the sleep is fixed and that all that is optimal and the chaos happens in the space of ideas as opposed to the space of biology, but you know, I'm not sure if there's a, uh, that requires real discipline and forming habits. There's some aspect to which some of the best days and weeks of my life have been, yeah, sleeping under a desk kind of thing. And I don't, I'm not too willing to let go of things that empirically worked for things that work in theory. And so I'm again, I'm absolutely with you on sleep also, I'm with you on sleep conceptually, but I'm also very humbled to understand that for different people, good sleep means different things. I'm very hesitant to trust science on sleep. I think you should also be a scholar of your body. Again, the experiment of end of one. I'm not so sure that a full night's sleep is great for me. There is something about that power nap that I just have not fully studied yet. But that map is something special that I'm not sure. I found the optimal thing. Um, so like there's a lot to be explored to what is exactly optimal amount of sleep, optimal kind of sleep combined who died and all those cousins. I mean that all maps to sort of data leads the truth. Exactly. All referring to, [/INST] here's a data point for your consideration, the progress in biology over the past. It's a decade has been stunning. Yes. And it now appears as if we will be able to replace Our Organs. zero extra transplantation. And so we probably have a path to replace and regenerate every organ of your body except for your brain. You can you can lose your hand and your arm and leg. Get an official heart, you can't operate your brain. And so when you make that trade off decision of whether you're going to sleep under the desk or not and go all out for a four day marathon, right? There's a there's a cost benefit tradeoff of what's going on, What's happening to your brain in that situation, we don't know the consequences of modern day life on our brain. We don't, it's the most valuable organ in our existence and we don't know what's going on. If we and how we're treating it today with stress and with sleep and with dietary. And to me then, if you say that you're trying to you're trying to optimize life for whatever things you're trying to do. The game is soon with the progress in anti asian and biology. The game is very soon going to become different than what it is right now with Oregon rejuvenation, organ replacement. And I I would conjecture that we will value the health status of our brain above all things. </s><s>[INST] Yeah, absolutely everything you're saying is true. But uh, we die, we die pretty quickly. Life is short. And I'm one of those people that I would rather die in battle than uh than stay safe at home. It's like, yeah, you look at kind of, there's a lot of things that you can reasonably say this, this is the smart thing to do that can prevent you that becomes conservative that can prevent you from fully embracing life. I think ultimately you can be very intelligent and data driven and also embrace life. But I are on the side of embracing life. It's very, it takes a very skillful person to not sort of that hovering parent that says no, you know what? There's a three chance that if you go out, if you go out by yourself and play, you're going to die, get run over by a car, come to a slow or a sudden and and uh, I am more a supporter of just go out there if you die, you die. And that's a, it's a balance you have to strike. I think there's a balance to strike in the long term optimization and uh short term freedom for me, for programmer for programming mind, I tend to over optimize and I'm very cautious and afraid of that to not over optimize and thereby be overly cautious, sub optimally cautious about everything I do and that's the ultimate thing I'm trying to optimize for. It's funny you said like sleep and all those kinds of things. I tend to think, yeah, this is, you be more precise than I am, but I think I tend to want to minimize stress, which everything comes into that from you sleep and all those kinds of things. But I worry that whenever, I'm trying to be too strict with myself, then the stress goes up when I don't follow the strictness. And so you have to kinda it's a weird, it's uh there's so many variables in objective function as it's hard to get right. And sort of not giving a damn about sleep and not giving a damn about diet is a good thing to inject in there every once in a while for somebody who's trying to optimize everything. That's but that's me just trying to uh like it's exactly like you said, you're just a scientist. I'm a scientist of myself, your scientists of yourself. It'd be nice to somebody else is doing it and had much better data then because I don't trust my conscious mind. And I pigged out last night at some brisket in L. A. That I regret deeply [/INST] still uh </s><s>[INST] there's no point to anything I just said. [/INST] But what is the nature of your regret on the brisket? Is it do you wish you hadn't eaten it entirely? Is it that you wish you hadn't eat as much as you did? Is it that </s><s>[INST] I think uh well the most regret, I mean if you want to be specific, I drank way too much like dad's order my biggest regret is like having drinks so much diet soda. That's the thing that really was the problem, I had trouble sleeping because of that because I was like programming. And then I was editing so stipulated night and then I had to get up to go p a few times and it was just a mess. And it was, it's not really a mess, but like it's so many, it's like the little things I know if I just eat, I drink a little bit of water and that's it. And there's a certain all of us have perfect days that we know diet wise and so on, that's good to follow you feel good. I know what it takes for me to do that. I didn't fully do that and thereby because there's there's an avalanche effect where the other sources of stress, all the other to do items I have pile on my failure to execute on some basic things that don't make me feel good and all that combines to uh you know, to create to create a mess of a day. But some of that chaos, you know, you have to be okay with it. But some of it I wish it was was a little bit more optimal. And your ideas about eating in the morning are quite interesting as an experiment to try. Can you elaborate? Are you eating once a day? Yes, in the morning. And that's it. Can you maybe speak to how that you spoke? It's funny, he spoke about the metrics of sleep, but you're also, you know, you run a business, you're incredibly intelligent, you have to most of your happiness and success relies on you thinking clearly. So how does that affect your mind and your body in terms of performance. So not just sleep, but actually like mental performance [/INST] as you were explaining your objective function of for example, in the criteria you were including you like certain neurochemical states, like you like feeling like you're living life that life has enjoyment, that sometimes you want to disregard certain rules to have a moment of passion, of focus. There's this architecture of the way Lexus which makes you happy as a story you tell as something you kind of experience. Maybe the experience is a bit more complicated, but in this idea you have, this is a version of you and the reason why I maintain the schedule I do is I've chosen a game to say I would like to live a life where I care more about what intelligent yeah. What people who live in 2000 the year 2500 think of me than I do today, that's the game I'm trying to play. And so therefore the only thing I really care about on this optimization is trying to see past myself, past my limitations using zeroes principal thinking, Pull myself out of this contextual measured in right now and say what will matter 100 years from now, in 200 years from now, what are the big things really going on that are defining reality? And I find that if I were to hang out with diet soda lex and diet soda brian were to play along with that and my deep sleep were to get crushed As a result, My mind would not be on what matters in 100 years or 200 or 300 years, I would be irritable. I would be, you know, I've been a different state and so it's just gameplay selection. It's what you and I have chosen to think about. It's what we've chosen to. I'll work on. And this is what I'm saying that no generation of humans have ever been afforded the opportunity to look at their lifespan and contemplate that they will have the possibility of experiencing an evolved form of consciousness. That is unidentifiable that following a zero category of potential that to me is the most exciting thing in existence. And I would not trade any momentary neurochemical state right now in exchange for that, I would be willing to deprive myself of all momentary joy in the pursuit of that goal because that's what makes me happy. </s><s>[INST] Yeah, that's brilliant. But I'm I'm a bit I just looked it up with just looked up Braveheart speech and William Wallace, but he's in a fight and you may die run and you'll live at least awhile and dying in your beds many years from now, would you be willing to trade all the days from this day to that for one chance, just one chance picture of mel Gibson saying this to come back here and tell our enemies that they may take our lives with growing excitement, but they'll never take our freedom. I get excited every time I see that in the movie. But that's kind of how I approach life. And do [/INST] you think they were tracking their sleep? </s><s>[INST] I did. We're not tracking their sleep and they ate way too much brisket and they were fat, unhealthy, died early and uh were primitive. But there's some there's something in my eight brain that's attracted to that, even though most of my life is fully aligned with the way you see yours and part of it is for comedy of course, but part of it is like I'm almost afraid of over optimization [/INST] really. What you're saying though, if we're looking at this, let's say from a first principles perspective, when you read those words, they conjure up certain life experiences, but you're basically saying I experience a certain neurotransmitter state when these things are in action. That's all you're saying. So whether it's that or something else, you're just saying you have a selection for how your state for your body. And so if you as an engineer of consciousness, that should just be engineer a ble Yeah, and that's just triggering certain chemical reactions and so whether so it doesn't mean they have to be mutually exclusive. You can have that and experience that and also not sacrifice long term health and I think that's the potential of where we're going is we don't have we don't have to assume they are trade offs that must be had. </s><s>[INST] Absolutely. And so I guess from my particular brain is useful to have the outlier experiences that also come along with the illusion of free will, where I chose those experiences that make me feel like its freedom, listen, going to texas made me realize I spent so I was, I still am but I lived at Cambridge and M. I. T. And I never felt like home there. I felt like home in the space of ideas with the colleagues like when I was actually discussing ideas but there is something about the constraints, the how cautious people are, how much they valued also kind of uh material success, career success. When I showed up to texas, it felt like I belong, that was very interesting, but that's my neurochemistry, whatever the hell that is, whatever whatever maybe probably is routed to the fact that grew up in the soviet union, it was so such a constraint system that you'd really deeply value freedom and you've you always want to escape the the man in the control of centralized systems. I don't know what it is, but that's at the same time, I love strictness, I love the dogmatic authoritarianism of diet of like the same habit exactly the habit you have. I think that's actually when bodies perform ultimately my body performs ultimately. So balancing those two, I think if I have the data every once in a while party with some wild people, but most of the time he wants a day perhaps in the morning I'm gonna try. That might be very interesting, but I'd rather I'd rather not try it. I'd rather have the data that tells me to do it. But in general you're able to eating once a day. Think deeply about stuff like that's a concern that people have is like, you know, what does your energy wayne all those kinds of things? Do you find that it's especially because um it's unique. It's vegan as well. So you find that you're able to have a clear mind focus and just physically and mentally throughout. [/INST] Yeah, I find like my personal experience in thinking about hard things is often times I feel like I'm I'm looking through a telescope and I come aligning two or three telescopes so you kind of have to close one eye and move it back and forth a little bit and find just the right alignment. Then you find just a sneak peek at the thing you're trying to find. But it's fleeting. If you move just one little bit, it's gone and oftentimes what I feel like our the the ideas I value the most are like that. They're so fragile and fleeting and slippery and elusive and it requires a sensitivity to thinking and a sensitivity to maneuver through these things if I Concede to a world where I'm on my phone texting, I'm also on social media. I'm also doing 15 things at the same time because I'm running a company and I'm also feeling terrible from the last night. Um it all just comes crashing down and the quality of my thoughts goes to a zero. I'm just, I'm a functional person to respond to basic level things. But I don't feel like I I'm doing anything interesting. </s><s>[INST] I think that's a good word sensitivity because that's when you, that's, that's what thinking deeply feels like is you're sensitive to the fragile thoughts and you're right. All those other distractions kind of dull your ability to be sensitive to the fragile thoughts. It's a really good word out of all the things you've done. You've also climbed Mount Kilimanjaro. Is this true? [/INST] It's true. </s><s>[INST] Uh huh. What do you uh why and how and what do you take from that experience? [/INST] I guess the backstory is relevant because That in that moment it was the darkest time of my life. I was ending a 13 year marriage. I was leaving my religion. I sold Braintree and I was coming battling depression where I was just at the end and I got invited to go to Tanzania as part of a group that was raising money to build clean water wells. And I had made some money from braintree. And so I was able to donate $25,000 and it was the first time I had ever had money to donate outside of pain ties into my religion. It was such a phenomenal experience too. Two contribute something meaningful to someone else in that form. And as part of this process we were going to climb the mountain and so we went there and we saw the clean water wells were building, we spoke to the people there and it was very energizing and then we climbed Kilimanjaro and I came down with stomach flu on day three and I also had altitude sickness, but I became so sick that on day four, we are somebody on day five, I came into the camp base camp at 15,000 ft. Uh, just you know, going to the bathroom on myself and like falling all over. It was just, I was just a disaster. It was so sick </s><s>[INST] just flew and altitude sickness. [/INST] Yeah. And I just was destroyed from the situation And </s><s>[INST] plus one psychologically one of the lowest [/INST] points. Yeah. And I think that was probably a big contributor. I was, I was just smoked as a human. Just absolutely done. And I have three young Children and so I was trying to reconcile like this is not a weather, what whether I live or not is not my decision by itself. I'm now intertwined with these three little people and I have an obligation whether I like it or not, I need to be there and so it did. It felt like I was just stuck in a straitjacket and I had to decide whether I was going to summit the next day with the team and it was a difficult decision because once you start hiking there's no way to get off the mountain and midnight came and our guide came in and he said were you out? And I said I think I'm okay, I think I can try and so we went and so from midnight to I made it to the summit at five a.m. it was one of the most transformational moments of my existence and mhm the mountain became my problem, it became everything that I was struggling with and when I started hiking it was the pain got so ferocious that it was kind of like this uh it became so ferocious that um I turned my music to Eminem and it was you know Eminem was the he was the only person in existence that spoke to my soul and it was something about you know his anger and his vibrancy and his multi eventually he's the only person who I could turn on and I could just say like I feel some relief, I turned, I turned on Eminem and um I made it to the summit after five hours but just just 100 yards from the top I was with my guide ike and I started getting very dizzy and I was, I felt like I was gonna fall backwards off this cliff area we are on, I was like this is dangerous. And he said look brian I I know what you're at, this guy, I know where you're at and I can tell you you've got it in you, I want you to look up, take a step, take a breath and look up, take a breath and take a step. And I did and I made it and so I got there and I just I sat down with him at the top. I just cried like a baby </s><s>[INST] broke down, [/INST] just I just lost it. And So you know he let me do my thing and then we pulled out the pulse oximeter and measure my blood oxygen levels and it's like it was like 50 something percent and it was danger zone. So he so he looked at it and I think he was like really alarmed that I was in this situation. And so uh He said we can't get a helicopter here and we can't get you emergency evacuated, you've got to go down, you've got to hike down to 15,000 ft to get base camp. And so he we went on the mountain, I got back down to base camp and again that was pretty difficult and then they put me on a stretcher, This metal stretcher with this one will and a team of six people will be down the mountain and it was it was pretty tortuous, I'm very appreciative. They did also the trail was very bumpy. So they'd go for the big rocks and so my head would just slam against this metal thing for hours. And so I just felt awful. Plus I get my head slammed every couple seconds. So the whole experience was really a life changing moment and that's it. That was the demarcation of basically building your life, basically I said I'm going to reconstruct brian my my understanding of reality, my existential reality is what I want to go after and I try I mean as much as that's possible as a human, but that's when I set out to rebuild everything. </s><s>[INST] Was it the struggle of that? I mean there's also just like the romantic poetic, it's a freaking mountain, he's a he's a man in pain, psychological and physical, struggling up a mountain but its just struggle just in the in the face of just pushing through in the face of hardship or nature too. Something much bigger than you. Is that was that the thing that just clicked [/INST] for me, it felt like I was just locked in with reality and it was a death match. It was in that moment, one of us is going to die. </s><s>[INST] So you're pondering death, like not surviving [/INST] and and it was and that was the moment and it was the summit to me was I'm gonna come out on top and I can do this and giving in was it's like I'm just done. And so it did. I locked in and uh, that's why yeah, mountains are magical to me. I didn't expect that. I didn't design that. I didn't know that was gonna be the case. I not it would not have been something I would have anticipated. </s><s>[INST] But you are not the same man afterwards. Yeah. Is there advice you can give to a young people today that look at your story that's successful in many dimensions advice you can give to them about how to be successful in their career, successful in life, whatever path they choose. [/INST] Yes, I would say listen to advice and see it for what it is a mirror of that person and then map and know that your future Is going to be in a zero principle land. And so what you're hearing today is a representation of what may have been the right principles to build upon previously, but they're likely do appreciate him very fast. And so I am a strong proponent that people ask for advice, but they don't take advice. </s><s>[INST] So how do you take advice properly? [/INST] It's in the careful examination of the advice. It's it's actually you the person makes a statement about a given thing, somebody should follow, the value is not doing that. The value is understanding the assumption stack. They built the assumption of knowledge that they built around that that body of knowledge. That's the value is not doing what they say </s><s>[INST] considering the advice, but digging deeper to understand the assumption stack like the full person. It's I mean this is deep empathy essentially to understand the journey of the person that arrived at the advice and the advice is just the tip of the iceberg that ultimately is not the thing that gives you, it could it could be the right thing to do, It could be the complete wrong thing to do depending on the assumptions stack. So you need to investigate the whole thing. Is there some, are there been people in your start up in your business journey that's have served that role of advice giver has been helpful or do you feel like your journey felt like a lonely path? Or was it one that was of course we're all we're all they're born and die alone uh by uh do you fundamentally remember the experience is one where you leaned on people at a particular moment in time that changed everything? [/INST] Yeah. The most significant moments of my memory, for example, like on Kilimanjaro when I kick some person I had never met in Tanzania was able to in that moment apparently see my soul when I was in this death match with reality and he gave me the instructions look up step. And so there's magical people in my life that have done things like that. And I suspect they probably don't know, I probably should be better at identifying those things and but yeah, hopefully the, I suppose I can wisdom I would aspire to is to have the awareness and the empathy to be that for other people and not a a retail advertiser of advice of tricks and for life, but deeply meaningful and empathetic with a one on one context with people that it really can make a difference. </s><s>[INST] Yeah, I actually kind of experience, I think about that sometimes, you know, you have like an 18 year old kid come up to you. It's not always obvious. It's not always easy to really listen to them. Like not not the facts, but like see who that person is. I think people say that about being a parent is you know, you want to consider that you don't want to be the authority figure in a sense that you really want to consider that there is a special, unique human being there with a unique brain that may be um brilliant in ways that you are not understanding that you'll never be really tried to hear that. So when giving advice, there's something to that. It's a both sides should be deeply empathetic about the assumptions stack. I love that. The terminology. What do you think is the meaning of this whole thing of life? Why the hell are we here, brian johnson, We've been talking about brains and studying brains and you had this very eloquent way of describing life on earth as uh, as an optimization problem. Uh the cost of intelligence going to zero at first through the evolutionary process and then eventually through building uh through our technology building more and more intelligence systems, you ever ask yourself why is doing that? [/INST] Yeah, I think the answer to this question again, the information value is more in the mirror. It provides of that person which is a representation of the technological, social political context of the time. So if you asked this question 100 years ago, you would get a certain answer that reflects that time period, same thing would be to over 1000 years ago. It's rare. It's difficult for a person to pull themselves out of their contextual awareness and offer truly original response. And so knowing that I am contextually influenced by the situation that I am a mirror for our reality. I would say that in this moment, I think the real game going on is that in evolution built a system of scaffolding intelligence that produced us. We are now building intelligence systems that are scaffolding higher dimensional intelligence that's developing more robust systems of intelligence in doing in that process, with the cost going to zero, then the meaning of life becomes goal alignment which is the negotiation of our conscious and unconscious existence. And then I'd say the third thing is if we're thinking that we want to be explorers is our technological progress is getting to a point where we could aspirational, we say we want to figure out what is really going on really going on. Because does any of this really make sense Now, we may be 100 200 500,000 years away from being able to poke our way out of whatever is going on. But it's interesting that we could even stay in aspiration to say we want to poke at this question. But I'd say in this moment of time, the meaning of life is that we can build a future state of existence that is more fantastic than anything we could ever imagine. </s><s>[INST] The striving for something more amazing. [/INST] And that defies expectations that we would consider bewildering and all the things that that that and I guess the last thing, if there's millions of life, it would be infinite Games. You know? James Carse wrote the book finite games. Infinite Games. The only game to play right now is to keep playing the game. And so this goes back to the algorithm of the lexx algorithm of diet soda and brisket and pursuing the passion. I'm what I'm suggesting is there's a there's a moment here where we can contemplate playing infinite games. Therefore it may make sense to err on the side of making sure one is in a situation to be playing infinite games. If that opportunity arises. So just the landscape of possibilities changing very, very fast and therefore our old algorithms of how we might assess risk assessment of what things we might pursue and why those assumptions may fall away very quickly. </s><s>[INST] Well, I think I speak for a lot of people when I say that the game you mr brian johnson have been playing is quite incredible. Thank you so much for talking today. Thanks lex. Thanks for listening to this conversation with brian johnson and thank you too for stigmatic net suite Graham early and express VPN. Check them out in the description to support this podcast. And now let me leave you with the words from Diane Ackerman. Our brain is a crowded chemistry lab bustling with nonstop neural conversations. Thank you for listening and hope to see you next time. [/INST] </s> |
<s>[INST] space, the meeting them in person. Like for me it was a magical moment that I can't as a life transforming. That I recently met spot many from boston dynamics, I don't know why but on a human robot interaction for some reason I realized how easy it is to anthropomorphize and it was, I don't know it was it was almost like falling in love with this feeling of meeting and I've obviously seen these robots a lot on video and so on. But meeting in person just having that one on one time it's different. So have you had a robot like that in your life that was made you maybe fall in love with robotics sort of like meeting in person. [/INST] I mean I mean I loved robotics and yeah, so that was a 12 year old like I'm gonna be a roboticist actually was I called it cybernetics but so my my motivation was bionic woman, I don't know if you know that. Um and so I mean that was like a seminal moment but I didn't make like that was tv right, like it wasn't like I was in the same space and I met I was like oh my gosh, you're like real </s><s>[INST] just lingering on bionic woman, which by the way, because I read that about you, uh I watched a bit, bit of it and it's just so no offense terrible. It's [/INST] cheesy. Now I've seen a couple of reruns lately </s><s>[INST] but it's but of course at the time was probably captured the imagination. It especially when when you're younger just catch you. But what's your aspect, did you think of it? You mentioned cybernetics. Did you think of it as robotics or did you think of it as almost constructing artificial beings? Like is it the intelligent part that that captured your fascination? Or was it the whole thing? Like even just the limbs and [/INST] just so for me it would have in another world I probably would have been more of a biomedical engineer because what fascinated me was the bionic was the parts like the bionic parts, the limbs. Um those aspects of it, </s><s>[INST] are you especially drawn to humanoid or human like robots? [/INST] I would say human like not humanoid, right? And when I say human, like I think it's this aspect of that interaction whether it's social and it's like a dog, right? Like that's human like because it's understand us and interacts with us at that very social level um to you know human noise are part of that but only if they interact with us as if we are human </s><s>[INST] but just to linger on Nasa for a little bit. Uh what do you think? Maybe if you have other memories but also what do you think is the future of robots in space? We mentioned how but there's incredible robots and Nasa is working on in general thinking about in our as we venture out human civilization ventures out into space. What do you think the future robots is there? [/INST] Yeah so I mean there's a near term for example they just announced the uh the rover that's going to the moon which you know that's kind of exciting but that's like near term. You know my favorite favorite favorite series Star trek right? You know I really hope and even star trek like if I calculate the years I wouldn't be alive but I would really really love to be in that world Like even if it's just at the beginning like you know like voyage like Adventure one. </s><s>[INST] So basically living in space. [/INST] Yeah </s><s>[INST] with what robots what robots [/INST] data what role the data would have to be even though that wasn't you know that was like later. </s><s>[INST] So data is a robot that has human like qualities [/INST] without the emotion ship </s><s>[INST] you don't like emotion [/INST] well so data with the emotion ship was kind of a mess. Right? It took a while for for that him to adapt. Um But and and so why was that an issue? The issue is is that emotions make us irrational agents. That's the problem. And yet he could think through things even if it was based on an emotional scenario right? Based on pros and cons. But as soon as you made him emotional one of the metrics he used for evaluation was his own emotions not people around him. Right? Like and so </s><s>[INST] we do that as Children. Right? So we're very egocentric when [/INST] we're very </s><s>[INST] egocentric. And so isn't that just an early version of the emotion ship then? I haven't watched much star trek [/INST] except I have also met adults. Um. Right and so that is that is a developmental process. And um I'm sure there's a bunch of psychologists that can go through like you can have a six year old adult who has the emotional maturity of a 10 year old. Right. And so there's various phases that people should go through in order to evolve? And sometimes you don't. </s><s>[INST] So how much psychology do you think a topic that's rarely mentioned robotics? But how much does psychology come to play when you're talking about Hr I human robot interaction when you have to have robots that actually interact with [/INST] you. So we like my group as well as I read a lot in the cognitive science literature as well as the psychology literature because they understand a lot about human human relations and developmental milestones and things like that. Um And so we tend to look to see what what's been done out there. Um Sometimes what we'll do is we'll try to match that to see is that human human relationship the same as human robot? Sometimes it is and sometimes it's different and then when it's different we have to we try to figure out okay why is it different in this scenario? But it's the same in the other scenario. Right? And so we try to do that quite a bit. </s> |
<s>[INST] and that was the first step towards the human. [/INST] That was the first step. And of course they were very particular kind of humans, business people, but it's different. So they got cobalt instead and etcetera etcetera and similar came out. No, let's not go to simulate yet. Let's go to alcohol. FORTRAN didn't have at the time the notions of not a precise notion of type, not a precise notion of scope, not a set of translation faces. That was what we have today. Mexico syntax semantics, it was sort of a bit of a model in the early days. But hey, they had just done the biggest breakthrough in the history of programming, right? So you can't criticize them for not having gotten all the technical details right? So we got alcohol that was very pretty and most people in commerce and science considered it useless because it was not flexible enough and it wasn't efficient enough and etcetera etcetera. But that was a breakthrough from a technical point of view. Then similar came along to make that idea more flexible and you can define your own types. And that's where I got very interested christ in. You go, who is the main idea man behind? Similar. </s><s>[INST] That was late 60s, [/INST] This was late 60s, was a visiting professor in uh, Ohs. And so I learned object oriented programming by sitting around and well in theory discussing with a snuggle butt based and once you get started and in full flow is very hard to get a word in edge ways where you just listen. So uh it was great. I learned it from there </s><s>[INST] not to romanticize the notion, but it seems like a big leap to think about object oriented programming. It's really a leap of abstraction. Yes. And was that as uh big and beautiful of a leap as it seems from now in retrospect or was it an obvious one at the time? [/INST] It was not obvious. And many people have tried to do something like that and most people didn't come up with something as wonderful as similar. Lots of people got their phds and made their careers out of forgetting about similar are never knowing it for for me, the key idea was basically I could get my own types and that's the idea that goes further into C plus plus, where I can get better types and more flexible types and more efficient types. But it's the fundamental idea when I want to write a program, I want to write it with my types that is appropriate to my problem. And under the constraints that I'm under with hardware, software, environment, etcetera. And that's that's the key idea. People picked up on the class hierarchies and the virtual functions and the inheritance and that was only part of it. It was an interesting and major part and still a major part in a lot of graphic stuff, but it was not the most fundamental. It was when you wanted to relate one type to another, you don't want them all to be independent. The classical example is that you don't actually want to write uh, city simulation with vehicles where you say, well, if it's a bicycle to write the code for turning a bicycle to the left, if it's a normal car, turn right, the normal car way, if it's a fire engines and write the fire and in way that are that are about you get these big case statements bunches of if statements such instead you tell the base class that that's the vehicle um, saying turn, turn left the way you want to. And this is actually a real example. They used it to simulate um, and optimize the emergency, the emergency services for somewhere Norway Uh back in the 60s. So this was one of the early examples for why you needed inheritance and you needed a runtime polymorphism. Because you wanted to handle this set of vehicles in a manageable way. You can't just rewrite your code each time a new kind of vehicle comes along. </s><s>[INST] Yeah, that's a beautiful, powerful idea. And of course it stretches through your work. You C Plus plus as we'll talk about. But I think you've structured nicely. Uh what other breakthroughs came along in the history of programming languages. If we were to tell the history in that way, [/INST] obviously, I'm better telling the part of the history that is the path. I'm one as opposed to to all the paths you </s><s>[INST] skip the hippie uh john McCarthy and this is one of my favorite languages. [/INST] But listen, but listen, it's not one of my favorite languages. Yes, it's obviously important. It's obviously interesting. Lots of people write code in it and then they rewrite it into C. S. C plus plus when they want to go to production. It's in the world I met which are constrained by performance, reliability, um, issues, deploy, ability, cost of hardware. Um, I, I don't like things to be too dynamic. It is really hard to write a piece of code that's perfectly flexible that you can also deploy on a small computer and that you can also put in say a telephone switch in bogota. What's the chance if you get an error and you find yourself in the debug that the telephone switch in bogota on late sunday night has a programmer around right there chances cyril. And so a lot of things I think most about can't afford that flexibility. I'm quite aware that maybe 70, of all code are not under the kind of constraints I'm interested in, but somebody has to do the job I'm doing because you have to get from these high level flexible languages to the hardware. </s> |
<s>[INST] No, you want, no, no, from the audience, but in an interesting way. [/INST] Random, sufficient, so random amongst good choices. Couldn't you have people just like submit a form and then you just randomize it and then select one? And then if it's terrible, you just go randomize it again. Like the first not terrible option. Yeah, sure. </s><s>[INST] Somebody's like drown yourself. But I feel like then it's no longer random. You kind of want to do random, you just do it and just do it like across the world somewhere in some random place. [/INST] Just for like a single event, for like a dinner. </s><s>[INST] You got some sort of itch in you. Well, yeah, I mean, yeah, the itch to live. Sometimes it's nice to drop a little like chaos into a thing, right? What's your chaos survey, by the way? [/INST] Like you mentioned that earlier, I kind of saw it. Yeah, that's one of like the sort of artistic attempts at a survey, because, you know, like at least from what I understand the big five and the way that they used to do IQ tests, I've heard is that they do factor analysis. You know, where they ask a whole bunch of questions and then they run calculations on the data to like sort of group it by organic clusters. So like with the big five, it's like people who say, oh, I like to be at parties. They also tend to say yes to the questions, like I like being the center of attention. And so you notice that, like, there's a cluster of ways people are answering the question and then you can sort of pull out an organic spectrum. And so I was like, okay, we've done that a whole bunch with things like personality or like romantic stuff. Like I did it with the rape spectrum survey, but like what happens if you apply that method to a completely unselected group of questions? Just like no random chaotic, no thing whatsoever. Like what happens if you ask all possible questions, what natural things evolve out of that natural spectrums? So I had other people submit questions for a very large survey and I took the first, I think 1100 and barely filter them at all. </s><s>[INST] And then I just had a whole bunch of people answer them. Well, can you give like a hint to what it looks like? [/INST] Like what, like how crazy did the question get? I mean, a lot of them were standard, but somebody was like if Beyazabab like did something in 1512 to like turn the world over, would you, would you like it? I don't know. I say it was really just insane questions. There's a couple of those. A lot of like, would you fuck Ayla ones? But I don't know, this was all across the spectrum. A lot of them, would you fuck Ayla? Yeah, I had to. But just do like. Oh, this is all across spectrum. A lot, would you fuck Ayla? Yeah, I had to. </s><s>[INST] Oh, a lot of the same question. Just do like. A lot of the same question. Yeah. Ones, okay, I gotcha. [/INST] Yes, yeah. I gotcha. Ones, okay, I gotcha. Yeah, so it's really all, it was like normal personal habits. It was you know, romantic preferences or political preferences, personality stuff, </s><s>[INST] like random opinions about media. Okay, that's interesting. I'd love to see those actual questions. But, because your audience probably with really super interesting minds. Okay, you mentioned body count. You said you can answer that one easily. Do you share your body count? Do you know your body count? [/INST] Is there a spreadsheet? </s><s>[INST] There's a spreadsheet, yes. Is it Google Sheets, is it Excel? Yeah. Okay, you don't have to share the contents, [/INST] but is there data on each, is it Excel? Is it Google sheets, yeah. So I track paid clients and free sex separately. And I track different things on either of them. Like with clients, I track like positions we used and who had an orgasm. And with personal people, I just track basically like age, city, you know, name. And I've had sex with like 42 people, I think, for free. So I'm sharing this because I want people to calibrate. Like it's not like huge, it's not like tiny. </s><s>[INST] It's like I want people- One of the people I've recently talked to, Mel, Destiny's, Stephen's wife is a huge fan of yours. She was actually really excited to get to talk to you. But I think she said her body count is more than 42. I think she said 60, something like this. And so it's interesting. Cause she was like saying like, she loves like looking at your work, talking to you because you have similar perspectives on the world and it's really refreshing, it's liberating. [/INST] Wow. </s><s>[INST] That's really sweet. It's kind of interesting. So is there like an optimal body count? If you were to map, I wonder, yeah, what have you found out about body count in doing? Have you actually done surveys on body count? [/INST] Like on how many people have had sex with? Yeah, I actually have collected that information on my last survey. I just haven't looked at it yet. There's just so many things to look at. So I haven't. But I think if I'm sleeping with a guy and he's had sex with more than 120 people, then I start to get a little bit wary. Yeah, 120 as opposed to 100. I don't know. I just like kind of skimmed through the numbers in my head </s><s>[INST] and picked one that felt right. Just now. Yeah. [/INST] 120. Yeah, ish. I think that's when I'm starting to like. </s><s>[INST] Ish, ish. So you're flexible. [/INST] I am flexible, I am flexible, very, very. But 200 is a hard line for sure. </s><s>[INST] Well, it's, you know, we have to. [/INST] Depends, the factors. Cause like there's a level of body count at which you start to wonder if how much like </s> |
<s>[INST] but it's possible that that would be a sign that you could separate the environment from the basic ingredients. So you can have like a life gun you shoot throughout the universe. And then uh like once you shoot it, things like the Simpsons with the makeup gun, that was a great episode. When you shoot this life gun, he'll he'll find the Earth's, it'll get sticky, it'll stick to the Earth's and that kind of reduces the barrier of like the time it takes the luck it takes to actually from nothing from the basic chemistry, from the basic physics of the universe for the lights to spring up. [/INST] Yeah, I think this is actually super important to just think about like does life getting seated on a planet have to be geo chemically compatible with that planet. So you're suggesting like we could just shoot guns in space and like life could go to mars and then it would just live there and be happy there. Um But that's actually an open question. So, one of the things I was going to say in response to your question about whether the origin of life happened once or multiple times is for me personally right now, in my thinking, all those changes on a weekly basis, but um is that I think of life more as a planetary phenomena. So I think the original life because um because life is so um intimately tied to planetary cycles and planetary processes. And this goes all the way back through the history of our planet. That the origin of life itself grew out of geochemistry and became coupled and controlled geochemistry. And when we start to talk about life existing on the planet is when we have evidence of life actually influencing properties of the planet. Um And so so if life is a planetary property, um then going to MArs is not a trivial thing because you basically have to make ours mars more earth like. Um And so in some sense, um like when I think about sort of long term vision of humans in space, for example, really what you're talking about when when you're saying, let's send our civilization to Mars is you're not saying let's send our civilization on Mars, you're saying let's reproduce our planet on mars, like, the information from our planet actually has to go to MArs and make MArs more earth like, which means that you're now having a reproduction process like a cell reproduces itself. To propagate information in the future, planets have to figure out how to reproduce the conditions including geochemical conditions on other planets in order to actually reproduce life in the universe. Which is kind of a little bit radical. But I think um for long term sustainability of life on the planet that's absolutely essential. </s><s>[INST] Okay, so if we were to think about life as a planetary phenomena. And so life on MArs would be best if it's way different than life on earth. We have to ask the very basic question of what is life. [/INST] I actually don't think that's the right question to ask. It took me a long time to get there right. </s><s>[INST] So yeah, [/INST] you cross it off your list. It's wrong. Uh no, no, no, no. I mean, I think it has an answer, but I think that part of the problem is um, you know, most of the places in science where we get really stuck is because we don't know what questions to ask. Um and so you can't answer a question if you're asking the wrong question. Um and I think uh the way I think about it is obviously I'm interested in what life is, so I'm being a little cheeky when I say that's the wrong question to ask, That's exactly like the question that's like the core of my existence. But um but I think the way of framing that is what is it about our universe that allows features that we associate life to be there. Um and so really what I guess what I'm asking that question, what I'm after is an explanatory framework for what life is, right? And so most people, they try to go in and define life and they say, well, life is uh say as self reproducing chemical system capable of Darwinian evolution. That's a very popular definition for life um or life is something that metabolizes and eats um that is not how I think about life, what I think about life is there are principles and laws that govern our universe um that we don't understand yet um that have something to do with how information interacts with the physical world. I don't know exactly what I mean, even when I say that, because we don't know these rules, um but it's a little bit like um I like to use analogies, give me time to be like a little long winded for a second even in as I um but um but sort of like if you look at the history of physics, for example, this is like, so we are in the period of the development of thought on our planet where we don't understand what we are yet. Right. Um There was a period of thought in the history of our planet where we didn't understand what gravity was. Um and we didn't understand, for example, the planets in the heavens. You know, we're actually planets or that they operated by the same laws that we did. Um and so there has been this sort of progression of getting a deeper understanding of explaining basic phenomena, like I'm not gonna drop the cup, I'll drop the water bottle, you go, okay, that fell right, but why did that fall? Um This is why I'm a theorist not experiments. </s><s>[INST] I could have gone wrong in so many ways. Kind [/INST] especially to the confidence </s> |
<s>[INST] I mean, everything. Everything. I wonder what that trade-out discussions are like cause you can't really perfectly plan everything. So, and you always have to have some spare leeway, especially as you're testing new vehicles like Starship. Yeah, margins are important. Yeah, having a margin, giving all the uncertainty that's there. That's really interesting, like how they do those kinds of trade-offs, because they're also rapidly designing and redesigning and re-engineering. And ultimately, you want to give yourself the freedom to constantly innovate, but then through the process of testing, you solidify the thing that can be relied upon, especially if it's a crude mission. Yeah. [/INST] How to do that in a rapid cycle. Yeah, margins are important. Yeah. I remember at some point that NASA, as they're leading up to flying humans for the first time for NASA, you know, there's some talk that like, we're gonna do a design freeze, because SpaceX does evolve and iterate so quickly. You know, they were saying that it was leading, because especially at the time, it was a mission called AMOS 6, and they lost a rocket. They only lost two rockets, like ever really, as far as trying to get something to space, for the Falcon 9, sorry. And the second one, AMOS 6, I mean, that was back in 2016, so it's been a long time. And, but at the time, they're looking at flying humans in the near future. And it's like, if you guys keep tweaking this thing every time you take it out to the pad, well, there's gonna be a problem, you know? And so there is some pressure from NASA to kind of slow down on that iterative process. And, but that is also why they were able to evolve the Falcon 9 to be what it is today, is because they did just evolve it so quickly. Literally like one after another was never really the same. And we're definitely seeing that with Starship now, like it's evolved so quickly that you just can't even keep up with it, you know? </s><s>[INST] So there's a fascinating culture clash there. Have you just, in observing and interacting with NASA folks, seen them sort of grow and change and evolve themselves, sort of inspired by this new developments [/INST] in commercial space flight? Oh, yeah, yeah, yeah. There's a lot of, especially like around DM2, there's a lot of talks in the press conferences and stuff where you'd hear people say, you know, this was a big, this is well outside of our comfort zone to work with SpaceX in this manner, because we take this approach to things, we're X, Y, and Z in this way, the way we normally certify things. And we're not used to SpaceX, like, well, let's just try it, you know? Like, and do something, you know, to a point. And so they said it ended up being fantastic. They loved working that way because it was just less paperwork almost and more just do. And, but at the same time, SpaceX, I think, even expressed, I don't remember if it was Hans Königsmann or someone in a press conference said, well, we really liked having someone just double check us so that we're not doing something super stupid right before we test something, you know? So there was a cool collaboration because it is two very different philosophies of development and managing, you know, space programs. </s><s>[INST] I wanted to talk to you a lot about engines and maybe about Starship and maybe about your own becoming an actual astronaut. But like, let's just go there before all that and talk about the actual culture of SpaceX and your conversations with Elon. You've toured SpaceX facilities with him. You've interviewed him. You've interacted with him. What have you learned about rockets, about propulsion, about engineering, about design, about life from those interactions? He's pretty transparent, open human being [/INST] as an engineer, as a leader, as a person. I would definitely say the biggest takeaway I've had from my times with Elon at SpaceX is really, like, the idea of questioning your constraints. He says that a lot, but he also does it a lot. Like, there'll be times where, like, you'll see him change on a dime because he's, like, rethinking of something in a newer, different way. And for me, I think we all put constraints on ourselves. We think about our own limits on things that we can or cannot do. And I think it's made me kind of question, like, well, why am I, why did I say, no, I can't do that? Or, you know, just off the top of my head. A good example. Yeah, I, so in Iowa, I live in Iowa or half the time, or whatever, there's a bike ride across the state of Iowa called RAGBRIE. And every year, you just, you know, like thousands of people get together and they ride across to Iowa. And there was the last summer, I met up with some friends and like, hey, you don't wanna go on RAGBRIE this year. I'm like, it's like a week away. And so I did, you know? And it was one of those moments where I was proud of myself cause, like, it's easy to just be like, no, you know, I'm not ready this is my constraint, it's like I'm not in shape, but like just question that, you know? And so I think when it comes down to questioning your own constraints, it's yes, even to that level of like, why do you question yourself </s> |
<s>[INST] I I believe so as well. The thing is in the short term freedom of speech, absolute freedom of speech can be quite destructive, but you nevertheless have to hold on to that because in the long term, I think you and I guess are optimistic in the sense that good ideas will win out. [/INST] I don't know how strongly I believe that it will work, but I will say I haven't heard a better idea. Yeah. Um I would also point out that there's something very significant in this question of the hubris involved in imagining that you're going to improve the discussion by censoring, which is the majority of concepts that the fringe are nonsense, that's automatic. But the heterodox e at the Fringe which is indistinguishable at the beginning from the nonsense ideas is the key to progress. So if you decide, Hey, the fringes 99% garbage, let's just get rid of it. Right? Hey, that's a strong wind. We're getting rid of 99% garbage for 1% something or other. And the point is, yeah, but that 1% something or other is the key you're throwing out the key. And so that's what youtube is doing frankly. I think at the point that it started censoring my channel, you know, in the immediate aftermath of this major reversal of lap for lab leak, It should have looked at itself and said, well what the hell are we doing? Who are we censoring for sensory? Somebody who was just right right in a conflict with the very same people on whose behalf we are now censoring right, That should have caused them to wake up. </s><s>[INST] So he said, one approach, if you're on YouTube is just basically let all videos go that do not violate the [/INST] law, I should fix that. Okay, I believe that that is the basic principle eric makes an excellent point about the distinction between ideas and personal attacks, doxing these other things. So I agree there's no value in allowing people to destroy each other's lives, even if there's a technical legal defense for it now, how you draw that line. I don't know. But you know what I'm talking about is yes, people should be free to traffic and bad ideas and they should be free to expose that the ideas are bad and hopefully that process results in better ideas winning </s><s>[INST] out. Yeah. There's an interesting line between, you know, like ideas like the earth is flat, which I believe you should not censor and then like you start to encroach on like personal attacks. So not not, you know, doc saying yes, but like not even getting to that. Like there's a certain point where it's like, that's no longer ideas that's more that somehow not productive. Even if it feels like believing the earth is flat, it's somehow productive because maybe a [/INST] tiny percent chance it </s><s>[INST] is. You know, like it just feels like personal attacks. It doesn't uh well, you know, it's, I'm torn on this because there's assholes in this world is fraudulent people in this world. So sometimes personal attacks are useful to reveal that. Um but there's a line you can cross, like there's a comedy where people make fun of others. I think that's amazing. That's very powerful. That's very useful. Even if it's painful. But then there's like when it gets to be um yeah, there's a certain line, it's a gray area where you cross where it's no longer in any possible world productive and that's a really weird gray area for youtube to operate in and it feels like it should be a crowdsourced thing where people vote on it. But then again, do you trust the majority to vote on what is crossing the line and not? I mean, this is where this is really interesting on this particular, like the scientific aspect of this. Do you think Youtube should take more of a stance, not censoring, but to actually have scientists within Youtube having these kinds of discussions and then be able to almost speak out in a transparent way. This is what we're going to let this video stand. But here's all these other opinions, almost like take a more active role in its recommendation system in trying to present a full picture to you right now. They're not, they're recommended systems are not human. Fine tuned. They're all based on how you click and there's this clustering algorithms, they're not taking an active role on giving you the full spectrum of ideas in the space of science. They just sense or not. Well [/INST] at the moment it's going to be pretty hard to compel me that these people should be trusted with any sort of curation or comment on matters of evidence because they have demonstrated that they are incapable of doing it well. Um, you could make such an argument and I guess I'm open to the idea of institutions that would look something like youtube that would be capable of offering something valuable, I mean, and you know, even just the fact of them literally curating things and putting some videos next to others, you know, implies something. So yeah, there's a question to be answered. But at the moment, no, at the moment, what it is doing is quite literally putting not only individual humans in tremendous jeopardy by censoring discussion of useful tools and making tools that are more hazardous than has been acknowledged seems safe. Right. But it is also placing humanity in danger of a permanent relationship with this pathogen. I cannot emphasize enough how expensive that is. It's effectively incalculable if the relationship becomes permanent, the number of people who will ultimately suffer and die from it is indefinitely large. </s> |
<s>[INST] the following is a conversation with Andrew bustamante former CIA covert intelligence officer and U. S. Air Force combat veteran including the job of operational targeting, encrypted communications and launch operations for 200 nuclear intercontinental ballistic missiles. Andrews over seven years as a C. I. A spy have given him a skill set and a perspective on the world that is fascinating to [/INST] explore. </s><s>[INST] And now a quick few second mention of each sponsor. Check them out in the description is the best way to support this podcast. We got Wealthfront for savings [/INST] element </s><s>[INST] for hydration, better help for mental health Express. VPN for privacy and master class for intellectual inspiration, choose wisely my [/INST] friends and </s><s>[INST] now onto the full ad reads never any ads in the middle. I hate those and the ads I do here up front. [/INST] I do try </s><s>[INST] to make interesting but if you must skip them to your friends please still check out the sponsors. I enjoy their stuff. Maybe you will too. This show is brought to you by a new sponsor called Wealthfront. They do savings and automated investing accounts to help you build wealth and save for the future. It's a beautifully designed and streamlined interface. It's honestly really surprising to me how many financial institutions [/INST] of all kinds </s><s>[INST] on the internet don't have a good interface. It's clunky. I don't understand it. They're taking your money. Obviously it should be frictionless to move your money around anyway. I think I have a lot of trouble with companies that don't do a good job with the interface and Wealthfront does a good job with that. I think it's very important to save for the future [/INST] from </s><s>[INST] a stoic perspective, you should consider that you can die any day now, but from a financial perspective you should consider that if you're lucky, you're gonna live for quite a long time and in that case you want to invest into your [/INST] future, </s><s>[INST] nearly half a million people use Wealthfront. You can go check them out at Wealthfront dot com slash lex and you'll get a $50 bonus with a $500 deposit. This episode is also brought to you by element electrolyte drink mix spelled L M N. T. I really love element, it's one of the things that really brings joy to my day. I drink, I don't know how many, Maybe 5, 6 element packets a day. [/INST] So </s><s>[INST] for low carb diets, all that kind of stuff, it's essential to get sodium, potassium, magnesium and they have a really nice balance of that. I think watermelon salt is the one I go to to just feel refreshed to make my water go down in a way where I really enjoy it. It's the thing that makes all the fast thing I do and if I do carnivore diet or keto diet, it's the thing that makes that really enjoyable and easy. [/INST] Never </s><s>[INST] any headaches, never knew that [/INST] kind of stuff. It's </s><s>[INST] the thing I drink before and this thing I drink after to feel refreshed and to make sure I have enough electrolytes in my system to handle the 10 12 13 15 mile runs that I do in the insane heat of Austin. Get a sample pack for free with any purchase when you go to drink element dot com slash [/INST] flex. </s><s>[INST] This episode is also brought to you by better help spelled H E L P help. They figure out what you need a match with a licensed professional therapist in under 48 [/INST] hours. </s><s>[INST] I recently had an offline conversation with Duncan Trussell. I got a chance to meet him. I'm such a huge fan of Duncan, he's such a beautiful person, he's such a sweetheart. He's both hilarious and kind [/INST] but also </s><s>[INST] is willing to go to the wildest ideas and not just for a little bit [/INST] but a full </s><s>[INST] journey through the wildest possible ideas. It's like I feel like Alice in wonderland every time I [/INST] talk to him </s><s>[INST] anyway we've talked about his time with depression and and the value of therapy. [/INST] It </s><s>[INST] really is something [/INST] especially </s><s>[INST] in your darker moments in life that can really, really help. And it could also help to help avoid those darker [/INST] moments. So </s><s>[INST] it's definitely something you should consider check out better help at better help dot com slash lex and save on your first [/INST] month. </s><s>[INST] This show is also brought to you by express VPN. I've used them for many years primarily because they have a big sexy button that I can press and it can do. The thing is supposed to do and that kind of thing is like the easy button. That kind of thing brings joy to my O C. D [/INST] heart that </s><s>[INST] there are software services out there that do a thing and do it well. But I also use it to protect my privacy on the internet, Make sure that SPS can't collect all of my data even when I go to shady websites, which of course I never, ever [/INST] do </s><s>[INST] in incognito mode in chrome. [/INST] The </s><s>[INST] thing also works super [/INST] fast, which is really, </s><s>[INST] really important on any operating system including Linux. It also works on android [/INST] iphone anything </s><s>[INST] you could imagine, any operating system that I at least know of. It works. It's super [/INST] fast. You can </s><s>[INST] use it to watch shows that are geographically constrained on netflix and other such services, [/INST] I encourage </s><s>[INST] you to go to express VPN dot com slash flex pod to get an extra three months free. This show is also brought to you by Master Class $180 a [/INST] year gets </s><s>[INST] you an all access pass to watch courses from the best people in the world, in the respective disciplines. The list of people is just insane from chris Hadfield who I really need to [/INST] talk to soon. </s><s>[INST] I've been trying to talk to him. We agreed to talk. We just haven't been able to make it happen, [/INST] but </s> |
<s>[INST] of the [/INST] best podcasters are ones where when you're on my side of the table, you feel like it's more of a conversation and less like an interview where you're answering all the same questions you've asked, you've answered a million times before. It's really interesting how different the experiences </s><s>[INST] and you're right, the uh the audio thing um if you can lose yourself in that, the intimacy of that and you don't even remember what stupid stuff you [/INST] said </s><s>[INST] people, I've seen that. I mean people don't give them enough credit as um you might, you might not be aware might not be a fan, but joe Rogan is a incredible conversationalist in that he makes you forget that anything is being recorded, that you're talking at all. It makes you forget time and you just enjoy yourself and that's whatever that is. Um and that plugs then you plug into that primal connection to other humans. What's your favorite Leonard Cohen song? [/INST] Famous Blue raincoat? Do you know that </s><s>[INST] one? [/INST] Yeah. </s><s>[INST] For people [/INST] who don't know Leonard Cohen, and this is your first introduction to him. It's gonna sound so gloomy, but it's so good. </s><s>[INST] He's got this deep, rich voice Tory most covering famous Blue in Korea. No, we want what the original, just like Hallelujah, Jeff buckley covered Leonard Cohen. That was a really good one. [/INST] That was a really good one. Yeah. And I also really like Rufus Wainwright's cover um but famous blue raincoat for people who don't know it it's basically about a love triangle and it's told from the perspective of a man whose wife has just been with another guy who is also his friend and he's writing a letter to that other guy and and he's reflecting on the way that all the relationships have changed in the wake of this this event. So they're still well, he he refers to him as my brother, my killer, which is such a Leonard cohen thing to do because it's always like, you know, it's light and it's dark all at once. Nothing is ever all one thing. Yeah, </s><s>[INST] I love this song. [/INST] Yeah, right. I mean, he </s><s>[INST] just speaks in the end of december, [/INST] The fact that it's 4:00 AM and it's the end of December. Those are transitional moments. It's night going in today </s><s>[INST] and [/INST] it's december going into the new Year. </s><s>[INST] It's [/INST] not an </s><s>[INST] accident. There's something about december. This, whatever there's certain scenes you can paint in your mind. Um there's a there's a poem by Charles Bukowski called Nirvana. It's a young man traveling through the middle of nowhere in the snow. There's something about the snow and the rain or the [/INST] snow can </s><s>[INST] put you in a certain kind of mood. That just uh what is it? James, Joyce's the dead, The snow is falling and Dublin. Yeah, I [/INST] mean, David Yaden who's a he's a researcher and psychedelics and consciousness at johns Hopkins. He's a great guy and he's done research that has found that when people are in their transitional moments of life, you know, and it could be a career change, it could be a divorce, it could be that they're nearing the end of their life, that they very often will say those are their most meaningful moments and their most spiritual moments. And so I feel like that's what Leonard Cohen knows how to tap into instinctively. The year after he died, his son Adam Cohen made a memorial concert for him where all these famous musicians came to Montreal where they had lived um and performed his music. And my husband who's not a Leonard Cohen fan and he's not a bittersweet type at all, but he knows how I feel about him. He's like, you know, you should really go to that concert. I felt so ridiculous. The whole family went all the way to Montreal on a monday monday. It was just like a random monday. And we got on the plane, like, so like everyone's out of school, just so I can go to this concert and and I got there and at the beginning I was feeling like this was all a terrible mistake because it's all these other musicians playing this music and I don't actually really want to hear them. Like I'd rather listen to him on Youtube and then and then a musician named Damien Rice came and played famous blue raincoat and he's saying it and he, he did the most amazing thing at the end, the whole thing was amazing. But then at the end he sang this musical riff that was like all I could say is it was like a musical lamentation of the ages and the whole audience just rose silently to its feet and it was one of the greatest moments that I've ever had. There is sometimes </s><s>[INST] certain artists in a cover can capture in some kind of deeper way like carrying the thread of the power of the song. So been listening a lot to johnny cash Heart which is a nine inch nails [/INST] you talked about on your podcast with rick Rubin </s><s>[INST] which is when I reached [/INST] out to you. Like I love that interview and I love that song also. </s><s>[INST] Yeah, yeah, yeah. So there's, there's that, there's the Kennedy center honors where they, they celebrated certain artists that did that for led Zeppelin and I forgot what her name is but the lead singer of heart um perform stairway to [/INST] heaven. And </s> |
<s>[INST] You are much less constrained. You are much less constrained. What's the purpose to remove constraints? Is it the escape from the harshness of the constraints of the real world or is it just remove constraints in order to explore some N getting deeper understanding of our world. What is it? I mean, why do people reach that? [/INST] I'm not a cheap fantasy reading kind of person. One story that it sounds plausible to me is that there are sort of these deep story structures that we love and we want to realize and then many details of the world getting their way. Fantasy takes all those obstacles out of the way and lets you tell the essential hero story or the essential love story, whatever essential story you want to tell. The reality and constraints are not in the way. And so science fiction can be thought of as like fantasy, except you're not willing to admit that it can't be true. So the future gives the excuse of saying, well, it could happen. And you accept some more reality constraints for the </s><s>[INST] illusion at least that maybe it could really happen. Maybe it could happen and that stimulates the imagination. The imagination is something really interesting about human beings. And it seems also to be an important part of creating really special things is to be able to first imagine them. With you and Nick Bostrom, where do you land on the simulation and all the mathematical ways of thinking it and just the thought experiment of it? Are we living in a simulation? [/INST] That was the just discussion we just had. That is, you should grant the possibility of being a simulation. You shouldn't be 100% confident that you're not. You should certainly grant a small probability. The question is, how large is that probability? </s><s>[INST] Oh, you're saying we would be misunderstood because I thought our discussion was about replaying things that already happened. [/INST] Right. But the whole question is, right now, is that what I am? Am I actually a replay from some distant future? </s><s>[INST] But it doesn't necessarily need to be a replay. It could be a totally new. You don't have to be an NPC. [/INST] Right. But clearly, I'm in a certain era with a certain kind of world around me. So either this </s><s>[INST] is a complete fantasy or it's a past of somebody else in the future. No. It could be a complete fantasy, though. [/INST] It could be, right? But then you have to talk about what's the fraction of complete fantasies. </s><s>[INST] I would say it's easy to generate a fantasy than to replay a memory, right? [/INST] Oh, but the fraction. We just look at the entire history of everything. Sure. We just say, but most things are real. Most things aren't fantasies. Therefore, the chance that my thing is real. So the simulation argument works stronger about sort of the past. We say, ah, but there's more future people than there are today. So you being in the past of the future makes you special relative to them, which makes you more likely to be in a simulation, right? If we're just taking the full count and saying in all creatures ever, what percentage are in simulations? Probably no more than 10%. </s><s>[INST] See, so what's the good argument for that? That most things are real. Yeah. Because it was Boston who says the other way, right? [/INST] Yeah. Because it was in a competitive world, in a world where people like have to work and have to get things done, then they have a limited budget for leisure. And so, you know, leisure things are less common than work things, like real things, right? That, that, that's just. </s><s>[INST] But if you look at the stretch of history in the universe, doesn't the ratio of leisure increase? [/INST] Isn't that what we, isn't that the for doing, isn't that the for? Now, we're looking at the fraction of leisure, which takes the form of something where the person doing the leisure doesn't realize it. Now there can be some fraction of that? That's much smaller, right? Yeah. Clue as four years or somebody is clueless in the process of supporting this, this leisure, right? It might not be the person leisurering somebody there, a supporting character or something, but still, that's got to be a pretty small fraction of leisure. </s><s>[INST] What you mentioned, the children, are one of the things that things that are a source of meaning, broadly speaking. Then let me ask the big question. What's the meaning of this whole thing? The Robin, meaning of life. What is the meaning of life? We talked about alien civilizations, but this is the one we got. Where are the aliens? Where are the human? Seem to be conscious, be able to introspect. What's, why are we here? [/INST] Why are we here? This is the thing I told you before about how we can predict that future creatures will be different from us. We, our preferences are this amalgam of various sorts of random sort of patched together preferences about thirst and sex and sleep and attention and all these sorts of things. So we don't understand that very well. It's not very transparent and it's a mess, right? That is the source of our motivation. That is how we were made and how we are induced to do things. But we can't summarize it very well and we don't even understand it very well. That's who we are. And often we find ourselves in a situation where we don't feel very motivated. We don't know why. In other situations we find ourselves very motivated and we don't know why either. And so that's the nature of being a human of the sort that we are, because even though we can think abstractly and reason abstractly, this package of motivations is just opaque and a mess. And that's what it means to be a human today and the motivation. We can't very well tell the meaning of our life. It is this mess that our descendants will be different. They will actually know exactly what they want. And it will be to have more descendants. That will be the meaning for that. </s> |
<s>[INST] Please don't. I I understand this. It's not woo woo. I'm not. We could but it very well could be there could be something at the at the physics level, right? It could be at the chemical, at the biological level things that are happening that we're just close too close minded. Because our conception of life is at the level of like us, like at the jungle level of mammals and on the time scale. That's the human time scale. We may not be able to perceive what alien life is actually like. Uh the scale at which their intelligence realizes itself when we're not able to perceive. And the other thing that's really important about alien visitations whether it happened or not is especially after Covid in 2020 I'm losing a little bit of faith of our government being able to handle that. That well not our government, but us as a society, as a collective, being able to deal with new things in an effective way that's inspiring. That's efficient. That uh, like whether it's, if it's a dangerous thing to deal with it to alleviate the danger, whether it's the possibility of new discoveries or something inspiring to ride that wave and make it inspiring all those kinds of things. I honestly think if aliens showed up, they would look around everybody would ignore them and the government might like hide it, try to like see to keep it from the chinese and the Russians. If it's the United States, uh, call it a military secret in a very close minded way. And then the bureaucracy withdrawn it away to where through paperwork, the poor aliens would just waste away in a cell somewhere. Like there's a [/INST] certain not happen. That would never happen. Part of the reason that I feel so confident that aliens have not visited because they would have had to visit just to have a look remotely, you know, from Neptune or something. Which makes no sense because Interstellar travel is so difficult that it would be quite a ridiculous proposition, but that's the bit that I think is technically possible if they did come here and they were visible by anyone detectable by anyone. The thought that any government, no matter or any military could just contain them, these beings are capable of traveling interstellar distances when we can barely go to the moon, like barely go to </s><s>[INST] the [/INST] weight. And the fact that we think are puny a military of any, even if all the military in the world got together and the fact that they could somehow contain its that is trying to contain </s><s>[INST] it visited them. But [/INST] and scientists, you would have to bring scientists on board. You've met a lot of scientists. How good are they keeping secrets? Because in my experience, they're absolutely appalling and keeping secrets. Even the faucet on venus thing, which was a pretty well kept secret. </s><s>[INST] This is true. You had a bunch of people that I [/INST] told my dad, you know, my dad knew and hopefully didn't tell anyone. But if it had been an alien visiting, he probably would have told them mate, you know. And so these secrets could not be kept by any scientists that I know and certainly not collaborative scientists which would be needed. You need all sorts of scientific teams. So between the pathetic power of any world's military compared to any civilization capable of traveling and our absolute inability to keep secrets. Absolutely not. I will bet everything that we have not been visited because we are too pathetic to hold that to hold that truth </s><s>[INST] for making a like a $10 bet the possibility here that the main say there exists one alias of other intelligent alien civilization in the galaxy. Mhm. The to me if they visit earth was going to visit earth is like the crappy like the really crappy short straw like like this this like really dumb thing. That's I don't know like the early game Boys or something. Like [/INST] there's a cartoon about this. There's an alien that gets sent to Earth Commander spit or something and it's kind of a punishment or something. But that's not possible. That's the thing because interstellar distances are so hard to cross. You have to do it on purpose. You have to do on purpose has to be a big big deal. And we know this because yes, you're right. We don't know enough about galactic biology. We don't know what the universal rules of biology or biochemistry are because we only have the Earth. But we do know that the laws of physics are universal. We can predict behavior in the universe and then see it happen based on the laws of physics. We know that the laws of chemistry are universal. We know the periodic table is all they have to choose from. So yes, there may be some sort of unimaginable intelligence but they still have to use the same periodic table that we have access to. They still have a finite number of molecules they can do things with. So they still have to use the resources around them, the stars around them, the universe around them and we know how much energy is in these places. And so yes, they may be very capable capable beyond our wildest dreams, but they're still in the same universe and we know a lot of those rules were not completely blind, </s><s>[INST] but there's a college years at Harvard. Uh Cameron wafa is a theoretical physicist and if you know him, [/INST] I've only joined Harvard about six months ago, </s> |
<s>[INST] So what we're talking about some basic ingredients, maybe we'll talk about that, what those basic ingredients could be and how many steps, when you say shortest path, how many steps it takes to turn those basic ingredients into the final meal. So how to make a pizza, what's the shortest way to make a pizza? Or a pie. An apple pie. That's right. And the pizza and the pie together. Scratch. Yeah. So there's a lot of ways. There's the shortest way and you take the full spectrum of ways and there's probably an average, like duration for a noob to make an apple pie. Is the average interesting still? If you measure the average length of the path to assemble a thing, does that tell you something about the way nature usually [/INST] does it? Or a pie. Or a pie. An apple pie. That's right. And the pizza and the pie together. Scratch. </s><s>[INST] Versus something fundamental about the object, which I think is what you're aiming at with the assembly index. [/INST] Yeah, yeah. I mean, look, we all have to quantify things. The minimum path gives you the lower bounds, you know, you're detecting something, you know, you're inferring something. The average tells you about really how the objects are existing in the ecosystem or the technology. And there has to be more paths explored because then you can happen upon other memories and then condense them down. I'm not making too much sense. But if you look and say, let's just say, I mean, maybe we're going to get to alien civilizations later, right? But I, I would argue very strongly that alien civilization A and alien civilization B, they're different assembly spaces. So they're kind of going to be a bit messed up if they happen to come on another. Only when they find some joint overlap in their technology, because if aliens come to us and we, they don't share any of the causal graph we've showed, but hopefully they share the periodic table and some other bonds and things that we're going to have to really think about the language to talk to us aliens by inferring by using assembly theory to infer the their language, their technology and other bits and bobs. And the shortest path will help you do that quickly. </s><s>[INST] All right. So all all aliens in the causality [/INST] graphs have a common ancestor in the if the building blocks are the same, which means they live in the same universe as us. So it depends </s><s>[INST] on how far back in time you go, though. So in this, it depends on how far back in time you go, though. But the universe has all the same building blocks. Yeah. And like we have to assume that. Yeah. So there's there's not different classes of causality graphs, right? No, the universe doesn't just say like, here, you get the the red causality graph, then you get the blue one, these basic ingredients, and they're geographically constrained or constrained in [/INST] space or time or something like that, right? No, they're constrained in time because only by the virtue of the fact that you need enough time to have passed for some things to exist. So the universe has to be big enough in time for some things. So just the one point on the shortest path versus the average path, which I think we'll get to this is you had a nice way of saying it's like the minimal compression is the shortest path for the universe to produce that. But it's also like the first time in the in ordering of events that you might expect to see that object. But the average path tells you something about the actual steps that were realized. That becomes an emergent property of that object's interaction with other objects. So, it's not an intrinsic feature of that object, it's a feature of the interactions with other things. And so one of the nice features of assembly is you basically have gotten rid of...you just look at the things that exist, and you've gotten rid of the mechanisms for constructing them in some sense like the machines are not as important in the current construction of the theory, although I would like to bridge it to some ideas about constructors. But then you could only communicate with things as Lee was saying if you have some overlap in the past history. So if you had an alien species that had absolutely no overlap, then there would be no means of communication. But as we progress further and further in time and more things become possible because the assembly spaces are larger, because you can have a larger assembly space in terms of index and also just the size of the space because it's exponentially growing, then more things can happen in the future. And the example I like to give is actually when we made first contact with gravitational waves, because that's an alien phenomena that's been permeating our plate, not alien, in life by alien, like something we had never knew existed. There's gravitational waves rippling through this room right now. But we had to advance to the level of Einstein writing down his theory of relativity and then 100 years of technological development to even quote unquote </s><s>[INST] see that phenomena. Okay, to see that phenomena, our causal graph has to start intersecting. [/INST] Yeah, we needed the idea to emerge first the abstraction, right? And then we had to build the technology that could actually observe features of that abstraction. </s><s>[INST] So the nice promising thing is, over time, the graph can grow. So we can start overlapping [/INST] eventually. Yeah, so the interesting feature of that graph is there was an event, you know, 1.4 billion years away of a black hole merger that we detected on our detector. And, you know, now suddenly, we're connected through this communication channel with this distant event in our universe, that you know, if you think about 1.4 billion years ago, what was happening on this planet, or even further back in time, that you know, there's common physics underlying all those events, but even for those two events to communicate, I understand what you were going on about the other week. Yeah, I'm sorry. Great. But yeah, I'm sorry. But but it's your causal graphs are not overlapping. Well, let's just say now, our causal graphs are overlapping in the deep past. You made a connection with it. No, I do like that. No, you can tell me what your epiphany is now. That's good. Because I was, and I should get the jokes before 30 seconds after. Oh, I get it now. Two minutes ago, I wasn't able to comprehend what you're talking about with the channel communicating to the past. But what you're saying is we were able to infer what happened 1.4 billion years ago. We don't take to the gravity wave. I mean, I think it's amazing that, you know, at that time we weren't even, we were just becoming multicellular, right? It's like insane. And then we, we, we progress the multicellular literacy through to technology and build the detector and then for, you know, and then we went to extrapolate backwards. So, so I, although we haven't didn't do anything back to the graph back in time, we understood his existence then overlapped going forward. And that was slow on the uptake. Well, that's because our graphs are larger. Yeah. But that means that has a consequence. One of the things I was trying to say is like, I'm, I'm, I'm, I think, I don't know, Sarah might be, she can correct me, information first. And I'm a object first kind of guy. So I mean, as things that get constructed, there has to be this transition in random constructions so when the constructing, the object that's construct being constructed by the process, bakes in that memory and those memories, then add on and add on and add on. Um, so as it becomes more competent in life is about taking those memories and compressing them increasing their autonomy. And, and so I think that, you know, like the cell that we have in biology on earth is our way of doing that. That really their maximum ability to take memories and to act on the future? Oh, I think that's mathematics. No, mathematics doesn't exist. No, but that's the point, the point is that abstractions do exist, they're real physical things. We call them abstractions, but the point about mathematics that I think is, so I don't disagree that, I think you're object first and I'm information first, but I think I'm I'm only information first, in the sense that I think the thing that we need to explain is why what abstractions are and what they are as physical things because of all of human history we've thought that there were these properties that are disembodied exist outside of the universe and really they do exist in the universe and we just don't understand what their physics is. So I think mathematics is a really good example we do theoretical physics with math but imagine doing physics of math and then thinking about math as a physical object. And math is super interesting. I think this is why we think it describes reality so well, because it's the most copyable kind of information. It retains its properties when you move it between physical media, which means that it's very deep. And so it seems to describe the universe really well, but it probably is because it's information that's very deep in our past. And it's just, we invented a way of communicating it very effectively between us. Isn't math more fundamental, isn't the assembly of the graph, isn't basically, I sound completely boring, it's like math, assembly theory invented math, but it did. It has to be. </s> |
<s>[INST] I guess that's a that's a primal fear of almost almost kind of uh a kind of mortality. So around the time you said you work with it's stanford with Ed Feigenbaum. So let's look at that one person throughout his history. Clearly key person, one of the many in the history of I how has he changed in general, around him? How stanford changed in the last how many years are we talking about [/INST] here since </s><s>[INST] 65 6, 65. So maybe it doesn't have to be about him. It could be bigger. But because he was a key person in expert systems for example, how is that? How are these folks who you've interviewed In the 70s 79 changed through the decades? Mm [/INST] In Ed's case. I know him well. We are dear friends. We see each other every month or so. He told me that when machines who think first came out, he really thought all the front matter was kind of bologna? Mm And 10 years later he said, no, I see what you're getting at. Yes. This is an impulse that has been, this has been a human impulse for thousands of years to create something outside the human cranium that has intelligence. Uh I think it's very hard when you're down at the algorithmic level and you're just trying to make something work which is hard enough. Just step back and think of the big picture. It reminds me of when I was in santa fe, I knew a lot of archaeologists which was a hobby of mine. And I would say, yeah, yeah, well you can look at the shards and say, oh this came from this tribe and this came from this trade route and so on. But what about the big picture? And a very distinguished archaeologist said to me, they don't think that way, you know, they're trying to match the shard to the to where it came from. That's where did this corn remainder of this corn come from? Was it grown here? Was it grown elsewhere? And I think this is part of the ai any scientific field. Uh you're so busy doing the hard work and it is hard work that you don't step back and say, well now let's talk about the, you know </s><s>[INST] the picture meaning of all this. Yes. So none of the even Minsky and McCarthy, they [/INST] owe those guys did. Yeah, the founding fathers did </s><s>[INST] early on or [/INST] pretty early on that they had but in a different way from how I looked at it. The two cognitive psychologists, Newell and Simon, they wanted to imagine reforming cognitive psychology so that we would really, really understand the brain. Minsky was more speculative and john McCarthy saw it as I think I'm doing, doing him right by this. He really saw it as a great boon for human beings to have this technology. And that was reason enough to do it. And he had wonderful, wonderful fables about how if you do the mathematics, you will see that these things are really good for human beings. And if you had a technological objection, he had an answer, a technological answer, but here's how we could get over that and then blah blah blah blah. And one of his favorite things was what he called the literary problem, which of course he presented to me several times that is everything in literature. There are conventions in literature. One of the conventions is that you have uh a villain and a hero and the hero in most literature is human and the villain in most literature is a machine. And he said that's just not the way it's going to be, but that's the way we're used to it. So when we tell stories about ai it's always with this paradigm, I thought yeah, he's right. You know, looking back the classics are you are certainly the machines trying to overthrow the humans. Frankenstein is different Frankenstein is a creature, he never he never has a name. Frankenstein of course is the guy who created him, the human dr Frankenstein. This creature wants to be loved, wants to be accepted. And it is only when Frankenstein turns his head in fact runs the other way and the creature is without love that he becomes the monster that he later becomes. </s><s>[INST] So who's the villain in Frankenstein? It's unclear, [/INST] right? So it is unclear. Yeah. </s><s>[INST] It's really the people who drive him by driving him away, they bring out the worst. [/INST] That's right. They give him no human solace and uh he is driven away. You're right. Uh He becomes at one point the friend of a blind man and they he serves this blind man and they become very friendly. But when the sighted people of the blind man's family commit ah you got a monster here. So it's it's very didactic in its way. And what I didn't know is that mary Shelley and Percy Shelley were great readers of the literature surrounding abolition in the United States, the abolition of slavery and they picked that up wholesale um you know, you are making monsters of these people because you won't give them the respect and love that they deserve. </s><s>[INST] Do you have if we get philosophical for a second, do you worry that once we create machines that are a little bit more intelligent. Let's look at Roomba that vacuums cleaner, that that this darker part of human nature where we abuse uh the other the somebody who's different will come out [/INST] I don't worry about it. I could imagine it happening. Uh But I think that what ai has to offer the human race will be so attractive that yeah people will be won over. </s> |
<s>[INST] How are you testing in general? Just for yourself? Like experiments and stuff. Alright. Uh Where are you? Where are you located in SAN Diego SAN Diego. Okay. Uh What? So you basically drive around there to collect some data and watch? [/INST] we have a simulator now and we have our simulator is really cool. Our simulator is not it's not like a unity based simulator. Our simulator lets us load in real estate. </s><s>[INST] I mean we [/INST] can load in a drive and simulate what the system would have done on the historical </s><s>[INST] data, interesting. So [/INST] right now we're only using it for testing, but as soon as we start using it for training, that's </s><s>[INST] it for testing. What's your feeling about the real world versus simulation? Do you like simulation for training? If if this moves to training? [/INST] So we have to distinguish two types of simulators, right? There's a simulator that like is completely fake. I could get my car to drive around in GT A. Um I feel that this kind of simulator is useless. You're never there's so many. My analogy here is like okay fine, you're not solving the computer vision problem but you're solving the computer graphics problem, </s><s>[INST] right? And you don't think you can get very far by creating ultra realistic [/INST] graphics because you can create ultra realistic graphics of the road now create ultra realistic behavioral models of the other cars. Oh well I'll just use my self driving. No you won't. You need real, you need actual human behavior because that's what you're trying to learn. The driving does not have a speck. The definition of driving is what humans do when they drive whatever Waymo does. I don't think it's driving. </s><s>[INST] Right, Well, I I think actually way more and others, if there's any use for reinforcement learning, I've seen it used quite well. I studied pedestrians allowed to is try to train models from real data of how pedestrians move and try to use reinforcement learning models to make pedestrians moving human like way by [/INST] that point you've already gone so many layers. You detected a pedestrian, did you did you hand code the feature vector of their state? Did you guys learn anything from computer vision before deep learning? Well, okay, you know, I feel like </s><s>[INST] this is it's a perception to you, is the sticking point is I mean what what's what's the hardest part of the stack here? [/INST] There is no human understandable uh feature vector separating perception and planning. That's the best way I can, I can put that. </s><s>[INST] There is no it's all together and it's it's it's uh it's a joint problem. So [/INST] you can take localization, localization and planning. There is a human understandable feature vector between these two things. I mean, okay, so I have like three degrees position three degrees orientation and those derivatives. Maybe those second derivatives. Right? That's human understandable, That's physical. The between perception and planning. Um So like Waymo has a perception stack and then a planner. Um And one of the things we know is right is they have a simulator that can separate those two. They can like replay their perception data and test their system, which is what I'm talking about about like the two different kinds of simulators. There's the kind that can work on real data and this is the kind of can't work on real data. Now, the problem is that I don't think you can hand code a feature factor, right? Like, like you have some list of like, oh, here's my list of cars on the scenes. Here's my list of pedestrians in the scene. This isn't what humans are doing. </s><s>[INST] What are humans doing [/INST] global? </s><s>[INST] Some something you're saying that's too difficult to uh hand engineer. [/INST] I'm saying that there is no state factor given a perfect I could give you the best team of engineers in the world to build a perception system and the best team to build a planner. All you have to do is define the state factor that separates those two. </s><s>[INST] I'm missing the state vector that separates those two. What do you mean? [/INST] So what is the output of your perception system? </s><s>[INST] I'll put in the perception system. Uh it's uh there's okay, well there's several ways to do it with the 11 is the slam components, localization, the others, drivable area, drivable space, space and then there's the different objects in the scene. Uh Yeah. And uh different objects in the scene over time. Maybe to give you input that then try to start modeling the trajectories of those objects? Sure. That's it. [/INST] I can give you a concrete example of something you missed. What's that? So say there's a bush in the scene. Humans understand that when they see this Bush, that there may or may not be a car behind that Bush drive double area and a list of objects does not include that humans are doing this constantly at the simplest intersections. So now you have to talk about occluded area. </s><s>[INST] Right. [/INST] Right. But even that, what do you mean by included? Okay, so I can't see it. Well, if it's the other side of the house, I don't care. What's the likelihood that there's a car in that included area. Right. And if you say, Okay, we'll add that. I can come up with 10 more examples that you can't add. </s><s>[INST] Certainly included area would be something that simulator would have because it's simulating the entire, you know, the conclusion is part of it, [/INST] including part of the vision stack. But what I'm saying is if you have a hand engineered, if your perception system output can be written in a spec document, it is incomplete. </s><s>[INST] Yeah, I mean, certainly it's uh it's hard to argue with that because in the end that's going to be true. [/INST] And I'll tell you what the output of our perception system is. It's 1000. It's 1,024 dimensional vector. Uh </s> |
<s>[INST] Mhm. It's a good payback. No, [/INST] We actually met. So there's two elderly people in their 60's who meet each other after so many years. And uh the one that ended the relationship started the conversation by saying, you know what? I made a really bad mistake and and the tears came down her cheeks. I wasn't asking for that. I wouldn't I wasn't happy about it, but it did feel good now now a while later uh I knew why she said she made a mistake. I met her husband. </s><s>[INST] Yeah. I mean there's um there's a Tom Waste is a song called Martha where he made um where an older gentleman calls somebody he used to love. And they have a conversation. They're both married now. And it's sometimes you can meet people from your past and it gives you a glimpse of a possible different life you could have [/INST] had. Uh and you know, I was actually when she said I made a mistake and I was thinking to myself, no, you didn't. There was none. There was nothing left with, nothing left. And also the person that she became uh personality wise wasn't as attractive as I remembered her. You know? It's puppy love. You know? </s><s>[INST] Yeah, [/INST] it was </s><s>[INST] it was [/INST] passionate love for sure. And I would have I would have thrown myself under the bus if I could save her. It was that strong and just as strong as the love for my two girls. </s><s>[INST] Yeah. Life is full of moments and periods like that of love and that that's what makes life so so freaking awesome. But it does come to an end and [/INST] so does this conversation I </s><s>[INST] guess this goes on for many more hours. But yes. Uh do you think about your own death? Do you think about death? Do you think about your own death? Are you afraid of it? [/INST] Yes. Even though I'm a question um </s><s>[INST] as a christian, do you have a sense what's coming after? [/INST] Have a hope? I have a hope you know? Um There's a lot of there's a lot of Christianity which is quite logical, a lot of Christianity which is also you know the life of christ there's a lot of a lot of proof but you know and I became a christian uh starting with a head and and I was already quite old and I um you know when you don't when you don't get this faith very early, it's tougher to buy into everything. You know there are some there are some things that are difficult for me to understand and believe but but there's many, many other things that I can't explain only with the existence of a god but whether he lets us go again for an eternity. I just hope I won't convince somebody else at this point which is doesn't make me a really really good question because I'm supposed to evangelize </s><s>[INST] but there's still a fear, there's a fear and a hope [/INST] on the other hand uh I know that you see, see this, this is this is how I approached the last years of my life. Ah I will not, I will not mentally or physically get decrepit, I will do everything I can do to be alert and fit. I still run, I won four or 5 times a week and I'm going to start lifting weights again. </s><s>[INST] Good. You stayed physically mentally sharp, go out with guns blazing. [/INST] That's that's and I once read a book written by, by a medical doctor. He said most people when, when, when, when they're becoming mature that the rest of their life is a slow downward move and not </s><s>[INST] for, you know, [/INST] the last years are pretty bad. He said you got to do this. Boom, </s><s>[INST] That's pretty good advice from a doctor. Um and if nothing else from Christianity, whichever parts you take on one of the big ones is love. And that's something you've lived from the very beginning before, before God was part of your life before anything was part of your life. It seemed that love was part of your life and has been a consistent threat throughout [/INST] her. And uh there's a short sentence in the bible says God is love. And the other thing I want to say the christian morality is, is I'm I can sign that with my blood. Okay, </s><s>[INST] God is love Amen Jack, You're an incredible person had lived an incredible life. Thank you for talking today. Thank you for telling your story. Uh, thank you for being who you are and thank you for being Um all about love. This is a this is a beautiful conversation. Was an honor. Thank [/INST] you, appreciate the tough questions that you asked. </s><s>[INST] Thanks for listening to this conversation with Jack Barsky. To support this podcast. Please check out our sponsors in the description and now let me leave you with some words from Edward Snowden. You can't come up against the world's most powerful intelligence agencies and not accept the risk if they want to get you over time, they will thank you for listening and hope to see you next time. [/INST] </s> |
<s>[INST] are like [/INST] very angry. Uh, you know, only vegetarian or vegan folks because they will tear you apart and try to convert you as much as </s><s>[INST] possible. Did [/INST] you just, did you just </s><s>[INST] point a large number of, of haters onto this very podcast? Is this what just hap no. Is there like several people that were very upset at you right now throwing things? [/INST] No, that's always the joke that I've made because if people have chest dot com and I love all people, but I'm just saying chess dot com patrons do not try to actively convert folks, only chess folks on </s><s>[INST] are like, [/INST] you know, there's a meme chess dot com </s><s>[INST] started, started, [/INST] started somewhere in red unrated anarchy chazz kind of </s><s>[INST] solely chess is a little bit of an anarchist organization. Would you, would you go as far as to say there are terrorist terrorist extremist organization. Are we going there for [/INST] legal reasons. That's uh, I thought leeches has like </s><s>[INST] really good analysis. Somebody does it have an engine for analysis of like games or is that is that an open source thing that like [/INST] They both do? They both use stock fish? 15. </s><s>[INST] Okay. And then the rest is the interface around stock stock fish that shows [/INST] it's tough. It's it's the life. So chest has a live server where you and I can play a game against each other. We just both seek and if we have the same rating, we have the same criteria. We'll play a game. But there's also reviewing your own games, there's an opening database so you can see what the most popular trends are. So leeches is great. Like I'm sponsored by dot com and I will openly say that, but you can't </s><s>[INST] have your deeply biased. [/INST] Yes. But I'm also complementing the competitor but </s><s>[INST] can you play games only chess or is it just for analysis? [/INST] You can So </s><s>[INST] it's the same exact thing. So they're like legitimately competitors, not exactly the same thing, but they have the they're trying to match for features, but you're saying lee chess is more chaotic and then chest dot com is more like professional. [/INST] Yeah. I don't, I don't know. I don't know if it's chaotic. I just know that it's uh, you have to you no one's gonna hold your hand If you, if you go to you absolutely can, you can play games, you can analyze your games but you have to discover yourself. The whole point of dot com is to make the journey as simple as possible. Uh But I also firmly believe you can't have any sort of growth in chess without a chess dot com or a chess 24 </s><s>[INST] What's What's Chess 24. [/INST] So Chess 24 was another live server with some lesson libraries and so on. But they were, I think the process was they were bought by play Magnus. So </s><s>[INST] what's play magnus [/INST] Play magnus? </s><s>[INST] That's magnus Carlsson's [/INST] Yeah, he doesn't own it. He owns some stake in it. I think nine or 10%. They owned a bunch of chess companies including chess 24 but now it seems like they're either merging or basically getting acquired by chess. Dot com. </s><s>[INST] Got it. And then play magnus. It's an app also where you can play magnus at different levels, but there's also the educational [/INST] stuff. </s><s>[INST] Okay. The [/INST] for profit chess companies make the option for grand masters to make a living to make chess in the sport leeches is great. It doesn't put on any events, There's no commentary so you, you can have both in theory and probably some controversy is good. </s><s>[INST] Does chess dot com. Like sponsor you that help you out in some way, Like what's the connection between your videos and streams and so on and chest dot com. Like are they supporting peop [/INST] my content? They don't necessarily, I just make whatever I want. Like I don't have not sense like they do something stupid. I will call out their leadership. It's not like but I too have the logo up like in my Youtube videos or Yeah, it's just </s><s>[INST] that kind of stuff. Yeah. So anyway, back to, I mean that was really helpful. I was confused about all that. Um the guessing people's rating. So the thing you mentioned about the end game, if you don't know what the hell you're doing with the end game, what does that mean about your writing? If you don't know how to finish with just a few pieces on the board. You [/INST] could be my rating. </s><s>[INST] The [/INST] game is tough. </s><s>[INST] That's the self deprecating humor. We tuned in for. Uh [/INST] games are hard man </s><s>[INST] there. You [/INST] can't have, there's a reason magnus is the best because seven hours into a game when everybody's given up, he's still squeezing juice out of the fruit. So that's the way I would describe it. So </s><s>[INST] that's not good source of information. If you [/INST] Know within the 1st 15 moves generally, you can </s><s>[INST] tell [/INST] because you can tell how well they played the opening. So how well they knew what they were supposed to memorize what they were supposed to play and then how they react to piece interactions. So if they are faced with a move that a more advanced player would deal with very swiftly. Because there's kind of a natural response that gives you information if they move their king when they're in check, when they didn't have to. That's a massive giveaway. Some people just think I'm in check so I have to move my king. </s> |
<s>[INST] You don't think of string theory as an original idea. [/INST] Oh, I mean, it was original to Venustiano probably is older than the baby boomers and there are people who are younger than the baby boomers who are still doing string theory. And I'm not saying that nothing discovered within the large strength, theoretic complex is wrong. Quite the contrary. A lot of brilliant mathematics and a lot of the structure of physics was elucidated by string theorists. What do I think of the delivery, herbal nature of this product that will not ship called string theory. I think that it is largely an affirmative action program for highly mathematically and geometrically talented baby boomer. Physics physicists so that they can say that they're working on something within the constraints of what they will say is quantum gravity. Now there are other schemes, you know, there's like a symptomatic safety. There are other things that you could imagine doing. I don't think much of any of the major programs but to have inflicted this level of loyalty through a shibboleth. Well, surely you don't question X while I question almost everything in the string program and that's why I got out of physics when you called me a physicist. It was a great honor. But the reason I didn't become a physicist wasn't that I fell in love with mathematics. As I said, Wow. In 1984, I saw the field going mad and I saw that mathematics which has all sorts of problems, was not going insane. And so instead of studying things within physics, I thought it was much safer to study the same objects within mathematics. There's a huge price to pay for that. You lose physical intuition. But the point is that it wasn't a north korean reeducation camp either. </s><s>[INST] Are you hopeful about cracking open the Einstein unified theory in a way that has been really, really uh understanding whether just uh uniting everything together with quantum theory and so [/INST] on. I mean, I'm trying to play this role myself to do it to the extent of handing it over to the more responsible, more professional, more competent community. Um so I think that they're wrong about a great number of their belief structures, but I do believe, I mean, I have a really profound love hate relationship with this group of people. </s><s>[INST] I think the physics side, oh yeah, because the mathematicians actually seem to be much more open minded and [/INST] uh well they are in there are there are open minded about anything that looks like great math. Right, Right. They'll study something that isn't very important physics, but if it's beautiful mathematics then they'll have, they have great intuition about these things as good as the mathematicians are. And I might even intellectually at some horsepower level give them the edge. The theoretical theoretical physics community is bar none. The most profound intellectual community that we have ever created. It is the number one. There is nobody in second place as far as I'm concerned. Look in their spare time and the spare time, they invented molecular biology. </s><s>[INST] What was the origin of molecular biology? You're saying something like [/INST] Francis crick. I mean, a lot of, a lot of the early molecular biologists, physicists. Yeah, I mean, you know, Schrodinger wrote, what is life? And that was highly inspirational? I mean, you have to appreciate that there is no community, like the basic research community in theoretical physics and it's not something I'm highly critical of these guys I think that they would just wasted the decades of time with um a near religious devotion to their misconception. Ization of where the problems were in physics. But this has been the greatest intellectual collapse ever witnessed within academics. </s><s>[INST] You see it as a collapse or just a lull. [/INST] Oh I'm terrified that we're about to lose the vitality. We can't afford to pay these people um we can't afford to give them an accelerator just to play with in case they find something at the next energy level. These people created our economy. They gave us the rad lab and radar. They gave us two atomic devices to end World War Two. They created the semiconductor and the transistor to power our economy through moore's law as a positive externality of particle accelerators. That created the World Wide Web. And we have the insolence to say why should we fund you with our taxpayer dollars? No. The question is, are you enjoying your physics dollars? </s><s>[INST] Uh huh. Right. [/INST] These guys signed the world's worst licensing agreement. And if if they simply charged for every time you used a transistor or a U. R. L. Or enjoyed the peace that they have provided um during this period of time through the terrible weapons that they developed uh or your communications devices, all of the things that power our economy I really think came out of physics even to the extent the chemistry came out of physics and molecular biology came out of physics. So, first of all, you have to know that I'm very critical of this community. Second of all, it is our most important community. We have neglected it. We have abused it. We don't take it seriously. We don't even care to get them to rehab after a couple of generations of failure. All right. No one, I think the youngest person Uh to have really contributed to the standard model of theoretical level was born in 1951. Right frank wilczek. And almost nothing has happened um That in theoretical physics after 1973, that's sent somebody to Stockholm for theoretical development, that predicted experiment. So, we have to understand that we are doing this to ourselves now with that said, these guys have behaved abysmally in my opinion. Um because they haven't owned up to where they actually are, what problems they're really facing, how definite they can actually be. They haven't shared some of their most brilliant discoveries which are desperately needed in other fields like gauge theory, which at least the mathematicians can share, which is an upgrade of the differential calculus of Newton and Leibnitz and they haven't shared the importance of renormalization theory. Uh even though this should be standard operating procedure for people across the sciences dealing with different layers and different levels of phenomenon </s> |
<s>[INST] Peterson [/INST] anaconda, right, we're still great friends, great friends, we talk all the time, I love him to death. There's a long story there about like why and how we can cover in some, some other podcasts, perhaps sort of more, maybe have more business focused one, but there's one area where I think Kanda should be more community driven, like he should be pushing more to get more community contributors to conda and let let let the, not the kind of constantly fighting this battle, right? It's actually, it's really a developers exact, you said like help the developers and then they'll actually move in the right direction, </s><s>[INST] that was the problem. I have as many of the cool kids I know don't use Kanda and that to me is confusing, [/INST] it is confusing and it's really a matter of kinda have some challenges first of all, kind of still needs to be improved, there's lots of improvements made and that is that aspect of weight, who's doing this and the fact that then the pipe a really stepped up, like they were not solving the problem at all and now they kind of got to where they're solving it for the most part and then effectively you could get like kinda solved a problem that was there and it still does and it's still, you know, there's still great things that can do, but um and we still use it all the time at one site and with other clients but with uh but you can kind of do similar things with pip and doctor. Right, So especially the web development community, that part of it again is this is the, there's a lot of different kind of developers in the python ecosystem and there's still a lack of, of some clear understanding, I go to the python conference all the time and there's only a few people in the people who get it and then others who are just massively trumpeting the power of pit but just do not understand the </s><s>[INST] problem. So one of the obvious things to me from a mom from a non program of perspective is the across operating system usability, that's much more natural. So they use windows and just it seems much easier to uh to recommend Kanda there, but then you should also recommend it across the board so I'll definitely sort of [/INST] what I recommend now is a hybrid. I do, I mean I'm is it possible to use it, is it, is what I like build the environment with pip with conduct, build an environment with conda and then pip, install on top of that, that's fine, be careful about pip, installing open c V or tensorflow or because if somebody is allowed that it's going to be most surely done in a way that can't be updated that easily, </s><s>[INST] so install like the big packages, the infrastructure, Kanda and then the weirdos [/INST] that like the weird like </s><s>[INST] implementation for some head um, there's a cool library. I used that based on your location and time of day and date tells you the exact position of the sun relative to the earth and it's just like a simple library but it was very precise and was like, all right. But that was that was in this pit is [/INST] the thing they did really well is python developers who want to get their stuff published. They, you have to have a pit recipe. Right? Even if it's, you know, the challenges and there's a key thing that needs to be added a pip. Just simply add to pit the ability to defer to a system package manager like because it's, you know, recognize you're not going to solve all the dependency problem. So let's give up and allow the allow system packager to to work that way and icon is installed. It has pip. It would default to conduct to install this stuff but red hat rpm would default rpm to install. That's all more things like that's the, that's a key not difficult but somewhat were some work feature needs to be added. That's an example of something like I've known we need to do it. I mean it's where I wish I had more money, I wish I was more successful in the business side trying to get there but I wish my you know my family, friends and full community that I know was larger was larger and had more money because I know tons of things to do effectively with more resources but you know I have not yet been successful channel tons of it some you know, I'm happy with what we've done. We've created again at one site what we created to get any kind of started we created humanity is going to kind of started done it again with Kwan site. Super excited by that by the way it took for years to do it. </s><s>[INST] What is Quan site? What is its mission? We've talked a few times about different fascinating aspects of it but it's like big picture what [/INST] quantity is uh it's vicious to connect data to an open economy. So it's basically consulting the pilot ecosystem. It's a consulting company and what I've said when I started it is we're trying to create products, people and technology. So it's divided into two groups and a third one as well. The two groups are a consulting services company that just helps people do data science and data engineering and data management. Uh better and more efficient. Full staff science, full thing. We'll help you build a infrastructure. If he was in jupiter we need we do staff augmentation need more pro programmers help used as more effectively. Help use Gpus more effectively. Just basically a lot of people need help. So we do training as well to help people, you know, both immediate help and then get get learned from somebody. Uh, we've added a bunch of stuff to, we kind of separate some of these other things in another company called open teams that, that we currently started. One of things I loved what we did. Anaconda was created a community innovation team. So I want to replicate that. This time we did a lot of innovation and anaconda. I wanted to do innovation but also contribute to the projects that existed, create a place where maintainers so that sci fi and numpy and number and all these projects we already started can pay people to work on them and keep them going. So that's labs. Concert Labs is a separate organization. It's a nonprofit mission. The profits of Quan said help fund it. And in fact every project that we have at quan site, a portion of the money goes directly to coincide. Labs to help keep it funded. So we've gotten several mechanism, we keep one site labs funded. Currently I'm really excited about labs because it's been a mission for a long time. </s> |
<s>[INST] the type annotations are there inside the variable as its runtime. [/INST] They're mostly associated with the function object. Not with each individual variable, but uh you can sort of map from from the arguments to the variables </s><s>[INST] And that's what a 3rd party library [/INST] exactly. And the problem with that, is that all that extra runtime type checking uh is going to slow your code down instead of speed it </s><s>[INST] Up, I think uh the reference this uh sales pitchy blog post that says 75% of developers time is spent on debugging. I would say that in some cases that might be okay. It might be okay to pay the cost of performance for the catching of the types, the type errors. [/INST] And in most cases doing it statically before you ship your code to production is more efficient than doing it at runtime piecemeal. </s><s>[INST] Can you tell me about M. Y. P. Y. My pi project. What is it? What's the mission and in general what is the future of static typing in python? [/INST] Well, so my pie was started by finished developer. You so </s><s>[INST] many cool things out of Finland? I gotta say just that part of the world. [/INST] I guess people have nothing better to do in those long cold </s><s>[INST] winters. I [/INST] don't know. I think you lived in England when he invented that stuff actually. But my pie is the original static type checker for python and the type annotations that were introduced with pep 4 84 were sort of developed together with the static type checker. And in fact Yuka had first invented a different syntax that wasn't quite compatible with python and uh U. K. And I sort of met at the python conference in I think in 2013 and we we sort of came up with a compromise syntax that would not require any changes to python and that would let my pie sort of be an add on static type checker for python? </s><s>[INST] Just out of curiosity was like double colon or something. What what was he proposing that would break python. I [/INST] think he was using angular brackets for types like in C plus plus or java generics. </s><s>[INST] Yeah you can't use angular brackets in python would be too tricky. Well [/INST] we the the key thing is that we already had uh syntax for annotations, we just didn't know what to use them for yet. So type annotations were just the sort of most logical thing to to use that existing dummy syntax for. But there was no there was no syntax for defining generics directly. Syntactic lee in the language my pie literally meant my version of python where my refers to yuka, he had a parse er that translated my pie into python by like doing the type checks and then removing the annotations and all the angular brackets from the positions where where he was using them. But a pre processor model doesn't work very well with the typical workflow of python development projects. </s><s>[INST] That's funny. I mean that could have been another major split if it became successful. Like if you watch typescript versus javascript is like a split in the community over types right? That seems to be stabilizing. Now [/INST] it's not necessarily a split. There's certainly plenty of people who don't use typescript but just use the original javascript notation. Just like there are many people in the python world who don't use type annotations and don't use static type checkers. No, </s><s>[INST] I know but there is a bit of a split between typescript and Java's old school javascript E. S. Whatever. Well [/INST] in the javascript world, transpire colors are sort of the standard way of working anyway, which is why typescript being a transpire for itself is not a big deal </s><s>[INST] and transparent for people who don't know. It's what's exactly the thing you said with my pies. It's the code I guess you call it pre processing code that translates from one language to the other and that's part of the culture, part of the workflow of the javascript community. So that's [/INST] right at the same time, an interesting development in the javascript slash typescript world at the moment is that there is a proposal under consideration. It's only a stage one proposal that proposes to add a feature to javascript where just like python, it will ignore certain syntax when running the javascript code and what it ignores is more or less a super set of the typescript annotations syntax </s><s>[INST] interesting. [/INST] So that would mean that eventually if you wanted to you could take typescript uh and you could shove it directly into javascript interpreter without translation. The interesting thing in the javascript world at least the web browser world the web browsers have changed how they deploy and uh they they sort of update their javascript engines much more quickly than they used to in the early days and so there's much less of a need for translation in javascript itself because most browsers just support the most recent version of Atmos script. </s><s>[INST] Just an attention of attention. Do you see if you will recommend somebody use the thing, would you recommend typescript or javascript? I [/INST] would recommend typescript just </s><s>[INST] because of the strictness of the typing, [/INST] it's an enormously helpful extra tool that helps you sort of keep your head straight about what your code is actually doing. </s><s>[INST] I [/INST] mean it's it's it helps with editing your code, it helps with ensuring that your code is not to incorrect and it's actually quite compatible with javascript. Never mind this syntactic sort of heck that is still years in the future. But any library that is written in pure javascript can still be used from typescript programs and also the other way around, you can write a library in typescript and then exported in a form that is totally consumable by javascript. That sort of compatibility is is sort of the key to the, to the success of typescript. </s> |
<s>[INST] meaning? Like for us humans to connect with each other or to connect with other living entities? I think we need to feel like in order for us to uh truly feel like that there's another being there, we have to believe that they're conscious and so we won't ever connect with something that doesn't have elements of consciousness. Now, I tend to think that that's easier to achieve than it may sound, because we anthropomorphize stuff so hard, like you have a mug that just like has wheels and like rotates every once in a while and makes a sound, I think a couple of days in, especially if you're uh if you're if you don't hang out with humans, you might start to believe that morgan wheels is conscious. So I think we anthropomorphize pretty effectively as human beings, but I do think that it's in the same bucket that will call the motion that show that you're, you know, I think of consciousness as the capacity to suffer and if you are an entity that's able to feel things in the world and to communicate that to others um I think that's a really powerful way to interact with humans and in order to create an A. G. I. System I believe you should be able to richly interact with humans. Like humans would need to want to interact with you. Like it can't be like it's the self supervised learning versus like uh like the robot shouldn't have to pay you to interact [/INST] with me. So </s><s>[INST] like it should be a natural fun thing and then you're going to scale up significantly how much uh interact gets its the elect surprise which they were trying to get me to be a judge on their contest. Let's see if I want to do that. But there there are challenges to uh Talk to you, make the judge make the human sufficiently interested that the human keeps talking for 20 minutes to Alexa. Yeah and right now they're not even close to that because it just gets so boring when you're like when when the intelligence is not there it gets very not interesting to talk to it. And so the robot needs to be interesting and one of the ways it can be interesting is display the capacity to love to suffer. And I would say that essentially means the capacity display consciousness like it is an entity much like a human being of course what that really means. I don't know if that's fundamentally a robotics problem or some kind of problem that we're not yet even the word like if it is truly a hard problem of consciousness, I tend to maybe optimistically think it's a um we can pretty effectively fake it till you make it. So we can display a lot of human like elements for a while and that will be sufficient to form really close connections with humans. What to use the most beautiful idea in self supervised learning. Like when you sit back with, I don't know with a glass of wine, an armchair and just a fireplace, just thinking how beautiful this world that you get to explore is. What do you think is the especially beautiful idea? [/INST] The fact that like objects level what objects are in some notion of objectives emerges from these models. But I just like self supervised learning. So for example, like um one of the things like the Dino paper that I was a part of facebook is uh the object sort of boundaries emerged from these representations. So if you have like a dog running in the field, the boundaries around the dog, the network is basically able to figure out what the boundaries of this dog are automatically. It was never trained to do that. It was never trained to uh no one thought it that this is a dog and these pixels belong to a dog, it's able to group these things together automatically. So that's one I think in general, that entire notion that this dumb idea that you take like these two crops of an image. And then you say that the feature should be similar that has resulted in something like this. Like the model is able to figure out what the dog pixels are and so on. That just seems like so surprising. Um And I mean I don't think a lot of us even understand what how that is happening really and it's something we're taking for granted. Uh maybe like a lot in terms of how we're setting up these algorithms, but it's just it's a very beautiful and powerful idea. So it's really fundamentally telling us something about that. There is so much signal in the pixels that we can be super dumb about it, about how we're setting up the cells to preserving problem and despite being like super dumb about it, Well actually get very good. Uh well actually get something that is able to do very like surprising things. </s><s>[INST] I wonder if there's other like object Nous other concepts that can emerge. I don't know if you follow francois surely he had the competition for intelligence that basically it's kind of like an IQ test but for machines but for an I. Q. Test you have to have a few concepts that you want to apply one of them is object Nous. I wonder if those concepts can emerge through self supervised learning on billions of images. [/INST] I think something like object permanence can definitely emerge. Right? So that's like a fundamental concept which we have maybe not two images through video? But that's another concept that should be emerging from it because it's not something that if we don't teach humans that this is this is about this concept of object permanence that actually emerges and the same thing for like animals like dogs. I think actually permanent automatically is something that they are born with. So I think it should emerge from the data, it should emerge basically very quickly. </s> |
<s>[INST] And that's something we should, you know, talk about. And that's a really complicated human question. It does seem that the rhetoric, the populism of workers unite. We've been fucked over for way too long. Let's stand together. Somehow that message allows flawed or evil people to take power. It seems like the rhetoric, the idea is so good, maybe the utopian nature of the idea is so good that it allows a great speaker to take power. It's almost like if the mission, like come with me friends, beyond the horizon, a great land is waiting for us, that encourages sort of, yeah, dictators, authoritarians to take power. Is there something within the ideology that allows for that, for the sort of, for lying to people, essentially? [/INST] Well, I might surprise you with my answer because I would say, yes, maybe. But I think that it's not just socialism, any sort of ideology that appeals to the collective and appeals to our long-term destiny, either as a species or as a nation or as a class or whatever else, can lend itself to authoritarianism. So you can see this in many of the nationalisms of the 20th century. Now some of these nationalisms use incredibly lofty collective rhetoric, like in Sweden, the rhetoric of we're going to create the people's home. We're going to make this a country with dignity for all Swedes. We're going to make this a country that's more developed, more free, and so on. And they managed to build a pretty excellent society in my estimation from that. In countries like fascist Germany and Italy, they managed to do horrendous things in Japan and horrendous things with that. In the US, with national popular appeals, FDR was able to unite a nation to elevate ordinary working class people into a position where they felt like they had a real stake in the country, and I think did great things with the New Deal. In Russia, of course, this language was used to trample upon individual rights and to justify hardship and abuses of ordinary individual people in the name of a collective destiny. A destiny, of course, was just decided by the party in power and during the 30s and 40s by just Stalin himself, really. Now I think that that's really the case for making sure that we have a bedrock of civil rights and democracy, and then on top of that, we could debate. We could debate different national destinies. We could debate different appeals, different visions of the world, but as long as people have a say in what sacrifices they're being asked to do, and as long as those sacrifices </s><s>[INST] don't take away what's fundamentally ours, which is our life, which is our basic rights. And voice, our voice. So this complicated picture, because, help me understand, you mentioned that social democracy is trying to have social policies within a capitalist system in part, but your vision, your hope for a social democracy is one that goes beyond that. How do you give everybody a voice while not becoming the Soviet Union, while not becoming where basically people are silenced either directly through violence or through the implied [/INST] threat of violence and therefore fear? So I think you need to limit the scope of where the state is and what the state can do and how the state functions, first of all. Now for me, social democracy was like the equivalent of, I'll give a football analogy, it was the equivalent of getting to the red zone and then kicking a field goal. You'll take the three points, but you would have rather got a touchdown, and for me, socialism would be the touchdown. </s><s>[INST] It's not a separate, different playing field. [/INST] Some people would say socialism would be an interception. Sure, sure. </s><s>[INST] No, and they would have the right to, again, to say that and to say we shouldn't go further. And most coaches would take the safer route, right? So you're going against the decision. Anyway, I'll just take it too far. But I understand, I understand. [/INST] So for you, the goal is full socialism. But I'll take the three points. It's part of, I just want to march down the field. I want to get within scoring position. The reason why we should really move from this analogy, but the reason why I call myself a socialist is looking through history and these examples of social democracy, you saw that they were able to give working class people lots of rights and income and power in their society. But at the end of the day, capitalists still have the ultimate power, which is the ability to withhold investment. So they could say in the late 1960s and early 70s, listen, I was fine with this arrangement 10 years ago, but now I feel like I'm going to, you know, take my money and I'm going to go move to a different country or I'm just going to not invest because my workers are paid too much. I'm still making money, but I feel like I could be making more. I need more of an upper hand, right? So their economic power is then challenging the democratic mandate of Swedish workers that were voting for the Social Democratic Party and were behind this, this advance. So to me, what socialism is in part is taking the means of production, right, where this capitalist power is coming from and making it socially owned so that ordinary workers can control their workplaces, can make investment decisions and so on. Now does that mean total state ownership of everything or a planned economy? I don't think that makes any sense. You know, I think that we should live in a society in which markets are harnessed and regulated and so on. My main problem is capitalist ownership, in part on normative grounds, just because I think that it doesn't make sense that we celebrate democracy and all these other spheres, but we have workplaces that are just treated like tyrannies. And in part because I think that ordinary workers would much prefer a system in which over time they, you know, accrued shares in ownership where they got, in addition to base kind of ways, they got dividends from their firm being successful and that they figured out how to, you know, large firms, they're not going to be making day-to-day decisions by democratic vote, right, but maybe you would elect representatives, elected management once every year or two, depending on your operating agreement and so on. That's kind of my vision of a socialist society and this sounds, I hope, like agree or disagree, like it would not be a crazy leap into year zero, right? This could be maybe a way in which we could take a lot of what's existing in society but then just add this on top, but what it would mean is a society without a capitalist class. This class hasn't been, you know, individually, these people, you know, haven't been taken to re-education camps or whatever else, but they're just no longer in this position. And they're now part of the economy in other ways, like they'll probably be the first set of highly competent technocrats and managers and so on, they'll probably be very well compensated for their time and expertise and whatever else. But to me, both the practical end of things, like taking away this ability to withhold investment and increasing our ability to democratically shape investment priorities and to continue down the road of social democracy and on normative grounds, my egalitarian belief that ordinary people should have more stake in their lives in the workplace leads me beyond social democracy to socialism. </s> |
<s>[INST] Your support means a lot and inspires me to keep this series going. And now here's my conversation with kevin scott. [/INST] You've </s><s>[INST] described yourself as a kid in a candy store Microsoft because of all the interesting projects that are going on. Can you try to do the impossible task and give a brief world wind view of all the spaces that Microsoft is working in both research and product [/INST] if you include research, it becomes even even more difficult. So, so I think broadly speaking, Microsoft's product portfolio includes everything from, you know, big cloud business, Like a big set of sass services. We have, you know, sort of the original or like some of what are among the original productivity uh software products that everybody used. We have an operating system business, we have a hardware business where we make everything from uh computer mice and headphones to high end high end personal computers and laptops. We have a fairly broad ranging research group where like we have people doing everything from economics research. So like there's this really uh really smart young economist Glenn while who like my group works with a lot who's doing this research on these things called Radical markets. Uh like he's written an entire entire technical book about about this whole notion of a radical market. So like the research group sort of spans from that human computer interaction to artificial intelligence. And we have we have ghetto, we have linked in, we have search advertising and news business and like probably a bunch of stuff that I'm embarrassingly not recounting in this gaming </s><s>[INST] to Xbox and so on [/INST] gaming for sure. Like I was I was having a super fun conversation this morning with with Phil spencer. So when I was in college there was this game that Lucas arts made called day of the tentacle that my friends and I played forever and like we're you know, doing some interesting collaboration now with the folks who made uh day of the tentacle and I was like completely nerd ng out with tim schafer, like the guy who wrote a day of the tentacle this morning, just a complete Fanboy, which you know, sort of it like happens a lot, like, you know, Microsoft has been doing so much stuff, it's such breath for such a long period of time that you know, like being cto like most of the time, my job is very, very serious and sometimes like I get to get caught up in like how amazing it is to be able to have the conversations that I have with the people, I I get to have them with, </s><s>[INST] you had to reach back into the sentimental and what's the, the radical markets and economics. So [/INST] the idea with radical markets is like, can you come up with new market based mechanisms to uh you know, I think we have this, we're having this debate right now, like does capitalism work like free markets work? Can the incentive structures that are built into these systems produce outcomes that are creating sort of equitably distributed benefits for every member of society, you know, and I think it's a reasonable, reasonable set of questions to be asking. And so what glenn and so like, you know, one motor thought there, like if you have doubts that the, that the markets are actually working, you can sort of like tip towards like, okay let's let's become more socialist and uh you know like have central planning and you know governments or some other central organization is like making a bunch of decisions about how you know, sort of work gets done and uh you know like where the you know where the investments and where the outputs of those investments get distributed. Glenn's notion is like lean more into uh like the market based mechanism. So like for instance, uh you know, this is one of the more radical ideas like suppose that you had a radical pricing mechanism for assets like real estate where you were, you can be a bit out of your position and in in your home. Uh you know, for instance, so like if somebody came along and said, you know, like I've I can find higher economic utility for this piece of real estate that you're running your business in. Uh like then uh like you either have to, you know, sort of bid to sort of stay or like the thing that's got the higher economic utility uh you know, sort of takes over the asset, which would make it very difficult to have the same sort of rent seeking behaviors that you've got right now because uh like if you did speculative bidding, like you would very quickly like lose a whole lot of money. And so like the prices of the assets would be sort of like very closely index to uh like the value that they could produce And like because like you have this sort of real time mechanism that would force you to sort of mark the value of the asset to the market, then it could be taxed appropriately. Like you couldn't sort of sit on this thing and say like this house is only worth $10,000 when like everything around it is worth 10 million, </s><s>[INST] let's finish. So it's an incentive structure that where the prices match the value much better. So [/INST] Glenn does a much, much better job than I do and selling and I probably picked the world's worst example, you know? And and and but like it's it's intentionally provocative, you know, so like this whole notion like, you know, like I'm not sure whether I like this notion that like we could have a set of market mechanisms where I could get bit out of out of my property, you know? But, but you know, like if you're thinking about something like Elizabeth Warren's wealth tax for instance, like you would have, I mean it'd be really interesting and like how you would actually set the price on the assets and like you might have to have a mechanism like that if you put a tax like that in </s><s>[INST] place. It's really interesting that that kind of research at least tangentially touching Microsoft research. Yeah, you're really thinking broadly uh maybe you can speak to this connects to a I so we have a candidate. Andrew yang who kind of talks about artificial intelligence and the concern that people have about our, you know, automation impact on society. And arguably Microsoft is at the cutting edge of innovation in all these kinds of ways. And so it's pushing ai forward. How do you think about combining all our conversations together here with radical markets and socialism and innovation in ai that uh that Microsoft is doing and then Andrew Yang's worry that uh that that will that will result in job loss for the lower and so on. How do you think about that? I think [/INST] it's sort of one of the most important questions in technology, like maybe even in society right now about how is ai going to develop over the course of the next several decades and like what's it going to be used for and like what uh what benefits will it produce and what negative impact will it produce? And you know, how who gets to steer this whole thing, You know, I'll say it at the highest level. One of the real joys of of getting to do what I do at Microsoft is Microsoft has this heritage as a platform company. And so you know, like Bill Bill has this thing that he said a you know, a bunch of years ago where you know, the measure of a successful platform is that it produces far more economic value for the people who built on top of the platform than is created for the the platform owner or builder. And I think we have to think about ai that way, </s><s>[INST] like platform [/INST] Yeah, it has to like, it has to be a platform that other people can use to build businesses to fulfill their creative objectives to be entrepreneurs, to solve problems that they have in there, working in their lives. Uh it can't be a thing where there are a handful of companies uh sitting in a very small handful of cities geographically who are making all the decisions about what goes into the Ai and uh and like and then on top of like all this infrastructure, then build all of the commercially valuable uses for it. So like, I think like that's bad from a you know, sort of, you know, economics and sort of equitable distribution of value perspective, like, you know, sort of back to this whole notion of, you know, like to the markets work, But I think it's also bad from an innovation perspective because like I have infinite amounts of faith in human beings that if you give folks powerful tools, they will go do interesting things and it's more than just a few tens of thousands of people with the interesting tools that should be millions of people with the tools. So it's sort of like, you know, you think about the Um the steam engine in the late 18th century, like it was you know, maybe the first large scale substitute for human labor that we've built like a machine. Uh and uh you know, in the beginning when these things are getting deployed, the folks who uh got most of the value from the steam engines were the folks who had capital so they could afford to build them and like they built factories around them and businesses and the experts who knew how to build and maintain them. But access to that technology democratized over time like now, like uh like an engine, it's not uh it's not like a differentiated thing. Like there isn't one engine company that builds all the engines and all of the things that use engines are made by this company and like they get all the economics from all of that, like, like fully demarcated. Like they're probably, you know, we're sitting here in this room and like even though they don't, there are probably things, you know, like the, the memes, gyroscope that are in both of our folks, like they're like little engines, you know, sort of everywhere. They're just a component in how we build the modern world, like AI needs to get there. </s><s>[INST] Yeah, so that's a really powerful way to think if we think of aI as a platform versus a tool that Microsoft owns as a platform that enables creation on top of it. That's the way to democratize it. That's really, that's really interesting actually and Microsoft throughout its history has been positioned well to do that [/INST] and the you know the tie back to the to this radical markets, things like that. So my team has been working with Glenn on this and jaron Lanier actually. So jarron is the like the sort of father of virtual reality uh like he's one of the most interesting human beings on the planet, like a sweet sweet guy uh and so Jared and Glenn. Uh and folks and my team have been working on this notion of data as labor or like they call it data dignity as well. And so the the idea is that if you you know again going back to this, you know sort of industrial analogy if you think about data is the raw material that is consumed by the machine of ai in order to do useful things. Uh then like we're not doing a really great job right now and having transparent marketplaces for valuing those data contributions so and we all make them like explicitly like you go to linkedin, you sort of set up your profile on linkedin like that's an explicit contribution, like you know exactly the information that you're putting into the system and like you put it there because you have some nominal notion of like what value you're going to get in return but it's like only nominal like you don't know exactly what value you're getting in return, like services free, you know like it's low amount of like perceived out and then you've got all this indirect contribution that you're making just by virtue of interacting with all of the technology that's in your daily life. And so like what Glenn and jarron and this data dignity team are trying to do is like can we figure out a set of mechanisms that let us value those data contributions so that you could create an economy and like a set of controls and incentives that would allow people to like maybe even in the limit like earn part of their living through the data that they're creating. And like you can sort of see it in explicit ways. There are these companies like scale Ai and like there's a whole bunch of them in uh in china right now that are basically data labeling companies. So like you you're doing supervised machine learning. You need you need lots and lots of labeled training data. Yeah. And like those people are getting competent like who work for those companies are getting compensated for their data contributions into the system. And so </s><s>[INST] that's easier to put a number on their contribution because they're explicitly labeling data. But you're saying that we're all contributing data into all kinds of ways and it's fascinating to start to explicitly try to put a number on it. Do you think that's that's possible? [/INST] I don't know it's hard. It really is because you know we don't have as much transparency is uh is I think we need uh in like how the data is getting used and it's you know, super complicated, like, you know, we we you know, I think it's technologist sort of appreciate like some of the subtlety there, it's like, you know, the data, the data gets created and then it gets, you know, it's not valuable. Like the data exhaust that you give off or the, you know, the explicit data that I am putting into the system isn't value valuable. It's super valuable atomically. Like it's only valuable when you sort of aggregated together and to, you know, sort of large numbers. It's true even for these like folks who are getting compensated for like labeling things like for supervised machine learning now, like you need lots of labels to train, you know, a model that performs well. And so, you know, I think that's one of the challenges. It's like how do you, you know, how do you sort of figure out like because this data is getting combined in so many ways like through these combinations, like how the value is flowing. </s><s>[INST] Yeah, that's that's that's tough. Yeah, it's fascinating that you're thinking about this and I was I wasn't even going into this conversation expecting the breadth of uh of research really. That Microsoft broadly is thinking about you're thinking about Microsoft. So if we go back to uh 89 when Microsoft released office or 1990 when they released Windows three point oh, how's the In your view? I know you weren't there the entire, you know through his history, but how is the company changed in the 30 years since as you look at it now, [/INST] the good thing is it's started off as a platform company life, it's still a platform company. Like the parts of the business that are like thriving and most successful or those that are building platforms, like the mission of the company now is the mission's changes, like, changing a very interesting way. So, you know, back in 89 90 like they were still on the original mission which was like put a pc on every desk and in every home uh like and it was basically about democratizing access to this new personal computing technology, which when Bill started the company, integrated circuit microprocessors were a brand new thing and like people were building, you know, homebrew computers, uh you know, from kits, like the way people build ham radios right now. And I think this is sort of the interesting thing for folks who build platforms in general, Bill saw the opportunity there and what personal computers could do and it was like, it was sort of a reach. Like you just sort of imagine like where things were, you know, when they started the company versus where things are now like in success when you democratize the platform, it just sort of vanishes into the platform, you don't pay attention to it anymore. Like operating systems aren't a thing anymore, like they're super important, like completely critical and like, you know when you see one, you know fail like you you just, you sort of understand but like it's not a thing where you're, you're not like waiting for, You know, the next operating system thing uh in the same way that you were in 1995, right? Like 1995, like, you know, we had rolling stones on the stage with the Windows 95 roll out like it was like the biggest thing in the world, everybody would be lined up for the way that people used to line up for iPhone, but like, you know, eventually and like this isn't necessarily a bad thing, like it just sort of, you know, it the successes that it sort of becomes ubiquitous, it's like everywhere and like human beings when they're technology becomes ubiquitous, they just sort of start taking it for granted. So the mission now that's satya re articulated five plus years ago now when he took over his ceo of the company, our mission is to empower every individual and every organization in the world to be more successful and so, you know, again like that's a platform mission and like the way that we do it now is is different, it's like we have a hyper scale cloud, that are building applications on top of like we have a bunch of ai infrastructure that people are building their a i applications on top of we have uh you know, we have </s><s>[INST] a [/INST] productivity suite of software like Microsoft dynamics, which, you know, some people might not think is the sexiest thing in the world, but it's like helping people figure out how to automate all of their business processes and workflows and uh you know, like help those businesses using it to like grow and be more so. It's a it's a much broader vision in a way now than it was back then, like it was sort of very particular thing and like now, like we live in this world where technology is so powerful and it's like such a basic fact of life that it uh you know, that it it both exists and is going to get better and better over time, or at least more and more powerful over time, So like, you know, what you have to do is a platform player is just much </s><s>[INST] bigger, right? There's so many directions in which you can transform, you didn't mention mixed reality, you know? That's uh that's that's probably early days, it depends how you think of it, but if we think in a scale of centuries, just the early days of mixed reality for sure. And so yeah, with Hollande's uh Microsoft is doing some really interesting work there, do you do you touch that part of the effort, what's the thinking do you think of mixed reality as a platform to [/INST] Oh sure. when we look at what the platforms of the future could be so like fairly obvious that like ai is one like you don't have to I mean like that's you know you sort of say it to like someone and you know like they get it. Um But we also think of the like mixed reality and quantum is like these two interesting, you know, potentially </s><s>[INST] computing. Okay, so let's get crazy then. So [/INST] so </s><s>[INST] you're talking about some futuristic things here? Well the mixed reality Microsoft is really not even futuristic is here. It is incredible [/INST] stuff and and and look and it's having it's have an impact right now. Like one of the one of the more interesting things that's happened with mixed reality over the past a couple of years that I didn't clearly see is that it's become the computing device for for folks who for doing their work who haven't used any computing device at all to do their work before. So technicians and service folks and uh people who are doing like machine maintenance, some factory floors. So like they you know because they're mobile and like they're out in the world and they're working with their hands and you know sort of servicing these like very complicated things. Uh there they don't use their mobile phone. Uh and like they don't carry a laptop with them and you know they're not tethered to a desk and so mixed reality like where it's getting traction right now, where Hololens is selling a lot of, a lot of units is for these sorts of applications for these workers. And it's become like, I mean like the people love it, they're like, oh my God, like this </s><s>[INST] is like [/INST] for them, like the same sort of productivity boosts that, you know, like an office worker had when they got their first personal computer. </s><s>[INST] Yeah, but you did mention it's necessarily obvious ai as a platform, but can we dig into it a little bit? How does a I begin to infuse some of the products in Microsoft? So currently providing um training of, for example, neural networks in the cloud or providing uh pre trained models or uh just even providing computing resources, whatever different inference that you want to do using neural networks. Well, how do you think of ai infusing the as a platform that Microsoft can provide? [/INST] Yeah, I mean, I think it's it's super interest. It's like everywhere, and like we we run these uh we run these review meetings uh now where uh it's bee and Sasha and uh like members of SATa's leadership team and like a cross functional group of folks across the entire company who are working on like either a i infrastructure or like have some substantial part of their of their product work using ai in some significant way now. The important thing to understand is like when you think about like how the Ai is going to manifest in like an experience for something that's going to make it better. Like I think you don't want the the ai nous to be the first order thing. It's like whatever the product is and like the thing that is trying to help you do like the ai just sort of makes it better and you know this is a gross exaggeration, but like I yeah people get super excited about like where the Ai is showing up in products and I'm like, do you get that excited about like where you're using a hash table like in your code. Like it's just another, it's a very interesting programming tool but it's sort of a like it's an engineering tool and so like it shows up everywhere, so like we've got dozens and dozens of features now in office that are powered by like fairly sophisticated machine learning. Our search engine uh wouldn't work at all if you took the machine learning out of it. Uh The like increasingly, you know, things like content moderation on our Xbox and X cloud platform, you </s><s>[INST] know when you meet in moderation to be like the recommended is like showing what you wanna look at [/INST] next, It's like anti bullying, </s><s>[INST] so the usual social network stuff that you have to deal [/INST] with. But it's like really it's targeted, it's targeted towards a gaming audience. So it's like a very particular type of thing where you know the line between playful banter and like legitimate bullying is like a subtle one and like you have to like it's sort of tough. Like I have </s><s>[INST] uh I'd love to if we could dig into because you're also you lead the engineering efforts to linked in and uh if we look at, if we look at Lincoln as a social network and if you look at the xbox gaming is just the social components. The very different kinds of I imagine communication going on on the two platforms and the line in terms of bullying and so on is different on the platforms. So how do you, I mean it's such a fascinating philosophical discussion and where that line is, I don't think anyone knows the right answer. Uh, twitter folks are under fire now Jack or twitter for trying to find that line, nobody knows what that line is. But how do you try to uh find the line for, you know, uh trying to prevent abusive behavior and at the same time let people be playful and joke around and that kind of thing. [/INST] I think in a certain way like you know, if you have what I would call vertical social networks, uh it gets to be a little bit easier. So like if you have a clear notion of like what your social network should be used for or like what you are designing a community around then you don't have as many dimensions to your sort of content safety problem as uh, you know, as you do in a general purpose platform. I mean, so like on on linkedin, like the whole social network is about connecting people with opportunity, whether it's helping them find a job or to, you know, sort of find mentors or to, you know, sort of help them like find their next sales lead or uh, to just sort of allow them to broadcast their, their, you know, sort of professional identity to their, um, their network of peers and collaborators and, you know, sort of professional community like that is, I mean, like in some ways like that's very, very broad, but in other ways it's sort of, you know, it's narrow and so like you can build a eyes, uh, like machine learning systems that are, you know, capable with those boundaries of making better automated decisions about, like what is, you know, sort of inappropriate and offensive comments or dangerous comments or illegal content when you have some constraints, you know, same thing with Yeah, same thing with like the, the gaming gaming social network. So for instance, like it's about playing games not having fun. Uh, and like the thing that you don't want to have happen on the platform is why bullying is such an important thing, like bullying is not fun. So you want to do everything in your power to encourage that not to happen. And yeah, but I think it's it's sort of a tough problem in general is one where I think, you know, eventually we're going to have to have some sort of clarification from our policymakers about what it is that we should be doing, like where the lines are because it's tough. Like you don't like in democracy right? Like you don't want uh you want some sort of democratic involvement. Uh like people should have a say in like where, where the lines lines are drawn, like you don't want a bunch of people making like unilateral decisions and like we, we are in a we're in a state right now for some of these platforms where you actually do have to make unilateral decisions where the policy making isn't gonna happen fast enough in order to like prevent very bad things from happening. But we need the policy making side of that to catch up I think is as quickly as possible because you want that whole process to be a democratic thing. Not a, you know, not not some sort of weird thing where you've got a non representative group of people making decisions that have, you know, like national and global impact. </s><s>[INST] And it's fascinating because the digital space is different than the physical space in which nations and governments were established and so what policy looks like globally what bullying looks like globally, what's healthy communication looks like global is, is an open question and we're offering a freaking it out together. Yeah, I mean [/INST] with, you know sort of fake news for instance and </s><s>[INST] do fakes and fake news generated by [/INST] humans. Yeah, so we can talk about defects, like I think that is another like, you know, sort of very interesting level of complexity. But like if you think about just the written word, right? Like we have, You know, we invented papyrus, what, 3000 years ago, where we you know, you can sort of put put word on on paper and then uh 500 years ago, like we we get the printing press, like where the word gets a little bit more ubiquitous. And then like he really, really didn't get ubiquitous printed word until The end of the 19th century when the offset press was invented and then, you know, just sort of explodes and like, you know, the cross product of that and the industrial revolutions need for educated citizens resulted in like This rapid expansion of literacy and the rapid expansion of the word. But like we had 3000 years up to that point to figure out like how to, you know, like what's what's journalism, what's editorial integrity, like what's, you know, what's scientific peer review. And so like you built all of this mechanism to like try to filter through all of the Noise that the technology made possible to like, you know, sort of getting to something that society could cope with and like if you think about just the piece, the PC didn't exist 50 years ago. Uh and so in like this span of, you know like half a century, like we've gone from no digital, you know, ubiquitous digital technology to like having a device that sits in your pocket where you can sort of say whatever is on your mind to like what what would it mary having or mary meeker Just released her new uh like slide deck last week. You know, we've got 50% penetration of the Internet to the global population, like they're like 3.5 billion people who are connected now. So it's like it's </s><s>[INST] crazy, crazy [/INST] like inconceivable like how fast all of this happened. So you know, it's not surprising that we haven't figured out what to do yet, but like we gotta we gotta really like lean into this set of problems because like we basically have three millennial worth of work to do about how to deal with all of this and like probably what amounts to the next decade worth of time. </s><s>[INST] So since we're on the topic of tough, you know, tough, challenging problems, let's look at uh more on the tooling side in ai that Microsoft is looking at the face recognition software. So there's there's a lot of powerful positive use cases for face recognition, but there's some negative ones and we're seeing those in different governments in the world. So how do you, how does much, I think about the use of face recognition software as a platform and governments and companies, how do we strike an ethical balance here? [/INST] Yeah, I think we've articulated a clear point of view. So brad smith wrote a blog post uh last fall, I believe that's sort of like outlined like very specifically what uh you know what our what our point of view is there and you know, I think we believe that there are certain uses to which face recognition should not be put and we believe again that there's a need for regulation there. Like the government should like really come in and say that you know this is this is where the lines are and like we very much wanted to like figuring out where the lines are, should be a democratic process. But in the short term like we've drawn some lines where uh you know, we push back against uses of face recognition technology. Um you know like this city of SAN Francisco for instance, I think has completely outlawed any government agency uh from using face recognition tech. Uh and like that may prove to be a little bit overly broad. Um but for like certain law enforcement things like you, you really, I would personally rather be overly cautious in terms of restricting use of it until like we have, you know, sort of defined a reasonable, you know, democratically determined regulatory framework for uh like where we could and should use it and you know, the other thing there is um like we've got a bunch of research that we're doing in a bunch of progress that we've made on bias there. And like there are all sorts of like weird biases that These models can have. Like all the way from like the most noteworthy one where you know, you may have um underrepresented minorities who are like underrepresented in the training data and then you start learning uh like strange things. But like they're even, you know, other weird things like we've uh I think we've seen in the public research like models can learn strange things like all doctors are men for instance. Uh Yeah, I mean and so like it really is a thing where it's very important for everybody who is working on these things before they push publish uh they launched the experiment. They, you know, push the code, you know online. Are they even publish the paper that they are at least starting to think about what some of the potential negative consequences are. Some of this stuff. I mean this is where you know, like the deep fake stuff I find very worrisome just because they're going to be some very good beneficial uses of like gan generated uh imagery and like and funny enough like one of the places where it's actually useful is we're using the technology right now to generate synthetic synthetic visual data for training some of the face recognition models to get rid of the bias. Uh So like that's one like super good use of the tech but like you know, it's getting good enough now where you know, it's gonna sort of challenge normal human being's ability to like now you're just sort of say like it's it's very expensive for someone to fabricate a photo realistic fake video. And like gans are going to make it fantastically cheap to fabricate a photo realistic fake video. And so like what you assume you can sort of trust is true versus like be skeptical about is about to change. Uh like we're not ready for it. I don't think </s><s>[INST] the nature of truth, right? That's uh it's also exciting because I think both you and I probably would agree that the way to solve to take on that challenge with technology right? There is probably going to be ideas of ways to verify which which kind of video is legitimate, which kind of not. So uh to me that's an exciting possibility most most likely for just the comedic genius that the internet usually creates with these kinds of videos and hopefully will not result in any serious harm. [/INST] And it could be, you know, like I think we will have technology too that may be able to detect whether or not something is fake or real, although the fakes are pretty convincing even like when you subject them to machine scrutiny. But you know that we we also have these increasingly interesting social networks you know that are under fire right now. Um for some of the bad things that they do. Like one of the things you could choose to do with the social network is like you could you could use crypto and the networks to like have content signed, where you could have a like full chain of custody that accompanied every piece of content. So like when you're viewing something and like you want to ask yourself like how you know how much can I trust this? Like you can click something and like have a verified chain of custody that shows like oh this is coming from you know from this source and it's like signed by like someone whose identity I </s><s>[INST] trust. Yeah [/INST] I think having you know having that chain of custody like being able to like say oh here's this video like it may or may not have been produced using some of this deep fake technology but if you've got a verified chain of custody where you can sort of trace it all the way back to an identity and you can decide whether or not like I trust this identity. Like oh no this is really from the White House or like this is really from the you know the office of this particular presidential candidate or it's really from you know Jeff Weiner Ceo of linkedin or satya Nadella Ceo of Microsoft like that might that might be like one way that you can solve some of the problems and so like that's not the super high tech, like we've had all of this technology forever um and but I think you're right like it has to, it has to be some sort of technological thing </s><s>[INST] because the [/INST] the underlying tech that is used to create this is not going to do anything but get better over time and the genie is out of the bottle, there's no stuffing it back in </s><s>[INST] and there's a social component which I think is really healthy for a democracy where people will be skeptical about the thing they watch in general. Uh so you know, which is good skepticism in general is good in your content. So deep fakes in that sense are creating global skepticism about can they trust what they read? It encourages further research. I come from the soviet union where basically nobody trusted the media because you know it was propaganda and that encourage that kind of skepticism encouraged further research about ideas. You're supposed to just trusting anyone source. [/INST] Well look, I think it's one of the reasons why the you know, the scientific method and our apparatus of modern science is so good like because you don't have to trust anything like you like the whole notion of you know like modern science beyond the fact that you know this is a hypothesis and this is an experiment to test the hypothesis and you know like this is a peer review process for scrutinizing uh published results, but like stuff is also supposed to be reproducible. So like, you know, it's been vetted by this process, but like you also are expected to publish enough detail where you know, if you are sufficiently skeptical of the thing, you can go try to reproduce it yourself and like, I don't know what it is. Like, I think a lot of engineers are, are like this where like, you know, sort of this uh like your brain is sort of wired for for skepticism, like you don't just first order trust everything that you see an encounter and like you're sort of curious to understand, you know, the next thing, but I I think it's an entirely healthy, healthy thing. Uh and like we need a little bit more of that right now, </s><s>[INST] so I'm not a large business owner, so I'm just, I'm just a huge fan of many of the Microsoft products. I mean, I still actually, in terms of, I generate a lot of graphics and images and I still use power point to do that. It beats illustrator for me, even professional, a sort of uh, it's fascinating. So, uh, I wonder what is the future of, let's say, a Windows in office look like, do you see it? I mean, I remember looking forward to XP was an exciting when XP was released, just like you said, I don't remember when 95 was released, but uh XP for me, it was a big celebration and when 10 came out I was like, okay, well it's nice, it's a nice improvement. But uh so what do you see the future of these products? Uh [/INST] you know, I think there's a bunch of exciting, I mean on the office front there's going to be this uh like increasing productivity winds that are coming out of some of these ai powered features that are coming. Like the products will sort of get smarter and smarter and like a very subtle way, like there's not going to be this big bang moment where you know, like clip e is going to re emerge and </s><s>[INST] it's going to be in a minute. Okay, we'll [/INST] have to wait, wait, </s><s>[INST] wait, it's clipping coming back. Well it's quite seriously um so injection of Ai, there's not much or at least I'm not familiar sort of assistive type of stuff going on inside the office products in like a clip e style assistant personal assistant. Do you think that there's a possibility of that in [/INST] the future? So I think there are a bunch of like very small ways in which uh like machine learning powered assistive things are in the product right now. So there are uh there are a bunch of interesting things like um the auto response stuff is getting better and better and it's like getting to the point where you know, it can auto respond with like, okay let you know this person is clearly trying to schedule a meeting so it looks at your calendar and it automatically like tries to find like a time in a space that's mutually interesting. Um like we we have um this notion of Microsoft search where it's like not just web search but it's like search across like all of your information that's sitting inside of like your office 3 65 tenants and uh like you know potentially in other products and like we have this thing called the Microsoft graph that is basically an ap I fed aerator that uh you know, sort of like gets you hooked up across the entire breadth of like all of the, you know, like what were information silos before they got woven together with the graph. Um like that is like getting increasing with increasing effectiveness sort of plumbed into the, into some of these auto response things where you're going to be able to see the system like automatically retrieve information for you. Like if you know like I I frequently send out, you know, emails to folks were like I can't find a paper or document or what, there's no reason why the system won't be able to do that for you. And like I think the it's building towards like having things that look more like uh like a fully integrated uh you know assistant, but like you'll have a bunch of steps that you will see before you, it will not be this like big bang thing where like clip he comes back and you've got this like you know manifestation of you know, like a fully fully powered assistant. So I think that's um that's definitely coming in like all of the, you know, collaboration co authoring stuff's getting better, you know, it's like really interesting like if you look at how we use uh the office product portfolio and Microsoft, like more and more of it is happening inside of like teams as a canvas and like it's this thing where you know, you've got collaboration is like at the center of the product and uh like we we we built some really cool stuff that's some of which is about to be open source that are sort of framework level things for doing uh for doing co authoring. Uh </s><s>[INST] So uh is there a cloud component to that? So on the web or is it um forgive me if I don't already know this, but with office 265 we still the collaboration we do if we're doing word we still send the file around. No, so this is [/INST] we're already a little bit better than that and like, you know, so like the fact that you're unaware of it means we've got a better job to do, like helping you discover discover this stuff but yeah, I mean it's already like got a huge huge clock input and like part of you know, part of this framework stuff, I think we're calling it? Like I we've been working on it for a couple of years so like I know the internal code name for it, but I think when we launched it, a bill is called the fluid framework. Um and but like what fluid lets you do is like you can go into a conversation that you're having in teams and like reference like part of a spreadsheet that you're working on, where somebody is like sitting in the excel canvas, like working on the spreadsheet with a you know, chart or whatnot. And like you can sort of embed like part of the spreadsheet in the team's conversation where like you can dynamically updated, like all of the changes that you're making to the to this object are like you know, cord and everything is sort of updating in real time. So like you can be in whatever canvas is most convenient for you to get your work done. </s><s>[INST] So out of my own sort of curiosities engineer, I know what it's like to sort of lead a team of 10, 15 engineers Microsoft has uh I don't know what the numbers are maybe 50, maybe 60,000 engineers [/INST] and a lot, I don't know exactly what the number </s><s>[INST] Is. It's a lot, it's tens of thousands, right? This is more than 10 or 15 what what what I mean? You've uh you've led uh different sizes, mostly large size of engineers, What does it take to lead such a large group into uh continue innovation, continue being highly productive and yet to develop all kinds of new ideas and yet maintain like what does it take to lead such a large group of brilliant people? [/INST] I think the thing that you learn as you manage larger and larger scale is that there are three things that are like very very important for big engineering teams. Like one is like having some sort of forethought about what it is that you're going to be building over large periods of time, like not exactly like you don't need to know that like, you know, I'm putting all my chips on this one product and like this is gonna be the thing but like it's useful to know like what sort of capabilities you think you're going to need to have to build the products of the future and then like invest in that infrastructure like whether and I'm like I'm not just talking about storage systems or cloud api is it's also like what is your development process look like, what tools do you want? Like what culture do you want to build around? Like how you're, you know, sort of collaborating together to like make complicated technical things and so like having an opinion and investing in that is like it just gets more and more important and like the sooner you can get a concrete set of opinions like the better you're going to be like, you can wing it for a while, uh small scales like, you know when you start a company like you don't have to be like super specific about it, but like the biggest miseries that I've ever seen as an engineering leader are in places where you didn't have a clear enough opinion about those things soon enough and then you just sort of go create a bunch of technical debt and like culture debt that is excruciatingly painful to, to clean up. So like that's one bundle of things like the other, the other, you know, another bundle of things is like, it's just really, really important to like have a clear mission. That's not just some cute crap you say, because like you think you should have a mission, but like something that clarifies for people like where it is that you're headed together, like I know it's like probably like a little bit too popular right now, but uh, Yuval Harari book sapiens one of the central ideas in, in his book is that like storytelling is like the quintessential thing for coordinating the activities of large groups of people. Like once you get past Dunbar's number and like I really, really seen that just managing engineering teams, like you can, you can just brute force, things when you're less than 100 and 20 150 folks where you can sort of know and trust and understand what the dynamics are between all the people, but like past that, like things just sort of start to catastrophically fail if you don't have some sort of set of shared goals that you're marching towards. And so like, even though it sounds touchy feeling and you know, like a bunch of technical people will sort of balk at the idea that like, you need to like have a clear like the missions, </s><s>[INST] like very, very, very important is write, write stories, that's how our society, that's the fabric that connects us, all of us is these powerful stories and that works for companies to it works for everything. [/INST] Like it means even down to like, you know, you sort of really think about like a currency for instance, is a story, A constitution is a story. Hour laws are story. I mean like we believe very, very, very strongly in them and thank God we do, but like they are, they're just abstract things, like they're just words like if we don't believe in them, they're nothing. </s><s>[INST] And in some sense, those stories are platforms and uh the kinds some of which itself is creating, right? Platforms in which we define the future. So, last question, what do you get philosophical, maybe bigger than you have a Microsoft? What do you think The next 2030 plus years looks like for computing for technology, for devices, do you have crazy ideas about the future of the world. [/INST] Yeah, look, I think we you know, we're entering this time where we've got we have technology that is progressing at the fastest rate that it ever has and you've got you got some really big social problems like society, scale problems that we have to we have to tackle and so you know, I think we're going to rise to the challenge and like figure out how to intersect like all of the power of this technology with all of the big challenges that are facing us, whether it's uh you know global warming, whether it's like the biggest remainder of the population boom is in uh africa for the next 50 years or so. And like global warming is going to make it increasingly difficult to feed the global population in particular. Like in this place where you're going to have like the biggest population boom um I think we you know like a i is gonna uh like if we push it in the right direction, like you can do like incredible things to empower all of us to achieve our full potential and to um you know like live better lives but like that also means focus on like some super important things like how can you apply it to health care to make sure that uh you know like our quality and cost of and and sort of ubiquity of health coverage is is better and better over time. Like that's more and more important every day is like in the in the United States and like the rest of the industrialized world, western europe china, japan Korea, like you've got this population bubble of like aging, working, you know, working age folks who are, you know, at some point over the next 2030 years, they're going to be largely retired and like you're going to have more retired people and working age people and then like you've got, you know, sort of natural questions about who's gonna take care of all the old folks and who's going to do all the work. And the answer is to like all of these sorts of questions like where you're sort of running into, you know, like constraints of the, you know, the world and of society has always been like what tech is gonna help us get around this. You know, like when I was when I was a kid in the seventies and eighties, like we talked all the time about like uh like population boom, population boom, like we're gonna uh we're not gonna be able to like feed the planet. And like we were like right in the middle of the green revolution where like </s><s>[INST] this this [/INST] massive technology driven uh increase in crop productivity like worldwide and like some of that was like taking some of the things that we knew in the west and like getting them distributed to the, you know to the to the developing world and like part of it were things like um you know, just smarter biology like helping us increase and like we don't talk about like, yep overpopulation anymore because like we can more or less we sort of figured out how to feed the world, like that's a that's a technology story. Um and so like I'm super super hopeful about the future and in the ways where we will be able to apply technology to solve some of these super challenging problems, like I've I've like one of the things that I I'm trying to spend my time doing right now is trying to get everybody else to be hopeful as well because you know, back to Harari, like we we are the stories that we tell, like if we, you know, if we get overly pessimistic right now about like the the potential future of technology, like we, you </s><s>[INST] know, like [/INST] we we may fail to fail to get all of the things in place that we need to like have our best possible future </s><s>[INST] and that kind of hopeful optimism. I'm glad that you have it because you're leading large groups of engineers that are actually defining that are writing that story that are helping build that future, which is super exciting and uh I agree with everything you said except I do hope clip he comes [/INST] back, we </s><s>[INST] miss them, I speak for the people so Callan, thank you so much for talking [/INST] today, thank you so much for having me. It was </s><s>[INST] a pleasure. [/INST] </s> |
<s>[INST] all that stuff is big. It's amazing that the brain instantly just does all that. The idea that there's there's water, it's liquid and the idea that you can uh drink it when you're thirsty, the idea that there's brands and then there's like all of that information is instantly like built into the whole thing when you want to proceed. I [/INST] wanted to get back to your point about hierarchical reputation. The world itself is hierarchical, right? And I can take this microphone in front of me. I know inside there's gonna be some electronics, I know there's gonna be some wires and I know there's gonna be a little die from them was back and forth. Um I don't see that, but I know it um so everything in the world is hierarchical, you just go into room, it's composed of other components of kitchen has a refrigerator. You know, the future has the door, the door has a hinge, hinges screws and pin, you know, So anyway, the modeling system that exists in every cortical column learns the hierarchical structure of objects. So it's a very sophisticated modeling system in this grain of rice? It's hard to imagine, but this, grand rice can do really sophisticated things. We've got 100,000 neurons in it. Um it's very sophisticated. So the same mechanism that can model of water bottle or coffee cup can model conceptual objects as well. It's if that's the beauty of this discovery that this guy vernon Mount Castle made many, many years ago, which is that there's there's a single cortical algorithm underlying everything we're doing. </s><s>[INST] So common sense concepts and higher level concepts are all represented in the same way there [/INST] stepped in the same mechanisms. Yeah, it's a little bit like computers. All computers are universal turing machines. Even the little teeny one that, you know, my toaster and the big one that's you know, running some cloud servers someplace. Um they're all running on the same principle, They can be like different things. So the brain is all built on the same principle, It's all about learning these models, structured models using movement and reference frames and it can be applied to something as simple as what about in a coffee cup? And it can be just thinking like what's the future of humanity and you know, why do you have a hedgehog on your desk? I don't know, </s><s>[INST] Nobody knows. Well, I think it's a hedgehog. That's right, it's a hedgehog in the fog. It's a Russian reference does it give you any inclination or hope about how difficult it is to engineer common sense reasoning. So how complicated this is this whole process. Looking at the brain. Is this a marvel of engineering or is it pretty dumb stuff stack on top of each other over? Can can be [/INST] both. Can't be both. Right. </s><s>[INST] I don't know if he can be both because if it's an incredible engineering job, that means it's so evolution did a lot of work it? Uh, [/INST] yeah. But then, but then it just copied that. Right? So, as I said earlier, the figure out how to model something like a space is really hard and evolution had to go through a lot of tricks. And these these these cells, I was talking about these grid cells in place else. They're really complicated. This is not simple stuff. This neural tissue works on these really unexpected weird mechanisms. Um, but it did it, it figured it out. But now you can just make lots of copies of it. </s><s>[INST] But then finding, Yeah. So it's a it's a very interesting idea that's a lot of copies of a basic mini brain. But the question is how difficult it is to find that mini brain that you can copy and paste effectively. [/INST] Today. We know enough to build this. I'm sitting here with, you know, I know the steps, we have to go. There's still some engineering problems to solve, but we know enough. And this is not like, oh, this is an interesting idea. We have to go think about it another few decades. No, we actually understand it pretty well details. So not all the details, but most of them. So it's complicated, but it is an engineering problem. So in my company we are working on that, we are basically the roadmap, how we do this. Um It's not gonna take decades, it's better a few years. Um optimistically, but I think that's possible. Um it's, you know, complex things. If you understand them, you can build them. </s><s>[INST] So in which domain do you think it's best to build them? We're talking about robotics, like uh entities that operate in the physical world that are able to interact with that world. We're talking about entities that operate in the digital world. Are we talking about something more like uh more specific, like it's done in the machine learning community where you look at natural language or computer vision? Well, where do you think is easiest to? [/INST] It's the first, it's the first two, more than the third one, I would say. Um Again, again, let's just use computers as an allergy. Um the pioneers of computing people like john Bannerman, I'm touring, they created this thing, you know, we now call the Universal turing machine, which is a computer, right. Did they know how it's gonna be applied where it's going to be used. You know, could they envision any of the future? No, they just said this is like a really interesting computational idea about algorithms and how you can implement them in a machine and we're doing something similar to that today. Like we are we are building this sort of universal learning principle that can be applied to many, many different things. </s><s>[INST] But the robotics piece of that. The interactive [/INST] All right. There has to be specific you can think of this quarter column. Is this what we call a sensory motor learning system and has the idea that there's a sensor and then it's moving. That sensor can be physical. It could be like my finger and it's moving in the world. It could like my eye and it's physically moving. It can also be virtual. So it could be um example would be I could have a system that lives in the internet that that samples information on the internet and moves by following links. That's that's a century motor system. </s> |
<s>[INST] both basically want to kill any independent minded person. Oh, you're equating communism and Stalinism. [/INST] No, I'm equating communism. I don't know what Stalinism is. I don't care. Stalinism is one version of communism. It's an implementation. Communism is an evil ideology, no matter who practices it. </s><s>[INST] It's an implementation. [/INST] I don't think that's too loose, because here's one example. The first person who went to the Soviet Union from the left and denounced it was Emma Goldman. She was an anarcho-communist, right? So she went there. She got deported from the United States. She went to Lenin to his face. Hold on, let me finish. You're already dismissing what I'm saying. Me? Your body language. Your emotions. Listen to history. History doesn't carry your feelings either. She goes to Lenin. She goes, we're supposed to be about free speech. We're supposed to be about the individual freedom. What are you doing? And he goes, free speech is a bourgeois extravagance. You can't have it during a revolution too bad. She comes back to the West. Wait, he's right? Oh, no. Yeah, correct. Yeah, I understand. He's more consistent with the idea. He's more consistent. She's a compromise. Yeah, you're right. Well, she comes back to the West, the big red Emma, the big hero of the left. And she goes, you guys, this is bad. She didn't say bad. She was very random. She goes, this is pure evil. This is horrifying. What they're doing to the workers, which you supposedly care about, completely oppressing. And one person described, they go, when she got up to talk, it was a standing ovation. And when she was finished, you could hear a pin drop because she wasn't some capitalist. She wasn't some bourgeois conservative. She was as hard left for violent revolution as it gets. And so I don't think she, as a communist, is an evil person. Listen to history doesn't carry her. She's a compliment. I think she is. Because if she wasn't evading with Rand, and I think in reality, the essence of evil is evasion, is ignoring the facts of reality, is putting your feelings ahead of your facts. She would realize that what was going on in the Soviet Union was the inevitable consequence of her ideas. That could be just as dumb. So she could have changed her mind. She could have, coming back to the Soviet Union, said, these ideas are wrong. I now repudiate my ideas, not just the implementation, but my ideas. And then I would have said, yeah, she'd been mistaken before. Now she's confronted reality. But if she stayed a leftist, if she stayed a leftist to that extent, not just about mildly, then I think she's dishonest and therefore immoral. Right? So so years, that could be, that could be just so she could have, not just about mildly, but you're using three words identically, you're saying dishonest, immoral and evil, and I'm... Ok, so evil is more, is an extreme form of your morality. Sure. Of course. ok so she's immoral, the ideology she holds is still evil because of the ideology. Maybe she's delusional. She might be delusional. But delusional and even the same. But she can be delusional, she cannot be delusional. But delusional and even the same. Yeah, but I'm willing to accept her delusion before she has gone to the Soviet Union and Cena. Once she has gone to see it. don't think that excuse holds anymore. I think now she's being confronted and she's lying to herself about the implications of it. Logically, it's inevitable that what happens in the Soviet </s><s>[INST] Union has to happen in any communist context. To play a little bit of a devil's advocate here, is it logically inevitable? Can you imagine that there is communist systems where the consequences we've seen in the 20th century are not the consequences we get? Imagine future societies under different conditions, under different, you know, with the internet, different communication schemes, different set of resources. [/INST] Smallest human beings are what we are. Now, the Borg, you remember the Borg from Star Trek or whatever the series was? Okay, nerd. Okay, nerd. Yeah, I mean, okay, okay. No, I, yeah, I mean, okay, okay. No, I'm a nerd, okay. The Borg- The highest of compliments. The Borg? In this household. In this household. The Borg is the highest of Lex. The Borg is… Now we're talking. The Borg is communist, right? The Borg is a different species, it has a different biology, it has a business, different form consciousness. Now, whether such a being could survive evolution is a question. Whether such… Or ants, they don't have to be intelligent. Yeah, but then the question is, can you have free will, a human, a cognitive cognition and be a bork, I don't think so. But maybe, maybe in another planet. You got to take the temps to meet the bork. You got to say temps to meet the... It's human beings, no. The reason communism is evil is its anti reality, anti human nature, anti the individual and therefore it is inherently evil. It cannot result in anything good coming out of it. Only bad can come of it. You could have predicted that before the 20th century. Yes, and plenty of people did. It's not- You know who did? Mikhail Bakunin. Mikhail Bakunin, who was an early communist, Marx's rival, in 18- this is going to be in my upcoming book- in 1860, he sat down and wrote an essay and goes, what Marx is advocating is insane. This is going to be worse than the czar. You're talking about complete totalitarian nightmare. When you put this into practice, it's going to be something we've never seen before. It's a pure horror. He was a hardcore leftist. Look, Marx predicted it, right? We talked about the- Yeah, that's true. Yeah, yeah. Marx at some point says certain people cannot be part of the politician, they have to be liquidated. So this idea of mass murder and mass killing, it's not new to communism. It is an inherent part of what it means. You're either a politician or you're not. And you look- and in Marx, it's in Marx, right? The individual doesn't matter. Now he might matter in his utopia because he knows he's got a marketing problem. See, Marx has a marketing problem because the fact is you have individuals. How do you convince individuals to give up their individualism, to give up their individuality? What you say is, well, we have to go through this difficult process to get to this utopia. And then this utopia- I mean, he's very Christian. I mean, this is the other thing about Marx. But the end times. Marx is very Christian in everything, in his morality, in his collectivism. The end times for Marx is going back to the garden of Eden. The end time for Marx is you don't have to do anything. Health is just available. Wealth is just available. You can do your hobbies, you can do everything. You can do whatever you want. Whatever feelings, whatever. So it's going back to a Garden of Eden perspective on human... He knows what that is going to require. It's going to require this dictatorship of the politician to get there, and he never tells you how we get there. There's no game plan. It would this way. Yeah, yeah. It's the dictatorship, then this utopia. Yeah, the utopia. Go row... It's like Underpants. It's like Underpants. Nothing. question mark. Step three, utopia. Step one. The question mark is where the action is, right? In I Yeah, you yada-yada the important part. And people buy this garbage, right? So there's nothing of value in Marx. I mean, let me be very clear. There's nothing... He gets capitalism wrong. He gets the proletarian wrong. He gets the workers wrong. He gets the labor theory of value is wrong. There's nothing of value. There's nothing of value in communism. It is a wrong, unfitted-to-human nature </s> |
<s>[INST] The hypervigilance loop, is that still with you today? What are the echoes of that that's told you today? The good and the bad. [/INST] If you put yourself in the mind of a young child, the thing that that does to you is at a very core basic level that says you're worthless, right? Because if you can step outside of that and you think about any child in the world, they don't deserve to go through that. And at some point, by the way, I should tell you, like, I don't blame my parents anymore. It was a process to get there, but I feel like they did the best they could and they suffered their own issues and enormous pressures and stresses. And so, you know, I've really, for the most part forgiven them. </s><s>[INST] How did you sorry to interrupt, let go of that blame. [/INST] That was a really long process where For I would say the 1st 35 years of my life, I compartmentalized and I avoided all of those memories and I saw external validation, right? Going back to this self worth idea if you're taught as a child that you're worthless because why would somebody do these things to you? It's not because you're worth something you think to yourself very viscerally you're worth nothing. And so then you go out and you seek external validation. Maybe you try to go and get into a great college, you try to get a good job, you try to make a lot of money, you try to, you know demonstrate in superficial ways with the car you drive or the clothes you wear that you deserve people to care about you to try to make up for that really deep hole. But at some point you it doesn't get filled in and so you have a choice. And so for me what happened was in in the course of a six month period, I lost my best friend and I lost my father and it was really like the dam broke loose because I the compartmentalization stopped working because the reminder of why I was compartmentalizing was gone. And so I had to go through this period of disharmony to really understand and steel man his perspective and can you imagine trying to do that to go through all of the things where you have to now look at it from his perspective and find compassion and empathy for what he went through and then I shift you know the focus to my mom and I said well you were not the victim actually, you were somewhat complicit as well because you were of sound mind and body and you were in the room when it happened. So then I had to go through that process with her and steal man her perspective at the end of it. I never justified what they did, but I've been able to forgive what they did. Um I think they did the best they could and at the end of the day they did the most important thing, which is they gave me and my sisters a shot by emigrating by giving up everything by staying in Canada and doing whatever it took between the two of them to sort of claw and scrape together enough money to live so that my sisters and I could have a shot and I'm very thankful for them. Could they have done better obviously, but I'm okay with what has taken place, but it's it's been a long process of of that steel manning so that you can develop some empathy and compassion and forgive. </s><s>[INST] Do you think if you talk to your dad shortly after he died and you went through that process or today you'll be able to have the same strength to forgive him? [/INST] I think it would be a very complicated journey. I think I've learned to be incredibly open about what has happened and all of the mistakes I've made. I think it's it would require him to be pretty radically honest about confirming what I think he went through because otherwise it just wouldn't work. Otherwise I would say let's keep things where they are, which is I did the work, you know with with people that have helped me obviously, but you know, um it's better for him to just, you know, kind of hopefully he's looking from someplace and he's thinking it was worth it. I think he deserves to think that all of this because, you know, I think the immigrant challenge, we're not even the immigrant challenge, the lower middle class challenge anybody who really wants better for their kids and doesn't have a good toolkit to give it to them, some of them just, they choke up on the bat. They just get so agitated about this idea that all this sacrifice will not be worth it. That it spills out in really unproductive ways. And I would put him in that category </s><s>[INST] and their self evaluation, introspection, their tunnel vision. So they're not able to often see the damage that did. I mean, I know like yourself, a few successful people that had very difficult relationships with their dad and you take the perspective of the dad, they're completely in denial about any of it. So if you actually have a conversation, there would not be a deep honesty there. Uh, and that I think that may be in part the way of life. [/INST] Yeah. And you know, I remember pretty distinctly after I left and in this, you know, in my middle thirties where, you know, by all measure, I had roughly become reasonably successful and my dad didn't particularly care about that, which was so odd because I had to confront the fact that, you know, whether it was a title or money or press clippings, he never really cared. He moved on to a different set of goals, which was more about my character and you know, being a good person to my family and really preparing me to lead our family when he wasn't there. And that bothered me because I thought I thought I got to the finish line and I thought there was going to be a, a medal, you know, meaning like I can tell you lex, you know, he never told me that he loved me. I'm not sure if that's normal or not. It was my normality. And I thought there's gonna be something some gold star which never appeared. And so that's like a hard thing to kind of confront because you're like, well, now what is this, what is this all about? Um, was this all just kind of a ruse? But then I realized, well hold on a second, there were these moments where in his way again, putting yourself in his shoes, I think he was trying to say he was sorry, he would hold my hand, you know, and he would interlock the fingers, which I felt is that's a really intimate way of holding somebody's hand, I think. Um, so I remember those things, so, you know, these are the things that are just etched in, at least in my mind and at the end of it, you know, I think, uh, I've done a decent job in repairing my relationship with him, even though, you know, it was posthumous, </s> |
<s>[INST] of the plague, you open the book with [/INST] that quote from camus, camus brings me to tears. And it's funny because I reread the myth of Sisyphus, which I've been recommending to people like this book is not good, but he's got his ethos is my favorite of all the philosophers. It </s><s>[INST] sounds like the myth of Sisyphus was a myth. [/INST] He says. All I maintain is that on this earth there are plagues and there are victims and it's up to us so far as possible not to join forces with the plagues and why have that as the introductory quotes the book is I think morality and ethics are very, very complicated subjects. There's lots of gray areas where you don't know which way to choose, but at a base level. He has another quote that subscribed to him, he never actually said, but something about um you know, is the duty of thinking people not to be on the side of the executioners. If you are, we should do whatever we can not to have blood on our hands, not to be murderers, not to want death and that in and of itself is a big pill for a lot of people to swallow were all brought up, taught that war is a last resort and yet when it comes to international affairs, it's always often a first priority and people are champing at the bit to start going in and killing people and what war means isn't good guy soldiers versus bad guy soldiers. It my concern is always with the civilians with the kids who become orphans. With the wives had become widows and and things like that and and then communities which are, you know, ruined forever. Uh so I love that quote of his, I think he's I mean the book start it was going to be a re conceptualization of cameras thought I was going to rip off my old buddy vine holiday what he did with the stoics and do about camus. And then when I started reading camus, I'm like, oh I've read more into him than is really there. And then it went to a whole other direction. Uh </s><s>[INST] so you wanted to do almost like an existentialist manifesto. So like imagine that one must imagine Sisyphus happy [/INST] Well more like a move for today And what his philosophy can teachers like Ryan did with his many books about the stoics </s><s>[INST] that [/INST] it was gonna be called The point of tears </s><s>[INST] lived to the point of tears. [/INST] Yes, but the title was given the point of tears that </s><s>[INST] he [/INST] has so many good lines, maybe it's not </s><s>[INST] right. [/INST] You know, he was a big he was a big lothario. He was probably he got around </s><s>[INST] what [/INST] what </s><s>[INST] percent of the audience of humans on earth do you think? Know the word Lothario? [/INST] What percent them have a computer? Look it up. </s><s>[INST] Lothario. [/INST] It's not some weird term. L O T H A R. I O Lothario </s><s>[INST] Lothario. A man who behaves selfishly and irresponsibly in his sexual relationships with women. They're seduced by handsome quotes. They're seduced by handsome lothario who gains control of their financial affairs. [/INST] I didn't think I always thought it was just someone who's like a stud. </s><s>[INST] Like a player, [/INST] but no player. </s><s>[INST] There's a malevolent, malevolent. [/INST] I didn't realize that. Okay, well then </s><s>[INST] he selfishly. [/INST] Okay, that's not him </s><s>[INST] irresponsibly And a man to um although Iran would be proud selfishly, [/INST] she wouldn't like that kind of selfishness </s><s>[INST] behaves a man who behaves selfishly and irresponsibly in his sexual relationships with women. Huh? Yeah. Okay. So he was he was just a player [/INST] not, maybe maybe a stud. I don't think he was promiscuous, particularly. </s><s>[INST] Nietzsche didn't get he got he didn't never got laid right. He [/INST] was </s><s>[INST] like, it was from [/INST] prostitutes. </s><s>[INST] You're asking me like I knew the guy [/INST] I heard it's </s><s>[INST] from um it he'd never had a deep loving fulfilling relationship. He had a very skewed understanding and uh the way he wrote about women. Although somebody wrote to me and said that's a mischaracterization that he was actually very respectful. [/INST] But he had that line, if you're going before women bring a whip. Wasn't that him? But if </s><s>[INST] I were to quote you from your twitter, I think I could make a very convincing argument that you're sexist, racist and probably a nazi. Well, [/INST] I do own </s><s>[INST] like [/INST] some of Hitler's stuff. </s><s>[INST] Exactly. [/INST] I got the I </s><s>[INST] rest my case. [/INST] I feel like I'm in Nuremberg. I'm gonna be hung by his own tie. This isn't a tie. It's a news. </s><s>[INST] You should have thought about that when you were saying all those things. Okay, what do you think of the leak of the twitter files? [/INST] I was so happy that Ellen gave the information to matt Taibi and Barry? Weiss. Who are both by any metric lefties, </s><s>[INST] who are [/INST] both professional journalists of long standing with great resumes and overnight now they're they're doing pr for the world, which the party line was the fact that you had all these corporate journalists now having to play catch up and not having control of the microphone to me was just absolutely amazing. Um, I think transparency is what brought down in many aspects of soviet union and what will bring down what negative aspects of the regime we have here when you see the machinations behind the scenes. And then when you see the rationalizations after the fact you realize, oh these people are not acting in good faith. The fact that for example, the new york post article about the hunter biden laptop and how the, the new york times covered it as well. They didn't mention any kind of dick pics, twitter made it so I couldn't even DM you the link to the new york post article, which was a tool they had previously used only to prevent child pornography. So that shows to what extent they were willing to put their thumb on the scale. But it also shows that for any layman when they're looking at this, to realize what you are perceiving as news or information is very much sculpted, edited and guided by powerful people who have a vested interest in maintaining their power. </s> |
<s>[INST] but there's a balance between I think just like you said, this is the privacy, uh, somehow allows for the intimacy. So like being able to, uh, as opposed to putting putting on an act, which I realize we do when we're visually presenting ourselves in a remote communication. [/INST] But I think that there's so few places where people can actually communicate without the fear of penalty. Those that's the, you know, woefully absent these days. And so maybe people are just relieved to be in a place where they feel like I can say what I want or not say anything and it's okay. </s><s>[INST] And so so clubhouses, you dance to your kind of question is, uh, there was a big improvement to me over discord, which is, it has tiers is, has a stage where people, the person that created the room can invite people up that would like to speak, potentially have the opportunity to speak. And then there's a bigger audience that don't get a chance to speak unless they click raise their hand and they get called on. So there's like a tear system that allows for there to be A group of like 5 10 2030 people talking and a lot larger amount in the audience, which in discord is the problems that everybody could talk. And the other thing about clubhouses, everybody, it is strongly encouraged to represent themselves. So you're using your real name, it's not anonymous. [/INST] How many people were in that game? Stop discussion what </s><s>[INST] They currently, uh limit rooms to 5000. So, I'm sure max out of 5000, there's a lot of overflow rooms. This is the cool thing about clubhouse. Really big people were on there. All tuned in and having a conversation, having all from, you know, all these different worlds. Being able to connect. Even though without the niceties of like arranging the meeting, you could just show up and leave. Which is nice. But the reason I'm, for my lessons from Discord, I am going to mostly stay away from co house and I think, [/INST] or going there under another name, </s><s>[INST] right? Uh, [/INST] Pretend I know the actual you're actual name. one. </s><s>[INST] I've learned. It's quite addicting. It's a it's a time sink. It's so, the intimacy of it is you find yourself wasting quite a bit of time on there. It pulls you in. Well, it's [/INST] interesting. They which sort of going back to the podcast or earlier time about books or creating a technology. One thing that's absolutely clear is that anything that's easy to reproduce is probably not worth much effort and time, Right? I mean, most posts could be easily reproduced. Repost them. So now there are some original posts that for which the attribution goes to the original person and it's clear it came from you. But anything that can be easily reproduced is doesn't really expand us very much as individuals or as groups. And most of what I see on social media is stuff that is purely reproduced. But I think clubhouse, I mean, it could be that some real magic emerges on there. </s><s>[INST] So in moderation can be good. The magic is this is another thing that I've found through. Covid that maybe you can think about is, uh, live. I used to be not understand the appeal of live video or live connection or like in this clubhouse live events. Because clubhouse is technically for the most part, it's not supposed to be recorded. Most people don't record most conversations. It's a one time live event. And there's a magic to [/INST] that. There is </s><s>[INST] that's not captured by a, like your podcast or my podcast produced video that's like recorded like packaged [/INST] up for anything can happen. It's that anything can happen. And those, that, that's the kind of thing, like live concerts. I definitely I love live music. And it's the idea that because you can always listen to the album actually, the album usually sounds cleaner and better, but it's just this idea that anything can happen. </s><s>[INST] And then you listen to like, the parts, I don't know, you, uh, like Costello did something weird, your dog did something weird. And then you have to go, goddamn it. You have to go to the kitchen or something to get something and then you come back and it's funny. I watched live video like that of people and I'll be there for the whole time. I'll wait for them to go to the kitchen and come back it's not like I tune out and that makes it like a richer experience for some reason it's weird. [/INST] Well it humanizes it and I think there is this weird effect of whether or not it's a podcast instagram or twitter or anything else. There is kind of like two people shouting into a tunnel and then a bunch of people with tears at the other end of those tunnels and shouting some things back. You know, that's, that's kind of the format we're in. I think I'll check out clubhouse again. I've gone in there a few times during the day and I was surprised to see how many people were in there in the middle of the day. I was like what are these people supposed to be working? But maybe that is their work </s><s>[INST] will be very careful about the time. Think of it. But yeah, if you want to, you're not go together, we'll have a conversation on there. But one of the things you have to figure out, I don't still know how to do it, but how to exit [/INST] which is you just do that isn't there? The leave quietly button. </s> |
<s>[INST] your better days when you see a positive future, what do you think is the way out of this chaos of 2020? Like if you visualize a 2025 that's a better world than today. What is that? How do we get there? What does that look like? [/INST] It's a good question. I can honestly say. I don't know. And uh, I wouldn't have said, I don't know. A year ago, a year ago, I would have said we're going to be okay as much people hate trump the upon the economy is doing great. I think we're gonna be fine. That's not how I feel today. Today. Uh, I don't think there's a clear solution politically because I think if trump wins, people gonna be furious. And I think if biden wins, people gonna be furious. Um, particularly like if things get more woke. You know, if people continue to enforce this, uh, forced compliance and make people behave a certain way and act a certain way, which seems to be a part of what this whole woke thing is that is the most disturbing for me is that I see what's going on. I see there's a lot of losers that have hopped on this and they shove it in people's faces and it doesn't have to make sense. Like there was a black lives matter protest that stop this woman at a restaurant. They were surrounding her outside a restaurant. They were forcing her to raise her fist and compliance. There's a woman who's marched for black lives multiple times. Black lives matter multiple times and the people around her doing this, we're all white. It's all it's all weird. My friend coach T he's a wrestling coach, is also on a podcast. My friend brian moses his take on it. Is that black? And he's a black guy? He's The Black Lives Matter is a white cult. I'm like when you see that picture, it's hard to argue that he's got a point. I mean, it's clearly not all about that, but there's a lot of people that have jumped on board that are very much like cult members because the thing about Black Lives Matter or any movement is you can't control who joins. There's no entrance examination. So you don't go, okay, how do you feel about this? What's your perceptions on that? Like how like the man who shot the trump supporter in Portland, you know that guy who murdered the trump supporter and the cop shot him. That guy was walking around with his hand on his gun looking for trump supporters. Just want I mean, it's a known violent guy who was walking around looking for trump supporters, found one and shot one that has nothing to do with Black Lives Matter. He's a white guy shot another white guy. It's just it's just madness. You know? And that kind of madness is uh it's disturbing to see it ramp up so quickly. I mean, there's been, there's been riots in Portland's every night. Oh, excuse me, demonstrations for 100 and one days now, 101 days in a row of them lighting things on fire, breaking into federal buildings. It's like whoever saw that coming, Nobody saw that coming. So I don't know what the solution is and I don't know what it looks like in five years. So 20, to answer your question, like it could be anything. I mean, we could be looking at mad max, we could be looking at the, the apocalypse. We could, we could also be looking at an invasion from another country. We could be looking at a war like a real hot war </s><s>[INST] to put a little bit responsibility on you. Like for me, I've listened to you since the Red band, Olive Garden Days. That's the very beginning. And uh, there was something in the way you communicate about the world, maybe there's others, but you're the one I was aware of as you're open minded and like loving towards the world, especially as the podcast developed. Like you just demonstrated and lived this kind of just kindness or maybe even like lack of jealousy in your own little profession of comedy. It was clear that you didn't, you didn't succumb to the weaker aspects of human nature and thereby inspire like people like me who I was, I was naturally probably, especially like the 20s, Early 20s, kind of jealous of the success of others and you're really the primary person that taught me to uh truly celebrate the success of others. And so by way of question, you kind of have a role in this, of making a better 2025. You have such a big megaphone. Is there something you think you can do on this podcast with the words The way you talk the things you discuss that could create a better 2025 [/INST] I think if anything I could help in leading by example, but you know, that's only going to help the people that are listening. I don't know what else I can do in terms of like make the world a better place other than express my hopes and wishes for that and just try to be as nice as I can to people as often as I can. But I also think that I've fallen into this weird category, particularly the Spotify deal where um, you know, I'm one of them now, I'm not a regular person anymore. Now I'm like some famous rich guy. So you go from being a regular person to a famous rich guy that's out of touch, you know, and uh, that, that's a real issue. Whenever you're talking about the economy about just real life problems, </s> |
<s>[INST] I'm a fan of so many people. I love celebrating people, and wearing merch or owning merch is a way to one, celebrate those people. But two, if it's a thing you can wear, you can meet other people, then it starts a conversation, you're like, holy crap, we both like the same thing. Or, holy crap, what is that? I don't know anything about it, tell me about it. And you get to share the things you love with others. It's so awesome. And obviously Shopify is a place you can do that really effectively and make that part of your income a part of your life, a part of your lifestyle, part of your career. So it's awesome that they've created this kind of platform. Sign up for $1 per month trial period at Shopify.com slash Lex. That's all lowercase. Go to Shopify.com slash Lex to take your business [/INST] to the next level today than yours do. </s><s>[INST] But early signs. This episode is also brought to you by ExpressVPN, a VPN provider I've used for many years. Way, way, way before there was a podcast, way before there were a sponsor, there were a source of happiness, a source of security, a source of a kind of blanket protection and help ensure that to whatever degree, at the very basic level, my privacy is protected on the internet. Everybody should be using a VPN. It's in the digital space, it's the first layer of protection. You should definitely be using it. And the one I recommend, the one I've always used is ExpressVPN. There's a lot of other features, like you can watch different shows that are geo-constrained on Netflix and other services. But honestly, to me, the security and the privacy that comes with the VPN is the big plus. And the other point is with ExpressVPN, it's fast and it works everywhere, works on Linux. I don't know why that's such a awesome thing for me. Maybe now it's obvious, but in the early days when they worked on Linux, like early, early days, I don't know how many years ago, but I was like, holy crap, this is so awesome. This is so awesome that they care about this operating system that I love so much. So yeah, it works anywhere. Android, your iPhone, all of that. By the way, I should mention that the peer pressure I have to switch to an iPhone. I do have an iPhone, I just don't use it. The peer pressure is immense, but I remain with the Android. It is the phone of the people. I still like the customization. I like developing for the Android as well. And I have several Android phones and I love them very much. The customization, the freedom, actually the principles that's behind it. But of course, I also love beautiful design. Johnny Ives is one of, if not the greatest tech designers of all time and he's a hero of mine. He's somebody that inspires me as a human being, as a designer. So all of that combined, I don't know. I should be using both actively and giving both love and developing for both. Let's see what the future holds. The point is ExpressVPN works across all of those, no matter what choice I make. Go to expressvpn.com slash LexPod for an extra three months free. This is the Lex Friedman podcast. To support it, please check out our sponsors in the description. And now, dear friends, here's David Backman. Are there interesting differences to you between terms like liberal, Democrat, left-wing, leftist, progressive, socialist, communist, Marxist, far left, center-left, all of these labels. [/INST] Is there interesting distinctions between them? Yeah, there's two sets of distinctions. One is if you just want to say, let's define each of these as political terms. They're all different terms. You can be a progressive ideologically but not be a member of the Democratic party. Many say the Democratic party isn't even really very progressive. So these are certainly terms that we could define in order to have a conversation about the next thing kind of as a precursor to a conversation. Sometimes the terms are used in order to tag someone with a certain ideology that's not really linked to policy or any particular political question, but they can be used positively or negatively to just kind of say, here's the image of this individual that I have in my mind. So like Marxist is right now very popularly being used by some on the right to attack Democrats. There's very few actual Marxists, certainly not in positions of power in the United States but even among the general population. So I think it's important to distinguish are we defining these terms because we want to compare and contrast the ideas that a particular group might bring to the discussion or are we using them as insults or to stifle conversation? There are terms that can be used to start a conversation </s><s>[INST] or to stop it. And the use of those terms is evolving rapidly month by month. So the term leftist, I think is a relatively popular term now to use in the negative context to describe [/INST] what an outraged left wing commentator. I think what you're kind of grasping onto is that there's probably some set of ideas that would apply to most of those who consider themselves to be on the left. The discussion of how that term is mostly being used is not about policy ideas. You're accurately kind of identifying that. And it does seem like progressive is no longer being used as a smear and leftist is being used as a smear </s><s>[INST] more at this point. Okay, but sometimes some of these terms are useful. Like can we try to pick the terms that are useful [/INST] like liberal and progressive and Democrat </s><s>[INST] and liberal and progressive. Is there an interesting definable distinction [/INST] between liberal and progressive to you? That's maybe one of the most interesting ones. 10 years ago, liberal often meant what now we mean by progressive. More recently, the progressive socialist leaning part of the political spectrum has started to use liberal to mean Joe Biden, to mean someone who is not really left enough. So liberal is very interesting because I remember talking with my audience years ago, maybe eight years ago or something like that, where I identified, I'm going to now use the term progressive more commonly to describe my own beliefs because liberal has now been made a smear, it's being shifted into something else and it also means more of like a center left politics. So it's changed in some sense by necessity, by force </s><s>[INST] and also because the spectrum has shifted to some degree. So the term liberal has evolved. Now liberal meaning some kind of embodiment [/INST] of the mainstream democratic party, almost. To some degree, sometimes I'm called, I'm written off by, within my space, there are all sorts of shades of gray, which I'm sure we can talk about, about where I am versus should be, could be, or am wrongly placed. And sometimes an attack on me is he's just a lib, meaning I'm not left enough. I'm not progressive, socialist, wherever else you want to go. So yeah, the problem with a lot of these terms and they're used very casually by people who call into my show, is that unless we actually define them each time, they very often mean very different things to different people and often come with an agenda attached to them. And so I find that they often stifle meaningful conversation </s><s>[INST] rather than encouraging. Do you sense that there's a drifting of what is the threshold to be a progressive or should be used progresses synonymously [/INST] with the democratic socialist? I think we should not use it synonymously with democratic socialist. And this is where there is another linguistic confusion and a political confusion. So we'll first talk about the linguistic one. Social democracy versus democratic socialism. Very similar words in a different order, okay? The way I operate is democratic socialism is actually a form of socialism where one would seek to socialize ownership of the means of production as an example. Social democracy is a very highly regulated form of capitalism, the likes of which we would see in Northern Europe, Denmark, et cetera. These are very different things. I associate progressivism in 2023 with social democracy and would consider democratic socialism a form of actual socialism that is different. We're no longer talking about </s><s>[INST] a capitalist organization of society. So transition from one to the other [/INST] is a fundamental shift in how society operates then. Absolutely. And when you talk about social democracy, you're talking about socializing a couple more things than we socialize in most modern capitalist countries. I had this conversation with Patrick Bet David recently. Social democracy is, okay, we've socialized the military already in the United States. We've socialized some healthcare in the sense of like the VA and Medicaid, et cetera. We're talking about socializing a couple more things still in a capitalist country. Democratic socialism would be something beyond that. And as someone who is not a democratic socialist myself, I'm maybe not the best advocate for explaining exactly how that system would function, but it would have some version of socializing </s><s>[INST] of ownership of the means of production, businesses, et cetera. So you mentioned you appeared on the PBD podcast with Patrick Bet David. The debate was pretty intense. I should say I personally enjoyed it. I thought, actually you did well and I thought Patrick did well and it was a good conversation. I thought there was a little bit of tension. And I thought that Patrick actually, so I disagree with the internet. I thought Patrick just took on a kind of devil's advocate. Like he was purposely being stubborn to bring out the best in you. But the internet thought that he's being stubborn and not being open to your ideas. I thought the tension between ideas, I think a lot of the tension had to do probably [/INST] with Donald Trump and Trump supporters. There was a little bit of- Yeah, that certainly could be the case. And people wrote to me after, people wrote to me the full gamut of everything you can imagine from this was your best thing you've ever done in public to you got humiliated and your mother should have aborted you. Okay, and everything in between. So take your pick. But the most interesting feedback I got was from people who asked me after was incredibly tense and awkward and because it seemed so combative. And I think I'm so used to those types of tensions in the discussions that I have that it's very comfortable to me. It's not like afterwards there's a grudge or it's tense or whatever the case may be. I'm very comfortable. I disagree with people and that's it. So I did not find anything that happened inappropriate. </s><s>[INST] I disagreed with a lot of the things he said, certainly. So you've also spoken with Michael Knowles, I think about the idea of what is a woman. Can you speak broadly about your conversation with the people you disagree with? [/INST] Some of the cases, it feels like it's gone wrong. What is a woman? The conversations have gone wrong. Yeah, I mean, I think there's a couple of different things and I'm the first to tell you that depending on who I'm talking to, I go in with a different attitude about how quote seriously I'm taking it in the sense of whether I think it's going to be a deep policy discussion versus whether it's going to be more of a performance for an audience that is expecting a certain thing. And I think there's different types of shows. When I was interviewed by this guy, Jesse Lee Peterson in Los Angeles, it's very different, for example, than when I'm talking to Patrick Bette David, just to give two examples. I think the reason I stopped doing the Michael Knowles show was the number of threats I would get after the fact. That's really the reason, I was glad to engage with him to the extent that the interviews were interesting and we could organize it reasonably efficiently. But the reason I stepped away was sort of the aftermath. But I did find him to be someone who was abundantly clear about his view and where he comes from. And while I could not possibly disagree more with him in terms of politics and culture and our backgrounds, everything is just so different, I found it easy to engage in the conversation just because of how upfront and clear he was </s><s>[INST] about what his beliefs were. [/INST] But the number of threats, it's too much. Yeah, it was just too much. And I don't know how much you saw about this recent Twitter dustup I was involved in that peaked with Donald Trump Jr. tweeting about me </s><s>[INST] and then declining from there. Let's talk through it, I didn't see it. I have to understand, like the way you study Shakespeare, I have to study your Twitter. I have to understand how much of it is sarcasm. [/INST] It's mostly sarcasm, okay, it's mostly sarcasm. I mean, here's the thing, and I know that there are people who will say, David, you're dealing with such serious issues. It's really not okay not to take everything you do completely seriously. But my view is it's so incredible that I've between chance and timing and so different things fallen into a position where this is what I do professionally. And it's a career and it's financially sustainable and all these different things. I don't want to end up taking myself too seriously because I recognize the timing and luck and all of these other things. And this could have gone a completely different way. So my approach to a lot of this is let's not take ourselves too seriously. And in particular on Twitter, a platform that, you know, the degree to which it should be taken very seriously maybe has changed over time. I'm always sort of thinking a little bit tongue in cheek </s><s>[INST] on Twitter. So what happened with Donald Trump Jr.? [/INST] Or the full arc of it? So yeah, to give you a one minute arc and then we can pick whichever parts we want. After a mass shooting, now you might say there's like two or three a day, you're correct. After the Nashville mass shooting at a Christian school, I tweeted snarkily tongue in cheek to point that thoughts and prayers not only aren't particularly useful after a shooting, they also don't prevent shootings, that there's some confusion about how there would be a shooting at a Christian school given that it is a place where prayer is taking place. I think I, you know, jokingly said something like </s><s>[INST] were they not praying enough for correctly? I think in my deep journalistic integrity. You have it. I have your tweet. This is the only display of journalistic degree I will show today, okay. And then I have a couple responses. Beautiful. And you deleted the tweet since then. [/INST] Which I regret. </s><s>[INST] You have it, which I regret. Oh interesting. And we can talk about that. [/INST] I would love to, because it's such a interesting decision </s><s>[INST] and we can talk about that. Because when you tweet something, one of the things I've also learned is you don't often understand how it's going to be read. It's going to be analyzed, like I mentioned, Shakespeare. There's certain, the use of certain words that you regret saying in a certain kind of way. Maybe just because it wasn't as eloquent as powerful. It didn't actually convey the thing. Or it's a distraction to the main message, all that kind of stuff. Okay, the actual tweet is very surprising that there will be a mass shooting at a Christian school given that lack of prayer is often blamed for these horrible events. Is it possible they weren't praying enough or correctly just by being a Christian school? And a lot of people quote, retweeted that, which I'm assuming was a criticism. So Colin Wright wrote, I used to consider you a reasonable progressive, but you clearly devolved into partisan hackery. I'm an atheist. It cannot begin to fathom using the murder of children and adults at a Christian school as an opportunity to dunk on the concept of prayer. And you responded, I'm dunking on the people who send thoughts and prayers and do nothing else. And the shootings continue. [/INST] Okay, I'm sure there's a lot of other interaction. There's a few other 100,000 interactions. So do you want the arc leading to the deleting? So basically- I just wanted to display the- Do you know what time of day I tweeted the original one? I feel like it was in the afternoon or evening </s><s>[INST] of on a Monday deleting. So basically- I just wanted to display the- 3 42 PM on 27th, March 27th. Which was a Monday. [/INST] Okay. Which was a Monday. Okay. So basically I tweet that and then I finished the day. And I- So you tweet and then you go on with your day. I might've looked once at Twitter and it had 2000 likes and a few people saying, eh, this might've missed the mark, but it's sort of like it's one of my 20,000 tweets. I don't know. I wake up the next morning, my baby daughter did not sleep till 7 30, the way I would like. So she's up at 6 AM and I get up and I'm just there starting to make breakfast. And I glance at my phone and I'm starting to- This was when verified meant a different thing than it means now. I'm seeing all these verified accounts that are, you know, quote, tweeting it and demanding a retraction and whatever. And I go, oh, okay. This looks like it's getting, looks like it's getting some attention. I then continue about my day. Around noon, I hear from my dad that he got a hundred messages from, you should have aborted your son to we're going to find all of you to whatever else. My dad has no idea what's going on. He's like, I don't know what this is, but I have a hundred DMS to everything else you can imagine. And I start to get emails about, you know, we, you know, your Jewish faith, this and that and the other thing. And so at that point to me, I thought this is just going to get worse and worse and worse. And so I deleted the tweet. And I really regret doing that because over the 48 hours that followed, yes, the attacks escalated. It went through Candace Owens and then at Fox news.com Newsmax kind of peaking with Donald Trump Jr. And it was horrible. I mean, thousands and thousands of the, okay. But once I told my audience about what happened, I got thousands of messages from people saying, David, only someone who doesn't know you and is determined to interpret this in the worst possible faith would think you're blaming kids who died for getting shot. Of course you weren't doing that. I wish you hadn't deleted it so that it would still be up and you would now see the tide kind of turning on it. This was not a fun three days regardless, but I do regret having deleted it because I wanted to do the quickest thing I thought I could to get people to stop trying to find family members and send them threats. And so around noon, that's what I did. And the truth is the threats didn't stop anyway because everybody had screenshotted it. </s><s>[INST] And I do wish I had left it up. And is there some degree, maybe stepping outside yourself, do you regret tweeting that? In that it feeds the mockery engine that fuels Twitter. [/INST] So like, does that tweet really represent what you believe? It absolutely represents the disgust with a politics that includes saying, we can't touch guns, we just, we can't. But we're willing to point to mental health or say we need more prayer in schools or whatever. 1000%, it represents that view. Is it the type of snark and sarcasm that I would use if given an hour to discuss the topic rather than whatever the number of characters is now on Twitter? No, definitely not. And so I am very cognizant of the fact that </s><s>[INST] it was unnecessarily provocative how it was written. I think I asked a similar question to Ben Shapiro. Do you worry that this style of presentation can turn you from being a deeply thoughtful, objective political thinker to somebody who is just a partisan hack or partisan, [/INST] what's a good word, talking head? Do you mean with regard to Twitter </s><s>[INST] or the format of my show in general? So Twitter for now, let's start with Twitter for now. And can you silo your style of communication on Twitter from being a virus that affects your mind? [/INST] Right. I don't have deep thoughts about the Twitter component beyond, I think, across all sorts of disciplines. This is not the best way to most effectively solve problems and figure out solutions to complex issues. You're talking about Twitter. Right now I'm talking about Twitter. That being said, I think all of us, to some degree, have to adapt our content to the platform that we're using in the same way that what I post to YouTube is different than what I post to TikTok. What I post to Twitter is also different. Do I think Twitter has been an unmitigated good for society? No. Have I chosen to step into Twitter as one of the ways in which I get my message out with the good and the bad? Yes. And I think that there is a deep conversation to be had there. I think zooming out a little bit in terms of what I do, and I was hoping this would come up because I think it's really interesting. I will often get emails from people who say two things. I will get the, you would have such a bigger audience if you did X type emails. And usually they are plays to sensationalism, salacious and titillating content, more pop culture stuff, et cetera. On the other hand, it's folks who say, listen, what you're doing really isn't as serious as it could be. And it seems like you could do something more serious and you should consider doing deep dives. Once it was, do a deep dive into Calvin Coolidge. And I was like, nobody will watch that. So there it's not by accident that my show is the way it is, right? In an hour, I'm thinking of all the platforms I'm on and I'm saying, okay, I want to do a relatively deep dive on the federal budget. And I want to talk about some of the political tomfoolery going on within the post office. And I'm going to do a segment about the wacky rally where Trump said crazy things and made up three words and said he endorsed a candidate who's named it, right? I'm crafting that in total to find a balance between let's build this audience as much as I can in order to have a bigger base to get my message out there and include the more serious stuff with the hope that there's a little bit of something for everyone. And I'm finding a balance between those two sides of the spectrum. It's a deliberate thing. And I'm aware that if I were producing my show 50 years ago, the balance would probably be different and it would probably change again. If we didn't, if the show was audio only rather than having all these video platforms, it would also be different. But it's a decision that's proactively made to try to get the best and most out of the hour </s><s>[INST] that I'm creating every day. You're talking about Twitter. It just feels like there's an entire machine fed by Twitter and journalism that wants to divide people and the drama of that division, highlighting the partisan division, the drama of that division feels like it's a tension with objective clear thinking sometimes. And so that's the, I worry that there's a drug to it. There's too much fun to mock ridiculous people [/INST] on the other side of that division. I think you're right about that. And the fact that that is true to me supports, I've talked with my audience about, you know, like the old food pyramid, which I guess was like wrong, but let's imagine that there was a pyramid that made sense. What's in the bottom bread? I think like whole grains maybe, I don't remember. It's been a white dice on top. Junk food is at the very top. I'm very open with my audience. The vast majority of what I do is the top of that pyramid. </s><s>[INST] What's on the bottom bread? [/INST] I don't remember it's been a white dice on the top and I tell people very openly, I don't consume a lot of the type of content I produce. And I think it's really important to, as a base, be doing critical thinking, epistemology, how do we believe the things we believe, basics about the world. After that, reading history, economics, philosophy, et cetera. After that, now we're getting into current events. I would mostly be looking at consuming primary source reporting, things like associated press, whatever. I know everybody will have a different list of what counts there. After that is when I'd say indulge in some of the commentary type stuff that I do. If you find that I'm thoughtful enough to make it into that, but I'm very open. And really what I try to do on my show often is in being that at the top of the pyramid, tell people there's all this other stuff that should be forming your foundation that I hope you're consuming in addition to just watching me. </s><s>[INST] And I'm very open with my audience about that. What about the shape, the dynamics, the characteristics of your audience? Is there some degree to which you're through mocking maybe Republicans that there's a lean to that audience and then you become captured by the audience? [/INST] Do you worry about the audience capture? I worry about it. I'm relatively comfortable that it's not shaping the program to a great degree in the sense that at this point I have a pretty good sense of the things I can say that will upset what I might call my core audience. One of the interesting things just to briefly go back to the Twitter thing was those people who were furious with me on Twitter and they contacted my advertisers and some advertisers dropped me and on and on and on. None of them are actually in my audience. None of them are regular consumers of my audience. They were kind of weaponized against me by people who said, hey, look at this. The people who follow Candace Owens on Twitter other than for their kind of shock value, they're not in my audience. And with my core audience, I know there are things I can talk about that will generate displeasure, I guess you could say with my audience. Sometimes when I touch the Israeli-Palestinian conflict, that will happen. Sometimes on vaccines, there's a portion of my audience that is more generally skeptical of vaccines, sometimes on some foreign policy issues, or I'm not a big fan of Marianne Williamson nor Bobby Kennedy Jr.'s challenges to Joe Biden, not because I love Joe Biden, but because I don't consider them to be the most serious challenges. I know there's people in my audience who don't like that. They get mad at me about that. And I'm totally okay with that. And that tension with my core audience. So in that sense, I don't feel as though I've had that audience capture take place, but I know it can happen. And I'm very open to being told ways </s><s>[INST] in which it may be happening without me noticing. So I've made a call for questions on Reddit for this conversation. There's a lot of good questions that I'll probably bring up. But one of them was about Marianne Williamson asking why David thinks she is a garbage candidate. Which of course- I've never said. But perhaps you have more eloquently criticized. So let's go there to the 2024 election. Okay. So Joe Biden officially announced that he's running again. [/INST] Donald Trump officially announced that he's running again. </s><s>[INST] I've never said, okay. [/INST] And if that's the matchup, who do you think wins? If the election's held today, I think Biden. Why? Well, first of all, I believe he won last time. And if I start with the results from 2020, and I think to myself what has happened since then that would push or pull voters one way or the other, I have a hard time making a case that Trump is in a better position today than he was in November of 2020. So that's kind of my starting point, which is it's a rematch of an election with a known outcome. What has changed? And I can't make a case for circumstances having changed in Trump's favor to give a couple of state level examples. Florida seems to be kind of moving more to the Republican side since 2020, but Trump won that state already in 2020. So it wouldn't really change the outcome. Arizona was close. I think Arizona has moved to the left since 2020. So I don't see Trump taking that one. Wisconsin, I think the same sort of thing applies. So being very like practical, </s><s>[INST] that would be kind of the start of my reasoning. Do you think Joe Biden is a better candidate now [/INST] than he was in 2020? And is it? I think he's a worse candidate. This is going to sound ageist, but I think he's a worse candidate in that he's even older and there already seems to be an appetite for younger candidates, particularly on the Democratic voting side. So he's going to be four years older. And in a sense, that could be a liability. However, he also is going to have four years of accomplishments. Now you might not like the things he's done, in which case that would hurt him, but he has started to accumulate not insignificant number of accomplishments. Some of the big things that are known, Inflation Reduction Act and COVID stimulus, but also less well-known things like a bunch of little tweaks to healthcare, a bunch of little tweaks to student lending. There's been a lot of little things at the macro level. I don't actually think Joe Biden has that much to do with this, the same way I didn't credit or attack Trump for a lot of the macroeconomic stuff, but inflation has started to come down significantly. The stock market's quite steady. Yeah, these sort of things. I think looking historically, it's a pretty okay environment for Joe Biden, with the exception that he was already the oldest president to be inaugurated in 2021. And he would beat his own record in January of 2025. </s><s>[INST] And I just don't know how voters are gonna see that. So in terms of just a public human being, how would you compare Trump and Biden? So if I were to give criticism towards Trump, it would be that he's chaotic, maybe to the point of being disrespectful to a lot of different groups, to a lot of different ideas, to a lot of different nations and leaders and all that kind of stuff. And then the criticism towards Biden would be that maybe perhaps because of age or any other kind of cognitive capabilities is not really there mentally, in the way that perhaps you could say that Barack Obama was there, just mentally being able to handle all kinds of aspects of being a public representative of a nation to the world and to the people of that nation. So which in the competition of personality flaws, [/INST] which do you think is more powerful? There. There's a way that you played out fair and I believe accurate assessments of elements of both of those men. You haven't weighed in on to what degree you value each of those assessments, which is where I think the kind of meat of this question really is. I don't see, and I know that Biden's gonna get us into World War III, World War III, that doesn't seem to be happening. I don't see the Biden deficits you listed, which I agree with you on. I don't see them as dangerous or threatening to the standing of the United States in this kind of environment with our Western traditional Western allies and geopolitics, et cetera, in the way that the sort of unhinged personality of Trump, combined with his lack of knowledge about most issues, is a threat. So for me, if those two are the candidates Biden would be my choice. Now, are there people I would rather see on the Democratic side? Yes. If I knew the president would be a Republican, can I think of better options than Trump? Absolutely, you know, it's so funny. When in 2012 it was Obama versus Romney, the difference seemed so significant between them. Thinking back, I'm sure I would disagree with Mitt Romney about tax rates and his views on LGBT, or I'm sure I know are different than mine, but it seems without looking at him with rose-colored glasses, so comparatively benign given the four years of Trump. </s><s>[INST] So that's kind of where I come down. Even McCain and Obama, [/INST] the differences seem quite drastic. Yeah, McCain was interesting because Palin, as his running mate, opened the door to the sort of cartoonish stuff that we've started to see on the Republican side. Palin, Trump, Marjorie Taylor Greene, it started going in that direction, which has made the party a bit of a joke, aside from what you believe the tax rate would be, right? You can say taxes are too high, but Jewish space lasers, come on, you know? </s><s>[INST] So, but I agree with you on McCain also. So, going back to the political terms we talked about, where in that spectrum do you place yourself today? Which of the label do you think [/INST] captures your political views today? Progressive Social Democrat, which again, is a capitalist. I own my own business. I pay the taxes I'm legally required to pay and not a penny more and, you know, all those things. </s><s>[INST] That's where I place myself. Would you place yourself to the left of Joe Biden? Yes, yes, yes. Where does the AOC fit into that? It's a good question. What do you think about AOC as a candidate? [/INST] Do you think she eventually runs? I think that if she doesn't run into some kind of scandal, and I don't mean scandal in the sense of some personal impropriety that, you know, but I mean some kind of major political problem, it seems that she has the staying power to be in American elected politics for a long time, whether she would even want to be president versus maybe going to the Senate or being governor or whatever the case may be. I have no idea what her ambitions are in that sense, but certainly like policy aside, she has this combination of charisma, likability to some, but also something about her personality that angers the people who don't like her in a way that only fuels her sort of presence, which I think applies to Trump as well, that I do think that she has the potential to be, to have significant staying power in American politics. </s><s>[INST] President, I don't know. President, I don't know. Do you think that's the future of political elections and politics in general? Is people who are able to skillfully piss [/INST] off the other side like AOC and Trump did? I think it's an aspect of it. I think it's also understanding how to communicate policy ideas. Trump, I have things I can praise Trump about if we want to get to that segment at some point, you let me know when that is, but I do think that there are some things Trump is very good at. And this is why it's very hard for me to believe that Ron DeSantis has what it takes to actually fight Trump in a national primary. And one of those things is Trump has, even though he often says very strange things that if you transcribe them, you go, what language is that? That doesn't make any sense whatsoever. In the moment, the way he relates to adversaries on stage, et cetera, is very good in that he is very much aware of how it is going to be seen by the audience. And so that's why a lot of times it's more about, doesn't matter that a word salad came out of his mouth, how he immediately responded and related to the person, very good. So I think that knowing how to be good when clips are shared all the time, often out of context is extraordinarily important. Knowing how to use social media, which every election cycle, that means something different, but understanding how to use social media, very important. Those things are absolutely so important. And whether you're able to do a deep dive on the deficit, certainly useful, but I would say it's a bad thing. It's becoming less important </s><s>[INST] in terms of figuring out who we want to represent us. So just lingering on the AOC, and then maybe let's throw in Bernie Sanders on that. Yeah, yeah. So where do you place yourself and how do you do the layout of the land of Bernie Sanders, AOC, Joe Biden, and David Pakman? [/INST] My instinct is, and I'm going to answer it, the thing that makes this tough is, Bernie says he's a democratic socialist. He ran as a social democrat. He didn't run on anything that was really socialism. </s><s>[INST] So I'm going by their public facing platforms. I've been listening to him for many, many years and all the way back to the Tom Hartman show. And I think using the terms as you've been using them, he has, I don't think, ever been a democratic socialist. I haven't heard him speak about socialism. I think I've heard him speak about social programs and the value of social programs throughout the history of the United States [/INST] and how they've been beneficiaries. My understanding is very similar to yours, although there may be stuff from the 70s where he really was talking about- We've all did shit in the 70s, hasn't we? Yeah, you and I even, who weren't around- Yeah, I feel like we- </s><s>[INST] We were doing stuff in the 70s. We've all did shit in the 70s. We were doing stuff in the 70s though- Yeah. [/INST] Yeah, I feel like we did, yeah. My sense would be, Biden is like center left and then I'm to the left of that but maybe just inside of where AOC and Bernie are, very, very similar to Bernie. I mean, I identify with a lot of Bernie's ideas. Maybe their implementation I'm more flexible on. I'll give you one example. Medicare for All. One way of trying to get healthcare to everybody, which Bernie's very big on, is you take the current Medicare program, you just eliminate the age limit, make it available to everybody, pay for it through taxation. Interesting. However, I'm open to other models if they get everybody healthcare. That is good quality and affordable. Singapore has an interesting model. Germany has an interesting model. I am more agnostic about how we do it than just saying, let's expand Medicare. Whether that puts me to the right of Bernie, I don't know, but I'm not like exactly right there </s><s>[INST] on it has to be Medicare for All. Yeah, that's more of a, that's more just flexibility versus dogmatism. So I don't know if that puts you to the left or to the right. I don't either. What do you think about the term manipulation or the corruption in the DNC that perhaps tipped the scales against Bernie in the election? Do you think there was such a thing? [/INST] In 2016 or 20? To the right. I think there was such a thing. </s><s>[INST] In 2016 or 2020? Both, I would say. In different, the dynamics there were different with Hillary Clinton and like the pressure from Hillary Clinton as a candidate and so on. Yeah, I mean, was there, why didn't Bernie win? I guess there's one way to ask. [/INST] Okay. I think there's a couple of things here. First, the DNC, I'm not a Democrat. Just your audience may not know. I'm just a independent. I mostly vote for candidates that end up being Democrats in local elections. Often there's no party designation. So, okay, I'm obviously on the left. I'm not denying that, but the Democratic party as an institution has never really been interesting to me. </s><s>[INST] You're still a rebel that resists belonging to any institution. [/INST] Exactly right, exactly right, exactly right. And whether it matters, I don't know. The DNC and the RNC really are organizations that to some degree exist to justify their own existence. Because if they were no longer necessary, they would go away. And so they have to assert their value and their importance. They do this in a number of different ways, organizing the way that the nominee has chosen, the convention, working with states on everything from redistricting to whatever else the case may be, setting the order of primaries and having some involvement in how that's all going to happen. And also coordinating behind the scenes, I guess they would describe it as making sure our candidates don't get in each other's ways. We might see it and say they're picking the winner. There's nothing illegal about them being involved in picking the winner. But we might say it's not in people's interests. I think the 2020 primary was really interesting. Bernie's supporter, myself, I started telling my audience after a couple primaries and even before based on polling and different things, I see a real uphill battle here for Bernie. And it's really important, people in my audience are not the average union worker in Michigan who is mostly working and raising a family and then goes to vote on primary day and goes to vote on election day. If you spend a lot of time on Reddit and Twitter, you're going to have an inflated sense of Bernie's popularity within the Democratic party. That was my sense. And to some degree, we saw that in certain states. I don't have the exact primary order and results in front of me or in my head, but the big turning point was South Carolina. South Carolina was when Joe Biden won and won handily, understood to be because of the larger African-American population in South Carolina. And right around that exact same time, I actually don't remember now whether it was the day after or the day before. Some of the smaller Democratic candidates, smaller in terms of support, got out and said, I'm endorsing Joe Biden. And to some degree, of course it was all organized and timed to help Joe Biden. There's no doubt about that. This is what the DNC does. It's hard for me to be mad at the DNC because this is sort of like, if we believe they were there to be unbiased arbiters and to stay as much on the side as possible, it would make sense to be furious that they've gone against their stated kind of mandate. But we know that the DNC negotiates and is working behind the scenes and has a favorite. That favorite was Hillary in 2016, 2020. So I share the frustration about the power that the DNC has, but for people who were saying they did something illegal or whatever else the case may be, that doesn't seem to be the case. But this is part of why, I mean, I would love there not to be this duopoly of Republicans and Democrats. And there's probably four major changes that have to happen in order to make that a reality. But I share the frustration of folks while recognizing that Reddit was not accurately representing </s><s>[INST] Bernie's level of popularity. Still, I wish that the bias wasn't towards what could be negatively turned to deep state, towards the bureaucracy, towards the momentum of the past, which I think Joe Biden kind of represents, versus new ideas, which is funny to say that Bernie Sanders somehow represents new ideas [/INST] because he's also an older gentleman. Well, it's a lot of framing. And the other aspect of that is, on paper, Joe Biden's platform was arguably the most progressive of any Democratic candidate, who won the nomination. Now, of course, there were people who challenged the nominations who were to Joe Biden's left. A lot of this is perspective. And that's how you end up saying the guy who's a couple years older than Biden is actually the guy with the fresh perspective, </s><s>[INST] which is interesting because I don't disagree with you. Yeah, and you also have to say the perspective doesn't always align with the policies. You're right and the actual policies of Joe Biden [/INST] are different than the, maybe the perception of Joe Biden. Or what he ran on. I mean, just two examples I would give are during his campaign, he played up a little bit his interest in doing student loan forgiveness and something on cannabis. I never bought it. I told my audience, I think he's saying this stuff because this is the way the tide is kind of, the wind is blowing and he's being advised to say this stuff. I don't think he's going to do very much on either of these things. He did actually do some student loan stuff, </s><s>[INST] but that would be two examples, I think. Okay, let's go to something you alluded to, which is the pros and cons of a particular candidate. Well, what do you, as a critic of Trump, what do you are the pros, the strengths of Donald Trump [/INST] and what do you are as big as weaknesses? The strengths of Trump, let's see how I can frame them in a way that is both accurate and accurately assesses my feeling about it. </s><s>[INST] It can be taken out of context most masterfully through the clipping process. [/INST] Yes, yes. Trump's strengths are mostly superficial and in terms of presentation. Trump was able to, I call it a grift. Some on the right say he's just so good at relating to different types of people. Trump, as a rich guy from New York City, was able to convince people that he spent most of his life trying to be kept isolated from, that he had their best interests in mind, that he knew why they weren't doing well in the 2016 economy and that he had solutions that he was going to bring forward. The truth is, he never really liked those people and as soon as they weren't useful to him for a brief period of time, he, you know, that love affair with his followers stopped and then now it's back that he needs them again. He didn't really understand the causes of the problems that those folks were experiencing and his solutions were laughable, right? Like Jared was going to solve the Israeli-Palestinian conflict in year one. He was going to replace Obamacare in 2017. Things that were never going anywhere, anywhere. But what he did really well was he put up a united front of I know what is ailing you. I know how to fix it and I know how to fix it, I guess because he's a businessman and he's been above the fray of politics for so long, knowing how to use political donations to his advantage. He called that smart, et cetera. </s><s>[INST] I think that's his greatest strength. Why do you say that the Jared plan for Israel and Palestine and the plan for healthcare to improve Obamacare? [/INST] Why do you say that's laughable? Well, only someone, I would include the North Korea plan as well, which I'm glad to talk about, only someone who doesn't know anything about the size and scope of these issues could so arrogantly say that they could solve them in that way and on that timeframe. I'm all for optimism and bringing a new face to things. Absolutely, without a doubt. But, you know, a wall with Mexico that Mexico will pay for at the end of my first term. I know there are people who believed it because they would call into my show and say, I'm voting for Trump because of it. But it's hard to believe that anybody serious would fall for that unless you were deliberately wanting to just believe whatever was being fed to you. Or you just hadn't ever thought about these issues before. The healthcare plan, you know, in 2017, they proposed one would have led to 24 million or so people ending up without healthcare. It didn't go anywhere because it was so terrible. And then in August of 2020, Trump said in two weeks, I'm going to finally have my healthcare proposal. It's 2023, we still never got it. You know, with all of these things, when you think them through, it was just sort of arrogance. And I get the perspective of I want optimism and I liked that optimism. It worked. I mean, fair. A lot of people saw it and liked it. As someone who followed a lot of those issues closely, </s><s>[INST] they seemed of course, like impossible promises. Well, it's a double-edged sword. So to push back a little bit, if you look at the things I have a little bit more knowledge about, which is the space of artificial intelligence, there's a company called DeepMind and there's a company called OpenAI that will laugh at for a long time when they were talking about that they're going to solve intelligence. And now they've made especially DeepMind and now most recently OpenAI with GPT, they've made progress that most of the community would not have imagined they'd be able to make. Everything from AlphaGo beating the World Go champion, just all the different steps and progress that I can get into were surprise to everybody and they are legitimately, fearlessly pursuing the task of solving intelligence. The other aspect, he gets a lot of criticism now, but another example is Elon Musk. I can say a lot of things like SpaceX, so commercial space flight. He was laughed at for a long time that that's possible. Same thing with autopilot in Tesla, autonomous vehicles. His approach was harshly criticized by all the experts and still criticized to this day, deeply criticized. And I, as a person that I believe objectively can look at the progress of autopilot as a semi-autonomous vehicle system has been incredibly surprising. So the reason I mentioned that is sometimes it feels like you need the guy or the gal who makes those preposterous, ambitious statements, and it's like, we're going to solve healthcare this year. And then there's experts like yourself that are looking, thinking, have you read anything about the history? Israel, Palestine is a good example of that. Do you know there's a history there? Do you realize how complicated, how many people have tried? How many people have failed? How many millions of people hate each other in this little place, in this land? Sometimes the expertise can really weigh you down. So to push back, sometimes you have to have the, almost be naive and stupid and just rush in [/INST] with an optimism in order to actually make some progress. I agree with you 100%. I think it's interesting that all of the examples you gave of successes are from the technology space. Not politics, yes. Not from politics, which, I mean, listen, I would love to be able to make headway on some of these issues more quickly without a doubt. I do think at some point though, when it comes down to voting and saying, one of these people is going to be ostensibly in charge for four years through all of the departments and secretaries and choices that they make, we do want to apply some level of realism with the understanding that your examples are from the tech space and they're good examples. There's no question about it. One thing I'll add to this, I recently read Bradley Hope's new book about North Korea and it's really about an activist who- It's not possible. It doesn't even really matter, in the background of the book, it's written much of what is written about happens during the Trump era and when Trump did the first and then the second, I guess you'd call them summits with Kim Jong Un. And it actually did seem like to some degree, Trump's we're going to handle this like I do a business deal approach to Kim Jong Un. In some sense, it actually was logical because of Kim Jong Un and the way that it was so ego-driven and they both as sort of authoritarian strongmen types to different degrees wanted that. There was actually a kernel where I actually thought as I read it, Trump's initial idea wasn't crazy. The problem was he knew nothing about the backstory of the relationship. He fell for all sorts of lies from Kim Jong Un and he made offers that didn't make any sense. It fell apart, fine. But that's an example where I think Trump's personality was not actually at its base the problem </s><s>[INST] when it came to North Korea. Well, there's other things of this nature that could go and some people argue goes into the strengths and pros of Donald Trump. For China, for example, terrorists in China. Can you make the case that there's some positive outcomes [/INST] of the way Donald Trump acted with China? It's really tough. And I'll give you a couple of- Okay, then also cons. I'll give you, it's tough to make. So the China thing is really, so just very recently to when we're recording this, Trump was on Fox News interviewed by a guy named Mark Levin and Trump proposed a new, I call it a conspiracy theory. Maybe it will strike you as something different about China, COVID and tariffs. And Trump's suggestion was that the tariffs cost China so much money. China sent the US so much money in tariffs that they released COVID as punishment. Now there's a couple problems with that. One, American companies pay the tariffs. Trump still doesn't seem to know this. Trump seems to believe that when he puts a tariff on Chinese imports, someone in China is cutting a check to the United States. American companies buy the stuff from China and then American companies cut a check to the United States for the tariff. </s><s>[INST] Trump doesn't seem to get that. [/INST] But it still has a sting to the Chinese economy. You can make the argument that if there is a suitable alternative domestically or from a different country, that it will reduce imports, but it didn't happen. And we actually have reports now that the tariffs on China cost about a quarter million American jobs. The other problem with that idea is China created and released a virus in order to hurt you. But as of today, 5.7 of the 6.8 million deaths were in other countries. It's a very indirect way. You're mostly killing people in other countries to hurt Trump. Maybe there was a, this is the sort of thing where when I think about how Trump dealt with China, it's very scary because given another four years, who knows what he might do if he still doesn't understand how tariffs work. </s><s>[INST] So geopolitics operates in complicated ways with carrots and sticks. And Henry Kissinger has written quite a lot about this and in some sense, the positive aspect here that Donald Trump is willing to take big risks in the game of geopolitics with this giant superpower that is China and a lot of others are too afraid, too afraid to call them out, [/INST] to come to the table and criticize. I certainly think that's an argument that can be made. My question would be what tangible positive outcomes did it lead to? And it's tough to identify any, but I think it's a great thing. I mean, listen, one of the things you're kind of getting at maybe indirectly is that there's been this sense that politics has been done very similarly for a long time. And even between Democrats and Republicans still, even with some policy differences, there's still the kind of feeling that it's disconnected folks in DC, mostly dealing with issues that don't directly affect. I get that. I'm with you on that. I think the question is to whether Trump's bluster was positive rather than extraordinarily humiliating in many ways. I just come down on, it was an absolute and total humiliation, but I understand that you can recognize Trump doesn't know a lot of stuff, but his attitude was refreshing in some way. That's a reasonable position for someone to take. </s><s>[INST] I disagree with it, but I understand it. [/INST] But it's trying and feeling better than not trying. This goes well beyond politics. You know, Wayne Gretzky has weighed in about this. Michael Jordan has weighed in about, I mean, this is a, yeah, is it, is it better to have tried and failed than never? Is it better to have loved and lost than never to have loved? I don't know. I mean, listen, we lived through four years of Trump. We know what that four year term was like. And it's very hard for me to say that the things he tried were overwhelmingly reasonable, but I get the point you're trying to make and I appreciate it. And it's, if we don't do any of it, then where do we end up? Sure. We know where we ended up with Trump </s><s>[INST] and it was pretty embarrassing. Okay, let's linger on some more strengths. We didn't start any new wars. Is there something to that? [/INST] We didn't start, yeah, that's, it's, it's interesting. There's a few different approaches to dealing with that. First, it's really important to remember that the counterpoint to that from the folks who liked to say that was that Hillary Clinton was going to start three wars. Sometimes they say four wars. Sometimes they say five wars. Okay. The geopolitical situation during the four years that Trump was in office, I don't know that they obviously lent themselves to wars that Trump just barely was able to keep us out of. I think the Russia thing is interesting because now it's very popular to go back and say, you know, the reason Putin didn't do the Ukraine thing when Trump, right? And to somehow give Trump credit for that. There's a counterpoint to it, which is Putin under Trump, particularly if Trump got four more years, would have been able to maybe consolidate power in other ways because of his relationship with Trump. I'm not coming down on one side or the other. It's not my area of expertise, but it's not the open shut slam dunk that, you know, Trump likes to say it is Putin didn't invade because he knew I would crush him. Okay. So it's not obvious to me that there were imminently wars that would have started during that time. That being said, you know, for all the criticism of Obama during Crimea, Trump seemed to just kind of forget about that after all the criticism and say, I'm not actually going to do anything about that. And so there's, there are foreign policy criticisms that could be made, but it is true. No new wars were started under Trump. And I like that. </s><s>[INST] I don't like wars. What do you think about his handling of COVID? Can you say what are the pros and cons [/INST] of his handling of COVID? The con for him is he'd be president right now if he had handled it differently. I think it's abundantly clear early on. And there's now a lot of really good reporting about the conversations he was having with Jared Kushner and others. He became convinced either because of things he was being told or because he decided this is the way it's going to be. This is going to go away fine. It's in China. Okay. It's in China and Italy. Okay. We have 15 cases, but it'll soon be zero. We'll be opened by Easter of 2020. None of it happened. If he had handled it in the following way, and I've said this to Rogan and I've said this to Patrick Bette David, and they tend to all see my side of this. If Trump had said, listen, we don't know how bad this is going to be, but I care too much about the American people to take a shot. So it's not going to be two weeks. It's going to be a little bit, but I need your help. We're going to bring everybody together. I don't care if you're a Democrat or a Republican. We're going to have MAGA masks and he could have kept 50 cents on the dollar to pay off, store me or whoever, right? But it would have been, I think he wins reelection because the perception was, and reality is a version of that. The perception was that he was way too cavalier about it early on. People died who didn't need to die. And I think that it was arguably the one area where he could have all but guaranteed </s><s>[INST] that he was going to get himself reelected. Well, to push back on that, I mean, because you mentioned sort of masks [/INST] and lockdowns kind of a solution to COVID. I didn't mention lockdowns, </s><s>[INST] but I'm glad to talk about Paul's policy. Sure, quarantine, like there's several solutions to a pandemic, broadly speaking. And one of them is a vaccine. And so you didn't mention that. He fast-tracked the development. He, his administration fast-tracked the development of the vaccine, which surprising, [/INST] he didn't really take much credit for. Yeah, I think he did. I think he tried. </s><s>[INST] There's a couple, there's a lot there. Well, to me, it seems like you could make the case with the Trump hand gestures that his decisions for fast-tracking the development of the vaccine saved tens of millions of lives. You can make, he could, in the Trumpian way, [/INST] make that case. So, couple different things. I know you don't necessarily follow Trump's rallies as closely as I do, and I'm jealous of you for that. But he did tout the vaccine stuff hugely for a while until his audience turned against him. And then he had to draw this line where he was going, I made the vaccines, which none of you have to take, by the way, freedom. You don't have to take them, but it's fantastic. And nobody else could have done it, but don't worry, nobody's gonna make you take the vaccine. And he actually got booed at a couple of his own rallies when talking about the vaccines. But let's back up a little bit. Fast-tracking, my understanding of what he did is he did what any president in his situation would do and what many world leaders elsewhere did as well, which is he agreed to pre-purchase supply of vaccine in order to provide money to pharmaceutical companies to scale up the manufacturing, which is absolutely fine. But he wants, one of the stories he tells is, it usually takes 12 years to develop a vaccine. We did it in nine months, thanks to me. Decades of mRNA technology being developed created the platform in which you can make a particular vaccine in nine months. Didn't have anything to do with Trump. He did pre-fund and say, we will buy huge supply and that provided liquidity to the pharmaceutical companies. </s><s>[INST] But he also delegated control to people, to experts that enabled that kind of [/INST] fast-tracking vaccines, right? He was very eager for the FDA to approve it </s><s>[INST] because he saw that there would be a political benefit. [/INST] He didn't get in the way, I guess. He didn't get in the way, fair. I think now we're on the same page. He did not get in the way of vaccines being developed, </s><s>[INST] which is good, which is good. Presidents and bureaucracies have a way of getting in the way. [/INST] I don't disagree with that. I'm not aware of really any governments that got in the way. I mean, it seemed given the global situation, everybody with European countries were pre-purchasing the vaccine. African countries who were going to be later to receive vaccines were partnering with the European countries that had pre-purchased. But the most interesting thing about all of this is Trump did play up the vaccines for a long time until his crowd didn't want to hear about it anymore, which was crazy. It was sort of like he became a victim </s><s>[INST] of the monster he created to some degree. One of the effects of all this that makes me truly sad is this division over the vaccines has created distrust in science. And also what makes me sad is the scientific leaders, Anthony Fauci being one of the representatives of that community, I would say completely dropped the ball. In what way? They spoke with arrogance. They spoke down to people. They spoke in a way that a great scientist does not speak, which is they spoke with certainty, without humility. Like they have all the wisdom and all of us are too dumb to understand it, but they're going to be the parent that tells us exactly what to do versus speaking to the immensity of the problem, the deep core of the problem being the uncertainty. We don't know what to do. The terrifying thing about the pandemic, we don't know anything about it as it's happening. And so you have to make decisions. You have to take risks about, well, maybe you have to overreact in order to protect the populace, but it's in the face of uncertainty that you have to do that, not empowered by science somehow. And the deep expertise that somebody like Anthony Fauci claims to have. So like, I just am really troubled by, yeah, the distrust in science that resulted from that. And that you have to blame the leaders to the degree, leaders take responsibility. And I think Anthony Fauci was the scientific leader behind the American response to the pandemic. And I think he failed as a scientist, [/INST] as a representative of science. Yeah, in what way? I'm less, I don't know if interested is the right word, but the kind of the Fauci review is less interesting to me in terms of what comes next than the first part you mentioned, which is the distrust in science. And sometimes I'll get voicemails or emails from people in my audience who say that I have had to backpedal on certain things related to this. And one of the things I tried to do from the beginning was not speak in certain terms when we really didn't have complete information. So there was this period where hydroxychloroquine was first sort of mentioned as a possible treatment, prophylactic or proactive treatment for COVID or active treatment for COVID along with a bunch of other stuff. There was ivermectin, there was vitamin D, there were all sorts of different things. And I tried to be careful to say, right now we don't have rigorous science that tells us that some of these things work. It doesn't mean that won't come in the future, at which point if there was something as cheap as hydroxychloroquine that treated COVID effectively, unbelievable, fantastic. It's not, there's no way it ever will be determined. We don't have that information right now. So it's not super wise right now to go and start taking this stuff. We eventually learned like with vitamin D, having an appropriate vitamin D level does seem to be based on what I most recently read, generally protective and a good thing when it comes to infections of different, great. Okay, so that one we figured out. One of the really difficult things is that the quote truth about the vaccines did change. And the original, again, this is all, I don't pretend to be an expert, but just someone who's synthesizing the medical data and writing about it. Originally, the first vaccine related to the wild type strain did seem to be very effective, not only at preventing death and serious illness, but also transmission. There were people then saying it doesn't prevent transmission. Over time, as the variants came forward, the vaccine became less effective at that. At that point, I started telling my audience something different because as far as I was concerned, the reality on the ground had changed. In my mind, that's how science works. It's not backpedaling, it's we're adjusting our beliefs to what is taking place in the real world. </s><s>[INST] Well, to be fair, the scientists, many of whom are my friends, biologists and biologists, they have way more humility than people like Anthony Faggio speaking about this, or the CEO Pfizer who are speaking about this. This is the fundamental problem here, is the way science works is there's usually a lot more humility and a lot more transparency about what we know and what we don't know. People like Anthony Faggio thought it would be beneficial for the world if he speaks with more certainty. But because of the political division that formed around that, that certainty resulted in, became completely counterproductive, that people didn't trust anything about the vaccine, didn't trust any institutions there were, that contained the experts that actually knew what they were doing and basically didn't trust anything that was coming out of the mouths of scientists, some large percent of the population. So that made you completely ineffective and at scale as a society trying to respond to a terrible pandemic. And that's where I put a lot of blame on leaders. So political leaders and scientific leaders are the ones that should inspire us to all get together and respond. That should be the case for the pandemic, that should be the case in the time of war, [/INST] all this kind of stuff. I generally agree with you and for me, it's really about shared blame and there were a lot of different reasons why that the early communication wasn't good. Part of it was, I mean, for me, I prefer accuracy rather than overconfidence. I would prefer, listen, we don't really know right now whether masks do X or Y. What we do know is the supply is really limited of this type of mask. We're gonna try to keep them for the frontline workers. I love that. That's the way I wanna be communicated to. A call was made to do it differently, which was to say, the masks don't actually help. But the real reason is they wanna keep them for healthcare workers. And then later, the masks are what's going to solve. I'm with you 100%. I think the other layer to it is you can't ignore the political situation at the time. If Trump had won reelection and the vaccine distribution had taken place while Trump was president rather than Biden, my belief is that the same number of Democrats would have gotten vaccinated, but way more Republicans would have as well because they were following not science, but political leaders. And when it was Biden in DC instead of Trump, a lot of those people said, I don't trust the vaccine, but wait, it's Trump's vaccine, I thought. Yeah, but something about the way Biden's distributing it. So I do think you can't ignore that political layer. </s><s>[INST] I agree with you, the communication was a disaster. Let me ask you about Joe Biden. [/INST] What are the strengths and weaknesses of Joe Biden? Weaknesses, I think, are some of the things you've identified. He is not seen as high energy. He is not the same Joe Biden that debated Paul Ryan in 2012 and ran circles around him in just an incredible debate performance. He is not inspiring in the way that someone like a Barack Obama was to people coming up and starting to get interested in politics. I think a lot of those are fair criticisms. I think on policy, he's not interested in a lot of the things that younger voters are interested in. I mentioned cannabis reform. I mentioned student loans. So I think that that's a deficit for Biden. I think the upside to Biden is when it comes to foreign policy, diplomacy, high level negotiations, knowing how to engage with allies in a productive way, it's tough to find someone with more experience than Biden. I know that there are counterpoints to what I'm saying. And those include, that was the old Biden. The new Biden doesn't have it. That includes, that's just a sign of rot because he's been around for so long. Nobody should be around that long in politics. Perfectly reasonable criticisms to talk about. But I do see that as one of his strengths. And he also is good at knowing when he can work with Republicans and when he can't and not wasting more time than is sort of expected for posturing reasons. </s><s>[INST] And I think that that's a good thing. Do you think he's actually there? So in a day-to-day operation of government, given his cognitive capabilities, [/INST] do you think he is an active and practicing executive? I don't know that I can say that it's because of what may be going on cognitively, but my sense from the people I talk to is that he's very much involved in the highest level geopolitical and big domestic economic stuff, but that a lot of the smaller issues that presidents might or might not be in, sort of plugged into, that he's not plugged into the details </s><s>[INST] of a lot of the lower level stuff. Yeah, you could probably apply the same exact criticism even more so towards the Donald Trump administration in terms of being a practicing active executive who's paying attention. Like for example, like Vladimir Putin is somebody who loves the role of the executive, has a huge amount of meetings, has constantly tracking information about agriculture and all the different subsystems of government. Stalin, funny enough, was also extremely good at this. So certain people just love the job of being an executive. And I'm not sure if Donald Trump did, and I'm not sure if Joe Biden in this current state [/INST] has the cognitive capability to. It's a good question. Kim Jong-un's another one, by the way. There's videos of him examining a pottery, a factory where they make plates and making very specific comments about how the plates should be made. I think that in that case, there's a lot of propaganda value to it. With Trump, I think you're probably right. He did get involved in the minutia of things. Once he pulled out a weather map and with a Sharpie drew a different hurricane path that was more politically convenient to him. That's pretty micro, saying the weather channel's wrong. I see what you did there. This is, okay. I see what you did there. Say that's a micro. He went to Puerto Rico and he gave out paper towels after a hurricane. Now he was shooting them like free throws, which didn't look very good. So he will get involved in the micro when it's advantageous, you know what I mean? But I do agree with you that he wants to just kind of make it so. Build the wall. I don't know, just build it. </s><s>[INST] Figure it out, get it done. It's wrong. I see what you did there. This is, okay. I see what you did there. Quick pause, bathroom break? Sure. Yeah, you're hilarious. And just for the sake of completeness, I should mention the subreddit, what Biden has done. There's also what Trump has done, but it's not as active. And it has like this master list of all the accomplishments. I recommend people look at it because it's kind of rigorous and interesting with Link's list of all the things he's done. Just list some of them. Restored daily press briefings. Canceled the Keystone Pipeline. Reversed Trump's Muslim ban. Required masks on federal property. Rejoins the Paris Climate Agreement. Extends student loan payment freeze. Extend eviction freeze. Historic stimulus bill, as you mentioned. Hence funding for border wall and so on and so forth. DACA, border strengthening of DACA. Rejoins the World Health Organization. And the timing of this, of course, is important. Yeah, several historic stimulus bills, which of course you could criticize or support. Raise the minimum wage for federal contractors and federal employees for $15. There's a lot. There's a lot. It makes you realize with both Trump and Biden that there's a bunch of small details that matter. Like that matter on people's lives, like actual little policies. Trump did a lot of stuff as far as I heard for the military. [/INST] Like not big stuff, but small stuff. You're hilarious. Yeah, I'd be curious what you're thinking of. I mean, I know one of the big things under Trump was we're gonna get trans people out of the military. That's not what I was referring to. You weren't referring to that. Trump's hilarious with these stories that he tells. And one of the stories, and you get to know them if you follow him at all. He tells the story. When I came into office, the generals came to me and they said, sir, the cupboards are bare. We have no bullets. And so I rebuilt the military. The cupboards were bare when Obama left it and it was just terrible. But I rebuilt it. And the generals, I've got the best generals. They said, sir, it's incredible what you were able to do. You look into it and it's like, yeah, that's not really true. It is true that there are armaments that just like on a schedule do get replaced. And that's part of the military industrial complex. But there's nothing like special Trump really did. But these stories become, they take on like a life of their own. And it's interesting to sometimes try to dig down and figure out like, was there any policy connected to that? </s><s>[INST] Or is that just a story? Do you think it's possible to have a good conversation with each of them? Donald Trump and Joe Biden in a podcast context [/INST] or in a debate context? Absolutely. Yeah, you're saying like, could I with either of them? </s><s>[INST] Oh, a hundred percent. Yeah, you're saying like, could I with either of them? Yeah, Joe Biden too. Sure. Yeah. [/INST] Look, can you dig into that a little more? Well, I mean, I don't know what, I think there's maybe something implicit in your question, </s><s>[INST] but this deeper about the nature of politics and politicians. [/INST] Yes. I think with either of them, I mean, the political differences wouldn't be an impediment to having a good conversation with either of them. I think one of the things that's really tough in my experience when talking to elected officials is they could be super interesting about a hundred different topics, but handlers decide or try to get you to talk about something you don't really care about and something really narrow, which doesn't bring out your best nor their best. And that's a frustration. But I think that given an unstructured three hour conversation, I think it would be interesting to talk to both. I mean, listen, with Biden, aside from his view on cannabis or whatever, his background and the incredible unimaginable family tragedy that he had in his first wife and multiple kids dying. I mean, it's just incredible, you know? And with Trump, I think also you could have </s><s>[INST] an interesting conversation. Yeah, there's the human beings with a life story. Yes. And they're some of the most successful humans who have ever lived to have rose to this highest office in interesting, complex ways. Yes. I mean, one of the things I'm troubled by, maybe you can speak to is why we're so negative towards presidential candidates and presidents. Why it's just, they go through this shit storm no matter who they are. They're like hated, like all the conspiracy theories and just, yes, just the dynamics of how we talk about them is vicious. If you just look at replies, Stephen Barack Obama on Twitter, it's like, what is going on here? Why, because we look at other leaders in other spaces [/INST] and we're generally positive about it. Yeah, there's a couple of different things. There's this dynamic, which is really unfortunate, which is you ask people, do you approve of the job a particular president is doing? And very often, if at any point while they were in office, they did something you don't like, people will say, I don't approve. And so by its nature, what that means is just like the longer you're in office, the lower your approval rating is going to be. And very often that's the way it works. I mean, there's major events like 9 11 spike George W. Bush's approval to an incredible level. Then it came back down with the Iraq war. But there's this unfortunate thing that when, when people are just asked, you think Biden's doing a good job? If four months ago Biden did something on healthcare that somebody didn't like, even if you like most of it, a lot of people from that point forward will say, I don't approve. They might still vote for him because they like him better than the alternative or whatever. It's, it's just the dynamic of politics. And I agree. It's, it's very, does it have to be that way? I don't think it has to be that way, but to unwind it, so many things would have to change. I think our election system is part of why politics is the way it is where you have two choices and it's first past the post. And we have this electoral college so that depending on which state you vote in the kind of meaning and significance of your vote is different. If you vote in Montana, it's the Republican candidates going to win and that changes the dynamics. I think that's part of it. I think that at a personal level, I've experienced this in my life a lot. We've become, and by we, I mean, people in the United States to some degree who talk about this stuff. We've become uncomfortable when there is disagreement and it bleeds over into now we can't have a normal interpersonal relationship anymore. I'm from Argentina and in Argentina, it's really common, even in my family, there are incredibly heated political debates at the start, the middle, the end of some kind of gathering, but then everybody just goes back to like, okay, we disagree on some things, but that's okay. And we can now go and, you know, finish cooking the beef or whatever it is that we're doing. And I experienced this even with people who come up to me on the street and they go just earlier today, a guy came up to me and he said, RFK all the way, baby. Talk about Bobby Kennedy Jr. And I just kind of said, Oh, all right, you know, let's see what happens. And then there was another moment where the guy ended up standing next to me for maybe longer than he thought. And I could tell this guy is getting so awkward because it was an utterance he thought that would just be on the fly and he'd be gone, but now we're standing next to each other waiting for our sandwiches. It's like no big deal. You know, it's just, oh, okay. You like Bobby Kennedy Jr.? I don't plan to go for it. It's fine, you know, and that's like a socio-cultural thing. I think there's lots of other countries. I've spent time in Italy. I have relatives in Israel where like shouting at each other is sort of like normal. And then you just go back and finish them. It sounds like shouting, I'm sort of exaggerating, but very animated, what seemed like big disagreements and then everybody's cool. </s><s>[INST] I wish it were more normal. So maybe the mechanism of going from shouting to being cool again needs to improve because maybe we can't solve the shouting at each other. Maybe not. So maybe we need to somehow figure out the de-escalation like making up. I've had a few recent fights with friends like that. Yeah, politics. No, oh, no, but political style, emotionally drenched stuff. And it was interesting to go through that full process and then make up at the end, but it was a process. And it was a process that required being in person and talking through it. And it was stressful, the whole thing. And then maybe because most of our interactions are online, we don't get a chance to do that in person, making up again. I don't know, but do you think it's a feature or a bug of the system that we're so, [/INST] we just hate the powerful? Maybe not, really, but for politics. No. You mentioned the online part. I think it's, you mentioned it earlier perfectly, which is you take contentious political issues, you create a platform that rewards controversy and disagreement and limits the number of characters you can use to express yourself. You kind of throw it into a baking dish and mix the entire thing up. It's complete and total chaos. And one of the things that I've talked before about all the angry emails and threats and stuff that I get, I'm acutely aware that if I had in-person conversations with most of these people, the conversations would basically be like, oh, we have different views about how to solve some of the problems we're facing. We probably agree about what the problem is and we probably share many values, but on these particular four issues, we may have very different views, but that's okay. Online, that's not the case. And it leads to the mess that we get ourselves in, but I think that it's a feature of a lot of the systems </s><s>[INST] that are being used to disseminate information. Again, let me linger on that. Do you regret some of the mockery and the snark you use on Twitter [/INST] and even in your show that kind of feeds that division? I don't regret it in the sense that it's a calculated part or tool that I use in addition to figuring out how to simplify complicated concepts and choosing stories that I think are underrepresented. It's all part of the package of what I'm doing. I recognize that my show is not the audio visual version of a peer reviewed, randomized controlled trial about abuse on abortion or whatever the case, like I'm very much aware of that, but I don't regret including it as a tool that I've used to build the community in some total </s><s>[INST] that I've built over the last more than 10 years. I guess I could ask about the different trajectories you think your show might take. So the dynamic you had with Donald Trump Jr. and maybe Candace Owens is the more appropriate comparison. Are you okay having that dance for the next few years between you and Candace Owens and just kind of the mockery, the derision that's a part of that process and taking part in that? [/INST] I'm fine with it in the sense of personally, I tolerate it well until it crosses the line and people pull my family in and people, right? </s><s>[INST] So that's the part that's the whole. So if we set the family stuff aside. If I set that aside. [/INST] Just in the digital space. If I set that aside, I'm glad to mix it up. Now, the truth is Candace Owens has had me blocked for years up until this incident. I don't know why. She unblocked me just to tweet about what I tweeted about. I don't know the backstory of that genuinely. I have no idea. So I don't have a sense that she's super interested in engaging with me on that, but all of these people, I mean, Candace Owens is welcome on my show anytime. Don Jr.'s welcome on my show anytime. It's been a decade since I had Ben Shapiro on. He's welcome at anytime. I'm glad to have these conversations and I think it's an important thing. And also I wish that everybody was willing to have the conversations in good faith rather than as performance. It's not even really performance art rather than being simply performative </s><s>[INST] for an audience that you have. In terms of your motivations, do you see, do you worry about the effects of something you spoke off, spoke about offline or like the YouTube algorithm? Do you, are you driven by the number of views [/INST] your videos get or are you driven by something else? So in my world, I guess I would say, the number of views that any platform generates is a metric that I can choose how to interpret. I can choose to interpret it as I've created content that's interesting to people or I've created content that's really angering people and that's why they're showing up. They don't actually like it. It's because they're angry or whatever else the case may be. But it is true that there are algorithmic changes that can take place. Something happened in early January that affected us on YouTube or there are periods on TikTok where you can tell, we're doing all the same things. Something has happened and then you never usually figure out what it is. So for me, it's sort of just like a general tool to see what is the level of interest in what I'm doing and are the numbers so out of whack with what I would expect that I should look into whether something deeper is happening. Has there been some change to an algorithm or whatever the case may be? I had a debate once with someone who accused me of using clickbait to generate views and we had a really interesting conversation where I said, tell me really what you mean by that. Is your argument that I'm using titles that don't actually represent what's in the video? No, what's in the title is in the video. I go, okay, so it's not that the title is dishonest. Are you saying I'm deliberately picking titles that will garner a larger audience? And they said, yeah, that's kind of what I mean. And I said, isn't that kind of what we're all doing? The alternative would be choosing titles to generate a smaller audience, which seems like a real kind of waste of time. So I'm trying to navigate and play the game in a way that's comfortable, but use the metrics more as a tool </s><s>[INST] than as something to obsess over. Nevertheless, the metrics are what they are and that they are able to affect your psyche. It's very difficult, which is why I have a Chrome extension that hides all the views and all that on YouTube for me. It's difficult not to let it affect how you think about ideas. So maybe your extensive exploration of a particular topic like healthcare generated very few views. It's difficult for you to still care about healthcare. There's some aspect of the human mind that starts being affected by those views. And I think that's a really dangerous thing. Mostly it's probably beneficial because it probably makes you a better presenter. If you do care about a topic a lot, you become more charismatic, more you learn sort of in a Jimmy, Mr. Beast way, how to present the ideas better, but it also can affect which topics you choose to cover, what you choose to think about those topics, the audience capture those topics. And that's a really scary effect. I'm really worried about my own mind in that. [/INST] So I run from that aggressively. One of the things that I include in my overall approach is I don't think about any one clip. I think about an entire show or a week of shows or a month of shows. And so it's less about does any one clip do well? My view going in is I'm going to do stuff that won't do that well, but I think it's really important to do. And I want to make it part of my show. And so when I did a clip with 10 ideas for reducing gun violence, I know that that's not going to get 500,000 or a million views. I know it's just not going to. And the first day it'll get 12,000 and I'll go, I don't care. That's fine. There's a group of people in my audience that values this stuff. And I want to keep doing this stuff. I'll end up surprised sometime. And two weeks later has 150,000 views because it started being shared or great. But I don't go into it thinking these all need to be home runs by that metric. I always go in saying, I want to put out a diversity of content, including stuff that is less titillating and salacious, but is important to do. It's more researched, et cetera. And so that's the way I try to resist </s><s>[INST] exactly what you're talking about. And I think you have to probably know yourself. Like for me, metrics, I just like numbers too much. And for me, metrics do affect me. This is why I don't pay attention at all. Like I can't, I would love to hire somebody on the team who cares, because we currently have folks who all of us just don't care. Because he probably is good to care enough to kind of just do good thumbnails and this kind of stuff to pay attention. But to me personally, I just find inner peace and focus if I don't think about the numbers at all. Because I find myself, I just remember a long time ago when I started a podcast, I would think that I failed if it didn't do well. Like if I didn't celebrate the person well enough, I didn't do a good job enough of a conversation. Well, that's not necessarily at all what that means. [/INST] It's hard not to- This is tough stuff. I mean, yeah, I know exactly what you're saying. And part of it is, I mean, it starts in my, you have a little bit of a different situation than me, because you're doing long-form conversations with people. And the prep is a little bit different. One of the things in my space, because I'm reacting mostly to what's going on in the news and then also picking topics to dive into it a little bit more deeply, is I have very little control over the news cycle. And there is a metametric or a macro metric that affects me that will quadruple my audience and then take 75% of it away, which is the seasonality of election cycles. And the first few election cycles, it's very tough, because I go, it's October. I'm like, at this rate, we're going to have 20 million subscribers by next, these numbers are unbelievable. And then it's January 30th, the inauguration's over, the debate is about the debt ceiling and nothing's going on. And I go, nobody's watching my content. I must have forgotten to upload a show, like something must be wrong. It's completely beyond my control. And I think part of what you're saying is, I try to focus on the things I can control and understand those that I really have no control over </s><s>[INST] whatsoever and try not to worry about them. And try to do the things that make you happy at the end of the day, the things that, you mentioned RFK, the guy you met. What do you think about some of the other candidates outside of Joe Biden in the Democratic Party, RFK Jr.? What do you think of him as a candidate? [/INST] I've met him, we once had dinner and we have a number of friends in common, which is what makes this a little more awkward. But I think his campaign is basically sort of like a chaos candidacy to raise awareness and maybe raise money either for his book or his anti-vaccine organization children's defense fund, I believe it's called. I think there's some reporting that Steve Bannon really liked the idea of him running as a Democrat, again, to just generate chaos. I don't find it super interesting. I don't find it worthy of that much discussion. Smart guy, nice guy, has been doing anti-vaccine work that I don't find particularly inspiring. </s><s>[INST] So it's not just anti-COVID vaccine, [/INST] it's more broader than that. He's been in that space long before the COVID vaccines. </s><s>[INST] Yeah, I don't find it super interesting. Well, he also wrote the book, [/INST] The Real Anthony Fauci, is that the name of the book? Did he write that? I don't know, I'm not sure about that. </s><s>[INST] I'm aware of that book, I didn't know he wrote it. I think I need it, but it's been on my reading list to get, I've been trying to get a good, balanced reading list about the COVID pandemic to understand what the hell happened. And anytime I start to try to go into that place, [/INST] it's just, I'm exhausted, exhausted by it. Well, it's interesting to me that you wouldn't wait longer before delving into those books </s><s>[INST] to have maybe a more clear hindsight. But I think this is a pretty good time. You don't think so? Like this is, it depends on your goals. If you're thinking of it as a historical event, yes, you should probably wait longer. But if you're thinking about like understanding what is broken about our system that we responded so poorly, that there was so much division, what is broken about our political system that it didn't unite us, it divided us. Who's to blame? There's probably a lot of different narratives, but I feel like the more you learn about this, the better you can understand. I read, on just Vladimir Putin, I read like five biographies already, maybe more. Just, it helps to really understand the people involved, the organizations involved, I don't know, everything from the scientists to the political leaders. It felt like the blog posts and the tweets didn't quite capture the story. [/INST] They didn't quite, they didn't quite, no, one of the things I read a ton, I don't read any like modern political books. So I don't read the memoirs of elected officials. I don't read any, I just feel like I get enough of it in my job. So my reading list is just other things. It's history, it's narrative nonfiction, economics, et cetera. And that's my bias because I'm so overloaded with a lot of the stuff you're talking about. I haven't read any of Obama's books. I didn't read John Bolton's book or, you know, I don't read any of that stuff, </s><s>[INST] although I'm sure there is value to be gleaned from it. What about the other candidate that, according to the subreddit, and as you mentioned, you've criticized it a little bit, Marianne Williamson, do you think, [/INST] what are the pros and cons of her as a candidate? This is another area where many in my audience really are angry with me. I don't find her candidacy super interesting. I'll tell you the pros and the cons as I see them. I do think that we have elected officials in the U.S., particularly presidents, from a really narrow range of backgrounds. So it's lawyers and sometimes business people, very, very often lawyers. I think we would benefit from a much greater diversity of backgrounds. And I once said, and that would include people from education, people from the science world, people with backgrounds, maybe running nonprofits, et cetera. Now, Marianne Williamson did, I guess, at one point, run some kind of small nonprofit. And some in my audience thought that credential alone would make me fall head over heels in love with the idea of a Marianne candidacy. I've interviewed for her. It's just not for me is the way I like to say it. It's the background of the woo woo type stuff is a bit off-putting to me. I understand that someone with literal Christian Bible beliefs that also I don't like, maybe I'm more willing to accept as most of our presidents, of course, have had those views because they're otherwise more qualified. But some of the things that she says just strike me as, I just don't know. I'll give you an example. When she was on with Russell Brand, she said, there's no such thing as clinical depression. It just means someone in a clinic told you, you have depression. I don't believe that to be the case. I think we have an understanding. There's two types of depression. There's like a genetic predisposition depression. There's like a acute, something's happening in my life. Temporary depression, okay. When she was asked about it recently, she said, I didn't mean it. I was just trying to impress Russell Brand. I don't know if I'm more bothered by the things she first said or by the fact that she wanted to impress Russell Brand. But it's just like, it's just really not for me. And I agree with her on, we need to take the climate more seriously. We need to expand access to hell. I'm with all of that stuff. Now I want to say one other thing about this. Anybody who wants to run should run. I am not suggesting there should be an uncontested primary for Joe Biden. Absolutely. So you think it should be contested? Well, what I mean by contested is, so there's two parts to what we mean by contested. Will the DNC organize debates? And we'll get to that in a second, but should anybody who's on the left get out of the way because Joe Biden is president and he's running for reelection? Absolutely not. The question about should there be debates? I would like there to be debates. The DNC pretty clearly isn't going to organize them. I think if you did them, you would have to say at what polling level do you qualify? And I don't know exactly where you put that number, but I think it would be a great thing to put Joe Biden on a stage with, if you can get what, 6%, 8%? I'm not really sure what the number would be. </s><s>[INST] I'm totally all for that. Why is this set of candidates, at least from my perspective, so weak? [/INST] Do you have an understanding? Do you have an understanding? There's a lot of different answers to this. One aspect of this, which I think is more of a socio-cultural thing, which I've recently read about to some degree, is the job actually turns off the people who would be best at it because of what you need to do to become president. And it includes all but completely abandoning your existing day-to-day life job, which you may depend on, and family to some degree. It's horribly negative, as we already talked about. And at the end of all of that, you either lose and then have to rebuild, and maybe you're not in a position to be able to do that, or you win, and then now you've got four years of being one of the most hated people, no matter how good a job you do. So I think by its nature, it turns off a lot of people that would otherwise be good. I also think that there's a lot of posturing from within the parties about, well, you might be good, but it's not your time yet, so you should wait, and then let's talk about maybe a Senate seat here and there. So it's like a company, essentially, and they're figuring out where they want to place people. I think all of these things make it so we end up with candidates most people aren't super thrilled with. </s><s>[INST] So it's difficult for somebody who's young [/INST] or an outsider to quickly become a candidate, young. I think that that's true, and I think also, in a lot of ways, it's just not, would you want to be president? No. I mean, I can't be, because I wasn't born in the US, </s><s>[INST] so it's easy for me to say, but. If everyone says no, then we'll get the people that we have. No, I understand that. So I would love to help somehow. Sure. And I feel like there's not even a mechanism for helping, except through the democratic, through the voting process. But I'm just annoyed how little technology there is in the whole process, how little innovation there is [/INST] in the whole process, all of this. The sad thing is, this is written about a lot, which is there's this thing called political hobbyism, and I think there's a good chance that some of the people in my audience are political hobbyists, in the sense that they follow this stuff as entertainment, to some degree. And I've written a lot about how, I've read a lot and talked a lot about how, okay, we vote every two years or every four years in our local elections, et cetera. And then we think about politics all the time. Neil Postman wrote about this in his book, Amusing Ourselves to Death. But what are you actually going to do about the kids starving in this country and the nuclear buildup in that country? Okay, if everybody refocused their attention on their immediate communities, and that could mean any number, it could mean the town or city you live in, or it might mean an athletic club or whatever. If everybody, this time they spent on political hobbyism, they moved somewhere else, which might put me out of a job. That's okay, I'm willing to lose my job because I think it would be so beneficial. Then our communities would just be that much better because you can actually affect change in a much more tangible way locally, whether it's obvious people talk about potholes, </s><s>[INST] but other things as well. Yeah, and I wish our system was more amenable to that kind of contribution, hopefully to the digital space it would be. Let me ask you about, on the Republican side, Ron DeSantis, what do you think of him as a candidate? [/INST] Money against Donald Trump. Think of him as a candidate. I think in the couple of weeks before our discussion today, his campaign, which hasn't even started, has sort of started to implode. And this was something that I started thinking about in September, October. He really doesn't seem ready for prime time in the sense that just being confronted, and confronted's not even the right word, just being asked about some topics he didn't really seem to want to talk about. He responded in such a sort of disproportionate, unhinged way during his recent trip to Asia. He was asked about, why aren't you, or why are you responding but in this weird way to Trump's attacks on you? And he went into this weird bobblehead thing with a weird smile, and something came out that didn't make any sense, and he sort of got mad at the reporter. And it was just like, if you can't handle that, you can't be on a debate stage with Donald Trump. And again, for all my criticisms of Trump, the guy gets you on a debate stage, he can make you look pretty silly. He was recently asked about his role at Guantanamo Bay when he was an officer in, I forget which branch of the armed forces, and he just sort of attacked the journalist asking the question, and it just looked very bad. And there are increasingly big Republican donors who are not fans of Trump, and were sort of hoping to put their eggs in the Ron DeSantis basket who are saying, this guy just doesn't have what it takes, I don't think he can do it. So I don't know if DeSantis will be able to get away. Once you're polling 20 something like he is, and you haven't even announced, it's very attractive. And he probably to some degree is thinking, if I wait till 2028, I might not have this opportunity again. But Trump's polling 5253, which means even if DeSantis gets all of the current non-Trump vote, he has to figure out how to take something more from Trump. </s><s>[INST] I just don't know how he does it. First of all, the implosion aspect, that's part of the process, isn't it? You kind of implode a bunch of times. And then rebuild yourself. [/INST] And rebuild them because the new cycle kind of forgets. And then rebuild yourself, it's possible. The problem is, the first debate is in August. So that's only a few months away. And the decision's going to have to be made pretty soon. And unless he can get a new momentum going, I just don't know how he gets what he needs </s><s>[INST] in order to really have a shot. [/INST] So would anyone else running against Donald Trump? It's very tough right now. I mean, there are other people running. There's this guy, Vivek Ramaswamy, who's running. Nikki Haley is running her campaign, basically dead on arrival. Trump actually does better in polls, the more people run. When it's just him and DeSantis, that's the best scenario for DeSantis. It's not great for DeSantis, but it's certainly better. But I think the difficulty is, this is a question for Republicans to figure out. The people who rightly recognized in 2016 that this guy is not good for their party, still believe this guy is not good for their party. But many of them recognize that most of the voters are still behind him. You can always say it's early, his polling doesn't really mean anything, anything could happen. Something major would have to happen for Trump to lose that lead. If he got more, if he was arrested two more times and had more indictments and it just became like, this guy can't even campaign because he's so busy going from court to court. Maybe that would make a difference. </s><s>[INST] It's really tough to imagine. You said that there are three categories of people who vote Republican and that Trump introduced the fourth one. [/INST] Well, can you go through the four categories? Sure. So you've got like your pro-business low tax Republicans. These are mostly people like Mitt Romney. Mitt Romney has a bit of the social conservatism as well. He's Mormon and that's there, but Mitt Romney primarily, particularly as a Northeast sort of Republican. I mean, I know Utah, but governor of Massachusetts, he is like a low tax pro-business type guy. You've got your libertarian type Republicans who are primarily about freedom and liberty. Often they are actually more socially liberal where they go, I don't care about gay marriage liberal. You know, I don't care so much about abortion. And that overlapped a little bit with the Tea Party movement in 2010, although Tea Party did have a religious component, but sort of like the libertarian freedom minded folks and then the religious conservatives, people that support candidates like Josh Hawley or Ted Cruz, et cetera, where they're a big thing are social issues. Often they actually want Christianity being civil government. They don't want separation of church and state. Those are traditionally the three Republican groups. The one that Trump introduced was people who just didn't really pay attention to politics, but either followed celebrity or had grievances that they didn't yet have a scapegoat for and were sort of right leaning culturally, even though they didn't attribute that to Republicanism. And Trump was able to bring them into politics often for the first time as voters. They could be part of any of those three groups if they get more into politics or kind of be their own thing, but they're more kind of like cult of personality. </s><s>[INST] I'm here for Trump types. Did it have to do anything about the culture wars [/INST] and the identity politics, all that kind of stuff? Yeah, I mean, so in 2016, when Trump mobilized them, those weren't really issues the way they are now. </s><s>[INST] So I think at that time, it certainly was not a factor. What was the mobilizing issue? [/INST] It was just anti-Hillary in 2016? He did a good job on anti-Hillary, but a lot of it was identifying real economic problems, wage depression, lack of jobs in parts of the country, you know, Ohio and Indiana. Trump rightly identified, like we have an issue here. We don't have enough entrepreneurship, et cetera. But there was also a lot of scapegoating that was, you know, China and people coming through the U.S.-Mexico border were popular scapegoats for a lot of those problems. This gets us kind of to populism. Populism is a rhetoric and populism as a rhetoric doesn't necessarily come with particular policies. You can be a populist, a user of populist rhetoric and propose solutions that would be more aligned with Bernie or Tucker Carlson. Populists will often identify the plight of the middle class. The difference would be Bernie will say, we've got to put some restrictions on how much billionaires can make. And we've got to reinvest in these social programs. Tucker will say, BLM taking your house and a brown person from Mexico taking your job are what we need to deal with. So the populist rhetoric can lend itself to very different policy. And Trump used that very effectively in 2016. </s><s>[INST] Why do you think Hillary Clinton was hated as intense as she was by a certain percent of the population? It feels like that's the first election I witnessed where there's a lot of hate. Maybe I'm misremembering. I don't remember Obama misremembering. I don't remember the degree of hate. There was a conspiracy theory that he wasn't born [/INST] in this country, but I don't remember hate towards Obama. Record death threats under Obama </s><s>[INST] more than any previous president. Towards who? [/INST] Towards him. Yeah. Do you mean more hate between voters? </s><s>[INST] Between voters, between voters. But like, that's I guess what I was speaking to, but that hate was directed towards the narrative, the thread that connected all of that in 2016 [/INST] was Hillary Clinton. Few different things. And I'm not ranking these. These are just all things that come to mind. One is Hillary Clinton had been around in the political space for a long time, from her time as first lady, through a senator, secretary of state, et cetera. So I think that there was enough time for different groups to develop an antipathy towards her for different reasons. So time. Secondly, Trump's branding of her as crooked was very effective. Where there were so many people demanding that she be imprisoned. If you ask them what is the crime, they don't know. But she should definitely be locked up. That became a very big thing. The email story, as it were, and James Comey doing a second public event about that investigation, even though there wasn't any actual news about it, just doing a second event about it at the last minute, I think hurt her and also generated some hate. And I don't find Hillary Clinton to be particularly likable. Although I voted for her, I thought she was the better candidate. And I think that there are others who also didn't find her particularly likable. </s><s>[INST] Those are a lot of impediments to becoming president. Well, I was trying to understand why there's so many conspiracy theories about Clintons, in general, Bill Clinton and Hillary Clinton. [/INST] And I, maybe I'm not researched well enough. There is- </s><s>[INST] Of the why of it. The why of it, actually the extent of the conspiracy theories, the sort of the conspiracy theories [/INST] that they've killed a lot of people, this kind of stuff. It's hard for me to speak to them because I'm aware that they exist, but I'm not an expert in them because they seem so obviously baseless to the degree that I've researched them a little bit. And then I move on and, you know, it's been years since I've looked at this stuff. I know there's the Seth Rich one and there's the Clinton body count one. I think there's one connected to Epstein, if I recall correctly. There's all sorts of these different ones. Without speaking to any of them specifically because I'm not the expert on Clinton conspiracies, it does seem as though this stuff for so long has generated an audience. I mean, I remember in the supermarket when Bill Clinton was president at the checkout, seeing the tabloids and there were stuff about Hillary birthed an alien baby and, you know, all the, it seems like it's been titillating to people </s><s>[INST] for a very long time. Well, another question from Reddit, speaking of aliens, I would be curious to hear David's views on conspiracies and conspiracy theories, the extent to which real conspiracies happen and why conspiracies that have little evidence behind them managed to be so compelling to people regardless. Also, please bring up aliens and UAPs. Okay, where do we start? The conspiracy, what? So what in general, as a person who thinks about politics, thinks about this world, [/INST] like where do conspiracy theories fit in for you? And you, I think there have been conspiracies and by conspiracies, I'm using a colloquial definition, which is basically individuals working together to, in a clandestine way, impact or affect some kind of event or phenomenon very, very broadly. I mean, certainly that those things have happened. To jump around to some of the things that were in there, I think the reason that conspiracy theories are so compelling is that it's really tough for a lot of people to accept. There are random events, not predictable specifically, at a stochastic level, we might be able to predict them, but specifically unpredictable, bad events in many ways. I could be the victim of one or you could, or my family could. That's really scary to a lot of people, understandably so. And for some people, it's less scary and more soothing in a way to say, there aren't really random events like this. Somebody planned it. And if we had just known who planned it, it just could have been stopped because we would have known exactly when. That's just a psychological level, easier to accept for people. And I get that to some degree, because listen, it's not the most exciting thing that everything can just be going fine and something absolutely horrible happens and kills, who knows, some number of people or, so I think that's the biggest attractor to a lot of these conspiracy theories. </s><s>[INST] It doesn't apply to all of them though. But yeah, but there's still kind of a basic understanding of human nature where people, some people are greedy and want power and are corrupted by power. So there's kind of these compelling narratives that stick that, I don't know, the vaccine is an opportunity for a powerful billionaire to implant chips into you so he can control you further. It doesn't seem, what do I wanna say? It's like, for some reason, that doesn't seem as crazy as it should. Because you think like, maybe Hollywood contributes to that, but you think, yeah, you could imagine an evil person, a person that wants more control, more power, and is also at the same time able to convince themselves, as history shows, that they actually have the best interest of the populace in mind, that they're trying to do good for the world. So they do evil while trying to do good. You can kind of imagine it. So it's like, why not? And you listen to people in power, authorities, they kind of look and sound shady, you know? Like, the transparency, especially the older ones, I think younger folks are better at being real and transparent and just like revealing their flaws in the basic humanity. But people that are a little bit older in the positions of power, they're more polished. They're more like, it feels like they're presenting a narrative [/INST] where the truth is hidden in the shadows. I don't think there's anything wrong with suspecting. Maybe a public figure isn't giving me the full story. Totally reasonable thing to question. I don't think there's anything wrong with exploring a lot of these different things. I think the problem becomes, and I know you've talked about this in so many different ways with other guests, the problem becomes when we lose a shared understanding of how we would assess whether any of these things are true. And then both alleged evidence and an absence of evidence both become supportive of the conspiracy theory, because if there's bad evidence, you manipulate it and say it's good evidence. If there's no evidence, you say the evidence was obviously hidden by the people who carried out the thing or whatever. So unless we can have a shared understanding of how we would determine what's true, these are common conversations often between atheists and religious folks. How can we deter, like, is my faith in something or my desire for something to be true, a good way to evaluate whether it is true? </s><s>[INST] They're really similar questions. Well, let me ask you about Trump on that front about the election, 2020 election, maybe the better question is about January 6th. [/INST] Do you think January 6th was a big deal? I do. How big of a deal? Compared to what? Civil war. I think it was less of a big deal than the Civil War. Okay. No, I mean, so it's a very interesting thing though, right? Because we have not only the event, that's clever actually, it's not only the event, but it's what led up to it and what has happened since and did it change what is considered on the table that citizens can, should, or might do if they disagree with the results of an election? So I think that there are further reaching consequences than just was the six hour period on January 6th, a bigger or smaller deal than the Civil War. And there's so much wrapped up into it. Many conspiracy theories flowed from January 6th as well. 60 Minutes recently featured a guy named Ray Epps who was targeted by some on the right, claiming that he was an instigator or an agent of the FBI or something along those lines. There were people claiming that no real, it was like a no true Scotsman sort of thing. Like Trump supporters wouldn't riot. So by definition, it must have been Antifa. Police let him in or police were, you know, all these different things. I think it was a big deal in a lot of ways because it completely made us have to go back to the top to say, okay, what are the parameters of valid discussion </s><s>[INST] and activism in the United States? [/INST] But what aspect of the January 6th was bad for you? </s><s>[INST] Well, I mean, if you're thinking it from a big philosophical political perspective, so presumably the number of people hurt and the number of people who died [/INST] is not the only metric to consider here. Absolutely. I think the sum total of what it means about how the United States operates is what's most concerning. And I'll kind of just like flesh it out a little bit. So summer of 2020, Trump's already saying they're going to cheat. Now, the polling is close, but it shows that Biden's in a good position. People aren't happy with Trump. Any reasonable person would look and say, it's going to be close, but Biden certainly wouldn't be a crazy thing if Biden won, Trump's already saying they're going to cheat with mail in ballots. So they're going to cheat with early voting or they're gonna cheat with machines or we should do only in person or whatever else the case maybe we have the election. We knew in certain states how the vote count was going to go. Some states stop counting at 10 P.M. some states count all of the mail and stuff up front. Some don't, everything was completely predictable, at 2 a.m. Trump comes out and says, I won okay, but where are you getting that, sir? As he claims, people always refer to him. Where are you getting that? And with that statement, immediately we see that there is a large portion of this country that either is unable or unwilling to say, wait a second, the polling all said this was a real possibility. The counting schedules are all being adhered to. But Trump won, that doesn't make any sense. That doesn't happen. It builds, people are donating millions to Trump for supposed audits which nobody can define and lawsuits which go nowhere. And it builds and builds and builds. And we have a total separation from a factual reality. There's no reason to think by December 1st, right? Give three weeks to look through some of this stuff. By December 1st, there's no reasonable case to be made that Trump actually won, but it doesn't end there. It goes into maybe we can just like send different electors even though Biden won Arizona. Let's just like send, I don't remember how many electors it is in Arizona, let's just like send Republican electors to say we vote for Trump, but that's not democracy. That's not the way the system works. Let's make sure we're ready. Ready for what exactly? And then it builds to maybe Mike Pence can just like prevent Biden from being president or maybe we can just interfere in this other way. And then it gets to let's break into the Capitol. It's the height of saying we no longer comport ourselves attached to what is a verifiable factual reality. And when we no longer do that, we're also willing to commit crimes, property crimes, violent crimes, okay, to different degrees in order to try to have something other than democracy. It wouldn't be democracy if any of those things had happened. </s><s>[INST] Yeah, I think it's not the height of it. I think there is still a case to be made that that did not leave the realm of protest versus a violation of the principles of democracy. So to me, the height of what could happen on January 6th is if Donald Trump was much better executive, [/INST] he could take control of the military. </s><s>[INST] If it had succeeded. No, not even succeeded. [/INST] The attempt would have been more empowered. </s><s>[INST] I understand. The way not to bring up Hitler every other word, which is something your subreddit also told me not to do. It's kind of an important figure. It's interesting to study that moment in history because it reveals so much about human nature and that all of us are capable of good and evil. But thank you to your subreddit or Redditor for your contribution to the conversation. I will keep bringing up Hitler and the Third Reich and I'll keep bringing up Stalin. There's so much to learn from that. Anyway, an effective practice authoritarian could roll the tanks out into the city streets to establish order and in so doing, pause the process of democracy, as opposed to a few protesters breaking in [/INST] to a questionably protected building. I agree that what you're saying would be worse. I don't want to use it to minimize what the protesters were intent on doing. </s><s>[INST] They failed, fortunately. But to you, the intention was there. [/INST] Well, the intention was Trump should remain president. That's the intention. And to what length they would have been willing to go if by the evening, early evening, they were sort of like forced out, I don't know. I agree with you that Trump trying to use the military would absolutely be worse. There's these reports that he tried to seize voting machines, which is kind of funny because it's like, once you get the machine at Mar-a-Lago, what do you do with it exactly? I don't know. There's like a comedic element to Trump sitting around with voting machines, but he did float trying to do some other things. I don't believe there's reporting </s><s>[INST] that he actually tried to use the military. I wonder to what degree this opened the door to further things like this with other candidates on, you know, even in the Democratic Party also. Do you think there'll be more and more questioning [/INST] of the election results? There has been already. It's very clearly the playbook. Kerry Lake lost. She ran for governor in Arizona, 2022. She lost. What I mean by that is her opponent received more votes. It's like very clear what it means that she lost. She insists to this day that she won. To this day, she did the same grift Trump did about donate. We've got a case. We won in the case. He didn't win. They just set a court date. Like that's not what, you know, lies upon grift upon lies. So they did it then. It is, I, I, it's extraordinarily saddening, but it seems like this is now going to be part </s><s>[INST] of the playbook. [/INST] Do you think people on the left will start doing it? I don't have a reason to believe that that is going to happen, but I'm not going to say it never could. Absolutely. It certainly could. People on the left could start using it as a tactic. Right now there's not a sign that that's going to happen, but it's certainly good. My expectation is, and I'm not a betting man, but I would bet money. If Joe Biden loses in November of 2024, he will say, I lost. He will call the winner. He will concede and he will leave the White House </s><s>[INST] in an orderly fashion. You don't think there'll be claims of a hacked election. The ability to hack elections is becoming more and more effective with the developments [/INST] on the artificial intelligence side. The difficulty is you're basically saying, will something happen without me knowing anything about the election? Imagine there really was evidence of a hacked election. Then I would want those claims to be made, but the way elections have gone in the past, I don't expect that that's a claim that would be made. </s><s>[INST] No. Speaking of evidence of things that were claimed, what do you think about the Hunter Biden laptop? Or as you tweeted, the laptop from hell, the laptop from hell TM. Right. To what degree was this laptop story important? [/INST] To what degree was it not? Right. At this point, I have said many times, if there is any reason to believe that Hunter Biden, Joe Biden, Naomi Biden, Jill Biden, Hillary, Obama, Doug M, if there's any evidence, any of them committed a crime, they should be investigated. They should be charged and they should be tried, period. The Hunter Biden laptop thing has been floating around for so long and we still have zero actual pieces of evidence of any crime, particularly involving Joe Biden. There's the claim from some that references to the big guy are about Joe Biden getting 10% for some illicit. It's been years they've been saying this, they've not been able to bring forward any evidence on it. So my assessment of the Hunter Biden laptop is, it seems to mostly be a story about nude images released without someone's consent, which is illegal in most states and violates Twitter's own policies. That's the main story to me. Beyond that, I don't know how many people have a copy of this hard drive at this point. Rudy had it, Tucker. Do you remember when Tucker, this is unbelievable. Tucker said that he mailed himself a copy, a USB stick and it got lost in the mail. You have the mother load proving the criminality of Joe and Hunter Biden. And I don't, you just dropped it off with a stamp and it got lost in the mail. You don't have a backup copy. So I'm ready for the evidence to come forward. Hunter Biden has nothing to do with Joe Biden's administration, but as a person who, if he committed a crime charge him, investigate him, whatever, but it's almost getting satirical, the degree to which they're talking </s><s>[INST] about the Hunter Biden laptop. Yeah. What do you think about the social media aspect of this, that that story got censored? And what do you think about censorship in general on social media, that that story during an important time [/INST] in the electoral process got censored? So I, as a matter of principle, I think we have to define what we mean by censorship, but I'm against censorship short of illegal content, I guess, is the way I would put it. I do respect the company's right to have terms of service and to enforce them, as long as they're not illegal. If Twitter were to say, we don't publish content from Jewish people. Okay, now we've got a problem on our hands. But what is dubious to me is the claim that had people been able to see Hunter Biden's genitals, they would have voted for Trump, which I know it's like, David, you're making light of, but at the end of the day, what exactly is the claim? That if you had known more about Hunter Biden, I guess allegedly hiring prostitutes and having a drug problem and seeing pictures, you wouldn't have voted for Joe Biden. </s><s>[INST] I mean, I know me as a voter, I don't feel that way. I think it's less about the content of the story and about the actions of a social media company to control what you see and what you don't see. So you could imagine a social media company like Facebook and Twitter making the same kind of decision about our more impactful story [/INST] than a few dick pics on a laptop. Well, I think if that happened, then my view might be different, right? But I do, my general view though on the Hunter Biden story is had the articles not contained those images that were illegal in many States and violated Twitter's policies, I would say publish it, absolutely. I don't think it would have had an impact, but I would be in favor of it being, </s><s>[INST] of the links being allowed 100%. Okay, you mentioned Tucker. What do you think about Tucker getting fired from Fox? You're a media person that works independently. Yes. Tucker was a media person who doesn't work independently. Right. Yeah, what do you think about that particular situation? Is it representative of some big shift that's happening in mainstream media? What would the shift be? Basically, mainstream media freaking out because the funding is getting less and less and less and less, [/INST] and then it's going to give more power to individual- </s><s>[INST] What would the shift be? Commentators, basically Tucker Carlson [/INST] just starting a podcast and a YouTube channel. I think that's what he should do. I think that's the most profitable path rather than maybe going to work for Newsmax or whatever the case may be. But the firing fundamentally was not a politically oriented firing that suggests Fox News is changing its tune politically in any way. There's no evidence of that whatsoever. Tucker Carlson basically became a legal problem for Fox News. There's really four points to it. One is the $787.5 million settlement with Dominion partially was because of the claims that went out on Tucker Carlson's program. So to some degree, Tucker's program was a prominent node of the problematic claims that became the subject of the lawsuit. That's number one. Number two, Smartmatic, which is another voting machine company, still has a similarly sized lawsuit against Fox News based on the exact same sorts of claims it may cost Fox News again. So this is now two problems that Tucker's a big contributor to. Number three, former Tucker staffer has brought a lawsuit and I don't remember the exact claims, but I know that there are claims of different types of discrimination. It seems like it has legs and that may be a third payout related to Tucker Carlson. And based on the 60 Minutes piece from a few weeks ago, Ray Epps saying Tucker ruined his life by fomenting conspiracies about him around January 6th. That's ripe for another lawsuit. So to me, Tucker's firing was a risk mitigation strategy. Of many that will be employed as these lawsuits come forward, there's no evidence that it's because Fox didn't like. And what we mean by that, are we talking about Rupert Murdoch doesn't like or the, I don't know, but I don't have any reason to believe it's because Tucker's ideas were no longer welcome on Fox. </s><s>[INST] Certainly the audience liked them. So interesting. It's not even about the ratings. [/INST] It's about just the legal costs. Fox is interesting. The ratings question is interesting because Fox, unlike most other or every other cable news channel, they negotiate a fee from every cable subscriber. If you have Fox News as a channel, even if you don't watch it, Fox gets a little bit of money. They are dramatically less dependent on ad revenue than CNN and MSNBC. So the ratings question is an interesting one, </s><s>[INST] but Fox's position is different on that. Another question from Reddit. Both sides are the same in quotes, is a meme notion that has spread far and wide in American political discourse on the internet. To what extent do you agree or disagree with this notion? And why do you think it is so popular? Now, this Reddit comment also says that podcasts like Russell Brand and Joe Rogan or the legendary comic George Carlin are examples of big proponents of this notion, all of which I kind of disagree with. Russell Brand, Joe Rogan, and George Carlin claim that both sides are the same. The same and use that, you know all politicians are crooked and they suck and this kind of thing. [/INST] I don't know if they're... Same, both sides are the same? </s><s>[INST] I don't know if that's true maybe George Carlin. Anyway, leave that aside. To what degree do you think... Do you agree with this notion that both sides are the same? Left and right, the crooked, corrupt politicians, [/INST] they do what politicians do. I don't agree that it's the same. I think there are different factions that like to say that for different reasons. There are some individuals who want to present themselves as kind of being above the fray of partisan politics and so I call it enlightened centrism. </s><s>[INST] Do you mean that positively or negatively? [/INST] No, I mean it negatively. Yeah, it's a bit of a pejorative. The idea that I am not going to fall for being a Democrat or a Republican. I can see that these are just two sides of the same coin, equally bad, lying to every... Okay, so that's one, it's sort of like, it's popular at dinner parties in some circles to go, oh, I'm... Both all these politicians, you know, left and right. So that's one side of it. The other side of it is that it's often used when your side has really stepped in it. It's a popular way to acknowledge that your side has done something wrong, but while framing it as it's not uniquely wrong and it's not worse than what anybody else does. And I find that it's one of the lamest and most kind of cringe inducing things to hear because of the what comes next. And usually what comes next is not a good, accurate criticism of something that took place and a discussion of how to solve a real problem that we have. I find it a conversation stifler. It also is used to kind of suppress voter turnout, not actively. It's not that the people who say that go around saying, don't vote. But the idea, of course, is the more people that believe that it doesn't really make a difference who you vote for, it's going to suppress voter turnout. And I want voter turnout to be as high as possible, not as low as possible. </s><s>[INST] So I also dislike it for that reason. So is it possible to say that one side is worse [/INST] than the other in modern current political climate? Listen, I'm a person on the left. I'm not pretending to come here and not knowing that my view is biased because I'm a person of the left. If you ask Ben Shapiro, he'll tell you something different. I think in 2023, some total, the influence of the American right wing, if the American right wing were to get everything it wants, it would be a horrifying reality. If the left were to get everything it wants, we'd have to figure out a few things, including exactly how we pay for certain programs. But they're mostly noble goals. And I believe that they are more supportive of an individual self-determining what they want to do in life and how they want to live and is more in line with the idea of freedom and liberty than what the right is currently proposing. That's my view. And of course, people will disagree with me all day. No, we get to freedom and liberty the way that the right wants to do it. </s><s>[INST] Okay, well, we can have that conversation. So I think you've implied in your answer, it was kind of focused on policy. It felt like it was focused on policy. There's other stuff that people worry about, particularly with the left, what may be termed the woke mind virus. [/INST] Where have I heard, who's using that term a lot now? </s><s>[INST] I'm trying to think. I'm not sure, I'm not sure. I'm not sure where it comes up. But the cultural aspect of this, that if you give a lot of power to people on the left, as you gave as an example, there would be a lot of kind of censorship and suppression of speech and a kind of dividing up of a society of who's allowed to, basically a reallocation of resources, not based on merit, but based on some kind of high ethical notions of what is right. And only a very small percentage of the population gets to decide what is fair, what is right, [/INST] which is, you know. We already have a small portion of the population that's deciding fair. Okay. </s><s>[INST] Yes. But I don't know how many different ways I can say kind of a negative characterization of folks on the left when we're now comparing it, just as to play devil's advocate. Sure. So is that something that you worry about? So setting policies aside, wokeism. Yes. [/INST] How big of a problem is it? Yes. This is a great conversation. So let's, two sides of it. Okay. We have new polling that seems to suggest so-called wokeism is kind of more popular in the United States than anti-wokeism. And I'll tell you what I mean by that. This is the less interesting part. We'll go to the more interesting part second. People, sometimes what people mean by wokeism is an overreaction to a perceived injustice that goes beyond what would be fair and equitable. There was this really interesting poll in it. Ask questions like, for example, do you believe society has gone too far, not far enough, or just about the right amount in dealing with issues affecting the trans community? The woke position, which is society hasn't gone far enough, was far more popular than we've gone too far. Now, the right-wing media narrative is we've gone way too far. This is out of control. And there are lots of other similar answers. It's not a huge margin. A lot of these are like 58 to 42, 60 to 40. It's not like 90 to 10. But by a small margin, the so-called woke perspective of we actually haven't yet done enough to fix some of these issues is a little bit more popular. So if we went back to DeSantis, this is part of why I think DeSantis's anti-woke agenda </s><s>[INST] may just be a political misstep. That's a really interesting result. I wonder how the questions are framed. But it's still interesting, nevertheless, no matter what, to hear that people are, majority of people in America, are woke, [/INST] and not in the negative sense of the word. The poll didn't use the term woke. Right. Right. This is a critical thing. </s><s>[INST] Let's use... This is a critical thing. [/INST] Let's use the term woke positively. The term has kind of been perverted. Yes. Four years ago, when the term was started to be used, I would have said, oh yeah, woke just means like, I have become aware of problems that are bigger than any one person can fix for themselves that relate to the system. I think that's what... And we might disagree on which problems fall into that category, but like it was kind of benign. I think now it just means like, outrageously left wing, maybe even with socialist or Marxist undertones. </s><s>[INST] It's become a pejorative at this point. But also like bullies. Like people... Bullies, sure. [/INST] Like people... Bullies, sure. </s><s>[INST] Sensors. Yeah, but people that go around calling others racist, sometimes, oftentimes, without any proof of that or justification. Fair. But that's a few folks on Twitter, you're saying like the polling is starting to show that like, no, they're still... Most Americans still care about these issues [/INST] and want to improve, want to make progress. I think that's the case. And they want to do it in a genuine way that doesn't suppress or oppress anybody. But now let me get to like, to what degree do I think that actual, when it goes too far is a problem. It absolutely exists. We can find instances of where this exists on the left. I've been told many times that as a Jewish, Argentinian immigrant to the United States, I actually don't qualify as oppressed enough because Jews are privileged now in the US and my family had just enough money to leave Argentina. So there's this kind of like oppression Olympics thing where I've been told you don't get to comment. For example, like a topic in the Latino community now is, are you familiar with Latin X? Okay. In Spanish, there's an analogous movement where words by their nature sort of like have a gender. So like the word for friend is amigo. But if it's a woman, you would say amiga. So right from there, you can tell the gender that we're talking about. And if it's a mixed group, you say amigos. It's the male with an S, but it could include both. There's a movement now which wants to do away with that and put the letter E in. It's a new word. Okay. It's a gender neutral word. Amigos, totally new. I don't like that. And I don't know anyone. No one in my family uses it. And I think it's kind of like a strange imposition from someone kind of with a solution in search of a problem. I've been told you moved to the US long ago and like your English is good and like you look wide and so like you don't get to weigh in on that. That I think is an example, if I understand correctly, of the type of thing you're talking about. I'm kind of being bullied. I'm fine. I'm surviving fine, but I'm being bullied over it and disqualified and saying you don't get to speak on this issue. All of those example, all of that stuff, I am completely against. And I tell people on the left, we're actually hurting our own movement with this stuff. </s><s>[INST] I just don't think it's as big as some others believe. It's you don't think it's an existential threat to our civilization in the West. [/INST] No, I don't. No, I don't. And I mean, look, we've got a Biden administration. I see Biden as center left. Those who see Biden as extreme far left. This stuff has played almost no role whatsoever in the first two plus years of his administration. What does people that see him far left as far as far left? There's people on the right who I mean, Trump says Biden's a Marxist socialist communist. I haven't heard that. </s><s>[INST] I haven't heard that because I don't think that would stick very much. I think that's it at every rally. [/INST] Yeah, which I love very much. I think this is at every rally, which I love to tell us that you don't watch these things. </s><s>[INST] It's like I love how deeply researched you are in Trump. I can only imagine how good your Trump impression is at this point. [/INST] It's not very sadly. It's not. It's not. All right. No, but and I'll say one other thing on that, you know, take trans because just to talk about it a little bit, we haven't dealt with it much. The trans issue has become huge, I believe, because the right is obsessed with it. The right is very much not concerned with gay men anymore. It used to be that gay men is like, oh, we have to stop gay men from adopting and unnatural and pedophiles. Now it's trans. It's drag shows, et cetera. I do think that there is a fair question to say. How do we deal with trans women in a very small short list of sports? That's real. OK, my view, though, is I go, OK, we have all issues. We have issues related to gender and sexual orientation. We have issues related to trans. Within that, we have specifically sports. You can eliminate from that trans men. Nobody's worried about women, biological women who are trans men. And then when you say it's only in certain sports that it matters. Hey, I'm right there. I think it's a complicated question. I don't know how we deal with it. I would ask leagues that have experienced with this already. Whatever. The problem I have is pretending that the the vanguard of left wing politics right now is trying to force trans women into sports. It's like it's just not the big issue that the right is reacting as if it were. </s><s>[INST] It's not. All right. But perhaps because of the right, it's forcing the left to to continue discussing it. I mean, I feel like it, even in institutions, even at universities, it feels like these ideas of diversity, inclusion and equity are taking some of the air out of the room of what a university should also care about, which is merit. It feels like reprioritization is going a little too far the other way, meaning prioritizing this kind of amorphous concept of diversity is moving away, is giving power to people that don't care about merit. And it just want to bully people with a big stick that says racism or sexism or anti diversity. And it kind of suffocates the people that care about merit, about meritocracy, about inspiring people from all kinds of backgrounds to succeed. And it's just you kind of observe that. I'm sure that happens in all kinds of institutions. And the concern, I think the people that are concerned about wokeism are concerned about at scale, what impact does that have on a society when there's so much conversation about racism and oppression not to talk about merit, like who's the actual good person in the room, the best person in the [/INST] room. Generically, that's a concern to me, the degree to which it's happening at different institutions, I think is worthy of exploration. I know people who work in academia that are getting out of academia because they don't like the environment on their campuses for exactly the reason you're saying so it exists. There is no question about it. I also think that the idea of a perfect meritocracy is maybe not necessarily the goal in the sense that when you talk about perfect meritocracy, someone wrote a book about this who I interviewed about a year and a half ago and whose name escapes me. There are problems with a perfect meritocracy. I think what we want to do is generate roughly equal opportunity for people understanding that there is going to be an outcome on a gradient or a bell curve, allowing people generally speaking to determine the path that they want to take and giving them, if it's possible, the ability to pursue that without suppressing limiting. I mean, this is like relatively uncontroversial stuff among, I would argue, 95% of the left with the caveats of what you're talking about, which I agree exists. </s><s>[INST] It would be nice to know the actual data. Sometimes people blow stuff out of proportion. What is it's hard. It's hard to measure how much self censorship happens at university campuses. That's true. [/INST] That's true. I think also it's sort of like the pit bull bite stories thing where when a pit bull bites a person, it's more likely to be reported on because it fits a certain narrative. And there are right wing publications that are very interested in making this seem as if it is an epidemic. I'm the first to say it is happening to a degree. I don't know the degree that it's happening to. I know a lot of people in academia. Only a couple of them say that it's an issue. </s><s>[INST] Would they say it though, if they believed it? [/INST] I think they would say it to me. These are just personal contacts. It's not like I'm going to go blabbing. To push back. </s><s>[INST] I kind of agree with you, but at the same time, most, I mean, I'm deeply connected in academia. I have a huge number of colleagues. Most people self censor by not thinking about it at all. They're like, screw it. That's deeper. Whatever. I'm just going to focus on the thing I love doing, which is the work. And they don't think about, they basically remove themselves from politics and social issues. And they just kind of say, I'm going to do my engineering. [/INST] We'll do my mathematics. Sure. The problem with that is it's kind of, you can't go anywhere further to figure it out. It's sort of like, there's this funny clip where Jordan Peterson says, even atheists are actually religious. They just don't know it. And it's like, it's hard to test that, you know, I don't know. Okay. I mean, I don't, I don't know, but it's a, it's a fair point. I mean, there may be some people, if it has become so toxic for some people, they may have repressed it way down into their subconscious. But I don't know how we would know that. </s><s>[INST] But you, you, you know, symptoms of it because when certain people speak up kind of lightly and then a 19 year old or a 20 year old responds and is outraged. The fact that the administration listens to that 19 and 20 year old and then reprimands whoever spoke up a little bit. That's a really dangerous sign to me. And I don't really care about these, like, so I, I'm more with you. I don't think it's a big issue. But then I notice it. I wonder, wait a minute. Would this kind of environment allow a young Noam Chomsky to be around? Would this environment allow like, uh, I don't know, like, uh, what tenure was designed for, which is to have controversial thinkers and not kind of weird controversial things, but really people that challenge [/INST] things that should be challenged a little bit. Yeah, I sympathize with that significantly. I always try to look at specific examples. And sometimes I'll look at people else. I'll ask for them and people will send me five. And one of them is a legit bona fide example of what we're talking about. And for kind of like, uh, there was a complaint and it was investigated, but the teacher's tenure was never in jeopardy. And I don't know that I chalk this up to a big woke event. What do you think the kind of apparatus of the four year degree in college is going to look like in 20 years? </s><s>[INST] Oh, that's, I mean, we're like day by day that seems to be changing with GPT. I don't know if you've gotten a chance to interact with chat GPT. Absolutely. [/INST] My entire show now is written by chat GPT. </s><s>[INST] I mean, there's a, that's partially a joke. [/INST] It is only because it stopped looking at the internet in 2021. If it was current, I could completely just tune it out. No, I'm kidding. But it's a fascinating tool. </s><s>[INST] And, uh, it's changing the nature of how we, uh, do homework assignments. It's changing the nature of how we learn, how we look up new information, how we explore information, how we care about things we're interested in. I think it, um, I don't think we'll have value for university degree in 20 years the way we do now. I just think it changes everything. I think, uh, language models, I mean, Google search has already, and Wikipedia has already transformed, I would say our civilization, but it's, there was still a value for basic education. I don't, I think that starts to dissipate, uh, with, with chat GPT. So I don't, I don't know. I really, I really don't think there's a university the way we think of a university in 20, 20, 30 years. [/INST] I mean, I have a personal interest in it in that my daughter is 10 months old and I'm doing the 529 account. I'm going through the motions as if, but I also recognize, you know, if she went to the schools I went to just with the rate of tuition increase, you're talking 200 K a year by the time she's 18. And what happens with wages relative to that? This is like separate from the technological thing. And in my mind, I'm thinking, is this going to continue being the right path? What I would love to see is so many people that I interact with just by virtue of what I do have no foundation in critical thinking, epistemology, philosophy, media literacy. And if there were some way to make that the core of some basic education that everybody's receiving, which goes beyond, you know, chat GPT can do so many things, but I've not yet seen good examples of how it can teach you to think. Maybe you have a different view on how chat GPT can teach a user to think. But those skills seem to be so lacking in so many of the people I interact with. If there's any positive change to come from a changing dynamic with higher education, I wish it would be to go in that direction. </s><s>[INST] Well, no, chat GPT is actually much better at helping me think than any educator, even books that I've encountered, because it's very good at presenting the full picture, even better than a lot of Wikipedia articles, you know, on questions like the the virus leak from a lab, the COVID leak from a lab, it just presents to you all the different hypotheses, the amount of evidence available to it. It's like, it's like a full, calm, objective picture of it. There's no partisanship. It's like a really nice list of things that's available. [/INST] But I guess what I mean is, does it tell you how as a thinking human, you should evaluate the strength of each of the paragraphs it presents to you? You can literally ask. You can ask it to do it. </s><s>[INST] Okay. Okay. Yeah. And then it's actually a fun, it's fun to ask chat GPT that question, because you get good answers. And so you basically have a kind of Socratic, like a deep, intimate, like great podcast style conversation with an AI system every single day, or as many hours as you want, especially as it improves, and as the interfaces by which you communicate with a thing improves. So yeah, I think it will do exactly that, which is teach you how to think, because you will offload the memory of facts and equations and whatever else a school teaches you, you'll offload that to AI. And instead, you'll be using your human mind, which is what it, for now, is uniquely good at, which is asking good questions, [/INST] thinking through the complexities of issues when there's multiple perspectives on it, all of that. Well, then I stand corrected. Maybe then I don't know what college is going to be in 20 years. </s><s>[INST] Well, but you were sort of commenting, I see, to the, the financial aspect of it. Like, why does it even make sense? [/INST] Yeah. Yeah. </s><s>[INST] I'm thinking about the transformative effects of AI and what starts to ask, what is the, what is even education? Right. What do you suppose, what is the purpose of education? So one is to give you kind of a background knowledge on a bunch of different topics, but the other is to discover the thing you're truly passionate about and the thing you're really good at, such that you can make money and you can contribute to society and have a fulfilling life. [/INST] Yeah. And also learning to interact with other people, relationships are built, socializing, and so many other things as well. </s><s>[INST] But is that, you know, that is the big value of university. And maybe it should be called something else. [/INST] Yeah. Can you get that for less than 200K a year? Exactly. Or else? Yeah, no, it's a fair question. </s><s>[INST] A kind of social club. [/INST] And you know, one of the things I think about also is people who are well connected. I mean, this has always been, this isn't new, right? But if you're well connected and you have a sort of drive towards entrepreneurship and doing your own thing, and you're not pursuing a field that is very licensing dependent, like medicine or law, getting started four years earlier with some internships can be a privilege in some cases. But again, that's that path is available to the people that would likely do well, regardless of whether they went to college. And so it's a very privileged, self-selected group anyway. </s><s>[INST] Another question from Reddit. Ask David to explain why American style libertarianism is an unserious philosophy. [/INST] I don't know what they mean by American style libertarianism. I've talked before about these kind of utopian libertarians where, you know, we have we don't have police. You just kind of like hire a for profit company if you want protection. And if there's a conflict between two of these private security companies, then I don't know. You figure it out somehow. </s><s>[INST] So it's almost like anarchism. [/INST] Yeah, yeah. Yeah. If by I don't know what the question means by that American style libertarianism, but in general, my problems with libertarianism, as it is often presented, come from the work of sociology as well as human psychology, which is the reality that once you get a group that's bigger than one hundred and fifty people, you really have to start centralizing some decisions unless you're going to subdivide the one fifty endlessly into two seventy fives that now no longer have contact. But then that's not really one society. Now it's two. I've not seen good evidence. And I've read a fair bit about this, that once you get beyond one fifty, you can keep all decisions decentralized. And once you say some things need to be centralized, then it's a matter of how you do it. And it's going to be some version of government that conflicts with aspects of libertarianism. </s><s>[INST] Well, it could be companies, right? It could be it could be more market driven, which is the idea of anarchism, that you're not you don't give any centralized entity of monopoly over violence. And then if you think that the markets are efficient at delivering, especially in this twenty first century and beyond where a market could have perfect information about people. So one of the issues is that you can manipulate markets because there's not perfect information. But now in the digital age, we can we can be higher bandwidth participants in the market. So if you're choosing between different security companies or you're choosing between different providers, different services, you can do so more efficiently and more effectively and in the digital space. So you can kind of imagine it. But we haven't successfully done it without governments. [/INST] Yeah. And I think there's a practical once you get beyond one fifty, you also start specializing. It just is a matter of fact, you don't have everybody isn't growing their own food. Some people grow the food and other people do other things. And you come across a lot of the problems that started at the agricultural revolution. And whether you say that it's a company that's solving it or a government, the problems are going to be very similar. And I've not read anything that to my satisfaction explains how you deal with that. </s><s>[INST] Well, there's underlying principles of libertarianism, which is putting priority at the freedom of the individual. Right. And that's a compelling notion. [/INST] Yeah. Whenever I do these various political compass things that put you on two axes on the authoritarian libertarian axis, I am way down on the libertarian side as a left libertarian. So my tendencies are always anti-authoritarian and towards that option when it makes sense. </s><s>[INST] So I sympathize with that a lot. Another question from Reddit. Ask David what issues he disagrees with you on. Is there something? I have no idea. Okay, that's great. There you go. There's no issues. Perfect agreement. What's your view on Tesla? That's a good opportunity to ask. What do you think is strengths and weaknesses of Elon Musk? [/INST] You mentioned Twitter. Have you paid your $8 idea? Okay, that's great. I have not paid my dollars. I don't see the point in paying for it. I have no problem paying for services. I use a ton of services. I'll try the free. I'll go to the paid right now. So the way I used to use the verified feed was I would post a tweet and then the next day when I, you know, review what's going on in my social media, I would look at the replies to the tweet, which give me a mix of replies from verified and unverified people. But then I also look at the verified and see who that are verified public folks have responded to me or maybe I want to engage with or whatever the case may be. There's, I don't even understand why I would look at the verified feed anymore. So I never do because it's random folks who I don't </s><s>[INST] know when it, it sort of lost its utility to me. And then, yeah, sorry to interrupt, but the idea is if everybody who's human pays the eight dollars, it shows to you that it's not [/INST] bots. It's at least humans from the reports about the number of people that have bought the blue check Mark. I think we may be a thousand years from enough signups in order to make that sort </s><s>[INST] of like a reality. I don't know. That was the idea. It's an interesting idea. Honestly, I know [/INST] that was the idea. It's an. From my experience, the obviously, I was seeing all sorts of attack comments, some of which were, I'm sure, from bots. But I'm ignoring all of those comments anyway. So it really didn't affect my experience that much. I mean, here's the thing about Elon and I say this people sometimes like David, you obviously hate Elon or you obviously love Elon. I was an investor in Tesla starting in 2015. I've since sold all my shares. Great run. I'm on my second Tesla right now. I probably won't get a third one because I think that electric vehicle technology is now maturing such that when my lease is up, I'm going to have many more options with the range and charging network that's important to me. But I could be wrong. Maybe, you know, I don't know. I have no the cult of personality around people. They mean nothing to me. So for me, it's just like people are people. Nobody has only good ideas. Fine. I think that what Elon Musk did accelerating and pushing forward the battery and electric vehicle technology is unbelievable. It's it's a it's a one person wrecking ball in the best sense of saying we're not going to slow play this and do. OK, now Toyota has a Toyota hasn't actually entered, but now whoever we've got a 90 mile range car and next year it'll be 110. And it's just like we're doing this right now. You can compete or you can opt out and look at what's happened. Fantastic. On the Twitter side of things, I don't really get the whole plan. I don't know if it started maybe as kind of a goof of some kind. And it developed into I guess I have to buy it. And I think something about it ended up with there was a clause invoked where I think he did try to get out of buying it, but then was forced to to some degree. He was forced. The way Twitter used to work was you followed people. And when you looked at your feed, you either saw the posts from the people you were following in reverse chronological order or posts from the people you followed algorithmically tailored to what you're most likely to want to see. And if you didn't follow someone, you generally wouldn't see their posts unless it was like a sponsored tweet or someone you follow quoted or retweeted them. Fine. The for you feed TikTok, I believe, first had a so called for you feed. The idea is this is stuff you might like based on I don't know what either demographic data about you, your other habits, whatever. And so it's useless to me. It's just </s><s>[INST] it's just basically mostly right wing content that that is not an interesting thing. That is, I mean, so the the signals that are used to generate the for you page is looking at all your your likes, all your comments, all your blocks and mutes and all that is show that I mean, [/INST] I don't know why it's looking up. OK, so it's supposed to be very pleasant for you. So that I mean, I don't know why it's OK. I'm sure other people go, wow, this for you thing is awesome. And like, if you had insert some right wing or sitting here, they would go. Twitter used to suppress right wing voices, and now finally they're getting the fair shake that they deserve </s><s>[INST] in the for you feet. OK, I mean, I wonder if there's left wing folks setting their feelings of Elon aside that are enjoying the for you page. That's a really important question because it's supposed to be people on the left and people on the right should be enjoying the for you page. [/INST] Sure. Yeah, I mean, so for me, my thought on Elon is some incredible successes. I don't know about Twitter. I do think that I don't believe Elon is a right winger. And when you see interviews with him, certainly at least socially and in many ways culturally seems very moderate or even somewhat on the left in my experience. So I don't think it's Elon's a right winger. I don't that's not an interesting critique. It does seem, though, that throughout the Twitter escapade, he certainly ended up closer to some voices that may be influencing him in a particular way. That's giving some people that impression, you know, but as far as like the Elon hate or the Elon love, it's just it's just a person who's done some interesting things, some of which I like and some of which I could kind of leave aside. </s><s>[INST] I have seen folks drift towards the right more in response to just the viciousness of attacks from the left. [/INST] Like who? I'm all Elon. And so like who? So you do you do think he's drifted towards the right? </s><s>[INST] In so I don't think at the core, but I think on the surface. Okay. I think and I think Joe Rogan has as well on the surface, because I think maybe you can correct me. But it feels like people on the left attack more viciously. That has not been my experience. Well, it hasn't. No, this goes. So yeah, let me know, because my sense was that they attack people on the left viciously as well. Left attacks its own because you're not progressive enough. You're not, you know, it's [/INST] just this kind of bullying. Yeah, it was very intensely. Yeah, it was very intensely. No, you're 100 percent right that when the left has attacked me, it's almost as vicious as when the right attacks me. The difference in my experience is it's a smaller contingent on the left that's willing to levy those attacks against me. But I'm on the left. So to some degree, you could say, </s><s>[INST] well, that that's to be expected. There is toxicity on the left. But it's intense, isn't it? Like, that's what I mean, like the attacks on people who are on the left just you're not left [/INST] enough. Yeah, that's no, that's the I mean, it is a small number of people. I can't deny that that is absolutely absolutely a real phenomenon. And it depending on what sort of topics you take on publicly, you are going to suffer the wrath of that to a greater or lesser degree. But with all of these things, what I always go back to is, you know, I probably would have more disagreements with Rogan today than the last time I was on his show, which was like at the beginning of the pandemic. But there would be zero. And I've done clips critical of things that he has said substantive, of course, to me, it's sort of like, oh, yeah, I could sit down with him and do a podcast and it would be zero big deal. And I would tell him I stand by everything I said about what you said. And I would say it to you right now. There are people who write to me and go, oh, man, things must be really, really tense. Now, if you were to Rogan would never have you on because you disagree. He loves you. I'm sure he's just not thinking of it. I'm not the most important thing to Joe Rogan. I think both of us would be able to sit down and talk about every one of my criticisms. It would not be taken personally. And then we would move on and it </s><s>[INST] would be the next day. And it is a small number of people. You get attacked a lot. How do you not [/INST] let that break you mentally? I don't know. So let's see. I try to I mean, I'm in a toxic space. The news and politics, partisan news and politics, partisan news and politics on the internet with a social media component, just completely and totally toxic. From a personal perspective, when I'm done producing my last show of the week, until Monday, I try to completely tune out from news and politics altogether and also make an effort to just not look at feedback and what's going on. I also really limit my visibility. I don't need to read every comment. I don't need to look at every email or every tweet. I have 15 minutes each day where I go through my social media platforms, look at generally what is the reaction been, maybe include that in my assessment of how I want to tackle a certain issue if I missed a good point or something like that, and basically try to move on. When something like we talked about at the beginning happens, it becomes obsessive. I mean, it's unhealthy, right? Where I'm going, oh, my God, who's attacking me now? That's scrolling. It becomes, you know, I'm sweating. It's horrible. But I think just like limiting exposure to that and remembering that it is impossible to please everybody. And so I'd really rather have fresh, genuine views each day rather than views that are sort of like restricted and flattened by what I perceive to be people's preferences. </s><s>[INST] Yeah. So just can you speak a little more to the full process of creating the David back in the [/INST] show? Like what you wake up because you're doing five shows a week. I have the Letterman schedule, which means I do five shows in four days. I shoot Monday to Thursday, but we're doing five episodes. Basically, our guests we schedule in advance. I'm picking six to eight stories each day that are, like I said, a blend of stuff. I think will be interesting things I want to talk about and things where there's it's being discussed at one layer and I want to go deeper on it. And I feel like I'm able to do that. I choose those stories in the morning, record in the early afternoon, </s><s>[INST] and we put the show out by that afternoon. What's the preparation? How do you take notes? [/INST] Are you on a sheet of paper? No sheets of paper anymore. I used to do sheets of paper. I found something about it, like at work, the tactile nature of it. It became inconvenient for sharing the notes with my team, but basically we use a Wiki type system. It's called MediaWiki, which is basically like a Wikipedia clone old school. Yeah. Old school. So we can have pages for every guest, every topic. That's interesting. I haven't heard that. Yeah. I don't know anyone else who's using it. It works really well. It's so fast and it takes up almost no space. So it just is a really good tool. When my team, you know, when we book a guest and they have notes from the publicist, they'll put it in there and then I can access it. So I'm basically working off of notes rather than a script. I'll pull any audio visual stuff that I want so that that's available. And it's, I mean, it's really a very seamless, you know, we're doing this every day, four days a week. And so we have </s><s>[INST] it down to a well-oiled machine. We haven't heard that. Yeah. Where do you get ideas from? [/INST] Everywhere. I have a bunch of subreddits that I follow that I think are talking about interesting things. I have a curated list for which I still use Twitter and that is very good for this. It's a curated private list of journalists that I think are doing interesting work. So I'll see what's there. Look at the sort of standard news reporting, wire services, AP and Reuters. Glance at what everything from drudge to CNN to whoever is covering that day. Look at Google news. </s><s>[INST] How do you try to fact check stuff on your show? So like, is there sources or is there a process? [/INST] I always try to get to a primary source first and foremost for the facts of the story. And then I'll use other tools for background research. Oftentimes Wikipedia's footnotes, I find to be useful tools. Chat GPT is a good one. It, you really have to fact check it, but it'll give you ideas of where to do the fact checking, which I think is fantastic. Sometimes it gives me information that's flat out wrong. And when you ask for the source, it's like, oh, yeah, that, that actually is not real. Um, which is, Hey, it's part, part of the process. But, um, and then when there's like an expertise type of thing, if it's a breaking legal matter, I'll just call like a friend who's a lawyer or call a friend who's a doctor or something like </s><s>[INST] that. If it lends itself to that. Let me ask you about the nature of truth. Do you think it's becoming more and more difficult to know what is true and will become [/INST] continuously continue to get more difficult, especially with GPT? I think the big difficulty is in getting people to agree as to what is a statement of fact and what is a statement of opinion. I think once we can do that, reasonable people can more or less agree on how to get to the truth, or if we can't get to it, at least figure out how we would if the information were available. But the bigger challenge I'm having is someone will call in with an opinion, but say they want to talk about fact. And I have to explain to them, you're talking about an opinion and not a fact. And this goes back to the lack of critical thinking and lack of media literacy. Uh, but </s><s>[INST] that's the bigger challenge for me right now. But I mean, I think the big statements are always going to be somewhat opinions. Like, was the elect was the 2020 election fair? I think any answer to that is an opinion. I disagree. If I disagree, if we define fair. Well, yes. So then I don't think it's possible to define fair in a way that's not several paragraphs where each sentence now has facts, right? So what do you mean by fair? Is it, uh, who could show up to vote? What was the process of how easy it is to vote? Uh, was there actual, uh, cheating going on in different, like what is the evidence of that cheating? You have to actually get to the actual like details of a thing. High level, you know, uh, everything is just going to be an opinion. It feels like, and you can approximate that to be like, it's a well-founded opinion. Well, most of science is an opinion, even physics is an opinion. So like, I think there's a threshold beyond which an opinion becomes like, uh, this is a pretty reliable thing to assume for now [/INST] that that's okay. So let me revise. So I think maybe better said, I think that the difficulty, I mean, it is the process you described is probably the right process and is it's exhausting for mundane things. And that causes major problems. If we were to say, is it better for the economy to have a tax rate on people making over a million dollars, that's 20% or 50%. Okay. What do we mean by better for the economy? It's not an overwhelming task to decide on that. We could say, well, we'll say it's better for the economy by looking at what was the unemployment rate based on the tax rate on million, you know, people earning a million a year and what was GDP and whatever. Okay. We've, we've agreed. This is a statement. We are now in the realm of just determining what is given the parameters that we've established. I think that that's, that's relatively doable. The issue is with the bigger ones like you're talking about where, what do we mean by a fair election and fair in whose eyes and, but I am with you that it often devolves into a conversation about </s><s>[INST] opinions about what is fair rather than an ascertainment of the facts. Yeah. Yeah. And it feels like maybe avoiding some of these big, maybe there's some trigger words too, maybe avoiding them allows you to actually talk about the facts and through that, educate yourself and learn about like, uh, whether the virus leaked from a lab or not to me was always a super interesting question. I don't know why everybody got super touchy about it. Uh, most of the people I know, uh, colleagues, biologists thought it's pretty good likelihood that it leaked from a lab given everything. They just didn't, the evidence is not there for a either one. And so like, you should be able to just openly talk about it unless you're in a high political office where there could be geopolitical consequences to your statements. But in general, it's an interesting question. You should be able to talk about it, but there's no, first of all, there's not many facts around there, unfortunately. Um, and a lot of very conclusive statements about, especially in the early days were just opinions. And so you have to minions the idea of what is true and not becomes a little, even mentioning the word truth in that [/INST] context. It feels, um, defensive. Yeah. I completely agree with you, which is strange. Like it really, you think it shouldn't, one of the really good opening questions that I've had worked to my advantage when talking with people who I know disagree with me about a contentious topic is how do you think we would figure out X? And it often gets people thinking first collaboratively. And obviously we might have very different opinions, but with something like the COVID lab leak, I think it's an interesting one because if you say, okay, maybe it leaked, maybe it didn't, how would we figure that out? Who would we trust to weigh in on that? What evidence would count? Now we're kind of on the same team. And then if we can establish that, then we're on a search for a capital T truth together or whatever. It's kind </s><s>[INST] of pie in the sky, but in some conversations I've actually had success with that. And then you can kind of realize if, uh, if there's no amount of evidence that's going to prove a show to you that [/INST] you're wrong in your current opinion, that that's probably a really bad sign for you. It's a waste. It may be a waste to pursue the conversation further at that point. Yeah. Yeah. What? Oh, so, okay. You think Trump was a good president. How do you determine that? And what evidence might exist that would change your mind? There is no evidence Trump was the best </s><s>[INST] president ever. I think the conversation is probably done. Except a, yeah. All right. Uh, you mentioned Israel, Palestine. Well, what do you think about the situation in Israel and Palestine? Something you've thought about, spoken about for quite a time. Do you think [/INST] we'll ever see peace in this part of the world? I don't know. You know, I mean, uh, I could say, yes, I could say yes. I, I, the, you know, one of the problems is, and I'll give, you may not know that the, there are people on the left of my audience who call me a Netanyahu shill, even though I've never been a supporter of Netanyahu and I'm, I'm on the left. I just don't think that some of the, uh, kind of black and white characterizations about Israel are even remotely accurate. And I think most people, uh, it's become a sort of litmus test. Are you criticizing Israel enough? Are you showing us that you're actually left wing? I don't do any of that stuff. I really </s><s>[INST] look at the situation for what it is. I could say yes. That's become a litmus test in American [/INST] politics, uh, in the spectrum of American politics. Yeah. Yes. Um, my view big picture is that, uh, I don't think we're going to really get anywhere until some pre negotiated terms are set and the parties to do the negotiating are all good faith parties. For example, I don't think Israel's right wing party Likud is a particularly good faith arbiter of peace because I think leek wood benefits from there not being peace and the threat of violence, and there is violence. It's not just the threat of violence. I don't think Hamas is going to be an arbiter of peace for the Palestinian people either. I think the Palestinian authority is a question mark. I'm not sure. So I think that there need to be some pre conditions that would need to be set with regard to everything from settlements to a lot of this minutia. Big picture, though, if I imagine what the most likely solution looks like, it doesn't mean it's a perfect solution. And obviously, it's a solution. Many people will say it's not it's not going to happen. I think it's a solution where the borders are similar to what was being discussed in the Clinton era, to some degree, as many of the settlements as possible have to go understanding that some of the bigger ones are just not going to go. And there's going to have to be meaningful land swaps with which Yasser Arafat seemed to be amenable to when he weighed in on it. I believe it was in the 90s. The topic of the Temple Mount and Jerusalem, et cetera, is a complicated one. But I think that almost certainly East Jerusalem is going to have to be part of an eventual Palestinian state. You know, I mean, like we can go as kind of as far as as we want to with a lot </s><s>[INST] of this stuff. What role does U.S. have to play in this coming to the table with good faith parties? [/INST] I don't know whether I go back and forth between believing that the U.S. should play a big role to the U.S. should play essentially no role whatsoever, because, of course, of the funding of Israel that the U.S. provides will the U.S. I don't it's not that I have a personal problem with American involvement. And somebody like Bill Clinton was arguably relatively well positioned to try to make something happen. It's more just will there will it be seen as credible on the global stage? And that's, I think, the most important thing, because at the end of whatever negotiation takes place, both sides need to agree that this is where we are renouncing all past claims. And in the future, if there's a disagreement, we can't go back to that thing from the 80s or the </s><s>[INST] 90s. That's just like a critical piece of this. Yeah, it has to be stable and, you know, materialize into something stable over years, over years. Yes. Another difficult conflict going on in the world is the war in Ukraine. What do you think about the Russian invasion of Ukraine in February [/INST] 2022? I don't pretend to be an expert on this issue. I think you probably know more about this than I do just from the brief conversation we had before we started filming my view as a general observer of geopolitics and the way that this area, this part of the world is related to American presidents over the last several, you know, cycles is I don't think it's controversial to say that this was a war of aggression, an invasion of aggression, an act of aggression by Vladimir Putin. I do believe that if Trump had been reelected, Putin may have seen himself as having other tools with which to try to expand influence that may have been different than geographical pursuits, geographic pursuits. But we don't know that for sure. I also have a really hard time imagining what the end of this looks like. And that's very scary because sometimes the most benign end seems to be that Putin ends up out of power, either through no longer being alive or deposed in some way. It doesn't feel like that latter is super likely the former. There's reports about his health. I don't know how accurate they are. It's just hard to imagine a face saving exit that is going to be even remotely. What's the word? It's not even a question of acceptable. Just it's not satisfying either. Just not tragic, I guess is what I'm </s><s>[INST] looking for. In terms of Putin speaking to the Russian people and being able to figure out what to say, what kind of narrative to say why this war made sense. Yes. The same on the Ukrainian [/INST] side to figure out how to exit this war. Yes. I mean, to some degree, it requires Russian troops leaving Ukraine. And that is somewhat under the control. I mean, of course, it's not up to Ukraine whether the initiative continues. But what I am not thrilled with are some of the reflexive. You know, if Trump had been in power instead of Joe Biden, a lot of the reflexive comments about, oh, you're if you if you say Ukraine is just acting defensively, you're supporting neo Nazis or some of these things that have come out of the American Republican Party seem both wacky and like they would be saying completely different things. If Trump happened to be in the Oval Office, they're really proxy attacks on Joe Biden. </s><s>[INST] Yeah. Well, that in some sense, Ukraine is also kind of political litmus test of how you speak about it, I think, because of the huge amount of funding that's going from US to Ukraine. Maybe you can correct me if I'm wrong. But it seems to it seems to me that [/INST] this topic has become politicized already. A hundred percent. There are people like Marjorie Taylor Green and others saying we should be doing nothing for Ukraine. Zelensky is a comedian and we're supporting neo Nazis. That's it. Full stop. And you either subscribe to that or you don't. And it very quickly becomes it very quickly becomes as partisan as so many other issues. And it's really the most disappointing thing is that some of these issues become incredibly divisive, divisive, but they're simple. Like, for example, a conspiracy theory that we know isn't true. It shouldn't be devices divisive because it's so simple. Other issues become divisive and they are simplified. But in reality, they are extraordinarily complex and you lose the </s><s>[INST] ability to talk about the complexity because they're becoming partisan. Do you think there will always be war in the world as a bunch of folks in the subreddit that were interested in your different complex perspectives on foreign policy? So let's talk about war. When you look at the war in Ukraine, you look at what's going on in Israel and Palestine, you look at the wars across the world. Do you think there will always be war? As the Redditor put it, is it a necessary [/INST] evil in the game of geopolitics? I used to have what I now believe is an extremely naive perspective, which is that if we somehow if intelligent aliens arrived here, it would be so momentous for Homo sapiens that all of our differences would immediately be exposed to so insignificant. We would never fight again and we would realize that intelligent life. And then I spoke to people who deal in space exploration and other other scientists and they all said that David, that's extraordinarily naive. There would be a period during which this was as momentous as you're imagining and then it would become normal. And then we would go back to many of the same conflicts that we have now, sectarian, et cetera. I think that in all likelihood, there will always be conflict between factions, whether it's what we currently think of as war, probably not. I mean, it seems as though the tactics will evolve and it will be less about missiles and I don't know where it's going to go. I don't know whether it's going to become more biological or cyber or certainly something we haven't even considered yet. But I think there will always be conflicts we would </s><s>[INST] refer to in that way. Do you agree with Chomsky on his general harsh criticism of U.S. foreign policy in war that many actions, military actions in the United States are criminal in nature, [/INST] almost terrorist in nature? I am not, it's been a decade or more since I've read any Chomsky and I don't keep up with everything that he has recently said. So I don't want to </s><s>[INST] mischaracterize any of it. In general, Americans are sold the view that we're the good guys spreading freedom across the world. And no chance it takes a perspective that, yeah, but if you look at the number of civilians you kill while doing it, it's incomparable to any [/INST] other military actions across the world. Right. So I very much disagree with those who take the view that the U.S. is this wonderful global police force that's spreading democracy and fixing problems very, very much wrong. I think where I've had disagreements with Chomsky in the past is more he frame he seems to frame the U.S. as a uniquely bad actor in some of these cases. And I think it's more an outcropping of the size and wealth of the U.S. and less about uniquely negative intentions. And so I think that would be my general disagreement with Chomsky based on </s><s>[INST] stuff I read a decade ago. Well, he says that he knows the United States. He's an American. And so he feels his focus of criticism should be in America. And I think that's one of the great things about being an American and being in America is the freedom to criticize harshly. Sure. While we being a university professor, by the way, he's basically the embodiment of why 10 years are really valuable thing. I agree. Whether you agree with him or not. A question from Reddit. Sure. I agree. Ask David what he plans for his garden this year. [/INST] Is this a joke or is this not a joke? Is this a joke? It's not a joke. I got into gardening a few years ago. Honestly, I'm with the baby. I can't do a garden this year. And I have a lot of travel coming up, so everything would die. But I did start to try to figure out gardening. If you're stressed by the toxicity of the social media world, gardening is a great hobby. It really </s><s>[INST] is. But it is extraordinarily time consuming. So I have no garden planned this year. Other books are maybe movies in your life that had a big impact on you that, you know, you're thinking about that diet. Has there been stuff you read, forget it, but even just books like blogs or writers or just sources of information that had molded you into the intellectual, [/INST] into the political thinker that you are. It's so hard. This is sort of like, you know, you win an Oscar and you want to make sure you thank all the right people. I read so much and have been reading for so long that it's really hard to say. But I think certainly for me, narrative nonfiction has been a fantastic genre to learn not only about history, but also about people and psychology. And very often when people say, I don't really read, like, what can you recommend to me that might be interesting? Depending on, you know, knowing them to some degree, I'll give recommendations there in terms of just things I picked up recently that that I think are interesting. I've been reading a bunch of Neil Postman. I read a Jenny Odell has a new book on time and the concept of like saving time, spending time, etc. She just published it. Super interesting. I just read Lansing's book about the Shackleton voyage in Antarctica in </s><s>[INST] 1914, 15 and 16. Super interesting. I'm really all over the map. I have that one on audio book. [/INST] I've been meaning to listen. It's very interesting. And it seems inconceivable how these guys survived. </s><s>[INST] It's completely inconceivable. And yet they did. It kind of inspires you to think of space exploration and taking on similar kinds of risky and dangerous journeys. In narrative nonfiction, I agree with you very much. I've been reading a lot of 20th century history about Stalin and about [/INST] Hitler. Rise and Fall of the Third Reich, I've read twice now. What did you get out of reading </s><s>[INST] at the second time? The second time I listened to the audiobook as I ran, I get the same thing from it as I get maybe reading Man's Search for Meaning, which is all the troubles of day to day in the modern world fade away and dissipate when I'm thinking about the embodiment of evil at scale at that recent time in human history. It fills me with gratitude to have all the freedoms, all the simple joys of life that we have today. I think the second time as I was reading it, because William Shire was there, he's the author, he was there through the whole thing. You start to pick up little details. It's supposed to be like big things. You start to pick up the little quirks of how history turns and just like these little events. You notice the dynamics between people in a room during a meeting with Hitler. You just notice these little things that are mentioned because he was either there directly or heard it the next day. That's why to me, Rise and Fall of the Third Reich is interesting. It's because it's by a guy who was there, who's reporting on it versus a more distant, displaced retelling. I also like biographies. I'm a big fan of biographies. Walter Isaacson has just written some incredible ones, and Steve Jobs and Einstein, all that kind of stuff. [/INST] Victor Frankel's book is one I've read a bunch of times, and it's so short. Reading in general, I know a lot of people who read way more than I do, and I also know a lot of people who don't read at all. I mean, they haven't read a book since college, essentially. To me, it's almost like the amount I get from it, it's almost like a secret weapon where when I think in two or three or four hundred pages, which I can read in whatever 10 days or however long it takes reading 30 pages a day, the amount of information insights into so many aspects of the human psyche that I can get, it's sort of like it's not like I'm in a competition for anything in particular with anybody. I just do my show. But it's sort of like if I'm reading dozens of books a year and you're reading zero, I'm exposed to so many different things and ideas that are not even in your universe. It just seems like the power of reading just seems overwhelming. </s><s>[INST] I had speaking of getting attacked, I had a fun time getting attacked a few months ago for publishing a reading list, some reading at least a book a week, read 18 or 19 books from the [/INST] beginning of the year. You got attacked for the books you chose or for this? I don't know for what. I don't know for what, but it became quite viral. Attacked for reading? That's something. </s><s>[INST] So basically what happened is that people, I actually don't, it's not worth folks who know. Fair. Folks who don't even worry about it. What I really loved about being attacked for is it shows you can get attacked for anything, apparently. So it's not like I did something wrong. It was kind of a beautiful thing and it was just the most intensely beautiful display of absurdity of Twitter and the internet. There were articles written about me with a book list. There's no bad books on it. The thing I was being mocked for is reading Dostoyevsky, reading stuff that sounds like a high school reading list. Oh, I see. Or all these kinds of aspects of the reading list which doesn't stand up to any sort of legitimate kind of criticism. But the fact that people are just looking for single words or single aspects of a tweet and so on to criticize. It actually forced me to, because I released a video about summarizing my takeaways from one of the books and I've been meaning to do more and more, but every time I start to record it, I have this negative feeling. They kind of ruin the fun of sharing with others. [/INST] I know it's fair, apparently. Oh, I see. Yeah, I know exactly what you're talking about. My advice on that is don't do it. Just don't record it. And is that what you did basically? </s><s>[INST] Yeah, for now. But I think time cures it. But for now, I decided not to. Yes. [/INST] It's just until I feel joy when I do it. We are in such a privileged position to even be able to do this sort of thing, right? I have taken on projects and then it sort of sounds good or I end up doing it because there's some third party that brings the idea and I feel like I can't really say no or whatever. And then when I get in front of the camera or I have to write something for a while, I did a newspaper column that I hated doing. I realized that I'm ruining the exact thing that I have worked to build, which is that I can just do whatever I want. Why am I doing this? And sometimes it takes me a week to realize it. Sometimes it takes me a year, but just don't do it. That's the- </s><s>[INST] In this case in particular, it's also that there's a private thing I enjoy, which is reading. Right. And if sharing that private thing you enjoy is not fun, then just don't share it. Yeah, there's certain things, there's certain private things that should remain private, which is one of the first things ever. I'm the same person privately as I am publicly, but the books, it's like, man, I don't get to share, I guess through these conversations I can share some of the stuff I'm reading and enjoying it. Because it sucks. It sucks to get attacked for stuff. And it sucks to get attacked for stuff you love. [/INST] Yeah, especially reading. That's the bottom of the barrel. I have these ideas where I'll go, maybe for my next thing, I'll go from politics, which is so toxic. I'll go to travel blogging because there's so many travel bloggers I follow and there's so many interesting places. And then I go, wait a second. I like traveling and just hanging out. Now traveling is going to be my job and now I've got to bring two cameras with me and I've got to get shots and I've got to film my food. I'm not going to do that. I'm just going to do what I'm doing, but then I'll travel </s><s>[INST] when I want to take a vacation. And of course, some of it could be fun. I mean, I have to say, when I did one video on a book in 1984, I really enjoyed it. That whole process was fun. It was, um, um, I don't think I've ever thought as hard about a book when I had to make a video about it. Cause I had to like, you know, I read 1984. I don't know how many times, probably five, 10 times. I don't remember. Um, I read animal farm way more. Uh, but I don't think I was like, what do I think? What are the key takeaways for me? I didn't really know. Like if you asked me what I think about even animal farm, cause I haven't done that one and I've read that one. I don't know. Over 50 times is probably my favorite book is like, I would have to struggle and making a video about it. Basically a little mini lecture forced me to actually have an opinion about the details of it and to do enough research to think like, okay, what is the historical context of this book? I mean, it allowed me to say interesting and to think interesting stuff about the book. I, I, it was, I found it to be really rewarding to basically the old Feynman [/INST] thing. Uh, one of the best ways to learn is to teach video about it. Yeah. Yeah. I can't think of one thing I would say about animal farm and I read it again, not that long ago, but I don't know </s><s>[INST] what comments you kind of have a generic comment. Yeah. Like, uh, authoritarianism and so on, whatever. Yeah. But there, there could be interesting quirks of the book and the characters and the how, uh, how corruption happens. You could, you could say all kinds of stuff that it may be contrasting it. Like even when 1984 allowed me to contrast with Brave New World and, um, and, uh, and how, uh, that 1984 was politicized and how it's used by the Republican party of today. Like you could say a lot of interesting stuff if you like think about it and write it down on a sheet of paper. Maybe you don't need to make a video about it. So I found it to be really rewarding in general. So I probably will do more of it, but not always, not as a meat profession, just like with the travel blog. Yeah. I agree with that. I mean, you get threatened a lot. You get attacked a lot online. Do you think about your mortality? [/INST] Well, the other day I went to the doctor and he said, you know, next physical, we're going to be talking about a lot of new things. And so I was thinking about it a lot that day. Yeah. Uh, no, I mean, um, it's funny. I like, I recently did a bunch of estate stuff. Yeah. And when you have intellectual property, there's a question of like, okay, I have my assets, but also if I died tomorrow, especially in a particularly fiery death, my YouTube channel would probably for a while generate more money because it would be like, Oh my goodness, this person died in a terrible, what happens with a future revenue stream and all these different things. And it got me thinking about legacy and about the fact that people who do this sort of thing, it's kind of a new thing in a sense. And so, you know, if you work at ABC news, at some point you just retire and someone else fills in for you. How does my career wind down given like, I don't actually know the answer. I'm not sure. Um, what is it? I just one day stop posting videos, but all my content stays up, getting fewer and fewer views. Or do I delete </s><s>[INST] everything? Do I, I don't know. What did, what is the, what is the, I mean, so you, my trip to Ukraine, cause I knew I was going to the front. It's the first time I did, um, I recorded a video if I die and I posted it and I gave instructions to, uh, to folks what to do. So like there's a closure, but it's an interesting process. Like what happens to your, at which point does GPT [/INST] take over the continued tweeting for David pathway? Well, well, the tweeting I care less about right now, unless blue becomes something unbelievable. I'm less worried about Twitter, but some of my audience members have been saying, you know, some of these tools, David are getting good enough that we could clone your voice and also make it match video. And with scripts, you could just keep pumping out content, even if you were gone. And I said, now that I'm interested in that. I </s><s>[INST] want to learn more about boy, it's going to be a weird future. Uh, what advice do you have to [/INST] young folks that are facing this future? Almost always it's some version of start right away. And that applies in so many different ways. So if you're thinking about, oftentimes the context is people want to do what I do. And I always say, do not sit around for a year thinking about lighting. This is how you never do anything. And I, dozens of people who I've felt obligated to talk to on the phone because of a personal connection, I go through all the advice and I can tell they're not going to do it. They just, they're, it's already sounding too complicated. And so instead they'll sort of say, well, I got to get the right lighting and the right room and blah, blah, blah, blah. The best thing you can do, no matter what you're doing is just start right away. And that applies in this business and in whatever else you're doing. If you want to learn a new thing, find a new hobby, the ability to get data right away about what's working, what's not working, and whether you even like this approach that you're taking is so valuable and it will allow you to iterate. And the sooner you do it, the cost to a change of direction will also be lower. If there's any, I don't do like self-help or generic advice type stuff, but the one thing that applies in so many situations is situations is just try it right away and iterate from there. Yeah, start today and then do it every day. Every day. Or decide, hey, you know what? I figured out I don't actually want to do it. </s><s>[INST] Yeah, and iterate. Yeah. Well, usually you'll discover, you do. Do you think we'll make it out of the century, humanity, human civilization? [/INST] Yeah, out of the, so like to 2100? </s><s>[INST] Yeah, how much we got? 80 years? Yeah, 77. I think we're going to make it. I think we're going to make it. You think so? Yeah. What are the biggest threats facing our civilization? If not, woke us. [/INST] Yeah, if it's not woke ism, it's hard to say. I actually think that if you believe that we are on an inflection point of sorts in changes to society and acceleration of technology, et cetera, I think it's really tough to know in 2090 what will actually be the biggest threat. So I don't know. It's so cliche to say nuclear and climate change and another pandemic. </s><s>[INST] Technologically, our world might look so different. Yes. Yes. Unimaginable. What it means to be human is unimaginable. And also, the degree that we make progress out into space is also unimaginable. [/INST] Yes, yeah. I think space is super interesting. And there's people on both the left and right who, for different reasons, are kind of not into the whole space exploration thing. The people I hear from, the ones on the right, think it's just kind of dumb. The ones on the left think it's an excuse </s><s>[INST] not to fix problems here. And also, they say it's the plaything of billionaires. Sure. Which is another funny kind of concept. [/INST] Yeah. I mean, someone's got to pay for it. Why not be people who have a lot of money to plug in? </s><s>[INST] It can either be billionaires or governments that are trillionaires. Sure. [/INST] Somebody has to pay for big, ambitious moonshot projects. To me, the most interesting thing is that in getting closer to the next step of space exploration, we may well learn things that can then be used to improve circumstances here. For me, it's not one or the other. And I recently read a long piece about why not Mars, because it's terrible in every way for supporting life. Okay, so that's one perspective. But still, in so exploring, who knows what we might end up learning. So I'm big on it. I don't share the view of some on the left about it. </s><s>[INST] So I guess to add to your advice to young people, if a thing seems terrible, you still might want to consider doing it. [/INST] I would say so. Yeah. How many things I've seen. I mean, listen, there are so many trips where the day before I say, why am I doing this, the jet lag, I've got to do this and that. And now who if my guest host falls through, I should just stay in work. And I go, hold on, you do this every time. Yep. Just go. You never regret it. You learn something, you try something. I never regret the trip. </s><s>[INST] This hopefully applies to the conversation we had today. David, I'm a big fan of yours. Thank you so much for talking today. Thank you for being patient with me. We tried to talk earlier. Please continue doing what you're doing. Please continue being objective and thoughtful and fearless. Thank you. On the internet. [/INST] Thank you. Big fan of yours as well. I appreciate it. </s><s>[INST] Thanks for listening to this conversation with David Pakman. To support this podcast, please check out our sponsors in the description. And now let me leave you with some words from Mahatma Gandhi. What difference does it make to the dead, the orphans, and the homeless? Whether the mad destruction is wrought under the name of totalitarianism or in the holy name of liberty or democracy? Thank you for listening and hope to see you next time. [/INST] </s> |
<s>[INST] Sure, [/INST] yeah, first of all, I much prefer Janz metaphor. Um Miles Davis's was a real explorer in jazz and um, he had a coherent story, so I think I have one and, but it's not just the one you lived, it's the one you think about later. What a good historian does is they look back and they revisit. Um, I think what's happening right now is not a i that was an intellectual aspiration that's still alive today as an aspiration. But I think this is akin to the development of chemical engineering from chemistry or electoral entering from, from electromagnetism. So if you go back to the thirties or forties, there wasn't yet chemical engineering, there was chemistry, there was fluid flow, there was mechanics and so on. Um, but people pretty clearly viewed uh, interesting goals to try to build factories that make chemicals products and do it viably safely make good ones do it at scale. So people started to try to do that of course. And some factories worked. Some didn't, you know. So we're not viable. Some exploded. But in parallel developed a whole field called Chemical engineering. Right? And chemical engineering in the field it's it's no no bones about it has theoretical aspects to it. It has practical aspects. It's not just engineering, quote unquote, it's the real thing. Real concepts were needed, you know? Same thing with electrical engineering. You know, there was Maxwell's equations which in some sense where everything you know about electromagnetism but you needed to figure how to build circuits, how to build modules, how to put them together, how to bring electricity from one point to another safely and so on so forth. The whole field to develop code electrical injury. All right. I think that's what's happening right now is that we have we have a proto field which was statistics computed more the theoretical side of algorithmic side of computer science that was enough to start to build things. But what things systems that bring value to human beings and use human data and mix in human decisions. The engineering side of that is all at hawk. That's what's emerging. In fact if you want to call machine learning a field, I think that's what it is that the proto form of engineering based on statistical and computational ideas of previous generations. </s><s>[INST] But do you think there's something deeper about ai in his dreams and aspirations. As compared to chemical engineering? Electrical engineering? [/INST] Well, the dreams and aspirations maybe. But those are from those are 500 years from now. I think that that's like the Greek sitting there and saying we need to get to the moon someday. Um I think we have no clue how the brain does computation. We just a clueless. We're like, we're even worse than the Greeks on most anything interesting. Uh Scientifically of our era. </s><s>[INST] Can you linger in there just for a moment because you stand not completely unique, but a little bit unique in the in the clarity of that. Can you, can you elaborate your intuition of why we're like where we stand in our understanding of the human brain. And a lot of people saying you're scientists say we're not very far in understanding human brain, but you're like you're saying we're in the dark here. [/INST] Well, I know I'm not unique. I don't even think in the clarity. But if you talk to real neuroscientists that really study real synapses are real neurons. They agree they agree it's 100 hundreds of your task and they're building it up slowly. Surely what the signal is? There is not clear. We think we have all of our metaphors. We think it's electrical maybe it's chemical. It's a it's a whole soup, it's ions and proteins and to sell and that's even around like a single synapse if you look at a electro micrografx of a single synapse? It's a it's a city of its own and that's one little thing on a dendritic tree which is extremely complicated electrochemical thing. And it's doing these spikes and voltages have been flying around and then proteins are taking that and taking it down into the D. N. A. And who knows what? Um So it is the problem of the next few centuries. It is fantastic. But we have our metaphors about it. Is it an economic devices? It like the immune system or is it like a layered, you know, set of comedy? You know er thematic computations what we've all these metaphors and they're fun. Um But that's not real science per se. There is neuroscience that's not neuroscience. All right. That that's that's like the greek speculating about how to get to the moon fun, right? And I think that I like to say it's this fairly strongly because I think a lot of young people think they were on the verge because a lot of people who don't talk about it clearly let it be understood that yes, we kind of this is the brain inspired were kind of close breakthroughs are on the horizon and that scrupulous people sometimes who need money for their labs. Um That's what I'm saying. Unscrupulous but people will over sell um I need money from them. I'm gonna I'm studying your computational neuroscience um I'm going to over sell it. And so there's been too much of that. </s><s>[INST] So step into this like the gray area between metaphor and engineering with. I'm not sure if you're familiar with brain computer interfaces. So a company like Elon musk's neuralink that's working on putting electrodes into the brain and trying to be able to read both, read and send electrical signals just as you said, even the basic mechanism of communication in the brain is not something we understand. But do you hope without understanding the fundamental principles of how the brain works will be able to do something interesting at that gray area [/INST] of metaphor. It's not my area. So I hope in the sense like anybody else hopes for some interesting things to happen from research. I would expect more. Something like Alzheimer's will get figured out from modern neuroscience that, you know, a lot of there's a lot of human suffering based on brain disease and we throw things like lithium at the brain. It kind of works. No one has a clue. I that's not quite true. But you know, mostly we don't know and that's even just about the biochemistry of the brain and how it leads to mood swings and so on, how thought emerges from that we just we were really, really completely dim so that you might want to hook up electrodes and try to do some signal processing on that and try to find patterns fine, you know, by all means go for it. It's just not scientific at this point. It's just so it's like kind of sitting in a satellite and watching the emissions from a city and trying to affirm things about the micro economy, even if you don't have microeconomic concepts, I mean, it's really that kind of thing. And so yes, can you find some signals that do something interesting or useful? Can you control a cursor our mouth with your brain? Yeah, absolutely. You know, and then I can imagine business models based on that and even, you know, medical applications of that, but from there to understanding algorithms that allow us to really tie and deeply to, from the brain to computer, you know, I just no, I don't agree with Elon musk. I don't think that's even that's not for our generation is not even further century. </s><s>[INST] So just uh in the hopes of getting you to dream, you've mentioned coma Gaurav and touring might pop up. Mhm. Do you think that there might be breakthroughs that will get you to sit back in 5, 10 years and say, wow, [/INST] Oh, I'm sure there will be. But I don't think that there'll be demos that impressed me. I don't think that having a computer call a restaurant and pretend to be a human is breakthrough. And people, you know, some people presented as such. It's imitating human intelligence. It's even putting cuffs in the thing to make a bit of a pr stunt. And so fine that the world runs on those things too, And I don't want to diminish all the hard work and engineering that goes behind things like that, and the ultimate value to the human race, but that's not scientific understanding. And I know the people who work on these things, they are after scientific understanding, you know, in the meantime, they've got to kind of, you know, the train's got to run and they got mouths to feed and they got things to do and there's nothing wrong with all that. Um, I would call that though just engineering and I want to distinguish that, perfecting an engineering field like electoral insurance injury that originally, that originally emerged that had real principles and you really know what you're doing and you had a little scientific understanding, maybe not even complete. Um, so it became more predictable and it was really gave value to human life because it was understood and, and so we have to, we don't want to muddle too much these waters of uh, you know, what we're able to do versus what we really can't do in a way that's going to press the next, so I don't, I don't need to be wild, but I think that someone comes along in 20 years, a younger person who's absorbed all the technology and for them to be wild, I think they have to be more deeply impressed. A young coma, Gaurav would not be wowed by some of the stunts that you see right now coming from the big </s><s>[INST] companies, the demos. But do you think the breakthroughs from Komarov would be, and give this question a chance? Do you think they will be in the scientific fundamental principles arena? Or do you think it's possible to have fundamental breakthroughs in engineering? Meaning, you know, I would say some of the things that, you know, mosque is working with SpaceX and then others sort of trying to revolutionize the fundamentals of engineering and manufacturing of of saying here's the problem, we know how to do a demo of and actually taking it to scale. [/INST] Yeah, so there's going to be all kinds of breakthroughs. I just don't like that terminology. I'm a scientist and I work on things day in and day out and things move along and eventually say, wow, something happened. But it's I don't like that language very much also, I don't like to prize theoretical breakthroughs over practical ones. Um I tend to be more of a theoretician and I think there's lots to do in that arena right now. Um, and so I wouldn't point to the Komura's, I might point to the Edison's of the era and maybe muscles a bit more like that, but um, you know, must God bless him also, we'll say things about ai that he knows very little about and and and he doesn't know what he is, you know, it leads people astray when he talks about things he doesn't know anything about, trying to program a computer to understand natural language to be involved in a dialogue we're having right now and that happen in our lifetime. You can fake it. You can mimic sort of takes old sentences that humans use and re tread them. But the deep understanding of language, No, it's not going to happen. And so from that, you know, I hope you can perceive that deeper yet deeper kind of aspects and intelligence are not going to happen now. Will there be breakthroughs? You know, I think that google it was a breakthrough. I think amazon's breakthrough, you know, I think Uber is a breakthrough, you know, that bring value to human beings at scale in new brand new ways based on data flows and so on. A lot of these things are slightly broken because there's not a kind of a engineering field that takes economic value in context of data and and that, you know, planetary scale and worries about all the externalities, the privacy, you know, we don't have that field. So we don't think these things through very well. But I see that is emerging and that will be constantly, you know, looking back from 100 years, that will be constantly breakthrough in this era. Just like electoral injury was a breakthrough in the early part of the last century and chemical injury was a breakthrough. </s><s>[INST] So the scale the markets that you talk about and we'll get to we'll be seen as sort of breakthrough. And we're in the very early days of really doing interesting stuff there and we'll get to that. But it's just taking a quick step back. Can you give uh, we kind of threw off the historian hat, I mean you briefly said that uh the history of Ai kind of mimics the history of chemical engineering. But [/INST] I keep saying machine learning, you keep want to say, I just let you know, I don't, you know, I, I'd resist that. I don't think this is about a, I really was john McCarthy as almost a philosopher saying, wouldn't it be cool if we could put thought in a computer, if we could make the human capability to think or put intelligence in some sense into a computer. That's an interesting philosophical question. And he wanted to make it more than philosophy. He wanted to actually write down logical formula and algorithms that would do that. And that is a perfectly valid, reasonable thing to do. That's not what's happening in this era. </s><s>[INST] So the reason I keep saying, hey, I actually, and I'd love to hear what you think about it. Machine learning has uh, has a very particular set of methods and tools. [/INST] Maybe your version of it is that mine doesn't know. It doesn't very, very open. It does optimization, It does sampling, it does </s><s>[INST] systems that learn is what machine learning [/INST] is. Systems that learn and make decisions </s><s>[INST] and make decisions. [/INST] So weird pattern recognition and you know, finding patterns. It's all about making decisions in real worlds and having close feedback loops. </s><s>[INST] So something like symbolic ai expert, systems reasoning, systems, knowledge based representation, all of those kinds of things. Search does that neighbor fit into what you think of as machine learning? [/INST] So I don't even like the word. But you know, I think that with the field you're talking about is all about making large collections of decisions under uncertainty by large collections of entities. </s><s>[INST] Right? [/INST] And there are principles for that at that scale, you don't have to say the principles are for a single entity that's making decisions, single agent or a single human. It really immediately goes to the network of decisions a good word for that. There's no good words for any of this. That's kind of part of the problem. Um So we can continue the conversation to use ai for all that. I just want to kind of raise the flag here that this is not about. We don't know what intelligence is and real intelligence. We don't know much about abstraction and reasoning at the level of humans. We don't have a clue. We're not trying to build that because we don't have a clue. Eventually it may emerge. They'll make I don't know if they'll be breakthroughs, but eventually we'll start to get glimmers of that. It's not what's happening right now. Okay, we're taking data, We're trying to make good decisions based on that. We're trying to scale, we're trying to economically viably we're trying to build markets, we're trying to keep value at that scale. Um and aspects of this will look intelligent, they will look computers were so dumb before they will see more intelligent. We will use that buzzword of intelligence so we can use it in that sense. But you know, so machine learning, you can scope it narrowly is just learning from data and pattern recognition. But whatever I when I talk about these topics, maybe data science is another word you could throw in the mix. Um it really is important that the decisions are as part of it. It's consequential decisions in the real world arm. I have a medical operation. Am I going to drive down the street, you know, things that were their scarcity, things that impact other human beings or other, you know, the environment and so on. How do I do that based on data? How do I do that undoubtedly? How do I use computers to help those kind of things go forward, whatever you want to call that. So let's call it a I let's agree to call it Ai but it's um let's let's not say that what the goal of that is is intelligence. The goal of that is really good working systems at planetary scale we've never seen before. </s><s>[INST] So reclaim the word ai from the Dartmouth conference for many decades ago of the dream [/INST] of human. I don't want to reclaim it. I want a new word. I think it was a bad choice. I mean, you know, if you read one of my little things, um the history was basically that McCarthy needed a new name because cybernetics already existed and he didn't like, you know, no one really like Norbert Weiner, Weiner was kind of an island to himself and he felt that he had encompassed all this. And in some sense, he did. You look at the language of cybernetics? It was everything we're talking about. It was control theory and single processing and some notions of intelligence and close feedback loops and data. It was all there. It's just not a word that lived on, partly because of the maybe the personalities. But McCarthy needed a new word to say. I'm different from you. I'm not part of your, your show. I got my own invented this word. Um, and again, as a kind of uh thinking forward about the movies that would be made about it. It was a great choice, but thinking forward about creating a sober academic and world world discipline. It was a terrible choice because it led to promises that are not true that we understand, we understand artificial perhaps, but we don't understand intelligence. </s><s>[INST] It's a small tangent because you're one of the great personalities of machine learning, whatever the heck you call the field. The do you think science progresses by personalities or by the fundamental principles and theories and research that's outside of personality [/INST] of both. And I wouldn't say there should be one kind of personality, I have mine and I have my preferences and uh, I have a kind of network around me that feeds me and, and some of them agree with me. Some would disagree, but you know, all kinds of personalities are needed. Um, right now, I think the personality that it's a little too exuberant, a little bit too ready to promise the moon is a little bit too much in ascendance. Um, and I do, I do think that there's some good to that. It certainly attracts lots of young people to our field, but a lot of people come in with strong misconceptions and they have to then unlearn those and then find something you know, to do. Um, and so I think there's just got to be some multiple voices and there's, I didn't, I wasn't hearing enough of the more sober voice. </s><s>[INST] So uh, as a continuation of a fun tangent and speaking of vibrant personalities, what would you say is the most interesting disagreement you have with john Macoun. [/INST] So yeah, he's an old friend and I just say, say that I don't think we disagree about very much really. Uh, he and I both kind of have a let's build that kind of mentality and does it work kind of mentality and kind of concrete, um, we both speak french and we speak french water together and we have, we have a lot of, a lot in common. Um and so, you know, if one wanted to highlight a disagreement, it's not really a fundamental when I think it's just kind of where we're emphasizing um john has uh emphasized pattern recognition and has emphasized prediction. All right. So, you know, um and it's interesting to try to take that as far as you can, if you could do perfect prediction, what would that give you kind of as a thought experiment? Um and um I think that's um way too limited. Um we cannot do perfect prediction. We will never have the data sets allow me to figure out what you're about, ready to do, what question you're gonna ask next. I have no clue. I will never know such things. Moreover. Most of us find ourselves during the day in all kinds of situations we had no anticipation of that are kind of very, very novel in various ways. And in that moment we want to think through what we want. And also there's gonna be market forces acting us. Uh I'd like to go down that street, but now it's full because there's a crane in the street. I gotta I gotta think about that. I got to think about what I might really want here and I got to sort of think about how much it cost me to do this action versus this action. I got to think about the risks involved. You know, a lot of our current pattern recognition and prediction systems don't do any risk evaluations. They have no error bars, right. I gotta think about other people's decisions around me. I have to think about a collection of my decisions. Even just thinking about like a medical treatment, you know, I'm not going to take a prediction of a neural net About my health, about something consequential and I already have a heart attack because some number is over .7. Even if you had all the date in the world has ever been collected about heart attacks better than any doctor ever had. I'm not going to trust the output of the neural net to predict my heart attack. I'm gonna want to ask what if questions around that I'm gonna want to look at some other possible date. I didn't have causal things. I'm going to have a dialogue with the doctor about things we didn't think about when you gather the data. You know, I could go on and on and I hope you can see and I don't, I think that if you say predictions everything that that that you're missing all of this stuff. Um, and so prediction plus decision making is everything but both of them are equally important. And so the field has emphasized prediction, john rightly so has seen how powerful that is. But at the cost of people not being aware of the decision making is where the rubber really hits the road, where human lives are at stake, where risks are being taken, where you've got to gather more data, you've got to think about the air bars, you've got to think about the consequences of your decisions and others got about the economy around your decisions, blah, </s><s>[INST] blah, blah, blah. [/INST] I'm not the only one working on those, but we are a smaller tribe and right now we're not the one that people talk about the most. Um, but you know, if you go out in the real world and industry, um, you know at amazon, I'd say half the people there are working on decision making and the other half are doing, you know, the pattern recognition, it's important </s><s>[INST] and the words of pattern recognition and prediction, I think the distinction there not to linger on words, but the distinction there is more a constrained sort of in the lab data set versus decision making is talking about consequential decisions in the real world under the messages and the uncertainty of the real world and just the whole of the whole mess of it that actually touches human beings and scale that you send market forces. That's the that's the distinction. [/INST] It helps add those, that perspective, that broader perspective, you're right. I totally agree on the other hand, if you're a real prediction person, of course you wanted to be in the real world, you want to predict real world events. I'm just saying that's not possible with just datasets that it has to be in the context of, you know, uh strategic things that someone's doing data, they might gather things, they could have gathered the reasoning process around data. It's not just taking data to make predictions based on the data. </s><s>[INST] So one of the things that you're working [/INST] on, I'm sure there's others working on it, but I don't hear often uh </s><s>[INST] it talked about especially in the clarity that you talk about it and I think it's both the most exciting and the most concerning area of ai in terms of decision making. So you've talked about Ai systems that help make decisions that scale in a distributed way, millions, billions decisions, a sort of markets of decisions. Can you as a starting point? Give an example of a system that you think about when you're thinking about these kinds of systems. [/INST] Uh Yeah, so first of all, you're you're absolutely getting into some territory which will I will be beyond my expertise and and there are lots of things that are going to be very not obvious to think about just like Just uh again, I like to think about history little bit but think about put yourself back in the 60s, there was kind of a banking system that wasn't computerized really. There was there was database theory emerging and database people had to think about how do I actually not just moved it around, but actual money and have it be, you know valid and have transactions at ATMs happen that are actually, you know, all valid and so and so forth. So that's the kind of issues you get into it, you start to get serious about sort of things like this. Um, I like to think about is kind of almost a thought experiment to help me think uh something simpler which is a music market and uh because there is uh the first door, there is no music market in the world right now in the, in our country for sure. Uh there are something called things called record companies and they make money uh and they prop up a few um really good musicians and make them superstars and they all make huge amounts of money. Um, but there's a long tail of huge numbers of people that make lots and lots of really good music that has actually listened to by more people than the famous people. Um um uh, they are not in a market, they cannot have a career, they do not make money. </s><s>[INST] The creators [/INST] creators, the so called influencers or whatever that diminishes who they are, right? So there are people who make extremely good music, especially in the hip hop or latin world these days. Uh they do it on their laptop, that's what they do um on the weekend. Uh and they have another job during the week. They put it up on Soundcloud or other sites, eventually it gets streamed, it gets turned into bits. It's not economically valuable that the information is lost. It gets put up there. People streamed. You walk around in a big city, you see people with headphones on, you know, especially young kids listen to music all the time. If you look at the data, none of them very little of the music they listen to. It is the famous people's music and none of its old music. It's all the latest stuff. But the people who made that latest stuff for like some 16 year old somewhere who will never make a career out of this, who will never make money. Of course, there will be a few counter examples. The record companies incentivized to pick out a few and highlight them. Long story short, there's a missing market there. There is not a consumer producer relationship at the level of the actual creative acts. Um, the pipelines and Spotify, Eyes of the world that take this stuff and stream it along. They make money off of subscriptions or advertising and those things, they're making the money all right. And then they will offer bits and pieces of it to a few people again, to highlight that, you know, they're the simulator market anyway. Real market would be if you're a creator of music that you actually are, Somebody who's good enough that people want to listen to you. You should have the data available to you. There should be a dashboard showing a map of the United States. So in last week here's all the places your songs we listened to, it should be transparent Um vegetable. So that if someone and down in providence sees that you're being listened to 10,000 times in providence that they know that's real data. You know, it's real data. They will have you come give a show down there, they will broadcast to the people have been listening to you that you're coming. If you do this right, you could, you could, you know, go down there make $20,000, you do that three times a year, you start to a career. So in this sense ai creates jobs. It's not about taking human jobs. It's creating new jobs because it creates a new market. Once you've created a market, you've not connected up producers and consumers, you know, the person who's making the music and say to someone who comes to their shows about, Hey, I'll cut your daughter's wedding for $10,000. You'll say 8000, they'll say 9000. Um then you again, you, you can now get an income up to $100,000. You're not going to be a millionaire. All right. And and now even think about really the value of music is in these personal connections even so much so that um a young kid wants to wear a T shirt with their favorite musicians signature on it, right? So if they listen to the music on the internet, the internet should be able to provide them with a button as they push and the merchandise arrives the next day we can do that right now. Why should we do that? Well, because the kid who bought the shirt will be happy, but more the person who made the music, we'll get the money, there's no advertising needed, right? So you can create markets in prison, consumers take 5% cut. Your company will be perfectly uh sound, it will go forward into the future and it will create new markets and that raises human happiness. Um, now this seems like it was easy just create this dashboard kind of creates some connections and all that. But you know, if you think about Uber or whatever, you think about the challenges in the real world of doing things like this and they're actually, new principal is going to be needed. You're trying to create a new kind of two way market at a different scale that's ever been done before. There's going to be uh, you know, uh, unwanted aspects of the market. They'll be bad people, they'll be, you know, um, the data will get used in the wrong ways. You know, it will fail in some ways, it won't deliver value. You have to think that through just like anyone who ran a big auction or you know, ran a big matching service and economics will think these things through. And so that maybe didn't get all the huge issues that can arise. We start to create markets but it starts for at least for me, solidify my thoughts and allow me to move forward in my own thinking. </s><s>[INST] Yeah, so uh I talked to had a researcher Spotify actually, I think their long term goal they've said is to uh have at least one million creators make a make a comfortable living putting on Spotify. So in and I think you articulate a really nice vision of uh the world and the digitals in the cyberspace of markets. What what do you think companies like Spotify or Youtube or netflix can do to create such markets. Is it an ai problem is in an interface problems for interface design, is it uh some other kind of is an economics problem. Who should they hire to solve these problems? [/INST] Well, part of it's not just top down. So the Silicon Valley has this attitude that they know how to do it. They will create the system just like google deal with the search box. That will be so good that they'll just everyone adopt that. Right? Um It's not it's everything you said, but really I think missing that kind of culture. All right. So it's literally that 16 year old who was able to create the songs. You don't create that as a Silicon Valley entity. You don't hire them per se, right? You have to create an ecosystem in which they are wanted and that they're belong, Right? So you have to have some cultural credibility to do things like this, you know, netflix to their credit. Wanted some of that, some credibility. They created shows, you know, content, they call it content. It's such a terrible word, but it's it's culture, Right? And so with movies, you can kind of go give a large sum of money to somebody graduate from USC film school. Uh it's a whole thing of its own, but it's kind of like rich white people's thing to do, you know, and, you know, american culture has not been so much about rich white people. It's been about all the immigrants, all the the Africans who came and brought that culture and those, those rhythms and and that to this world and created this whole new thing, you know, american culture. And and so companies can't artificially create that. They can't just say, hey, we're here, we're gonna buy it up. You got a partner and um, so anyway, you know, not to denigrate these companies are all trying and they should and they, I'm sure they're asking these questions and some of them are even making an effort, but it is partly respect the culture as you are, as a technology person, You've got to blend, your technology with cultural with cultural uh you know, meaning </s><s>[INST] how much of a role do you think the algorithm, the machine learning has been connecting the consumer to the creator sort of [/INST] the recommend er system aspect of this? Yeah it's a great question I think pretty high recommend you know um there's no magic in the algorithms but a good recommend er system is way better than a bad recommend er system and recommended systems is a billion dollar industry back even in you know, 10 20 years ago um and it continues to be extremely important going forward. </s><s>[INST] What's your favorite recommended system? Just so we can put something [/INST] just historically I was one of the you know when I first went to amazon, you know I first didn't like amazon because they put the book people out of business or the library, you know the local booksellers went out of business um I've come to accept that they're you know they're probably more books being sold now and poor people reading them than ever before. And then local book stores are coming back so you know that's how economics sometimes work you go up and you go down. Um But anyway when I finally started going there and I bought a few books I was really pleased to see another few books being recommended to me that I never would have thought of and I bought a bunch of them so they obviously had a good business model but I learned things and I still to this day kind of browse using that service. Um and I think lots of people get a lot, you know there that is a good aspect of a recommendation system. I'm learning from my peers in a in an indirect way. Um and their algorithms are not meant to have them impose what we, what we learn. It really is trying to find out what's in the data. Uh it doesn't work so well for other kind of entities but that's just the complexity of human life like shirts. You know, I'm not going to get recommendations on shirts and but that's that's that's interesting if you try to recommend restaurants it's it's it's it's hard it's hard to do it at scale and but a blend of recommendation systems with other economic ideas, matching and so on is really really still very open research wise and there's new companies that emerge that do that. Well </s><s>[INST] what what do you think was going to the messy difficult land of say politics and things like that that youtube and twitter have to deal with in terms of recommendation systems being able to suggest? Uh I think facebook just launched facebook news sort of having uh recommend the kind of news that are most likely for you to be interesting. You think this is a I solvable again, whatever term you want to use. Do you think it's a solvable problem for machines or is it a deeply human problem that's unsolvable. [/INST] Uh so I don't even think about at that level. I think that what's broken with some of these companies, it's all monetization by advertising, they're not at least facebook, let's I want to critique them. They didn't really try to connect a producer and a consumer in an economic way, right? No one wants to pay for anything. And so they all, you know, starting with google and facebook, they went back to the playbook of, you know, the television companies back in the day, no one wanted to pay for this signal, They will pay for the tv box, but not for the signal at least back in the day. And so advertising kind of fill that gap and advertise. It was new and interesting and it somehow didn't take over our lives quite alright. Fast forward, google provides a service that people don't want to pay for. Um And so somewhat surprisingly, 90s, they may end up making huge amounts. They cornered the advertising market, it didn't seem like that was gonna happen, at least to me. Um these little things on the right hand side of the screen just did not seem all that economically interesting, but that companies had maybe no other choice, the TV market was going away and billboards and so on. Um So they got it and I think that sadly that google just has, it was doing so well with that and make it such that they didn't think much more about how, wait a minute is there a producer consumer relationship to be set up here, not just between us and the advertisers market to be created. Is there an actual market between the producer consumer? They're the producer is the person who created that video clip, the person that made that website, the person who could make more such things, the person who could adjust it as a function of demand. The person on the other side who's asking for different kinds of things, you know? So you see glimmers of that now there's influencers and there's kind of a little glimmering of a market, but it should have been done 20 years ago, I should have thought about it should have been created in parallel with the advertising ecosystem. Uh and then facebook inherited that. And I think they also didn't think very much about that so fast forward and now they are making huge amounts of money off of advertising. And the news thing and all these clicks is just is feeding the advertising, it's all connected up to the advertising. So you want more people to click on certain things because that money flows to you facebook, you're very much incentivized to do that. And we start to find it's breaking people are telling you, well, we'll get into some trouble as you try to adjust it with your smart ai algorithms, right? And figure out what are bad click. So maybe shouldn't be click through rate, it should be. I find that pretty much hopeless. It does get into all the complex of human life and you can try to fix it. You should. But you could also fix the whole business model and the business model. Is that really what are there some human producers and consumers out there? Is there some economic value to be liberated by connecting them directly? Is it such that it's so valuable that people are willing to pay for it? All right. And micro, but even after the micro, so I like the example, suppose I'm going next week. I'm going to India, never been to India before. Right. I have a couple of days in Mumbai. Um I have no idea what to do there. Right? And I could go on the web right now in search. It's gonna be kind of hopeless. I'm not going to find, you know, um I'll have lots of advertisers in my face. Right? What I really want to do is broadcast to the world that I am going to Mumbai and have someone on the other side of the market look at me and there's a recommendation system. They're not looking at all possible people coming to Mumbai, they're looking at the people who are relevant to them. So someone my age group, someone who kind of knows me in some level. Um I give up a little privacy by that. But I'm happy because what I'm gonna get back is this person can make a little video for me, are they gonna write a little two page paper on, here's the cool things that you want to do and move by this week, especially right, I'm gonna look at that. I'm not gonna pay a micro payment, I'm gonna pay you $100 or whatever for that, its real value, it's like journalism um as a non subscription, it's that I'm gonna pay that person in that moment, company's gonna take 5% of that and that person has now got its a gig economy if you will, but you know done for thinking about a little bit behind youtube. There was actually people could make more of those things. If they were connected in the market, they would make more of those things independently, You have to tell them what to do, you don't have to incentivize them any other way. Um And so yeah, these companies, I don't think of thought long along, I heard about that, so I do distinguish on facebook on the one side who's just not thought about these things at all. I think thinking that ai will fix everything. Uh and amazon thinks about them all the time because they were already out in the real world, they were delivering packages. People's doors, they were they were worried about a market, they were worried about sellers and you know, they worry and some things they do are great, some things maybe not so great, but you know, they're in that business model. And then I'd say google sort of hovers somewhere between. I don't I don't think for a long, long time they got it. I think they probably see that Youtube is more pregnant with possibility than than, than they might have thought and that they're probably heading that direction. Um, but uh, you know, Silicon Valley has been dominated by the google facebook kind of mentality and the subscription and advertising and that is that's the core problem, right? The fake news actually rides on top of that because it means that you're monetizing with click through rate and that is the core problem. You've got to remove that. </s><s>[INST] So advertisement, we're going to linger on that. I mean, that's an interesting thesis. I don't know if everyone really deeply thinks about that. So you're right. The thought is the advertising model is the only thing we have the only thing we'll ever have. So we have to fix, we have to build algorithms that despite that business model, you know, find the better angels of our nature and do good by society and by the individual. But you think we can slowly, you think, first of all, there's a difference you should and could, so you're saying we should slowly move away from the advertising model and have a direct connection between the consumer and the creator, The question I also have is, can we because the advertising model is so successful now in terms of just making a huge amount of money and therefore being able to build a big company that provides, has really smart people working that create a good service. Do you think it's possible? And just to clarify, you think we should move [/INST] away? Well, I think we should. Yeah, but we as you not me society. Yeah. Well, the companies, um, I mean, so first of all, full disclosure, I'm doing a day a week at amazon because I kind of want to learn more about how they do things. So, you know, I'm not speaking for amazon in any way, but um, you know, I did go there because I actually believe they get a little bit of this or trying to create these markets </s><s>[INST] and they don't really use advertising is not a [/INST] crucial part of it. That's a good question. So it has become not crucial, but it's become more and more present. If you go to amazon website and you know, without revealing too many deep secrets about amazon, I can tell you that, you know, a lot of people company question this and there's a huge questioning going on. You do not want a world where there's zero advertising. That actually is a bad world. Okay, so here's a way to think about it. You're a company that like amazon is trying to bring products to customers. All right, And the customer and you get, the more you want to buy a vacuum cleaner say you want to know what's available for me and you know, it's not gonna be that obvious. You have to a little bit of work at it. The recommendation system will sort of help. Alright. But now suppose this other person over here has just made the world, you know, they spent a huge amount of energy. They had a great idea. They made a great vacuum cleaner. They know they really did it. They nailed it an M I. T. You know, whiz kid that made a great new vacuum cleaner. All right. It's not gonna be in the recommendation system. No one will know about it. The algorithms will not find it and ai will not fix that. Okay at all. Right. How do you allow that vacuum cleaner to start to get in front of people be sold well, advertising and hear what advertising is. It's a signal that you're you believe in your product enough that you're willing to pay some real money for it. And to me as a consumer, I look at that signal, I say, well, first of all, I know these are not just cheaper lads because we have now right now that I know that, you know, these are super cheap. You know, pennies if I see an ad where it's actually I know the company is only doing a few of these and they're making, you know, real money is kind of flowing and I see an ad I may pay more attention to it and I actually might want that because I say, hey, that guy spent money on his vacuum cleaner. Uh, maybe there's something good there. So I will look at it and, and so that's part of the overall information flow in a good market. So advertising has a role. Um, but the problem is of course that that signal is now completely gone because it just, you know, dominate by these tiny little things that add up to big money for the company. You know, so I, I think it will just, I think it will change because the society is just don't, you know, stick with things that annoy a lot of people and advertising currently annoys people more than it provides information. And I think that a google probably is smart enough to figure out that this is a dead, this is a bad model, even though it's a hard huge amount of money and they'll have to figure out how to pull it away from it slowly. And I'm sure the ceo there, we'll figure it out, but they need to do it and they needed to, uh, so if you reduce advertising not to zero, but you reduce it at the same time, you bring up Producer, consumer, actual real value being delivered. So real money is being paid and they take a 5% cut, that 5% could start to get big enough to cancel out the lost revenue from the kind of the poor kind of advertising and I think that a good company, we'll do that. We'll realize that. Um, and there are already on facebook, you know, again, God bless them. They bring, you know, grandmothers, uh, they bring Children's pictures into grandmother's lives. It's fantastic. Um, but they need to think of a new business model and and they that's that's the core problem there until they start to connect producer consumer. I think they will just just continue to make money and then by the next social network company and then by the next one and the innovation level will not be high and the health, health issues will not go away. </s><s>[INST] So I apologize that we kind of return to words, I don't think the exact terms matter, but in sort of defensive advertisement, don't you think the kind of direct connection between consumer and creator? Producer is the best like the is what advertisement strives to do, right? So that is the best advertisement is literally now facebook is listening to our conversation and heard that you're going to India and we'll be able to actually start automatically for you making these connections and started giving this offer. So like uh, I apologize if it's just a matter of terms, but just to draw a distinction, is it possible to make advertisement just better and better and [/INST] better algorithmic lee </s><s>[INST] to where it actually becomes a connection. [/INST] Almost that's a good question. So let's put on the pushing first of all what we just talked about. I was defending advertising. Okay, so I was defending it as a way to get signals into a market that don't come any other way. And especially algorithmic lee, it's a sign that someone spent money on it as a sign they think it's valuable and if I think that if others think someone else thinks it's valuable and if I trust other people I might be willing to listen. I don't trust that facebook though, is who is an intermediary between this? I don't think they care about me. Okay. I don't think they do and I find it creepy that they know I'm going to India next week because of our conversation. </s><s>[INST] Why do you think that? So what you can just put your pr hat [/INST] on? Why </s><s>[INST] do you think you find facebook creepy and not trust them as do a majority of the population. So they're out of the silicon valley companies. I saw like not approval rate, but there's there's ranking of how much people trust companies and facebook is in the gutter [/INST] in the gutter including people inside of facebook. </s><s>[INST] So what what do you attribute that [/INST] to because when you don't find it creepy that right now we're talking I might walk out on the street right now that some unknown person who I don't know kind of comes up to me and says I hear you're going to India, I mean that's not even facebook, that's just if I want transparency in human society, I want to have, if you know something about me, there's actually some reason, you know something about me that's something that if I look at it later and audited kind of I I approve, you know, something about me because you care in some way there's a carrying relationship even or an economic one or something, not just that you're someone who could exploit it in ways I don't know about or care about or or I'm troubled by or or whatever and we're the world right now where that happens way too much and that facebook knows things about a lot of people and could exploit it and does exploited at times. I think most people do find that creepy. It's not for them, it's not, it's not the facebook does not do it because they care about them right in in a real sense and they shouldn't, they should not be a big brother caring about us. That is not the role of a company like </s><s>[INST] that way, not the big brother part but scaring the trust thing. I mean don't those companies just to linger on it because a lot of companies have a lot of information about us, I would argue that there's companies like Microsoft has more information about us than facebook does and yet [/INST] we trust Microsoft more, Well, Microsoft is pivoting Microsoft under satya Nadella has decided this is really important. We don't want to do creepy things. Really want people to trust us to actually only use information in ways that they really would approve of that. We don't decide </s><s>[INST] right. [/INST] And um I'm just kind of adding that the health health of a market is that when I connect to someone who producer consumer is not just a random producer consumer is people who see each other. They don't like each other, but they sense that if they transact some happiness will go up on both sides. If a company helps me to do that and moments that I choose of my choosing um then fine. So, and also think about the difference between you know browsing versus buying right? There are moments in my life I just want to buy you know a gadget or something. I need something for that moment. I need some ammonia from my house or something cause I got a problem with the spill. Um I want to just go in. I don't want to be advertised at that moment. I don't want to be led down very, you know that's annoying. I want to just go and have it extremely easy to do what I want. Um uh other moments I might say no, I'm, it's like today I'm going to the shopping mall, I wanna walk around see things and see people will be exposed to stuff. So I want control over that though. I don't want the company's algorithms to decide for me, right? I think that's the thing we there is a total loss of control of facebook thinks they should take the control from us of deciding when we want to have certain kinds of information, when we don't what information that is, how much it relates to what they know about us, that we didn't really want them to know about us. They're not I don't want them to be helping me in that way. I don't want them to be helping them, but they decide they have control over um what I want and win. </s><s>[INST] I totally agree. So, so facebook, by the way, I have this optimistic thing where I think facebook has the kind of personal information about us that could create a beautiful thing. So I'm really optimistic of what facebook could do. It's not what it's doing, but what it could do. So [/INST] I don't see that. I think that optimism is misplaced because there's not a bit you have to have a business model behind these things create a beautiful thing is really let's be let's be clear, it's about something and people would value and I don't think they have that business model and I don't think they will suddenly discover it by what, you know, a long hot shower. </s><s>[INST] I disagree. I disagree. In terms of uh you can discover a lot of amazing things in a shower. [/INST] So I say that I said they won't they won't they won't do it. But in the shower, I think a lot of other people will discover it. I think that this guy, so I should also full disclosure. There's a company called United Masters which I'm on their board and they create this music market. They have 100,000 artists now signed on and they've done things like going to the N. B. A. And the NBA, the music you find behind NBA eclipse right now is their music, right? That's a company that had the right business model in mind from the get go right executed on that. And from day one there was value brought to, so here you have a kid who made some songs who suddenly their songs around the NBA website, right? That that's real economic value to people. And so you know, </s><s>[INST] so you and I differ on the optimism of being able to sort of uh change the direction of the titanic. Right? So yeah, [/INST] I'm older than you. So, titanic's crash </s><s>[INST] got it. But uh just to elaborate because I totally agree with you and I just want to know how difficult you think this problem is of. So for example, I um I want to read some news and I would, there's a lot of times in the day where something makes me their smile or think in a way where I like consciously think this really gave me value. Like I sometimes listen to uh the daily podcast in the new york times way better than the new york times themselves, by the way for people listening, that's like real journalism is happening for some reason, on the podcast base. It doesn't make sense to me, but often I listen to it 20 minutes and I would be willing to pay for that like $5.10 dollars for that experience. And how difficult that's kind of what you're getting at is that little transaction. How difficult it is to create a frictional system like Uber has, for example, for other things. What's your intuition there? [/INST] So first of all, I I pay a little bit of money to, you know, to say there's something called courts that does financial things. I like medium as a site. I don't pay there. But um, I would, </s><s>[INST] you had a great post on medium. I would have loved to pay you a dollar, [/INST] but I wouldn't want, I wouldn't have wanted to per se because um there should be also sites where that's not actually the goal. The goal is to actually have a broadcast channel that I'm monetizing some other way. If I chose to. I mean, I could now, people know about it. I could, I'm not doing it, but that's fine with me. They're also the musicians who are making all this music. I don't think the right model is that you pay a little subscription fee to them. All right, Because because people can copy the bits too easily and it's just not that somewhere the value is the value. Is that a connection was made between human beings then you can follow up on that. All right. And create yet more value. So no, I think uh there's a lot of open questions here. Hot open questions. But also yeah, I do want good recommendation systems that recommend cool stuff to me, but it's pretty hard. Right? I don't like them to recommend stuff just based on my browsing history. I don't like that based on stuff they know about me calling quote what's unknown about me is the most interesting. </s><s>[INST] So that this is the this is a really interesting question. We may disagree. Maybe not. I think that I love recommending systems and I want to give them everything about me in a way that I trust, [/INST] but but you don't because so for example, this morning I clicked on, you know, it's pretty sleepy this morning. Um I clicked on a story about the Queen of England, </s><s>[INST] right? [/INST] I do not give a damn about the Queen of England. I really do not. But it was Clickbait, it kind of looked funny and I had to say, what the heck are you talking about that? I don't want to have my life, you know, heading that direction. Now that's in my browsing history. The system and any reasonable system will think history. Right? But but you're saying all the trace all the digital exhaust or whatever that's been kind of the models. If you collect all this stuff, you're gonna figure all of us out. Well, if you're trying to get like kind of one person like trump or so, maybe you could figure him out, but if you're trying to figure out, you know, 500 million people, you know. No way. No way. Do you think so? No, I do. I think so. I think we are, humans are just amazingly rich and complicated. Every one of us has our little quirks. Everyone else has our little things that could intrigue us that we don't even know, it will intrigue us and there's no sign of it in our past, but by God there it comes and you know, you fall in love with it and I don't want a company trying to figure that out for me and anticipate that I want them to provide a forum, a marketplace that I kind of go and by hook or by crook, this happens, you know, I'm walking down the street and I hear some Chilean music being played and I never knew I like chili music wow, so there is that side and I want them to provide a limited, but you know, interesting place to go, right and so don't try to use your ai to kind of, you know, figure me out and then put me in a world where you figured me out, you know, no, create huge spaces for human beings where our creativity and our style will be enriched and come forward and it will be a lot of more transparency. I won't have people randomly anonymously putting comments up and especially based on stuff they know about me facts that you know, we are so broken right now, if you're especially if you're celebrity, but you know, just about anybody that anonymous people are hurting lots and lots of people right now and that's part of this thing that Silicon Valley is thinking that, you know, just collect all this information and use it in a great way. So, you know, I'm I'm not I'm not a pessimist, I'm very much an optimist by nature, but I think that's just been the wrong path for the whole technology to take be more limited, create let humans rise up. Don't don't try to replace them. That's the ai mantra. Don't try to anticipate them. Don't try to predict them because you're not good at, you're not going to do the things, you're gonna make things worse. </s><s>[INST] Okay, so right now, just give us a chance right now the recommend er systems are the creepy people in the shadow watching your every move, so they're looking at traces of you, they're not directly interacting with you, sort of your close friends and family the way they know used by having conversation by actually having interactions back and forth. Do you think there's a place for recommended systems sort of two step because you just emphasize the value of human to human connection but let's give a chance ai human connection. Is there a role for an air system to have conversations with you in terms of to try to figure out what kind of music you like? Not by just watching what you're listening, but actually having a conversation, natural language or otherwise. [/INST] Yeah, no, I'm I'm so I'm not against this, I just want to push back against that. Maybe you're saying you have to sort of facebook so there I think is misplaced but um I think that distributing facebook, no, so good for you, go for it. That's the hard spot to be. Yeah, good human interaction. Like on our daily the context around me in my own home is something that I don't want some big company to know about it. But I would be more than happy to technology help me with it, </s><s>[INST] which kind of technology, [/INST] you know, just </s><s>[INST] Alexa. [/INST] Well, a good Alexis done right. I think Alex is a research platform right now more than anything else. But Alexa done right, You know, could do things like I I leave the water running in my garden and I say, hey lex, so the waters are in my garden and even have Alexa figure out what that means when my wife comes home that she should be told about that. That's a little bit of a reasoning, I'd call that A I and by any kind of stretches a little bit of reasoning and it actually kind of make my life a little easier and better and you know, I don't I wouldn't call this a wow moment, but I kind of think that overall rises human happiness up to have that kind of thing. Um </s><s>[INST] but not when you're lonely, Alexa knowing loneliness. [/INST] No, no that I don't want to be feel intrusive and I and I don't want just the designer of the system to kind of work all this out. I really want to have a lot of control and I want transparency and control and if the company can stand up and give me that in the context of technology um I think they're good first will be way more successful than our current generation and like I said, I was measuring Microsoft and I really think they're pivoting to kind of be the trusted old uncle, but you know, I think that they get that this is a way to go that if you let people find technology empowers them to have more control and have and have control, not just over privacy but over this rich set of interactions um that that people go like that a lot more and that's that's the right business model going forward, </s><s>[INST] what is control over privacy look like, do you think you should be able to just view all the data that [/INST] No, it's much more than that. I mean, first of all, it should be an individual decision. Some people don't want privacy. They want their whole life out there. Other people's wanted um Privacy is not a 01. It's not a legal thing. It's not just about which data is available, which is not. Um I like to recall the people that, you know, a couple 100 years ago. Everyone there was not really big cities. Everyone lived in the countryside and villages. Um and in villages, everybody knew everything about you very you don't have any privacy? Is that bad? Are we better off now? Well, you know, arguably, no, because what did you get for that loss of certain kinds of privacy? Um Well, uh people help each other. If they because they know everything about you, they know something bad is happening. They will help you with that. Right? And now you live in a big city, no one knows about that. You get no help. Um So it kind of depends the answer I want. Certain people who I trust and there should be relationships. I should kind of manage all those, who knows what about me? I should have some agency there. It shouldn't I shouldn't be adrift in a sea of technology where I know I said I don't wanna go reading things and checking boxes, so I don't know how to do that. And I'm not a privacy researcher per se, I just I recognize the vast complexity of this. It's not just technology, it's not just legal scholars, media technologists. Uh there's got to be kind of the whole layers around it. And so I when I lose to this emerging engineering field, this is a big part of it. Um what when electrical engineering come came, I'm not waiting around at the time, but you just didn't plug electricity, you know, into walls and all kind of work. You don't have, like, you know, underwriters laboratory that reassures you that that plug is not going to burn up your house and that that machine will do this and that and everything will be whole people who can install things, there'll be people who can watch the installers, there'll be a whole layers, you know, an onion of these kind of things. And for things as deepen, lee interesting as privacy, which is as least essentially electricity. Um, that that's gonna take decades to kind of work out, but it's gonna require a lot of new structures that we don't have right now. So it's kind of hard to talk about it. </s><s>[INST] And you're saying there's a lot of money to be made if you get it right. So [/INST] absolutely a lot of money to be made in all these things that provide human services and people recognize them as useful parts of their lives. So, yeah. Um, so yeah, the dialogue sometimes goes from the exuberant technologists to the no technology is good, kind of, and that's, you know, in our public discourse, you know, and in newspapers, you see too much of this kind of thing and, and the sober discussions in the middle, which are the challenge he wants to have or where we need to be having our conversations. And you know, this is not actually not many forum forum for those. Um, you know, there's, that's, that's kind of what I would look for. Maybe I could go and I could read a comment section of something and it would actually be this kind of dialogue going back and forth. You don't see much of this, right? Which </s><s>[INST] is why actually there's a resurgence of podcasts out of all because goods are really hungry for conversation, but there's technology is not helping much. So, comments sections of anything including [/INST] Youtube </s><s>[INST] is not helping, hurting, I'm not helping. And you think technically speaking it's possible to help. [/INST] I don't know the answers, but it's a, it's a, it's a less anonymity, a little more locality, um, you know, worlds that you kind of enter in and you trust the people there in those worlds. So that when you start having a discussion, you know, not only is that people not gonna hurt you, but it's not gonna be a total waste of your time because there's a lot of waste enough time that, you know, a lot of us, I I pulled out of facebook early because it was clearly going to waste a lot of my time, even there was some value. Um and so yeah, worlds that are somehow you enter in, you know what you're getting and it's kind of appeals to you might, new things might happen, but you kinda have some some trust in that world. </s><s>[INST] And there's some deep, interesting, complex psychological aspects around anonymity, how that changes human [/INST] behavior that indeed quite dark, quite dark. Yeah, I think a lot of us are especially those of us who really loved the advent of technology. I love social networks when it came out. I was just I didn't see any negatives there at all. But then I started seeing comment sections. I think it was maybe you don't want to CNN or something and I started calling, wow, this, this darkness I just did not know about. And um and our technology is now amplifying it </s><s>[INST] so sorry for the big philosophical question, but on that topic, do you think human beings, because you've also out of all things had a foot in psychology too. Uh the do you think human beings are fundamentally good? Like all of us have good intent that could be mined or is it depending on context and environment? Everybody could be evil. [/INST] So my answer is fundamentally good. Um, but fundamental limited. All of us have very, you know, blinkers on we don't see the other person's pain that easily. We don't see the other person's point of view that easily. We're very much in our own head, in our own world. Um, and on my good days, I think the technology could open us up to you no more perspectives and more less blinkered and more understanding. You know, a lot of wars in human history happened because of just ignorance. They didn't, they thought the other person was doing this well, that person wasn't doing this and we have a huge amounts of that. Um, but in my lifetime I've not seen technology really help in that way yet. And I do, I do, I do believe in that. But you know, no, I think fundamentally humans are good. People suffer. People have grieves and sins. Could you have grudges and those things cause them to do things they probably wouldn't want, they regret it often. Um, so no, I, I think it's, you know, part of the progress of technology is to indeed allow it to be a little easier to be the real good person you actually are. </s><s>[INST] But do you think individual human life or society could be modeled as an optimization [/INST] problem? Um, not the way I think typically, I mean that's your time, one of the most complex phenomena in the whole, you know, in all with </s><s>[INST] individual human life for society as a whole. [/INST] Both. Both. I mean individual human life is, is amazingly complex. And so, uh, you know, optimization is kind of just one branch of mathematics that talks about certain kind of things and it just feels way too limited for the complexity of such things. </s><s>[INST] What properties of optimization problems do you think so? Do you think most interesting problems that could be solved through optimization? Uh What kind of properties does that surface have? Non convexity, convexity, linearity, all those kinds of things saddle points [/INST] well, so optimization, just one piece of mathematics, you know, there's like just even in our era, were aware that's a sampling. Um it's coming up examples of something um come in with a distribution </s><s>[INST] ization. What's sampling? [/INST] Well, you can if you're kind of a certain kind of vision, you can try to blend them and make them seem to be sort of the same thing. But optimizations, roughly speaking, trying to uh find a point that a single point that is the optimum of a criterion function of some kind. Um And sampling is trying to from that same surface, treat that as a distribution or density and find points that have high density. So, um, I want the entire distribution and a sampling paradigm and I want the, you know, the single point. That's the best point in the in the sample, in the optimization paradigm. Now, if you were optimizing in the space of probability measures the output of, that could be a whole probability distribution. So you can start to make these things the same. But in mathematics if you go too high up that kind of abstraction and you start to lose the uh you know, the ability to do the interesting theorems. So you kind of don't try that, you don't try to overly over abstract. </s><s>[INST] So as a small tangent, what kind of world do you do you find more appealing one that is deterministic or [/INST] stochastic? Uh Well, that's easy. I mean, I'm a statistician, you know, the world is highly stochastic. Wait, I don't know what's gonna happen in the next five minutes. Right. So what you're gonna ask what we're gonna do, the uncertainty due to the massive uncertainty, you know, massive uncertainty. And so the best I can do is have come rough sense or probably distribution on things. And somehow use that in my reasoning about what to do now. </s><s>[INST] So how does the distributed at scale when you have multi agent systems uh look like So optimization can optimize sort of it makes a lot more sense, sort of at least a mile from robotics perspective for a single robot, for a single agent trying to optimize some objective function. Uh When you start to enter the real world, this game theoretic concept starts popping up uh that how do you see optimization in this? Because you've talked about markets and the scale, what does that look like? Do you see this optimization? Do you see it as sampling? Do you see how [/INST] is your mom, he's all blend together. Um and a system designer of thinking about how to build an incentivized system will have a blend of all these things. So, you know, a particle and a potential well, is optimizing a functional called Grandjean, right? The particle doesn't know that there's no algorithm running that does that. It just happens. So it's a description mathematically of something that helps us understand as analysts what's happening. Right? And so the same will happen when we talk about, you know, mixtures of humans and computers and markets and so and so forth. There'll be certain principles that allow us to understand what's happening whether or not the actual algorithms are being used by any sense. It's not clear. Um Now, at some point, I may have set up a multi agent or market kind of system and I'm now thinking about an individual agent in that system and they're asked to do some task and they're incentivizing somewhere, they get certain signals and they have some utility, whether what they will do at that point is they just won't know the answer. They may have to optimize to find an answer. Okay, so an artist could be embedded inside of an overall market. Uh you know, and game theory is, is very, very broad. Um It is often studied very narrowly for certain kinds of problems. Um but it's roughly speaking, that is just the, I don't know what you're gonna do. So I kind of anticipate that a little bit and you anticipate what I'm going anticipating and we kind of go back and forth in our own minds. We run kind of thought experiments. </s><s>[INST] You've talked about this interesting point in terms of game theory. You know, most optimization problems really hate saddle points. Maybe you can discover saddle points are, but I've heard you kind of mentioned that there's uh there's a branch of optimization that you could try to explicitly look for saddle points as a good thing. [/INST] Oh not optimization, that's just game theory. That that's so uh there's all kinds of different equilibrium game theory and some of them are highly explanatory behavior. They're not attempting to be algorithmic. They're just trying to say if you happen to be at this equilibrium, you would see certain kind of behavior and we see that in real life, that's what an economist wants to do. Especially behavioral economist um uh in continuous uh differential game theory, you're in continuous spaces. A some of the simplest equilibrium. Our saddle points, a nash equilibrium as a saddle point. It's a special kind of selling point. So classically in game theory, you were trying to find nash equilibrium and algorithmic game theory were trying to find algorithms that would find them. Uh So you're trying to find saddle points. I mean that's that's literally what you're trying to do. Um But you know, any economist knows that nash equilibrium to have their limitations. They are definitely not that explanatory in many situations, you're not what you really want. Um, there's other kind of equilibrium to, and there's names associated with these because they came from history with certain people working on that, but there will be new ones emerging. So, you know, one example is a stock Hilberg equilibrium. So, you know, nash, you and I are both playing this game against each other or for each other, Maybe it's cooperative and we're both going to think it through and then we're gonna decide we're going to, you know, do our thing simultaneously, you know, in a stock Oberg No, I'm gonna be the first mover. I'm going to make a move, you're going to look at my move and then you're gonna make yours now, since I know you're going to look at my move, I anticipate what you're gonna do and so I don't do something stupid, but, and, but then I know that you are also anticipating me. So we're kind of going back and silver mine, but there is then a first mover thing. And so there's a, there's a different equilibrium, all right. And uh, so just mathematically, yeah, these things have certain topology of, certain shapes, They're like salad. What's an algorithmic lee or dynamically, how do you move towards them? How do you move away from things? Um, you know, so some of these questions have answers, They've been studied, others do not, especially if it becomes stochastic, especially if there's large numbers of decentralized things, there's just, you know, young people getting in this field who kind of think it's all done because we have, you know, tensorflow. Well, no, these are all open problems and they're really important and interesting and strategic settings. How do I collect data? I suppose. I don't know what you're going to do because I don't know you very well. All right, well, I gotta collect data about you. So maybe I want to push you in a part of the space where I don't know much about you so I can get data because and then later I'll realize that you'll never you'll never go there because of the way the game is set up. But, you know, that's part of the overall, you know, data analysis context, </s><s>[INST] even the game of poker is fascinating. Space, whatever, There's any uncertainty, a lack of information, it's a super exciting space. Yeah, just uh, linger and optimization for a second. So if we look at deep learning, it's essentially minimization of a complicated loss function. So, is there something insightful or hopeful that you see in the kinds of function surface that loss functions that deep learning and in the real world is trying to optimize over. Is there something interesting? It was just the usual kind of problems of optimization, [/INST] I think from an optimization point of view, that surface versus it's pretty smooth. Um and secondly, if there's over if it's over parameter risers kind of lots of paths down to reasonable optima? Uh and so kind of getting downhill to the to an optimum is viewed as not as hard as you might have expected in high dimensions. The fact that some optimal tend to be really good ones and others not so good and you tend to not sometimes you find the good ones is sort of still needs explanation, But the particular surface is coming from a particular generation of neural nets. I kind of suspect those will those will change in 10 years. It will not be exactly those surfaces, there'll be some others that are an optimization three will help contribute to why other surfaces or why other algorithms, layers of arithmetic operations with a little bit of non linearity. That's not that didn't come from neuroscience per se. I mean maybe in the minds of some of the people working on it, they were thinking brains, but they were arithmetic circuits in all kinds of fields, you know, computer science, control theory and so on. And that layers of these could transform things in certain ways and that if it's smooth, maybe you could, you know, find parameter values. Um you know, it's a big, is a, is a sort of big discovery that it's it's working, it's able to work at this scale, but um I don't think that we're stuck with that and we're certainly not stuck with that because we're understanding the brain. </s><s>[INST] So in terms of on the algorithm size of gradient descent, do you think we're stuck with gradient descent variants of it? What variants do you find interesting or do you think there will be something else invented that is able to walk all over these optimization spaces in more interesting ways. [/INST] So there's a co design of the surface and they are the architecture and the algorithm. Um So if you just ask if we stay with the kind of architecture that we have now and not just neural nets, but, you know, phase retrieval architectures are Mitchell's completion architecture and so on. Um You know, I think we've kind of come to a place where yeah, a stochastic gradient algorithms are dominant and um there are versions uh you know, that are a little better than others. They, you know, have more guarantees, they're more robust and so on and there's ongoing research to kind of figure out which is the best time for which situation. Um but I think that that will start to co evolve. That that'll put pressure on the actual architecture and so we shouldn't do it in this particular way. We should do it in a different way because this other album is now available if you do it in a different way. Um so uh that that that I can't really anticipate that co evolution process, but, you know, gradients are amazing mathematical objects. Um They have a lot of people who uh sort of study them more deeply mathematically uh kind of shocked about what they are and what they can do. Um I mean you think about this way, if I suppose that I tell you if you move along the X axis, you get uh you know, you go uphill in some objective by you know, three units, whereas if you move along the y axis, you go uphill by seven units right now, I'm gonna only allow you to move a certain, you know, unit distance. All right. What are you gonna do? Well, the most people will say that I'm gonna go along the y axis, I'm getting the biggest bang for my buck, you know, and my buck is only one unit. So I'm going to put all of it in the y axis, right? And uh why should I even take any of my strength, my step size and put any of it in the X axis? Because I'm getting less bang for my buck. That seems like a completely, you know, clear argument and it's wrong because the gradient direction is not to go along the y axis, it's to take a little bit of the X axis. Uh and that to understand that you have to you have to know some math and so even a trivial, so so called operator operating is not trivial. And so, you know, exploiting its properties is still very important. Um Now we know that just creating dissent has got all kinds of problems, it gets stuck in many ways and it didn't have, you know, good dimension dependence, and so on. So, um, my own line of work recently has been about what kinds of stochastic city, how can we get dimension dependence? Can do the theory of that? Um and we've come a pretty favorable results with certain kinds of stochastic city. We have sufficient conditions. Generally, we we know if you if you do this, we will give you a good guarantee. Uh we don't have necessary conditions that it must be done a certain way in general. </s><s>[INST] So stuck plasticity. How much random is to inject into the and to the walking along the gradient. [/INST] What kind of randomness? </s><s>[INST] Why is random is good in this process? Why is the elasticity good? [/INST] Yeah. So, um, I'll give you simple answers, but in some sense, again, it's kind of amazing plasticity. Just uh, you know, particular features of a surface that could have hurt you if you were doing one thing, you know, deterministic lee won't hurt you because uh you know, by chance, you know, there's very little chance that you would get hurt. And um, you know, so, here stochastic city um you know, it's just kind of saves you from some of the particular features of surfaces that, um, you know, and in fact, if you think about uh, you know, surfaces that are discontinuous in the first derivative, like, you know, absolute value function, um you will go down and hit that point where there's non differential bility, right? And if you're running demasiado at that point, you can really do something bad, right? Where so Cassidy just means it's pretty unlikely that's gonna happen. You're gonna you're gonna hit that point. Um so, you know, it's again, not trivial analyzed, but um, especially in higher dimensions, also stood plasticity. Our intuition isn't very good about it, but it has properties that kind of are very appealing in high dimensions for kind of law of large number of reasons. Um, so it's, it's all part of the mathematics behind it. That's what's fun to work in the field, is that you get to try to understand this mathematics and um, but long story short, you know, partly empirically it was discovered stochastic gradient is very effective in theory kind of followed, I'd say um that, but I don't see that we're getting clearly out of that uh </s><s>[INST] what's the most beautiful, mysterious, a profound idea to you in optimization? [/INST] I don't know the most, but let me just say that, you know, Nesterov is work on Nesterov acceleration to me is pretty, pretty surprising and pretty deep. Um can you elaborate? Well, they're strong acceleration is just that uh I suppose that we are going to use gradients to move around in a space for the reasons, I've alluded to there there, there nice directions to move and suppose that I tell you that you're only allowed to use gradients you're not going to be allowed to use this local person that can only sense kind of a change in the surface. Um But I'm gonna give you a kind of a computer that's able to store all your previous gradients and so you start to learn some something about the surface. Um And I'm gonna restrict you to maybe move in the direction of like linear span of all the gradients. So you can kind of just moving some arbitrary direction. Right? So now we have a well defined mathematical complexity model. There's a certain classes of algorithms that can do that and there's a can't and we get asked for certain kinds of surfaces. How fast can you get down to the optima? So there's an answers to these. So for uh you know a smooth convex function there's an answer which is one over the number of steps squared, you will be within a ball of that size uh After after k steps um gradient descent in particular has a slower rate? It's one of her. Kay okay. Um So you could ask is gradient ascent actually even though we know it's a good algorithm is it the best algorithm? And the sense of the answer is no well well not clear yet because what one of our case score is a lower bound that's that's probably the best you can do what gradient is one. Okay but is there something better. And so I think it's a surprise to most, the Nesterov discovered a new algorithm That has got two pieces to it. It uses two gradients and uh puts those together in a certain kind of obscure way and uh the thing doesn't even move downhill all the time and sometimes goes back uphill um and if you're a physicist that kind of makes some sense, you're building up some momentum and that is kind of the right intuition, but that that intuition is not enough to understand kind of how to do it and why it works. Um but it does, it achieves one of our case squared and it has a mathematical structure and it's still kind of to this day, a lot of us are writing papers and trying to explore that and understand it. Um So there's lots of cool ideas and optimization but just kind of using gradients I think is number one that goes back, you know, 150 years. Um and then that stuff I think has made a major contribution with this idea. </s><s>[INST] So like you said, gradients themselves are, in some sense, mysterious. Yeah, they're not, they're not as trivial [/INST] as not as trivial, mathematical coordinate descent is more of a trivial when you just pick one of the coordinates, that's how that's how our human minds are, Human minds think and gradients are not that easy for a human mind to grapple with </s><s>[INST] an absurd question, but what is statistics? [/INST] So here is a little bit, it's somewhere between math and science and technology, It's somewhere in that context hole. So it's uh it's a set of principles that allow you to make inferences that have got some reason to be believed and also principles of how you make decisions where you can have some reason to believe you're not gonna make errors. Um So all of that requires some assumptions about what do you mean by an error? What do you mean by, you know the probabilities and um but you know, start after you start making some assumptions. You're led to uh conclusions that yes, I can guarantee that you know, you know if you do this in this way your probability making air will be small. Um your probability of continuing to not make errors over time will be small and uh probability found something that's real will be </s><s>[INST] small, will be high. The decision making is a big [/INST] part in making a big part. Yeah. So the original so statistics, you know short history was that you know, it's kind of goes back, It's as a formal discipline, you know, 250 years or so. Um it was called inverse probability because around that era uh probability was developed sort of especially to explain gambling um situations and um interesting so you would say well given the state of nature is this there's a certain roulette or that has a certain mechanism and it uh what kind of outcomes do I expect to see? Uh And um especially I do things long, long amounts of time what outcomes by seeing the faces start to pay attention to this. Um And then people said well given let's turn the problem around, what if I saw certain outcomes could infer what the underlying mechanism was, that's an inverse problem. And in fact for quite a while statistics was called inverse probability. That was the name of the field. And I believe that it was La Plaza who was working in napoleon's government who was trying who needed to do a census of France, learn about the people there. So he went and got and gathered data and he analyzed that data to determine policy. And I said well it's called this field that does this kind of thing statistics because um the word state is in there in french. That's a to but you know it's the study of data for the state. Uh Anyway that caught on and um it's been called statistics ever since. But But by the time it got formalized it was sort of in the 30s. Um and uh around that time there was game theory and decision theory developed nearby um people that air didn't think of themselves as either computer science or statistics or controlled or econ they were all they were all the above. And so you know von norman is developing game theory but also thinking about his decision theory Wall is an economy attrition, developing decision theory and then turning that into statistics. And so it's all about, here's uh here's not just data and you analyze it, here's a loss function. Here's what you care about here is the question of trying to ask I hear is a probability model and here is the risk you will face if you make certain decisions. Um and to this day and most advanced statistical curricula used, teach decision theory is the starting point and then it branches out into the two branches of basing a frequentist but that's it's all about decisions </s><s>[INST] in statistics. What is the most beautiful, mysterious, maybe surprising idea that you've come across. [/INST] Uh Yeah, good question. Um I mean there's a bunch of surprising ones, there's something that's way too technical for this thing, but something called James Stein estimation, which is kind of surprising and really takes time to wrap your head around. Can you try to maybe, I think I don't want even want to try um let me just say a colleague at steve Stephen Stigler University Chicago wrote a really beautiful paper on James stein estimation which helps to its views of paradox, it kind of defeats the mind's attempts to understand it, but you can and steve has a nice perspective on that. Um they're so one of the troubles with statistics is that it's like in physics that are in quantum physics you have multiple interpretations. There's a wave and particle duality in physics and you get used to that over time, but it's still kind of haunts you that you don't really, you know, quite understand the relationship the electrons away when electrons are particles. Well, um well the same thing happens here. There's Bazian ways of thinking and frequentist and they are different. They they sometimes become sort of the same in practice, but they are physically different. And then in some practice they are not the same at all. They give you a rather different answers. Um and so it is very much like wave particle duality and that is something you have to kind of get used to in the field. </s><s>[INST] Can you define Beijing a frequentist? [/INST] Yeah. Decision theory. You can make I have a like I have a video that people could see. It's called are you a basin or a frequentist. And kind of help try to to uh to make it really clear. It comes from decision theory. So, you know, decision theory. Uh you're talking about loss functions which are a function of data X and parameter data there a function of two arguments. Okay, neither one of those arguments is known. You don't know the data a priori it's random and the parameters unknown. All right. So you have this function of two things. You don't know when you're trying to say, I want that function to be small, I want small loss. Right, Well um what are you gonna do? So you sort of say well I'm going to average over these quantities or maximize over them or something so that you know I turned that uncertainty into something certain. Um So you could look at the first argument an average over it or you can look at the second annual average over it. That's basin frequentist. So the frequent just says I'm going to look at the X. The data and I'm gonna take that as random and I'm going to average over the distribution. So I take the expectation of loss under X. Fate is held fixed. All right. That's called the risk. And so is looking at other all the data that you could get. All right. And seeing how well will a certain procedure do under all those data sets that's called a frequent is guarantee. All right. So I think it is very appropriate when like you're building a piece of software and you're shipping it out there and people using all kinds of datasets you wanna have a stamp of guarantee on it that has people running on many many data sets that you never even thought about that 95% of the time. It will do the right thing. Um perfectly reasonable. The Beijing perspective says, well no, I'm going to look at the other argument of the loss function. The fate apart. Okay that's unknown and I'm uncertain about it. So I could have my own personal probability for what it is. You know, how many tall people are there out there? I'm trying to for the average height of the population. Well, I have an idea roughly what the height is. So I'm gonna average over the the theater. So now that loss function has only now, again, one argument is gone. Now it's a function of X. And that's what position does is they say, well, let's just focus on the particular X. We got the data set. We got we condition on that conditional on the acts. I say something about my loss. That's a basin approach to things. And the position will argue that it's not relevant to look at all the other data sets. You could have gotten an average over them. The frequentist approach, it's really only the data that you got. All right. And I do agree with that. Especially in situations where you're working with a scientist, you can learn a lot about the domain and you're really only focus on certain kinds of data and you gather your data and you make inferences. Um, I don't agree with it though, that, you know, in the sense that there are needs for frequentist guarantees your writing software people are using out there. You want to say something. So these two things have got to fight each other a little bit, but they have to blend So long story short, there's a set of ideas that are right in the middle there called empirical bayes and empirical base starts with the Bosnian framework. Uh, it's it's kind of arguably philosophically more, you know, reasonable and kosher write down a bunch of the math that kind of flows from that and then realize there's a bunch of things you don't know because it's the real world and you don't know everything. So you're uncertain about certain quantities at that point. Ask is there a reasonable way to plug in an estimate for those things? Okay. And in some cases there is quite a reasonable thing to do um, to plug in. There is a natural thing you can observe in the world that you can plug in and then do a little bit more mathematics and assure yourself it's really good. </s><s>[INST] So my math are based on human expertise, what's what [/INST] are good, they're both going in the basin framework allows you to put a lot of human expertise in. Um, but the math kind of guides you along that path and then kind of reassures at the end, you can put that stamp of approval under certain assumptions. This thing will work. So you asked question was my favorite. You know, it was the most surprising nice idea. So one that is more accessible is something called false discovery rate, which is um, you know, you're making not just one hypothesis test or making one decision, you're making a whole bag of them and in that bag of decisions. You look at the ones where you made a discovery, you announced that something interesting that happened. All right. That's gonna be some subset of your big bag in the ones you made a discovery. Which subset of those are bad. There are false false discoveries. You like the fraction of your false discoveries among your discoveries to be small. That's a different criterion. That accuracy or precision or recall or sensitivity and specificity. It's it's a different quantity. Those latter ones are almost all of them um um have more of a frequentist flavor. They say given the truth is that the null hypothesis is true. Here's what accuracy that would get or given that the alternative is true. Here's what I would get. It's kind of going forward from the state of nature to the data. The basin goes the other direction from the data back to the state of nature. And that's actually what false discovery rate is. It says given you made a discovery. Okay that's condition on your data. What's the probability of the hypothesis? It's going the other direction. Uh And so um the classical frequency. Look at that. So I can't know that there's some prior is needed in that and the empirical base and goes ahead and plows forward and starts writing down to these formulas and realizes at some point some of those things can actually be estimated in a reasonable </s><s>[INST] way. [/INST] And so it's kind of a beautiful set of ideas. So I this kind of line of argument has come out? It's not certainly mine, but it sort of came out from Robin's around 1960 brad Ephron is has written beautifully about this in various papers and books and and the F. D. R. Is, you know, Benjamin e uh in Israel um john's story, did this basin interpretation and so on. So I just absorbed these things over the years and find it a very healthy way to think about statistics. </s><s>[INST] Let me ask you about intelligence to jump slightly back out into philosophy. Perhaps you said that maybe you can elaborate. But you said that defining just even the question of what his intelligence is. Uh where is this? Is a very difficult question. Is it a useful question? Do you think will one day understand the fundamentals of human intelligence and what it means? You know, have good benchmarks for general intelligence that we put before our machines. [/INST] So I don't work on these topics so much that you're really asking a question for a psychologist really. And I studied some but I don't consider myself um leased an expert at this point. Um you know, a psychologist aims to understand human intelligence, right? And I think maybe psychology I know are fairly humble about this. They might try to understand how a baby understands, you know, whether something is a solid or liquid or whether something's hidden or not. And maybe the how uh, you know, child starts to learn the meaning of certain words what the verb, what's a noun and also, you know, slowly but surely trying to figure out things. Um But humans ability to take a really complicated environment. Reason about it, abstract about it. Find the right abstractions, communicate about it, interact and so on is just, you know, really staggeringly rich and complicated. Um And so, you know, I think in all humidity, we don't think we're kind of a me for that in the near future. And certainly psychologists doing experiments with babies in the lab or with people talking is it has a much more limited aspiration and you know, economy diversity. We look at our reasoning patterns and they're, they're not deeply understanding, although how we do our reasoning, but they're sort of saying, hey, listen, here's some oddities about the reasoning and some things you used to think about it. But also I as I emphasized and things, some things I've been writing about ai the revolution hasn't happened yet. Um, I've been emphasizing that, you know, if you step back and look at uh intelligent systems of any kind, whatever you mean by intelligence, it's not just the humans or the animals or you know, the plants or whatever, You know, so a market that brings goods into a city, you know, food to restaurants or something every day, uh, is a system. It's a decentralized set of decisions looking at it from far enough away. It's just like a collection of neurons, Everyone, every neuron is making its own little decisions presumably in some way. And if you step back enough, every little part of an economic system is making its all of his decisions and just like with the brain, who knows what any of the Children doesn't know what the overall goal is, right, But something happens at some aggregate level, Same thing with the economy. People eat in a city and it's robust, It works at all scales small villages to big cities, it's been working for thousands of years. It works rain or shine, so it's adaptive. Um so all the kind of, you know, those are adjectives. One tends to apply to intelligence systems robust adaptive. You know, you don't need to keep adjusting it itself, self healing, whatever, plus not perfect, you know, intelligences are never perfect and markets are not perfect. Um but I do not believe in this era that you cannot, that you can say, well our computers are, humans are smart, but you know, no markets are not more, markets are so they are intelligent. Uh now we humans didn't evolve to be markets, we've been participate in them, right? But we are not ourselves a market per se. Um </s><s>[INST] the neurons could be viewed as [/INST] the market, There's economic, you know, neuroscience kind of perspective. That's interesting to pursue. All that. The point though is that if you were to study humans and really be a world's best psychologist, study for thousands of years and come up with the theory of human intelligence, you might have never discovered principles of markets, you know, spy demand curves and you know, matching and auctions and all that. Uh those are real principles and they lead to a form of intelligence that's not maybe human intelligence. It's arguably another kind of intelligence. There, probably our third kinds of intelligence, or fourth that none of us are really thinking too much about right now. So if you're really and and all those are relevant to computer systems in the future, certainly the market one is relevant right now. Whereas understanding intelligence is not so clear that it's relevant right now. Probably not. Um So if you want general intelligence, what everyone means by that or you know, understanding intelligence and a deep sense and all that. It is definitely has to be not just human intelligence, it's gotta be this broader thing. And that's not a mystery. Markets are intelligence. So, you know, it's definitely just a philosophical stance to say we've got to move beyond intelligence, intelligence. That sounds ridiculous, </s><s>[INST] but it's not. And in that block walls to define different kinds of like intelligent infrastructure II, which I really like this. Some of the concepts you've just been uh describing, do you see ourselves? We see earth human civilization as a single organism? Do you think the intelligence of that organism? when you think from the perspective of markets and intelligence, infrastructure is increasing, Is it increasing linearly. Is that increasing exponentially? What do you think the future of that intelligence? [/INST] And I don't know, I don't tend to think I don't tend to answer questions like that because, you know that science fiction is </s><s>[INST] hoping to create jobs [/INST] guard. Well </s><s>[INST] again, because you said it's so far in the future, it's fun to ask. And you'll probably, you know, like you said, predicting the future as really nearly impossible. But say as an axiom one day we create a human level of super human level intelligence. Not the scale of markets, but the scale of an individual. What do you think is what do you think it would take to do that? Or maybe to ask another question is how would that system be different than the biological human beings that we see around us today? Is it possible to say anything interesting to that question? Or is it just a stupid question? [/INST] It's not a stupid question. But it's science fiction, science fiction. And so I'm totally happy to read science fiction and think about it from time. My own life. I loved there was this like brain in a vat kind of, you know, a little thing that people were talking about when I was a student. I remember, you know, imagine that, uh, um, you know, between your brain and your body? There's a, you know, a bunch of wires, right? And suppose that every one of them was replaced with a uh, literal wire. And then suppose that wire was turning actually little wireless, you know, there's a receiver and sender. The brain has got all the centers and receiver on all of its exiting. Uh, you know, axons and all the danger writes down the body. You have replaced with senders and receivers. Now you could move the body off somewhere and put the brain in a vat, Right? And then you can do things like start killing off those senators receivers one x one and after you killed off all of them were, is that person, you know, they thought they were out in the body walking around the world and they moved on. So those are science fiction things that are fun to think about. It's just intriguing about where is, what is thought, where is it all that? And uh, I think every 18 year old is to take philosophy classes and think about these things. And I think that everyone should think about what could happen in society that's kind of bad and all that. But I really don't think that's the right thing for most of us that are my age group to be doing. And thinking about I really think that we have so many more present, you know, uh verse challenges and dangers and real things to build and all that. Um, such that uh, you know, spending too much time on science fiction, least in public for it like this I think is not what we should be doing, </s><s>[INST] maybe over beers [/INST] in private. That's right. And I'm well, well, well I'm not gonna broadcast where I have beers because this is gonna go on facebook and a lot of people showing up there, but I'll uh </s><s>[INST] I love facebook, twitter amazon youtube. I have, I'm optimistic and hopeful, but maybe maybe I don't have grounds for such optimism and hope. Let me ask, you've mentored some of the brightest sort of some of the seminal figures in the field. Can you uh give advice to people who undergraduates today? What does it take to take, you know, advice on their journey if they're interested in machine learning and ai and in uh the ideas of markets from economics and psychology and all the kinds of things that you are exploring what what's what steps they take on that journey. [/INST] Well, first off the doors open and second it's a journey, I like your language there. Um uh It is not that you're so brilliant and you have great brilliant ideas and therefore that's that's just, you know, that's how you have success or that's how you enter into the field. Uh It's that you apprentice yourself, you you spend a lot of time, you work on hard things, you um try and pull back and you be as broad as you can you talk a lot of people. Um, and it's like entering any kind of a creative community, there's um, years that are needed and human connections are critical to it. So, you know, I think about, you know, being a musician or being an artist or something, you don't just, you know, immediately from day one, you know, you're a genius and therefore you do it. No, you um, you know, practice really, really hard on basics and you uh be humble about where you are and then, and you realize you'll never be an expert on everything, so you kind of pick and there's a lot of randomness and a lot of kind of um, luck, but luck just kind of picks out which branch of the tree go down, but you'll go down some branch. Um, So yeah, it's a, it's a community. So the graduate school is I I still think it's one of the wonderful phenomena that we have in our, in our world. It's it's very much about apprenticeship with an adviser. It's very much about a group of people you belong to. It's a four or five year process, so it's plenty of time to start from kind of nothing to come up to something, you know, more, more expertise and then start to have your own creativity start to flower even surprising to your own self. Um, and it's a very cooperative endeavor. It's, I think a lot of people think of, um, science is highly competitive and I think in some other fields it might be more so um here it's way more cooperative than you might imagine. Um and people always teaching each other something and people are always more than happy to be clear that. So I feel I'm an expert on certain kind of things, but I'm very much not expert on lots of other things and a lot of them are relevant and a lot of them are, I should know, but it should in some sense, you know, you you don't, so um I'm always willing to reveal my ignorance to people around me so they can teach me things and I think a lot of us feel that way about our field. So it's very cooperative. I might add it's also very international because it's so cooperative, we see no barriers and uh so that the nationalism that you see, especially in the current era and everything is just at odds with the way that most of us think about what we're doing here, where this is a human endeavor and we we cooperate and are very much trying to do it together for the benefit of everybody. </s><s>[INST] So last question where and how and why did you learn french and which language is more beautiful [/INST] english or french? Um great question. So um first of all, I think Italians actually more beautiful than french in english and I also speak that. So I'm I'm married to an italian and I have kids and we speak italian. Um anyway, all kidding aside, every language allows you to express things a bit differently. Um and it is one of the great fun things to do in life is to explore those things. So in fact when my kids are teens or college kids ask me what they study, I say, well do what your heart, where your heart is, certainly do a lot of math, Math is good for everybody, but do some poetry and do some history and some language to um you know, throughout your life you want to be a thinking person, you'll want to have done that. Um, for me, yeah, french, I learned when I was, I'd say a late teen um I was living in the middle of the country in Kansas and uh not much was going on in Kansas with all due respect to Kansas, but uh, and so my parents happen to have some french books on the shelf and just in my boredom I pulled them down and I found this is fun and I kind of learned the language by reading and um when I first heard it spoken and I had no idea what was being spoken, but I realized I had somehow knew it from some previous life and so I made the connection um, but then you know, I traveled and just, I, I love to go beyond my own barriers and uh my own comfort or whatever and I found myself in you know on trains in France next to say older people who had you know lived a whole life of their own and uh the ability to communicate with them was was you know special and uh ability to also see myself in other people's shoes and have empathy and and kind of work on that language as part of that. Um so um so after that kind of experience um and also embedding myself in french culture which is you know quite quite amazing you know languages are rich not because there's something inherently beautiful about it but it's all the creativity that went into it. So I learned a lot of songs, read poems, read books um and then I was here actually at M. I. T. Where we're doing the podcast today and uh young professor um uh you know not yet married and uh you know not a lot of friends in the area so I just didn't have just kind of a board person. I said I heard a lot of italian surround there happened to be a lot of Italians at M. I. T. Professor for some reason and so I was kind of vaguely understanding what they were talking about. I said well I should learn this language too. So I did and then later met my spouse and uh you know italian became a part of my life but but I go to china a lot these days, I go to in North Asia, I go to europe and um every time I go I kind of amazed by the richness of human experience and uh people don't have any idea if you haven't traveled kind of how amazingly rich and I love the diversity. It's not just a buzzword to me, it really means something, I love the, you know, the you know, embed myself with other people's experiences. And so yeah, learning language is a big part of that. I think I've said in some interview at some point that if I had you know, millions of dollars in an infinite time, whatever what would you really work on if you really wanted to do a I and for me that is natural language and and really done right, you know, deep understanding of language. Um that's to me an amazingly interesting scientific challenge and uh </s><s>[INST] one We're very far away, [/INST] one we're very far away, but good natural language people are kind of really invested then I think a lot of them see that's where the core of ai is that if you understand that you really help human communication, you understand something about the human mind, the semantics that come out of the human mind and I agree, I think that will be such a long time. So I didn't do that in my career just because I kind of I was behind in the early days, I didn't kind of know enough of that stuff was at M. I. T. I didn't learn much language. Uh it was too late at some point to kind of spend a whole career doing that. But I admire that field. And uh um and so in my little way by learning language, you know, kind of uh that part of my brain is um has been trained up. </s><s>[INST] Yang was right, you're truly are the Miles Davis and machine learning. I don't think there's a better place than it was. Mike was a huge honor talking to you today, Merci beaucoup. [/INST] All right, it's been my pleasure. Thank you. </s><s>[INST] Thanks for listening to this conversation with Michael I jordans and thank you to our presenting sponsor, cash app, download it used collects podcast, You'll get $10 and $10 will go to first an organization that inspires and educates young minds to become science and technology innovators of tomorrow. If you enjoy this podcast, subscribe on Youtube, give it five stars on Apple podcast, support on Patreon or simply connect with me on twitter. A lex Friedman and now let me leave you with some words of wisdom from Michael I jordans from his blog post titled artificial intelligence. The revolution hasn't happened yet, calling for broadening the scope of the ai field. We should embrace the fact that what we are witnessing is the creation of a new branch of engineering. The term engineering is often invoked in a narrow sense in academia and beyond, with overtones of cold effect lys machinery and negative connotations of loss of control by humans. But an engineering discipline can be what we wanted to be in the current era with a real opportunity to conceive of something historically new, a human centric engineering discipline, I'll resist giving this emerging discipline and name. But if the acronym AI continues to be used, let's be aware of the very real limitations of this placeholder. Let's broaden our scope, tone down the hype and recognize the serious challenges ahead. Thank you for listening and hope to see you [/INST] next time. </s> |
<s>[INST] toolbox. It's just a robustness to I mean [/INST] exactly all the problems of dealing with data and bias and data, all the problems of you know suffer too dot oh and one of the great things that Andres is arguing towards which I completely agree with them is that when you start implementing things with deep learning, you need to learn from software one dot Oh in terms of testing continuous integration, how you deploy, how do you validate all these things and building building systems around that? So you're not just saying like oh it seems like it's good ship it. Right. Well what happens when I regret something, what happens when I make a classification? That's wrong? And now I heard somebody right? I mean the same to you have to reason about </s><s>[INST] Yeah, but at the same time the bootloader that works for our forest humans is uh looks awfully a lot like a neural network right? It's messy and you can cut out different parts of the brain. There's a lot of this New York plasticity work that shows it's gonna just, it's uh, it's a really interesting question. How much of the world programming could be replaced by software 2.0 like with [/INST] Well, I mean it's probably true that you could replace all of it. </s><s>[INST] Right? So then [/INST] so anything that's a function you can. So it's not a question about if I think it's a economic question, it's a, what kind of talent can you get? What kind of trade offs in terms of maintenance? Right. Those kinds of questions. I think, what kind of data can you collect? I think one of the reasons that I'm most interested in, uh machine learning is a programming paradigm. Is that one of the things that we've seen across computing in general is that being laser focused on one paradigm often Put you in a box. It's not super great. And so you look at object very programming. Like it was all the rage in the early 80s and like everything, it has to be objects and people forgot about functional programming even though came first. And, and then people rediscover that hey, if you mix functional and object oriented and structure, like mix these things together, you can provide very interesting tools that are good at solving different problems. And so the question there is how do you get the best way to solve the problems? It's not about who's tribe should win, right? It's not about, you know, that that that shouldn't be the question. The question is how do you make it so that people can solve those problems the fastest and they have the right tools in the box to build good libraries and they can solve these problems. And when you look at that, that's like, you know, you look at reinforcement learning as one really interesting subbed amount of this reinforcement learning. Often you have to have the integration of a learned model combined with your Atari or whatever the other scenario it is that you're working in, you have to combine that that thing with the robot control for the arm. Right. And so now it's not just about that one uh paradigm. It's about integrating that with all the other systems that you have, including often legacy systems and things like this. Right. And so to me, I think that the interesting the interesting thing to say is like how do you get the best out of this domain? And how do you enable people to achieve things that they otherwise couldn't do without excluding all the good things we already know how to do. </s><s>[INST] Right. But okay, this is just a crazy question. But we talked a lot about about GPT three. But do you think it's possible that these language models That uh in essence in the language domain software 2.0, could replace some aspect of compilation for example or do program synthesis, replace some aspect of programming? [/INST] Yeah, absolutely. So I think that that learned models in general are extremely powerful and I think the people underestimate them, um </s><s>[INST] maybe you can suggest what I should do. So uh you know, have access to the GPT three. Ap I would I be able to generate swift code for example, do you think that could do something interesting and uh [/INST] GTT three is not probably not trained on the right corpus, so it probably has the ability to generate some swift. I bet it does. It's probably not going to generate a large enough body of swift to be useful, but but like taking the next step further. Like if you had the goal of training something like GPT three and you wanted to try and generate source code right? It could definitely do that. Now the question is how do you express the intent of what you want filled in? You can definitely like Right, right, scaffolding of code and say fill in the hole and sort of putting some four loops and put in some classes or whatever. And the power of these models is impressive. But there's an unsolved question at least unsolved to me, which is how do I express the intent of what to fill in? Right. And kind of what you'd really want to have. And I don't know that these models are up to the task is you want to be able to say um here's the scaffolding and here the assertions at the end and the assertions always pass. And so you want a generative model on the one hand. </s><s>[INST] Yes. [/INST] Right? But you also want some loop back some reinforcement learning system or something where you're actually saying like I need to heal, climb towards something that is more correct. And I don't know that we have that. </s> |
<s>[INST] You said, I think to Sean Carroll, by the way, everyone should go check out Sean Carroll's Mindscape podcast. It's incredible. And Sean Carroll is an incredible person. I think you said there, maybe in a paper, I have a quote. You said that a soft particle is a particle that has zero energy, just like you said now. And when the energy goes to zero because the energy is proportional to the wavelength, it's also spread over an infinitely large distance. If you like, it's spread over the whole universe. It somehow runs off to the boundary. What we learned from that is that if you add a zero energy particle to the vacuum, you get a new state. And so there are infinitely many, plural for vacuum, which can be thought of as being different from one another by the addition of soft photons or soft gravitons. Can you elaborate on this wild idea? If you like, it spreads over the whole universe. When the energy goes to zero because the energy is proportional to the wavelength, it also spreads over an infinitely large distance. If you like, it's spread over the whole universe. Can you explain [/INST] these soft gravitons and photons? Right. Yeah. So the soft gravitons and photons have been known about since the 60s, but exactly what we're supposed to do with them or how we're supposed to think about them, I think has been well understood only recently. And in quantum mechanics, the energy of a particle is proportional to Planck's constant times its wavelength. So when the energy goes to zero, the wavelength goes to infinity. Now, if something has zero energy and it's spread all over the universe, in what sense is it actually there? Yeah. That's been the confusing thing to make a precise statement about when something is and isn't there. Now, the simplest way of seeing... So people might have taken the point of view that if it has zero energy and it's spread all over the universe, it's not there. We can ignore it. But if you do this, you'll get into trouble. And one of the ways that you'll get into trouble is that even though it has zero energy, it doesn't have zero angular momentum. If it's a photon, it always has angular momentum one. If it's a graviton, it's angular momentum two. So you can't say that the state of the system with the zero energy photon should be identified with the one without the zero energy photon, that we can just ignore them, because then you will conclude that angular momentum is not conserved. And if angular momentum is not conserved, things won't be consistent. And of course, you can have a lot of these things. And typically, you do get a lot of them, and you can actually do a calculation that shows that every time you </s><s>[INST] scatter two particles, you create an infinite number of them. Infinite number of the soft photons and gravity. [/INST] Of the zero energy ones. </s><s>[INST] Yeah. And so these are somehow everywhere. They're everywhere. But they also contain information or they're able to store information. [/INST] They're everywhere. And they're able to store information. They're able to store an arbitrary large amount of information. So what we pointed out is… So what these things really do, one way of thinking of them is they rush off to the edges of the universe, spreading all over the space. It's like saying they rush off to the edge of the universe. And that includes, if the interior of the black hole is not considered part of the universe, that includes the edge of the black hole. So we need to set up our description of physics so that all the things that are conserved are still conserved in the way that we're describing them, and that will not be true if we ignore these things. We have to keep careful track of these things. And people had been sloppy about that, and we learned how to be very precise and careful about it. </s><s>[INST] And once you're being precise, you can actually answer this kind of very problematic thing that Hawking suggested that black holes destroy information. [/INST] Well, what we showed is that there's an error in the argument that all black holes are the same because they hadn't kept track of these very subtle things. And whether or not this is the key error in the argument remains to be seen, or whether this is a technical point. </s><s>[INST] Yes. But it is an error. It is an error. [/INST] And Hawking obviously agreed with it. Hawking agreed with it, and he was sure that this was the critical error, and that understanding </s><s>[INST] this would get us the whole story, and that could well be. What was it like working with Stephen Hawking and this particular problem because it's kind [/INST] of a whole journey, right? Well, you know, I love the guy. He's so passionate about physics. </s><s>[INST] He just, yeah, his oneness with the problem and the, I mean it's- So his mind is all occupied by the world that's- Yeah. [/INST] And let me tell you, there's a lot of other things with his illness and with his celebrity </s><s>[INST] and a lot of other things. A lot of distractions pulling at his mind. He's still there. [/INST] He's still there. That's right. </s><s>[INST] I remember him turning down tea with Lady Gaga so we could spend another hour on paper. That my friend's dedication. What did you learn about physics? [/INST] What did you learn about life from having worked with Stephen Hawking? Well, he was one of my great teachers. Of course, he's older than me, and I was reading his textbooks in graduate school. And I learned a lot about relativity from him. I learned about passion for a problem. I learned about not caring what other people think. Physics is an interesting culture, even if you make a great discovery like Hawking did. People don't believe everything you say. In fact, people love to disagree. It's a culture that cherishes disagreement. And so he kept ahead with what he believed in and sometimes he was right and sometimes </s> |
<s>[INST] but you [/INST] buy the product because it was made salient to you. Now, you can't lie to yourself. Lex salience can catch attention, but attention can drive salience. So this is what I can do. I can make something salient by paying attention to it, and then that will tend to draw me back to it again, which, and you see what happens, which means it tends to catch my attention more so that when I go into the store, that bottle of liquor catches my attention and I buy it, you, </s><s>[INST] and that's why is that bullshit, because [/INST] what you're doing is being caught up in the salience of things independent from whether or not that salience is tracking reality. </s><s>[INST] Is it independent, or is it loosely connected? Because it's not so obvious to me when I see happy people at a bar, that I don't in part believe that well, my experience has been maybe different logically, I can understand, but maybe there's a bar out there, it's all happy people dancing. [/INST] In fact, </s><s>[INST] most of the bars I go to these days in texas is pretty lots of happy people. [/INST] I think you can I mean, there's probably variation, although I think it's very the truth seeking in there, let's say they're the intent is at least to try and shut off your truth seeking, it might not completely succeed, but that's the intent at times it can completely succeed because I can give you pretty much gibberish and never let it will motivate your behavior. There's there's this symptom, there's an episode from the classic Simpsons, not the modern Simpson, the classic symptoms where the there's aliens and they're running for office in the United States. Now I'm Canadian. So this doesn't quite work for me, but right. And the speech goes like this. My fellow americans when I was young, I dreamt of being a baseball, but we must move forward, not backward upward, not forward, twirling twirling towards freedom and people go and there's a rush nothing, there's nothing there. And yet it's great satire because a lot of political speech is exactly like that. There's nothing there. Right? </s><s>[INST] Well, I'm [/INST] not saying all political speech I said a lot, </s><s>[INST] but there there's a fundamental difference between and it's so hilarious. I remember that episode, uh there's a fundamental difference between that absurd sort of non secular speech and political speech because one of the things is political speech is grounded in some sense of truth. [/INST] And so if that requires you talking about alternative facts and weird, self destructive oxymoronic phrases. Isn't that approaching pull pure bullshit? </s><s>[INST] No, I think I think pure bullshit. Uh like the vacuum is uh is very difficult to uh to get to, but I get the point. So what exactly is truth is it possible to know. I [/INST] think Spinoza is right about truth. That truth is only known by its own standard, which sounds circular. There's a way in which he didn't mean that circularly. And I think this is also converges with plato. These are two huge influences on me. I think we only know the truth retrospectively when we, when we go through some process of self transcendence, when we move from a frame to a more encompassing frame so that we can see the limitations and the distortions of the earlier frame. You have this when you have a moment of insight, insight is you doing your you are really realizing what is relevant. You go, oh, oh! </s><s>[INST] I [/INST] thought she was aggressive and angry. She's actually really afraid. I was mis framing this right? And you change what you find relevant. You have those Aha moments. </s><s>[INST] So do you think it's possible to get a a sense of objective reality? So is it possible to have to get to the ground level of what something that you can call objective truth [/INST] or </s><s>[INST] is it are we always on shaky ground? [/INST] I think those moments of transcendence can never get us to an absolute view from nowhere. And so this is drew Highlands notion of finite transcendence. We are capable of self transcendence and therefore we are creatures who can actually raise the question of truth or goodness or beauty because I think they they all share this feature, but that doesn't mean we can transcend to a godhood to some absolute view from nowhere that takes in all information and organizes it in a comprehensive whole. But that doesn't mean that truth is thereby rendered valueless. Um I think a better term is real and real and illusory our comparative terms. You only know that something is an illusion by taking something else to be real. And so we're always in a comparative task, but that doesn't mean that we can we can somehow jump outside of our framing in in some final manner and say this is how it is from a God's eye point of view. </s><s>[INST] So what do you think if I may ask of somebody like Ayan rand and her philosophy of objectivism? So where the core principles that reality exists independently of consciousness and that human beings have direct contact with reality through sense perception. So they have that you do have that ability to know reality. [/INST] There's two things knowing that there's an independent reality is not knowing in that independent reality. Those are not the same thing. Yeah. </s><s>[INST] But I think objectivism would probably say that our human reason is able to have contact with that, [/INST] then I would respond and say, you have to I believe in fact, ultimately in in a conformity theory of knowing that what that the deepest kind of knowing is when there's a contact, a conformity between the mind when the embodied mind and reality. But and here's where I guess I'd push back on on rand. I would say you have to acknowledge partial knowledge as real knowledge because if you don't you're going to fall prey to minos paradox. Minos paradoxes. You know this in plato right to know P well if I don't know P I'm gonna go looking for it, but if I don't know P how could I possibly recognize it when I found it? I have no way of recognizing. I don't have no way of knowing that I found it. So I must know P but if I know P then I don't need to learn about it. I don't need to go searching. So learning doesn't exist. Knowledge is impossible. The way you break out of that paradox is saying, no, no, no. It is partially it is possible to partially know something. I can know it enough that it will guide me to recognizing it. But that's not the same as having a complete grasp of it because I still have to search and find what I don't yet possess in my knowledge. If we So </s> |
<s>[INST] So you think the neocortex, the whatever reasoning is that's the latest feature in the latest version [/INST] of this journey. It's extraordinary that humans have evolved so much in so little time. Again, if you look at the timeline of evolution, you basically have billions of years to even get to a dividing cell and then a multicellular organism and then a complex body plan. And then these incredible senses that we have for perceiving the world, the fact that bats can fly and they evolved flight, they evolved sonar in the span of a few million years. I mean, it's just extraordinary how much evolution has kind of sped up. And all of that comes through this evolvability, the fact that we took a while to get good at evolving. And then once you get good at evolving, you can sort of, you have modularity built in, you have hierarchical organizations built in, you have all of these constructs that allow meaningful changes to occur without breaking the system completely. If you look at a traditional genetic algorithm, the way that humans designed them in the sixties, you can only evolve so much. And as you evolve a certain amount of complexity, the number of mutations that move you away from something functional exponentially increases. And the number of mutations that move you to something better exponentially decreases. So the probability of evolving something so complex becomes infinitesimally small as you get more complex. But with evolution, it's almost the opposite, almost the exact opposite, that it appears that it's speeding up exactly as complexity is increasing. And I think that's just the system getting good at evolving. </s><s>[INST] Where do you think it's all headed? Do you ever think about where, try to visualize the entirety of the evolutionary system and see if there's an arrow to it [/INST] and a destination to it? So the best way to understand the future is to look at the past. If you look at the trajectory, then you can kind of learn something about the direction in which we're heading. And if you look at the trajectory of life on earth, it's really about information processing. So the concept of the senses evolving one after the other, you know, like bacteria are able to do chemotaxis, which means moving towards a chemical gradient. And that's the first thing that you need to sort of hunt down food. The next step after that is being able to actually perceive light. So all life on this planet and all life that we know about evolved on this rotating rock. Every 24 hours, you get sunlight and dark, sunlight and dark. And light is a source of energy. Light is also information about where is up. Light is all kinds of, you know, things. So you can basically now start perceiving light and then perceiving shapes beyond just the sort of single photo receptor. You can now have complex eyes or multiple eyes and then start perceiving motion or perceiving direction, perceiving shapes. And then you start building infrastructure on the cognitive apparatus to start processing this information and making sense of the environment, building more complex models of the environment. So if you look at that trajectory of evolution, what we're experiencing now and humans are basically, according to this sort of information, theoretic view of evolution, humans are basically the next natural step. And it's perhaps no surprise that we became the dominant species of the planet. Because yes, there's so many dimensions in which some animals are way better than we are. But at least on the cognitive dimension, we're just simply unsurpassed on this planet and perhaps the universe. But the concept that if you now trace this forward, we talked a little bit about evolvability and how things get better at evolving. One possibility is that the next layer of evolution builds the next layer of evolution. And what we're looking at now with humans and AI is that having mastered this information capability that humans have from this quote unquote old hardware, this basically biological evolved system that kind of somehow in the environment of Africa and then in subsequent environments and sort of dispersing through the globe was evolutionarily advantageous. That has now created technology, which now has a capability of solving many of these cognitive tasks. It doesn't have all the baggage of the previous evolutionary layers. But maybe the next round of evolution on Earth is self-replicating AI, where we're actually using our current smarts to build better programming languages and the programming languages to build, chat GPT and that then build the next layer of software that will then sort of help AI speed up. And it's lovely that we're coexisting with this AI that sort of the creators of this next layer of evolution and this next stage are still around to help guide it and hopefully will be for the rest of eternity as partners. But it's also nice to think about it as to simply the next stage of evolution where you've kind of extracted away the biological needs. Like if you look at animals, most of them spend 80% of their waking hours hunting for food or building shelter. Humans, maybe 1% of that time. And then the rest is left to creative endeavors. And AI doesn't have to worry about shelter, et cetera. So basically it's all living in the cognitive space. So in a way it might just be a very natural sort of next step to think about evolution. And that's on the sort of purely cognitive side. If you now think about humans themselves, the ability to understand a comprehendor on genome, again, the ultimate layer of introspection, gives us now the ability to even mess with this hardware, not just augment our capabilities through interacting and collaborating with AI, but also perhaps understand the neural pathways that are necessary for empathetic thinking, for justice, for this and this and that, and sort of help augment human capabilities through neuronal interventions, through chemical interventions, through electrical interventions to basically help steer the human bag of hardware that we kind of evolved with into greater capabilities. And then ultimately by understanding not just the wiring of neurons and the functioning of neurons, but even the genetic code. We could even at one point in the future start thinking about, well, can we get rid of psychiatric disease? Can we get rid of neurodegeneration? Can we get rid of dementia and start perhaps even augmenting human capabilities </s> |
<s>[INST] well I got to push back on that a little bit or as a, as a by way of a fan asking a dumb question. Okay, let me just give some examples. It's very common in sports. It's funny you said this example of like certain great players going to another team right at the end of their career and uh it always makes me sad. It almost makes me want to wish that he kind of retired right there. Um from a perspective of just like, do you ever as a, as an owner, but just in that space, think about like the Steelers in the full arc of human history, so not like as a business. Okay, that's [/INST] good news is I don't have to think about it as, you know, I'm a minority owner, so I can think about it almost as a fan, but I'm I'm sorry, go </s><s>[INST] ahead. Yeah, that's what I mean, I suppose this is a dumb question to think of, um like of a business in that way, not just investment, but like, like legacy of like what footprint would you leave on this world on [/INST] this history. That is one thing that I can say unequivocally and I only have the experience that I have. But one of the things that I'm so proud of um about the way the Steelers conduct themselves is, and that's the Rooney family. That's the legacy of the Rooney family is asking constantly about what's right for the league, what's right for the players? You know, what, what what's the right thing to do here and that that's something that I would hear, Mr Rooney say all the time. So I think that legacy is important because ultimately the team belongs to that city, right belongs to those fans and you know, the owners of the custodians of that. So I think, and when you realize what sports teams mean to the fans, the memories that creates the bonds that it creates, it's a, you know, it's a responsibility. Um, and I think that you do have to think beyond the, you know, certainly not just dollars and cents, but just sports is a very big deal in our society. And and it has to be I think held to a standard that's not just were we profitable this year, what that's there are other businesses for that. It is certainly a business I don't mean to romanticize to the point that it's not. But to me it's it's more than that or at least my experience has been that it's more than </s><s>[INST] that. It's a source of meaning for millions of people [/INST] like and you </s><s>[INST] see that most like during Covid for example, when there's so much desperation, so many people losing their jobs, so many people having to deal with the uncertainty of what the future holds. There's something about the sports that just unites us that again, the tragedy and the triumphs of sport, of uniting of gathering together with your friends, with family, shared experience of over like this Yeah, over just team, over, rooting for your team for your city [/INST] and the access, you know, again, as I alluded to, we didn't have anything when I was growing up, but I would pour through the box scores. I was a huge yankee fan and Steeler fan and feeling some ownership of that right that I could read the box score and relive what they did and occasionally see them on tv and I feel like I was part of that celebration when they want and everything. It's a very powerful thing. </s><s>[INST] You've been exceptionally successful in a bunch of avenues and a bunch of efforts. What advice would you give to a young person today, high school student, college undergraduate that's thinking about career, maybe advice not about just career, but about how to live a life they can be proud of. [/INST] You know, we talked earlier about intellectual honesty and to me that's the first step of just saying to the best of your ability, who am I and what I, what are, what's important to me and what do I want to do and accomplish? If you can start with that and develop some sort of rules based philosophical, here's what I'll, what I'll do what I won't do and that way you can be flexible and pliable and you're going to need to be, But if you, if you still have a compass that tells you, hey, at least I know this is the path I'm going to take. I think that's very important. The rules </s><s>[INST] you're referring to, the principles that's kind of like underlying integrity. So knowing what lines you don't cross on this path. [/INST] Exactly, right. Because if you have those absolutes, there are many decisions that come into focus very quickly, right? Because hey, I'm, that's not for me or hey, I'm willing to do whatever it takes to do X, y and z. </s><s>[INST] And it has to do with the thing you were talking about. It's kind of interesting, you mentioned that earlier in the, in the conversation about slippery slope and that's how often it happens. Like how the slipping into unethical behavior happens. It's a slippery slope of little adjustments you put stuff off and that, that I found that to be, uh, I've been fortunate to do not have to encounter these moments very much in my life, but I still encounter them. That's what integrity I think looks like is in as the slippery slope is happening, those little things is um without drama, without making a show of it, making a decision that stands behind your principles and just walking away. [/INST] Yeah. And besides the big ideas, I'm gonna change the world. I'm gonna innovate. I'm gonna do all those other things. I also start if I'm giving any advice which you know, we we can debate whether or not, you know, I should be giving advice, but just in terms of, well, let me start with this, are you a good friend? Can you be counted on? Do you do what you say you're going to do, right? Are you accountable to what you sign up for? And do you hold others accountable? Right? What what does all that look like? And then I think it's being as intellectually curious and well read as you can be. We live in a world that is designed to distract you right? And being able to sit with your thoughts or go on a walk and think deeply about something and not just surface area. You text me, I text you back and we decide the fate of the world based on a couple of text messages or something. Um you don't want to lose touch. I think with being well read and understanding and standing on great thinkers, shoulders and learning from from, from those works. And then I also think that, you know there's, there's resiliency and then there's grit and I heard someone say one time that those are slightly different and you know, I'm also, I know that there are all kinds of challenges in life, right? That that are tragic, that are unfair. There's no question, that's the world we live in. But for me personally to try as much as possible not to be in the victim mindset because unfair things are gonna happen and you know, we all want to live in an idealistic just world that that should be what we aspire to. I, I haven't seen that yet, I haven't experienced that yet, but yet you still have to function in that world. So you know, I think that that resiliency thing is very important and then putting yourself out there right? Because if you play scared and you're always afraid to fail, you know, this is, this is probably a dumb way to get to the end of the podcast. But there are times, especially I'm out west, I love the big sky out in, you know, Montana Idaho, places like that and when you look up at night, it's almost like I've never seen anything like this before because there's no light pollution, so to speak. And sometimes when I look up the most daunting problems that I'm experienced, I'm like those, those things have been there for a billion years or whatever and I'll be gone and it doesn't, you know, the most famous person on earth 200 years ago. So, you know, it's pretty fleeting and uh, so make sure you, you have a good journey and especially coming out of Covid, I think telling people that you care about that, you care about them and maintaining and cultivating your friendships and relationships and they're not just transactional, right? And, and making sure that someday when you're laying there, you can say, yeah, I was a good family member. I was a good, good friend. I was someone that could be counted on. I think all those things go into the mix of, you know, however you want to take the journey. </s> |
<s>[INST] Can we talk about the Fountainhead and Atlas Shrugs and which character do you find most fascinating ones that kind of you meet in your own mind that you almost have conversations with [/INST] there as an influence on you and your life in general? You know what character I like? Because I know no one ever gives this answer. But this is my, just aesthetically, you know how sometimes you're drawn to a character and it's, if this person were real, you think they're just, but there's something about the resonates with you. I can't even explain this. But I love the character in Atlas Shrugs of Lillian Reardon, who's Hank Reardon's wife. And what is amazing about her. So she's his wife. He's this big industrialist innovator. And she's this former beauty in that. But she's so cold and soulless that there's, I mean, I joke about, you know, Anne Rand's vampire novels. That character is as close to a literal vampire as you're going to see in Rand. And there's just this great scene where Hank Reardon invents Reardon metal. It's this great metal, which is extremely strong, but extremely, it's like light. So this creates all these innovations. And he brings her a bracelet made of the first Reardon metal. This is his life goal. This is, like, Prometheus bringing fire. And she's like, what the fuck is this? It brought me diamonds. Yeah, it could have brought me diamonds. What is this shit? And Dagny, who is another industrialist, she's a heroine, a very strong female character in Atlas Shrugs, is at a party. And she goes, I got diamonds. Let's trade. And she really was like, you want this? And she's like, yes, because that's the concretization of the human mind. These are rocks. And Lillian's like, okay, whatever. And that character is someone who has a lot of resonance in our culture, this kind of soulless. It's easy to write a soulless male figure, like Peter Keating in some ways is soulless, but that for some reason when it's like the soulless female, it seems that much more chilling and effective. Do you not agree, though, that Lillian Reardon is an amazingly- Oh, powerful. Very powerful figure. Powerful figure. </s><s>[INST] Good or bad, sorry. [/INST] No, it's an amazingly- Powerful figure. And I think Reardon is, too. And what I love about Reardon is his evolution, right? He's so flawed. He's a hero who is completely flawed. And it drives me nuts when people say, who characters are cartoonish, they never change, there's no emotion. Really? Did you read the same book I did? Because if you take Reardon, and he's struggling, and he's trying to deal with Lillian and his family and all this stuff, and we know family members like this, right? I mean, they were leeches and parasites, but he's excusing them because that's what he's supposed to do. And then as he evolves to fully realize what's going on, that evolution is difficult, it's hard. Like the scene after he has sex with Bagnie, of course, he gives a speech, but the speech is such a good speech in terms of conveying his mind-body split. He really had fun, he really enjoyed the sex, right? But he thinks it's animalistic, and he thinks it's a sign of his depravity, and he thinks, and here he is, this woman he loves, and he adores her, and he can't connect the two. He can't connect the sex with the love. He can't connect the sex with adoration, and with the value. So her characters are anything, I think, but cardboard characters, because I think they're Dagni and the scenes where she's listening to music, and gets captured by the music in the way Rand describes that. I think it's just beautiful. Or the scene, my favorite scene in Atlas is the scene where they're crossing, where they're taking the first train ride across the John Gold Bridge, and they're in the engine room, and it's traveling through, and the way she's describing Dagni, and it's almost like Dagni's having sex with the machine, right? It's so powerful, emotionally, their success, the fact that they did it. Everybody told them it was impossible, and the train is going really fast, and that whole, it's got a sexual vibe to it. It's all about passion, it's all about success, and it's all about the success of their minds, and nobody else matters. What's really great about that scene, just in terms of constructive novel, I'm not going to spoil anything. So the Atlas Shrugged has three acts, like three-act structure is not uncommon, and the first act is about Hank Reardon overcoming all this adversity at home in his personal life and in his business to create this great achievement. So Rand really makes the reader invested in this character and his accomplishments. He's unambiguously doing something good. There's no downside here. He's making it easier to transport people, transport food. This is really just great. And it's just once you read it and you look back, you're like, she does such a masterful job of making – you have to be a fan of this person and root for them, because she's like, oh, you think things are going great, he's overcome? Hold on a minute. And then the rest of it, she's just – and your sense of injustice is triggered as a reader to such an nth degree, because you saw what he went through to get to this point and now you're seeing it taking away people inferior. And one of the quotes on Twitter I use all the time is, I'll see someone, politician or a bureaucrat or a thinker, just advocate for something completely unconscionable. And I'll just quote and say, my favorite criticism of Ayn Rand is that they say her villains are too evil and unrealistic, because the things that people posit with a straight face are so much worse than she has in her book. And not just politicians. You find intellectuals today. Oh, of course. Oh, yeah, yeah. Way over the – even whenever they – Atlas Shrugged, I was going, nobody really talks like this. No, they do. Let me give you one example. There was a story she wrote which she never published. They published her journals, the Ayn Rand Institute. And there was one character, and this is a prototype of Ellsworth Tewey. He was the villain of – one of the villains of The Fountainhead. And basically, the kid had like deformed legs or broke his leg or something like that. And he wants to get leg braces. And the dad is like, oh, we're not going to do that. Why should you be better than anyone else? Like you should just have like this deformity. Except your fate. And you're reading this. I'm like, what dad is not going to give his kid leg braces? It's ridiculous. But now it's not uncommon for deaf children to not get cochlear implants and not be able to hear because their parents say, well, we're going to lose deaf culture. Hearing is just information. And you're sitting there, and whether you agree with this or not, this is very close to what she was saying. And when I read what she was saying, I'm like, okay, crazy Ayn Rand, this is not a thing. And it's like, oh, yeah, the craziness is that it's not braces, it's hearing. It's deformity. Except it's it's yeah. And what evil to deny your kid hearing? I mean, God, so Here's the other thing. If you want deaf culture, which I would believe is a thing, sign language, whatever, they could turn it off. Yeah. Yeah. If you want to give them the choice. Yeah. Let's go tonight. I'm sorry. One more thing to, you know, Rand use the word evil frequently. And I think maybe I can make the argument she's a too loosely. If you are denying a child the gift of music, I will say that's evil. I agree completely. Unambiguously. Go online and listen, watch videos of people getting hearing aids and being able to hear for the first time. And seeing what happens. They face it. I promise you, you will cry because there's no pure, I'm getting teared up right now. There's no pure expression of humanity and technology at its best than seeing a two-year-old or one and a half year old who can't even talk. And then you see the reaction when they hear mom's voice. It's so beautiful and moving. Absolutely. And seeing what happens, they </s> |
<s>[INST] I probably imagine there were two dinosaurs back in the day having this exact conversation and they look up to the sky and there seems to be something like an asteroid going towards earth. So it's while it's, it's very true that the ark of our society of human civilization seems to be progressing towards a better, better life by everybody in many ways that you described, uh, things can change in a moment and it feels like it's not just us humans, we're living through a pandemic. You could imagine that uh, epidemic would be more destructive or uh, or there could be asteroids that just appear out of the darkness of space, which I recently learned is not that easy to uh [/INST] give you another to detect </s><s>[INST] them. Yes. [/INST] So 48, what happened in 48 years? I'm not 2068 apophis there's an asteroid that's coming In 48 years. It has a very high chance of actually wiping us out completely. Yes. Yes. So we have 48, years to get our act together. It's not like some distant distant hypothesis. Like yeah, sure. They're hard to detect, but this one we know about it's going, </s><s>[INST] how do you feel about that? Why are you still talking? [/INST] Oh gosh, I'm so happy with where we are now. This is going to be great seriously. If you look at progress, if you look at again, the speed with which knowledge has been transferred, what has led to humanity making so many advances so fast. Okay, so what has led humanity making something advances is not just the hardware upgrades, it's also the software upgrades. So by hardware upgrades, I basically mean our neocortex and the expansion and these layers and folds of her brain and all of that, that's the hardware. The software hasn't uh you know, the hardware hasn't changed much in the last what, 70,000 years as I mentioned last time? If you take a person from ancient Egypt and you bring them up now they're just as equally fit. So hardware hasn't changed. What has changed is software. What has changed is that we are growing up in societies that are much more complex. This whole concept of mutiny basically allows the exponential growth. The concept that our brain has not fully formed has not fully stabilize itself until after teenage years. So we basically have a good 16 years, 18 years to sort of infuse it with the latest and greatest in software. If you look at what happened in ancient Greece, why did everything explode at once? My take on this is that it was the shift from the Egyptian in hieroglyphics software to the greek language software. This whole concept of creating abstract notions of creating these um layers of cognition and layers of meaning and layers of abstraction for words and ideals and beauty and harmony. How do you write harmony and hieroglyphics? There's no such thing as, you know, sort of expressing these ideals of peace and justice. And you know, these concepts of or even, you know, macabre concepts of doom, et cetera. You don't you don't have the language for it. Your brain has trouble getting at that concept. So what I'm trying to say is that these software upgrades for human language, human culture, human environment, human education Have basically led to this enormous explosion of knowledge. And eventually after the enlightenment. And as I was mentioning the 42 line Bible uh and the printed press the dissemination of knowledge. You basically now have this whole horizontal dispersion of ideas in addition to the vertical inheritance of genes. So, the hardware improvements happened through vertical inheritance. The software improvements happen through horizontal inheritance. And the reason why human civilization exploded is not a hardware change anymore. It's really a software change. So if you're looking at now where we are today, Look at coronavirus. Yes, sir. It could have killed us 100 years ago. It would have but it didn't why because in january. We republished the gina A month later. Less than a month later. The first vaccine designs were done. And now, less than a year later, 10 months later we already have a working vaccine that 90% efficient. I mean that is ridiculous by any standards and the reason is sharing. So you know, the asteroid yes, could wipe us out in 48 years but 48 years. I mean look at where we were for eight years ago technologically. I mean how much more we understand the basic foundations of space is enormous. The technological revolutions of digitization, the amount of compute power we can put on any like, you know, by nail size, you know, hardware is enormous. So and this is nowhere near ending. You know, we all have our like little, you know, problems going back and forth on the social side and on the political side on on the cognitive and on the sort of human side and the societal side, but science has not slowed down. Science is moving at breakneck pace ahead. So, you know, Ellen is now putting rockets out from the private space. I mean that now democratization of space exploration is you know, going to review is </s><s>[INST] going to explode, [/INST] Continue in the same way that every technology has exploded. This is the shift to space technology exploding. So 48 years is infinity from now in terms of space capabilities. So I'm not worried at all. </s><s>[INST] Are you excited by the possibility of a human 1? Human stepping foot on Mars and to possible colonization of not necessarily mars, but other planets and all that kind of stuff for people living in space never inevitable. Would you do it? Or you kind of like, [/INST] how many, </s><s>[INST] how many, how many people will you wait would you wait for? I think it was about when the Declaration of Independence was size, about 2 to 3 million people [/INST] lived here. So would </s> |
<s>[INST] So to go there. I mean there's several things with consciousness that make it a real discipline which is one is rigorous measurement of consciousness and then the other is the engineering of consciousness which may or may not be related. I mean you could also run into trouble like for example in the United States, for the department bot department of Transportation and a lot of different places put a value on human life. I think D. O. T. S. Values $9 million per person, sort of in that same way you can get into trouble if you put a number on how conscious of being is. Because then you can start making policy if a cow is 0.1 or like uh 10% as conscious as a human. Then you can start making calculations and might get you into trouble. But then again there might be a very good way to do it. [/INST] I would like uh to move to that place that actually we have scientific understanding what consciousness is and then we'll be able to actually assign value. And I believe that there is even the path for the experimentation in uh in it. So uh you know we said that you know you could put the probes inside of the brain. There is actually a few other things that you could do with devices like neuralink. So you could imagine that the way even to measure if a. I. System is countries is by literally just plug into the brain. I mean that assumes that it's kind of easy but the plugging into the brain and asking person if they feel that their consciousness expanded. Uh This direction of course has some issues. You can say you know if someone takes a psychedelic drug they might feel that their consciousness expanded even though the drug itself is not conscious, </s><s>[INST] right? So like you can't fully trust the self report of a person saying their consciousness is expanded or not. Uh Let me ask you a little bit about psychedelics because there's been a lot of excellent research on different psychedelic psilocybin. M. D. M. A. Yeah even D. M. T. Drugs in general marijuana too. What do you think psychedelics due to the human mind? It seems they take the human mind to some interesting places. Is that just a little hack a visual hack or is there some profound expansion of the mind? [/INST] So let's see I don't believe in magic, I believe in I believe in uh in science in in casa Latina. Still let's say. And then as I said like I think that the brain that the our subjective experience of reality is a we live in the simulation run by our brain and the simulation that our brain runs. They can be very pleasant or very hellish drugs. They are changing some hyper parameters of the simulation. It is possible thanks to change of these hyper parameters to actually look back on your experience and even see that the given things that we took for granted they are changeable. So they allow to have amazing perspective. There is also for instance the fact that after D. M. T. People can see the full movie inside of their head gives me further belief that the brain can generate the full movie that the brain is actually learning the model of reality to such extent that it tries to predict what's going to happen next. </s><s>[INST] Very high resolution. So you can replay reality is [/INST] actually extremely high resolution. Yeah, it's also kind of interesting to me that somehow there seems to be some similarity between these drugs and meditation itself. And I actually started even these days to think about meditation as a psychedelic. </s><s>[INST] Do you practice meditation? [/INST] I I practice meditation? I mean I went a few times on the retreats and it feels after like after second or third day of meditation. Uh there is a there is almost like a sense of you know tripping. </s><s>[INST] What what is the meditation retreat entail? [/INST] So you you wake up early in the morning and you meditate for extended period of time. Uh Yeah, so it's optimized even though there are other people, it's optimized for isolation. So you don't speak with anyone, you don't actually look into other people's ice. Uh and uh you know you sit on that shirt and it's a Vipassana meditation tells you to focus on the breath so you try to put all the all attention into briefing and breathing in and breathing out. And the crazy thing is that as you focus attention like that after some time their stems starts coming back. Like some Memories that you're completely forgotten. It almost feels like that you have a mailbox and then you know you are just like an archiving email 1x1 and at some point at some point there is like a amazing feeling of getting to mailbox 00 emails And uh it's very pleasant. It's kind of, it's it's crazy to me that that once you resolve these inner store stories or like an inner traumas then once there is nothing left, the default state of human mind is extremely peaceful and happy extreme. Like some sense it feels that the it feels at least to me the way how when I was child that I can look at any object and it's very beautiful. I have a lot of curiosity about the simple things and that's where the usually meditation takes me. </s><s>[INST] Are you, what are you experiencing? Are you just taking in simple sensory information and they're just enjoying the rawness of that sensor information. So there's no there's no memories and all that kind of stuff, you're just enjoying being. [/INST] Yeah, pretty much. I mean, still, there is a the its thoughts are slowing down, sometimes they pop up, but it's also somehow the extended meditation takes into the space that they are way more friendly, way more positive. There is also this uh this thing that we've extra can it almost feels that the it almost feels that the we are constantly getting a little bit of a reward function and we are just spreading this reward function on various activities. But if you stay still for extended period of time, it kind of accumulates accumulates accumulates And uh there is a there is a sense, there is a sense that at some point it passes some threshold and it feels us. Yeah drop is falling into kind of ocean of love at least and that's like this is like a very pleasant and that's what I'm saying, like that corresponds to the subjective experience. Some people uh I guess in spiritual community they describe it that that's the reality and I would say I believe that they're like all sorts of subjective experience that one can have. And uh I believe that for instance meditation might take you to the subjective experiences which are a very pleasant collaborative and I would like a word to move the word uh more collaborative uh place. Yeah, I would say that's very pleasant and I enjoy doing stuff like that. </s> |
<s>[INST] Multi model, Multi center across multiple cameras, but also in the case of car radar, ultrasonic sound even so all of those. [/INST] Right. Exactly. </s><s>[INST] So another thing, another part of your work has been in the space of privacy and that too can be seen as a kind of security vulnerability is also thinking of data as a thing that should be protected. And the vulnerabilities to data as vulnerability is essentially the thing that you want to protect the privacy of that data. So what do you see as the main vulnerabilities in the privacy of data and how do we protect [/INST] it? Right, so in insecurity we actually talk about essentially to in this case two different properties. One is integrity and one is confidentiality. So what we have been talking earlier is essentially the integrity of the integrity property. After learning system. How to make sure that the learning system is giving the right prediction for example and privacy centuries on the other side is about confidentiality of the system is how Attackers can when the Attackers compromise the confidentiality of the system, that's when the attacker is still sensitive information um, right about individuals and so on. </s><s>[INST] That's really clean those. Those are great terms integrity and confidentiality. So how what are the main vulnerabilities to privacy? We just say and how do we protect against it? Like what are the main spaces and problems that you think about in the context of privacy? [/INST] Right? So, um especially in the machine learning setting. Um so in this case as we know that how the process goes is that we have the training data and then the machine learning system trains from this training data and then build a model and then later on inputs are given to the model to influence, time to try to get prediction and so on. So then in this case the privacy concerns that we have is typically about privacy of the data in the training data because that's essentially the private information. So and it's really important because oftentimes the training data can be very sensitive. It can be a financial data is your health data are like in our case it's the sensors deployed in real world environment and so on and all this can be collecting very sensitive information and other sensitive information gets fed into the learning system and trains and as we know, these neural networks, they can have really high capacity and they actually can remember a lot and hence just from the learning the learned model in the end, actually Attackers can potentially infer information about the original training datasets. </s><s>[INST] So the thing you're trying to protect that is the confidentiality of the training data and so what are the methods for doing that, would you say? What are the different ways that can be [/INST] done And also we can talk about essentially how the attacker may try to write the information from the right. So so and also there are different types of attacks. So in certain cases, again, like in white box attacks, we can see that the attacker actually get to see the parameters of the model. And from that the smart attacker potentially can trying to figure out information about the training dataset. They can try to figure out what type of data has been the training dataset and sometimes they can tell like whether a person has been a particular person's data point has been used in the training dataset. </s><s>[INST] So white box meaning you have access to the parameters of saying neural network so that you're saying that it's some given that information as possible to some. [/INST] So I can give you some examples and another type of attack which is even easier to carry out is not a web box model is more of just a quarry model where the attacker only gets to quarry the machine learning model and then try to steal sensitive information in the regime training data. So, so I can give you an example uh in this case training a language model. So in our work in collaboration with researchers from google, we actually studied the following question. So so however, the question is as we mentioned, the new networks can have very high capacity and they could be remembering a lot from the training process. Then the question is can attack actually exploit this and try to actually extract sensitive information in the original training data set through just occurring the current model without even knowing the parameters of the model. Like the details of the model are the architecture of the model and so on. So uh so that's the that's the question we set out to explore. And in one of the case studies we showed the following. So we train the language model over. An email data sets is called an Enron email data sets. And any email data sets naturally contained uses Social security numbers and credit card numbers. So we train the language model over the citizens and then we showed that an attacker by devising some new attacks by just occurring the language model and without knowing the details of the model. The attacker actually can extract the original social security numbers and credit card numbers that were in the original training </s><s>[INST] So get the most sensitive personally identifiable information from the data set. I'm just carrying it. [/INST] Right. Yeah, that's an example showing that that's why even as we train machine learning models we have to be really careful with protecting users data privacy. </s><s>[INST] So what are the mechanisms for protecting? Is there, is there is there hopeful. So there's been recent work on on differential privacy for example that that provides some hope but that's [/INST] actually right. So that's also our finding is that by actually we show that in this particular case we actually have a good defense </s> |
<s>[INST] That's not having it. Yeah. So how do you deprogram? Because I don't like to bring up Ayn Rand just because I do see how people roll their eyes essentially. What's the upside? What's the upside exactly? But what is that? [/INST] Can we, can you speak to that programming that people have? That people have. Look, at the end of the day, if you talk about the ideas and ideas make sense, and people attract it to the ideas, then you say, Oh by the way, and this came from Ayn Rand, that's how you deprogram them. If you make the ideas prevalent in the culture, if people start viewing self-interest as That's interesting and worthwhile and something worth investigating and they said, oh, that came from Iron Man, then I think we'll deprogram them and get them changing their minds about these things. And also, going on shows where people are going to watch your show no matter who you bring on, right? So even though, now you do, if you put Iron Man in the title, that immediately reduces the number of people who watch. </s><s>[INST] So in the future, you put Echol-Auus in the title and then at least the female population too. Exactly. [/INST] The female, yeah, absolutely. It's just to say. So you go and you try to make them as credible as possible to as many people as possible over time. It takes time and ultimately I don't think the culture will have this response to her. They might still disagree with her, but I think over time, and already you're seeing it, younger people, I think today are far less. There was a generation who never read Iron Man and was like this, bring out the Gallic the crosses, we don't want to have anything to do with her. And I think today, there are many more people who've read her and might disagree or not disagree, right? And then there are a lot of people who haven't read her but who are not opposed to it or willing to engage. So I think it's changing already. And I think in 20 years, it'll be completely different. And just two more things that she does that I think it says that I think people find very, very off-putting given our culture. One is she will basically, you could sit down with Rand and be like, your fear is not in any way a hold on my freedom. Just that one sentence. And for a lot of people, that's very off-putting and very harsh. It's correct. But for them, it's just like, wait a minute, I'm still scared. It's like, I don't care. Like for example, like with lockdowns and things like this. It's like, well, I'm scared and maybe I have a right to be scared. Or like, I'm scared that you have a gun in your house. And it's like, I respect that you're scared. I don't care at the end. As you say, at the end of the day, this is my house. I'm going to live my life as I please, as long as I don't hurt other people. Well, you are hurting me because I'm scared. No, that's not- This is the feeling versus facts. Yeah, yeah. So that is one situation where- It's like the feeling versus freedom, essentially. Yes, where Rand puts a lot of people off. I also think that historically, a lot of people who were drawn to her are drawn to her for the wrong reasons. That a lot of times, like Howard Rourke, the hero, we're going to still say hero, you're supposed to say protagonist, but hero. The hero of the fountainhead, he's extremely intelligent, but he's also extremely uncompromising. What often ends up happening is, you'll have a young kid who is somewhat intelligent, but then they pick up the personality and now you're someone I can't work with. And then it's like, you're not Howard Rourke, relax. You're not that skilled, you're not that talented, but because the character has deep personification and have certain aspects together, when kids read that, they're going to might get the wrong idea, and that's not Rand's fault. And you care. Yeah, yeah. It's like the feeling versus freedom, essentially. And it's more than that. I completely agree with that, but it's even broader than that. So here is, in my view, one of the geniuses of the millennium, presenting a philosophy. And she's got not just the questions, in my view, she's got the answers. And you're reading them at 16, and you're eating the answers. You don't know at 16 that this is true. Yeah, yeah. You might have a sense that it's true, but you don't have the life experience, the learned experience. You don't have the facts, you don't have the knowledge. You're picking up truth. It's just being absorbed. You're accepting it is true, but you don't know it's true. And then you go out into the world advocating for it, which we all did, or at least I did when I was 16, and you're obnoxious, you can't prove what you argue here. Because you don't have the experience. It took me, I don't know, 10, 20 years, probably 20, to figure out that I really do think what she said was true, right? But I didn't know when I was 16. When I was 16, I just absorbed these ideas and accepted them in a sense, you know, with some connection to reality, but in a sense, on faith, right? At least presented it that way. And as a consequence, you come off as a detached from reality, a obnoxious human being. And I think of a lot of young objectivists aw, and it's hard not to be because you are you're confronted with genius. And you're not a genius. I certainly am not a genius. And I'm confronted with just genius and have all this information in my head now. I can articulate it. And it's hard to deal with yourself. What? There's an inside joke. Yeah, you said confronted genius, I pointed at us. Yeah, I'm confronted with you guys. I'm at an age where I know how to deal with geniuses. But I'm gonna say that there's something – but this is not why people don't like her, but there's something that the Fountainhead does, which I think is very – and I don't blame her, but it's a bad consequence. If you read the Fountainhead and you're young and you're intelligent and talented, the message – at least I got and I know I'm not alone – is you're going to think that you're gonna be a pariah, a lot of people are gonna be against you, and you're basically doomed for a short period of being isolated and alone. And that may have been the case when Fountainhead was written. But I think now with the internet and in my experience, both as a youth and someone who's a little bit older, I didn't appreciate and you're not going to get it from that book. And you can't get it through that book because it has to have a certain narrative. How many people who are a little older are giddy when they find young talent. Oh, yeah. How inspiring it is, how exciting it is. Like when you talk to these kids who are doing things on the internet or writing or whatever achievement, you want them to flourish. You're not threatened by them as the antagonists of the Fountainhead are. And that doesn't come through in the Fountainhead? It depends on your profession, right? I mean, for some of these parts of the world are better than others. If you're an artist, at least the way I conceive of art and you want to go study art today, be poo pooed and look down on and so on. So, yeah, I agree. I mean, in my generation, when I read Iron Man, there was no internet and I was in Israel. So we were isolated and there was nobody else who shared their ideas. And he did feel that kind of isolation, but Rock gave you, to me, he didn't teach me about, you know, you're going to be isolated partially because I wasn't look down on. Oh, of course. And maybe I was humble, right? I thought you were Israeli. When I read Atlas Shrugg, I identified with Eddie Willis. Okay. When I read The Fountainhead, I didn't identify with Howard Rock. How old were you when you read The Fountainhead? I didn't think about it. So I read Atlas when I was 16. I probably read the Fountainhead when I was 16 and a half, 17, Something like that. That is an unfavorable crime. You read The Fountainhead after Atlas Shrugg? Yeah. If anyone listening to this, they should read Fountainhead after Atlas Shrugg. No, that is a war crime. No, for me, eating Atlas Shrugg was much more important. It is more important, but my point is, I think The Fountainhead, in many ways, is redundant in certain aspects if you read Atlas Shrug first and because the Fountainhead is such a masterful book and such a personal book. I agree with that. So, ideally, you'd read the Fountainhead. That's what I'm saying, yes. And here's the other thing people don't appreciate. I'm sorry to interrupt you. People think Rand's always about politics, politics, politics. Because Fountainhead is not a political book. It's about... she talks about politics in Man's Soul, sure. But it's about ethics, how important everyone has to have a moral code. That's the other thing why people find Rand off-putting. If you have young people who now find it very important to live a moral life, who are like, what does that mean to have morality, to have ethics, to live with integrity for people who have gotten a little older, who have made these little sacrifices, who are like, I'm not going to fight at work. Do I really need to look for another job? Yeah, my wife's kind of, you know, getting annoying, but am I going to make a fight about it? These little sacrifices that they make every day. And big ones. And big ones, absolutely. So when you have someone who's saying, forcing you to look in the mirror and say, those little sacrifices and big sacrifices you made, you did the wrong thing and you're evading that you betrayed your own conscience, that to many people I think is very threatening. Ethics. A big one. This is why so many people say that Ayn Rand is for 14 year old boys. Right. Right. And there's a reason why it appeals to 14 is a little young, but 16, 18, it's because those are the ages where we're still open to idealism, idealism in a positive sense, right? To beautiful things, to ideals, to seeking perfection, to seeking a great life. I think as you grow older, most people become cynical. They give up on their ideals. Why? Because their ideals were wrong and their ideas failed. Right? My parents were socialist when they were young. Those ideas failed. So where do you go from socialism to idealism? Cynicism. Yes. Which is horrible. Right. Almost all adults are cynical and that has failed the idealism, and when they look at the young people, they see their idealism, oh well, that's, I was idealistic too. And they don't question the idealities, well, they're good ideals and they're bad ideals, they're right ideals and they're wrong ideals. The cynicism is economic, essential. and... And that's why they attribute it to, they attribute it to youth. So it's a threat to a lot of people. A lot of people, who... It's too late for... For some people, it's too late to change their minds and they know it. And they're too invested in it in the job, in the wife, in the compromises. In the comfort. And they're too invested in the comfort. Too invested in the compromises. Too invested in the comfort. And they know that they shouldn't be. They know they should change. And these young people are challenging that, and that is really, really scary for them, and that's why they reject it without even, without too much consideration. One of the things Rand, the working title for Fountainhead was Secondhand Lives. And Rand had two definitions of selfishness in that book. One is selfishness in the sense of my life is the most important thing. It's not the only important thing. My family would be number two, friends. They certainly are extremely high values, but you can't have these secondary values without the first value. But in the context of my life, right, because your family might not be a value. Right, you might hate your family. Yeah. You might not be a value. Right. Right, right, right. Sure, the point being, selfishness. Then there's the other kind of selfishness which is Peter Keating one of the villains of the book which is he's selfish in that he's greedy. He's looking out for number one, but he has no values. He has no sense of character. He just wants to be wealthy. He wants to have a beautiful wife. He wants to have a big house. Why? He couldn't tell you because other people have it and he wants to have it more than them. His sense of reference is other people. He's living second-hand. The problem with that is a lot of young people read Rand, and when they start arguing online, they just start trying to talk like Rand, whereas Rand would be like, be original, be an innovator. If you want to argue for objectivism in Rand's views, take her ideas, articulate them in your own way, because that's a good way of showing that you understand what she thinks. But what they end up doing is just talking like her. It sounds dated and comical, and that's going to be off-putting because it's like Rand wouldn't expect someone else to sound like Rand. She's a, you know, her own person. And she, of course, wouldn't view Keating as selfish in any sense, or even Greedy. Greedy is a tricky word. Well, she was selfish in the old-school sense. Yeah, he's selfish in the old, but even there, it's not as if he has some passion and he's going after passion no matter what. I'm going to light, she'd steal, I'm going... His passion is painting, and he doesn't pursue his passion. He pursues what his mother wants him to pursue, and he pursues money and he's completely second-handed </s> |
<s>[INST] Yeah, exactly. Creating creating incentives that and encourage the best and the most beautiful [/INST] aspects of nature. Will </s><s>[INST] it all boils down to meeting girls and boys? [/INST] Once again, you're getting to the bottom of the evolutionary motivations and you're always on safe ground when you do </s><s>[INST] that. This is a little difficult for me. I've, you know, and I'm sure it's actually difficult for you to listen to me, you say complimenting you, but it's difficult for both of us. Okay, So, but uh you know, you and I as I mentioned to you, I think I might have been friends for a long time. It's just been one way. So like everyone, it's two way, it's too right now. So like that's the beauty of podcasting, you know, I mean now just been fortunate enough with this particular podcast that I see it in people's eyes when they meet me that they've been friends with me for for a for a few years now and and we become fast friends actually after we start talking, but it's one way in the vet and now, first moment uh you know, like there's something about, especially hardcore history that, you know, I do some crazy challenges and running and stuff. I remember in particular Probably don't have time, one of my favorite episodes, the painful Tainment one. Some [/INST] people hate that episode </s><s>[INST] because it's too real. [/INST] Uh, it's my darkest one. We wanted to set a baseline. That's the baseline. </s><s>[INST] But I remember listening to that and when I ran 22 miles for me, that was a long distance and that's [/INST] entertainment, Right? </s><s>[INST] Yeah. And it just pulls you in and there's something so powerful about this particular creation that's bigger than you actually, that you've created. [/INST] It's kind of interesting. I think anything that is successful like that, like Dylan stuff to, it becomes bigger than you and that's, that's what you're hoping for, right? </s><s>[INST] Absolutely. Didn't mean to interrupt you [/INST] apologize. I guess </s><s>[INST] one question I have, if you like, look in the mirror, but you also look at me, what advice would you give to yourself and to me and two other podcasters, maybe to joe Rogan about this journey that we're on? I feel like it's something special. I'm not sure exactly what's happening, but it feels like podcasting is special. What advice? And I'm relatively new to it. What advice do you have for for people that are carrying this flame and traveling in this journey? [/INST] Well, I'm often asked for advice by new podcasters. People just starting out. And so I have sort of a tried and true list of dues and don't stand, but I don't have, um, advice or suggestions for you or for joe joe doesn't need anything from me, joe's figured it out, right? I mean he </s><s>[INST] hasn't yet. He's still confused kid curious about the world. [/INST] That's, but that's the genius of it. That's what makes it work, right? That's what, that's what Joe's brand is, right. Um, I guess what I'm saying is is by the time you reach the stage that you're at or joe's at or they don't need, they have figured this out. The people that sometimes need help our brand new people trying to figure out what do I do with my first show and how do I talk to them? And I've standard answers for that. But you found your niche. I mean, you don't need me to tell you what to do. As a matter of fact, I might ask you questions about how you do what you do, right? Well, </s><s>[INST] there's uh, I guess there's specific things like we were talking off line about monetization. That's a fascinating one. [/INST] Very difficult. Uh, as an independent </s><s>[INST] and uh, one of the things that joe is facing with, I don't know if you're paying attention, but he joined Spotify With $100 million exclusivity, that one, I don't give a damn about money personally, but I'm single. So, and I like like living in a shady place, so [/INST] I </s><s>[INST] enjoy, so I guess makes it easy [/INST] to get the freedom right. </s><s>[INST] Freedom materials is slave not [/INST] saving for anybody's college. </s><s>[INST] Exactly. Okay. So at that point, but I also, okay, maybe it's romanticization, but I feel like podcasting is pirate radio and when I first heard about Spotify partnering up with joe, I was like, you know Funk? The man I, I said, I I even I drafted a few tweets and so on. Just like attacking Spotify. Then I calmed myself down that you can't lock up this special thing we have. Uh, but then I realized that maybe that these are vehicles for just reaching more people and actually respecting podcast, there's more and so on. So that's what I mean by it's unclear what the journey is Because uh, you also serve as a beacon for now. There's like millions, one million plus podcasters. I wonder what the journey is. Do you have a sense? Um, are you romantic in the same kind of way in feeling that because you have a roots in radio to do you feel that podcasting is pirate radio Or is this Spotify thing one possible avenue. Are you nervous about Joe as a fan, as a friend of Joe or is this it's a good thing for us. [/INST] So my history of how I got involved in podcasting is interesting. I was in radio. Uh, and then I started a company back in the era where the dot com boom was happening and everybody was being bought up and it just seemed like a great idea, right? Started. Um, I, I did it with seven other six other people and the whole goal of the company was, and we had, we had to invent the term, I'm sure everybody, I mean, there's other places that invented it at the same time, but what we were pitching to investors was something called amateur content. This is before Youtube, before podcasting, before all this stuff and I, my job was to be the evangelist and I would go to these people and uh, and, and sing the praises of all the ways that amateur content was going to be great. And I never got a bite. And they all told me the same thing. This isn't gonna take off because anybody who's good is already going to be making money at this. And I kept saying, forget that we're talking about scale here. If you have millions of pieces of content being made every week, A small percentage is going to be good, no matter what, right, 16 year olds will know what other 16 year olds like. I kept pushing this nobody bit. But the podcast grew out of that because if you're talking about amateur content in 1999, well then you're already where, you know, you're ahead of the game in terms of, of not seeing where it's going to go financially, but seeing where it's going to go technologically. And so when we started the podcast in 2005 and it was the political one, not hardcore history, um, which was an outgrowth of the old radio show. Um we didn't have any financial um, ideas, we were simply trying to get a handle on the technology and how you distribute it to people and all that. And it was years later we tried to figure out, okay, how can we get enough money to just support us while we're doing this? And, and the cheap in the easy way was just to ask listeners to donate like PBS kind of model and that was, that was the original model. Um, so then once we started down that we figured out other models and this advertising thing and we sell the old shows and so all these became ways for us to support ourselves. Um, but as, as podcasting matured and as more operating systems developed and phones were developed and all these kinds of things, every one of those developments, which actually made it easier for people to get the podcast actually made it more complex to make money off of them. So while our audience was building the amount of time and effort we had to put into the monetization side began to skyrocket. So to get back to your Spotify question to use just one example, there's a lot of people who are doing similar things um, In this day and age, you know, we just sell MP three files and all you had to have was an MP three player is cheap and dirty. Now every time there's an os upgrade something breaks for us. So we're having, I mean my choices are at this point to start hiring staff, more staff, you know, people don't, and then be a human resources manager. I mean the pirate radio side of this was the pirate radio side of this because you didn't need anybody, but you know, you are you and another, I mean, you could just do this lean and mean and it's becoming hard to do it lean and mean now. So if somebody like a Spotify comes in and says, hey, um, we'll handle that stuff for you in the past, I would just say f off, we don't need you, I don't mind. And I definitely am not making what we could make on this, but what we would have to do to make that is onerous to me, but it's becoming onerous to me day to day anyway. And so if somebody were to come in and say, hey, we'll pick that up for you, we will not interfere with your content at all. We won't, and in my case, you can't say we need to show a month because that ain't happening, right? So, I mean, everybody's, everybody's uh design is different, right? So it doesn't, you know, there's not one size fits all, but I guess as a long time pirate podcaster, um, there are, you know, we've been looking to partner with people, but nobody is right for us to partner with. I mean, so, so I'm always looking for ways to take that side of it off my plate because I'm not interested in that side. All I wanna do is the shows and they, you know, it's really at this point you shouldn't call yourself an artist because you know, that's something to be decided by others. But I mean what we're trying to do art and there's something very satisfying in that, but the part that I can't stand is the increasing amount of time the monetization question takes upon us. And so there's a case to be made, I guess is what I'm saying that if a partnership with some outside firm enhances your ability to do the art without dis enhancing your ability to do the art, it's um, the word I'm looking for here is it's um, it's enticing uh, I don't like big companies. Um, so I'm afraid of, of whatever strings might come with that. And if I'm joe Rogan and I'm talking about subjects that can make company public companies, you know, a little nervous. Um, I would certainly be careful. But at the same time, people who are not in this game don't understand the problems that literally, I mean, just all the operating systems, all the podcasters every time some new podcaster comes out makes it easier to get the podcast. That's something we have to account for on the back end and I'm not exactly the technological wizard of all time. So, um, I think it is maybe maybe the short answer is is that as the medium develops, it's becoming something that you have to consider not because you want to sell out, but because you want to keep going and it's becoming harder and harder to be pirate. Like in this environment. </s> |
<s>[INST] Whatever the expression for that is, English is in fact my second language. I took a nap recently, I guess shortly into the past into the recent past. I took a nap that was about 20 minutes I want to say. And I woke up completely refreshed. I think there's probably really good science on that of just napping. [/INST] Is there </s><s>[INST] a book? Not on sleep but specifically on napping um mastering napping. Master napper. [/INST] If </s><s>[INST] There isn't a book, I'm gonna write one and will forever be remembered and it'll be a short one. I really enjoy napping and my favorite thing to nap on is an eight sleep bed because it cools it down with a warm blanket and it's just it's heaven check it out and get special holiday savings of up to $400 when you go to sleep dot com slash lex. This show is also brought to you by Inside Tracker a service. I used to track biological data that comes from my own body and gives me wisdom that only large scale raw data can provide. The signal that's pulled off from that data using machine learning algorithms. And we're talking about blood data, DNA data, fitness tracker data, all kinds of data. I'm actually going to a neuralink event very shortly and that event is about extracting data from your mind. Long term vision of brain computer interfaces. Two way communication between computers, maybe artificial intelligence enhanced computers and the human mind. That data is extremely powerful to tell you what's going on in your mind and your body. And I think Inside Tracker is at the cutting edge of uh what can actually lead to positive lifestyle changes. Using that data coming from the person personalized to that person. Alright. Get 200 bucks off Inside Trackers ultimate plan or 34% off the entire store when you go to Inside tracker dot com slash lex. This episode is also brought to you by element electrolyte drink. Mix spelled L. M. N. T. I drink a lot of element. There's some guests [/INST] that </s><s>[INST] was on recently. [/INST] I </s><s>[INST] might have been grimes or live, I'm not sure exactly, but they said they're a huge fan of element, who was it? But they said um we had like a debate about favorite flavors and went to drink and how much to drink and they discovered that I drink like way too much helmet [/INST] from </s><s>[INST] their perspective, from my perspective. Never [/INST] enough. </s><s>[INST] So it makes me feel great in terms of diet, it makes sure that I get enough hydration, makes water taste great for all the crazy exercise and mental and physical stuff. I do diet stuff I do, it's just really important to make sure your electrolytes are done correctly, you get a simple pack for free with any purchase. Try it at drink elements dot com slash lex. This is a lex Friedman podcast. To support it, please check out our sponsors in the description and now your friends, here's Todd, howard, is it possible that we are currently living inside a video game that the future you designed? Can you give hints as to how one would escape if this was a video game, how can a video game character escape to outside the video [/INST] game? Are </s><s>[INST] these things you don't consider when you design the game [/INST] actually we do because in the kind of games that we make, we want it to be as open as possible. So, you know, when you start a game, you're always testing it. What can I do? What, what would the game allow me to do and you check everything, you try to pick up the, you know, the mugs, you try every door, you collide with everything. Like, hey, what are the rules of this world? We try to do games where, you know, we say yes, as much as possible, that leads to some level of chaos. But if you were stuck in a video game, you would, you would try everything and usually you're gonna find a door or a space where the designers didn't anticipate you piling all those crates up and getting over a wall that they didn't expect, </s><s>[INST] right? So it's not a designed doorway out. It's uh accidental unintended doorway out and it's a, it's a happy bug, [/INST] you could, like Truman show just get in the ocean and go to </s><s>[INST] just keep going, keep going. But the more realistic the game becomes, the harder it is to find that door. The bigger the world, the bigger the open world [/INST] and then as we do it, we learn they're gonna find a way. So just don't try to pin them in. Usually we leave like this developer test cell area in the game that we don't anticipate anyone will find and they ultimately find it usually has crates of all the weapons in the game and things like that. </s><s>[INST] The little hints you drop now will just drive people mad, which is something I enjoyed, deeply. Uh, so Skyrim NPC s have at times hilarious dialogue. What does it take to build a good NPC dialogue? The [/INST] main thing is to make them reactive a lot of times when you write characters from movies or things like that, you want to make that character interesting for themselves. Right? What's their story? And there's some characters like that that the player definitely cares about, but the best characters are the ones that react to you. So you'll find a lot of people love our guards and the guards are written almost purely to be reactive, hey, nice tie like your jacket, do this cool watch, you know, hey, what you do. And so that hey, you're the man as you walk by that makes them interesting or the way they react to something that you do lydia in Skyrim who everybody loves? I'm sworn to carry your burdens. That's a generic line that all of the, you know, house carl's have and it just kind of lands when she says it, </s> |
<s>[INST] there's uh, there's maybe to get your comment on something which javascript and actually, most languages sort of python, such a big part of the experience of programming with those languages includes libraries, sort of using building on top of the code that other people have built. I think that's probably different from the experience that we just talked about from UNIX and C days when you're building stuff from scratch. What do you think about this world of essentially leveraging, building up libraries on top of each other and leveraging them? [/INST] Yeah, that's a very perceptive kind of question. One of the reasons programming was fun in the old days was that you were really building it all yourself. The number of libraries you had to deal with was quite small. Maybe it was printed after the standard library or something like that. Um, and that is not the case today. And if you want to do something and you mentioned python and javascript and those of the to find examples, you have to typically download a boat load of other stuff and you have no idea what you're getting absolutely nothing. I've been doing some, playing with machine learning over the last couple of days and gee something doesn't work? Well you pip install this okay. And down comes another gazillion megabytes of something and you have no idea what it was. And if you're lucky it works. And if it doesn't work, you have no recourse. There's absolutely no way you could figure out which of these 1000 different packages. And I think it's worse in the M. P. N. N. P. M. Environment for javascript. I think there is less discipline, less control there. </s><s>[INST] And there's aspects of uh not just not understanding how it works, but there's security issues. They're business issues. So you don't want to run a nuclear power plant using Javascript essentially. Probably [/INST] not. </s><s>[INST] So speaking to the variety of languages, do you think that variety is good or do you hope think that over time we should converge towards 123 programming languages that you mentioned to the bell out days when people could sort of the community of it. And the more languages you have, the more you separate the communities, There's the ruby community, there's the python community, there's C++ community. Do you hope that they will unite one day to just one or two languages? [/INST] I certainly don't hope it. I'm not sure that that's right because I honestly don't think there is one language that will suffice for all the programming needs of the world, Are there too many at this point? Well, arguably. Um but I think if you look at that, that's sort of the distribution of how they are used, there's something called a dozen languages that probably account for 95% of all programming at this point. And that doesn't seem unreasonable. Uh, and then there's another, Well, languages that are still in use that nobody uses and or at least don't use in any quantity. But I think new languages are a good idea in many respects, because they're often a chance to explore an idea of how language might help. I think that's one of the positive things about functional languages, for example, they're particularly good place where people have explored ideas that at the time didn't seem feasible, but ultimately have wound up as part of mainstream languages as well. Let me just go back as early as Rikers in lisp and then follow forward functions as first class citizens and pattern based languages and gee, I don't know, closures and just on and on and on lambdas, interesting ideas that showed up first, and let's call it broadly the functional programming community and then find their way into mainstream languages. </s><s>[INST] It's a playground for rebels. [/INST] Yeah, exactly. And, and so I think the languages in the playground themselves are probably not going to be the mainstream, at least for some while, but the ideas that come from, there are invaluable. </s><s>[INST] So let's go to something that when I found out recently, so I've known you've done a million things, but one of the things I wasn't aware of that you had a role in ample. And before you interrupt me by minimizing your role in it, [/INST] which was for minimizing functions. </s><s>[INST] Yeah. Minimizing functions. Right. Exactly. Um uh Can I just say that the elegance and abstraction power of ample is incredible when I first came to it about 10 years ago, or so. can you describe what is the ample language? [/INST] Sure. So ample is a language for mathematical programming? Uh technical term. Think of it as linear programming that is setting up systems of linear equations that are offer some sort of system of constraints so that you have a bunch of things that have to be less than this, greater than that, whatever. And you're trying to find a set of values for some decision variables that will maximize or minimize some objective function. So it's it's a way of solving a particular kind of optimization problem. A very formal sort of optimization problem. But one that's exceptionally useful </s> |
<s>[INST] it, it almost, how did you interpret it psychologically? Was it like some kind of, I mean, not to be spiritual or whatever, but some kind of superpower that was like, like a lingering feeling like holy sh it, I, you know, [/INST] I can't, I can't explain it and I haven't really tried hard enough to try to, but something changed. Something happened there. Yeah, something happened to me, I was sore for about three or four months afterwards. It's like, it smoked out my entire body. Yeah, that whole summer. I was kind of sore. And uh yeah, and then after that, like two or three years later, that's when I won the World championships. Um Yeah, I mean all the matches are, you know, you get something from people like, you know, you study them, you you take something from them. People have an invisible crown and he had one and I think I took it from </s><s>[INST] him. Maybe that was the feeling of wearing the [/INST] crown. </s><s>[INST] What about all the trash talk? How much of that did you learn that come naturally to you? You're, you're one of the most charismatic fun. I mean there's always like respect behind it, I would say to me and I'm a fan of a lot of sports, you're one of the greatest trash talkers in all of sports that I've ever seen because you're able to talk ship. But there's so much love and respect behind it. It's just masterful. But you also get into people's heads in the moment. It's beautiful to watch because it really gets, it gets to some people. So where does that come from? Its [/INST] powerful weapon? Right. Yeah. Your voice is a powerful, powerful weapon and it's underutilized by so many athletes because they think that it's not sportsmanlike or something like that. But the truth is, I mean, you can be a a week person, but with your voice, you can influence and change any number of things and the same thing happens in a, in a, in a fight between two people if you can just be a never ending, you know, flow of negative encouragement to someone or, you know, you know, suggestion anything can happen. It's a tool. Um and when you're fighting a person, you're not just fighting them. You're fighting everyone who's watching your fighting the crowd, the referees and you know, to get in the most ideal positions, situations you need to use your voice. </s><s>[INST] Yeah. Yeah. And there's a, for people who haven't seen, I definitely recommend you watch a bunch of arm wrestling matches because um there's a crowd really gets into it and it feels it feels like there's a really intimate connection with the crowd I suppose because the crowd is allowed to be very close to you. I said I love it. [/INST] I want the crowd like right up on me. </s><s>[INST] Yeah, yeah. So sometimes, [/INST] Oh yeah. </s><s>[INST] So who are you when, whenever you talk to somebody, you literally pick somebody from the crowd. Oh yeah, [/INST] I'll follow him. Like I'll start fucking off his fans and like, yeah, like I'll start talking to their wives or whatever. Yeah. Uh there's Jody. Um she's pretty dangerous to, to listen to also. But yeah, one of his buddies mike, Solaris, who's, you know, really good arm wrestler was talking was was cheering for him. So I started to go after him. Yeah. </s><s>[INST] Smiling the whole [/INST] fan. </s><s>[INST] It's fun to listen to. But it's also what's fun is how much it actually affects some of the people you're facing, they get frustrated, it's great to see you [/INST] have to fight, right? Like a lot of people think things will be given to them and and the thing that, you know, I've, I've always believed from the time I was very young, like I I was convinced that uh our inevitable death was going to come from aliens, right? Like some super aggressive, super violent species was going to come and smoke us all, you know? And I'm like, I'm I'm not like that, I'm like, but as soon as one person is then you're forced to have to accept it as reality, right? So I like to fight for every single thing I like to try and be more and more aggressive and if someone matches me, that's when I can use my endurance and if they don't, then I have the tactical advantage. So that's kind of my my balance point. </s><s>[INST] And then by the way, you also yell at the ref, I mean the games, there's like levels to this game, but you know, the, the feeling sometimes when people get frustrated like, okay, this person is cheating or like you're trying to get a good grip before they go before it goes. And and, and I think some of the frustration in combination with the trash talk is what this person is cheating, but everybody is like kind of trying to cheat, get an edge within the [/INST] rules. So I try and just ramp it rampant rampant, but you know, everybody's different, I've learned how to play the game based off of the tools that I have physically and for me this works because you know, my genetic makeup is more and more of a persistence hunter. Right? So like I need to extend things and that works well for me. Um, you know, if if I was more explosive, I probably wouldn't have the same strategies. Yeah. </s><s>[INST] By the way, for people who watch, who are watching, you're wearing no limits hoodie, which is one of your nicknames. I [/INST] don't wash this thing too much. It's my bacterial shield to uh, to the world. Yeah. </s> |
<s>[INST] K. And there's this thing called Bang Bang, which people are probably watching, know exactly what I'm talking about. It's this worst possible thing you can do in terms of meals, which is, you go to a restaurant, you're full meal and then go to another restaurant and do a full meal and you, you [/INST] exactly. So </s><s>[INST] they go mexican, italian sushi pizza barbecue, Ihop, that that one is disgusting. This kind of thing reminds me of the [/INST] joy of food. Last time we were hanging out, we went, we want to see joe do comedy and then we went to eat Russian food and it was a particularly </s><s>[INST] fun [/INST] experience to go to a Russian restaurant. I was the only person there that didn't speak Russian and eat Russian food with you and um because I felt walking in, they trusted you, they didn't trust me. Yeah, the </s><s>[INST] funny thing about the people there, they were talking to you in Russian and then they refused to sort of switched to english even though they understood you speak no Russian, this is Russian house in Austin by the way. Uh anyway, what, by way of question, what's the worst or the best, depending on your perspective, cheap meal, let's call it a pigging out meal. But it could be a cheap meal uh, that you've ever had or you want to have, that's like on the bucket list or something that's in the past, like where you did the, something like a bang bang, which is like you're talking about multiple, thousands of calories that you just feel horrible about yourself, but you still keep eating because it's delicious, but also great company, something about the atmosphere is just right, screw the diet, screw all the things, you know, I just like you should be doing, but just throw it all out the window, [/INST] I've done that several times. Yeah, I don't do this anymore. But um the entire time I was a postdoc. So five years and the entire time I was a pre tenured professor. So five years. So I basically followed the tim Ferriss slow carb diet, which is, you know, people can look it up but it worked really well. It was basically some, you know, like good animal proteins, you know, fish and meat and things </s><s>[INST] like that because [/INST] like low glycemic stuff is mostly lentils and beans and things and vegetables. No, no dairy, no. Um anyway, but then one day, no, no pasta. So it wasn't low carb, but it was low glycemic carbs and I did that and it works terrifically well just for energy levels because I wanna be able to train and work and then one day a week you're supposed to go full cheap day. And so I would do what used to be 12 hours, but then it became 20 for, you know, you start to redefine what the day is. Um and I would, and that was when Costello was pretty young and we would do it together. So I would get pizzas and croissants and donuts and I would just do the full thing and by the end of the day, you don't want to look at an item of food, you're just repulsed by food. The only modification I made was the next day, I would fast completely just to avoid the gastric distress of eating anything and so I would do them on Sundays and Mondays that fast all day and then by Tuesday I felt pretty good again, but sunday and monday or you just feel like you're sliding down the slope of just blood sugar disaster, </s><s>[INST] you [/INST] know, at the time I enjoyed it. I love doughnuts, croissants, all that kind of stuff. What's interesting is after stopping that whole protocol. Now, I'm just trying to eat. Well, it's really a protocol now. I basically, I do a sudo, intermittent fasting. I don't, I'm not really strict, but I'll start eating around 11. Eat my first meal around 11. I usually train in the morning, eat my last bite of food somewhere around eight or nine and I'm not super strict. I might have some berries or something late at night, two meals, 2-2 meals and then maybe a little bit of snacking on some nuts or something in the middle, </s><s>[INST] 24 [/INST] hours. Never done a long fast except when I was doing the gaze and then, um, and actually there are a couple different ways to do things that were fun. Like you were in a new city, you could try all the restaurants that you wanted. Yeah. And I think tim and our mutual friend john romaniello did a, I think it was like a cheat day marathon where they did, you know marathons, 26.3 miles. They went to 26.3 different locations in new york. They put it on a map and I never took it to that extreme. But </s><s>[INST] wait, wait over how many days [/INST] one day that was there </s><s>[INST] just [/INST] because they were, you know, </s><s>[INST] just a little bit of something at each [/INST] place. Yeah, exactly. I mean there are things that guys do in their thirties that you just shouldn't do in your forties. I can say that because I'm in my forties and uh now I just try and eat well most days. And what's interesting is about 12 to 14 months ago, I completely lost all appetite for sweets. I don't know what happened. I still love savory foods. So meat and butter and cheese. Uh and I love vegetables too. I love fruit also, but lost all appetite. So if you put a donut in front of me or ice cream or something like I just, it's, it's almost aversive to me and I don't know what happened. I don't know what changed. </s><s>[INST] It's probably a scientific explanation. It has to do [/INST] dementia, the </s><s>[INST] sugar, the, the desire for that [/INST] rush. Maybe </s><s>[INST] it's gone from your, from your soul. What was the most delicious things across? Aren't Donuts? What, what is there a thing that there's [/INST] a place in Portland, I don't know if it's still open called little tease bakery and they have croissants that easily rival the croissants in paris. People make a lot of the pastry in paris, but it's really the bread in paris, that's amazing. We lived there when I was a kid and we did a sabbatical there and you know, they're, they do the baguette morning break and afternoon bake and that there's nothing like the bread in paris or the people, you know, and but if you're in the, if you're in the pacific northwest, you know, you can find amazing croissants there. </s><s>[INST] What do you do with the croissant? What do you do with the bread butter? [/INST] Or is it just actually used to, I don't eat them anymore. I don't have much of an appetite for them, even though they're not a sweet food. But um I'm always putting butter on the croissant, butter on the butter croissant. No jam. I would never, I would never adulterated Micro since I have to </s><s>[INST] actually be honest about this because people talk about steak and they talk about bread with the butter. I feel like butter is cheating. I feel like you're disrespecting the fundamental food by adding butter. Because butter, it's like, it's like, it's like a elite version of ketchup. Well [/INST] there we diverge because for me, bread is just a vehicle for butter. </s><s>[INST] A [/INST] cracker is just a vehicle for cheese. Oh, </s><s>[INST] so that's just the cracker and the bread is just texture. [/INST] It's just that people look at you funny if you, if you just eat the butter straight, which occasionally I do. </s><s>[INST] I got it. But [/INST] so I put a little piece of bread underneath it. Not because I'm low carb, strictly low carb, but just because otherwise you get some funny </s><s>[INST] looks. Mm That's like pasta is a is a vehicle for pasta sauce. It's interesting. But like indian naan bread you have of the bread. I've had a lot of soul searching on which part of indian is brings me so much joy. Is it the bread or is it all the sauces that come with the bread? [/INST] Well, there we diverge again because for whatever reason and no disrespect to anyone. But indian food doesn't appeal to me. </s><s>[INST] Well, you're a lucky man because the number of calories in that food, it sneaks like naan bread. I don't know how naan bread is made, but I think it's just soaked in oil and it's just very intensely like the density of calories is very, very high for me. Barbecue. I would say it's probably the that's good [/INST] anytime I'm in Austin, I started thinking about barbecue. I do love, you know, I do love me. My dad's Argentina. I mean, I love steak. I love meat. I mean Argentina chorizo sausage is an appetizer before you have steak. So it's not just, you know, it's not just the men, right? You see women sometimes very petite women eating steaks that are bigger than their, that their skull size. You know, slowly. They eat very slowly there and they all eat dessert too, which is interesting. And they generally do this sort of one meal per day and that kind of reflexively, that's </s><s>[INST] how I think about it because I often eat one meal a day, especially when I'm traveling. It feels like a cheap meal because it allows it gives you a bit of more freedom to just lose yourself in the quantity of the food. I did the three day fast and that a chicken breast like literally chicken breast with nothing else just grilled and that is the most delicious piece of meat I've ever eaten. And that uh and that gives you, the problem is when you fast for three days you really can't pig out, You really shouldn't. You get, [/INST] your stomach will shrink in size already your gut microbiome is almost completely depleted by fasting. A lot of people think, oh, cleanses and fasts are great for the microbiome. They quash your microbiome. However, when you start eating again, the microbiome comes back better than it was before your fast. </s><s>[INST] For people who don't know, Sergei and Todd on the call. They're kind of pulling stuff up, they just pulled up Phelps with the I forget how many calories just eating 10,000. [/INST] You know what's interesting. There's some some cool physiology around this. The reason he needed to eat so much is not that he was burning that many calories in pure movement. It's that when you do exercise in water, even if it's warm water, the heat transfer and water is greater. So you burn far more calories. And again here, I'm admittedly lifting that from knowledge that was passed onto me by tim Ferriss I didn't so, but I checked it out and it's absolutely true. So if you exercise in water, even if it's not really cold water, your caloric needs to go way up, which is why you get out of the pool and you're often really hungry. </s><s>[INST] And for fans of the human lab podcast. And if you're not a fan, what what what are you doing in your life? Uh you would probably chuckle at the fact that uh Andrew just cited his sources even on that [/INST] statement </s><s>[INST] because you're so good at, I don't know how your memory works. But um, the only person who's memories, it's better than joe Rogan [/INST] is yours. But my colleagues joke um, you know, pub med sort of scrolls through through my, through my mind, um, also in science as you know, attribution is so baked into what we do. And um, and I think that it's interesting because now spending a lot of time on social media attribution is not as common and um, but in academia, you learned really early on that if you give a talk about your data and you cite all these amazing sources, all it does is make you look better, right? Whereas in social media and elsewhere in the business sector, it's almost like citing other people people feel as if it's going to take away some of the credit. All it does is place you in the company of people that do really nice work. So I have tremendous and I have genuine and tremendous respect for tim he's been about 10 years ahead on a huge number of health related things and other things, extremely kind person, very thoughtful person. So it's also just a pleasure to shine light on other people. </s><s>[INST] Yeah, well, I actually to push back, I know there's a culture of if you write a paper standing on the shoulders of giants is a powerful thing, but there's also a culture of not giving credit to the strongest idea in your paper and instead say it's kind of or imply that its original, there is a culture of kind of not celebrating others. I think people get most competitive in all walks of life, but especially in science when there as the closer they get and the exactly the thing they work on. And so there's this dance, you know, there's a few researchers in each of the individual little things that you work on if you're studying a particular kind of ant, you know, that other asshole that also studying that particular aunt and then you're not going to often give credit for the brilliant ideas that that other researchers doing. And I think one of the things you've discovered and just as part of your nature and which is why it's, it's really great that you've have an audience and inspire others to do the same as you celebrate that other ants study. Er it's great and you, everybody wins. It raises all boats. But that initial instinct to be like, what is it in Borat? Like my neighbor, my neighbor gets a toaster, I get a bigger toaster that, [/INST] yeah, that mindset, you know, it's not that I'm not competitive in certain domains, but um yeah, I get great pleasure from sharing things that I find and I think that, you know, at the end of the day, you're as strong as your community and you can build a wonderful community just by pointing out things that you love, like these are all just loves. I see a paper and I love it. Only rarely do. I think I wish we had done that. I usually think fantastic. Now I can just focus on something else because they checked off that </s><s>[INST] box. And by the way you mentioned pub med and barbecue, I should mention that I got a chance to hang out with rick Rubin. Thanks to you. He's a friend of yours and you made the connection. That was a huge gift to my spirit. I guess he's a truly, truly special human being and the there's a lot I could say about why he's a special human being. I'd love to learn how you met him. But I should also just mention on the pub med thing, it was so interesting talking to him about music and both on the podcast and privately and just listening to music together because when you mentioned a song, he does this thing where he like closes his eyes and he finds that song in the album that we're talking about and he steps through the album, you could you could see the brain like stepping through individual songs, defined that song in the album and there's that kind of look up process and then he puts himself mentally in that space of like, okay, this is uh you know, whatever the album is and not just the ones he produced, but all of it is an encyclopedia of music and it's so interesting. [/INST] It </s><s>[INST] also, the thing I really love about it is something like a calmness that radiates from them, that it's okay to close your eyes and place yourself in, in the in the place where that album was recorded, in the feeling of that album. Like that, that Silence, let's go there, let's go there together. It's like Alice in wonderland and we'll go there together. You [/INST] do a good rick Rubin minus the beard </s><s>[INST] minus the beard. [/INST] His beard is epic, right? You can't fake a beard like that. You know, how'd you guys meet? Yeah, well rick, I'm very blessed to consider a close friend um rick and I got introduced through a common friend during the pandemic and we started doing some face time together and just talking about things related to science and health. And I'm not a musician, I have no musical ability or talent, I have a good ability to memorize lyrics and I love lyrics and I love poetry. So I asked him a lot of questions about musicians that I happen to love that he's worked with and nose. And so he would give me stories about musicians and I would talk to him about health. And then eventually we formed a friendship where we talk about any number of different topics in </s><s>[INST] life. [/INST] And then we started spending time together in person when he was in town or nearby. And as you now know, Rick, in addition to all his incredible accomplishments, has an incredible understanding of how to get the brain and body into state, right? And as you pointed out, he's willing to do the things that allow him to help these incredible artists get into the best state to do their craft. And so if he needs to sit there and be quiet with his eyes closed for a minute or two and we're more, uh, he'll do that. Um, he has routines to allow himself to get into state. And it's really inspired me to think about states of mind is something that, you know, we'd all love to just just flip the switch and say we're focused or were creative. But um, to actually ratchet through the challenging steps in order to do that and to figure out what one needs to do on a regular basis to get into a proper state, it's not just going to come from a cup of coffee, uh you know, a lamp of a particular wavelength or something, it's gonna be those things, but it's also going to be really teaching oneself how to get into proper state. </s><s>[INST] Yeah, you did an episode on hypnosis. Do you think it's a kind of self hypnosis? [/INST] Yes, I do. Because hypnosis is a, you limit the context, you're very alert and you're very calm and um he has a number of these different practices and so we would talk about those and then we also have enjoyed a lot of discussions about deep neuroscience. In fact, I introduced Rick to a friend of mine who's a neurosurgeon and neuroscientist and they've become friendly, you know, rick is one of these people that he sort of defies definition, um incredibly kind, incredibly private person too. So, you know, I'm being respectful of that, but um and then of course he's a fan of your podcast and so when I learned that I I just made natural sense to introduce you and I know he really enjoyed meeting you and um we talked about you a lot and and of course in a positive, like, you know, I think his dedication to getting into these states of mind and his willingness to do that has completely transformed my routines around life, like, for instance, before doing a very long podcast, recording the solo ones, which often take me several hours or more? Six hours to record? Sometimes more, sometimes less. I realized that there's a certain brain state associated with that. So I have to really limit the kind of interactions I have for the two hours before I actually walk and talk out loud through my neighborhood. People think I'm crazy, but I live in a neighborhood where there are a lot of crazy creatives anyway, </s><s>[INST] You're not crazy. [/INST] Well, um at least not institutionally </s><s>[INST] defined [/INST] as crazy yet, but um you know, getting into state of mind is something that we all just imagine, we flip the switch, but rick really convinced me you have to do the work to do the work. </s><s>[INST] Can you maybe uh, linger on that loosened a little bit more of your process of how you get in that space. That's really interesting because I have to admit I do everything last minute before podcast. I don't know uh like there's a lot of anxiety because like whatever, if I have to pack, if I have to set up stuff, you were luckily a few minutes you showed up a few minutes later, right on time, but the stress is immense and uh on top of that, you look at like the situation with rick Rubin, he's all I had to set up microphones in front of him and just that stress the anxiety [/INST] knows a lot about microphones. </s><s>[INST] What did he say? Which I really loved. He's like, how close do you like the microphone to be? Like, [/INST] that's a very rick Rubin kind of thing, right? That the details really matter, the details really matter right down to your relationship to the </s><s>[INST] microphone, right? [/INST] Distance. And whether or not it brings out the timber in your voice. But of course that's what he does. He produces music. </s><s>[INST] But he also said like, you know, he is the professional. He said, how close do you like it to be? And he said it was a gentleness where I had like an existential crisis where I don't, I don't know, I, he gave me so much like, wow, like he made me feel like an artist like that the microphone, uh, distance is a decision you're supposed to make. [/INST] Well, I have to say. And this has actually come up in some of our conversations about it. I mean, you are, you are an artist and actually joe Rogan, once I heard him talking about podcasting and the fact that he's always trying to get better at it, you know, and he described podcasting at one moment as an art, right? And it is, it's a certain medium of communication and there's a cadence and a rhythm that um, when it's working it really can facilitate the transfer of information when it's not, it doesn't. I mean obviously joe just being himself has tapped into that cadence that allows and this made so many people excited to hear him talk </s><s>[INST] well in his case and in general I think part of the art is refusing the world as you get a bigger audience change who you are. [/INST] There's one quote that I've seen out there where he says, you know, I'm like the talking about himself, he says you know, I'm like the fish that got through the net. There's no stage version of me, how he is in person is how he is uh you know, out in the world and of course there's nuance to his life, right? And his different um relationships of course, but it's true. I mean we've had the you know the great fortune of spending time with him out away from the microphones, so to speak, joe is joe </s><s>[INST] so can you speak to your that process? You mentioned the walking and the talking to yourself cause that's [/INST] fascinating. I try and do a couple of things. Um First of all, when I was a kid I had a little bit of a grunting tick um when I was five or six um I would feel this build up of tension in my throat and I would do this grunting ticket if I get very tired. I start to do it still we actually know that this is related to these basal ganglia circuits for go no go you've got an accelerator or brake basically in your neural circuitry and um kids with Tourette's and O. C. D. The brake doesn't work quite as well. And so one thing that happens is if I wake up in the morning and especially if I'm well rested well if I'm not well rested I do hypnosis or yoga mudra in order to recover my sleep. That works really well. But then once I'm into the process of preparing the podcast I've already gone through my notes. I know what I want to say more or less in a kind of general contour. And then I take a walk and I I try to so no phone with me and I try to assess whether or not my energy is too high or too low for podcasting because when your podcast as you know you have to punch out a lot of material but then there's times when you really need to slow down and emphasize and articulate. And so what I do this is I don't I've never revealed this. What I do actually is I will recite the lyrics of songs for about 10 minutes. Um songs I love while I walk out loud </s><s>[INST] it calms you and focuses you. What does it different. [/INST] I think it gets my vocal cords warmed up and it also do </s><s>[INST] you sing or speak that [/INST] I often sing them uh and unfortunately nobody hears and as I do this I start to evaluate whether or not I'm straining to get the words out or whether or not I'm straining to make them slow enough so that I can articulate them. So there are days when I have so much energy that I trying to speak faster than I should in order to articulate properly. There are other days when I'm tired and I can't sort of keep up with my thoughts and so what I try and do is assess that and then adjust the transmission, the rpm, so to speak. For instance, I can speak very quickly and then I can slow down so I can change the cadence of my voice and when you teach in the classroom you learn as you know because you're an excellent teacher. I've watched your lectures in the classroom as you teach in the classroom. When you want to slow down, every teacher knows, you turn to the whiteboard or chalkboard and you start writing right, it gives you a break and then you turn around and you fire back the kind of machine gun fire of of information and then you slow down or you underline something when you podcast, you don't have that opportunity right? There are no visuals in my podcast. So what I try and do is always get my voice warmed up and make sure that I'm thinking and speaking at approximately the same rate. And then I also do this thing and I put my vision into panoramic vision when I walk, which is very calming and then I actually start to remind myself of the purpose of podcasting. This sounds very mission statement. But you asked what I do. I remind myself first and foremost that what I want to communicate, what I want to come through is the beauty and utility of biology. And I only feel comfortable saying the word beauty publicly now about science things thanks to you because I think </s><s>[INST] love and beauty [/INST] love and love and beauty, but also darkness and hatred. And if you're talking about the lex Fridman podcast, you have to adjust that you have to address the shadow also the shadow side. But I think about the I want to communicate the the beauty and utility of biology and then I check my, my emotional state. I want to make sure that I'm not angry about anything and certainly if I am that I'm going to set it aside for the podcast because that's not a place for for my whatever I might be dealing with. I also really start to feel into the parts of the research and the papers I found that I really love because that's the part of me that I like the most frankly and on the podcast. If there's a paper like for instance, we have a paper, excuse me a podcast coming out soon about um heat as a tool, you know, sauna but some other things and in researching this, I learned so much about um these heat shock proteins and the use of sauna in Finland for increasing growth hormone, but also for the treatment of mental illness. And I realized I fell in love with this literature. It's just a beautiful literature. These people are true pioneers for doing this work. Now everyone's in the sauna, but this was 20 years ago. The way the experiments were done were amazing with all these finished people with thermal couples up their rectum to measure temperature swimming in pools. It's hilarious and great. And so I start to think about it. I think, you know, I just start to really access my love of the work and then when we finally sit down meaning my producer rob and I and record, I just sort of want to just bask in in sharing it. Just like the little version of me when I was six or seven, I used to spend all weekend reading the encyclopedia Guinness book of World Records, making my mother driving me places to introduce me to have this obsession with trapping animals when I was a kid, meet these people. And then on monday I would insist on giving a lecture in class. It was a little kid. So that's basically what it is. I just try and access that that childlike energy. And um so I want to be clear. The goal is always to make the information interesting, clear and actionable. And if it's also surprising then there then that's a bonus. But that's basically the process. But yeah, I'm I'm singing and talking and and getting into state and I used to feel very sheepish about sharing any of this is the first time I've ever shared it out loud. But but Rick was the one who encouraged me to find a process that works and continue to develop that process and not let anything get near that process people in my personal life. No, this and when it's time, it's like, I don't care what else is going on on. I'm I'm moving into that brain state </s><s>[INST] and that's probably a process like that for anything that you do in life that you take seriously. So the people who have perfected this is athletes like olympic level athletes, they have to have a process like this. You [/INST] know what? I think Tiger Woods actually was taught self hypnosis quite young. Um and use self hypnosis often during his tournaments, sometimes too great uh success and other times less. So </s><s>[INST] is there other places in life that you use kind of a protocol, like a mental protocol to get ready? [/INST] Many of the best areas of life are their own form of hypnosis, Right? Um you know that you're in hypnosis if for instance you're in a movie and something happens and you feel the emotional lift with with without being self conscious about it. Um Yes, I think that um one thing that we've tried to do in our houses around meal times to try and set a state that food isn't just something that we just throw down our throats and I'm fortunate that, you know, my partner cooks really well and so I try and give her the space to do that and that's the whole thing of her getting into state and then </s><s>[INST] for the cooking [/INST] cooking, I can just see it. I just see the way she approaches the whole thing and the the pleasure and serving it and and I'm an eater, not a cooker. Um but </s><s>[INST] both are important roles. It could be a very good eater. Like there's something about is there anything better in this world and that feeling, especially if it's a family getting around the table. Just the warmth of that. I don't know, the, it's like the cold [/INST] outside </s><s>[INST] of the cruel world cannot touch you in this place that you returned to. And if, I [/INST] mean, did you grow up eating meals as a family? </s><s>[INST] Yeah. Sit [/INST] down. No television. </s><s>[INST] No. Well, I didn't really have television period outside of meals. [/INST] So </s><s>[INST] most of my time was spent um you know, like a stray cat outdoors, just running around playing soccer. [/INST] I imagine you in this like dirt or concrete lot between two very high rise buildings playing soccer in uh in like athletic gear that you only see in Eastern europe, you know, I have like you come to the States and people wear their athletic gear and you go to europe and you see maybe it's the soccer culture, but you see athletic gear that you just don't see anywhere else. </s><s>[INST] That's interesting. I mean I grew up pretty poor so first of all I was always wearing my brother's who's an older brother brother's clothes. Uh and they were like old uh like my favorite things were american things that didn't understand, it would be like a Pepsi shirt or something and it was just that was the gear and it was like too large for me. But I thought it was the coolest person ever just wearing this fancy like Kanye like type of fashion. [/INST] Yeah, there's something about it, I feel like in in Eastern europe they wear athletic gear where like the guys like zip up. No, that's like </s><s>[INST] fancy stuff that I feel like those are the cool kids, [/INST] like </s><s>[INST] the coolest soccer players, football players that like they were in a league of some kind so they would get uniforms or like or they somehow I always thought anyone who had anything nice had to do something really bad to get it. That that was my way view of the world because like um I guess I didn't understand how it's, it's possible to be rich because most of us were surrounded by people who are poor and then life is beautiful and simple. It's like why do you escape that life? But you still admire the the cool, like uh when we got Mcdonald's, it was like, what kind of world does this place come from? Like who invented this? This is a fascinating view from a child's perspective of like, of capitalism essentially. [/INST] Yeah. But, but the fact that you ate dinner together is really interesting. My parents divorced when I was an adolescent, so then there was a total fracture of any family structure, but prior to that we ate dinner together every night. I was expected to know how to use my knife and fork and you know, it was like a very um, structured thing. I don't know if kids do that now. Um, you know, if I ever have kids, they're gonna do that. And certainly, um, actually on the way over here, I was thinking, I was like, you know, I really wanted a lot of kids, I want to like a whole litter And um, I was thinking if lex has kids and I have kids and like then we can, we can like pit them against each other with jujitsu, this is my chance at redemption, uh, </s><s>[INST] soccer, [/INST] right? They'll all want to be engineers or physicists. Um, they don't want to be biologists. Um, but it, but in all seriousness, I look forward to the day that our, our kids play together. Yeah, </s><s>[INST] I think there's something so that the family dinner, the ritual of the family dinner like, but also the special occasion dinners [/INST] like </s><s>[INST] where there's a little bit more preparation, a little bit more cooking um whether it's on the weekend or for some holiday in Russia. It was the thing that actually I find completely missing for the [/INST] most part </s><s>[INST] in America is there was neighbors, there was a, [/INST] you </s><s>[INST] broke the walls between families much more commonly, like there would be kinda regular characters, like a sitcom almost, you know, if you watch the sitcom, it's never just the family, there's always like other characters that's [/INST] bursting in the door, bursting in the door must start doing that here just to make you feel at home, start showing up. I know where you live. I think </s><s>[INST] people want to respect like uh you know, Michael, malice lives next door to me and I think people want to respect each other's privacy or something like that and I think we all get super busy and you know, like [/INST] it's kind of </s><s>[INST] work to do this uh dinner together or you know, you know, if you see it as a thing that needs to be scheduled, it's work, we'll get busy, there's a lot of stuff going on. But if it's part of a ritual, a part of the culture, the, the, all, all of those walls get broken down and then you realize like that's like later looking back, those are the things you miss, like that's what, that's what life is about, like all the stupid stuff you're doing in terms of career or whatever, all the busy things, those don't matter what matters is the people and [/INST] in academia, you know this change in the last few years of course. Um but one of the great joys was professors will stop by your office or your lab, nobody set set up an appointment. There's a guy when I was a professor in san Diego, a guy named Harvey Carney's member of the national Academy is the, </s><s>[INST] the truly the [/INST] world's expert in the evolution of vision and evolution of brains generally. And he would show up in my lab and he would just start talking to the students and postdocs and I mean in a pure encyclopedia uh and then you at some point you'd say, hey harvey, I gotta go and you have to kick him out, right? Or this guy, he's a physicist. David Klein, David Kleinfeld who is the same way actually David Kleinfeld is interesting, one, he, a student of his went on to create the Beavis and butthead cartoon and one of them is David, he's a physics professor. Now people can look him up and David is one of those guys who just walked into your office and you just sit down and just start talking to you is and and so there's a kind of a family feels like cheers or Seinfeld or one of those shows where somebody just walks in and uh yeah, I think you and I both share a love of the community around things and podcasting is a little bit more isolated. Um I should say for the guest episodes, the preparation is completely different because it's more conversational and so there I don't do any of this business of putting myself into state. I just try to make sure that the guest is um taken care of and I do list out the questions I'm gonna ask before. But those actually really like the interview episodes far more than I like doing the solo ones. </s><s>[INST] I [/INST] just like learning from someone directly because you're asking an expert about something like sitting here with you when we recorded the podcast where you were a guest on the Huberman lab podcast and for the first time. And finally someone was explaining to me the difference between machine learning artificial intelligence and all these other things, you know, and I'm I've finally forgiven you for making me cry about Costello </s><s>[INST] on camera, [/INST] but because it helped me move through it, but but in all seriousness that the interview ones are are a sheer pleasure. The solo ones I really enjoy, but they're they're they're work sometimes. I think like I'm gonna sweat a little blood prepping for </s><s>[INST] that. Well, it's interesting because I do think prepping for interviews is having a similar process might be also very valuable, like I have to I have to think about that because um I think when you do a conversation for several hours, especially when it's a high stakes one, so it's not like you and I know it's more like it's just chatting and [/INST] world order isn't going to shift according to it, although you never know, we can never knowing you will probably be into some pretty controversial topics in a few </s><s>[INST] minutes. You like [/INST] to ride the edge more than there are a number of topics that I just completely avoid. And my response to those is always that I have a lot of opinions about that, but not a lot to say, you know, but whereas you, you've become far braver in terms of the topics you'll encounter and some of your guests have been a bit controversial, right? Some of them are are people that not a lot of that a lot of people don't like. Um and you've, you've been willing to just sit down and maybe it's the jiu jitsu thing, </s><s>[INST] you know? I don't know, it is tricky. One of my goals for this year is to talk to people that a lot of people really don't like. [/INST] Are you going to share with you? And here I am what </s><s>[INST] people like, they're in prison, major political leaders. I've been thinking a lot about how to talk to really difficult controversial figures, but find together something with them that's deeply honest about their nature about the, the ideas they have about the world, like reveal something real and some people, you have to be very careful. Some people are very good at hiding the real inside them even from themselves. That's something I think about a lot, I think about dictators in the past and I put myself in the mindset. Well how do you reveal something real about this person to themselves? I think that to me and you kind of spoke to that. But uh a great conversation is when one where both of you discover something new, like it's not just so I love that too, that's my favorite thing that you mentioned, which is allowing your curiosity to ask all kinds of questions and get excited to learn from an expert, but also to push them to discover something about themselves about their ideas together and then that discovery and sometimes it's uh like we don't see it in the moment, but the audience hears it. It's weird to say like I would compare it to when you're a musician, you're playing with other musicians, you lose yourself in the moment. Yeah, it's all it's like it's working right? It's working. But you don't really ah see the big picture impact of what it's working right? Actually feels like and that's where the audience uh can I could see that, like if you talk to somebody evil uh you know, for me as an interviewer, I have to empathize with that person if I want to understand, I have to put myself in that mind space and to put yourself in that mindset, you really have to become that you have to put you have to understand the evil inside of you, like you have, you can't just think if somebody is in power and has used that power to abuse others, you can't just be a I personally a person who seeks to understand. You can't just be a journalist asking generic questions. You have to put yourself in a in a place where you're somebody who's given a lot of power and slowly you start to abuse that power and what does that person become? Who are you? I have to plug myself into those moments of my life in the past where I've been angry at something ah and where I've been cruel because I was angry in little ways, but then you magnify them at scale and I have to have to go there and that's very human. And then I have to look at another person from across the table from me and understand, well you're there too, and then you had more opportunity to do truly cool things and and then um and then where like you have to plug myself into places where I've been, I can imagine I can go where I was cruel to others and was unaware of it. So, I was in the mind space where I was thinking that I'm doing good and I was doing not good again. I have never got an opportunity to do any of those things at a large scale, but all of us have done it at a small scale and I plug myself into that and then we're here, we're too, if it's somebody who's in prison, if it's somebody who's a dictator were in that space where evil is, is all of us have the capacity to do that evil, and I have to imagine myself being able to do that evil and then we're here together in that dark, dark place. And then if it if it's just write something real, can actually come something from that person's childhood maybe awakening to uh realization that I thought it was a good person and I'm not, and for that only happens when you truly empathize in those moments of discovery are beautiful, but they also happen in science when you just have a conversation and you and you realize uh feel like talking to Stephen Wolfram, I feel like we're constantly realize beautiful things together [/INST] on this element of um you know, evil and sociopathy that you know, young had this notion that we have all things inside </s><s>[INST] us and [/INST] that we all have the capacity to be good or evil etcetera. Um, but I have the good fortune of working with somebody who has deep understanding of psychiatry, but also psychoanalysis and young in theory. And um and he said to me recently, he said, you know, whether or not all people have all things inside them is still debated in the psychology community and in the neuroscience community and as a matter of philosophy, but there are certain people, not many, but there are certain people for whom they've actually lived out many versions of their possible selves in the first person. And so those are unique individuals. And even if they tapped into these things that as you mentioned as a at a more minor level, as opposed to impacting people negatively at a at a at scale. So being able to access those different parts of oneself is key and you've been willing to step into that, you know, my podcast is not one in which we get down to those matters. Um but yeah, you never know. We might do an episode on on narcissism and sociopathy. The other thing that I took away from a conversation with a friend who was a did a lot of years in special operations in the intelligence community. He said, you know, it's if you look at somebody's past at some point, you will come to understand some pretty good reasons as to why they became who they are. But you have to draw the his words, the red line someplace. And what he was referring to was the fact that certain people, at least in the eyes of certain communities deserve to be eliminated as a consequence of their actions, right? Regardless of what drove them to those actions. So that it gets right down to the line between nature, nurture uh neuroscience and the law and justice. Um complicated, complicated themes. I can think of a number of people that um I would love to hear you interview and here I'm not revealing the reasons why, but except for the fact that I think you would be uniquely suited to bring out the important components of the conversation that other people have not been able to do. Which for instance, it Liz Holmes. This is one of the most mysterious and yet disliked people on the planet. Um uh she's sort of synonymous with deception. Um I don't know if there's been any real interviews of her since the whole thing. Um I haven't followed that case. I listened to the book and I um I followed it a little bit because it was happening in my hometown. Right? Theranos was right up the road. The building is still there. It's interesting. It's it's some of the most premier real estate in Silicon Valley, but nobody wants it. It's sort of like it's very hard to sell a home where somebody committed suicide or committed a murder even if it's a beautiful home. I sort of feel like the Theranos building is that building. Um So that would be a really interesting interview. I would love to hear that interview, </s><s>[INST] one of the most interesting dark human beings in science. [/INST] Yeah. And then there will even be people that say, you know, um wasn't even science right? It might have all been deception. It might have been one part deception, one part goal setting mixed in with clearly that there were so many factors impacting what happened. Um, I think the big difference between Theranos and that story and some of the other stories about Silicon Valley where people promised a lot more than they could deliver is they were promising things that were directly related to health and healthcare. People were taking blood tests with the understanding that the data they were getting was important information about sexually transmitted diseases and other diseases and making real world decisions on the basis of that. Whereas if you remember when the iphone first came out and steve jobs was still alive and the phones were dropping calls if you held it in a particular way. And his response was a little flip, he said, hey folks, it's a phone as if like don't get so worked up. But people held him understandably to a very high standard. You know, she sort of, it seemed and I don't know because I certainly wasn't there. It seemed like she sort of adopted this idea that you could get it wrong a bunch of times before you get it right, except if the allegations are true and I think they, she was found guilty. I believe on a number of accounts that a number of the things that they were doing were were impacting real world decision making. So steve's point about the phone is just a phone. Well, it depends on the call. If you're calling 911, then it's not just a phone, right? Um, but in the case of blood tests and disease, you know, that's that's serious. I think that the Theranos case was super interesting to me because of the number of people from major universities and from government that both trusted her. And the number of people who did not trust her and yet either didn't speak up or no one listened to them. It was only in the forensic version of it that everyone said, oh yeah, I knew that she was lying etcetera, etcetera. They were lying. Multiple people involved in those lives apparently, But I have a deep interest in the neuroscience of of narcissism, sociopathy and some of the darker aspects of the mind. So, yeah, maybe someday, maybe we'll do a podcast together and be like in the in the in the kind of early 90s version of talk shows where we darken the lights and we we do it together. You can use your voice because your voice is much more sinister sounding in mind. </s><s>[INST] Uh well, it would be interesting from a scientific perspective of somebody who is a sociopath or a psychopath, how to reveal something real about them. I think that requires not just, well, I don't know what that requires that requires the same skill that it takes to be a good therapists, [/INST] right? And some therapists won't work with sociopaths because um they don't feel any progress can be made. Some therapists will work with sociopaths because for the wealthy ones, they often um they want their money. I think most therapists are good and benevolent, but there's some that will do it just the same way lawyers will work with criminals knowing they're criminals, right? Um, oftentimes because they're criminals. There are certain domains of psychiatry that are more tractable than others. Right? Borderlines are interesting. I should just mention because they have this phenomenon of splitting. So, in the in the world psychology, the idea is that being neurotic is actually the goal. The idea that you could be um, you know, feel something and then work a lot to overcome it or um have some sort of defense mechanism in place, but that's not destructive. That's actually a pretty healthy state to be in its uh provided it's not destructive, psychotic is truly delusional. Thinking about reality. And the idea is that borderlines split intermittently split between psychotic and neurotic. That's why it's called this beautiful work by Melanie Klein that describes this, which I'm just now kind of delving into. But, you know, so the borderline is the person who is like, I love you, I love you, I love you and then truly feels as if they hate you and you become the bad object. Um, Borderlines are challenging for psychologists because of the splitting right. Um, schizophrenics are challenging because of the the detachment from reality and narcissists are challenging because they're often so charming that even the therapists are charmed. </s><s>[INST] I believe you mentioned Carl Dezhurov. Uh well, [/INST] he's definitely not a narcissist, he's one of the more humble people, but he is brilliant. </s><s>[INST] Thanks again to you, you've you've connected us. Um I had the pleasure of having a conversation with him, You had a conversation with him. I really enjoyed it on the podcast. You guys come from the same size from the same place. Uh maybe different journeys, fascinating [/INST] levels. We were post docs together. Carl is truly the Michael Jordan, the Wayne Gretzky, five Children, amazing marriage to it also an amazing scientist. His wife, Michelle manages in our neurology department at stanford, in incredible thinker writer, very kind person, humble. Um speaking of getting into state, sorry, Carl, I'm gonna out you on this. But um, Karl, despite being at the highest levels of science and engineering and a practicing psychiatrist, his office is literally a coat closet with a small table lamp when you meet with Carl, if you manage to meet with him because he's very hard to get to you walk in, you sit down as if you're going through some interrogation and some spy novel and he'll ask you, What are you most excited about lately? And I've got 11 minutes or something and that's a meeting with Carl because he's that busy. But he doesn't have the office with the pictures of the kids, and the the thing and all that all that is kept elsewhere. So in order to get, I asked him why you work in this office, right? You work on light and channels of light, things relate to light of all things here, you are in this dark room. And he said, well this is what gets me into the state of mind to be able to do what I want to do. Very rick Rubin ish, in not that at all the same person, but very similar in that he's figured out the physical space he needs in order to get into the optimal state to do the work he needs to do in this lifetime. And it's very unusual, right? If I don't have a window, I kind of freak out, I can do it here for a while. We're in this black cube here floating in space of course. Um but but I I find that amazing that these, that these people that are operating in this super high level are willing to actually deprive themselves of a lot of conditions. They're not sitting there with, with the secretary coming in offering them espresso every five minutes and things that no, no, no, that's new york neuroscience. I'm picking the new york neuroscience mafia is kind of famous for having all the, you know, tickets to the opera and this and that and they enjoy lifestyle a lot. There is one, there definitely is one, they know who they are, they know who they are. </s><s>[INST] People don't know. Uh Andrew Huberman is from the west coast and now he's just starting wars with the neuroscience [/INST] mafia. They do amazing science. They think they, they love their lifestyle and that's wonderful. But the culture is very different. Um carl and I think Silicon Valley in general kind of prides itself on this kind of um monk like it that says system right? </s><s>[INST] But at the individual scale be deliberate about controlling the environment. I think about that with the conversations too. I haven't been deliberate about that either in terms of controlling the space you're in visually. Yes, black curtains, all those kinds of things. [/INST] There is nothing like the lex Friedman podcast studio 1st. 1st of all, when you, when you do them remotely, I always feel like I'm in a witness relocation program. You only get the coordinates at the last moment and you always get the sense that there are people behind the walls that um, you know, our recording </s><s>[INST] things. Well there there's something about creating a feeling, I have a sense that there's a robot over there. There's, there's several throughout this place. And I think [/INST] I </s><s>[INST] think part of that part of creating a feeling would be having the robots constantly moving around and having a mind of their own because that would most closely put guests and other humans that interact with into a place that's um closest to my mind because it's such an engineering mind and and one where when things come to life, it's a beautiful place to be and whatever that is that could be like art. But to me, robots are art. And so I'm thinking about that both for me and for guests. And I'm also thinking about the difficult guests is to return to You, said Elizabeth Holmes. one person, Maybe a couple of things I want to say, one person I think I would like to talk to is Ghislaine Maxwell. I [/INST] always get afraid right before you reveal these kinds of things and now I know why I get afraid. Yeah, I mean again assuming that she did the things that people claimed she did, they're despicable. Right? I mean these were underaged Children, right? There's just no version of the story where she did the things she was </s><s>[INST] accused of [/INST] doing and is still quote unquote good person. There's just in my mind, right? Um and yet I think there is tremendous interest in understanding like what led her to do all that. So at least for some people, </s><s>[INST] let me say a couple of things. So one is at a high level, let me say that she believes or her current story is is that she's the victim [/INST] of who </s><s>[INST] Jeffrey Epstein, [/INST] Oh my </s><s>[INST] I think I'll just leave that there as as is. So this is these are ideas that you're facing the nature of truth and the nature of the human mind is what it is, and this is imagine folks, if you went into a room with a person that says that, what do you do next? Let me also say that I never or rarely let me say nonsense. Never. I rarely mentioned names that I'm interested in talking to without having made significant progress in already securing that interview. So, people sometimes ask me about Vladimir Zelensky and Vladimir Putin. I do not bring them up lightly in terms of theirs in terms of there being a path, an actual conversation that said something I regret, but I'm not sure I know what to do with it. But in the case of all the people I just mentioned, I haven't been preparing for those conversations, I only start really preparing seriously when it's confirmed because it's such a heavy burden. And one of the things I regret in having mentioned a conversation with Vladimir Putin before the war in Ukraine broke out in the in the past few years is that I would mention it very loosely, very casually and without having really deeply put myself into a place that I'm ready to talk to him. And that that that's a freaky thing because then the internet, um, the the audience in general and just me when I listen back to my dumb self, I think, well, why are you speaking so lightly about these topics? [/INST] I know you've had a long standing interest in talking to him, I think now, you know, uh well, the, I don't understand um how </s><s>[INST] I [/INST] would sit down and have a conversation with somebody like that, but that's not in in the range of my skill sets, right? </s><s>[INST] Or like maybe not in the range of things that you're drawn [/INST] to somehow. Not so much. I mean, I would watch that episode with with great interest. Um well you did an episode recently with this guy who was a former cyber criminal turn stateside, right? I think he works for the government now. And there was a segment in there, remind me his </s><s>[INST] name, Brett johnson [/INST] johnson. There was a segment in there where he talked about stealing a lifetime's worth of collected coins from some elderly woman and this was everything she had. And then he openly admitted that he felt no remorse, which is the way he described as purely sociopathic. And then of course we learned that he grew up in a family where criminal behavior was very common. It was kind of embedded into his notions of what typical behaviors were. And I found </s><s>[INST] myself somewhat [/INST] conflicted, but also hung up, you know, hung up on this idea that, you know, I mean, he was, you know, he had behaved as a sociopath, um or in a sociopathic way and it created a an internal conflict because he's quite charming guest and his stories are terrific. Um especially I really enjoyed his discussions about how he would go out and do all these things out of a desire to please his his girlfriend, you know? So he was in service to other people despite being a sociopath. He could say he was in service to them as a way to extract. It gets very complicated, I think is the reason I went into science is that it, at some level, it's more about facts than it is opinions and judgments. And I don't know that I have the ability to suspend judgment over the away from the kind of top level contours of my initial reaction to like if it's true, like the Glenn Maxwell's and the Liz Holmes and the other sociopaths is one of just kind of revulsion and repulsion, but that could also reflect the fact that I'm not as, you know, neurological sophisticated as somebody that can spin all the plates of of empathy, forget forgiveness. But also um holding people accountable the same time. That's that's work that takes if you think about that's 34 brain circuits having to work in parallel. That's the difference between chess or a game of go and a game of checkers, I guess I'm playing checkers playing chess. </s><s>[INST] No, so one is actually holding in your mind and two is the raw skill of conversation. You're you're very just having listened to your interviews are very good conversation, but the skill of conversation is really tricky. I'm not being self deprecating. I'm being just objective, I'm not good at conversation, I'm working very hard, getting better at it. I'm speaking not about just podcasting, I'm speaking just normal life. I have anxiety from social interaction. I [/INST] do really </s><s>[INST] a huge amount. Yeah, [/INST] so this is interesting because I never detect that in you ever and I think there are people that we both know that have said to me that they too feel anxious and yet your voice is steady. I don't see any perspiration. Um You appear incredibly </s><s>[INST] chilis, I was scared shitless with rick Rubin. [/INST] Rick Rubin is at when you first meet him is intimidatingly calm, but as you get to know him a bit, you realize that his the kindness and the generosity that you sense is real. Um But yeah, I would never, in a million years have guessed that you get anxious in conversation. </s><s>[INST] Can I just make another quick comment that this may come off entertaining to you Andrew maybe you've already gotten the same. Um But having mentioned Vladimir Putin a lot of Mr Zelensky, Ghislaine Maxwell, there is a natural question, how does lex have access to these people, who does he work for, like how is the, who [/INST] works for him </s><s>[INST] for who works for him? What does he have on others this? I'm actually I asked my, when I look in the mirror um just somebody who kind of enjoys conspiracy theories. I want to ask the same question. Like well I usually ask in the following way, like how the funk am I so lucky, like who am I being in my robot being controlled by somebody else? Or like how is this, How is this my life right now? What is happening? It really does feel like a simulation. So let me just speak the to several things. First of all, I have no boss I know I know of nor am I controlled by any intelligence agencies of any nation. We're [/INST] gonna get you a dog lex. I </s><s>[INST] could talk to, [/INST] I'm </s><s>[INST] scared of getting a dog because I would fall in love so deeply. I think that [/INST] next time I'm bringing a puppy, </s><s>[INST] I'm [/INST] just gonna bring a puppy. Just leave it here man. </s><s>[INST] And then you'll never see me again. I mean I love dogs so much but the I was also surprised and maybe um I have never talk to an intelligence agency which is very interesting to me, I [/INST] think that you're aware of because they're very good at communicating, right? But I've been </s><s>[INST] very suspicious on this exact point. That's the downside of kind of being an introvert, having anxiety about social interaction, but then having so much love throwing your way because connect over podcast podcast have a powerful way of connecting people. So people come with you with love that I really love, I appreciate. But I wonder like exactly this question like [/INST] uh </s><s>[INST] like why is this person with a Russian accent talking to me and show showing me so [/INST] much love because sorry to interrupt you again. But um it's what we do um and it's a sign of interest by the way too. Sometimes, sometimes, yeah, I have a colleague at stanford and she said, you know, interruption 75% of the time is a sign of real interest in what the person is saying if nothing else. Uh well </s><s>[INST] you're [/INST] very lovable. </s><s>[INST] Well, that that I [/INST] mean I learned about hedgehog in the fog from you. You know, when I learned, you know, you're very lovable. People love you because you're lovable. </s><s>[INST] I love love Ok, so 100%. And it's I mean, especially here in austin texas, people are so, so amazing. I go just hugs and just I [/INST] love people, but do you want a family? Eventually? </s><s>[INST] 100%. I mean, your I take I take what you said is a challenge uh in terms of having a family with kids and they do jujitsu and obviously defeat you and make you um miserable for your failures as a father because you couldn't are [/INST] you gonna be a great dad, </s><s>[INST] build up an army of good judges of people? But yes, I would love a family. I would love to have Children, but I just want to finish that point because I'm nervous about it. I'm nervous about the way people perceive what you're seeing is a forrest gump type character, like what who I am I seem to be and this is how like the world seems to work is you just try you try to be yourself like you try to find yourself maybe the better way to say it and just be that be kind to people work your ass off and say f you to anybody that wants to control you or to tell you what to do, just be free and then put love out there in the world and doors open. This karma thing seems to work. Uh something like how the hell did how the hell my friends, you now, how the hell did I get a chance to eat barbecue with rick Rubin right? Like [/INST] Doris, have you guys had a barbecue? </s><s>[INST] We had barbecue. Uh He, right of [/INST] course he's from new york. Any new yorker that I know has very high standards for food because bad restaurants don't last long in new york </s><s>[INST] and barbecue Collins says [/INST] oh yeah oh yeah </s><s>[INST] texas barbecue. [/INST] Well you know I would also add that you whether or not you realize it or not you took tremendous risk when we come from the same original community which is academic science right? And to be at M. I. T. And to start posting lectures online is risky right to you know I was third or fourth man in in terms of podcasting as an academic because you had gone on broken many times. David Sinclair had gone on there, you know, the, especially before the pandemic, you just didn't see many academics and scientists talking in a public facing way. So you took tremendous risks, right? You took tremendous risk, always wearing that jacket and tie, right. Um the only time I haven't seen you in that truly is when we rolled jujitsu, which is, and I hear I'm being generous to myself saying I rolled jujitsu and basically you choked me out in front of hundreds </s><s>[INST] of thousands. It [/INST] was, it was, it was great fun and I I thank you </s><s>[INST] for doing that to have a beginner's mind is a beautiful [/INST] thing. I have admittedly, I have not been taking the classes, but I'm going to I truly am, especially should there's a small chance, I might find myself in Austin a bit more often in the, in the near future. But the, </s><s>[INST] well, if you're out in san Francisco, if you're training with Mark Zuckerberg, he just started. So [/INST] yeah, interesting, Sure. I </s><s>[INST] mean, he's actually uh people listen to an episode, perhaps he's a fascinating human being [/INST] listening to it. It's great. You took tremendous risk as an academic to do what you did. So I do believe that when one takes intelligent risk because you can die or can crash your career, you can do all sorts of um self destructive or destructive things when taking risk. You took risks and they paid off, right? And you take different risks at different stages, But I I don't throw around the word admiration lightly. I mean, I admire that you were in this classroom and my team, like I'm gonna film this and put it online. Uh you, one of your early interviews is with ido portal who is very hard to get to. I've communicated with Edo a few </s><s>[INST] times. [/INST] I can't wait to talk to him. I'm dying to talk to him. I was supposed to do some um course teaching with him uh, right before the pandemic hit and then it got canceled cause he couldn't travel. But getting to him is exceedingly challenging. So you do have this incredible ability to get to people um and for them to trust you and know you. And I think it's through your authenticity. And I think it's the fact that you're willing to go places where people haven't been before. You know, that this is what what's the saying about pioneers? How do you spot the pioneers? They're the people with the arrows in their backs, you know, So that's the, you know. Yeah, and and that's actually a quote that I lifted from Terry Sakhnovsky, who's uh, you know, um Terry's, you should talk to Terry. He's a uh, computational neuroscientist down at the Salk Institute, uh howard Hughes investigator, etcetera. But so, you know, taking risks that other people have not taken is that's a real thing. And to do it with integrity and rigor, that's a real thing. And so yeah, I'm complimenting you and I hope it I hope it lands and lands deeply. But I also hope that people will hear that and understand that it's one thing to do what other people are already doing boldly. It's a whole other thing to launch an entire art form or venue. And you did that and you didn't write a book. Hopefully you will someday. But you didn't go write a book. A lot of academics have written books. You went online, Jordan Peterson another controversial character. He did it to all those lectures that he filmed and then he has led to this other thing. So, um, you know, it there's karma and then there's also having the spine to just put it all on the line and do something for which there is no prior example to hold onto while you go through those headwinds. </s><s>[INST] The really fascinating thing is actually a lot of people tell me about you. Andrew Huberman. Mm like the reach of a podcast is really fascinating. It's not the it's not the numbers of people listen. I don't know if that's important at all is what's important, is like the depth of connection you have with certain people. It really moves them. Like a great and like they really get you. So there's a lot of big Andrew Huberman fans that really get you. It's not just the science, It's the stuff between the lines. It's Costello. It's the whole picture of a scientist that finds beauty and biology and reveals it and they love you for it, [/INST] you know? Um because it was on television at the time, I followed that Amanda Knox story pretty carefully. Um and I don't watch television, but whenever I would travel, if there was a tv on the airplane, I would find myself getting wrapped into things like locked up abroad, you know, like and these things where they would make you terrified to travel anywhere, let alone commit a crime overseas. Um you know, the the scenes of some of these prisons are so dramatic and you know, I mean, her case got a ton of interest and then, you know, she went and then I was a student at the University of Washington um and has talked quite openly about, you know, how she was treated and how people assume guilt and you know, and eventually, you know, she was exonerated and you know, we can only go by what we know with the law determined. But you know, these are people that the world is fascinated by. I would, I'm guessing about a third of people have already decided this person is despicable. Why would you ever give them an audience? About a third of people I think are open to or at least interested in learning more about them. And then I think the remaining third kind of the third that the category that I put myself in, which is what can I learn about people and myself, even in my revulsion. Right. What can I learn self yeah. What can I learn about myself from listening to this conversation with somebody that I that I like to think I'm not talking about Amanda here. I'm talking about the other people you're talking about that. I don't I can't relate to write, talk, hearing conversations with and about people that you cannot relate to is informative. Otherwise your whole mind literally becomes insular. Right. </s><s>[INST] Well, there's an interesting thing I also have to um, ever since the war in Ukraine broke up. one of the questions I was asking myself and this is not to be dramatic. It's just a very simple, honest question that I think a lot of journalists that operate in the war zone or documentary filmmakers that every reason they got a chance to meet have to be honest with themselves. Are you willing to put at risk your life for things you do? What [/INST] are you willing to die for? </s><s>[INST] What, what are you willing to die for? It sounds very dramatic, but whenever risk goes up. Um, I mean, I don't know, you you ask that if you want to take out a trip out to space on a commercial space flight, you have to Are you willing, are you willing to die for this for this journey? Now? The odds that [/INST] are really small. I just watched Apollo 13 again, great movie. </s><s>[INST] I'm not going [/INST] to space, I'm not going to space, </s><s>[INST] afraid of heights. [/INST] No, I don't operate of heights. I'm I just, it feels like a feels like a terrible place to die. </s><s>[INST] Yeah. Well, first of all, death anywhere [/INST] is not great. Yeah. Although you know, I have a song teed up in my phone. If my, if the plane starts to go </s><s>[INST] down, I'm gonna spend [/INST] the last few. It's a rare song, nobody knows. It's a song off a b track of my favorite band, which is rance is this thing called the sentence and nobody, nobody. And I love it and I listened to it almost every day. Um </s><s>[INST] ran to the sentence. It's called, [/INST] the band is called rancid famous band, </s><s>[INST] relatively [/INST] love those guys love their music. Um and the song is the sentence. You can only find it on like a B cider out take. And it's, if you don't know how to decipher tim armstrong's voice, then you probably won't understand the lyrics. But um because it sounds very, very fast, but if the plane ever goes anytime there's turbulence, I put that thing and I put the headphones and I was like, well, you know, it's time it's time I'm gonna go out like this. I don't want to drift off into the galaxy just slowly asphyxiating and freezing to death. That sounds horrible. Just like I wouldn't want to drown or get on a plane is okay. Well on the plane. I mean like if that thing starts going down and there's truly nothing you can do. You might as well at least listen to your favorite song. </s><s>[INST] I'll probably go with the pixies. Where is my mind? Like from fight club and just the calmness to sit back Like the musicians playing at the titanic. I [/INST] didn't know you were a pixies fan. I'm gonna have to not, not, </s><s>[INST] not so much a pixies fan. Actually, I should say that I just, that was the where's my mind? It was the chosen song for fight club at the end when the buildings are coming down or something like that. So that the, there's certain songs that just fit just right for the collapse of human civilization and you, you're calmly appreciating like that. That's just it. This is how absurd this life is at any moment it can end. And this is it. This is uh, [/INST] I love how we both have death and demise. Um, soundtracks. It's just a </s><s>[INST] question when you're an academic doesn't come up often. [/INST] That's all, that's, that's idea. There are some academics that are bold and brave. It's, it's not a phenotype being bold and brave in the physical world is not a common phenotype of academics. I mean, the great neurologists, one of my, I don't have any heroes, but Oliver sacks is a true hero. I mean, um, people think of him as a writer, but he was foremost a neurologist and he took tremendous push back from the neurology community for doing his books and his articles, He has a great biography called on the move. There's a wonderful documentary that just came out about him. He died in 2015. I'm actually um kind of a collector of his things. Um but he had tremendous, but he was accused of horrible things until the movie awakenings came out with de Niro and Robin Williams </s><s>[INST] amazing movie by the way. People don't, they seem to not say great things about the movie. I love that. It was [/INST] amazing and it was only once he became famous from that movie that his more academic work started to receive any kind of attention and he was invited back to Colombia and N. Y. U. You know the new york neuroscience mafia is a real thing. Um And yes you know who you are and some of them are actually coming on the podcast. Um They they you know, I </s><s>[INST] think we talked offline about this, we should start a mafia to bat to fight off whatever is going on in the east Coast, although I'm still in M. I. T. So I don't know how that works, but it is different than new york. [/INST] Yeah, so I have tremendous respect for science done in new york, don't get me wrong that they are excellent scientists. It's it's just a very different culture than on the west coast. Um And the personalities, the personality and </s><s>[INST] respect for the [/INST] mob and the personalities are, are a bit more um, grandiose. However, because of some of the shift in science culture in the last few years, things around, um, scandals and things of that sort. Um, they've been forced to tamp down some of their personality or at least their outspoken personality. And I actually think it's revealed something really important and useful in science, which is, you know, it used to be the case. You could really inject your personality into what you do. You know, Richard Feynman is a good example if he did what today, what he did, then bongo drumming on the roof of caltech naked. Um, working out theorems in um, strict clubs and things that he would have lost his job in moments. Right? So that kind of behavior isn't celebrated anymore. It's actually punished. Um, and I'm only half kidding about this new york neuroscience mafia, but because I now exist in multiple realms, I can say these sorts of things and I again, admiration and respect. But I will say that I think it's important that people in science and there are kids that are curious about science understand that you can have any personality provided that your ethical and respectful in science and do well right there. True bench scientists that just want to be at the bench, there are people that just want to be in their office. There are people that um, really enjoy public speaking and there are people that love meetings, There are people that hate crowds and so there's a place for every, but truly a place for everybody in science. I would like to be able to shine light on the fact that there are, you can have shy personality and outgoing personality and you can all of those can be have excellent careers in science, but you have to find the community in place. That's right for you. One reason I like stanford is that stanford is very much about the future, We have no about prize winners, we have fields medal winners and all that stuff and their names are on walls and we acknowledge their great works, but most of what you hear about in the halls of stanford is about what's happening now and what could happen next, It's really about the future, whereas when I spent time at other institutions, not to be named, you hear that, but there's a lot of kind of recycling and regurgitation of how wonderful people are based on things they did previously and the students at stanford because of Silicon Valley, sure, they have respect for Nobel prizes, they're delighted to be learning from and surrounded by all these great minds, but they're mostly interested in what they are going to create and so I kind of uh not kind of, I really like the shift toward possibility as opposed to things that are steeped in tradition, You know, I've never been to high table dinner at Oxford. I'm sure it's a wonderful experience. I'm also not sure what purpose it serves for the world, but I've never been and so I don't know what the conversations are and so maybe I'm you know, speaking out of line here and then now I'm definitely not getting invited, </s><s>[INST] You're you're definitely getting invited. But yeah, I'm with you that the cultures picked picked the right ones for you. That's why I like m I. T. This the spirit of [/INST] it, </s><s>[INST] to me it's not about the past or the future, it's about just tinkering and having fun, building cool stuff like the big ambitious projects. It's there, I mean maybe more in the biology and the house side but like the engineering [/INST] side it doesn't </s><s>[INST] matter if this has any impact. Let us build the coolest thing the world has ever built. [/INST] Well, what there, whenever I'm in Kendall Square, I've seen they have those buildings there that actually tilt toward the ground. These are these the architecture of MIT is also really impressive. Yeah. </s><s>[INST] This he pulled up a surrogate just pulled up your mama's tweet. I'm inspired by curiosity that is what drives me. So let us expand the scope and scale of consciousness so that we may aspire to understand the universe. There's there's like three tweets and one but curiosity. Yeah. Yeah, curiosity for its own sake. [/INST] What's that saying? I think Dorothy Parker said the cure for boredom is curiosity. There is no cure for curiosity </s><s>[INST] and you need to celebrate. So let me just briefly mention to my lovely friends and mitt to celebrate different weirdness to celebrate the weird characters. I've I sometimes get loving pressure from [/INST] my </s><s>[INST] lovely friends at M. I. T. To tone down the weirdness of [/INST] it really, even from MIT. </s><s>[INST] I'm very fortunate to have a lot of leverage to where I have completely resist the pressure, but I'm very sure that there's young faculty that with that subtle pressure would um [/INST] dissolve them into a puddle of tears. </s><s>[INST] Not, no, no, that's right, [/INST] that's </s><s>[INST] right. But it's a slight nudging towards conformity that I think ultimately destroys. Um or at least lessons the the power of the kind of science that you can do when you encourage diversity, diversity in all of its forms, including the weirdness of ideas, the out of the box thinkers, including the flamboyant behavior online. Uh how you choose to educate. How do you choose to inspire, you know, people talk about freedom of speech, but it's not just like freedom of speech to say controversial things. It's also freedom of speech to be weird. Like if you're for some reason fascinated in uh like you look at your mosque, he talks about sex a lot. Let the guy put sex memes up, who cares? [/INST] Like I mean I feel like Ellen can do basically whatever he wants, </s><s>[INST] right? There's no pressure, but there's a bunch of Elon's in the academic world. There's a bunch of uh no, actually, sorry, let me backtrack because the man deserves [/INST] props. He's unparalleled. </s><s>[INST] He's a ceo of major companies. You better believe there's pressure to behave more like a ceo as opposed to a giggling schoolboy who's posting memes throughout the night. But that is him and that freedom, that's what freedom looks like. I talked to a lot of C. E. O. S and a lot of them, I feel like a caged birds who have long ago forgotten how to sing quite honestly. Like they they there's like shareholders and they come up with excuses for themselves. Here's why I have to be this way you have to understand. So on. There's pr there's marketing people, there's lawyers, there's all that kind of stuff. But the final result is the authenticity suffocated the beautiful weirdness of a ceo of a leader of a creator of a scientist. All that that's all uh [/INST] that's all gone well, steve steve jobs wouldn't have um kept his job in acting the way he did in his twenties and thirties in today's climate. But he probably would have updated his his protocols. So </s><s>[INST] maybe, you [/INST] know, screaming at employees. I mean, these are these are anecdotes, right? I call them an IQ data because people treat them as data, but they're they're really just anecdotes. We don't know, I wasn't there. Um But you know, I like the idea of authenticity without over sharing right, you're very authentic. But there are aspects to your life that I'm aware of that your audiences will never be aware of and there are aspects of your life that I'll never be aware of and so you're still authentic but </s><s>[INST] which which ones are you aware of? [/INST] What people are gonna wonder </s><s>[INST] like what what do you think? [/INST] What is this? No no no but interesting but interesting choice of examples. Um No but I think that um you know people lose </s><s>[INST] lose the [/INST] careers on the basis </s><s>[INST] of the [/INST] movement of their thumbs. Right? I mean the chair of psychiatry at Columbia recently lost his position based on a response to a tweet. People can look that up is one of the most famous psychiatry departments in the world. And he put something out there that was very insensitive at frankly. And um everyone that I talked to about it was like gosh that was very very insensitive, not thoughtful at all and he lost his job right? Or at least had to step down. I don't know the specifics. So um you know I think I read someplace that more than half of the job loss due to online behaviors because people were trying to be funny. Mhm. Right. I mean not everyone can pull off with tim Dillon. Oh and by the way, congratulations I heard that you and then just got married no </s><s>[INST] no we didn't just get married, he proposed, [/INST] got it, got it, got it </s><s>[INST] and I said yes, [/INST] right, so some people can get away, thank </s><s>[INST] you, thank you sir. Guy has that [/INST] 13.3000 likes one of those is mine. </s><s>[INST] Uh So for people who are not aware, one of the days in april tweeted that tim Dillon asked me to get married and I said yes, I think tim Uh said the wedding will be on 6th Street in Austin, bring all of your weapons, which of course is totally inappropriate. This is [/INST] this is I was </s><s>[INST] I was like pG funny and he's goes rated r funny right away. But that said, I mean if there's anyone [/INST] I </s><s>[INST] would like to get married with, this is that guy and we would do it in Austin and when it would it would it would be epic, It would be like the the wedding from november rain um one of Mr and mrs mr mr, [/INST] I apologize. Well yeah, and you broke and you broke broke tradition with the, with the jacket color. So it sounds to me that you are a free speech absolutist. </s><s>[INST] I think freedom is really important and that includes letting people who are hateful letting people who are controversial have a voice on platforms, but it becomes, I'm not sure what exactly to think because um I also treasure the quiet voices in the back of the room and sometimes the assholes um silence those voices, meaning by being loud and obnoxious and so on, It pushes away the thoughtful people. So I'm also a fan of creating communities like you should be able to let people kind of build a community that's positive, that's loving or that's constantly trolling or that's uh super hateful. All those communities should have a place in the world. But like the thing I've noticed is that hate can destroy a community full of hate, can destroy community full of love easier than a community full of love can overtake one with hate. And so you have to kind of, I don't know exactly how, but create digital mechanisms that discourage the collision of these communities, they should all have a platform and ability to speak to a large audience, but I just, you have to be careful to protect that like little flame of um of connection that people have. [/INST] That's good, the goodness, it sounds like, I mean the um, yeah, I think you, you, you know, in any great city like new york, which I love by the way, um you want to have a symphony in an opera house and you want some punk rock shows happening on the lower east side, you, you want all of that, you just don't necessarily want them to overlap in terms of social media, you know, and then podcasts and an engagement. One thing that I decided very early on is was to encourage comments and feedback, etcetera, but I have in my mind what I call classroom rules, you've taught in the university and then you teach in the university and there's certain You establish a certain etiquette within the classroom of the kinds of questions that you'll tolerate, right? So there's always the student that's going to ask a question, which is basically a 10 minute monologue about their experience, that really isn't a question that pertains to a lot of people. So you, you politely discourage that kind of question and you encourage the kinds of questions that are likely to be in the minds of many other students. It's just more efficient that way </s><s>[INST] or not politely, which is [/INST] more, um, you know, I try and respond to comments and I try and respond, but also, you know, there's this also this really interesting question now, if you block people or restrict people, people think that you're somehow afraid of the information that they're posting, but that's often not the case. I'm not in the habit of blocking and restricting too many people. Occasionally, we've had to do it only because of how other people are being treated in the comments section. What I can take and what I think other people deserve to take are two completely different things. David Goggins, right? Who we both know. Well, um, I don't know if he still does this, but a few years ago he posted something like if people asked him, when do you sleep, he would just block them because it wasn't consistent with what he was trying to say, of course he sleeps, but it's, you know, he's trying to get a particular message out. I think people should just understand that everybody's pages their own two moderate, right? Just like in a classroom, there are certain rules of course, of institution, but then you establish the etiquette within the context of the kind of class, you know, a class about personality psychology or the psychology of love. You're gonna have a very different range of, of conversations than uh, you know, a class on um, you know, membrane physiology. So I think um social media is a great place for conversation, but it's not necessarily a great place for every kind of conversation. </s><s>[INST] Yeah. And I also just say the people that do get blocked, I never, this is something I do very deliberately blocked or ignored. I never think poorly of them actually explicitly think if there's somebody that's like saying hateful things about me or whatever, I always think positive thoughts, it's not some kind of weird guru thing, but just actually found that as a hack, I I think well of them and that allows me to never think of them again. [/INST] Like I send them </s><s>[INST] my love and like, I think this is a like fascinating human being with a fascinating story. I would love to have time to actually learn about their story, but there's not enough time in the world and I just think well of them and then I move on and enjoy a delicious meal with people that are close to me and I love and so on. It's just and move on and then never adding to the negativity of like just even in the privacy of my own mind thinking of hateful thought towards them, it serves no purpose whatsoever. [/INST] I love that about you and I know that what you just said to be true. One of the, I think more um toxic things in life is what's called, you know, evacuated projection when people feel something and they're trying to evacuate it and project it onto somebody else. Projection is fascinating, right? What you essentially just said is that you don't accept projections and in fact you transmute them to put in the language of the Buddhists. You know, you transmute it into positivity and in that way you, you know, you truly neutralize it. Um and transmute it. I think that if people were better understood when they were experiencing or observing evacuated of projection, um </s><s>[INST] the [/INST] world would be a much healthier and happier place, but it requires a certain stable internal rudder and um you know, when we're tired or sick or angry, you know, we were hungry, excessively hungry. Um all of us are less less good at it. I've been positively struck by the nature of most of the um interactions, not just feedback, but my favorite thing as an educator in the classroom, but also on social media. My absolute favorite thing is when the comments about other people's comments are positively reinforcing. So you see people having conversations within the comments and you realize this is like if you as an educator again, you know, it's fun to teach and it's fun to talk to the students, but the real pleasure is in walking by small group of students on campus and hearing them talking about the material that's like, that just fills me with joy. And because what it means is that the ideas are reverberating in their nervous systems and will eventually work out to others. So it's not just about feedback, it's about a venue for, for parsing information. </s><s>[INST] So you actually posted that we're going to talk on instagram and I collected a bunch of the questions which reminds me of, I have to um mentioned mike jones and a question he asked, but also a gift he gave quite a while ago. If, if it's okay. But first a quick bathroom break, [/INST] Yes, </s><s>[INST] We're looking at Instagram page of Mike Jones Knife and two, we should check it out. He get he uh Andrew gave me a gift from him that is a badass, a butcher knife, yours is the earth dies from Russia kipling. [/INST] Yeah, that's the story of this knife is kind of interesting perhaps to people where it was, I was coming out here to Austin to meet with lex and it was his birthday and I want to get him a gift, but I didn't know what to get him. And I contacted this guy, Mike jones that I learned about through joe Rogan because the first, remember in the old um days of joe Rogan, when you go on the episode afterwards, you take a picture with an object. So it's like Ellen with a flamethrower. People have the acts I picked up this um, bushwacker hatchet thing and I was like, I love this thing and, and joe said, oh yeah, you should check out mike jones's work. He does these beautiful knives. And so then I, I heard your episode with joe and you recited a poem at the end. It was right after your grandmother died and there's a line in that poem from, from if that um mike engraved on that knife for you. So he makes these by by hand. I love the old days before the podcast and </s><s>[INST] that [/INST] was the first time on there. And um it was a lot of fun um in the old, in the old studio in Los Angeles. And yeah, mike makes these beautiful knives and I have this and I just have great admiration for crafts people. </s><s>[INST] So [/INST] do you use it, do you cut your, your one meal a day, sticks with </s><s>[INST] it. I feel [/INST] you're taking it with you on your travels. Exactly. </s><s>[INST] I actually used to keep it on the table, but I thought it's really intimidated guests [/INST] a little bit, </s><s>[INST] but like [/INST] you put it on their side. Yeah. Right. </s><s>[INST] It's like, oops, it's [/INST] trust. Right? </s><s>[INST] What's what's the story I mean? Yeah, but it's because it's not it's it's quite badass if I may say so, The craftsmanship is obvious. But also it is a [/INST] knife. It's got some like dexter like </s><s>[INST] qualities to it. [/INST] It looks like it's designed to to cleave through a limb. If I had </s><s>[INST] like a family or something where people, there's nothing about this place that softens your kind of sense that this might, [/INST] the </s><s>[INST] person might not murder me. [/INST] Well, let's put it differently. Uh, this place could use a woman's touch. There's </s><s>[INST] one way to put it if it's okay. Let me because it is, it is a poem. I um go go too often actually. Um you mentioned reciting some lyrics and I'm actually gonna go back to that at some point to get get a few songs that touch you. But this is one of the things I I go to often I I'll read it to remind myself it's um advice from, from father to son and it's a kind of mantra that it's just nice to live by. So if it's killing me just use this opportunity to one more time read if, by Rudyard kipling if you can keep your head when all about you are losing theirs and blaming it on you. If you can trust yourself when all men doubt you, but make allowance for their doubting too. If you can wait to not be tired by waiting are being lied about. Don't deal in lies or being hated. Don't give way to hating. And yet don't look too good, nor talk too wise. If you can dream and not make dreams your master, if you can think and not make thoughts, your aim, if you can meet with triumph and disaster and treat those two impostors just the same. If you can bear to hear the truth, you've spoken twisted by knaves to make a trap for fools, or watch the things you gave your life to broken and stoop and build them up with worn out tools. If you can make one heap of all your winnings and risk it all on one turn of pitch, and toss and lose, and start again at your beginnings, and never breathe a word about your loss. If you can force your heart to nerve and send you to serve your turn long after they're gone. And so hold on when there's nothing in you except the will which says to them. Hold on, if you can talk with crowds and keep your virtue. I like this one, and walk with kings, nor lose the common touch! If neither foes and their loving friends can hurt you. If all men count with you, but none too much. If you can fill the unforgiving minute With 60 seconds worth of distance. Run, Yours is the earth and everything that's in it and which is more you'll be a man, my son, thank you Andrew. Thank you. Thank you. Mike for the knife. [/INST] I don't know. It's a it's an and engraved in it. Yeah, it's yours, </s><s>[INST] yours is the earth and everything that's in it. [/INST] We toiled over what to engrave. And then finally I just said, mike, just pick something that speaks to you. You're the craftsman. And so he selected that </s><s>[INST] there's certain ways to pull yourself in that book actually. Uh carl dies are all gonna die. Sarath. He wrote the book projections. One of my favorite, first of all, just as you said, incredible writer. Just amazing. Just, I mean, if you wrote fiction, if you wrote those kinds of things, I'm curious to see where he goes with his writing. It's very interesting. I [/INST] think that book took him 10 years to write, which is vindication for me and for you because we're both supposed to write books and we haven't done it. </s><s>[INST] Yeah, I mean, you know, in some sense, you're um, first book will have, you know, decades in it, right? Even if you just take half a year to write it. It's like the first book, like the first album for a musician. I mean, it's a light, it's a journey. It's a, it's a it's a but he uses uh poems and quotes and they're really well, it's [/INST] a beautiful book. It's a dreaming book. I think when people hear that it's a book about neuroscience, they think they're going to get a textbook or a protocols book or something. It's nothing like that. But it really is a deep dive into the mind of the psychiatrist and the researcher and so much feeling and compassion. I love that you love poetry. I mean, I didn't know that until I saw you on Rogan read if um, and I'm not a very rabid consumer of poetry, but I, I'm a big Wendell berry fan. Um uh, and I try and read a poem once every few </s><s>[INST] days [/INST] also. I think if it's a tough act to follow, I mean, that's the richness and the I mean, you said every 3rd line in there is something that you would, you know, you consider your life well lived. If you if you said that right, </s><s>[INST] what about the preparation for the solo podcast, you said you listen to certain songs, you know, you sing or recite the lyrics of certain songs is they're ones that kind of come to mind that are interesting. [/INST] Um yeah, I've always been very lyrics driven and I don't understand music. I've talked to rick about this. I think I've talked to you about this little, but I don't really understand. Yeah, I mean, I can hear music and like it, but I don't really understand the structure of it, but lyrics make a lot of sense </s><s>[INST] touch your soul, [/INST] it's the lyrics, it's not the instrumentals. So I'm a huge joe strummer fan and I'm gonna lose punk points for saying this, but I'm not a clash fan. So he obviously is best known for the clash most clash song start off great and then after about 30 seconds and at least in my mind just kind of disintegrated into a bunch of mush. Whereas um joe strummer and the Mescaleros, which is what he did as an adult, as a you know later. And some of his solo work, he actually rick produced some work that he did with johnny cash, you know rick pulled johnny cash out of essentially out of retirement and had him do his albums before he died. And so anything that strummer did, there's a there's a favorite song of mine by strummer. It's called Burning Lights. Um you can find it, there is an album now where you can find it or Tennessee Rain or some of these things that he did, which are a little bit more folky, so not really punk. So I love that song um a bunch of songs by rancid that I love, </s><s>[INST] you [/INST] know, and then if I listen to instrumentals I do um I'll listen to classical piano, Some </s><s>[INST] dreams are made for Children, but it's [/INST] not gonna sound good as a poem. They can play the people can play </s><s>[INST] the song. Yeah, [/INST] so I'll I mean because it has to be something joe's voice is what makes the song um Joe's voice is what makes the song. But yeah, that song burning Lights from I hired a contract killer or </s><s>[INST] pretty good. [/INST] They're pretty good. I mean, joe is an amazing writer, right? I'm, you know, I'm also a big bob Dylan fan. Um Glenn Gould for classical piano. He was Asperger's, you know, and um and actually I think you can hear him grunting. He had a Tourette's like tick. Um and I learned about Glenn Gould from Oliver sacks. Um so I'll listen to any number of things. It depends on my mood if I'm feeling a little more tired and I need to be amped up. I'll listen to something that's a little louder and faster if I'm feeling kind of keyed up and I need to bring the cadence down a little bit. Um Then I'll listen to something a little mellower popular. I I love bands like um yeah, I'm a big fan of this british pop band called James. There's like 20 bands named James, but this one, you know, and again I lose punk points for saying that, but they're amazing. Uh and best </s><s>[INST] accumulated enough points where you can afford to lose a [/INST] few. Um But in any case, uh yeah, music and poetry are there, they're the they're the subconscious, right? I mean, if you think about a bob Dylan song or a really good strummer song or a poem that the words don't mean anything when read linearly, but they make you feel something they're tapping into the subconscious, that's really what they're doing. They're they're pulling on neural threads of emotion based on either timber or cadence or something that's independent of the word structure. And that to me is the beauty of music and poetry. </s><s>[INST] I often say johnny Cash's version hurt that I say it would be my favorite the song ever. [/INST] We did a 9" nails song Rick produced that, pretty </s><s>[INST] sure they produced it. I mean, he did like the rick produced the, he pulled johnny Cash out from a dark place to produce something that um I mean when you look back as one of the great things ever in music, which are these like, haunting covers of certain songs and [/INST] originals, Johnny Cash and joe strummer did a version of Redemption song together. That is that rick produced, which is um on loop in my house sometimes, you know, for hours and hours. That song </s><s>[INST] is fascinating, bob Marley song [/INST] sung by johnny Cash and joe strummer. You know, sometimes I think what it would be to be a fly on the wall when these guys were doing this. </s><s>[INST] These songs of freedom. There's certain songs where you're like it um elicit an emotion that's unlike anything else. I mean, I was, I was trying to figure that out with with rick to like there's certain songs that make you want to pull up over to the side of the road and just weep or just get inspired to just get shipped done or all of those kinds of things. Remember your family, the people you've lost all that kind of stuff. I mean, hurt, [/INST] I </s><s>[INST] hurt myself today to see if I still feel there [/INST] are certain songs that um I've loved so much that I actually won't play them during a relationship until the relationship passes a certain duration. Because you if you start sharing those experiences with somebody in the room and it starts to become associated with the relationship, you're braiding it in with the dopamine of of love and that relationship ends, the song is forever tainted. There are certain songs that I will never play in the company of anybody else. They're mine. I just think it's too risky to uh to give those up and uh you know, be and I think that um </s><s>[INST] there's like levels [/INST] their levels, right? Exactly. We'll leave it at that. </s><s>[INST] Yeah. And the interesting thing about this kind of preparing for the solo episode, just interacting with rick about that process of preparation. And because you mentioned um with interviews by the way, so you do solo solo, you're the only one in the room [/INST] or No. Well it used to be robbed my producer who um I should say, you know, he's really the person behind the podcast. I mean, we're first of all, we're equal partners, you're just a </s><s>[INST] pretty face. [/INST] Uh we're just um and I'm aging and not to not, I'm actually really, I like I like aging. It's weird. A lot of people like friends with David Sinclair and it's all about not aging, I don't want to live past 90 95 I'm just trying to get as much done as I can in the short life and do it right? And with integrity and heart and accuracy, you know? Um </s><s>[INST] and you like the [/INST] stages, oh yeah, if you read Erikson's stages of development, you realize that every stage of life is a is a is a set of neural circuits trying to resolve a problem and um and if you're going to try and avoid that progression, sure you might live longer. But um you know, it's it's sort of like saying like, do you want to go win the high school, ju jitsu championship? No, you graduated high school a long time ago, right? So I actually look forward to the future. Um even if it means that I'm starting to shift, I think that my biology will shift, you know, I'll fight that, I try and take good care of myself, but um I don't want to get sick, I don't want to suffer who does, But I I'm embracing this whole developmental arc. I mean, we don't we're not Children and then adults, our entire life is one long developmental arc. And if you fail to embrace that you failed to extract the richness of of what it is to be a human being. So, um in any event for the um I record uh rob is in the room. I'll sometimes stop and ask him for feedback if I feel like something's not landing, right? So he gives, if it's clear, he'll let me know if it's not clear, he'll let me know, excuse me. And then, you know, Costello used to be in the room the early days of the podcast, which weren't that long ago, he's snoring at my feet and farting and smelling up the room and we're all just kind of like gasping for areas of bulldog. That's what they do with him gone. It it changed, you know, that the whole thing changed, there will be another dog soon. Um and as you know, I uh I've been moving through that grief process, but having him there gave me a levity that um I miss, but in my mind he's still there, he's still, yeah, he's still there. So, and you know, in time there will be another dog and and who knows, you know, maybe there'll be a dog and a couple infants running around, but that that would be more distracting. So, um but it's there's no podcast that exists just because of the podcaster, this is true for joe that's true for your podcast for me that there's it's not just a staff of people to post stuff, that's just the top level contour, There's the constant feedback and iteration of what you wanted to become and trying to hold on to something that's essential along the way because everything has to evolve. But you can't lose the essence of something any time, a company or brand or a, a course or a scientist has done that. It just ends up terrible. It just as a, you know, it becomes like a senate r version of itself. </s><s>[INST] So to rick is very, the power of the people in the room is great to in, to inspire and to destroy. So you have to be extremely careful with the selection of people that are in the room to me. I never really thought of it that way. I thought only only positive things could happen [/INST] by adding people in by adding people. So I think if they were in an audience in the room for well, you know, that someday I'd love to do a live podcast with you. Um we're just, </s><s>[INST] I saw you doing like a couple of live things, which is great that you're paving the way they're too Well, [/INST] we did one thing I went up to University of british Columbia um, and did a, A lecture on a, on a college campus and one of the more gratifying things that happens this got this kid since early 20s, I think stood up and said, you know, I've never been on a college campus. I didn't think I could go onto a college campus and now I still rings in my mind, whoever you are out there, that meant so much to me because I was like, yes, there was something about that to me. I was like, okay, this it made sense to come all the way up here and do this in person because you can get out to a lot more people online, public speaking events. It's not like it's that lucrative or anything. I mean, unless you're whatever you're famous celebrity or politician or something, I'm sure there are people that do well with it, but that's not what it's about for us, it's really about being able to connect with people in a different venue and for interactions like that. I don't know how many of them we will do. Um but I'm curious to see how it goes, but I'd love to do a podcast with you. </s><s>[INST] Is it energizing? My my fear is the fear of the introvert is that I don't know if I can handle so much love and fascinating people all around. It's like, I don't know, well [/INST] we'll invite a few haters </s><s>[INST] to. Yes, [/INST] but </s><s>[INST] I love the haters too. I don't know, it makes me nervous because Jordan Peterson is currently on tour. I got a chance to hang out with him [/INST] when he does, he does um a lot of lives speaking. </s><s>[INST] Yeah, he does like, he's not on tour where he does like every other day and, but [/INST] he doesn't have any small kids at home anymore. So you know, so yeah, you should do it before. It's also exhausting. </s><s>[INST] I mean, [/INST] I'm just </s><s>[INST] speaking from an athlete perspective, like if you're Mick jagger with the Rolling stones, it, it's just physically, I mean you have to speak potentially for two hours then offstage, like hanging out with people. [/INST] It's </s><s>[INST] a lot of hours. There's a lot of hours to stay focused to keep finding your place of like calmness and exciting. [/INST] Well, and you're staying in hotels, your circadian rhythm is disrupted. You're not getting your like cold and sauna and your workout everyday, your food isn't optimal. Um, I think done in patches. I could enjoy it um, because it's fun to meet people from different places. I'm doing a public lecture in Copenhagen for the Lundbeck Foundation in june june 3rd and that one is particularly gratifying for me because the Lundbeck Foundation is an academic foundation. So the fact that, and so when they invited, I asked, you know, do you want me to talk about what my lab does or do you want to talk about this stuff on the podcast? They're like, no, no, not your lab. You know, we want to hear about this, like health stuff and the stuff that we cover on the podcast. So that was amusing to me and tells me that, um, You know, that things are changing. And I think 2020 and 2021 revealed a lot of things about people to ourselves. But one thing that it made very clear is that there's an enormous appetite for tools For mental and physical health, but also understanding about science and how science is done. So thanks to you again, I'm not saying this to flatter you. It's true gratitude. There is now a a runway for scientists to talk to people. I mean, you had the I always forget this guy's name, the virus guy from Columbia. Yeah. Amazing. Right. I mean, forgetting the controversy around the all the stuff of 2020 21. I mean he is an encyclopedia of all things virology. </s><s>[INST] People should listen to his podcast this week in virology is also an incredible lecturer and educator. It's uh it's fascinating. It's fascinating when people take again that leap of putting all that education online. That's non controversial at all. It's like everybody there, people should go listen to him for the most part in terms of at his best. At least there's no politics in it. There's there's there's no, no, [/INST] no. He's a virus jockey. He likes playing around with bacteria and viruses. And </s><s>[INST] but that said we [/INST] all </s><s>[INST] we all say stuff carelessly all the time. So he he gets in a bit of trouble on some of the things you said about like dismissing lab leak theory. Like and there's no [/INST] way that </s><s>[INST] Yeah, but not, he's not making folks uh there's a difference when you say stuff like off the cuff and when you say stuff that's like courts your principles and you've thought about it for a very long time, you're talking out for hundreds of hours and you can just say stuff, you could just say your opinions um will smith. I [/INST] was wondering, okay, wait, how long have we been recording? I was wondering how long it was going to take us before someone? </s><s>[INST] No, [/INST] no, will smith. I was wondering whether or not we make it then I had it planned, I was literally in the back </s><s>[INST] of my mind, I [/INST] had it planned that at the end if we didn't talk about the Will smith chris rock thing that I was going to say, it's amazing. This is the first conversation to happen in uh in a long time where it wasn't mentioned. No, here we go. Here we go. It revealed some interesting things about um human beings, impulse control and lack thereof. But um you know, oh my goodness chris Rock has a material for the rest of his career. </s><s>[INST] Yeah, I think he's he's not short on material, but I [/INST] do see </s><s>[INST] if I, if I knew what I wanted to tweet, if I knew you're a lot to just slap comedians. My conversation with tim Dillon would have gone very differently. People are just being humans. There's so much fascinating human nature on display there. It's also in terms of it coming becoming a topic that a lot of people are talking about versus the war in Ukraine, for example, is also fascinating to watch. Like just these kind of new cycles moving through and [/INST] I think if I may I start to interrupt, but um you know, anytime we observe something very limbic, very emotional, you know, we generally can empathize someone, right? We all know what it's like to feel angry, we all know what it's like to feel ashamed. We all know what it's like to feel shocked images of war are for most people very hard to relate to. We see it. It's, you know, these, these images and they're very traumatic and challenging to look at at times and yet most people have no idea what it feels like to be shot at or what it feels like to have your home destroyed or what it feels like to be um uh an aggressor in that way. So it's very so I think that people naturally orient towards things that feel familiar to them, even though the circumstances are different </s><s>[INST] and people also forget they look at these celebrities, it's just like looking at criticism of will smith, you forget that they're human too. That's that's one of the most surprising things for me having done this podcasts and met celebrities and stuff like that. They're human, they're all human and that's inspiring to me. Like some of these great folks that have won Nobel prizes and build some cool things, they're just human, like the rest of us [/INST] well, and if you look at actors and actresses, I mean, there's some amazing ones, right? And who also do well in their outside life, but their careers were built on the business of pretending to be other people, and that's got to distort maybe, positively, but also, just, let's be honest, what is that? The neural plasticity there, the changes in the areas of the brain that represent personality have to be quite different for somebody who pretends to be lots of different personalities and gets paid for it, you're working the reward system into the system of self identity, and, you know, you have to imagine that that can really um contort somebody's neurology in ways that maybe they are not as, maybe they are not in touch with reality in the same way that we are. Remember earlier, we talked about neurotic versus psychotic, you know, they may be more borderline in their kind of ground state than than we think, and so I'm actually impressed anytime there's a celebrity who doesn't have a messed up </s><s>[INST] life, I'm [/INST] like, wow, you know, finally somebody who's managed to, you know, maintain some semblance at least from the outside of, of normalcy. </s><s>[INST] So, first of all, I can empathize with the actions the will smith did, right, they're not, I think they're kind of not, kind of, they're just shitty. You should probably talk privately man to man. Um Not because otherwise it's like a dramatic display. It's like it's almost like you are a fake act, you're acting [/INST] well. There are all these questions, right? I mean obviously it was aggressive at some level. There's this question of whether or not it was impulsive. I think most people feel, yes, there's a question, there was a protective nature of it because he was doing it to, you know, apparently in defense, but then there's also the the context. He lost touch with the context, right? Um Whereas chris rock basically gets um there there's the possible critique that he went too far that's going to be in the eye of the beholder. Um but then depending on how you view comedy and jokes, but then there's also the fact that he took that slap and then just snapped right back. So much so that people thought maybe it was faked. He also waited with his hands behind his back. </s><s>[INST] That's just natural. He likes to stand like that. I mean, I um the I got a little bit of a story here to connect to what chris rock did. Like I I wish what chris Rock did in terms of just taking this live and keep going. First of all, just props for somebody that's able to maintain cool in that situation. For the most part. I think I like watched it once. You [/INST] only have to be alive on this planet to see it. You can't avoid seeing it. </s><s>[INST] I wish at that afterwards. He would sort of say something loving and kind to will smith and his wife and then hit him real hard, lean [/INST] into the joke. But there, I think in hockey they call taking a number of a friend who plays hockey and their society that like if someone checks you really badly in one game, you don't go and check them again, you don't get into a fight. But three games later you like you blade them in the shin like you. So what the ability to defer and to handle it in whatever fashion one feels, isn't there probably also </s><s>[INST] friends and all those kinds of things that they respect each other so he probably didn't, but there's a comedian instinct. I saw this, I was in an open mic in here in texas, I won't say where there's many open mics, you [/INST] know, </s><s>[INST] so there, there is more sort of rougher [/INST] kinda. Yeah, you've been hanging out in like west texas. Exactly. Austin's too tame for lex. So he's like head to west texas. Exactly. </s><s>[INST] I put on a cowboy hat and instantly became a cowboy hat and talking like a cowboy. I mean I belong out there in the desert. [/INST] He's gone from eating, you know, meat and athletic greens. So rattlesnakes, rattlesnakes, you're exactly, </s><s>[INST] no, there was an open mic is late at night and this. I was one of the only people in the audience is a couple of drunk folks, a few drunk folks, one of them was a couple and like bikers like uh with helmets and so on. A guy and a girl. And then the comedian, the open mic comedian did a joke about people who wear helmets, I don't know if it was on purpose or not, but he did the joke and then the guy about women who wear helmets and the guy is this exact same situation. The guy stood up, walked up to him. There was no slap. It's so interesting because this happened before the will smith thing. So he walked up to the uh to the comedian and and said he like, he, he, I think he liked pointed his finger down and told him to stop or something like that. And then sat down, this is an audience of like six people, right? And, and uh at midnight around then there's no nobody, no security, nothing in texas in texas, which [/INST] implies then this </s><s>[INST] guy was the energy drunk but also a biker and has what he felt his lady was now attacked by the comedian right with his words. And this and the comedian was a kind of out of shape small guy, this is not threatening at all and probably in trouble. And the comedian after he sat down, he looked a little bit scared, he paced back and forth and then he did the joke [/INST] again, </s><s>[INST] wow and I was sitting and I started I leaned back and I just did this like, because that is comedy and the guy was ang getting angrier and angrier and he just sat there in and the community went on for a couple more minutes and then did another bad joke. But another joke about him, it's just like he leaned into it, [/INST] if you go to a small comedy club open mic or otherwise you're in the shooting gallery, like you're basically they're teed up as a pin to get it. We went and saw Andrew schulz in in san </s><s>[INST] Francisco in san Francisco. [/INST] Yeah, it was hilarious, it was amazing. I mean, he's he's </s><s>[INST] just [/INST] masterful in his ability to command an audience, you know, and but I felt for the people up front, but you know, no sympathy either because you know, you buy tickets to sit up front, asshole's show, you know, you're going to get it, but he was very loving </s><s>[INST] and funny. First of all, it's funny, the funniness really helps you, but the the ethic of the comedian is like that fearlessness, what I really liked, this is like the the danger, there's risk to comedy and there's also consequences. Have [/INST] you watched that show? The um what is it, the marvelous Mrs Maisel show, It's really good. Um I watched a few of them um guilty pleasure there, she plays a comic in the I think it's the mid 19 sixties in in new york. And um and there's a character that somewhat resembles Lenny Bruce was sort of meant to be Lenny Bruce. Um and they're always getting arrested and this and this kind of thing. I think I learned about it from joe. Anyway, it's the writing is great, it's very funny. Um but yeah, comedy is designed to push boundaries right and to get and to say the thing that you know, other people aren't feel, they can't say not something in science, right? Science you're supposed to etiquette is a big part of how you communicate ideas. It's about constraining communication. This is something I mean I confess on the podcast in the goals of making it clear uh interesting, surprising and actionable. You know, you have to constrain the amount and the style of information otherwise it becomes something else altogether. Right? </s><s>[INST] I saw Sandra Bullock, I google Ceo said that he likes the thing you mentioned not the yoga needle, but the I. N. S. D. Are not sleep, deep breath podcast over meditation. I don't know if you saw that. [/INST] I saw that. </s><s>[INST] Yeah. Why what do you think that is? What do you think the differences? [/INST] Yes. So non sleep depressed SDR is an acronym that I coined because it encompasses a lot of practices that are not meditation per se, but that bring the brain and body into a state of relaxation and focus. So hypnosis is one variant of NsD are there are other variants of NsD are you can just look this up and you'll find them and I think that they've caught on and that the google um the ceo of google uh is an avid practitioner of N. S. D. R. Because it has this amazing ability to reset your energy levels and focus. Whereas with meditation, many people find meditation hard and part of the reason they find it hard is that it requires focus. N. S. D. R. Is a state which is very calm and relaxing. You don't have to work too hard, you're just listening to a script. Whereas most forms of meditation, not all but most forms of meditation involved cranking up the activity in your prefrontal cortex and trying to see your thoughts as opposed to thinking your thoughts or um focus on your breath. But then third person ng yourself in some respect and that's work. And so many people who meditate quite intensely feel more exhausted now that doesn't mean that meditation doesn't have any utility but it's distinctly different than N. Str. And I think that people are working certainly the ceo of Google I have to imagine is working very hard and using his forebrain if he's gonna have 20 or 30 minutes to take a break. he should and I think this is what he's doing, he should go out for a jog and not listen to anything and just kind of let his mind wander or sit there in a chair and just zone out or do N. S. D. R. The problem is people are not that good at shifting states. We are all actually pretty good at even people with severe A. D. H. D. We had an episode about this can become hyper focused on things that they actually enjoy because dope. And most of the drugs designed to treat A. D. H. D. Are drugs that increase the levels of dopamine. So when you like something there's dopamine release and you can focus its when you don't like something that's hard to focus. Shifting states is hard. I'm sure you've experienced this. If you've ever been in deep research or podcasting, podcasting and then all of a sudden you go for a run. You probably spend the 1st 3rd of that run thinking. And then in the middle third you're kind of that thinking is is fractured a bit. And then in the final third is where you finally get to relax because the brain doesn't shift states very quickly. We can go from sleep to wakefulness quickly. We can go from wakefulness to sleep quickly but we don't shift between different states of consciousness. Like a step function. Mhm. Except in rare cases right. Fear is one all of a sudden we hear an explosion right now it's a step function. We're in fear or were in alertness right? Um heightened state of alertness. But N. S. D. R. Is terrific at allowing people to learn to shift their state. And I actually would venture to argue that part of the value of meditation and exercise is the actual state that you get into in deep meditation or exercise. But just as valuable is the transition that you have to take yourself through from one state of mind to the other and then back again when I look, you know, David Goggins, he always seems to come up. But he because he represents so many important things, drive determination, override of emotional state Going from being a £300 plus person to a fit person through. He's never revealed anything substantial about what he ate or what he didn't. He's basically says like listen, run a lot, eat less, right. Um but what's remarkable is so much of what he says is about those transitions about taking oneself from a state of I don't want to to scruff in oneself and like you're gonna do it anyway and then being able to carry that into into regular life, so to speak. So I think that um SDR is immensely powerful. It's zero cost. And one of the reasons I'm such a fan of people doing it is that most people don't stick to a meditation practice. There's also been a few cases you might find this interesting, there's a book by scott Carney, I forget what it's called. I think it's called the transcendence trap or something. I'm gonna have that title wrong. But there have been a fair number of cases of people that go and do very extensive meditation, silent meditation retreats who then return to normal life and end up killing themselves. There are states of mind inside of extended meditations or silent meditations that are very beneficial. And I'm certainly not suggesting people don't meditate, but I know at least one person who came back from one of these long extended meditation retreats and wasn't able to shift their state back into one that was functional in regular life. And that book includes a very dramatic story. I don't want to give it away in case people um check out the book. But Scott told the story to me directly once where so someone feels they have reached enlightenment and then commit suicide. So these very unusual brain states are potentially hazardous if people can't return from them. </s><s>[INST] So it's it's nice to focus not on those brains states, but instead on the shifting [/INST] right I do. This morning I woke up a little bit earlier than I would have liked. I used this reverie app. That's research backed R E V E R I dot com, there's a free version of it and or you can try it for free. So I feel </s><s>[INST] that hypnosis [/INST] for hypnosis and I do a self hypnosis to put me back into sleep and if I can't sleep, just put me into a state of deep relaxation. I would I would put hypnosis under the category of NsD our yoga mudra under the category of NsD are there now some N. S. D. R. Scripts online? If you just go to Youtube that are you can just listen to and </s><s>[INST] do you like those? [/INST] I do, yeah. I think the one from Made for is quite good. I have an affiliation with them but it's free. So I feel comfortable mentioning it. I do. I I really like the reverie app. Um I can vary and as you the more you do them, the more quickly you can shift your brain into a state of deep relaxation. I will sometimes stop mid podcast if it's sometimes our recordings to go 78 hours and I'll stop and I'll do a one minute hypnosis. They have one minute hypnosis. Inside reverie you're only going to you're only going to find that one minute hypnosis is effective if you Are routinely doing 10 and 15 minute hypnosis. In addition to that meaning, I do it every other day or so. 10 or 15. </s><s>[INST] So there is there a Youtube one minute hypnosis. [/INST] There are but inside of reverie as well you can find them online a really </s><s>[INST] good [/INST] um Yeah so reverie is good. And then Michael Sealey, S. E. A. L. E. Y. He has some long hypnosis scripts. But again these are all free and you know there's a lot of good research now on the neural networks and it shifts your so called default network, the default mode network, it shifts how much of your forebrain you're using. And it also is very, very good if you, I get so many questions about, hey, I'm really upset. I found out about my girlfriend's sexual past or hey, I'm so upset. I found out that my boyfriend was cheating or oh, someone so died. How do I get over these emotions? How do I deal with them? And hypnosis has shown to be very useful for people to learn to bring themselves into a state of deep relaxation to literally project in their mind's eye. These very intense things that they don't like. And then for people to associate with other emotions in their body to learn to be calm while feeling your feelings to dissociate the mind body communication to some extent, just observe the feelings, observe them and start to associate them with positive experiences. You're an android guy so soon it should be available on android and </s><s>[INST] then it doesn't exist for me. [/INST] Yeah, I know, you know, I don't get </s><s>[INST] android is the device of the people. All you elitist people with your iphone. [/INST] But tell me this about android now now you want to, this is the one thing that gets me because I'm very close to someone who uses an android phone. I feel like that. </s><s>[INST] So you, you have great people in your life that's good to know [/INST] know the messages always look green to me, but I answer yours despite that. Um but they, I feel like the android phones are very trigger happy, like anything I touch does something whereas the apple phone is kind of built for like a Macaque monkey to be able to operate, which is great for me because I'm more of a Macaque monkey and you're a more sophisticated ape. I think like you have to be </s><s>[INST] more sensitive. You [/INST] have, you have, you have, you know, I mean I've got fat fingers, you know, clumsy fingers, </s><s>[INST] you know the android is too well, maybe you need to soften your touch. [/INST] What I would do is go into the most sort by most popular um because there's some older ones that I really like and it generally skills with that. So I'll do the this one, the hypnosis for clearing subconscious um negativity, that's an hour long one, the sleeping anxiety 1 40 minutes. But those you listen to as you fall </s><s>[INST] asleep as you fall asleep, [/INST] we're going to do this now </s><s>[INST] let's listen to it. [/INST] And I have created this hypnosis recording for you to help you and </s><s>[INST] this is the voice. How often does the voice pop up [/INST] and at the same time you don't watch it, you just listen to your anxiety. Now. One of the most important things of any self hypnosis experience is to know and understand people really should know that stage hypnosis is about the hypnotist getting you to do things you wouldn't normally do self hypnosis which is what we're talking about here reverie and this is about you getting your brain into the state that you want. And um again I mean there's a ton of neuroimaging data and work on trauma and pain relief. And our labs are working on this with David Spiegel's lab. I really encourage people to explore Nasdr. And if this feels a little too wacky and out there then I would just put in N. S. D. R. Into Youtube and there's some good honest er scripts. </s><s>[INST] Yes that's by the way, uh Sandra is a is a fan of your podcast that's okay, we don't [/INST] need to play. Yeah so I don't know him and uh but I would get a lot of media outlets picked up on his love of N. S. D. R. And I have to imagine running google involves a lot of juggling a lot of </s><s>[INST] he's one of the great ceos because everybody loves him. Everybody loves him. Have [/INST] you interviewed him? </s><s>[INST] No but we'll do the interview eventually. So is this annoying thing about me being a stickler for three hours Ceos don't seem to understand. Like not understand but it's scheduling. So what happens is Saunders said yes definitely let's do it. I'm a fan of podcasts as a fan of yours. And and and then he goes to his executive assistant like oh let's find a slot and then they immediately think, alright well one hour, [/INST] that's good. Five </s><s>[INST] minutes, 90 [/INST] minutes, 90 </s><s>[INST] minutes. Yeah, right well no they know in person I'm sticking on that but like it's like no we need more and it's so hard to, to do, [/INST] you still travel to do your podcast or general, </s><s>[INST] most people come down here, most people uh but for certain situations obviously um like if you're in prison right or you're ahead [/INST] of you get out on work for a lot of people have anklets so that they can go down the lex Friedman pocket. That probably happened. Have you ever been in a prison? </s><s>[INST] No, [/INST] you know </s><s>[INST] either visitation or on the inside [/INST] from my hike I can see san Quentin, it's really weird that san Quentin and Alcatraz, you know Bay Area beautiful. Everyone thinks like you know like there's the bay and there's a Alcatraz and san Quentin sitting right there. Um you know it's amazing how easy it is to overlook that they're there and forget that they're there. But when I drive by san Quentin I think about it. Um I also think about the people who are in there who might be innocent. I've seen some of those episodes on Rogan and elsewhere. Amanda Knox talks a lot about this right? Whether or not you believe her story or not I happen to believe her story personally based on what I know um what, you know, I'm sure there are people disagree with me. I think to myself what it must be like to be in a cell and know in your hearts heart you didn't do it, you know, I mean I can't think of, I can't think of many things worse, I can't think of many things worse. </s><s>[INST] That's so clearly unjust. But life is full of unjust. Things like this, cruel things happen all the time. You lose a loved one for no good reason, you lose your job. Um you lose your home. Yeah, I've been talking to a lot of refugees now and the war in Ukraine has really focused my mind to how much suffering there is in the world and so just cruel things happen all the time and and people kind of there's this suffering and you you kind of go on, you stick to the people really close to you, there's still love all around you, traumatic events kind of focus your mind on this. Like very practical. Like okay, how do we solve the problem? How do we escape? Let's salt, like survival food, shelter [/INST] focus. Remember that book. Um all's Quiet on the Western Front by World War One. There's this line in there. I forget what it is about how war is like the smell of a skunk like a little bit is actually a little bit is slightly um there's something slightly delicious of it is what it says in the in the book. Um I happen to like the smell of like ferrets and skunks and things. I had a pet ferret when I was a kid, and I like that musky scent. People, most people just it's repulsive to them. It's actually a gene, believe it or not, Some people have the gene that makes that the musky scent repulsive. Some people love it. Um Let me ask you this, there's another gene, this is a fun one. Um microwave popcorn smells good, neutral or disgusting to </s><s>[INST] you. [/INST] There are people who have a gene that leads them to the perception that the smell of microwave popcorn that you find is good, it smells like putrid vomit to them. It's a particular gene variant, and they can smell certain elements within the microwave popcorn. Um It's pretty, it's prominent in France the this gene. And um so in laboratories where uh you have a lot of french people, it's often said like, you're not allowed to make microwave popcorn smells putrid, disgusting, you know, so a lot of it's in the perception of the beholder, right? Uh </s><s>[INST] But, okay, well, before I leave, the N str is uh focus in general, he said, it's for shifting mind states is their advice you have for how to achieve focus on a task. [/INST] Yes. First of all, we have to distinguish between modulators and mediators and I'll do this very briefly, there are a lot of things that will modulate your state of focus, but they don't directly mediate your sense of focus. So for instance if right now a fire alarm went off in this building, it would modulate our attention, we would get up and leave, it would be very hard to do what we're doing with that banging in the background at least at first. So it's modulating focus, but it's not really involved in the mechanisms of focus right in the same way being well rested when you sleep, your autonomic nervous system that adjusts states of alertness and focus and calm works better than when you're sleep deprived. So if you're sleeping better, you're going to focus better. So I always answer this way uh to a question like this because the best thing that anyone can do for their mental health, physical health and performance in athletic or cognitive endeavors or creative endeavors is to make sure that you're getting enough quality sleep, enough of the time for you and that's going to differ. We could talk about what that means now in terms of things that mediate focus without getting in the description of mechanisms because we have podcasts about that, it's very clear that mental focus follows visual focus provided that you're a sighted person. Mhm. Much of the training that's being done now in china to teach kids to focus better, literally has them stare at a target blinking every so often but really training themselves to breathe calmly and maintain a tight visual aperture when you read. You have to maintain a tight visual aperture, you're literally scrolling like a highlighter in your mind's eye right, it's kind of obvious once you hear it. So for people that have problems focusing sleep well learn to dilate and contract your visual field consciously. This can be done if you practice it a little bit and then as I said before it is very hard to get into a state of focus like a step function immediately like snapping your fingers. What you can do is you can pick any object but ideally an object at roughly the same distance, placed it roughly the same distance to which you're going to do that work and stare at it. You're allowed to blink and as your mind starts to drift every once in a while to understand that's normal but try and narrow your visual aperture and bring that into your Visual field so that that's the most prominent thing. Kind of like portrait mode in your phone this would look very different in portrait mode than it would in just a standard photograph mode. And then after doing that for 30 to 60 seconds moving into the work that you're about to do and really encourage yourself to do that. If you're somebody who's low vision or no vision you're gonna use your ears to do this braille readers have trouble focusing sometimes because they feel other stuff and they hear other stuff so you learn to adjust that aperture consciously. And then of course the pharmacologic tools just enough caffeine but not too much right. Um We talked about white noise, brown noise music or no music really varies, but it's very clear that binaural beats of 40 hertz can shift the brain into a heightened state of focus and cognition. So if you're going to use binaural beats, which should definitely be used with headphones and there are number of free apps out there and sources uh 40 hertz seems to be the frequency that best supports the brain shifting into a particular. </s><s>[INST] Can you give us the some some some some binaural beats? [/INST] Yeah, so you're gonna look for, you'd want to find uh an app that offers 40 hertz. I think brainwave allows you to slide bar up to the particular frequency that you want. And I should say that um there are other frequencies that are interesting but 40 hertz, binaural beats seems to be the one that there's the most quality research </s><s>[INST] on, it's like, it's like it's like a beat. Um But you're you're saying there's a lot of mixed science on the, on the Yeah, [/INST] you really should be doing this with headphones because binaural beats are best accomplished by feeding two different frequencies to the two years and then you have what's called the brain stem area that reads out what are called inter oral time differences and then it extracts the the delta essentially and then in other things that can enhance focus. So you know the pharmacology around this is pretty interesting things that tickle the dopamine pathway in the acetylcholine pathway they work. Um There's your riddle in your Adderall or modafinil which are prescription. And there's a lot of nonprescription use of those prescription drugs not so much in my generation But in people 35 and younger. You know I hear all the time from day traders and programmers and stuff and kids that play video games. A lot of Ritalin Adderall use. I think that unless it's prescribed by a doctor for a specific purpose of A. D. H. D. I don't think people should go that route frankly hits the dopamine system way too hard. Also has a number of negative effects on sexual side effects. All sorts of things that you just wouldn't want. There are a few compounds like alpha GPC um 300 mg to 600 mg of alpha GPC with a cup of espresso if you're well rested you're like a laser for 90 minutes, maybe two hours. But then it's going to taper off and you have to just recognize that and then there's this whole world of new tropics now and people trying to figure out the wrasse items process items and phenyl ethyl amine combined with this and you know it's not quite in the place where you'd like it to be, there are a few companies that are doing this better than others. We talked about some of these on the podcast, but um I would always start with behavioral tools and then consider pharmacology and, and then I suppose the other thing for focus is um this is a little more esoteric, but we cover this in an episode on workplace optimization. Um where you place your screen is important, staring down at a screen is not going to be as effective as placing it at eye level or above you when the eyes are up literally and your eyes are directed forward or up the brain stem centers for alertness are activated when your eyes are down. It's actually your, your sort of, it's like being pulled under water a little bit in the autonomic arousal sense. It's you're closing your eyes. I mean um is one, it reflects the brain stem centers that are active becoming less correct for alerting. Excuse me becoming less active, but there's a really cool effect that's active in this room right now, which is that there have been some really interesting studies that when people work in small compact spaces or wear a hoodie or a hat that can also improve focus like blinders on a horse for obvious reasons now based on what I said before, but also analytic work or the kind of work where there's a correct answer that you're seeking is best supported by these kind of low ceiling environments. Whereas there's something called the cathedral effect which is when you work in an outdoor environment or a high ceiling environment, it lends itself to kind of </s><s>[INST] pun [/INST] intended kind of loftier ideas and more creativity. And that probably has to do with the fact that there's a natural tendency a reflex to expand your visual field in these high ceiling environments, expansion of the visual field changes the way the brain works in the time domain, your engineering and biology oriented listeners will understand this for the music. For those that don't, the best way to think about is when you have a narrow focus portrait mode on your phone or your very alert, you are fine slicing life in time. It's like a think of it as a high frame rate, like you're shooting in slow motion when you have a, when you dilate your your view, you're taking bigger time bins. And that one way to just let this hopefully land home is that if you've ever had a really exciting day or podcast interview or experience of any kind, your system is flooded with dopamine and norepinephrine alertness and motivation. All this excitement. It seems like it goes by very, very fast and yet when you think back to that, it seems like a lot happened, this happened and that happened now. Think about waiting in the doctor's office in a blank waiting room with no interesting art on the walls. It feels like it goes by very, very slow dopamine and norepinephrine at an all time low. And yet when you think back on that experience, it's as if nothing happened because you were you're parsing time differently. So those are the roughly the tools and the and the neurochemicals around time perception in the time domain. Uh There's a wonderful book. I'm forgetting the title. So wonderful. I forget the title by Dean Ambrose romano from U. C. L. A. But I think it's called The Brain Is a time machine that talks about this expansion and contraction of the time domain and what you can do to leverage it for work and creativity. Focus. And so </s><s>[INST] yeah, it's fascinating that I think one way to define focus for me is uh to the experience, the feeling of focus is losing track of time is getting to a place where you're no longer on operating in [/INST] time well. And you mentioned being, you know, kind of cramming for for something, well you'll release a lot of adrenaline and you know, it is true. You can get a lot done under pressure because of the way that you're slicing time, you don't actually have more time. It's that you're finally in a brain state that lends itself well to parsing information really quickly. Now if we ramp up your level of stress enough, it's definitely uh you know, it's a more or less normal distribution. We get you stressed enough. It's hard to remember anything you're not parsing time well. But even that middle range, almost every study shows that the higher levels of autonomic arousal meaning norepinephrine and adrenaline in your system, the more effective you are at things and we, you know, we always hear stress and adrenaline, it's just bad, bad, bad. But my colleague ali Chrome at stanford has done these beautiful studies where if you just educate people on how adrenaline makes them sharper thinkers, they become sharper thinkers. If you educate them on the fact that stress makes your cognition worse, their cognition gets worse. This is why I don't wear a sleep tracker. If you tell people they slept poorly your recovery score sucks, They naturally perform less well the next day that if you tell them your recovery score is high and so I don't have anything against those companies. But I in fact we use some of their technology can be very useful in certain contexts, but you want to determine your, your mindset around these things and if you tell yourself, hey deadlines make me sharp pressure, makes me sharp, you will perform better. So </s><s>[INST] stress and anxiety, [/INST] what what </s><s>[INST] is that? And can it be leveraged for good? [/INST] Absolutely stressing whether or not you get into a cold ice bath or or a hot sauna. So hot you want to get out or you get hit square in the face with something over text that you really didn't want to hear or see, it's adrenaline, it's just adrenaline and so your subjective read out of that and what it means is really important </s><s>[INST] and you can just channel that [/INST] well you can, if you if you agree with the following statement, which I do and many people do because the data support it, which is ali crumbs statement not mine, which is she directs the mind body lab at stanford. She's brilliant by the way, brilliant. Harvard trained Yale trained, trained licensed clinical psychologist. Also tenure professors. You know, she's a uh Olympian. Uh excuse me, a division one athlete in gymnastics and uh martial arts and her dad um is a longtime martial arts trainer, has done work with special forces and amazing human being and very humble, very kind, lovely woman and professor scientist. She says anything that you do and experience, but especially stress is the consequence of that thing and what you believe about that thing. And so if you consume a lot of information about the powers of stressful states to bring out your best, you will perform better if you consume a lot of information about the power of stress to cripple you, you will perform worse. There's absolutely no question. The data are striking and this is not a growth mindset. This is just simply what sorts of, what do you believe about stress based on the dominant knowledge that you're consuming about it. So that's why it's fun to watch David Goggins. Here we go again. David or jocko or or joe or someone or campaigns, you know, put out this information about, or Ryan Hall who ran for stanford and then now is like into the power lifting thing and running, you know, then there are others too. Of course, when you start to consume a lot of that information, it's not just inspiring. It actually changes your perception of what your own stressful states mean. They you can actually get better from stress if you're in the ocean of knowledge, that stress grows. You. If you're in the ocean of living in the ocean of knowledge, I was saying like a pool in the summer, you got the kiddie pool, the kids all appearing in it, presumably you've got the diving thing, you got the high dive and all that. If you believe that the experience of belly flopping off the high dive is going to make you a better diver in some sense. It at least in this analogy it will. Whereas if you feel that it's just the most embarrassing thing ever and it's gonna cripple your ability to get out in the dive in front of anybody ever again. Well, you're, you're right about that too. </s><s>[INST] Yeah, we actually talked with carl about depression, all those kinds of things that there there could be these, what are commonly seen as negative journeys that could be when reframed can be [/INST] used. You know, one of the reasons I enjoy our friendship so much is that you bring this Russian thing, you know, which I don't really understand it at a deep level. How could I am not Russian. But um but this mindset like that there's pain in life. When I watched that hedgehog in the fog cartoon I thought no wonder Russians the way they do this is the most it's so sad, it's beautiful and sabbath so sad. Whereas out here it's like sesame street and you know, my mother would not let me watch Sesame Street when I was a kid. She thought it was too chaotic, </s><s>[INST] she's too [/INST] chaotic. She was like it's too chaotic. </s><s>[INST] Captain [/INST] kangaroo. We were allowed and then mr Rogers we were allowed. I never really liked shows I like doing things in outside in the in the yard um was trying to trap all the animals. I didn't want to watch stuff on tv. But you know hedgehog in the fog is enough to turn any kid into a thinker and a philosopher and a poet. Here we go. I fell in love with this when when you showed look it even walks with its arms behind its back. </s><s>[INST] So for people don't know and we're watching little clips here to get into and then it's a hedgehog that is wondering about in this fog at night and [/INST] I can't even see a lamp, the fog is so done </s><s>[INST] and there's a there's a feeling of searching and then there's a there's a horse that speaks from from a distance. Words of wisdom. Some people actually told me that they believe that's God that's supposed to represent God. I always thought it was a motherly voice or a voice, a voice of conformity that wants you to return to safety. And here's the hedgehog is searching for something that's in him for the unknown to explore the unknown. And ultimately as it um as the cartoon on roles, it's he discovers a friend in a bear and he also discovers a lifetime passion for looking up at the stars and the curiosity of exploring what is up there. And I see that as science is exploring the mystery. And also I see that as brave to explore the mystery given all the uncertainty all around you. But there is a melancholy, the whole sound of it, the feel of it, the look of it. It was um it just captures both the melancholy and the wander of childhood, which is like there's a loneliness to it. Like nobody understands me. Uh that's there that the Children can, can, can feel because you're trying to figure out my [/INST] favorite character right there. I love the owl. I love the owl. The owl shows up every once in a while. I love the owl. Sorry, I interrupted </s><s>[INST] you [/INST] again. There's </s><s>[INST] Non sequitur, it means you're interested 70% of the time. The other 30%. You're just an asshole. So you have to figure. [/INST] So I'm told </s><s>[INST] that uh there's non sequitur parts in this cartoon, It's it's voters one of the greatest cartoons of all time short short little films, documentary filmmakers. So it is um you know in the soviet Union in and a lot of sort of authoritarian regimes, there's channels to communicate difficult ideas, two people and you figure out those channels and in the soviet Union, one of those channels was Children's cartoons. So actually they're very much for adults. Yeah, [/INST] I like that. Um in some countries, not so much in the U. S. Uh Children are treated with more respect for their intelligence, you know, and not constantly getting this drivel of of just kind of moronic explosions and whistles and bells and the the voice is that um just kind of, you know, Children obviously our Children and need to be their brains are young and plastic and need to be um treated and nurtured as such. But they but they have an intelligence and I think that um you treat them like morons and and they're gonna behave like morons, you treat them as, you know, people who can </s><s>[INST] uh [/INST] consume information and make sense of it in their own way, and that's what they're gonna do. </s><s>[INST] They have a seriousness of looking at the world, I love people that talk with Children like they're adults well just like here as if you're talking to Minnie Einstein because you're like really uh they're asking some big questions and I think uh I mean people sometimes speak of me in this way, like how dumb is this childlike person, but like, no, [/INST] no, there's intelligence </s><s>[INST] in these dumb simple questions in like that a child asks. And I always love those questions, the simplicity, but also the depth of the, those, those questions. [/INST] The reason I started watching your podcast was you did an episode early on with Ray Dalio and the first, maybe the first, but a question that you definitely asked him was you just said what is money? And his answer was fantastic. It's a, it's a superb question and he gave a superb answer and I never would have thought to ask that question and it's, it's the question and it was the question to t things off with. Um so simple questions that get right to the heart of the matter, </s><s>[INST] you [/INST] know, and kids aren't often putting the same uh, cultural filters and um, you know, they're not kids gen generally aren't concerned about getting canceled </s><s>[INST] either. Um, [/INST] So they'll ask the question that no one else </s><s>[INST] is willing to ask and they're not concerned about the how dumb the question sounds. I find the most fascinating questions, it's just really, really simple and it is a bit embarrassing to ask those simple questions of what, like what [/INST] is, well, anything you're asking them for all of us. So please ask them. Um, I think that question, what is money is crucial? And I think the simple questions are the most, obviously the most interesting </s><s>[INST] I'm gonna ask you about you had awesome podcasts. I mean I can ask you questions about basically all your products people should definitely listen to Huberman lab but with with Andy Gap in the conversation he talked about strength and muscle building on that kind of stuff. [/INST] He's an encyclopedia and he also works with a lot of UFC fighters and he works with he has a lab that includes a gym and so he works on endurance and power lifting and also hypertrophy training etcetera. But he also does muscle biopsy. So he runs the full spectrum and he's a full tenured professor and he does all this stuff. So he's he's a really unique um person in this whole fitness landscape because there are a lot of P. T. S out there. There are a lot of kinesiology is there are a lot of people studying nutrition and sports training but he I think he has the among the people out there he's At least in the top five probably within the top three of people that really have their arms around the full extent of what's possible with with training. And um he works with the UFC performance center. I </s><s>[INST] mean he's just at a very systematic way of describing things that was really nice you know um skill speed, power strength hypertrophy. So muscle mass, right? Endurance all kinds of and then the philosophical of like adaptation of how to overload stuff. All that very is their stuff. I'll ask you about ice bath and sauna, which was surprising to me. There is there stuff you took away from that conversation like principles about how to get strong, how to build muscle mass that like broaden and deepen your [/INST] understanding of that task definitely. And I'll do these in bullet points because if people want the logic behind them in the mechanism they can listen to that episode. It's </s><s>[INST] a really good [/INST] I'll start with heat and cold really quickly and just say that avoid cold immersion. So ice baths and being in cold water up to the neck uncomfortably cold within the four hours after a training session that's designed to evoke an adaptation, either endurance hypertrophy or strength. Because the inflammation that you experience from a hard endurance workout or from a hard strength or a heart hypertrophy workout is the stimulus by that you're going to adapt to the cold water immersion, reduces inflammation and can short circuit some of that after four hours, you're probably ok. But if you can do it a different day or you can do it before those sessions, that's better heat. However, it can be done immediately after training and it's probably beneficial because of the way that it dilates the vascular system and delivered refuses the muscles and ligaments, etcetera with more nutrients. </s><s>[INST] And I should just mention that was a crucial piece of information. It's a little bit surprising. Was it surprising to you? [/INST] Absolutely, because I actually, the way I posed the question to him about cold was I hear that getting into an ice bath or a cold water immersion after training can reduce hypertrophy, but I'm guessing it's not that big of a deal. And he said no, it is a big deal, it will short circuit your progress now for people that are only interested in performance who are doing a lot of workouts and trying to recover but not trying to grow muscle, get stronger or build endurance, then it makes sense to do cold because your </s><s>[INST] skill development and skill [/INST] development or you're an athlete in season, you know, so you have to do what's so great about Andy is he really points out the specific ways to train, given your specific goals, so </s><s>[INST] for getting swole, stay out of the ice bath after a workout, [/INST] like it's always making fun of the Meatheads, I love it. Um I put myself in the Meathead category only because I don't do a real sport now, I work out and I run um which has </s><s>[INST] been aspiring meathead, [/INST] okay, so One of these days I'm going to get back to Jews or I'm going to get to jujitsu now in terms of training, he has this beautiful three x five concept for strength, Pick three exercises, compound exercises, multi joint movements, do them for Do 3-5 exercises for 3-5 repetitions per set rest 3 to 5 minutes and do that 3 to 5 times per week. And for details you can again look to the episode, it's time stamped. But what's interesting about this is 3 to 5 times a week is a lot for a muscle group squatting five times a week for five reps, meaning you're working pretty heavy, meaning you're close to failure but not failure for strength. Generally. What Andy taught me is that people who are training mostly for strength can do these low rep type regimens frequently because most of the adaptation is neural because you're not pushing to failure. In most cases you don't get that sore. And so it's the motor neurons getting the muscle fibers to contract more intensely or with more efficiency. In other ways that's leading to these strength gains. And this is why power lifters can train every day or five days a week or four days a week for hypertrophy. I learned from Andy that the repetition range can be pretty broad. You think anywhere from 6 to 30 repetitions, You should do 10 sets per muscle group per week, maybe even a bit more. </s><s>[INST] It's a high volume, high [/INST] volume, but you have to go to failure or beyond in order to stimulate growth. Why does it work at such a great range of repetitions? Well, there apparently are three ways that you stimulate hypertrophy and maybe more. One is tissue micro damage to the tissue the other is through some sort of tension based changes in the molecular de gene programs of cells that lead to protein synthesis that don't, that are distinct from damage and the other metabolic effects of like high repetition work of super fusion of the muscle with blood. We know that third category exists because people are now doing this blood restriction training where they cuff off a muscle and they'll use a really lightweight. I've done these before. You can use a £5 weight and do curls with this in your are in pain and the muscles are swelling up with blood. It does lead to hypertrophy, but in general you're not sore, you're not doing tissue damage. And by the way, don't just turn the kid off a muscle because you have to use the proper cuffs. Um because you need the blood still to flow in one direction, you can't just cinch it off or you'll you'll potentially kill yourself if you um get a clot or you do it wrong, so get the appropriate cuffs, They're out there and then for endurance, I learned something really cool. So I work out basically I go to the gym every other day on average three or four days a week. I do that but generally not two days in a row, it's workout next day I'll do cardio next year and the cardio for me is always a 30 to 45 minute jog kind of zone two cardio Andy informed me that to build endurance while building strength and maintaining some muscle size or even building muscle size. I would be wise to take one day a week and add to that all out Max heart rate work for 90 seconds at least, so do 90 seconds then rest and then maybe do another 90 seconds all out sprint. I almost missed my flight going from Los Angeles to Austin. I did that all out sprint in the airport yesterday so I actually can't think it's done for me. So </s><s>[INST] there was a sprinting Dr. Huberman throughout with three [/INST] bags because I traveled generally I'll travel with too much stuff. Um I </s><s>[INST] love how you were probably running late for a flight and use that as an opportunity to explore as well [/INST] as I was doing it. I was thinking to myself okay Andy that's a 92nd sprint because I got to the the security line I finally got TSC but </s><s>[INST] that's for better that's for extending [/INST] endurance. That's for yeah it actually has some carryover effects on on endurance if you're doing the other stuff. And then he also said one day a week to do this workout and I haven't done it yet. Maybe we do it tomorrow will be fun which is you run a mile. You ask yourself how long did that take? Let's say it took eight minutes Then you walk or rest for eight minutes. Then you run another mile as fast as you can and then you rest for the equivalent period and you do that 123 times once per week. And so as an all around fitness program, it makes you could collapse this into something where you say, okay, you're gonna workout with the weights for about an hour every other day, maybe take two days off every once a while. Maybe not. You're going to do 6 to 15 repetitions. You're gonna push the failure on some of those, not all because some of those are designed to build more strength, You're not going to failure and heavier. Some are designed for hypertrophy, higher rep and going to failure. And then on off days you're gonna jog for 30 or 45 minutes. But for two days a week you're either at the end of your jog Or whatever. You're going to do some all out sprints for 90 seconds and then rest and repeat. And for another day you're going to do these mile repeats. That's a pretty that's a pretty large chunk of exercise movement. But if you kind of thread through the middle of all that, what you end up with is some decent strength building protocols, some decent hypertrophy. Some cardiovascular training that establishes the so called a base or a so called base. So you're not gonna get really good at anything. You're going to become a marathon or this way and optimizing marathon, you're not going to optimize power lifting. you're not going to optimize hypertrophy. But for the typical person, 75% of people, 75% of the time they want some muscle, they want some strength, they want some endurance and they want the capacity to sprint to the, to the security gate without um, you know, leaving along in the terminal. So </s><s>[INST] it's like functional stuff like your life going up the stairs is easier moving about [/INST] the kind of just regular life. And I should mention that cold showers after training don't seem to short circuit the um, the training effect to the same extent that immersion in cold water does. And that really speaks to the fact that cold showers, even though they can provide some of the adrenaline for the mental effects of like, oh I have a lot of adrenaline, my system from a cold shower and I can remain calm. There's, there's utility too, that it's not going to have the same metabolic effects or other positive effects that cold water exposure has been shown to have. And that's unfortunate because most people have access to cold showers, not everyone has access to a cold dunker and I stunk, but here in Austin, you have this place and no, they don't pay me to say this, but I always like going to this place whenever I'm telling this place kuya and they've got a sauna and a couple ice baths and even have those salt tanks that you can float on the surface. They have cold water immersion. That's pretty cold. </s><s>[INST] Still haven't. I need to, [/INST] you're rushing. You'll probably get in and you won't even </s><s>[INST] know [/INST] exactly where people pay for this. I did a post right of you as a baby. It's you know, I had to go deep to get that photo of lex um in a bassinet in the snow because in Russia, they actually did this for a long time. They thought that it and indeed it does build the immune system to expose babies to the cold. </s><s>[INST] I don't, I still don't know where you got that photo and then you were able to find exactly the right. It was it was great. I didn't [/INST] have a tie on. But you had all the looking seriousness that you do now. So it's clearly nature. Nurture. Clearly you were born with that. </s><s>[INST] What about sauna? He does say that it's good to do heat. So [/INST] there are three ways you can do sauna that I can just toss out as like briefings if you want to get a really big growth hormone release for sake of metabolism. Fat loss. Your training really, really hard in jiu jitsu and you want to recover. You don't want a sauna too often Because the study that identified this massive 16-fold increase in growth hormone. They had people do this. It's crazy. They got into okay temperatures are 80 to 100 C. So that's 176 F to 212 F For 5 to 30 minutes. Is the typical ranges that people working in these research studies for maximum growth hormone release. Don't do sauna more than once a week, But get into the sauna for 30 minutes as hot as you can safely tolerate. So probably for you, they'll be 2 10 because you're, I suspect you'll be on the high end of things. Then get out for 5 to 10 minutes. No cold exposure, get back in the sauna for 30 minutes. Then they had them do it again out for five minutes back for 30 minutes out for five minutes back for three minutes. They had them do two hours of sauna exposure to get that growth hormone release. Now for the reduction in likelihood of dying of a cardiovascular events, stroke or otherwise. The more often you do sauna the better. So if you look at all cause all cause mortality or death due to cardiovascular events. And you look at sauna use frequencies using the same parameters 80 to 100 C 1, 27 times per week. Basically the more often you get into the sauna for 30 minutes Across the week. So 30 minutes a day is better than four times a week. Four times a week is better than two times a week and two times a week is better than one. And The reductions in mortality are really impressive. 27 if you get into the song of the way I just described, Not the two hours a day, but 30 minutes twice a week Or three times per week. You reduce the likelihood of dying of a cardiovascular event by 27%. If you do it four or more times per week, you reduce the probability of dying by 50% of a cardiovascular event. And in these studies, they rule out other things that people are doing smoking. They even asked them, do you live in an apartment, are you in a happy relationship like they evaluate other can potentially confounding variables. Now for people that don't have access to a sauna hot water bath or hot tub is gonna be your next best bet. And if you don't have access to that do like the wrestlers do, which is, you know, put on two sets of uh sweats and a hoodie and a stocking cap and wrap yourself in plastics underneath all that and go for a run. But don't, please nobody die of hypothermia. I mean you can die of warming up too much. Is this </s><s>[INST] experience? Um pleasant or stressful in the way. So is it as stressful as a nice bathroom? [/INST] Great question. People always ask how cold to make the ice bath or the cold water of the shower. You want it to be uncomfortably cold, meaning you want to feel like I really want to get out but you can safely stay in and that's going to vary by person and experience with </s><s>[INST] experience with [/INST] the sauna, it's the same thing how hot to make it well don't kill yourself obviously um be smart if you're pregnant, you shouldn't be doing this anyway. Um but it's very clear that what you need is the release of something called dine orphan. We have endorphins which makes us feel good, it binds to these new opioid receptors in the body. You have dine orphan which is the terrible feeling that you get when you're in really hot temperatures. It's also the terrible effect that alcoholics feel when they are in withdrawal you feel agitated, you want to get out, it's really unpleasant. It's dine orphan binding to the so called kappa opioid receptor, is that what you're trying to trigger when you do that? A number of things happen. You set off heat shock proteins that go repair broken proteins and misfolded proteins. It also makes it so that later endorphin binds its receptor more strongly. So when you have this uncomfortable experience in the heat, you literally feel better in real life when pleasurable events come on when you experience them in the same way. I like to say this that when you get into a cold ice bath or cold shower, the increase in epinephrine and dopamine is 2-300%. These are huge increases and they last many hours. This is shown because lately I've got a little bit of pushback on Twitter that, which is, you know, um interesting place. Um people say, well that's just in my snow. All the studies I just referred to are all done in humans, men and women, fairly broad age range is so you want to be uncomfortable in the cold, you want to be uncomfortable in the heat. And this is why I'm not a big fan of infrared saunas because they only go up to about 100 and 60 170 degrees infrared light and far red light of all kinds has been shown to be beneficial for wound healing. Acne skin, eyes. They're even guys now putting on their testicles because it can increase testosterone and sperm production. </s><s>[INST] Yeah, hormone release [/INST] hormone release. But in terms of the sauna, you want that strong heat stimulus and </s><s>[INST] Then that's when you crawl up to the 200 [/INST] mark and so on whenever I'm in new york. And there's also one in san Francisco, although the one in san Francisco is is clothing optional just to warn people there's a place called Archimedes Banya, is </s><s>[INST] there any scientific evidence that being naked is beneficial in the sauna? [/INST] Well, in certain contexts it leads to childbirth. </s><s>[INST] Okay, [/INST] but I suppose it's not required right for childbirth, but um but in all seriousness, you know, in new york, I'll go to a place called spa 88 actually uh Habib's pictures on the wall, he goes there and it's a there, that one. It's clothing it that they require clothing. I only just say that because it can be a little bit of a shock to people sometimes that they kind of walk in there, a bunch of naked people that went in san Francisco if I go on clothes and mostly because you know, I run into coworkers or things like that, you know, I sort of more old fashioned in that way I suppose. But um </s><s>[INST] would you like to wear clothes around coworkers? Yes. Yeah. [/INST] I mean it just, to me it just seems like, you know, just be aware. But but nonetheless, the banias have very hot sauce on us because they're Russian owned And in New York there's one on the lower east side. But the spy 88 place, they have some saunas that the moment I get into those I have a hard time catching a full breath. It burns. They've got a cold dunk that's like a shock. And then they've got a sauna wet sauna steam room. That's a little mellower. So the nice thing about a banya is you can kind of find your place and then they do the plaza where they take the eucalyptus leaves and you can pay someone and you basically, you cover your groin and then they beat you with the the, the leaves and it's supposed to bring the vasculature to the surface. I've only done it once and frankly I found it to be a little bit unnerving. I didn't really like the experience, but I'll try and get into a sauna as often as I possibly can, which is, you know, once or three times per week and I try and do the cold exposure shower or immersion, but early in the day because it really wakes you up. </s><s>[INST] one of my favorite things I've listened to, I wish there was a video is um listening to a bunch of stuff with rick Rubin. And um he did a thing with tim Ferriss, tim Ferriss podcast. I don't know if you've ever heard it, but he [/INST] forced </s><s>[INST] them to do, they did the podcast in a sauna and I don't think at the time to affairs was [/INST] adapted if you're not heat adapted, it can be pretty stressful. </s><s>[INST] And I mean obviously the whole experience as stressful as a, somebody with microphones like what, what is happening. But I just love that tim was vulnerable enough to kind of give themselves over to whatever the hell this experiences and I, I'm just so happy that rick won't like pushed [/INST] that kind of idea </s><s>[INST] and just, let's, let's do it. That's [/INST] a very rick Rubin kind of thing to do. And we must </s><s>[INST] not, we like, we must [/INST] do this, this has to be done a podcast that was done from a sauna continuously would be really interesting. Like, you could call it like the pressure cooker or something. </s><s>[INST] I mean like a regular [/INST] yeah, like it's you have to sit with your guests in the sauna um or they have to sit in the sauna. </s><s>[INST] That was one of the interesting things is um it was a sad thing because I believe there's no video of that podcast. But you could tell there is a kind of there was suffering on this push on tim's part. It was like a degradation. He he started over time not being able to put words together correctly, which he's very eloquent. And so you could see there's like there's [/INST] a struggle heat and cold pull you down from the inside. You have to I mean there's a reason why the screening process for um make you know seal seal, they call it seal training. But its really screening and training involves cold water because you know if you're in the heat too long you'll die or damaged tissue in cold. You can do it quite extensively before you die or damaged tissue. But it is stressful. I was gonna say one thing that um I sometimes enjoy seeing these social media posts where people will get into the ice bath. They look really stoic like they're really tough. Um But actually that's the wimpy way to go through it when you get into cold water. If you stay very still, you develop a thermal sheath around you that you're warming yourself. The really bold way is to get in and continue to sift your arms and legs and it ends up feeling miserably colder. And then </s><s>[INST] because you're breaking up and [/INST] bringing that thermal layer and then when you get out you'll notice a lot of people huddle where they'll they'll put they'll grab the towel in general, that's me, I'll get back, I'll get into the sauna. But if you really want to stimulate the big increases in metabolism, you stand out there and you dry off with arms extended in open air and as that water evaporates off you it is really cold but your body is forced to activate a number of the warming programs related to metabolism. This is the beautiful work of a woman named Susannah Soderbergh whose um Scandinavian, she published this paper last year and sell reports medicine and so I call this the sobered principle. Which is if you're doing ice and heat for whatever reason, it doesn't matter if you had it on heat or cold. But if you're using cold specifically to stimulate an increase in metabolism and with cold that's the sobered principle. </s><s>[INST] And with cold. Yeah if you're alternating and then uh if you want to do the tough way you let the shivering so you just stand out and let the water [/INST] evaporate. Yeah. I mean if you ever waded into a cold ocean, you know, everybody is kind of like holding themselves. You know if you really just if you let yourself extend your limbs and move them around a bit. So you break up that thermal layer. That's that's the tough way to. So when I see people on social media getting in and they're like really tough and trying to look hard, </s><s>[INST] you want to be moving around, [/INST] smiling, talking, moving around is way way colder. Are </s><s>[INST] you able to talk? Can you do so you suggest the podcast in the, in the sauna? How [/INST] about this? I proposed this since I got, you </s><s>[INST] want to do the next podcast? [/INST] So the folks from the plunge, maybe you could bring lexa a plunge. He certainly deserves one and we can go side by side coffin style or we can face one another when </s><s>[INST] we said we should do each other's podcast and maybe next year. I can't [/INST] wait to have you back on. I mean we only scratched the surface. </s><s>[INST] Let's do at least part of the next human lab podcast either in the, [/INST] I have a sauna and a cold plunge. So we could do, yeah, we could do, we do a sauna and a cold plunge version. </s><s>[INST] I wonder the recording how the recording works. If there was a bit [/INST] of an echo in the sauna, but I'm sure we can take out the reverb. So </s><s>[INST] sergei wants to ask you about sex performance. Very journalistic, very hardcore hitting questions that we have here in the [/INST] generally or a specific </s><s>[INST] uh he has a certain problem. He needs help with. No, generally you haven't done an episode on sex. [/INST] Well we did an episode early on on sexual development. </s><s>[INST] Yes, we've done [/INST] them on optimizing testosterone and estrogen and we touched a little bit on the on libido and somewhat on sex performance. But not much. We did an episode on relationships, love and desire where we touched on libido specifically. So just as a quick mention of something, a lot of people take S. S. R. I. S. Or antidepressants that can disrupt sexual function, there are a few compounds like Mca route and Tonga ali and things like that, that at least in a few studies in humans have been shown to offset some of the the sexual side effects. Um Now in terms of sexual and then the, sorry, the episode on sexual development was about how the brain and body become organized in certain ways, how the brain becomes organized. If you have X chromosomes or Y chromosomes or etcetera early development mainly and the effects of hormones later on that template, we will be doing a I'm actually putting together a series on sexual health, everything from the menstrual cycle, which both men and women should understand. Of course. Um understanding arousal, understanding for instance, a lot of people don't realize this, but that orgasm is actually the consequence of activity in the sympathetic meaning the stress arm of the autonomic nervous system, whereas arousal is the consequence of the activity of the parasympathetic, the calming aspect of the of the audience, </s><s>[INST] right? It's [/INST] counter intuitive and it kind of looks like a seesaw. I mean there's arousal, then there's relaxation, then there's arousal but the um and then immediately after orgasm and in males ejaculation, what ends up happening is there's a rebounding of the parasympathetic nervous system which it leads to. Oftentimes people feeling very relaxed or falling asleep. So I'm going to do a c a short series on sexual health that will be that will include stuff about sexual performance. But also um some I'm working on getting a an expert guest who can talk about some of the neurologic changes that happen um as a consequence of sexual activity. And we did an episode with uh guy from Ut Austin here, David Buss, whose evolutionary psychologist talking about um we went pretty deep into some of the but typical and unusual dynamics of of mating relation um whether or not people have kids or not and what impacts that, but we're going to do an episode on menopause andropause. What's very surprising is I get a lot of questions about sexual health from the young male audience um which tells me that. Well, here's what I think it reflects. I think that women because of their Menstrual cycles early on. Start to talk to one another about changes in physiology and psychology as a function of this 28 day cycle that they all experienced sooner or later males, there's less of a conversation and it usually arrives in code. People will say, hey, what should I take to increase my testosterone? And I'll say, well, maybe nothing, you know, what are you specifically concerned about? And then over time, if you pull on those threads a little bit, you know, you get your answer, sometimes I'll just get a direct question. Um but I think that uh the psychology of all this, and in terms of jealousy in the terms of um notions of roles and relationships is very dynamic right now and I'm fascinated by this. So we're gonna do a four episode series </s><s>[INST] about sexual fantasy. What to get Freudian for a second. What role does sexual fantasy have in the human condition? [/INST] There's a book called the erotic imagination. It's very psychoanalytic book written by the psychoanalyst that talks about how, well here's the uncomfortable reality Freud was at least right about one thing, which is that the brain circuitry that you used to develop attachments to your caregivers, mother and father, or other caregivers do not disappear when you hit puberty, they are repurposed for romantic and sexual relations. And so this is why the whole notion of anxious attached and secure attached, you know, stems from childhood attachment patterns, but it carries over to romantic relationships. So </s><s>[INST] that the relationship with your mother has [/INST] a </s><s>[INST] and father has a and probably other close people to you and your young age has a secondary tertiary, Some kind of ripple effect on hide your sexuality developed like what fantasies you might have all that. [/INST] Oh, without question. And of course early experiences too, and traumatic or positive or neutral. The thing that's really important to remember though in this transfer of circuitry from one role to another is that and it's certainly consistent with psychoanalysis, that gender is interchangeable. Sex is interchangeable. So, for instance, let's say you had a wonderful relationship, let's say this, let's take a hypothetical person. Okay, I'm truly not referring to myself, Let's let's take a young woman who has a wonderful relationship to her father and they just absolutely terrible abusive relationship to her mother. Just for sake of example, she then goes into adulthood and she is drawn to very abusive men. Not always, but let's just use in this example and the dynamic is exactly the same as the dynamic she had with her mother. That's actually a common occurrence. Even though in this context she's heterosexual. She's romantically attracted to men. What is seen over and over again is that the dynamic with one parent can be transferred onto a romantic dynamic, but it doesn't have to be, you know, that if it was with the mother, then it only has to do with relationships to women. So gender is interchangeable because these circuit trees our pre sexual they are laid down in our brain before. The brain has any concept of sexual interactions. It's pre pivotal. Excuse me. And so, um there are a lot of interesting examples and data to support this. Um the book attached is a pretty interesting book by two psychologists. One I think is at Columbia University, um that talks about how childhood dynamics carry over to adult romantic attachment. So as you can tell, I get pretty alert in response to these questions that I get a lot of them relate in this domain and they </s><s>[INST] have a lot of impact on people. And they were wondering about they wanna learn [/INST] and no one knows what other people are doing or what's normal. We kind of know deviancy, we know perversion, We know the extremes, we know the rules. Hopefully people know the rules, but you know, let's just be. There are a lot of people in, in the academic community in particular at certain East Coast schools not to be named that are in open relationships. This is more common now. Um It's not very common, but it's more common. And you know, obviously that's a way of bypassing some of these more primitive emotions about jealousy, etcetera and leveraging them towards maybe even ongoing relationships. I'm not passing judgment one way or the other. I always say four conditions have to be met for any discussion about, about sex and sexuality or sexual health, age appropriate context appropriate, consensual and species appropriate. </s><s>[INST] Well, that that's weird because the thing I'm trying to figure out is why my sexual fantasy is to go to uh furry orgies and have sex with others dress the squirrels, squirrels and me uh the other animals. So that could be that I have to, I'll see a therapist about that one. [/INST] I'm not going to respond to that except to say that. Um as long as those four conditions are </s><s>[INST] met [/INST] appropriate species appropriate. </s><s>[INST] So there's a bunch of questions on on instagram, one of them on this topic on relationships. Uh Somebody suggested to do a part three of why Lexus single. There's a running joke about this. [/INST] Yeah. But but I can answer it in part, right? Because well, partially because you're very busy, partially because you've decided that until it's time you're gonna wait until it's time. It's time right? Until it's time you're waiting. And then um you're not saving yourself for marriage. Uh I think, but but in some sense, um yeah. Your your wife, your future wife is out there. </s><s>[INST] Oh yeah, yeah. She's being programmed. No, I I mean I definitely, I definitely believe that. I mean, first of all, I just love people and I fall in love very easily with people with objects with things with with with life with every moment. [/INST] And that way you're like Oliver sacks he fell, he would fall in love with minerals and concepts and things like that. </s><s>[INST] And so like to me this kind [/INST] of </s><s>[INST] uh so relationship is more like a commitment to one particular kind of um object of your love, [/INST] like </s><s>[INST] it's almost like a it's a good journey that you take on together because also the interesting thing about humans is their moment by moment, a different person. Day by day, week by week, month by month, they change, they evolve, there's an ups and downs and stuff like that. So you're, what you're doing is you're saying, well I'm going to explore all the way that this human gets morphed and changed and the, what makes them cry, what makes them excited, what makes them lonely? Like the the, the habits like when they form certain habits with how they feel, when those habits are broken. Like the the stupid minute things that make everyday life, you're gonna be on that journey together, figure that out just the way we're trying to figure ourselves out when we're like optimizing these things about diet and health and so on, you're kind of doing this computation together because neither person really understands themselves um at all and you're together both confused about each other and you get to almost like um our relationship is a chance to understand yourself and to understand another person, like together that processes some colors iterative, [/INST] you know the dynamics, right? I mean you're merging two nervous systems. Once this was once described to me very well by an ex girlfriend um who's truly brilliant, she's really brilliant um she said, you know, there's four arrows, this is maybe to an engineer </s><s>[INST] or like a so it [/INST] makes sense, there's how you feel towards the other person, there's how they feel towards you, but then there's there's an arrow that comes back to you which is how you feel about how they feel and then they have an arrow of how they feel about how you feel, right? This is why if someone else's moody or somebody else is upset, there's one version of ourselves where we respond to that or they respond to us, but there's another version where we respond to that, but it's also there's a processing of what it means for us that they're behaving that way or feeling that way. And this again leads us back to that early attachment circuitry because of apparent was stressed. The child's role is not to sue the parent. In fact, healthy models of parenting say that Children shouldn't actually know how their parents feel for like the first eight years of their life, They're not supposed to be in that mindset of empathizing for the parent. This is often not the case, but maybe the cut off isn't exactly eight, but you get the idea. So the dynamics of relationships are where the learning is because we learn how we react to other people reacting. It's it's not a just a two arrow system. It's at least this four arrow think. Um but there's also the element of nurturing, right? I mean I think that um going through life with somebody is so much better than going through it alone and I had never thought I'd make that statement. Um </s><s>[INST] So it wasn't always obvious to, you [/INST] know, it wasn't always obvious to me and I mean I've I've been I've really enjoyed wonderful relationships um and some have been hard and there's certainly been a lot of growth. I'm on good terms with almost all my former girlfriends um and close with some enough that I'm I know their spouses and I'm close with their families and um but no it wasn't and I think that uh when people say relationship is hard, the only really hard part about of a good relationship is just dealing with oneself and making sure that you're staying in that mode of caretaking because I do believe that if one is mainly focused on taking good care of the other person, provided they are also focused on taking good care of you to some extent and we're good at taking care of ourselves, Everybody flourishes, everything gets better. But no, I don't think I experienced that until fairly recently. Um What </s><s>[INST] do you think is the secret to a successful relationship. [/INST] There isn't just one, but at the at least at in the top five is master or at least be good at autonomic self regulation, know how to calm yourself down, don't expect like looking to anything external to soothe yourself is it puts you in a terrible position to to be a caretaker of yourself and other people, right? So learn how to self soothe, right, learn how to calm your mind, steady your action, steady your voice. There are tools to do that we talked about on the podcast, but elsewhere have that in place. I also think that if if your main focus is on you want to have good boundaries etcetera, but on tending to the relationship doing a little bit more than you think you ought to do if everyone does that, it goes great. I mean I'm sometimes so positively struck by how supported I feel um because for many years I was just kind of doing everything on my own. So any little thing, I'm like oh my goodness, this feels huge. Um and also I think the dynamics have to be, right, let's let's be really honest, this is a little bit of a tricky topic, but um there is a power dynamic in relationships sometimes, not all, but in some relationships it works much better if one person leads and the other person follows in other relationships, it's more mutuality works best people need to know what they need and so knowing what you need and what you crave is really important and then once you do that, you can create the relationship you want. I've seen that over and over again and people are different. Um but I think that um ultimately, I mean, right, it's it's there's the dopamine phase of a relationship and then there's the serotonin phase, the kind of more mutuality, coziness and sweetness. There's a great book about how to make sure that the dopamine component and the serotonin components, so to speak, go on forever. And it has to do with, you know, when you first meet someone, you're attracted to him, you're essentially objectifying them. You meaning not in the way people might think you are not dependent on them for emotional stability or survival. As you get close with somebody, you really come to depend on them and then you tend to objectify them less. And so this book, the book is, as the name is kind of corny, but it's written by an analyst. Again, it's called ken Love last and it's a book about how really good strong relationships are the consequence of people constantly moving through this um dependency objectification dynamic. And I use those words in the true the psychological sense, not in the way they're typically thrown around nowadays. So the idea, you know, in some cultures, men and women will only touch for two weeks out of the month and then for the other two weeks, the excitement and the sensuality and all and the sexuality is very heightened. And then they go back to this kind of distancing. Now, I don't think that's feasible for most people. But if you look statistically, those relationships tend to last very long time with at least reported mutual feelings of intense attraction for many, many, many decades. So human beings need to learn how to at least understand and control these dynamics. And there's a lot of divorce, there's a lot of cheating. There's a lot of stuff out there would be great if people could resolve some of this stuff inside of the relationship, in my opinion. </s><s>[INST] Yeah. And this kind of intense attraction. There's actually one of the poems that carl uh distraught introduced me to. I think it's two english poems is the name. But one of the things I find myself for prolonged periods being attracted to is like you notice some kind of magic and you keep wanting to dig to the depths like of that magic [/INST] to really know that person </s><s>[INST] to really know a person deeply. Yeah. You noticed [/INST] something early </s><s>[INST] on. I don't know what that is, but you just noticed something special and you want to keep pulling at that thread and you never really do well, [/INST] you also have to be careful. You know, I get a lot of questions from God. You have to be careful. The questions you ask in a relationship to you have to make sure you really want that information. It's not just about people's past, right? If you ask somebody how they really feel about something about you and they tell you that may be soothing. It may be intensely stressful. You have to be, Here's one thing I know for sure for a relationship to work you have to be brave. You can't go in there fully protected and yet you also can't go in there with no boundaries because you'll end up beat up. What's that quote? If you want to be a warrior prepared to get hurt if you want to be an explorer prepared to get lost and if you want to be both, you know if you become a lover prepared to beat both or something, something like that. I forget this one of these instagram type things that you see passing by. And you know that's pretty true love love scary because it takes us back to that primitive circuitry that is as primitive and basic as hunger, thirst. The desire for heat when we're cold. The desire for cold when we're overly warm. It's a it's dine orphan when somebody leaves like the you know when somebody who were attached to leaves by death or by decision or you're forced apart. The dine orphan release is a massive it is true discomfort. People feel anxiety and discomfort and moving through. That is a hell of a process. I mean if I knew how to best break up at the neurological level or if you just plug yourself into a wall and reset. I mean I do that episode tomorrow but we don't have that knowledge. </s><s>[INST] Come on the I think we've covered this before and it's even been meme unified. I think losing love is part of the magic of love. It means you've felt [/INST] something, I agree, but at some point, like if you've done it enough times, you know, life is finite. You know, it is beautiful to see these couples that seemed very much in love despite many years, despite having been together many years. </s><s>[INST] Yeah. The way they look at each [/INST] other, they'll say </s><s>[INST] they still see the magic [/INST] and they'll say we got lucky or it was it's been hard or this and that. I think external conditions being a little tougher is helpful for a couple. </s><s>[INST] I [/INST] do, I do because I think that you rally, you know, you you and you bond with people, you know, being obviously you want to survive those conditions. But um yeah, I do. I think that </s><s>[INST] Bonnie and Clyde. So, and [/INST] they were a little a </s><s>[INST] little too much, a little bit too much [/INST] sociopaths. But the well, when two sociopaths, normally it's interesting. Normally sociopaths don't team up because they, because they manipulate each other, sociopaths sadly are are usually only interested in manipulating the highly pliable or unsuspecting. Um but when romantic attraction is woven in, then it gets um really diabolical </s><s>[INST] and your advice and finding the love of your life of my life, this is this is why Alexa single response. Why any advice. [/INST] Yeah, actually this comes from a friend of mine who is in a really excellent marriage. Um with great kids and family and high demand life. It's a decision, like at some point, you just priority, you just prioritize it as okay, I'm going to make this happen one way or another and um, you don't force the discovery of that person, but I mean, I've occasionally said, hey, I think you should meet this person or that person and well it wasn't, maybe my judgment might have been off, but the timing wasn't right or something, but I think that, yeah, it's a decision and it also has to do with life structure. I mean, there were years, so I, when I was in graduate school, I didn't want a girlfriend, I just wanted to be in lab and I'm sure I had romantic dating interests, but I wasn't going to meet them through a committed, you know, live together situation, it wasn't where I was at as a postdoc here, things are a little different, etcetera, etcetera. So, but at some point it's sort of like, what do I want my daily routine to look like? Because ultimately a relationship, however one structures is going to be part of your daily routine. So at the point where you're like, you know, I'd really love to wake up next to somebody and do blank and blank together and then I'd love to work and then we meet for dinner and then we, you know, take the dog for a walk or take kids out or whatever, it happens to be, take a trip, but do you have to be, one has to be in the mindset of wanting to do couple like things, people and a lot of people don't think about it that way. They, they either fall into something or they they don't see the benefits of coupling up. I think that the pandemic, um tuned people's awareness to the fact that some things are indeed easier on your own, depends on finances etcetera, etcetera. But a lot of things are made better done with other people. </s><s>[INST] 100%. But I also, so I was very deliberately it's an interesting way to put it, but what do you want your day to look like? I think, what do you want your data look like, what you want your life to be? I was very deliberately, always, uh first of all, happy to be alone, like a conscious thinking, I know a lot of friends who are just unable to be alone, I'm able to be alone, but I'm much happier with another person, like I'm able to share joy with other humans. I [/INST] look forward to the day that our kids are rolling jujitsu and my kids are, </s><s>[INST] you know, hanging [/INST] out with your kids and if that notion sounds even remotely interesting then and fun then then it's sort of like you kind of backpedal from that and you go, well, </s><s>[INST] how do you [/INST] get in here </s><s>[INST] and think from first principles about love Andrew your, thank you for being my friend, thank you for being an amazing human being, who is so inspiring to so many people for constantly. I told us the car, like one of the things that was really refreshing um about you is that, you know, when I tell you an idea and I tell you a thought, when I tell you something you didn't, you don't shut it down. As the first step was saying that that's common in the scientific community. That's common with people around you. You're, you're seeing what's the go out there, you get excited, get excited together and that's how you can really have a great friendship and a great, great, great stuff together. So I'm deeply grateful for that and just uh, for connecting so many interesting people together. You're doing an amazing job and thank you for existing. Thank thank you for being you. Thank you for talking today and next time I'll see you in the sauna and [/INST] yeah, well I want to say several things first of all, thank you for having me on. Again, it's an honor and a pleasure and I don't say that formally. I'd really truly mean it. I only human lab podcast as I always say only exists because you gave me the suggestion and I'm so grateful that you did so thank you and for doing what you do like you, you are brave and you're the first man in and you're just continue to do it. Just whatever as my postdoc advisor used to say whatever you're doing, just keep going. And then in terms of our friendship, I mean, I think, you know, and if you if you don't, I'm gonna just keep telling you anyway by texting in person. You're an amazing friend. Uh there's deep trust, there's immense respect and I love you brother, I </s><s>[INST] love you too, man. We did it. Thanks for listening to this conversation with Andrew Huberman to support this podcast. Please check out our sponsors in the description and now let me leave you with some words from ralph Waldo Emerson. It is one of the blessings of old friends. You can afford to be stupid with them. I look forward to doing just that in the many years to come of friendship and fun conversations with Andrew. Thank you for listening and I hope to see you next time. [/INST] </s> |
<s>[INST] Okay, so this okay, that makes a lot more sense. That's nice. So that you're trying to use sort of it's a probabilistic lee you're not, [/INST] you can't make a single particle collide with the single. So that's not an efficient way to do it. You'll be waiting a very long time to get anything. So </s><s>[INST] you're basically right to see, you're relying on probability to be that some fraction of them are going to collide and then, you know which it's a it's a swarm of the same kind of particle, [/INST] so it doesn't matter which ones hate each other. Exactly. I mean, that's not to say it's not hard. You've got a one of the challenges to make the collisions work is you have to squash these beams to very, very basic, their narrow where they are, the better because the higher chances of them colliding. If you think about two flocks of birds flying through each other, the birds are all far apart in the flocks, there's not much chance that they'll collide if they're all flying densely together and they're much more likely to collide with each other. So that's the sort of problem. And it's tuning those magnetic fields. Getting the family feels powerful after you squash the beams and focus them so that you get enough collisions. </s><s>[INST] That's super cool. Do you know how much software is involved here? I mean, it's sort of like um in the software world and it's fascinating. Uh this seems like it's a software is buggy and messy and so like you almost don't want to rely on software too much. Like if you do, it has to be like low level, like FORTRAN style programming. Do you know how much software is in the large Hadron collider. [/INST] I mean, it depends on which level a lot. I mean the whole thing is obviously computer controlled. So I mean, I don't know a huge amount about how the software for the actual accelerator works. Um but you know, I've been in the control center, so that's and there's this big control room, which is like a bit like a Nasa mission control with big banks, you know, desk where the engineers sit and they monitor the LHC because you obviously can't be in the tunnel when it's running, so everything's remote. Um I mean, one sort of anecdote about the sort of software side in 2000 and eight, when the LHC first switched on, they had this big launch event and then big press conference party to inaugurate the machine. And about 10 days after that, they were doing some tests and the dramatic event happened where a huge explosion basically took place in the tunnel that destroyed or damaged badly damaged about about half a kilometer of the machine. But the stories, the engineers are in the control room that day, they, one guy told me the story about, you know, basically all these screens they have in the control room started going red. So these alarms, like, you know, kind of software going off and then they assume that there's something wrong with the software because there's no way something this catastrophic could have could have happened. But I mean when I worked on, when I was a PhD student, one of my jobs was to help to maintain the software that's used to control the detector that we work on and that was, it is relatively robust. Not so you don't want it to be too fancy, you don't want to sort of fall over too easily. The more clever stuff comes when you're talking about analyzing the data and that's where they're sort of, you know, </s><s>[INST] are we jumping around too much? Do we finish with the standard model? We didn't we didn't we even started talking about quirks [/INST] we haven't talked about yet, We got to the messy zoo of </s><s>[INST] Particles. Let me uh let's go back there if it's okay, can you take us to the rest of the history of physics in the 20th [/INST] century? Sure, Okay, so 1960, you have this, you have these 100 or so particles. It's a bit like the periodic table all over again. So you've got like, like having 100 elements, it's sort of a bit like that and people try to start to try to impose some order. So, Murray gellman, his theoretical physicist America and from new york, he realizes that there are these symmetries in these particles that if you arrange them in certain ways they relate to each other. And he uses these symmetry principles to predict the existence of particles that haven't been discovered, which are then discovered in accelerators. So this starts to suggest there's not just random collections of crap, there's like, you know, actually some order to this underlying it A little bit later in 1960. Again, it's around the 1960s. Um He proposes along with another physicist called George zweig that these symmetries arise because just like the patterns in the periodic table arise because atoms are made of electrons and protons. That these patterns are due to the fact that these particles are made of smaller things and they are called quarks. So these are the particles are predicted from theory for a long time. No one really believes they're real. A lot of people think that there are kind of theoretical convenience that happen to fit the data, but there's no evidence, no one's ever seen a quark in any experiment. And lots of experiments done to try to find quarks to try to knock a quark out of her. So the idea of protons and neutrons are made of quarks, you should want to knock a quark out and see the quark. That never happens. And we still have never actually managed to do that. </s><s>[INST] We really [/INST] know. So the way, but the way that it's done in the end is this machine that's built in California at the stanford lab stanford linear accelerator, Which is essentially a gigantic three km long electron gun fires electrons almost speed of light at protons. And when you do these experiments, what you find is a very high energy, the electrons bounce off small hard objects inside the proton. So it's a bit like taking an X ray of the proton, you're firing these very light high energy particles and they're pinging off little things inside the proton that are like ball bearings if you like. So you actually that way they resolve that there are three things inside the proton which are quarks, The quarks that gell Mann and Zweig had predicted. So that's really the evidence that convinces people that these things are real. The fact that we've never seen one in an experiment directly, they're always stuck inside um other particles. And the reason for that is essential to do with the strong force. The strong force is the force that holds quarks together and it's so strong, it's impossible to actually liberate a quark. So if you try and pull a quark out of a proton, what actually ends up happening is that the you kind of create this that this spring like bond in the strong force, you imagine two quarks that are held together by a very powerful spring. You pull and pull and pull more and more energy gets stored in that bond, like stretching a spring and eventually the tension gets so great, the spring snaps and the energy in that bond gets turned into two new quarks that go on the broken ends. So you started with two quarks, you end up with four quarks. So you never actually get to take a clock out. You just end up making loads more quarks in the process. </s> |
<s>[INST] Yeah. It takes a lot of skill, a lot of character. And yeah, deep thinking to be able to operate within the system when needed, and having the fortitude and just the boldness to step outside and to burn the system down when needed. But rarely an opportune moments that would actually have impact. I mean, it's ultimately about impact within the society that you live in, not just making a statement that has no impact. [/INST] Yeah. And we were talking about how dangerous it is to do real philosophy at a dangerous broken times. He was going through the most broken time in history and he questioned the the methods which made a broken system able to survive. And he was so skilled and so graceful that he became a saint in that tradition. And there's something for me to really learn from there. </s><s>[INST] Do you draw any inspiration? Have any interest in the sort of more modern philosophers? Maybe the existentialists a niche is one of the early ones. Do you have thoughts on the guy in general or any of the other existentialists? [/INST] Well, with regard to Nietzsche? I think I think Yeates might have said that he's the worst. You know, he was, it was certainly filled with, with passionate intensity. Um, </s><s>[INST] I think compliment he was the worst or her criticism. [/INST] He said this has this big line, the best lack all conviction. The worst are filled with passionate, passionate intensity. Um, so, um, I think Nietzsche was was destroyed by the horrors of everything that that went on around him. And I think he never really recovered from it. I think that's because, um, if you think about Nietzsche's philosophy, he was very opposed to any sort of acceptance of what one had, One should always envy those who have more and use that envy to, uh, to fuel their their growth. And because, you know, accept whatever the human condition and desires are, and you use those desires to want more and more and, and make use of your greed. I think it's very difficult to be truly happy if the thing which you, uh, the thing that you pride yourself most on is, uh, never being satisfied. And I think Nietzsche was never satisfied. And that was the danger of his philosophy. I think also with his Amoral is um, you know, there is no good or evil. I sort of disagree with that on a, on a pretty fundamental basis. I think that, um, our notion of morality is by no means subjective. It's really the proxy for the fitness of a society. I think whatever we consider ethical, like, don't steal, don't murder, don't do this. Uh societies have a very difficult time running. It's very hard to run a civilization when everyone is stealing from everyone else and people are murdering each other and uh committing these things which we would consider a atrocities. So I think we also we know this because I think very similar notions of morality of evolved convergent lee from different traditions. I think um mm good is a proxy for a civilizations. Fitness. And the good news is that that means that evil uh in being anathema to that good uh must therefore be uh the opposite of stable in whatever way that it's evil and that means that good will always be more stable than evil. And the only way evil can really win is like if everyone dies. So um </s><s>[INST] so wait, can you say it again? Good as a proxy for societies? What [/INST] good is a proxy for the stability and fitness of a civilization? </s><s>[INST] Uh that's a good definition. Thank you. You're throwing some bombs today. Okay, okay. Um this is exciting. Sorry to interrupt your flow there, but just a good damn good. Like uh so in that sense, that's kind of optimistic view that if by definition good as a proxy for stability, then it's going to be stable unless the entire world just blows itself up. So good wins in the end. By definition. Yeah. Or uh no actually, well, good wins unless it all goes to complete destruction. Beauty that's beautifully put on the topic of uh sort of, you know, good and evil being, human illusions. You've said that more broadly than that about truth. That it is easier in some ways to be unified under truth because it is universal than it is to be unified under belief. Which at times can be completely subjective. So what is the nature of truth to you? Can can we understand the world objectively or as most of what we can understand about the world is just uh subjective opinions that we kind of all agree on in these little collectives and over time it kind of evolves completely detached from objective reality. [/INST] I think this is the greatest argument for objectivity. Uh is that something that is objectively true cannot be true to me and untrue to to you, you can feel that it's that it's untrue, but that would be uh unproductive and create unnecessary tension and conflict. I think this is one reason for the importance of science as a tool for stability. If science is the search for truth. Um and truth can never really be, I shouldn't say that truth should never be an engine uh of conflict because no two people should disagree on something which is objectively true, then in some sense, search for truth is searching for a common ground where we can all exist and live without contradicting or attacking each other, </s><s>[INST] you have a hope that there is a lot of common ground to be discovered? [/INST] Sure. I mean, if we continue scientifically, uh we are discovering truth and in that discovering common ground on which we can all agree. That's that's one reason why I think uh caring about science, if you have a culture which cares very deeply about science, that's a culture which is not necessarily bound to endure unwarranted internal conflict. I think that's one reason that I'm so passionate about science is its search for universal ground. </s> |
<s>[INST] Yeah, So that's super exciting. I mean it's not just that it's connected to all kinds of tooling and you can go on mobile and with this full light, it can go in the cloud or serving and so on and always connected together. Some of the best software written ever is often done by one person sometimes too. So with a google you're now seeing sort of caress having to be integrated intensive form. Sure has a ton of engineers working on so and there's, I'm sure a lot of tricky design decisions to be made. How does that process usually happen from at least your perspective? What are the, what are the debates like? What is there? A lot of thinking? Considering different options and so on. [/INST] Yes. So a lot of the time I spent at google is actually discussing design discussions, right? Uh, writing design darks, participating in design review meetings and so on. Uh, this is, you know, as important as actually writing the code. </s><s>[INST] Right? What? [/INST] So there's a lot of thoughts, There's a lot of thought and a lot of care that is uh, taken in coming up with these decisions and taking into account all of our users because tensorflow is this extremely diverse user base. Right? It's not, it's not like just one user segment where everyone has the same needs. Uh we have a small scale production uses large scale production users, we have uh, startups, we have researchers, um, you know, it's sort of other place and we have to catch up to all of the onions. </s><s>[INST] If I just look at the standards debates of C plus plus or python, there's some heated debates. Do you have those at google? I mean, they're not heated in terms of emotionally, but there's probably multiple ways to do it. Right? So how do you arrive through those design meetings at the best way to do it? Especially in deep learning where the field is evolving as you're doing it? Is there some magic to it? There's some magic to the process. [/INST] I don't know, just magic to the process, but there definitely is a process. So making design decisions about satisfying a set of constraints, but also trying to do so in the simplest way possible because this is what can be maintained. This is what can be expanded in the future. So you don't want to naively satisfy the constraints by just, you know, for each capability you need available. You're going to come up with one argument in the api and so on. You want to design GPS, um, that are modular and hierarchical so that they have uh an an api surface that is as small as possible. Right? And, And you want uh these smaller hierarchical architecture to reflect the way that domain experts think about the problem because like as a domain expert when when you're reading about a new ep you're reading toil or some darks pages um you already have a way that you're thinking about the problem. You already have like uh certain concepts in mind and you're thinking about how they relate together and when you're reading docks you're trying to build as quickly as possible and mapping between the concepts feature the new API and the concept in your mind. So you're trying to map your mental model as a domain expert to the way things work in the API. So you need an API and an underlying implementation that are reflecting the way people think about these things. So in minimizing </s><s>[INST] the time it takes to do the mapping. [/INST] Yes. Minimizing the time the cognitive load there is in interest in this new knowledge about AP and NPR should not be self referential. Are referring to implementation details, it should only be referring to domain specific concepts that people already understand. </s><s>[INST] Brilliant. So what's the future of keras and tensorflow look like? What does tensorflow? Three point Oh look like. [/INST] So that's going to fall in the future for me too. Especially uh since I'm not I'm not even the one making these decisions. But so from my perspective which is you know just one perspective among many different perspectives on the transfer team. I'm really excited by developing even higher level api s higher level and Cara's I'm very excited by hyper parameter tuning by automated machine learning or two Ml I think the future is not just, you know, defining a model like uh like you were assembling lego blocks and then collect fit on it. It's more like an auto magical model that we just look at your data and optimize the objective you you're after. Right? So that's that's uh what what I'm looking into. </s><s>[INST] Yeah. So you put the baby into a room with the problem and come back a few hours later with a fully solved problem. [/INST] Exactly. It's not like a box of legos, right? It's more like the combination of a kid that's very good at legos and a box of figures. It's just building the thing. Very nice. </s><s>[INST] So that's that's an exciting future. And I think there's a huge amount of applications and revolutions to be had under the constraints of the discussion we previously had. But what do you think of the current limits of deep learning if we look specifically at these function approximate ear's that tries to generalize from data? You've talked about local versus extreme generalization. You mentioned in your networks don't generalize? Well humans do. So there's this gap. So and you've also mentioned that generalization. Extreme generalization requires something like reasoning to fill those gaps. So how can you start trying to build systems like that. [/INST] Right. Yeah. So this is this is by design. Right? Deep learning models are like huge biometric models differentiable, so continuous uh that go from an input space to unite with space and they're trained with gradient descent. So they're trying to pretty much point by point. Uh they are learning continuous geometric morphing from from an input vector space tonight protective space. Right. And because this is done point by point, a deep neural network can only make sense of points in experience space that are very close to things that has already seen in stream data. At best. It can do interpolation across points. But that means, you know, it means in order to train your network you need a dense sampling of the input cross output space almost a point by point sampling, which can be very expensive if you're dealing with complex real world problems like autonomous driving, for instance, or robotics. Uh it's doable if you're looking at the subset of the of the visual space. But even then it's still fairly expensive. Is still in millions of examples and it's only going to be able to make sense of things that are very close to waste has seen before. And in contrast to that. But of course you have human intelligence. But even if you're not looking at human intelligence, um you can look at very simple rules algorithms if you have a symbolic cruel, it can actually apply to a very, very large set of inputs because it is abstract. It is not obtained um uh by doing a point by point mapping, right? For instance, if you try to learn a sorting algorithm using a deep neural network well you're very much limited to learning point by point what the sort of representation of this specific list is like but instead you could have a very very simple sorting algorithm written a few lines, maybe it's just you know, two nested loops. Um and it can process any list at all because it is abstract because it is a set of rules. So the planning is really like point by point, geometric, more fins, more things strange is going in this sense. And meanwhile abstract rules can generalize much better and I think the future is really to combine the two. So </s> |
<s>[INST] And like you said like you know the exact $1,000 mark might be uh might not be the correct one, but you should take the steps to try to uh to implement these solutions and see see [/INST] what works. </s><s>[INST] So I think you and I eat some more diets and at least I was uh [/INST] the first time I've heard this. </s><s>[INST] Yeah, so I was doing [/INST] it first time anyone has said that to me in this case. Yeah, </s><s>[INST] but it's becoming more and more cool and but I was doing it before it was cool. So intermittent fasting and fasting in general, I really enjoy, I love food but I enjoy the the I also love suffering because I'm Russian so fast thing kind of makes you appreciate them uh makes you appreciate what it is to be human somehow. So, but I have outside the philosophical stuff, I have a more specific question. It also helps me as a programmer and a deep thinker like from the scientific perspective to sit there for many hours and focus deeply. Maybe you were a hacker before you were ceo what have you learned about diet lifestyle mindset that helps you maximize mental performance to be able to focus for uh to think deeply in this world of distractions. [/INST] I think I just took it for granted for too long um which aspects just a social structure of, we eat three meals a day and there's snacks in between and um I just never really asked the question why, oh, </s><s>[INST] by the way, in case people don't know, I think a lot of people know where you, you at least do famously eat once a day, you still eat once a [/INST] day. I ate dinner </s><s>[INST] by the way, what made you decide to eat once a day because to me that was a huge revolution that you don't have to eat breakfast. I was like, I felt like I was a rebel, like I like abandoned my parents or something and it doesn't [/INST] anarchist when you, when you first, like the first week you start doing it feels you kind of like have a superpower, then you realize it's not really a superpower, but it, I think he realized at least I realized just how much is how much our mind um uh dictates what were possible of um and uh, and sometimes we have structures around us that incentivize like, you know, there's three million a day thing, which was purely social um structure versus necessity for our health and for our bodies and um I, I did it just, I, I started doing it because I played a lot with my diet one, I was a kid and I was vegan for two years and just went all over the place, um just because a health is the most precious thing we have and none of us really understand it. So being able to ask the question through experiments that I can perform in myself and um learn about I is compelling to me. And I heard this one guy on the podcast, Wim Hoff, um who is famous for doing I spouse and holding his breath and all these things. Um he said he only eats one meal a day. I'm like, wow, that sounds super challenging and comfortable. I'm gonna do it. So I just, I learned the most when I make myself, I want to say suffer, but when I make myself feel uncomfortable, because everything comes to bear in those moments and uh and you really learn what you're, what you're about or what you're not. Um so I, I've been doing that my whole life, like when I was a kid, I could not, like I was, I could not speak like I had to go to a speech therapist and it made me extremely shy and then one day I realized I can't keep doing this and I signed up for the, for the speech um club and you know, it was the most uncomfortable thing I could imagine doing getting a topic on a note card, having five minutes to write a speech about whatever that topic is not being able to use the note card when I was speaking and speaking for five minutes about that topic. So, um, but it just, it puts so much, it gave me so much perspective around the power of communication around my own deficiencies and around um if I set my mind to do something, I'll do it. So it gave me a lot more confident. So I see fasting in the same light. This is something that it was interesting, challenging, uncomfortable and has given me so much learning and benefit as a result and will lead to other things that I'll experiment with and play with. But um yeah it does feel a little bit like a superpower. Sometimes The most boring superpower one can imagine. </s><s>[INST] No it's quite incredible. The clarity of mind is pretty interesting. Speaking of suffering, you kind of talk about facing difficult ideas. You meditate. You think about the broad context of life of our society. Let me ask sort of apologize again for the romanticized question. But do you ponder your own mortality? Do you think about death? About the finite nous of human existence when you meditate when you think about it and if you do what how do you make sense of it? But this thing ends? [/INST] Well, I don't try to make sense of it. I do think about it every day. I mean it's it's a daily multiple times a day. Are you afraid of death? No, I'm not afraid of it. Um I I think it's um it's a transformation. I don't know to what, but it's also a tool um Two feel the importance of every moment. Um So I I just used as a reminder like I have an hour, is this really what I'm going to spend the hour doing? Like I only have so many more sunsets and sunrises to watch. Like I'm not going to get up for it, I'm not going to make sure that I that I that I try to see it. So it just puts a lot into perspective and it helps me prioritize. Um I think it's I don't I don't see it as something that's like um that I dread or is dreadful. It it's a it's a tool that is available to every single person to use every day because it shows how precious life is and there's reminders every single day, whether it be your own health or a friend or a coworker or something you see in the news. Um So it's to me it's just a question of what we do with our daily reminder. And for me it's um am I really focused on what matters. And sometimes that might be work. Sometimes that might be friendships or family or relationships or whatnot. But that that's it's the ultimate clarified in that sense. </s> |
<s>[INST] deep understanding of [/INST] the cause of fact relationships that are leading you to place that bet in anything okay anything important. Let's see if it was do surgeries and you would say how do I do surgeries? I think it's totally fine to watch all the doctors do the surgeries you can put it on uh take a um a digital camera and do that convert that into a. I algorithms that go to robots and have them do surgeries and I'd be comfortable with that because if it will do if he keeps doing the same thing over and over again and you have enough of that that would be fine. Even though you may not understand the algorithms because you're if the things happening over and over again and you're not asking the future would be the same. That appendicitis or whatever it is will be handled the same way the surgery that's fine. However what happens with A. I is for the most part is it takes a lot of data and it um with a high enough sample size and then it puts together its own algorithms. Okay. There are two ways you can come up with algorithms. You can either take your thinking and express them in algorithms or you can say put the data in and say what is the algorithm when you that's machine learning and when you have machine learning um it'll give you equations which quite often they're not understandable if you would try to say okay now describe what it's telling you, It's very difficult to describe, and so they can escape understanding. And so it's very good for doing those things that can be done over and over again if you're watching and you're not taking that, but if the future is different from the past and you have that, then your future is different from the past and you don't have deep understanding, you're gonna get in trouble. And so that's the main thing, as far as ai is concerned, ai and let's say computer replications of thinking very ways, I think it's particularly good for processing, but but the the notion of what you want to do is better most of the time determined by the human mind. That what are the principles like, okay, how should I raise my Children? It's gonna be a long time before ai you're going to say it has a good enough judgment to do that, who should I marry? All of those things? Maybe you can get the computer to help you, But if you just took data, a new machine learning, it's not going to find it. If you were to then take one of my criteria for um any of those questions and then say put them into an algorithm and you'd be a lot better off than if you took a I to do it. But by and large, the mind should be used for inventing and those creative things. Um and then the computer should be used for processing because it could process a lot more information a lot faster, a lot more accurately and a lot less emotionally. So any notion of thinking in the form of processing type thinking should be done by a computer and anything that is in the notion of doing that other type of thinking should be operating with with the brain operating in a way where you know, you can say ah that makes sense. </s><s>[INST] You know, the process of reducing your understanding down two principles is kind of like the process the first one you mentioned type of ai algorithm where you're encoding your expertise, your trying to program, write a program, the humanist trying to write a program. How do you think that's attainable? The process of reducing principles to a computer program Or when you when you say when you write about when you think about principles, is there still a human element that's not reducible to an algorithm? [/INST] My experience has been that almost all things, including those things that I thought were pretty much impossible to express. I've been able to express in algorithms but that doesn't constitute all things. So you can you can who you can express far more than you can imagine you'll be able to express. So I use the example of okay, it's not how do you raise your Children? Okay, you will be able to take it one piece by piece? Okay. How at what age what school and the way to do that. That with my experience is to take that. And when you're in the moment of making a decision or just passed making a decision to take the time and to write down your criteria for making that decision in words. Okay. That that way you'll get your your principles down on paper. I created an app um online call. It's right now just on the iphone it'll be a it'll be a it'll be a few months, it will be on Andros but it has an app in there that helps people write down their own principles because this is very powerful. So when you're in that moment where you've just you're thinking about it and you're thinking your criteria for you know choosing the school for your child or whatever that might be. And you write down your criteria or whatever they are those principles you write down and you you that will at that moment make you articulate your principles in a very valuable way. And if you have the way that we operate that you have easy access. So the next time that comes along you can go to that or you can show those principles to others to see if they're the right principles, you will get a clarity of that principle that's really invaluable in words and that will help you a lot. But then you start to think how do I express that in data and it will shock you about how you can do that. You'll you'll form an equation that will show the relationship between these particular parts and then the essentially the variables that are going to go into that particular equation and you will be able to do that and you take that little piece and you put it into the computer and then take the next little piece and you put that into the computer and before you know it you will have a decision making system that's of the sort that I'm describing. So </s> |
<s>[INST] But to you he was fun. [/INST] He was a lot of fun. He wasn't my dad, but I spent a lot of time with him. I was into boating accidents with him, you know to boating accidents involved. Yes, he was usually alcohol was involved when he left his house um and when he was at home as well, but I was in to boating accidents and do do you know how fun someone has to be to get in a second boating accident, do you know what a good time, someone has to be to get in a boat with them after you've already gotten in one wreck, </s><s>[INST] never get fooled. What was that line? George bush never get fooled again. [/INST] Right? So if you're getting fooled again, you know there's a reason for it. But he was a he was a fun guy. He did have a death wish the second boating accident, he grabbed me and said you can't hang out with me anymore. And I said why? He goes, I'm trying to kill myself. And I was like, oh and then I understood that like all of the fun under the fun lived a very destructive person who not only was destructive but wanted to die. </s><s>[INST] So speaking of fun, people that want to die? I don't know if you're we can go hunter? S Thompson, but uh Charles bukowski, I don't know if you're aware of the guy [/INST] I'm aware of, I'm sure I've read some </s><s>[INST] stuff, so his tombstone says, I just want to ask you a question about it. His tombstone says, don't try interesting, what do you think about that advice as a way to approach life? [/INST] I I think for many people it's a good, good advice because the people that are going to try, we'll do anyway and the people that need to be told there's a whole cottage industry now of motivational speakers and life coaches and gurus uh that tell people uh that they all have to own their own business and be their own boss and be a disruptor and get into industries, you know, that's incredibly unrealistic for most people. Most people are not suited for that and you know, the Gary V's in the world to tell everybody that they should just hustle and grind and hustle and grind very light on the specifics of what they should actually do. Um yeah, I think a lot of people that's not horrible advice to give to a lot of people, I think I think my generation got horrible advice from our our parents, from our teachers and that advice was follow your dreams? Uh nobody and that was it by the way? There was no, like, what are your dreams? Are they realistic? What happens when they don't work out? Well your dreams make you happy? Are your dreams real? Do they exist on earth? Can you follow everybody follow your dreams? You can be anything you want to be horrible advice, horrible advice. Worst advice you can ever give a generation of people. Really, truly, I mean, think about think about it if you were talking to somebody and you were trying to make them succeed, are there any two uh, worse pieces of advice to give them, then follow your dreams and you can be anything. You want to be? Those to me are the two most destructive pieces of information I've ever heard. </s><s>[INST] So let me push back because that's fair many [/INST] people do. </s><s>[INST] So, uh, yeah, this is like a rigorous journalistic interview, Larry King by the way passed away today. So I'm taking over the I'm carrying the very sad, I'm king. Yeah. What was that even going to say? Oh, let me push back on the follow your dream thing is I come from an immigrant family where I was always working extremely hard and stuff like in a stupid way I would, I love, there's something about me that loves hitting my head against the wall over and over and over until either my head breaks or the wall breaks. Just like I love that dedication for no purpose whatsoever. It's like the mouse that's stuck in a cage or whatever. And you know, and everybody always told me my family, the people around me to sort of uh, the epitome of what I could achieve is to be kind of a stable job. You know, the old like lawyer doctor in my case, it's like scientists and so on. But I had these dreams at this fire, you know about love robots and that nobody ever gave me permission to pursue those dreams. I know you're supposed to grab it yourself. Nobody is supposed to give you permission. But there's something about just people saying, you know, fuck what everyone else thinks. Like giving you permission a parent or somebody like that saying, do your own thing, go become an actor, go become like do the crazy thing. You're not supposed to do an artist, go build a company, quit school, All that kind of stuff. [/INST] Sure. </s><s>[INST] That's the push back against the uh, follow your dreams as a, in [/INST] mass. If you were to look at mass in mass, if you were to look at statistically how few people that works out for, I'm just, let's be very honest, be very honest. So, I mean like, yeah, if you're gonna go be an actor, I was broke for 10 years before I became a, before I was making money as a comedian. I get it. I didn't need Gary Vanya chuck to tell me to follow my thing, right? And here's the other thing. I was kind of funny and like I was kind of a lot of things were in my favor of being a comedian, right? I had this kind of crazy fun life, I had a lot of stories, I had exhausted or I was willing to fail. I had failed before I was broke. I didn't care about being broke, I knew how to be broke. Um I had, I was shameless to, to a degree, I was, I would get on a stage night after night and be laughed at, I would have a high threshold for being embarrassed. I had a high threshold for people thinking that I was a scumbag, right? And showing up at family parties and being like, yeah, I still really don't have a job and I'm just, I work at comedy clubs kind of and I get booked when I can. Um and I, I was, you know, suited for it. There's this idea that people can just roam around the world injecting themselves into other things. They have no aptitude for it all. And will that to happen? A small percentage of people might be able to do that. But the vast majority of people have something they might key into that they're meant to do like you loved robots, You love technology and you found a place in that world where you thrive. But I think many people, a lot of people love robots. Right? So a lot of people think everything you do is interesting. I think your ship is fascinating. I I watch you or podcast and I think it's very interesting. I have no place in your world. You know what I mean? I have no place in that world. I don't like remedial math. I don't like community college math. I think it's a waste of my time. </s> |
<s>[INST] Yeah, I didn't think you would. No, because immediately everything stops being fun. The first, it's only fun the first time. But if you want it to be fun. But like what would be my source of fun? I feel like I would, like on day four, just to get off, [/INST] I would need to like do like nuclear war. </s><s>[INST] Yeah, but if you want it to be fun. [/INST] Because it'll escalate quickly. </s><s>[INST] I feel like if everything is possible. I assume you mean like something that like is not just normal human things. Yeah, magical world. Magical world. Then you start escalating really quickly. Like I wonder, I'll probably do like, I want everybody to just fly into the air and hover in the air. Everybody. And then you're like, oh, life is meaningless. Like why does, like you go, I feel like you get, no, actually that'd be a really interesting experiment. Like what are the limits? [/INST] Like are we all capable of becoming psychopaths essentially? </s><s>[INST] Yeah, magical world. Like I like to believe not. There's a very hard limits on that. Like in our own mind, like of basic compassion. Because I love being compassionate towards other human beings. And it's one of the things I think about if you give me power, like a lot of power, like absolute power. And I think that's the power you mentioned is the scariest kind of power. Cause it's like, it's not even power in this normal world. It's like magical power where you lose, it's a dream world power where you like video game power. You don't even think of it as reality. You could just mess with the world. And I feel like that's terrifying. Yeah, you'd basically be God. God, yeah. But without like, I feel like the idea of God, it wants to like kind of keep things [/INST] like functioning properly. And then you'd probably would, if you wanted to keep them functioning properly, then it would wrap it up. Like you would never experience a time where you're like, oh no, that was a mistake. Because as soon as you, like before you even experienced that the world would shift to match it. </s><s>[INST] Yeah. Oh, interesting. No, I think I would actually, I take it back. I think I would regret the first time I heard somebody. See in my visualization was like a video game where everybody's like NPC really dumb. No, I think the first time I witnessed pain from anybody, that's when I would stop. And I would probably run into that very quickly. Like even just the hovering, make a person hover. And they're going to be probably really upset with the hovering, right? And so I'm going to be like, no, don't do that anymore. And then I'll probably go to, honestly, I'll just return back to my normal life. [/INST] Yeah, that's kind of what I feel like. Like if I had the power to do anything, I think I would probably want to have a life </s><s>[INST] very similar to where I am now. Yeah. Yeah. I mean, there's, it's like with Uber, like it would be probably more convenient to do certain things. But even then, like the struggle like I've got a flat tire, so I have to fix that. I kind of, the flat tire makes everything more beautiful. It's like cool, I can do like a normal manual thing. But also it makes you like appreciate your car, appreciate transportation, appreciate the convenience, [/INST] the transportation, all of it. I know some people who would like call this a bunch of copium like you just sort of making do with what you have, like we wouldn't go back to Amish times or like pre-technology because to like in order to make ourselves appreciate things more and so it seems like a hindsight reasoning uh which is like I can </s><s>[INST] appreciate that argument but I don't know I'm like anyone who uses sorry to interrupt the word copium [/INST] in their um in their argumentation um I think it's sus it's sus yeah it's sus yeah it's sus </s><s>[INST] my entire argument is now no I'm just kidding I'm sorry go ahead sorry I interrupted rudely the floor of thought uh but you you so you don't think so in part you disagree with that kind of [/INST] argument um yeah because I think people have this idea that if you uh like come to accept or like find meaning in what you have now this is sort of at odds with trying to improve it and right I don't find this to be the case I find like the attempt to improve it to also be part of of it. I enjoy the fact that there's something problematic going on because now I get the experience of striving to make it go away. That in itself is where the meaning lies. It's not just that things are bad, it's that things are bad and we're trying to stop it </s><s>[INST] and also. Exactly. If you combine that with a sense of optimism that the future can be better, yeah, that feeds into this productive effort of making things better. It somehow makes the vision of the things that are better more intense, having experienced [/INST] shitty things. </s><s>[INST] Yeah. So we talked about free will and consciousness and what drives human civilization. Question left unanswered. It's a homework problem for the reader. Okay, let's. [/INST] I'm going to get like a scoreboard at the end, the amount of questions. The answer. </s><s>[INST] Complete successfully versus not. The answer. Complete successfully versus not. Like polls. Yeah. [/INST] Can we talk about some practical things? </s><s>[INST] Yeah, sure. So one of the many amazing things, I think of you as a researcher, but you've also been [/INST] doing research in the field. Yeah fieltrick. Fielwork. </s><s>[INST] structural work. The sex work. How did you get? [/INST] What's the the short and a long story of how you got into sex work? I get into sex work well that I mean there's a whole like childhood thing where I was conservatively homeschooled. </s> |
<s>[INST] and counterintuitively, the machine learning mechanism you can say is domain specific, but because it's leveraging data, it's actually could be very broad in terms of in terms of the domains that could be applied in. [/INST] Yeah, that's exactly right sort of it's almost </s><s>[INST] Sort of people sometimes talk about the idea of software 2.0, we're almost taking another step up in the abstraction layer in designing machine learning systems. Because now you're programming in the space of data, in the space of hyper parameters is changing fundamentally the nature of programming. And so the specialized devices that accelerate the performance, especially neural network based machine learning systems, might become the new general. [/INST] Yes. So the this thing that's interesting to point out these are not coral these are not tied together. The enthusiasm about machine learning about creating programs driven from data that we should figure out the answers from data rather than kind of top down which classically the way most programming is done in the way artificial intelligence has to be done. That's a movement that's going on at the same time coincidentally. And and the and the first word machine learning machines, right? So that's going to increase the demand for computing because instead of programmers being smart writing those, those things down, we're gonna instead use computers to examine a lot of data to kind of create the programs. That's the idea. And remarkably this gets used for all kinds of things very successfully. The image recognition, the language translation, the game playing. And you know, it gets into uh pieces of the software stack, like databases and stuff like that. We're not quite sure how general purposes but that's going on independent hardware stuff. What's happening on the hardware side is moore's law is slowing down, right? When we need a lot more cycles. It's failing and it's failing us right, when we need it because there's going to be a greater in peace, a greater increase in computing. And then this idea that we're going to do so called domain specific. Here's a domain that your greatest fear is you'll make this one thing work. And that will help, you know, 5% of the people in the world. Well, this this looks like it's a very general purpose thing. So the timing is fortuitous that if we can perhaps if we can keep building hardware that will accelerate machine learning the neural networks, that will be the timing will be right. That that neural network revolution will transform Software, the so called Software 2.0 and the software the future will be very different from the software in the past. And just as our microprocessors, even though we're still going to have that same basic risk instructions to run a big pieces of software stack, like user interfaces and stuff like that. We can accelerate the kind of the small piece that's computational intensive. It's not lots of lines of code, but it takes a lot of cycles to run that code that that's going to be the accelerator piece. So that's what makes us from a computer designers perspective a really interesting decade. Uh But Hennessy and I talked about in the title of our touring warrant speech is a new golden age. We we see this as a very exciting decade, much like when we were assistant professors and the risk stuff was going on. That was a very exciting time, was where we were changing what was going on. We see this happening again tremendous opportunities of people because we're fundamentally changing how software is built and how we're running it. </s><s>[INST] So which layer of the abstraction do you think most of the acceleration might be happening if you look in the next 10 years sort of google is working on a lot of exciting stuff with the tpu sort of, there's a closer to the hardware that could be optimizations around the uh closer to the instruction set that could be optimization at the compiler level. It could be even at the higher level software stack. [/INST] Yeah, it's gonna be, I mean if you think about the the old risk, this debate, it was both uh it was software hardware, it was the compilers improving as well as the architecture improving and that's likely to be the way things are now with machine learning. They are using uh domain specific languages. The languages like tensorflow and pytorch are very popular with the machine learning people that those are raising the level of distraction. It's easier for people to write machine learning in these uh, domain specific languages, like, like pytorch and tensorflow, </s><s>[INST] so where the most optimization [/INST] and so, and so there'll be both the compiler piece and the hardware piece underneath it. So, as you, kind of, the fatal flaw for hardware people is to create really great hardware, but not have brought along the compilers. And what we're seeing right now in the marketplace because of this enthusiasm around hardware for machine learning is getting, you know, probably a billions of dollars invested in startup companies were seeing startup companies go belly up because they focus on the hard work, but didn't bring the software stack along. Uh we talked about benchmarks earlier. So I participated uh in machine learning, didn't really have a set of benchmarks. Uh I think just two years ago, they didn't have a set of benchmarks and we've created something called ml perf, which is machine learning benchmarks sweet and pretty much the companies who didn't invest in software stack couldn't run ml perfectly well and the ones who did invest in software stack did, and we're seeing, you know, like kind of in computer architecture, this is what happens. You have these arguments about risk versus cis people spend billions of dollars in the marketplace to see who wins. And it's not it's not a perfect comparison, but it kind of sorts things out and we're seeing companies go out of business and then companies like, like there's a company in Israel called Havana, they came up with machine learning accelerators. They had good ml Perf scores. Uh Intel had acquired a company earlier called Nirvana a couple years ago. They didn't reveal them per scores, which was suspicious, but a month ago, uh Intel announced that they're canceling the Nirvana product line and they've bought Havana for $2 billion. And Intel is going to be shipping Gabbana chips which have hardware and software and run the ml perf programs pretty well. And that's going to be their product line in the future, </s> |
<s>[INST] let me ask you because you've really challenged a lot of ideas in biology in in the work you do probably because some of your rebelliousness comes from the fact that you came from a different field of computer engineering. But could you give advice to young people today in high school or college that are trying to pave their life story, whether it's in science or elsewhere, how they can have a career, they can be proud of or a life, they can be proud of advice [/INST] but it's dangerous to give advice because things change so fast. But one central thing I can say moving up and and through academia and whatnot. You will be surrounded by really smart people and what you need to do is be very careful at distinguishing specific critique versus kind of meta, meta advice. And what I mean by that is if if somebody really smart and successful and obviously competent is giving you specific critiques on what you've done it, that's gold, that's an opportunity to hone your craft to get better at what you're doing to learn to find your mistakes. Like that's great if they are telling you what you ought to be studying, how you ought to approach things, what is the right way to think about things you should probably ignore most of that. And the reason I make that distinction is that a lot of really um </s><s>[INST] really [/INST] successful people are very well calibrated on their own ideas and they in their own field and their own, you know sort of area and they know exactly what works and what doesn't and what's good and what's bad, but they're not calibrated on your ideas. And so so uh the things they will, they will say, oh, you know, this is a dumb idea, don't do this and you shouldn't do that. That stuff is generally uh worse than worse than useless. It can be very, very um uh demoralizing and and and and really limiting. And so so what I say to people is read very broadly work really hard to know what you're talking about, take all specific criticism as a, as a as an opportunity to improve what you're doing and then completely ignore everything else. Because I just tell you from, like from from my own experience, most of what I consider to be interesting and useful things that we've done very smart people have said this is a terrible idea. Don't, don't, don't do that, don't, you know, just um, yeah, I think, I think we we just don't know, we we have no idea beyond beyond our own, like at best we know what we ought to be doing. We very rarely know what anybody else should be doing. Yeah, </s><s>[INST] and their ideas, their perspective has been also calibrated, not just in their field and specific situation, but also on a state of that field at a particular time in the past. So there's not many people in this world, they're able to achieve revolutionary success multiple times in their life. So whenever you say, somebody very smart, usually what that means is somebody who's smart who achieved the success at certain point in their life, and people often get stuck in that place where they found success to be constantly challenging your worldview is a very difficult thing. Um, so yeah, and also at the same time, probably if a lot of people tell that's the weird thing about life, if a lot of people tell you that something is stupid or it's not gonna work, That either means it's stupid. It's not gonna work or it's actually a great opportunity to do something new and you don't know which one it is. It's probably equally likely to be either if, well, I don't know the probabilities, um, depends how lucky you are, depends how brilliant you are, but you don't know. And so you can take that advice as actual data. [/INST] Yeah. You have to, you have to, and this is, this is kind of hard and fuzzy, like hard to describe and, and fuzzy, but I'm a firm believer that you have to build up your own intuition. So over time, right? You have to take your own risks that seem like they make sense to you and then learn from that and build up so that you can trust your own gut about what's a good idea. Even when, and then sometimes you'll make mistakes and they'll turn out to be a dead end and that's fine. That's, that's science. But, but um, you know what I tell my students is, uh, life is hard and science is hard and you're gonna sweat and bleed and everything and you should be doing that for ideas that, that, that really fire you up inside and, and um, you know, and, and, and really don't let, uh, kind of the, the common denominator of standardized approaches to things slow you down. </s><s>[INST] So you mentioned plan area being in some sense immortal, what's the role of death in life? What's the role of death in this whole process we have, is it uh, when you look at biological systems, is death an important feature, especially as you climb up the hierarchy of competency boy? [/INST] That's an interesting question. Um, I think that uh, it's certainly a factor that promotes change and turnover and uh, an opportunity to do something different the next time, um, for a larger scale system. So apoptosis, you know, it's really, it's really interesting. I mean, death is really interesting in a number of ways. One is like, you can think about like what was the first thing to die? You know, that's, that's an interesting question. What was the first creature that you could say actually die? It's a tough, it's a tough thing because we don't have a great definition for it. So if you bring a cabbage home and you put it in your fridge, at what point are you gonna say it's died right then? So, so that's, it's kind of hard um, to know. There's also there's also, uh, there's, there's, there's one paper in which I talk about this idea that, I mean think about think about this and imagine that you have you have a creature that's aquatic, let's say, let's say it's a, it's a frog or something or, or a chapel and the animal dies in the in the pond, it dies for whatever reason most of the cells are still alive. So you can imagine that if when it died there was some sort of breakdown of of the of the connectivity between the cells a bunch of cells crawled off. They could have a life as amoebas. They some of them could join together and become a and toodle around. Right? So we know from plan area that there are cells that don't obey the hey flick limit and just sort of live live forever. So you could imagine an organism that when the organism dies it doesn't disappear. Rather the individual cells that are still alive crawl off and have a completely different kind of lifestyle and maybe come back together as something else or maybe they don't. So so all of this I'm sure is happening somewhere on some on some on some planet. So, so um death in any case, I mean we already kind of knew this because the molecules we, you know, we know that when something dies the molecules go through the ecosystem. But even the cells don't necessarily die at that point, they might have another life in a in a different, in a different way you can think about something like hell. Right. The hela cell line, you know that has this that's had this incredible life. There are way more hela cells now than there ever been than there than there were when when she was alive it </s> |
<s>[INST] So you've written some of my favorite books all over the place. So starting from enlightenment now to uh the Better Angels of our nature blank slate, how the mind works. The one about language, language instinct. Uh Bill Gates, Big fan too. A set of your most recent book that it's uh my new favorite book of all time. Um, so for you as an author, what was the book early on in your life that had a profound impact on the way you saw the world? [/INST] Certainly this book Enlightenment now is influenced by um David Deutsch is the beginning of infinity. They're rather deep reflection on knowledge and the power of knowledge to improve the human condition. Uh they end with bits of wisdom such as that problems are inevitable, but problems are solvable given the right knowledge and that solutions create new problems have to be solved in their turn. That's I think kind of wisdom about the human condition that influenced the writing of this book. There's some books that are excellent but obscure, some of which I have. On my uh, on a page of my website, I read a book called The History of Force self published by a political scientist named James Pain on the historical decline of violence. And that was one of the inspirations for the Better Angels of our Nature. Uh the um, what </s><s>[INST] about early on back when you were maybe a teenager. [/INST] I loved a book called 123 Infinity. When I was a young adult, I read that book by George Game off the physicist, very accessible and humorous explanations of relativity of number. Theory Of uh dimensionality, high multiple dimensional spaces. Uh in in a way that I think is still delightful 70 years after it was published, I like that the Time Life Science series. These are books that would arrive every month that my my mother subscribed to each one on a different topic, one would be on electricity, what would be on forests want to be on evolution? And then one was on the mind and I was just intrigued that there could be a science of mind. And that book I would cite as an influence as well. Then </s><s>[INST] later on you fell in love with the idea of studying the mind. It was just one thing that grabbed you. It was [/INST] one of the things I would say. Um the uh </s><s>[INST] I read as [/INST] a college student, the book reflections on language by Noam Chomsky spent most of his career here at M. I. T. Richard Dawkins two books, the blind watchmaker in the selfish gene were enormously influential partly for mainly for the content, but also for the writing style, the ability to explain abstract concepts in lively prose. Stephen jay Gould's first collection ever since Darwin also. Uh excellent example of lively writing George Miller psychologists that most psychologists are familiar with came up with the idea that human memory has a capacity of seven plus or -2 chunks. That's probably his biggest claim to fame. But he wrote a couple of books on language and communication that I read as an undergraduate. Again beautifully written and intellectually deep. </s><s>[INST] Wonderful steven. Thank you so much for taking the time today. [/INST] My pleasure. Thanks a lot lex. </s> |
<s>[INST] right? [/INST] So how </s><s>[INST] it would look, how you would feel. All [/INST] of it. It was it was all of those physical things around that. And watching the process to get there. That was enlightening for me, right? It opened my mind to go, oh, okay, just like there's a process for all these other things. It wasn't just magic and you say, ha ha there it is. It was really a process of refinement, you know, of opening the funnel at the beginning and refining down over time to get to that final, the final and selecting and doing the selection and certain types. You could, certain times there were opinion based design </s><s>[INST] but [/INST] a lot of data, a lot of data driven designs of what can we, what can we deliver in volume, what can we do different things. So you always had these constraints that you had to work with under and sometimes they and the team, not just I would say we need this and we're like we can't deliver that, but maybe we were able to work together to find different design characteristics and different implementation characteristics that could get to that point without what they were describing and instead of yes, yes, yes, no, no, no. Let's find some other way to solve the problem together. </s><s>[INST] Yeah. Is, and I've seen this. Um, and several companies have more closer interact with like Tesla as an example, sometimes, you know, talking about curves, sometimes it's very painful on the engineering side to to deliver a very specific kind of And one question that comes up in my mind is like, well, how far should we go to try to deliver a tiny adjustment in a curve in the curvature or in a like the whatever the form factor is in the color of the material When the cost is like 10 X to deliver. Not financially, but just like how many problems still have to solve. Um, [/INST] I don't know, I don't know </s><s>[INST] if you can say wisdom to that because because when you're thinking about curves, you're designing in the space of ideas, you're like platonic forms kind of thing. Not always grounded to like how much this is how much pain is going to be involved in delivering this, but that's as you should perhaps because then if you're always thinking about the pain required to deliver this thing, you would be too conservative. You wouldn't do the wild ideas [/INST] right? Exactly. But you have to understand again the why behind it. And at nest when we had limited resources, you know, putting a screwdriver in the box, a custom designed screwdriver in the box was born out of those experiences I had at Apple and seeing how you can create something that's emotional. It's part of marketing and it's part of the product experience overall, even though it seems extraneous. I went back and made the design team and the mechanical team changed some curves on the nest, protect the smoke and Ceo detector. We did at nest after they had already tooled it. And I said there said this cost more. I said it doesn't look right. There is a but they're like, oh well we had, I said, no, you're gonna go back and you're gonna make that change. I told you you want, we needed to do it. We had a better looking model that is gonna get done. I know it's gonna be a terrible cost to you. But we already had this discussion and that's the way it's going to have to be. And I'm sorry, but it is what it is. Um you know, because it's better for the customer and it looks better in the pictures and all the other stuff. And then we did it and it was great. And everyone agreed it was great at the end, but it was paying to get there. Um those are where those little details are, where the magic comes out, right? And you know, if you don't do, if you don't take those pains and put in the love, the customer's gonna feel, it's going to be there. They're going to feel the pain or they're gonna feel the </s><s>[INST] love if [/INST] you put it in, right? So it depends on you know, how much time and effort you want to put into something and what really matters to you and to how you communicate what you do. </s><s>[INST] We're human beings after all. Is there something you've learned from the tensions that are natural or that happen in teams when they're passionate and they're trying to solve these problems? Is that the way of life and and there's the human drama is that just is that always go is that it is what it is. Does that make you better? Actually, the drama of the tension between personalities and all that kind of stuff. [/INST] Look a roller coaster ride without ups and downs is no fun. </s><s>[INST] It's [/INST] the journey. </s><s>[INST] It's [/INST] the journey that brings, it brings out the best in everyone were forged were tempered by those experiences, not all the ups but also the downs and that's when you get the humanity and the connection and we can tell these stories till we're blue in the face and smile every time because we did something together that we each of us couldn't do apart. But when it comes together, that's where all the emotions happen and that's where if it's born out of the right reasons and the right story and the right way, That's where the magic happens, not just for the customer, but for how it transforms each person who is working on it and they will never forget those experiences in their life positively and negatively. That happened at the time. But they look back and it's only positive because they did something that mattered. </s> |
<s>[INST] 40, I'm pushing 50, I think 48. [/INST] Even more impressive because you know, many people who have been exceedingly high output for a decade or more don't do well, their system breaks </s><s>[INST] down. Well, this is what he was saying. He actually, uh, I mean, I don't listen to all of his interviews, but on that live on the clubhouse, you mentioned that he was kind of worried. It's interesting. He was worried that like sometimes what I think he said is I'm worried that some at some point my brain is just going to fail because of the amount of load is under. Like how much I have to think through throughout the day, like how many like problems you have to think through. You know, it's like puzzles, puzzle solving. [/INST] I would be concerned about taking somebody who's in that regime and suddenly putting them into a regime where they don't have enough to bite down into. Its like my bulldog Costello. He's happiest when chewing and tugging that big old neck of his and he is just not going to become a retriever. He's not gonna, he does well and gets his dopamine hits from chewing and pulling and it, it seems like Ellen is that ended up where he is by way of his natural leanings unless there's a backstory that's um, trauma based or something. And I don't even begin to think that there is, it seems that he has, he's one of those rare individuals in history that has an immense drive to create in all these different domains. I'm just saying the obvious here, but it seems like that's what makes him tick. I mean you're doing an awful lot to </s><s>[INST] well, but the problem is not really. The problem is, um, about I've been on the verge of pulling the trigger on, on starting a company which will increase the workload significantly and I'm attracted to that because of a dream I have. But it's a little bit scary because it can destroy you in a, in a lot of ways. There's two, there's two sources of destruction. So one source is, uh, I've, for the first time in my life a few, um, months ago, I think have gotten, it feels like such a new thing to say it, but I've gotten some hate on the internet. No, I know right, But like I'm such an idiot. I'm so naive to. It was I had the question that I guess a lot of people have when they get hate on the internet is like, it's like mom, why are these people making up stuff about me? You know, that kind of feeling of like why, why are you saying that? And, and the reason I mentioned that is like, well if you go, if you want to go and start a business and do as I think people should when they start a big ambitious business, really try to go big, like what does success look like in terms of your emotional journey, you're going to have a lot of people who make up stuff about you who say negative majority, hopefully if you do a good job will be supportive and but they're still going to be this army of people there and like that, that was scary to me because of how much emotional impact that had on me. [/INST] Well. And I also know a little bit, I have some glimpse into the fact that you put your heart and soul into everything you do. You're not a, you're lighthearted about certain things, but you're even lighthearted about being full gas pedal 24 7. There's kind of this, you know, uh was it um, was it Laird Hamilton's always says, you know, the big wave surfers, uh he always says, you know, um bright, light, dark shadow, you know, and I think it's that intensity and when you do that and then suddenly people are starting to like throw some paint on your picture, you're like, wait, hold, you know, you're going max capacity, but I think the company is an interesting one because you've talked about doing this company before, </s><s>[INST] I've been afraid. I've just not been pulling trigger uh out of fear because I enjoy this life, This is that's inside to draw. But it's ultimately this question of taking a leap is like uh say you're in academia, it's like you're at MIT. Yeah, I really love doing research at MIT. I really loved that life. Why take a leap out? You know? But I did uh because it's been a dream. But now accidentally along the way I found this podcasting thing which is also really fulfilling and you know, it's like why take a leap [/INST] because you have a huge lust for life. Yeah, I mean that's you. I mean sometimes when I'm on the internet and I think is that you hear about it like, oh, it's addicting, you know, Youtube is addicting all that. Actually. Sometimes I think maybe that's true, but a lot of times I just think there's so much here. There's a lot of garbage, but there's so many gems out there in the world now. It's almost like sure how you allocate time is key. But I I think you can do it all. No, maybe not five more things. But it all and and one thing I just had this idea and this is not grounded in any scientific paper, but I think the answer might come to you during this um this torture that you're about yourself through with David because in those mental states you're really asking the question, right? You're asking the question, where is my capacity? And they might even close to my capacity. And if I am what's what's up the most value. I think we find the answers to those things in those non verbal non analytic states, it just comes to us. I </s> |
<s>[INST] And it's fascinating because I think ideologies also have an impulse towards forming taxonomy and there is. Um so just so uh being at M. I. T. I've gotten to learn about this character named Jeffrey Epstein, I didn't know who this was until all the news broke out and so on. And it started to wonder how did all these people at M. I. T. That I admire would hang out with this person just lightly just have conversations. I don't mean any of the bigger things, but even just basic conversations and I think this has to do. You said scientists are widget builders and texana misers. I think there's power in somebody like the nazi regime or like a Jeffrey Epstein just being excited about your widgets and making you feel like the widget serves a greater purpose in the world. And so it's not like you're, you know, some sometimes people say scientists want to make money and uh or they have a big kind of ideological drive behind it. I think there's just nice one, the widgets you like building anyway, somehow somebody convinces you some charismatic person that this widget is actually has a grander purpose and you don't almost feel think about the negative or whether it's positive, just the fact that it's grand is already super exciting. [/INST] Yeah, I think that's right. I think that's the story of verner von braun, you know, in the fascination with rockets and this will, you know, enlarge something in the world and here he is. He's an sS officer, he's working around slave labor. Uh huh. And then, but his rocket then gets compressed into the Western world or the american world and basically launches us to the moon. And we forget about the sauce, how the sausage was made originally. </s><s>[INST] Well, can you talk about him a little bit more because he's such a fascinating character, because he so he's he was a Nazi, but it was also an american and it had such a grand impact on, on both. And like there's this uncomfortable fact that he's, you know, one of the central figures, they gave birth to the american space exploration efforts. Yeah, he's [/INST] An interesting figure, fascinated in a kind of a tunnel vision way with space flight. He makes these beautiful rockets already beginning in the 20s, early 30's ends up for a while at Panama Donde using slave labor to build V two engines and and so forth like that. I remember going to Panama NDA where people have actually tracked the Flights of aborted V two rockets and found some of these beautiful, beautiful old engines, Just the most works of art. These engines used to rain terror on on the british. It's interesting because in that same spot I was hunting for amber Baltic amber because I'm a stone collector and among the amber collectors there, there's a famous story of the Panama to burn. It's called because they find yellow phosphorus. They think it's amber, they put in their pocket and then it dries out and then explodes and creates this big burn burn on their legs. But the whole Nazi regime is full of things like that is full of these scholars who get twisted into a mindset and mm hmm. It's also important to realize that people didn't often see what was coming and we look back and we say, how could you, X, y or Z. But before the holocaust, there's not the holocaust, there are versions of it, but things get on a new meaning, get a new meaning in light of subsequent events </s><s>[INST] and there's an entire propaganda machine that makes it easier for you to to hold the narrative in your head, even if you kind of intuitively know there's something really wrong here because of the propaganda. You can kind of convince yourself to be able to sleep at night. [/INST] That's right. And we have to remember that Goebbels Office was not the Office of propaganda. It was the office of enlightenment of of popular enlightenment and propaganda. So enlightenment </s><s>[INST] enlightenment [/INST] was part of his </s><s>[INST] just the new era of enlightenment. From his perspective, [/INST] it was supposed to be the new age, a new era of enlightenment. It's a little bit like the the kind of myth of Hitler's failed artist and you know, his art is not that bad, you know, there are a lot of artists who are who are worse. And I had a very interesting conversation once with my college roommate who became a librarian at Harvard and at Harvard he met an old old librarian, a german woman who had met Hitler as a kid when she was like eight years old. Her dad was like a gold lighter for the Nuremberg area and she said that for 15 minutes Hitler goes out onto the balcony with her and has this conversation alone with this, you know, eight year old girl and she said he was charming and funny and then he said he loved kids and she she said he was the most charming sort of person and that's part of the history to that. We tend to forget when we make a scarecrow image of this rabid, raging fanatic, you know, there's more to it than that. </s> |
<s>[INST] So what do you think about that psychology that uh looks at all the different possible trajectories of an A. G. I. System, many of which perhaps the majority of which are positive and nevertheless focuses on the negative trajectories. I mean you get to interact with folks, you got to think about this maybe within yourself as well. Um You look at Sam Harris and so on. It seems to be sorry to put it this way but almost more fun to think about the negative possibilities whatever that's deep in our psychology. What do you think about that and how do we deal with it because we want ai to help us. [/INST] So I think there's kind of two problems entailed in that question. Uh The first is more of the question of how can you even picture what a world with a new technology will be like Now imagine we're in 1950 and I'm trying to describe uber to someone. </s><s>[INST] Apps and the internet. Yeah I mean you're that's going to be extremely complicated, but it's [/INST] Imaginable. It's imaginable, right? But and now imagine being in 1950 and predicting Uber, right? And you need to describe the internet, you describe gps, you need to describe the fact that everyone's going to have this phone in their pocket. Yeah. And so I think that just the first truth is that it is hard to picture how a transformative technology will play out in the world. Um We've seen that before with technologies that are far less transformative than a G I will be. And so I think that that one piece is that it's just even hard to imagine and to really put yourself in a world where you can predict what that that positive vision would be like. And you know, I think the second thing is that it is I think it is always easier to support the negative side than the positive side. It's always easier to destroy than create and you know, less than a physical sense and more just in an intellectual sense, right? Because you know, I think that that with creating something, you need to just get a bunch of things right and to destroy, you just need to get one thing wrong. And so I think that what that means is that I think a lot of people's thinking dead ends as soon as they see the negative story, but that being said, I actually actually some hope, right? I think that the positive vision is something that I think can be um is something that we can we can talk about. I think that just simply saying this fact of Yeah, like there's positive, there's negatives. Everyone likes to dwell on the negative people actually respond well to that message and say, huh you're right, there's a part of this that we're not talking about, not thinking about and that's actually something that's that's that's I think really been a key part of how we think about A G. I at open ai right? You can kind of look at it as like okay, like opening, it talks about the fact that there are risks and yet they're trying to build this system. Like how do you square those, those two facts. </s><s>[INST] So do you share the intuition that some people have? I mean from Sam Harris to even Elon musk himself that it's tricky as you develop a G I to keep it from slipping into the existential threats into the negative. What's your intuition about how hard is it to keep a eye development on the positive track? What's your intuition [/INST] there to answer the question? You can really look at how we structure open ai so we really have three main arms, we have capabilities which is actually doing the technical work and pushing forward what these systems can do, there's safety which is working on technical mechanisms to ensure that the systems we build are lined with human values and then there's policy which is making sure that we have governance mechanisms answering that question of well whose values And so I think that the technical safety one is the one that people kind of talk about the most right. You talk about like think about all of the dystopic ai movies, a lot of that is about not having good technical safety in place. Um And what we've been finding is that I think that actually a lot of people look at the technical safety problem and think it's just intractable, right? This question of what do humans want, How am I supposed to write that down? Can I even write down what I want? No way. And then they stop there. But the thing is we've already built systems that are able to learn things that humans can't specify. You know, even the rules for how to recognize if there's a cat or a dog in an image, turns out it's intractable to write that down. And yet we're able to learn it and that what we're seeing with systems, we build it open ai and they're still in early proof of concept stage is that you are able to learn human preferences, you're able to learn what humans want from data. Um And so that's kind of the core focus for our technical safety team. And I think that that they're actually we've had some pretty encouraging updates in terms of what we've been able to make work? </s><s>[INST] So you have an intuition and a hope that from data, you know, looking at the value alignment problem from data we can build systems that align with the collective, better angels of our nature. So aligned with the ethics and the morals of human beings [/INST] to even say this in a different way. I mean think about how how do we align humans right? Think about like a human baby can grow up to be an evil person or a great person. And a lot of that is from learning from data, right? That you have some feedback as a child is growing up, they get to see positive examples. And so I think that that just like the only example we have of a general intelligence uh that is able to learn from data to align with human values and to learn values. Um I think we shouldn't be surprised that we can do the same sorts of techniques or whether the same sort of techniques end up being how we we saw the value alignment for a Gs. </s> |
<s>[INST] look at my interviews. Yeah. I think it's kind of productive. Yeah. So what about more prescient for me? I can't believe I'm walking to this fire for no good reason whatsoever. But Anthony Fauci. So let me tell you why I care about Anthony Fauci because I care a lot about science and the way science is viewed in society. And um, not to put it at the at the feet of this one person, but I him and certain members of the scientific community that was responsible for managing the response to covid I think are somewhat or entirely responsible for a significant decrease in trust in science. Yes. No question. In the past couple of years there was [/INST] a poll that just came out this week that said the numbers just collapsed </s><s>[INST] and if you don't blame him for it, I personally blame him for not um improving the problem. And so there's definitely would be harsh conversation there to be had and I think I wanna have it. But how do you do it? It's tough. Yeah. Because you know, again politicians, there's political answers. If you, if they get too frustrated too quickly, they will not explore these difficult things with you, they'll just shut down. But then if you say too many nice things because I I should also say Anthony Fauci is an incredible career. Like there's several hours worth of conversation to be had about how amazing of a person he is. Well, I [/INST] would also be curious about the AIDS stuff because that's something gets criticized about and I wouldn't come out aggressively. I would say let's set the record straight. This is on the criticism you get blah blah blah. Your role in the AIDS crisis. Let's talk about this. And this is something that is important part of american history. There was a pandemic and but it was localized to certain populations and that part of that population at the first at least was pretty much told goodbye and good luck you're gonna have to deal with this. So how did you deal with that? I mean, were you scared of getting AIDS? You know, so on and so forth. But also there was that comment when and correct me if I'm wrong. I'm not a Fauci expert when he basically they told people not to wear masks or they lied about it to some extent because they said that people are going to run out of them or something like that and they admitted they were being inaccurate, I would nail him on that and like, let's address this, were you being dishonest? Is there sometimes when it's important to be dishonest in service of whatever? Also, I would ask him how as someone who's not a politician, whether his level of fame and adulation has gotten to his head. How do you have a perspective when and how does it feel when a sitting senator tells you that you should be imprisoned? Do you think Ted Cruz means it or you think Ted Cruz is just playing to his base? </s><s>[INST] Yeah, I like the same one, I would love to sneak up. I mean that's got question applies to you too. The question applies to me when you start getting more fame or money or power, are you aware of how that changed you and like explore that? Like how has that changed you? Like if you like in the privacy of your mind, Michael malice, like how did you change now that you've gotten more attention? Let's say, you know, or even the success of the book, like, is it like, take, take yourself back to the, you know, you talk about the 20 uh early twenties, the mid twenties person. How are you different from that person? Are you the same person? Are you totally different? That's an interesting thought is Putin the same person in 2020 as he was in 2010 and then in 2000 it's ah it's a nontrivial almost like and then [/INST] the other thing was actually is this is a dynamic system. Like on the one hand he's gonna want to say we got it right every time. Right. But then how is that even possible when you're dealing with the evolving unknown dynamic situation? When did you guys get it wrong? Did that result in lives lost? Do you feel guilty about that? </s><s>[INST] I mean the big problem with the masks, the changing of mind and on the mask is the arrogance and how it was communicated to me a lot of this goes on to uh how things are communicated. It's like it's obvious that you need to change your mind when you get new information or sometimes yeah, you take policies that are like we know the truth but we're going to lie for a particular reason. Like you have good intentions but if you're not able to communicate that later, like we made a mistake [/INST] or even ask him, can you understand how a rational person might choose not to get vaccinated? </s><s>[INST] Yes, yes. [/INST] Yes. And if you can't steal man that then then that's a situation </s><s>[INST] that's a good test and I've tried and some people succeed and some people fail is the ability to really steal man. The other understand that somebody would be hesitant about taking the vaccine. Yeah. It's a giant mess man. Uh this podcasting is is just a fun little conversation but it also has a responsibility. I don't know. I don't know how joe does it. [/INST] I don't think joe cares as much as you do. It's more fun for him in a sense. And he's less concerned about the I mean he's not unconcerned with the cultural impact but for him it's just more growing out. Yeah. Like he doesn't do as much property doesn't come in with three pages single spaced you. No questions. Yeah. And that's why he's talking to blair white for 10 minutes about whether sharks lay eggs without knowing </s> |
<s>[INST] like how that's and of course, [/INST] of course, </s><s>[INST] of course you want to fly by it. You know, there's an there's an argument against that kind of perspective that maybe the thing is dangerous. Maybe we don't, but perhaps that's part of the reason you want to fly by. It is to understand better what it is. If it's a threat, we [/INST] have a lot of contact now that we didn't back then, you know, And so it was still a, hey, is this a balloon is just a drone? You know, at a certain point? And we're also aware of, you know, potential intelligence gathering operations that could be going on. We're up there flying our tactics were emitting, we're practicing our e w you know, we're turning at particular times like there's stuff that can be learned, It's not a secret. And, you know, countries keep different fishing vessels and whatnot in international waters off there. So it's not exactly a secret that we're being observed out there. So to think that a foreign hospital or a foreign nation would want to um, you know, somehow intercept information, whether that's um our radar signals are jamming capabilities to try to um break that down or understand it better be ready for that next fight. Um I mean, that's what that's what scares me about this scenario because we didn't jump, right, the aliens or UFOs we thought you know this is a radar malfunction. We need to be aware of it's a safety issue. And then you know this could be a tactical problem right here because everything we do is based off crypto and and locate, you know locations. Everything is classified. We do out there. Right? And so over time if you gather enough data about those fights and just modern them forever, just like uh some nations do with other piece of technology or software, um they could probably learn a line. So we have to be cognitive effect and defend against it. </s><s>[INST] So what can you say about the other characteristics of these objects? Like shape, size, texture, luminosity? How else to describe object? Is there something that could be said? So you said like there's the takedown radar step one. Now you have clear images that can give you a sense that that's actually a physical object. What else can be said about those physical objects? [/INST] So eventually someone did see one with their own eyeballs, um multiple people And it and they saw it in a somewhat interesting way. Um The object presented itself at the exact altitude and geographic location of the entry points into our working areas. So we enter at a very specific point at a certain altitude and people leave the areas at the same point at a lower altitude, Probably one of the busiest pieces of sky on the eastern seaboard. So two jets from my squadron went out and they went flying and they entered the area where these objects went right between the aircraft </s><s>[INST] they're flying in formation and the object went between the aircraft [/INST] they went between the object I think. I don't think that the object was moving. I don't think it aggressively went at them. I think it was located still there and then they flew through it. Um But they didn't have it on their radar. Um And that would I think the radar might have been malfunctioning. I don't know that for sure. I would like to look into it. But my supposition is that if their radar was malfunctioning it would make sense that they wouldn't avoid the object that was there because they knew these were physical at that point. Um And we we would go up to these objects all the time time and try to see them. We couldn't see them and we didn't know what it was. Um Was it they were they just not there were being fooled was something happening where they where they moving dropping out to the last minute you know we're going by pretty quick. So it's difficult to tell. Um But perhaps if his radar wasn't working he wasn't receiving energy from the jet and of course didn't know that he was there. And so whatever the case was they flew right by and they described it just as a dark gray or black cube. Um inside a clear, translucent sphere and the kind of the apex, a little cube were touching the inside of that sphere, </s><s>[INST] that's an image that's haunting. So what do they think it is? What did they think at that moment? Uh, that they, is it just this kind of cloud of uncertainty that, that they're just describing a geometric object? It's not on radar. So it's unclear what it is. Um, what was, uh, the, any kind of other description they've had of it in terms of the intuition from a pilot's perspective, You know, you have to kind of identify what the thing [/INST] is to answer the first part, they, they actually cancel the flight and came back because they were, you know, like if there's one of these out here, we're almost hitting them and it's right there then um, you know, perhaps we need to get a different jet with better radar, but so they came back and they're in their gear and they're, they're talking to the front desk and talking to skipper and like, hey, we almost hit one of those damn things out there and this kind of was one of those kind of slight watershed moments where we all were kind of like, all right. Like this is a serious deal. Now, You know, maybe it was, maybe we thought they were balloons or drones or malfunctions or maybe we thought it was spying. But the end of the day if we're gonna hit one of these things and we need to, you know, we need to take care of the situation. Um and that's actually when we start submitting hazard reports or has reps to the navel to the naval aviation safety um kind of communication network. And it's, you know, it's not like a big proactive thing where people can go investigate, it's more of a data collection mechanism so that you can kind of share that aggregate data and make sure that things are progressing. Um So it wasn't a mechanism that would result in action being taken, but we were hoping to at least get the message out to whomever was maybe running a classified program that we were not aware of or something like that. That hey, like you could kill somebody here like you've, you've grown too big for your britches here, take a step back. So that was that was our concern at that point. That's kind of where we were thinking this was going, What's </s> |
<s>[INST] Any time, you know, networks, anytime you learn from data form representation from data an automated way, it's not very explainable as to or it's not introspective to us humans in terms of how this neural network sees the world. Where why does it succeed so brilliantly on so many in so many cases and fail so miserably in surprising ways and small. So what do you think this is uh the future. There can simply more data, better data, more organized day to solve that problem Or is there elements of symbolic systems that need to be brought in which are a little bit more explainable? [/INST] So I prefer to talk about trust and validation and verification rather than just about explain ability. And then I think explanations are one tool that you use towards those goals. And I think it is important issue that we don't want to use these systems unless we trust them and we want to understand where they work and where they don't work and in an explanation can be part of that. Right? So apply for a loan and I get denied. I want some explanation of why. And uh you have uh in europe we have the G. D. P. R. That says you're required to be able to get that. But on the other hand, an explanation alone is not enough, right? So you know, we were used to dealing with people and with organizations and corporations and so on and they can give you an explanation and you have no guarantee that that explanation relates to reality, right? So the bank can tell me why you didn't get the loan because you didn't have enough collateral and that may be true or it may be true that they just didn't like my religion or or something else. Uh I can't tell from the explanation. And that's, that's true, whether the decision was made by computer or by a person. So I want more, I do want to have the explanations and I want to be able to have a conversation to go back and forth and said, well, you gave this explanation, But what about this? And what would have happened if this had happened and what I need to change that? So, I think a conversation is a better way to think about it than just an explanation as a single output. Uh, and I think we need testing of various kinds. Right? So in order to know was the decision really based on my collateral or was it based on my religion or skin color or whatever. I can't tell if I'm only looking at my case, but if I look across all the cases, then I can detect the pattern. Right. Right. So you want to have that kind of capability? You want to have these adversarial testing? Right? So we thought we were doing pretty good at object recognition and images. They said, look, we're at sort of pretty close to human level performance on image in that and so on. Uh, and then you start seeing these adversarial images and you say, wait a minute. That part is nothing like human performance. </s><s>[INST] We can mess with it really easily. [/INST] You can mess with it really easily. Right? And yeah, you can do that to humans too. Right? So in </s><s>[INST] a different way, perhaps [/INST] humans don't know what color the dress was. And so they're vulnerable to certain attacks that are different than the attacks on the on the machines. But you know, the tax machines are so striking. Uh they really change the way you think about what we've done, right? And the way I think about it is I think part of the problem is we're seduced by our low dimensional metaphors, right? So, you know, you like that. You look in a textbook and you say, okay, now we've mapped out the space and you know, cat is here and dog is here and maybe there's a tiny little spot in the middle where you can't tell the difference. But mostly we've got it all covered. And if you believe that metaphor, uh then you say, well we're nearly there. And uh you know, there's only gonna be a couple of adversarial images, but I think that's the wrong metaphor. And what you should really say, it's it's not a two D flat space that we've got mostly covered, it's a million dimension space. And cat is this string that goes out in this crazy path. And if you step a little bit off the path in any direction, you're in nowhere land and you don't know what's going to happen. And so I think that's where we are. And now we've got to deal with that. So it wasn't so much an explanation, but it wasn't an understanding of what the models are and what they're doing. And now we can start exploring how do you fix that? </s><s>[INST] Yeah, validating their boston's of the system so on. But take you back to the this uh this word trust. Do you think we're a little too hard on our robots in terms of the standards we apply? So you know of uh there's a dance, there's a there's a there's a dance and nonverbal and verbal communication between humans. You know, if we apply the same kind of standard in terms of humans, you know, we trust each other pretty quickly. Uh you know, you and I haven't met before and there's some degree of trust, right that nothing's gonna go crazy wrong and yet to ai when we look at ai systems were we seem to approach whose skepticism always, always. And it's like they have to prove through a lot of hard work that they're even worthy of even inkling of our trust. What do you what do you think about that? How do we break that very close that gap? [/INST] I think that's right. I think that's a big issue. Uh Just listening, my friend uh Mark Moffett is a naturalist and he says uh the most amazing thing about humans is that you can walk into a coffee shop or a busy street in a city and there's lots of people around you that you've never met before and you don't kill each other? </s> |
<s>[INST] So what role do you think government, our favorite entity has in setting policy and rules about this domain? From research to the development. Too early stage to late stage AI and AJ development. [/INST] So I think that the first of all um is really important that governments in there right in some way, shape or form, you know, at the end of the day, we're talking about building technology that will shape how the world operates and that there needs to be government as part of that answer. And so that's why we've we've we've done a number of different congressional testimonies, we interact with a number of different lawmakers and uh you know, right now, a lot of our message to them is that it's not the time for regulation, it is the time for measurement, right? That our main policy recommendation is that people and you know, the government does this all the time with bodies like nest um spend time trying to figure out just where the technology is, how fast it's moving um and can really become literate and up to speed with respect to what to expect. Um So I think that today the answer really is about about about measurement. Um and I think there will be a time and place where that will change, and uh I think it's a little bit hard to predict exactly what what exactly that director should look like. </s><s>[INST] So there will be a point at which regulation federal, in the United States, the government steps in and and helps b the I don't want to say the adult in the room to make sure that there is strict rules may be conservative rules that nobody can cross. [/INST] Uh Well, I think there's this kind of maybe 22 angles to it. So today with narrow ai applications uh that I think there are already existing bodies that are responsible and should be responsible for regulation. You think about, for example, with self driving cars that you want, the, you know, the National highway uh Exactly, to to be very good in that that makes sense, Right. That basically what we're saying is that we're going to have these technological systems that are going to be performing applications that humans already do great. We already have ways of thinking about standards and safety for those. Um So I think actually empowering those regulators today is also pretty important. And then I think for for a g I you know, that there's going to be a point where we'll have better answers and I think that may be a similar approach of first measurement and start thinking about what the rules should be. I think it's really important that we don't prematurely squash. You know, progress. I think it's very easy to kind of smother the budding field and I think that's something to really avoid, but I don't think it's the right way of doing it, is to say, let's just try to blaze ahead and not involve all these other stakeholders. </s><s>[INST] So, uh You've recently released a paper on gpt two language modeling [/INST] uh </s><s>[INST] but did not release the full model because you have concerns about the possible negative effects of the availability of such model. It's uh outside of just that decision is super interesting because of the discussion at a societal level, the discourse it creates. So, it's fascinating in that aspect. But if you think that's the specifics here at first, what are some negative effects that you envisioned? And of course, what are some of the positive effects? [/INST] Yeah, so, again, I think to zoom out like the way that we thought about GTT two is that with language model and we are clearly on a trajectory right now where we scale up our models and we get qualitatively better performance. Right? GPT two itself was actually just a scale up of a model that we've released in the previous june right? And we just ran it at a much larger scale and we got these results where suddenly starting to write coherent prose, which was not something we've seen previously. And what are we doing now? Well, we're going to scale up GPT two by 10 X. 500 X by 1000 X and we don't know what we're going to get. And so it's very clear that the model that we're, that we released last june, you know, I think it's kind of like it's a good academic twe it's not something that we think is something that can really have negative applications or to the center to count the positive of people being able to play with it is, you know, far, far outweighs the possible harms you fast forward to not GPT two by Gbu 20 and you think about what that's going to be like and I think that the capabilities are going to be substantive and so there needs to be a point in between the two where you say this is something where we are drawing the line um and that we need to start thinking about the safety aspects and I think for GPT two we could have gone either way and in fact when we had conversations internally that we had a bunch of pros and cons um and it wasn't clear which one which one outweighs the other. Um and I think that when we announced that hey, we decide not to release this model, then there was a bunch of conversation where various people said it's so obvious that you should have just released it, there are other people said it's so obvious, you should not have released it and I think that that almost definitional means that holding it back was the correct decision, right? If it's, if there's, if it's not obvious whether something is beneficial or not, you should probably default to caution. And so I think that the, the overall landscape for how we think about it is that this decision could have gone either way. There's great arguments in both directions. But for future models down the road. Um, and possibly sooner than than than you'd expect because you know, scaling these things up, doesn't actually take that on those ones. You're definitely not going to want to, to release into the wild. And so, um, I think that we almost view this as a test case and to see, can we even design, how do you have a society? How do you have a system that goes from having no concept of responsible disclosure where the mere idea of not releasing something for safety reasons is unfamiliar to a world where you say, okay, we have a powerful model. Let's at least think about it. Let's go through some process. And you think about the security community, it took them a long time to design responsible disclosure. Right? You know, you think about this question of, well, I have a security exploit, I tended to, the company, the company is like tries to prosecute me or just just ignores it? What do I do? Right? And so, you know, the alternatives of, Oh, I just just always publish your exploits, that doesn't seem good either. Right? And so it really took a long time and took this this it was bigger than any individual, right? It's really about building a whole community that believe that okay, we'll have this process where you sent to the company, you know, if they don't act in a certain time, then you can go public and you're not a bad person, you've done the right thing. Um And I think that in a I part of the response to GPT two just proves that we don't have any concept of this. Um so that's the high level picture. Um and so I think that I think this was this was a really important move to make. Um and we could have maybe delayed it for GPT three, but I'm really glad we did it for GPT two. And so now you look at GPT to itself and you think about the substance of okay, what a potential negative applications. So you have this model that's been trained on the internet which, you know, it's also going to be a bunch of very biased data, a bunch of, you know, very offensive content in there and you can ask it to generate content for you on basically any topic, right? You just give it a prompt and we'll just start start writing and writes content like you see on the internet. You know, even down to like saying advertisement in the middle of some of its generations. And you think about the possibilities for generating fake news or abusive content? And you know, it's interesting seeing what people have done with? You know, we released a smaller version of GPT two and that people have done things like try to generate uh you know, to take my own facebook message history and generate more facebook messages like me um and people generating fake politician uh content or you know, there's a bunch of things there where you at least have to think is this going to be good for the world? There's the flip side, which is I think that there's a lot of awesome applications that we really want to see like creative applications in terms of if you have sci fi authors that can work with this tool and come with cool ideas like that seems that seems awesome if we can write better sci fi through the use of these tools and we've actually had a bunch of people right into us asking, hey, can we use it for, you know, a variety of different creative applications. So </s> |
<s>[INST] Yeah, but so if you look at the space of land change, you know, some percentage, not 100% that we make as humans is not a pleasant experience because we mess some part of it up. It's nerve racking to change. Look to see that to accelerate. How do we label the ones that are natural and feel good? You know, that's the because that's your ultimate criticism. The current uh, navigating anthropologist doesn't feel good. Well, [/INST] the current navigate on autopilot is a hand coded policy written by an engineer in a room who probably went out and tested it a few times on the 2 80 </s><s>[INST] probably a more a better version of that. But yes, that's [/INST] how we would have written it to come. Yeah, Baby Tesla. Tesla, they tested it and </s><s>[INST] That might have been two [/INST] engineers supposed to. Yeah, I know. But so if you learn the lane change, if you learn how to do a lane change from day to just like just like you have a label that says lane change and then you put it in when you want to do the lane change, it will automatically do the lane change, that's appropriate for the situation now to get at the problem of some humans do bad lane changes. We haven't worked too much on this problem yet. It's not that much of a problem in practice. My theory is that all good drivers are good in the same way and all bad drivers are bad in different ways and we've we've seen some data to back this up. </s><s>[INST] Well, beautifully put. So you just basically, if that's true hypothesis, then your task is to discover the good drivers [/INST] um the good drivers stand out because they're in one cluster and the bad drivers are scattered all over the place and your net learns the cluster. </s><s>[INST] Yeah, that's uh so you just learned from the good drivers and they're easy to cluster, [/INST] We learned from all of them and then it automatically learns the policy that's like the majority but will eventually probably have to feel so </s><s>[INST] if that theory is true, I hope it's true because the counter theory is um there is many clusters uh maybe arbitrarily many clusters of good drivers because if there's one cluster of good drivers, you can at least discover a set of policies, You can learn a set of policies which would be good universally. Uh That would be a nice. That would be nice if it's true. And you're saying that there is some evidence that, [/INST] let's say lane changes can be clustered into four clusters. </s><s>[INST] Alright, there's this finite level of, [/INST] I would argue that all four of those are good clusters. All the things that are random our noise and probably bad And which one of the four you pick or maybe it's 10 or maybe it's 20. You can learn that it's context dependent. It depends on the scene </s><s>[INST] and the hope is it's not too dependent on the driver. [/INST] Yeah, the hope is that it all washes out. The hope is that there's that the distributions not by model. The hope is that it's a nice calcium. </s><s>[INST] So what advice would you give to test? Uh, how to fix how to improve navigate on autopilot. That the lessons you've learned from comedy. I [/INST] the only real advice I would give to Tesla is please put driver monitoring in your car with respect to </s><s>[INST] improving. You can't do that anymore. I said I to interrupt but you know, there's a practical nature of many of hundreds of thousands of cars being produced that don't have a good driver facing camera. The model [/INST] three has a selfie cam. Is it not good enough? Did they not have put I. R. L. E. D. S for night? </s><s>[INST] That's a good question. But I do know that the it's fisheye and it's relatively low resolution. It's really not designed. It wasn't it wasn't designed for time. You can hope that you can kind of scrape up and and and have something from it. But [/INST] why didn't they put it in today? Put it into that today. Every time I've heard Carpathia talk about the problem and talking about life software 2.0 and how the machine learning is gobbling up everything. I think this is absolutely the right strategy. I think that he didn't write navigate on autopilot, I think somebody else did um and kind of hacked it on top of that stuff. I think when Carpathia he says, wait a second, why did we hand code this lane change policy with all these magic numbers, we're gonna learn it from data, They'll fix it. They already know what to do there. </s><s>[INST] Well that's that's Andres job is to turn everything into a learning problem and collect a huge amount of data. The reality is though not every problem, it can be turned into a learning problem in the short term. In the end everything will be a learning problem. The reality is Uh like if you want to build L5 vehicles today that will likely involve no learning and that's that's the reality is so at which point does learning start? It's the crutch statement that lighter is a crutch, At which point we'll learning get up to part of human performance. It's over. Human performance on image. Net classification on driving is the question still, [/INST] it is a question, I'll say this, I'm here to play for 10 years. I'm not here to try to I'm here to play for 10 years and make money along the way. I'm not here to try to promise people that I'm going to have my L five taxi network up and working in two </s> |
<s>[INST] and you get what I'm saying, that's a beautiful personal journey you're on. But you get what I'm saying that [/INST] the personal is for my people as a whole, as a tribal, small </s><s>[INST] company, small company [/INST] as a tribal person, I believe that I am my </s><s>[INST] people and [/INST] and and the thing that, that businessmen have done to my people have pulled the brightest out of our tribes and siloed them and made us lose our culture and lose who they were all the only thing I wanted to say at Virgil's funeral, which I wasn't allowed to, right? It was a white pastor that talked the majority of the funeral half the funeral was piste piste right? Um and uh and this pastor actually married me and kim right, It looks like Justin timberlake a little bit. Uh and um he talked after funeral, he knew Virgil's passing, did a collaboration with him before he passed by the way, right? A clothing collaboration. I didn't know Virgil was passing, but the thing I wanted to say, I saw ASAP Rocky and I saw some other members of his gang, you know, in the audience at the funeral and all I wanted to tell them is don't let them split the gang up. Don't let them split the gang up. When I did the first Easy uh because I did Kanye West to fashion shows before as a high end luxury, all leather kind of design or not all leather, but you know, high end materials, um mink this kind of thing. Um and then I came back with Easy with Adidas and this fashion show was so popular that Justin Bieber had to sit in the second row, right, This thing had every name you could think of had kim Kardashian, kris Jenner, Kendall Jenner, it was Kylie's first fashion show, she'd been in. And in the second fashion show, I put Kylie and Bella Hadid next to each other in the fashion show. You had puff daddy at that time, puff daddy. Uh had beef with drake, drake still came to the show and jay Z had to break up the fight backstage. The designers, you had jerry Lorenzo, that's Head of fear God, you had kim throb, head of scams, you had Virgil Ablow, Head of Louis Vuitton, you had Demna head of balenciaga. All working for Yay, for the leader for the philosopher, right? For the person that put who put this together me, that's who, right? You have these people working for the king of new york based the boss. Yay, right? You had, you had jay Z and the audience, Rihanna and the audience um Beyonce in the audience sitting next to anna Winter in this audience and guess who heard wind of this? One of the richest men in the world? Bernard Arnault caught wind of this, what's going on, they're building up something and we need to stop it. So then he met with me and politely offered me backing from my clothing line, it would be Kanye West, they would get 49%, I would get 49%, they have control and they were gonna give me all of the support from Louis Vuitton. Uh so I had to go to Adidas and I told Adidas, hey, let's identify the apparel. Uh so Adidas, you're not gonna do the apparel anymore. Hey, we had a, we had a good time but we're gonna run off with Giselle now. Right, So the, that's like you told your girl that and you're like, no, we're supposed to, we had the proudest moment of our career. And so, uh, so then he offers me to deal with Alexandre Arnault who's went to gone on and rape and pillage from all of the talent that I had afterwards said, I say before I tell Adidas to identify the apparel, can I get a written contract from your dad? Bernard Arnault and he says, my dad will never go back on his word. So you already know what this thing is going, right, You can spoiler alert. Right? Uh, he went back on his word. So three months into the deal I get anna winter, I say, who should I use for my lawyer? She picks my lawyer for me, right. I just found out even a couple of days that the lawyer demanded an airplane during negotiations had nothing to do with me. Right? They said that Bernard Arnault got freaked out and then alexander no calls me and says the deal got dropped at the board. I went back and told my high maintenance wife, I was supposed to become this designer at Louis Vuitton or the Louis Vuitton group was gonna back the Kanye West line because that's how good I've done in fashion babe. And now the deal is dropped now the deal has dropped. So then I did a second collection And we didn't have any support to be able to build the collection. Then I went and found a third collection. We did it, we took over. MSG 4th collection went and the show started an hour late. Then a week later, kim got robbed. Then I told scooter braun my manager at that time, I say I I'm looking you know, I need to go to Japan, I'm tired, I'm tired. He says no you need to make more money. I do four more shows on the second leg of the tour and I suffer from exhaustion and go to the hospital and then get diagnosed with the disorder. This is the first time I ever suffered from exhaustion by the way. I haven't been to the hospital since. Haven't been to the hospital since and haven't taken you know medication in two years. And I'm sure there will be people in the media, We won't say where phone will say, well that's obvious. Right? So, so right now I'm talking to you right, I'm not on medication. I just go to sleep. I have sleep </s> |
<s>[INST] the history of slavery in America? Oh my. So what does that tell you about people? [/INST] Well, I </s><s>[INST] Think of two things right off the top of my head. one is about the capacity of people for looking the other way in the face of unethical and uh, you know, morally profoundly problematic practice. So, I mean, slavery was controversial. [/INST] It was </s><s>[INST] controversial. Going all the way back to the founding of the United States of America. [/INST] The </s><s>[INST] country was founded on a compromise where [/INST] half of the </s><s>[INST] country, I thought [/INST] that slavery </s><s>[INST] was, was abhorrent and would not have had uh, countenanced in the [/INST] constitution. The other half </s><s>[INST] of the country [/INST] were steeped </s><s>[INST] in the dependence on the labor of these african [/INST] captives </s><s>[INST] and their descendants. The economy depended upon it. They [/INST] owned them as property. That was their </s><s>[INST] wealth. Their wealth was invested to some degree and the value of these human beings. And in [/INST] order for the United </s><s>[INST] States to come together as a confederation of [/INST] the several </s><s>[INST] colonies, [/INST] there had to be a compromise made and it was made, where slavery </s><s>[INST] was allowed to [/INST] persist. Uh, </s><s>[INST] and [/INST] uh, the people who </s><s>[INST] were against [/INST] it or who </s><s>[INST] thought it morally [/INST] problematic. </s><s>[INST] We're able to [/INST] countenance </s><s>[INST] the practice in [/INST] the southern states </s><s>[INST] where slavery [/INST] flourished And that went on for 75 </s><s>[INST] years after the [/INST] founding of the country, </s><s>[INST] until the [/INST] crisis of </s><s>[INST] the late 18 [/INST] 50s that led to the civil war </s><s>[INST] and ultimately [/INST] To the emancipation. So, one </s><s>[INST] thing I think about human nature, from the fact of slavery [/INST] is that the </s><s>[INST] ability of people to live with [/INST] terrible </s><s>[INST] morally [/INST] questionable </s><s>[INST] practices and have that as a part of their institutions. It took a movement, [/INST] a massive </s><s>[INST] movement of [/INST] abolitionists, uh, struggling against slavery </s><s>[INST] for [/INST] the better part of a century </s><s>[INST] before, [/INST] um, before </s><s>[INST] that that [/INST] practice could be eradicated. </s><s>[INST] But [/INST] the other thing about </s><s>[INST] human nature [/INST] that I see is the ability of people to sustain </s><s>[INST] their humanity [/INST] under the most </s><s>[INST] awful [/INST] oppressive </s><s>[INST] conditions. [/INST] Um, the enslaved </s><s>[INST] persons, the slaves, [/INST] um, and their Children, </s><s>[INST] I mean, they were [/INST] chattel, they </s><s>[INST] were bought and sold like [/INST] horses or cattle, </s><s>[INST] um, and yet, [/INST] uh, they were </s><s>[INST] not, their [/INST] humanity was not destroyed by </s><s>[INST] that and [/INST] they were able </s><s>[INST] to [/INST] sustain their </s><s>[INST] dignity to [/INST] some degree in such a manner that once </s><s>[INST] emancipation [/INST] finally did arrive, </s><s>[INST] the [/INST] freedmen and women, the </s><s>[INST] persons who had been [/INST] enslaved and who were set </s><s>[INST] free, [/INST] we're able </s><s>[INST] to, [/INST] over the following decades </s><s>[INST] build [/INST] a foundation for </s><s>[INST] the development of [/INST] african americans within </s><s>[INST] the context of american society [/INST] that </s><s>[INST] eventually [/INST] culminated in the civil rights movement of the middle of the 20th century </s><s>[INST] and [/INST] has led us into the present day. </s><s>[INST] So, [/INST] uh, you </s><s>[INST] know, [/INST] human nature can countenance </s><s>[INST] awful evil, [/INST] but human nature can also </s><s>[INST] survive in the face of [/INST] terrible evil. </s><s>[INST] That's what I take from slavery. That's survival. [/INST] That </s><s>[INST] flame can burn even when this, the world around it tries to put it out there, there's still a little flame of human consciousness, of spirit, of culture, of whatever the hell that [/INST] is, that makes </s><s>[INST] humans flourish and makes [/INST] humans beautiful, </s><s>[INST] that lives on. That's everyone said, Yeah, I think you you put it very well, [/INST] there's got to be some </s><s>[INST] poetic way of expressing that. Uh, leave it to the poets. [/INST] What about the people </s><s>[INST] that look the other way? How many people do you think just regular people? I knew that something [/INST] is this is </s><s>[INST] wrong or did do people through generations convince themselves most people, most regular people convince themselves that there's nothing wrong? [/INST] Alright. Yeah, </s><s>[INST] I asked this question because I wonder what we're looking the other way on today. Also [/INST] because </s><s>[INST] you mean, you have to kinda [/INST] if were you have to </s><s>[INST] ask yourself these difficult questions [/INST] of </s><s>[INST] assuming we're the same people. We were. [/INST] Yeah. Back </s><s>[INST] then then we're we can be flawed [/INST] in that same kind of way. </s><s>[INST] We can look the other the other [/INST] way, just as others have </s><s>[INST] in history? [/INST] Yeah. </s><s>[INST] You spoke of the european context and of the nazis and certainly a lot of people had to be looking [/INST] the other way </s><s>[INST] when the massive crimes that were committed by that regime were being undertaken. I mean, railroad cars full of human being being taken off to be slaughtered or to be [/INST] worked to death </s><s>[INST] and labor camps or [/INST] to be gassed, </s><s>[INST] uh, etcetera. A lot of people had to know about what was going on and look the other way [/INST] or enthusiastically </s><s>[INST] supported the, [/INST] the persecution </s><s>[INST] of the jews and the gypsies and so on. [/INST] And I don't know, I wasn't, you know, I wasn't around </s><s>[INST] in 18 40. [/INST] My sense of the </s><s>[INST] matter is that like many practices that are unjust, most people thought that's just the way it is. [/INST] I mean, that's the world that </s><s>[INST] they inherited. They were not [/INST] moralists, they were </s><s>[INST] not revolutionaries. They just wanted to go [/INST] along. Some </s><s>[INST] people might have been [/INST] troubled by it, but thought there's nothing that can be done. </s><s>[INST] Some people might have thought, [/INST] well, </s><s>[INST] they're these black Africans, they're not really [/INST] like us and, you know, </s><s>[INST] they are lucky to be here. If they were in africa, they'd [/INST] be worse off still. </s><s>[INST] Some people might have [/INST] thought that, </s><s>[INST] uh, some people might [/INST] have been disturbed, but </s><s>[INST] not been able to [/INST] see what </s><s>[INST] it is, that they could do about it. [/INST] Uh, they </s><s>[INST] might have thought, oh, [/INST] this is, you know, this is </s><s>[INST] disgusting, This is, uh, you know, not something I wouldn't want to have anything [/INST] to do with, but </s><s>[INST] uh, not knowing [/INST] whether there's </s><s>[INST] any practical [/INST] way of opposing it. </s><s>[INST] That that's why you need a [/INST] movement, You need for </s><s>[INST] the people who are [/INST] troubled by </s><s>[INST] the practice to know [/INST] that there are others like themselves, equally </s><s>[INST] troubled. And [/INST] as they gather </s><s>[INST] together collectively, [/INST] they can exert </s><s>[INST] their their influence. [/INST] I mean, it debates about the </s> |
<s>[INST] but it is the modularity is a really powerful statement that it's an engineer. You can then assemble different things. You can count on them to be. I mean it's interesting. It's a balance. Like with everything else in life you don't want to get too obsessed. I mean this is what computer scientists do, which they tend to get obsessed. They over optimize things or they start by optimizing them. They over optimize. So it's it's easy to like get really granular about this thing, but like the step from an end squared to an end Lagan sorting algorithm is a big leap for most real world systems, no matter what the actual behavior of the system is, that's a big leap. And the same can probably be said for other kind of first leaps that you would take in a particular problem. Like it's a picking the low hanging fruit or whatever, the equivalent of doing the, not the dumbest thing, but the next to the dumbest thing is picking the most delicious reachable fruit, most delicious reachable from. [/INST] I don't know why that's not a saying. </s><s>[INST] Yeah. Okay, so, uh, so you, then this is the 80s and this kind of idea started to percolate of uh, [/INST] and at that point I got to read, I got to meet Rich Sutton. So everything was sort of downhill from there and that was, that was really the pinnacle of everything. Um, but then, you know, then I felt like I was kind of on the inside. So then as interesting results were happening, I could like check in with with rich or with jerry to sorrow, who had a huge impact on kind of early thinking in temporal difference learning and reinforcement learning and show that you could do, you could solve problems that we didn't know how to solve any other way. Um, and so that was really cool. So it was good things were happening. I would hear about it from either of the people who were doing it or the people who were talking to the people who are doing it. And so I was able to track things pretty well through through the 90s. </s><s>[INST] So what uh wasn't most of the excitement on reinforcement learning in the 90s era with what is the T. D. Gamma, like what's the role of these kind of little like fun game playing things and breakthrough is about uh you know, exciting the community. Was that like what were your, because you've also built across or were part of building a crossword a puzzle uh solver solving program uh called proverb. So so you were interested in this as a problem, like informing, using games to understand how to build Intelligence Systems. So like what did you think about TD gammon? Like what did you think about that whole thing in the 90s? [/INST] Yeah, I mean I found the Td Gammon result really just remarkable. So I had known about some of jerry stuff before, he did Td Gammon, he did a system just more vanilla, not not entirely vanilla, but a more classical back property kind of network for playing backgammon, where he was training it on expert moves. So it was kind of supervised, but the way that it worked was not to mimic the actions but to learn internally an evaluation function. So to learn well if the expert chose this over this, that must mean that the expert values this more than this and so let me adjust my weight to make it so that the network evaluates this as being better than this. So it could learn from from human preferences, it could learn its own preferences. And then when he took the step from that to actually doing it as a full on reinforcement learning problem where you didn't need a trainer, you could just let it play. That was that was remarkable, right? And so I think as as humans often do as we've done in the recent past as well, people extrapolate, it's like, oh well if you can do that, which is obviously very hard, then obviously you could do all these other problems that we, that we want to solve, that we know we're also really hard and it turned out very few of them ended up being practical, partly because I think neural nets certainly at the time were struggling to be consistent and reliable and so training them in a reinforcement learning setting was a bit of a mess. I had, I don't know, generation after generation of like master students who wanted to do value function approximation, basically reinforcement learning with neural nets and over and over and over again, we were failing, we couldn't get the good results that jerry to Zaragoza. I now believe that jerry is a neural net whisperer, he has a particular ability to get neural networks to do things that other people would find impossible and it's not the technology, it's the technology and jerry </s><s>[INST] together at which I think speaks to the role of the human expert in the process of machine learning. [/INST] Right? It's so easy. We were so drawn to the idea that, that it's the technology that is, that is where the power is coming from. That. I think we lose sight of the fact that sometimes you need a really good and just like, I mean no one would think, hey, here's this great piece of software here is like, I don't know the new imacs or whatever. Um, doesn't that prove that computers are super powerful and basically going to take over the world? It's like no Stallman is a hell of a hacker, right? So he was able to make the code do these amazing things. He couldn't have done it without the computer, but the computer couldn't have done it without him. And so I think people discount the role of people like jerry who, who have just a particular particular set of </s> |
<s>[INST] But it's a pandemic. There's a lot of money, there's a lot of incentive to work on it harder. [/INST] And also you don't need to work on the virus. You can take bits of it and work. You could say just the spike. Right and say can we make a vaccine with just the Spike? Because that doesn't require BSL three. So yes, </s><s>[INST] so, uh like building a vaccine requires you to figure out how or antiviral drugs, how to attack various structural parts of the virus and the functional parts of the virus. [/INST] You have to decide on a target. Yeah, I'm going to make an antiviral, what am I going to target in the virus. And there are a few things that make more sense than others. Usually we like to target enzymes, you know, if you remember any your biochemistry but enzymes are catalytic, you don't need a lot of them to do a lot of things. So they're typically in low concentrations in a virus infected cells. So it's easier to inhibit them with a drug and the Coronas have couple of enzymes that we can target. So you have to figure that out ahead of time and decide what to go after and then you can look for drugs that inhibit what what you're interested in. It's not that hard to do. </s><s>[INST] There's just something beautiful about biology, about the mechanisms of biology. And I kind of regret um, falling in love with computer science so much that I um left that biology textbook on the show and left it behind. But hopefully we'll return to it now because I think one of the things you learn even in computer science that studying biology and certainly neurobiology, uh, you you get inspired, here's the mechanism of incredible complexity that works really well, is very robust, is very effective efficient. It inspires you to come up with techniques that you can engineer in the machine. So [/INST] that's that's the what drives a field forward when people improvise and come up with new technologies that really make a difference. We have, we have a bunch of those Now, </s><s>[INST] what's the difference between the coronavirus family and the uh, the other popular family, influenza virus family is um, I mean, if I were, because you mentioned, we should have done a lot more in terms of vaccine development, that kind of thing for coronavirus is, but if I were back then from my understanding, the thing we should all be afraid of influenza, like some strong variants out from that family that seems like the one that will destroy civilization or or hurt us really badly. I don't know if you agree with this sense. But maybe um maybe you can also just clarify what to use the is the difference between the families. [/INST] So it's an interesting difference. They both they both have membranes, right? So then they have spike proteins embedded in them for and they're different spikes. In fact for influenza, there are two main ones. They're called the H. A. And the N. A. Um but what's inside is RNA but it's very different RNA. And here we have to explain that. So viruses with RNA can have three different kinds of RNA. They can have what we call plus R. N. A. They can have minus RNA. Or they could have plus minus actually two strands hybridized together. The Plus RNA simply means that if you put that plus RNA in a cell, you know yourself has ribosomes in it that make the proteins that you need. The ribosomes will immediately latch onto the Plus RNA and begin to make proteins minus RNA is not the right strand to make proteins. So it has to be copied first and then the plus minuses both together. So the stars coronavirus is all the corona viruses have Plus RNA. So as soon as that RNA gets in this album, it starts an infectious cycle. Same thing with polio virus by the way, which I worked on. influenza viruses are negative stranded. So they cannot be translated when they get in the cells. So that that's tough for the virus because the cell actually cannot make PLUS RNA from minus RNA. It doesn't have the enzyme to do it. So the virus has to carry it in inside the virus particle. And then when the minus aren't is in the south, the virus enzyme makes plus R. And S. And those get translated. It's a big difference. And then in the influenza viruses, not only is it minus RNA, But it's in pieces. It's an eight pieces we call that segmented whereas the corona is in one long piece of RNA. </s><s>[INST] So what is that? They're like floating separately. [/INST] So the genes are on separate pieces. They're all packaged inside that virus particle of influenza virus. But they're pieces. And why that's important is because if two different influenza viruses infect the same cell, the pieces as they reproduce can mix and out can come a virus with a new assortment of pieces. And that allows influenza virus to undergo extremely high frequency evolution. That's why we get pandemics. We have a new flu pandemics is because somewhere in some animal, two viruses have re assorted and made a new virus that we hadn't seen before. </s><s>[INST] So so you're you're you're talking about kind of biological characteristics. But what am I incorrect in my intuition that or from the things I've heard that the influence of a family of viruses is more dangerous. Like what? What makes it more dangerous to humans? [/INST] Well, it depends on the there are many flavors or vintages of influenza virus. Some are dangerous and some are not right. It depends on which one. Some like the 1918 apparently was very lethal, killed a lot of people. But more contemporary viruses, we had a pandemic in 2009 of influenza. That wasn't such a lethal virus. We don't know exactly why, but it didn't kill that. Many people transmitted pretty well </s> |
<s>[INST] You can buy fractions of a stock, say $1 worth no matter what the stock prices, brokerage services are provided by cash up investing subsidiary of square and member S. I. P. C. I'm excited to be working with cash app to support one of my favorite organizations called first, best known for their first robotics and lego competitions. They educate and inspire hundreds of thousands of students in over 110 countries and have a perfect rating on charity navigator, which means the donated money is used to maximum effectiveness when you get cash out from the app store or google play and use code lex podcast, you'll get $10 and cash up will also donate $10 to first, which again is an organization that I've personally seen inspire girls and boys, the dream of engineering a better world. And now here's my conversation with Sebastian, Thrun [/INST] you </s><s>[INST] mentioned that the Matrix, maybe your favorite movie. So let's start with the crazy philosophical question, Do you think we're living in a simulation? And in general, do you find the thought experiment interesting? [/INST] You find simulation? I would say maybe we are, maybe you're not, but it's completely irrelevant to the way we should act, </s><s>[INST] putting aside for a moment the fact that it might not have any impact on how we should act as human beings. For people studying theoretical physics, these kinds of questions might be kind of interesting looking at the universe is information processing system, [/INST] universe is an information processing system. It's a huge physical, biological can be a computer. There's no question. Um, but I live here and now I care about people who care about us. </s><s>[INST] What do you think is trying to compute? [/INST] And I think there's an intention, I think just the world evolves the way that evolves and it's, it's beautiful. It's unpredictable and I'm really, really grateful to be alive, </s><s>[INST] spoken like a true human, [/INST] which last time I checked that was </s><s>[INST] well that in fact this whole conversation is just a touring test to see if if indeed if indeed you are. You've also said that one of the first programs of the first few programs you've written was wait for a. T. I. 57 calculator, maybe that's early eighties. I don't wanna date calculators or anything. 30 eighties, correct? Yeah. So if you were to place yourself back into that time into the mindset you were in because you have predicted the evolution of computing ai the internet technology in in the decades that followed. [/INST] I was super fascinated by Silicon Valley, which I've seen on television once and thought my God, this is so cool that built like the rams there and Cpus How cool is that? And as a college student, a few years later a few years later I decided to re study intelligence and study human beings and found that even back then in the 80s and 90's artificial intelligence is what fascinated me the most was missing is that back in the day the computers are really small. They're like the brains you could build not anywhere bigger as a cockroach and cockers are very smart. So we weren't at the scale yet, where we are today. </s><s>[INST] Did you dream at that time to achieve the kind of scale we have today or did that seem possible? [/INST] I always wanted to make robots smart and I felt it was super cool to build an artificial human and the best way to build. Not official, you invent a robot because that's kind of the closest you could do unfortunately aren't there yet today are still very brittle. But it's fascinating to study intelligence from a constructive perspective. We could build something </s><s>[INST] to understand you build, what do you think it takes to build an intelligent system and an intelligent robot. [/INST] I think the biggest innovation that we've seen this machine learning and it's the idea that their computers can basically teach themselves. Let's give an example. I'd say everybody pretty much knows sort of walk and we learned how to walk in the first year or two of our lives. But no scientist has ever been able to write on the rules of human gate. We don't understand that. We can't be having our brains somewhere, we can practice it, we understand it, but we can't articulate it, we can't pass it on my language. And that to me is kind of the deficiency of today's computer programming. Even you could program a computer. They are so insanely dumb that you have to give them rules for every contingencies. Very unlike the way people learn from data and experience computers are being instructed and because it's so hard to get this instruction set right, we pay software engineers $200,000 a year. Now, the most recent innovation which has been to make for like 30, 40 years is an idea that computers can find their own rules, so they can learn from falling down and getting up the same way Children can learn from falling down and getting up. And that revolution has led to a capability that's completely unmatched. Today's computers can watch experts do their jobs, whether you're a doctor or a lawyer, pick up the regularities, learn those rules and then become as good as the best experts. </s><s>[INST] So the dream of in the 80s of expert systems for example had at its core the idea that humans could boil down their expertise on a sheet of paper, so to sort of reduce sort of be able to explain to machines how to do something explicitly. So do you think, what's the use of human expertise into this whole picture? Do you think most of the intelligence will come from machines learning from experience without human expertise input? [/INST] So the question for me is much more, how do you express expertise? Um You can express expertise, providing a book, you can express expertise by showing someone what you're doing, you can express expertise by applying it by many different ways and I think the expert systems was our best attempt in ai to capture expertise and rules, but someone sat down and say here the rules of human gait, here's when you put your big toe forward and your heel backwards and yahoo stop stumbling and as we now know the set of rules that sort of language that you can command is incredibly limited. The majority of the human brain doesn't deal with language. It is with like subconscious numerical perceptual things that we don't even have. We serve aware of. Um now when a AI system watches an expert do their job and practice their job. Um it can pick up things that people can't even put into writing into books or rules and that's where the real power is. We now have a I systems that for example, look over the shoulders of highly paid human doctors like dermatologists or radiologists and they can somehow pick up those skills that no one can express in words. </s><s>[INST] So you were a key person in launching three revolutions, online education, the autonomous vehicles and flying cars or beetles so high level and I apologize for all the philosophical questions, [/INST] no apology necessary. </s><s>[INST] How do you choose what problems to try and solve what drives you to make those solutions in reality? [/INST] I have to, to desires in life. I want to literally make the lives of others better or as few of them say maybe jokingly make the world a better place. I believe in this. It's as funny as it sounds and second I want to learn, I want to get in this case, I don't want to be in the drop I'm good at because if I'm in a job that I'm good at the chances for me to learn something interesting is actually minimized. So I want to be in a job I'm bad at. Um that's really important to me. So in a bid for example, but people often called flying cars with electrical vertical takeoff and landing vehicles. Um I'm just no expert in any of this and it's so much fun to, to learn on the job, what it actually means to build something like this. Now. It's saying that the stuff that I done lately after I finished my professorship at stanford, They're really focused on like what is the maximum impact on society? Like transportation is something that has transformed the 21st or 20th century more than any other invention of my opinion, even more than communication and cities are different workers, different women's rights are different because of transportation. And yet we still have a very sub optimal transportation solution where we kill 1.2 or so million people every year in traffic. It's like the leading cause of death for young people in many countries where we are extremely inefficient resource minds, just go to your average neighborhood city and look at the number of parked cars. That's a travesty in my opinion or where we spent endless hours in traffic jams and very, very simple innovations like a self driving car or what people call the flying car could completely change this and it's there. I mean the technology is, is basically there to close your eyes not to see it. </s><s>[INST] So lingering on autonomous vehicles, fascinating space, some incredible work you've done throughout your career there. So let's start start with DARPA. I think the DARPA challenge to the desert and an urban to the streets. I think that inspired an entire generation of roboticists and obviously sprung this whole excitement about this particular kind of four wheeled robots called autonomous cars, self driving cars. So, you lead the development of Stanley, the autonomous car that won that The race of the desert. The DARPA Challenge in 2005 and junior, The car that finished second in the DARPA Urban Challenge also did incredibly well in 2007. I think what are some painful inspiring or enlightening experiences from that time to stand out to you. [/INST] Oh my God, painful. We're all these incredibly complicated stupid bugs that had to be found. We had a phase where the Stanley our Our car that eventually wandered up again challenge with every 30 miles, just commit suicide and we didn't know why and they ended up to be that in the sinking of two computer clocks occasionally o'clock went backwards and that negative time elapsed screwed up the entire internal logic. But it took ages to find this. You were like bugs like that. I'd say. Enlightening is the stanford team immediately focused on machine learning and software. Whereas everybody else seemed to focus on building better hardware. Our analysis have been a human being with an existing rental car can perfectly drive the course, but I have to write off to get a better rental car. I just should replace the human being and the human being. To me was a conjunction of three steps. We had like sensors, eyes and ears, mostly eyes. We had brains in the middle and then we had actuated our hands and our feet. Now the extras are easy to build. The sensors are actually also easy to build was missing was the brain. So we had to build a human brain and nothing nothing clear then to me that that the human brain is a learning machine. So why not just train our robots? You would be a massive machine learning into our machine. And with that we're able to not just learn from human drivers. We had the entire speed control of the vehicle was copied from human driving, but also have the robot learn from experience where it made a mistake and recover from it and learn from it. </s><s>[INST] You mentioned the pain point of software and clocks. Synchronization seems to seems to be a problem that continues with robotics. It's a tricky one with drones and so on. What what does it take to build a thing? A system with so many constraints. You have a deadline. No time. You're unsure about anything really. It's the first time that people really even exploring. You know, it's not even sure that anybody can finish when we were talking about the race of the desert the year before nobody finished. What does it take to scramble and finish a product that actually a system that actually works? [/INST] I mean, we're lucky. We're very, really small team, the core of the team of four people. It was for, because five couldn't comfortably sit inside a carpet for food and I as a team leader, my job was to get pizza for everybody and washed the car and stuff like this and repair the radiator and it broke and debug the system. Um, and we're already kind of open minded. We had like no egos involved and we just wanted to see how far we can get what we did really, really well. It was time management. We were done with everything a month before the race and we froze the entire self a month before the ways. And it turned out, um, looking at other teams, every other team complaint. If they had just one more week, they would have won. And we decided, you know, it's going to fall into a mistake. We're gonna be early. And we had an entire month to shake the system. And we actually found two or three minor bucks in the last month that we had to fix. And we were completely prepared in the race </s><s>[INST] occurred. Okay, So first of all, that's, it's such an incredibly rare achievement in terms of being able to be done on time or ahead of time? What do you, how do you do that in your future work. What advice do you have in general? Because it seems to be so rare, especially in highly innovative projects like this. People worked at the last second. [/INST] But the nice thing about the topic, one challenge is that the problem was incredibly well defined. We were able for a while to drive the old topic, one challenge course, which had been used the year before. And then at some reason we were kicked out of the region. So we had to go to different desert, the Sonoran desert and be able to drive desert trails just at the same type. So there was never any debate about like what's actually the problem. We didn't sit down and say, hey, should we build a car or a plane? And we had to build a car that made it very, very easy. Then I studied my own life and life of others and realized that the typical mistake that people make is that there's this kind of crazy bug left that they haven't found yet. Um, and, and it's just, they regretted and the bug would have been trivial to fix it. Just haven't fixed it yet. They didn't want to fall into that trap. So I built a testing team, we had a testing team a bit of testing booklet of 160 pages of tests we had to go through just to make sure we shake up the system appropriately. And the testing team was with us all the time and dictated to us today, we do railroad crossings tomorrow, we do, we practice the start of the event and in all of these um, we, we we thought, oh my God, has long solved trivial. And then we tested it out. Oh my God, it doesn't work very well for us and why not? Oh my God, it mistakes the derails for metal barriers, We have to fix this. So it was really a continuous focus on improving the weakest part of the system. And as long as you focus on improving the weakest part of the system, you eventually build a really great system. </s><s>[INST] Let me just pause in that is, to me as an engineer is just super exciting that you were thinking like that, especially at that stage, as brilliant that testing was such a core part of it. It may be to linger on the point of leadership. I think it's one of the first times you were really a leader and you've led many very successful teams since then. What does it take to be a good leader? [/INST] I would say most of us don't just take credit uh, for the work of others. Right? Um, that's, that's very convenient, turns out because I can't do all these things myself, I'm an engineer at heart. So I care about engineering. So, so I don't know what the chicken and the egg is. But as a kid, I love computers because you could tell them to do something and they actually did. It was very cool. And you could like in the middle of night wake up monday morning and switch on your computer and what you told you to yesterday, I would still do. That was really cool. Unfortunately, that didn't quite work with people. So you go to people and tell them what to do and they don't do it. Uh they hate you for it or you do it today and then you go a day later and they'll stop doing it. So you have to. So then the question became, how can you put yourself in the brain of the people of people as opposed to computers? And it is the computers are super dumb then that's just so dumb. If people were as dumb as computers, I wouldn't want to work with them. But people are smart and people are emotional, people have pride and people have aspirations. So how how can I connect to that? Um, and that's the thing that most of our leadership just fails because many, many engineers turned manager believe they can treat their team just the same way into your computer and it just doesn't work this way. It's just really bad. So how how can I, how can I connect to people? And it turns out as a college professor? The wonderful thing you do all the time is to empower other people. Like your job is to make your students look great. That's all you do, you're the best coach and it turns out if you do a fantastic job with making your students look great, they actually love you and their parents love you and they give you all the credit for stuff you don't deserve. All my students were smarter than me, All the great stuff invented at stanford, their stuff, not my stuff and they give me credit and say, oh sebastian, but just making them feel good about themselves. So the question really is, can you take a team of people and what does it take to make them to connect to what they actually want in life and turn this into productive action? It turns out every human being that I know has incredibly good intentions. I've really, really met a person with bad intentions. I believe every person wants to contribute. I think every person I've met wants to help others. It's amazing how much of a urge we have not to just help ourselves but to help others. So how can we empower people and give them the right framework that they can accomplish this. If moments when it works, it's magical because you'd see the confluence of, of people being able to make the world a better place and deserving enormous confidence and pride out of this and that's when, when my environment works the best. These are moments where I can disappear for a month and come back and things still work. It's very hard to accomplish, but when it works, it's amazing. Mm </s><s>[INST] So I agree with you very much. It's not often heard that most people in the world have good intentions at the core. Their intentions are good and they're good people. That's a, it's a beautiful mother. It's not often heard [/INST] we make this mistake and this is a friend of mine exhibit uh penis that we judge ourselves by our intentions and others by their actions. And I think the biggest skill, I mean here in Silicon Valley were full of engineers who have very little empathy and, and, and I'm kind of befuddled by, it doesn't work for them. The biggest skill I think that, that people should acquire is to put themselves into the position of the other and listen and listen to what the other has to say. And they'd be shocked how similar they are to themselves and they might even be shocked how their own actions don't reflect their intentions. Um, I often have conversations with engineers and I say, look, hey, I love you. You're doing a great job. And by the way, what you just did has the following effects. Are you aware of that? And then people would say, oh my God not, I wasn't because my intention was that and say, yeah, I trust your intention. You're a good human being, but just to help you in the future, if you keep expressing it that way, then people just hate you. And I've had many instances would say, oh my God, thank you for telling me this because it wasn't my intention to look like an idiot, It wasn't my intention to help other people. I just didn't know how to do it. Very simple. By the way, there's a book dale Carnegie, 1990 36 How to make friends and how to influence others has the entire bible, you just read it and you're done and you apply it every day and I wish I could, I was good enough to apply it every day, but it's just simple things, right? Like be positive, remember people's name, smile and eventually have empathy, Like really think that the person that you will hate and you think it's an idiot, it's actually just like yourself, it's a person who's struggling who means well and who might need help and guess what you need help. </s><s>[INST] I've recently spoken with Stephen Schwarzman, I'm not sure if you know who that is, but so [/INST] he said on my list, I </s><s>[INST] noticed, but he said uh sort of to expand what you're saying that uh one of the biggest things that you can do is here people when they tell you what their problem is and then help them with that problem. He says, it's surprising how few people, like actually listen to what troubles others and because it's right there in front of you and you can benefit the world the most and in fact yourself and everybody around you by just hearing the problems and solving [/INST] them. I mean that's my my little history of engineering that is while I was engineering with computers, I didn't care at all what the computer's problems for because I just told him to do and to do it and it just doesn't work this favorite people, it doesn't work with me if you come to me and said with the way I do the opposite, </s><s>[INST] but let's return to the comfortable world of engineering. Can you, can you tell me in broad strokes in how you see it? Because you're the core of starting at the core of driving it, the technical evolution of autonomous vehicles from the first DARPA grand challenge to the incredible success we see with the program you started with google self driving car and way more in the entire industry that's sprung up all the different kinds of approaches, debates and so on. [/INST] When the idea of self driving car goes back to the eighties, there was a team of Germany and the team at Carnegie Mellon that did some very pioneering work. But back in the day, I'd say the computers were so deficient that even the best professors and engineers in the world basically stood no chance. It then folded into a phase where the U. S. Government spent at least half a billion dollars that I could count on research projects. But the way the procurement works. A successful stack of paper describing lots of stuff that no one's ever gonna read was a successful product of a research project. So we trained our researchers to produce lots of paper that all changed for the DARPA grand challenge. And I really got to credit the ingenious people at DARPA and the US government in Congress that took a complete new funding model where they said that's not fund effort, let's fund outcomes. And it sounds very trivial but there was no tax code that allowed the use of congressional tax money for a price. It was all effort based. So if you put in $100 in you could charge 100 hours, you put in $1000 and you could build $1000 by changing the focus on making the price we don't pay you for development, we pray for the accomplishment. They drew in, they automatically drew out all these contractors who are used to the drug of getting money power and they drew in a whole bunch of new people and these people are mostly crazy people. There were people who had a car and a computer and they wanted to make a million bucks. The million bucks for visual price money was then doubled and they felt if I put my computer in my car and program it, I can be rich and that was so awesome like like half the teams, there was a team that was a surfer dudes and they had like two surfboards on the vehicle and brought like these fashion girls, super cute girls like twin sisters. Um and you could tell these guys were not your common uh beltway bandit who gets all these big multi million and billion dollar countries from the U. S. Government um and there was a great reset universities moved in. I was very fortunate at stanford that had just received tenure, so I couldn't get fired when I want to do otherwise, I would have done it and I had enough money to finance this thing. Uh and I was able to attract a lot of money from from third parties and even car companies moved in, They kind of moved in very quietly because they were super scared to be embarrassed that they are covered flip over, but Ford was there and Volkswagen was there and a few others and GM was there. So it kind of reset the entire landscape of people and if you look at who's a big name in self driving cars today, these were mostly people who participated in those challenges. </s><s>[INST] Okay, That's incredible. Can you just comment quickly on your sense of lessons learned from that kind of funding model and the research that's going on academia in terms of producing papers, is there something to be learned and scaled up bigger having these kinds of grand challenges that could improve outcomes. [/INST] So I'm a big believer in and focusing on kind of an end to end system. I'm a really big believer in an insistence building. I've always built systems in my academic career even though I do a lot of mouth and an abstract stuff, but it's all derived from the idea of let's solve a real problem and it's very hard for me to be an academic and say, let me solve a component of a problem. Like if someone feels like non monetary logic or ai planning systems where people believe that a certain style of problem solving is the ultimate end objective and, and I would always turn around and say, hey, what problem would my grandmother care about that doesn't understand computer technology and doesn't want to understand how can I make her love what I do because only then do I have an impact on the world. I can easily impress my colleagues. That's that's that that is much easier. But impressing my grandmother is very, very hard. So I, I was always thought if if I can build a self driving car and uh and my grandmother can use it even after she loses her driving privileges or shedding can use it or we, we saved maybe a million lives a year, that would be very impressive. And then there's so many problems like this, like there's a problem with curing cancer or whatever that is, live twice as long Once the problem is defined. Of course. I can't solve it in its entirety. Like it takes sometimes tens of thousands of people to find a solution. There's no way you can fund an army of 10,000 at Stanford. So you're going to build a product. It's been a meaningful prototype. And the DARPA grand challenge was beautiful because it told me what this product I've had to do. I didn't have to think about what it had to do. It just had to read the rules and it was really beautiful </s><s>[INST] at its most beautiful. You think what academia could aspire to is to build a prototype. That's the systems level that solves, gives you an inkling that this problem could be solved with this [/INST] project. First of all, I want to emphasize what academia really is and I think people misunderstand it first and foremost, Academia is a way to educate young people first and foremost, a professor as an educator. No better every word, a small suburban college or whether you are a Harvard or stanford professor. Um that's not the way most people think of themselves in academia because we have this kind of competition going on for citations and and and publication. That's a measurable thing, but that is secondary to the primary purpose of educating people to think now in terms of research, most of the great science, the great research comes out of universities, you can trace almost everything back, including google to universities so there's nothing really fundamentally broken here. It's a good system and I think America has the finest university system on the planet. Um we can talk about reach and how to reach people outside the system. It's a different topic, but the system itself is a good system. If I had one wish, I would say it would be really great if there was more debate about what the great big problems are in society and focus on those and most of them are interdisciplinary. Unfortunately, it's very easy to fall into a inner disciplinary viewpoint where your problem is dictated. But but your closest colleagues believe the problem is it's very hard to break out and say, well there's an entire new field of problems. So give an example. Prior to me working on self driving cars, I was a roboticist and machine learning expert and I wrote books on robotics. Uh something called probabilistic robotics is a very methods driven kind of viewpoint of the world. I built robots that acted in museums as tour guides that let Children around. And it's something that at the time was moderately challenging. When I started working on cars, several colleagues told me Sebastian you're destroying your career because in our feature of robotics, cars looked like as a gimmick and they're not expressive enough, they can only for this model and and the breaks, there's no dexterity, there's no complexity, it's just too simple and no one came to me and said, wow, if you solve that problem, you can save a million lives right Among all robotic problems that I've seen in my life. I would say the self driving car transportation is that one has the most hope for society. So how come the robberies community wasn't all over the place? And it has become because we focus on methods on solutions and not on problems like if you go around today and ask your grandmother, what bugs you. What really makes you upset? I challenge any academic to do this and then realize how far your visa is probably away from that today. </s><s>[INST] At the very least. That's a good thing for academics to deliberate on. [/INST] The other thing that's really nice in Silicon Valley is Silicon Valley is full of smart people outside academia. Right? So there's the larry pages and magazines or books in the world who are anywhere smart or smarter than the best academics are made in my life. And what they do is they are at a different level. They build the systems they build, they build the customer facing systems. They built things that people can use without technical education. And they are inspired by research, they're inspired by scientists, they hire the best phds from the best universities for a reason. Um, so I think there's kind of vertical integration that between the real product, the real impact and the real thought the real ideas that's actually working surprisingly well in Silicon Value. It did not work as well in other places in these nations. When I worked at Carnegie Mellon, we had the world's finest computer science university, but there wasn't those people in Pittsburgh that would be able to take these very fine computer science ideas and turn them into massive the impactful products, uh, that symbiosis seemed to exist pretty much only in Silicon Valley and maybe a bit in boston and Austin. </s><s>[INST] Yeah, with stanford, that's, that's, that's really, really interesting. So if we look a little bit further on from the DARPA grand challenge and the launch of the google self driving car, what do you see as the state, the challenges of autonomous vehicles as they are now, is actually achieving that huge scale and having a huge impact on society. [/INST] I'm extremely proud of what has been accomplished and again, I'm taking a lot of credit for the work for us and I'm actually very optimistic and people have been kind of worrying. Is it too fast as the slow by the not there yet and so on. It is actually quite an interesting heart problem uh, in that a self driving car to build one that manages 90% of the problems encountered in everyday driving is easy. We can literally was over the weekend To do, 99% might take a month, Then there's 1% left. So 1% would mean that you still have a fatal accident every week. Very unacceptable. So now you work on this 1% and the 99% of that, there were any 1% is actually still relatively easy, but now you're down to like 1/100 of 1% and it's still completely unacceptable in terms of safety. Um so the variety of things you encounter are just enormous and that gives me enormous respect for human beings to be able to deal with the couch on the highway, right or the D. N. A headlight or the blown tire that had never been trained for and all of a sudden have to handle in an emergency situation and often do very very successfully. It's amazing from that perspective of safe driving actually is given how many millions of miles we drive every year in this country. Um, we are now at a point where I believe the technology is there and I've seen it, I've seen it in way more. I've seen it in active scene in cruise, in a number of companies and and voyage where vehicles not driving around and basically flawlessly are able to drive people around and in limited scenarios. In fact you can go to Vegas today and order a someone lift and if you get the right setting of your app, you'll be picked up by a driverless car. Now there's still safety drivers in there but it's a fantastic way to kind of learn what the limits of technology today and there's still some glitches. But the glitches have become very, very rare. I think the next step is going to be two down cost it to harden it. The entrapment that sends us are not quite an automotive grade standard yet and then to really build the business models to really kind of go somewhere and make the business case and the business case is hard work. It's not just, oh my God, we have this capability. People that's going to buy it. You have to make it affordable. You have to, uh, give people that find the social acceptance of people. None of the teams yet has been able to gutsy enough to drive around without a person inside the car. And that's the next magical hurdle will be able to send these vehicles around completely empty in traffic. And I think, I mean I would every day wait for the news that Raymond has just done this. </s><s>[INST] So, you know, interesting, you mentioned gutsy. Let me let me ask some, uh, maybe unanswerable question, Maybe edgy questions. But in terms of how much risk is required, some guts in terms of leadership style, it would be good to contrast approaches and I don't think anyone knows what's right. But if we compare Tesla and Waymo for example, Elon musk and the Waymo team, the, there's slight differences in approach. So on the Ellen side, there's more, I don't know what the right word to use but aggression in terms of innovation. And on Waymo side there's more sort of cautious safety focused approach to the problem. What do you think it takes, what leadership at which moment is right? Which approach is right? [/INST] Look, I I don't sit in either of those teams, so I'm unable to even verify, like somebody says correct in the end of the day, every innovator in that space will face a fundamental dilemma. And I would say you could put aerospace titans into the same bucket, which is, you have to balance public safety with your drive to innovate. And this country in particular in States has 100 plus year history of doing this very successfully. Uh, air travel is what 100 times a safe per mile than ground travel and then cars and there's a reason for it because people have found ways to be very method logical about ensuring public safety while still being able to make progress on important aspects. For example, like yellin noise and fuel consumption. Um, So I think that those practices are proven and they actually work, we live in the world safer than ever before. And yes, there will always be the provision that something goes wrong. There's always the possibility that someone makes a mistake or there's an unexpected failure. You can never guarantee to 100% absolute safety other than just not doing it. But I think I'm very proud of the history of the United States. I mean we've we've dealt with much more dangerous technology like nuclear energy and and kept that safe too. We have nuclear weapons and we keep those safe. So we have methods and procedures that really balance these two things very, very successfully. </s><s>[INST] You mentioned a lot of great autonomous vehicle companies uh, that are taking sort of the level four, level five, they jump in full autonomy with a safety driver and take that kind of approach and also through simulation and so on. There's also the approach that Tesla autopilot is doing, which is kind of incrementally taking a level two vehicle and using machine learning and learning from the driving of human beings and trying to creep up, trying to incrementally improve the system until it's able to achieve Love of four taught me so perfect autonomy in certain kind of geographical regions. What are your thoughts on these contrasting approaches? [/INST] When she first of all, I'm a very proud Tesla owner and I literally used the autopilot every day and it literally has kept me safe is a beautiful technology specifically for highway driving when I'm slightly tired because then it turns me into a much safer driver And that 100% confident that's the case in terms of the right approach. I think the biggest change I've seen since I've been away my team is it's a single deep learning. I think deep learning was not a hot topic when I when I started being more or google self driving cars, it was there. In fact we started google brain at the same time in google X. So I invested in deep learning, but people didn't talk about, it wasn't a hot topic. And nowadays there's a shift of emphasis from a more geometric perspective where you use geometric sensors, they give you a full three D view when you do geometric reasoning about all this box over here might be a car Towards a more human, like, Oh let's just learn about it. This looks like the thing I've seen 10,000 times before. So maybe it's the same thing, machine learning perspective and that has really put, I think all these approaches on steroids. Um, and Udacity, we teach a course in self driving cars. Uh in fact, I think we've graduated over 20,000 or so people on self driving car skills. So every, every self driving car team in the world now use our engineers and in this course, the very first homework assignment is to do lane finding on and images and lane finding images for laymen. What this means is you, you put a camera into your car or you open your eyes and even know where the line is, right? So so you can stay inside the lane with your car. Humans can do this super easily. You just look and you know where the line is just intuitively for machines for a long term was super hard because people would write these kind of crazy rules if there's like vinyl and Marcus and he's literally means this is not quite white enough. So it's all, it's not right or maybe the sun is shining, so when the sun shines and this is why And this is a straight line and maybe it's not quite a straight line because the vote is curved and and do we know that there's a six ft between lane markings or not or 12 ft whatever it is. Um and now what the students are doing, they would take machine learning. So instead of like writing these crazy rules for the lane marker is there to say, hey, let's take an hour driving and label it and tell the vehicle this is actually the laying by hand and then these are examples and have the machine find its own rules what lane markings are And within 24 hours now every student has never done any programming before in this space can write a perfect lane finder. As good as the best commercial land finders. And that's completely amazing to me. We've seen progress using machine learning that completely dwarfed anything that I saw 10 years ago ago. </s><s>[INST] Yeah. And just as a side note the self driving car, nano degree, the fact that you launched that Many years ago now, maybe four years [/INST] Ago, three years ago, three </s><s>[INST] years ago. It's incredible that that's a great example of system level thinking sort of just taking an entire course that teaches how to solve the entire problem, I definitely recommend people, [/INST] it's been popular, it's become actually incredibly high quality related with Mercedes and and and raise other companies in that space and we find that engineers from Tesla and Waymo are taking it today um the the inside was that two things one is existing universities will be very slow to move because the department lies and there's no department for self driving cars. So between mickey and doubly and computer science, getting these folks together into one room is really, really hard. Um and every professor listening, he ever know probably agree to that. And secondly, even if if all the great universities just did this which none so far has developed a curriculum in this field, it is just a few 1000 students they can partake because all the great universities are super selective. So how about people in India, how about people in china or in the Middle East or Indonesia or africa, why should those be excluded from the skill of building self driving cars? Are there any dumber than we are any less privileged? And the answer is we should just give everybody the skill to build a self driving car because if you do this then we have like 1000 self driving car startups and if 10% succeed it's like 100 that means 100 countries now we'll have self driving cars and be safer. </s><s>[INST] It's kind of interesting to imagine impossible to quantify but the number the, you know, over a period of several decades, the impact that has like a single course, like a ripple effect of society. I if you just recently talked to Andrew Ryan who was creative cosmos show, it's, it's interesting to think about how many scientists that show launched. And so it's really, um, in terms of impact, I can't imagine a better course than the self driving car of course that's, you know, there's other more specific disciplines like deep learning and so on that. Udacity is also teaching but self driving cars, it's really, really [/INST] interesting courses and it came at the right moment came at a time when there were a bunch of aqua hire is a acquisition of a company not for its technology or its products or business but for its people. Uh, so alcohol means maybe the company of 70 people. They have no product yet, but they're super smart people and they pay a certain amount of money. So I took the highest like GM Cruise and Uber and others and did the math and said, hey, how many people are there and how much money was paid and as a lower bound, I estimated the value of a self driving car engineer in these acquisitions to be at least $10 million. Right? So think about this, you, you get yourself a skill and your team up and build a company and you're worth now is $10 million. I mean that's kind of cool. I mean, But what other things could you do in life to be worth $10 million dollars within a year? </s><s>[INST] Yeah, amazing. But to come back for a moment on into deep learning and its application in autonomous vehicles. You know, what are your thoughts on Elon musk's statement? Provocative statement? Perhaps that light as a crutch? So this geometric way of thinking about the world may be holding us back if what we should instead be doing in this robotic space in this particular space of autonomous vehicles is using cameras, a primary sensor and using computer vision and machine learning is the primary way [/INST] to have two comments. I think first of all, we all know that people can drive cars without lighters in their heads because we only have eyes and we mostly just use eyes for driving. Um, maybe we use some other perception about our bodies, accelerations, occasionally our ears certainly not our noses. So so that the existence proof is there that ice must be sufficient. In fact, we could even drive a car. If someone put a camera out and then give us the camera image with non agency, you will be able to drive a car and that way the same way. So the camera is also sufficient. Secondly, I really love the idea that in in the Western world we have many, many different people trying different hypotheses. Um it's almost like an until like an hour until tries to forge for food, but you can sit, there is two aunts and agree with the perfect path is and then every single and marches for the most likely location of food is or you can even just spread out and I promise you that spread out solution will be better because if the discussing philosophical, intellectual and get it wrong and they're all moving the wrong direction, they're gonna waste a day and then we're gonna discuss again for another week. Whereas if all these ants going the right direction, someone's going to succeed and they're gonna come back and claim victory and get the Nobel prize or whatever the equivalent is and then all much in the same direction. And that's great about society, that's great about the Western society. We're not plant based, were not central base, We don't have a soviet union style central government that tells us where to forge. We just forged, we started in c corporate, you get invested money, go out and try it out and who knows who's gonna </s><s>[INST] win. I like it in your when you look at the long term vision of autonomous vehicles, do you see machine learning as fundamentally being able to solve most of the problems. So, learning from experience, [/INST] I'd say we should be very clear about what machinery is and is not, and I think there's a lot of confusion for this today is a technology that can go through large databases of repetitive patterns and find those patterns. So an example, we did a study at stand for two years ago where we applied machine learning to detecting skin cancer and images. And we harvested built a data set of 129,000 skin Photoshop s that all had been biopsied for what the actual situation was. And those included melanomas and carcinomas, also included rashes and and and and other skin conditions lesions. Um and then we had a network find those patterns and it was by and large able to then detect skin cancer with an iphone as accurately as the best board certified stanford level dermatologists. We proved that. No, no, this thing was great in this one thing I'm finding skin cancer but I couldn't drive a car. Um So, so the difference to human intelligence, as we do all these many, many things and we can often learn from a very small data set of experiences. Whereas machines still need very large data sets and things that were very repetitive. No, that's still super impactful because almost everything we do is repetitive. So that's going to transform human labor. But it's not this almighty general intelligence. We're really far away from a system that will exhibit general intelligence. Um to that end, I I actually committed at the naming a little bit because artificial intelligence, if you believe Hollywood is immediately mixed into the idea of human suppression and and machines superiority. I don't think that we're gonna see this in my lifetime. I don't think human suppression is a is a good idea. I don't see it coming. I don't see the technology being there but I see instead is a very pointed focus pattern recognition technology that's able to extract patterns from data from large datasets. And in doing so it can be super impactful, right? Super impactful. Let's take the impact of artificial terrorism. Human work We all know that it takes 7-10,000 hours to become an expert. If you're going to be a doctor or a lawyer or even a really good driver it takes a certain amount of time to become experts. Machines now are able and have been shown to observe people become experts and observe experts and then extract those rules from experts in some interesting way they could go from law to sales to driving cars to diagnosing cancer and then giving that capability to people who are completely new in their job. We now can and that's that's been done has been done commercially in many, many in sensations. That means you can use machine learning to make people expert on the very first day of their work Like think about the impact if if your doctor is still in the 1st 10,000 hours you have a doctor was not quite an expert yet who would not want the doctor who has devolved best expert and now we can leverage machines to really eradicate error and decision making error and lack of expertise for human doctors, they could save your life </s><s>[INST] if you can link on that for a little bit. In which way do you hope machines in the medical, in the medical field could help assist doctors. You mentioned this sort of accelerating the learning curve or people if they start a job Or in the 1st 10,000 hours can be assisted by machines. How do you, how do you envision that assistance looking? [/INST] So we built this this app for an iphone that can detect and classify and diagnose skin cancer. And he proved two years ago that it does pretty much as good or better than the best human doctor. So let me tell you a story. So there's a friend of mine that's called Ben Ben is a very famous venture capitalist. He goes to his doctor and the doctor looks at a mall and says hey that moral probably harmless and for some very funny reason he pulls out that form with high up, he is a collaborative in our study and the app says no, no, no, no this is a melanoma and and for background melanomas are and skin cancer is the most common cancer in this country Melanomas can go from stage 0 to stage four Within destiny year. Stage zero means you can basically cut it all yourself with the kitchen knife And be safe. And stage four means your chances of winning five more years and less than 20%. So it's a very serious, serious, serious condition. So this doctor who took over the iphone, look at the iphone was a little bit puzzled about just to be safe. Let's cut it out and biopsy it, That's the technical term for let's get an in depth diagnostics. It is more and just looking at it and it came back as cancerous as a melanoma and it was then removed. And my friend Ben, I was hiking with him and we were talking about ai and said, I told him to do this work on skin cancer. He's so funny. My doctor just had an iPhone that found my cancer, wow. So, I was like, completely intrigued, I didn't even know about this. So, here's a person. I mean, this is a real human life right now who doesn't know somebody has been affected by cancer. Cancer is cause of death. # two cancer is this kind of disease, that that is mean, in the following way, most cancers can actually be cured relatively easily if we catch them early. And and the reason why we don't tend to catch them early is because they have no symptoms, like your very first symptom of a gallbladder cancer or pancreatic cancer might be a headache. And when you finally go to your doctor because of these headaches or your your back pain and you're being imaged, It's usually stage four plus and that's the time when you're curing, chances might be dropped to a single-digit percentage. So if you could leverage the eye to inspect your body on a regular basis without even a doctor in the room, maybe when you take a shower over have you? I know that sounds creepy but then we might be able to save millions and millions of lives. </s><s>[INST] You've mentioned there's a concern that people have about near term impacts of ai in terms of job loss. So you've mentioned being able to assist doctors, being able to assist people in their jobs. Do you have a worry of people losing their jobs or the economy being affected by the improvements and they are [/INST] anybody concerned about job losses? Please come to get our city dot com. We teach contemporary tech skills and we have a kind of implicit job promise. We often when when we measure, we spend way over 50% of our graduates and new jobs and they're very satisfied about it And it costs almost nothing because like 1500 max of something like that. </s><s>[INST] And so there's a cool new program. They agree with the U. S. Government guaranteeing that you will help give scholarships that educate people in this kind of situation [/INST] you were working with the U. S. Government on on any idea of basically rebuilding the american dream. So you're asking is just dedicated 100,000 scholarships for citizens of America for various levels of course is that eventually will get you a job. And those courses are somewhat relate to the tech sector because the tech sector is kind of the hardest sector right now and they range from inter level digital marketing to very advanced self driving car engineering. And we're doing this with the White House because he thinks bipartisan it's an issue that is that if you want to really make America great being able to be part of the solution and live the american dream requires us to be proactive about our education and our skill set. It's just the way it is today and it's always been this way and we always had this american dream to send our kids to college and now the american dream has to be to send ourselves to college. You can do this very very very big efficiently and very very well. We can squeeze in in the evenings and things to online at all ages all ages. So our our learners go from age 11 to age 80. Um I just traveled Germany and uh and the guy in the train compartment next to me was my students, wow that's amazing, think about impact. We've become the educator of choice for now. I believe officially six countries or five countries, most in the Middle East like Saudi Arabia and in Egypt In Egypt. We just had a cohort graduate um where we had 1100 high school students that went through programming skills proficient at the level of computer science undergrad. And we had a 95% graduation rate even though everything is online, it's kind of tough. But we're kind of trying to figure out how to make this effective. The vision is the vision is very, very simple. Division is education ought to be a basic human, right? It cannot be locked up behind ivory tower walls. Only for the rich people, for the parents who might be bribed themselves into the system and only for young people and only for people from the right demographics and geography and possibly even the right race. It has to be opened up to everybody. If we if we are truthful to the human mission to be truthful to our values, we're going to open up education to everybody in the world. So udacity is pledge of 100,000 scholarships. I think it's the biggest pledge of scholarships ever in terms of the numbers. And we're working as I said at the White House and with very accomplished ceos like tim cook from Apple and others to really bring education to everywhere in the world, </s><s>[INST] not to ask you to pick the favorite of your Children, but [/INST] at this point it's transfer only have one that I know of? Okay, </s><s>[INST] good. Uh in this particular moment, What nano degree. What's that? Of course is are you most excited about udacity or is that too impossible to [/INST] pick? I've been super excited about something we haven't launched yet in the building, which is, let me talk to our partner companies. We have now a very strong footing in the enterprise world in order to our students, we've kind of always focused on these hard skills like the programming skills or math skills or building skills or design skills and a very common ask is soft skills. Like how do you behave in your work, how you develop empathy? How do you work in a team? What are the very basics of management? How do you do time management? How do you advance your career in the context of a broader community and that's something that we haven't done very valid audacity and I would say most universities are doing very poorly as well because you're so obsessed with individual test scores and so little pay, so little attention to teamwork in education. So that's something I see us moving into as a company because I'm excited about this and I think, look, we can teach people tech skills and they're going to be great. But if you teach people empathy that's going to have the same impact </s><s>[INST] maybe harder than self driving cars. But I [/INST] don't think so. I think the rules are really simple. You just have to, you have to, you have to want to engage its, we we literally went in school in K through 12, we teach kids like get the highest math score and if you are a rational human being, you might evolve from this education, say having the best math school and the best english scores making me the best leader. And it turns out not to be the case, it's actually really wrong because making, first of all in terms of math scores, I think it's perfectly fine to Ohio summer with great math skills, you don't have to do yourself, you can't hire some of the great empathy for you that's much harder but it can always hire some with great mouth skills. But we live in in a fluent world where we constantly deal with other people and that's a beauty, it's not a nuisance, it's a beauty. So if we somehow develop that muscle that we can do that well and empower others in the workplace, I think we're gonna be super successful </s><s>[INST] and I know many fellow robot assistant computer scientists that I will insist take this [/INST] course. So we named </s><s>[INST] You not to be named many many years ago, 1903. The Wright Brothers flew in kitty hawk for the first time and you've launched a company of the same name Kitty Hawk with the dream of building flying cars E vite halls. So at the big picture, what are the big challenges of making this thing that actually have inspired generations of people about what the future looks like, What does it take? What are the biggest challenges. [/INST] So so flying cars has always been a dream. Every boy, every girl wants to fly, let's be honest, yes, and let's go back in our history of your dreaming of flying. I think my honestly my single most remembered childhood dream has been a dream where I was sitting on a pillow and a good fly, It was like five years old, remember like maybe three dreams of my childhood, but that's the one I remember most vividly. Um and then Peter Steele famously said their promises flying cars and they gave us 140 characters pointing Twitter at the time, limited message sites, 240 characters. So if you're coming back now to really go for this super impactful stuff like flying cars um and to be precise, they're not really cars, they don't have wheels. Um they're actually much closer to the helicopter than anything else. They take off vertically in the fly horizontally, but they have important differences. One difference is that they are much quieter. Uh we just released a vehicle, project heavy side, they can fly over you as low as a helicopter and you basically can't hear, it's like 38 decibels, it's like, like the, if you go inside the library, you might be able to hear it but anywhere outdoors, your immune noises higher um secondly they're, they're much more affordable, they are much more affordable than helicopters And the reason is helicopters are expensive for many reasons. Um, there's lots of single point of figures and helicopter, there's a bold between the blades that's cause jesus bolt and the reason why it's called jesus borders, if this boat breaks, you will die. There is no second solution in helicopter flight. Whereas we have these distributed mechanism when you go from gasoline to electric, you can now have many, many, many small motors as opposed to one big motor. And that means if you lose one of those motors, not a big deal heavy side, if it loses a motor has eight of those, we lose one of those eight motors has seven left. You can take off just like before uh, and land just like before. Um, we're now also moving into a technology, it doesn't require a commercial pilot because on some level flight is actually easier than ground transportation in self driving cars. Uh, the world is full of like Children and bicycles and other cars and mailboxes and curbs and, and shrubs and what have you, all these things you have to avoid When you go above the buildings and tree lines, there's nothing there. I mean you can do the test right now look outside and count the number of things you see flying. I'd be shocked if you could see more than two things. It's probably just zero In the bay are the most I've ever seen was six And maybe it's 15 or 20, but not 10,000. So the sky is very ample and very empty and very free. So the vision is, can we build a socially acceptable mass transit transit solution for daily transportation that, that is affordable. And we have an existence proof heavy side can fly 100 miles in range with still 30% electric reserves. It can fly up to like 100 and 80 miles an hour. We know that that solution, that scale would make your ground transportation 10 times as fast as a car Based on use census of 36 data, uh, which means you would take your 300 hours of day of yearly commute down to 30 hours and giving 270 hours back. Who wouldn't want, I mean, who doesn't hate traffic? Like I hate, give me the person who doesn't hate traffic. I hate traffic every day every time I'm in traffic. I hated. Uh, and if we could free the world from traffic, we have technology, we can free the world from traffic. We have the technology. It's there. We have an existence proof that it's not a technological problem anymore. </s><s>[INST] Do you think there is a future where tens of thousands, maybe hundreds of thousands of both delivery drones and flying cars of this kind. A V stars fill the sky. [/INST] I absolutely believe this. And um, there's obviously the societal acceptance is a major question. And of course safety is I believe in safety gear and exceed ground transportation, safety as has happened for aviation already commercial aviation and in terms of acceptance, I think one of the key things is noise. That's why we are focusing relentlessly on noise and we've been perhaps the crisis electric veto vehicle ever built. Um, the nice thing about the sky is a three dimensional. So, so any mathematician will immediately recognize the difference between one d of like a regular highway to three of the sky. Um, but to make it clear for, for the layman, um, say you want to make 100 vertical lanes of highway 11 in SAn Francisco because you believe building 100 vertical lanes is the right solution. Imagine how much it would cost to stack 100 vertical lanes physically onto 101. There would be private if there would be consuming the world's GDP for entire year just for one highway. It's amazing, expensive. Okay in the sky it would just be a recompilation of a piece of software because all these lanes are virtual. That means any vehicle that is in conflict with another vehicle would just go to different altitude and then the conflict is gone. And if you don't believe this, that's exactly how how commercial aviation works. When you fly from new york to SAN Francisco, another plane flies from SAn Francisco new york, there are different altitudes, so they don't hit each other. It's a solved problem for the jets space and it will be a solved problem for the urban space there's companies like google Ring and Amazon working on very innovative solutions, how do we have space management? It is exactly the same principles as we use today throughout today's Jets. There's nothing hard about this. </s><s>[INST] Do you envision autonomy being a key part of it? So that that the the flying vehicles are either semi autonomous or fully autonomous. [/INST] 100% autonomous. You don't want idiots like me fly in the sky, I promise you. And if you have 10,000, what's the movie? The fifth element to get people to happen if it's not autonomous </s><s>[INST] and a centralized. That's a really interesting idea of a centralist sort of a management system for lanes and so on. So actually just being able to have similar as we have in the current commercial aviation but scale it up too much much more vehicles. That's a really interesting optimization problems. [/INST] It is very mathematically very very straightforward. Like the gap we live between jet's Gargantua and part of the reason is there isn't that many jets. So it just feels like a good solution today when you get vectored by air traffic control someone talks to you right so any ATC controller might have up to maybe 20 planes on the same frequency and then they talk to you have to talk back And it feels right because there is more than 20 planes around anyhow. So you can talk to everybody. But if there's 20,000 things around you can talk to everybody anymore. So we have to do something that's called digital like text messaging. Like we do have solutions like we have got 45 billion smartphones in the world now right? And they're all connected and some of the solve the scale problem for smartphones, we know where they all are. They can talk to somebody and they're very reliable, they're amazingly reliable. We could use the same system, the same scale for air traffic control. So instead of me as a pilot talking to a human being and in the middle of the conversation receiving a new frequency like how ancient is that? We could digitize the stuff and and digitally transmit the right flight coordinates and that solution will automatically scale to 10,000 vehicles. </s><s>[INST] We talked about empathy a little bit. Do you think we will one day build an ai system that a human being can love? And that loves that human back like in the movie her [/INST] look, I'm a pragmatist for me a i is a is a tool, it's like a shovel and the ethics of using the shovel. I always with us, the people and there has to be this way in terms of emotions, I would hate to come into my kitchen and see that my refrigerator spoiled all my food. Then have it explained to me that it fell in love with the dishwasher and it wasn't as nice as the dishwasher. So as a result it neglected me. That would just be a bad experience and it would be a bad product. Would probably not recommend this refrigerator to my friends. Um and that's where I draw the line. I think to me technology has to be reliable. It has to be predictable. I want my car to work. I don't want to fall in love with my car. I I just wanted to work. I wanted to compliment me not to replace me. I have very unique human properties and I want the machines to make me turn me into a superhuman. Like I'm already a superhuman today. Thanks to the machines that surround me and give you examples. I can Run across the Atlantic at near the speed of sound at 36,000 ft today. That's kind of amazing. I can uh my voice now carries me all the way to Australia. Um using a smartphone today and it's not not the speed of sound which would take hours. It's the speed of light. My voice travels at the speed of light. How cool is that? That makes me super human. I would even argue my flushing toilet makes me super human. Just think of the time before flushing toilets. And and maybe you have a very old person in your family that you can ask about this or take a trip to rural India to experience it. Um it makes me super human. So to me what technology does, it complements me. It makes me stronger therefore words like love and compassion have very little uh huh. I have very little interest in these four machines. I have interested in people </s><s>[INST] you don't think uh first of all beautifully put, beautifully argued. But do you think love has use in our tools [/INST] compassion? I think love is a beautiful human concept. And if you think of what love really is, love is a means to convey safety to convey trust. I think trust has a huge need in technology as well as people. We want to trust our technology the same or similar way we trust people. Um in human interaction standards have emerged and feelings, emotions have emerged. Maybe genetically maybe biologically that are able to convey a sense of trust, sense of safety, sense of passion, of love of dedication that that makes the human fabric. And I'm a big slacker for love. I want to be laughed, I want to be trusted to be admired all these wonderful things. And because all of us we have this beautiful system. I wouldn't just blindly copy this to the machines. Here's why When you look at say transportation um you could have observed that uh up to the end of the 19th century, almost all transportation Use any number of legs from one leg to two legs, 2000 legs. And you could have concluded that is the right way to move about the environment. Um, we've been made exceptional birds who is flapping wings. In fact, there are many people in aviation that flapped wings to their arms and jump from cliffs. Most of them didn't survive. Um, then then the interesting thing is that the technology solutions are very different. Uh, like in technology is very easily with the wheel in biology is super hard to build a way. There's very few perpetually rotating things in biology and they're usually one sells, uh, things in an engineering. We can build wheels and those wheels gave rise to cars. Um, similar wheels gave rights to, to aviation. Like there's no thing that flights, they wouldn't have something that rotates like a jet engine or helicopter blades. So the solutions have used very different physical laws in nature and that's great. So for me to be too much focused on or this is how nature does it let's just replicated. If he really believed that the solution to the Agriculture revolution was a humanoid robot, you would still be waiting today </s><s>[INST] Again, beautifully put you said that you don't take yourself to seriously [/INST] didn't say that. Maybe want me to say that maybe you don't take me seriously. I'm not right. I </s><s>[INST] just made that up. But you know, you have a humor and a lightness about life that I think is it is beautiful and inspiring to a lot of people. Where does that come from? The smile, the humor, the lightness amidst all the chaos of the hard work that you and where does that come from? [/INST] I just love my life. I love, I love the people around me and have, I'm just so glad to be alive. Like I'm what 52? How to believe people say 52 is the new 51. So now I feel better. Um but in, in, in, in, in, in looking around the world looking just go back 203 100 years like Humanity is about 300,000 years old. But for the 1st 300,000 years minus the last 100 Our life expectancy would have been clustered -30 years roughly. Give or take. So I would be long dead now. Like that makes me just enjoy every single day of my life because I don't deserve this. Like why am I born today when so many of my ancestors died of horrible deaths like famines, massive wars Uh that ravaged Europe for the last 1000 years mystically disappeared after World War II when the Americans and the allies did something amazing to my country that didn't deserve it, a country of Germany. This is so amazing. And then when you're when you're alive and feel this every day then it is so amazing what we can accomplish what we can do. We live in the world. That is so incredibly vastly changing every day. Almost everything that we cherish from your smartphone to your flushing toilet. Um to all these basic inventions, your new clothes, you're wearing your, watch, your plane peninsula in, I don't know uh anesthesia for surgery. penicillin Have been invented in the last 150 years. So in the last 150 or something magical happened and I would trace it back to Gutenberg and the printing press that has been able to disseminate information more efficiently than before. That all of a sudden to be able to invent agriculture and nitrogen fertilization that made agriculture is so much more potent that we don't have to work on the farms anymore. And we can start reading and writing and we become all these wonderful things we are today from airline pilot to massage therapists to software engineer. This is amazing. Like living in that time is such a blessing. We should sometimes really think about this right steven Pinker who has a very famous author and philosopher whom I really adore, wrote a great book called Enlightenment now and that's maybe the one book I would recommend. And he asked the question if there was only a single article written in the 20th century, only one article, what would it be, what's the most important innovation of the most important thing that happened? And he would say this article would credit a guy named carl bosch and I challenge anybody. Have you ever heard of the name carl bosch, I hadn't uh there's a, there's a bosch corporation in Germany, but it's not associated with carl bosch. Um so I looked it up. Kharboush invented nitrogen fertilization and in doing so together with an older invention of irrigation was able to increase the yield per agricultural land by a factor of 26. So a 2,500% increase in infertility of land and that. So steve Pinker argues saved over two billion lives today. Two billion people who would be dead if this man hadn't done what he had done. Okay, think about that impact and what that means to society. Um that's, that's the way I look at the world. I mean it's just so amazing to be alive and be part of this and I'm so glad I lived after carl bosch and not before. </s><s>[INST] I don't think there's a better way to end as Sebastian. It's an honor to talk to you to have had the chance to learn from you. Thank you so much [/INST] for talking. Thanks for coming on like a real pleasure. </s><s>[INST] Thank you for listening to this conversation with Sebastian Thrun and thank you to our presenting sponsor cash app, download it. Use cold lex podcast, you'll get $10.10 dollars will go to first a stem education non profit that inspires hundreds of thousands of young minds to learn and to dream of engineering our future. If you enjoy this podcast? Subscribe on youtube, get five stars on apple podcast, support on Patreon or connect with me on twitter [/INST] and now let me leave </s><s>[INST] you with some words of wisdom from Sebastian Thrun. It's important to celebrate your failures as much as your successes. If you celebrate your failures really well. If you say wow, I failed, I tried, I was wrong, but I learned something, then you realize you have no fear when your fear goes away, you can move the world. Thank you for listening and hope to see you next time. [/INST] Yeah. </s> |
<s>[INST] by the way, have the, That the watch, and um, that's because we're talking about 20, That was really, um, the guy in the lecture hall giving you a pat on the back, joe give me the watch. Was he has life changing from. Yeah, yeah, yeah. It doesn't even, it didn't the fact that it was on a podcast or whatever, doesn't matter, learn how to, [/INST] um, form boundaries. That's probably the biggest, that's gonna be number one on my list because you're gonna have people around you who feel the need, that they're entitled to your time, who feel the need to criticize you and they're not coming from a good place. So it's very good for you to be like, I'm not interested in talking about this anymore right now, even if it's your parents, even if it's, especially if it's your parents, like, I need my space right now, you're entitled to your space. You're entitled to your time. No one knows you're you don't owe anyone responds. If someone has a question, you know them and answer especially if they're not coming at you in good faith or they're coming in a hostile way. Um That's a big one. Uh It's hard to learn at that age. Um and um and and be valuable to those who are around you be someone who people are happy to see. And if things are bad, like you're the one that they can rely on. Like I was just uh you know, a little bit under the weather. And I thought to myself, you know what if things got really bad, I'll call Blair and she she would take care of me. And and that kind of was very reassuring. </s><s>[INST] And you can always call me if you have your stuff lifted in in a in an urgent matter [/INST] because of the robots. </s><s>[INST] No, it's just me. It's kind of like that's those things that can help with or you're actually literally bleeding. Not a good caretaker. I can save you though. I can murder if you need somebody murdered this. [/INST] Um Wait, what advice would you have two kids that age? Mhm. And you're you're a lot younger than you think you are. That's the other one. Like I know like it's impossible to understand when you're 26 that your forties are better than your thirties because like, okay, old man, you're that's all cope, I promise you. It is </s><s>[INST] yeah, I I think he said so many beautiful things, I would say another version of the openness, I'll say take big risks when you're [/INST] young because if you fail, who cares, you're sleeping on a futon, who cares </s><s>[INST] and take them often. Um also this is more a little personal to me, I get pushback on this, but I think take big risks and work really hard like at whatever you do, like I think you just have to give yourself to a thing, it doesn't have to be in terms of time, but really give everything, so it's not like I'm going to try doing this, I'll try, I'll try try good with all your heart, like really commit yourself, that doesn't mean necessarily ours, that doesn't mean, but like if you fail at doing a thing that you commit to, it should hurt. So like when I compete in jiu jitsu or you, you do like sports and so on, don't just say I'm gonna have fun out there so on, no try to win and that because then if you don't hurts and you learn from that and then throughout, I think that's the goodness thing is be kind, it's like some of it is also a skill allowing yourself to be kind, I found myself earlier in life, I still do this, I find like when I hang out with people, people are often like cynical and negative and yeah, I try to avoid those people know, but like they have, I think everybody falls into that and sometimes it's the party norm thing. There's a temptation to me to kind of fit in by being more negative than I'm comfortable being. And so um resist the pressure. I think especially when you're younger, it's not cool to care. [/INST] The thing that drives when you're young. If you are a fan of a band, a writer, a podcast or an actor and people roll their eyes at you, watch out, Those people are dangerous, You should have it. If you love Avril Levine with her terrible music and she makes you gives you joy and people crap on you, they're wrong and you're right. So hold on to those things that make you happy and if people want to take that away from you or the how could you like that? Those people are not your friends, </s><s>[INST] Why do you have to go make life so complicated? My she's my favorite um favorite musician of all time. Jimi Hendrix second ever Levin first, um thank you for almost bringing a tear to my eye. You mentioned the Shadows in terms of love and you should have kids by now, I apologize if it's a personal one, but I think at least I have this thought and not from society, but for myself, like I want to get married, I wanna have kids. Do you feel the pressure of that? Do you want to have kids? [/INST] I don't want to have kids </s><s>[INST] get married, [/INST] I do want to get married. Um uh this was an issue that I had to kind of work out earlier this year um in terms of um the possibility of having kids, because I was uh in a relationship with someone who would have been in many ways literally a perfect mom. So I did my due diligence and I actually sat down with friends of mine who had kids and I say, give me the downside. Um what are </s> |
<s>[INST] Will also donate $10 to first an organization that is helping to advance robotics and stem education for young people around the world. And now here's my conversation with dan Carlin. Let's start with the highest philosophical question, do you think human beings are fundamentally good or are all of us capable of both good and evil and it's the environment that molds, how we, the trajectory that we take their life, [/INST] How do we define evil, evil seems to be a situational eye of the beholder kind of question. So if we define evil, maybe I can get a better idea of and, and and that could be a whole show couldn't defining evil. But when we say evil, what do we mean? </s><s>[INST] That's a slippery one. But I think there's some way in which your existence, your presence in the world leads to pain and suffering and destruction for many others in the rest of the world. So you you steal the resources and you use them to create more suffering than there was before in the world. So I suppose it's somehow deeply connected to this other slippery award was just suffering as you create suffering in the world. You bring suffering to the world. [/INST] But here's the problem. I think with it because I, I fully see where you're going with that and I understand it. The problem is, is the question of the reason for inflicting suffering. So sometimes one might inflict suffering upon one group of individuals in order to maximize a lack of suffering with another group of individual or one who might not be considered evil at all, might make the rational, seemingly rational choice of inflicting pain and suffering on a smaller group of people in order to maximize the opposite of that for a larger group of </s><s>[INST] people. Yeah, that's one of the dark things about, I've spoken and read the work of Stephen Kotkin, I'm not sure if you're familiar with the historian and he's basically a Stalin, uh joseph Stalin scholar. And one of the things I realized, I'm not sure where to put Hitler, but with Stalin, it really seems that he was sane and he thought he was doing good for the world. I really believe from everything I've read about Stalin that he believed that communism is good for the world. And if you have to kill a few people along the way, it's like you said, the small groups, if you have to sort of remove the people that stand in the way of this utopian system of communism, then that's actually good for the world. And it didn't seem to me that he could even consider the possibility that he was evil. He really thought he was doing good for the world. And that's stuck with me because he's one of the most is to our definition of evil. He seems to have brought more evil onto this world than almost any human in history and I don't know what to do with that. [/INST] Well, I'm fascinated with the concept, so fascinated by it that the very first hardcore history show we ever did, which was a full 15 or 16 minutes um was called alexander versus Hitler and the entire question about it was the motivations, right? So if you go to a court of law because you killed somebody, One of the things they're going to consider is why did you kill them, right? And if you killed somebody, for example, in self defense, you're going to be treated differently than if you maliciously killed somebody maliciously to take their wallet, right? And in the show, we we wondered because, you know, I don't really make pronouncements, but we wondered about, uh, if you believe Hitler's writings, for example, Minkoff, which, you know, is written by a guy who's a political figure who wants to get off. So, I mean, it's about as believable as any other political tract would be, but in his mind, the things that he said that he had to do were designed to for the betterment of the german people, right? Whereas alexander the Great, Once again, this is somebody from more than 2000 years ago. So with lots of propaganda in the intervening years. But one of the views of alexander the Great, is that the reason he did what he did was to, for lack of a better word, write his name in a more permanent graffiti on the pages of history, right? In other words, to glorify himself. And if that's the case, does that make alexander a worst person, that Hitler, because Hitler thought he was doing good. Whereas alexander, if you believe the interpretation was simply trying to exalt alexander. So, the motivations of the people doing these things, it seems to me matter, um I don't think you can just sit there and go, the only thing that matters is the end result because that might have been an unintentional byproduct, in which case that person had, you been able to show them the future might have changed what they were doing. So were the evil or misguided or wrong or made, you know, so, and I hate to do that because there's certain people like Hitler that I don't feel deserve the benefit of the doubt at the same time, if you're fascinated by the concept of evil and you delve into it deeply enough, you're going to want to understand why these evil people did what they did. And sometimes it can confuse the hell out of you, You know, who wants to sit there and try to see things from Hitler's point of view to get a better understanding and, and sort of commiserated with. So. Um, but I'm obviously first history show, I'm fascinated with the concept. </s><s>[INST] So do you think it's possible if we put ourselves in the mindset of some of the people that have led created so much suffering in the world that all of them had their motivations were had good intentions underlying them? [/INST] No, I don't, I mean, it's simply because there's so many, I mean the law of averages would would suggest that that's not </s><s>[INST] true. I guess it is pure evil possible, meaning you are, again, it's slippery, but you, the suffering is the goal, [/INST] suffering, intentional suffering. Yes, I think that, and I think that there's historical figures that that that one could point. And but that gets to the deeper question of are these people saying, do they have something wrong with them? Are they twisted from something in their youth? Um, you know, I mean, these are the kinds of things where you start to delve into the psychological makeup of these people. In other words, is anybody born evil? And I actually believe that some people are, I think the D. N. A. Can get scrambled up in ways. I think the question of evil is important too, because I think it's an eye of the beholder thing. I mean, if Hitler for example had been successful and we were today on the sixth or seventh leader of the third Reich, since I think his entire history would be viewed through a different lens, because that's the way we do things, right. Um, Jenkins con looks different to the Mongolians than he does to the residents of Baghdad. Right. Um, and I think so, so, and I have the beholder question I think comes into all these sorts of things. As you said, it's a very slippery question. </s><s>[INST] Where do you put as somebody who is fascinated by military history, where do you put violence as uh, as in terms of the human condition is a core to being human? Or is it just a little tool that we use every once in a while. [/INST] So I'm going to respond to your question with a question. What do you see the difference being between violence and force? Let me go farther. I'm not sure that violence is something that we have to put up with as human beings forever, that we must resign ourselves to violence forever. But I have a much harder time seeing us able to abolish force and I there's going to be some ground where if those two things are not the same and I don't know that maybe they are, where there's certainly some crossover and the reason why I think force, you know, you're an engineer, you'll understand this better than I do, but think about it as a physical law. Um if you can't stop something from moving in a certain direction without pushing back in that same direction, um I'm not I'm not sure that you can have a society or civilization without the ability to use a counterforce when things are going wrong, whether it's on an individual level, right? Person attacks another person. So you step in to save that person um or on uh you know, even at the highest levels of politics or anything else, a counter force to stop the inertia or the impetus of of of another movement. So, I think that force is is a simple, almost law of physics in human interaction, especially at the civilisational level, I think civilization requires a certain amount of if not violence than force. So um and again, they talked, I mean it goes back into ST Augustine, all kinds of christian beliefs about the proper use of force and people have philosophically tried to decide between can you have a sort of an ahi NSA buddhist sort of, we you know, we would be non violent toward everything and exert no force or or there's a reason to have force in order to create the space for good. I think force is inevitable now we can talk and I have not come up to the conclusion myself, if there is a distinction to be made between force and violence, I mean this is um is a non violent force enough or is violence when done for the cause of good, a different thing than violence done either for the cause of evil as you would say, or simply for random reasons? I mean we humans lack control sometimes we can be violent for no apparent reason or goal. Um and that's, I mean you look at the criminal justice system alone in the way we we interact with people who are acting out in ways that we as a society have decided is intolerable. Can you deal with that without force? And at some level violence? I don't know, can you maintain Peacefulness without force? I don't know, </s><s>[INST] just to uh be a little bit more specific about the idea of force. Do you put force as general enough to include force in the space of ideas. So you mentioned buddhism or religion or just twitter? [/INST] I can think of no things farther apart than that. Okay. </s><s>[INST] Is uh the battles we do in the space of ideas of uh you know, the great debates throughout history. Do you put force into that? Or do you in this conversation? Are we trying to right now keep it to just physical force in saying that you you have an intuition that force might be with us much longer than violence? [/INST] I think the to bleed together. So, um take Because it's it's always it's always my go to example, I'm afraid, and I'm sure that the listeners all hate it, but but take take Germany during the 1920s, early 1930s, before the Nazis came to power. Uh and they were always involved in some level of force, you know, beating up in the streets or whatever it might be. But think about it more like an intellectual discussion until a certain point? Um, is that it would be difficult, I imagine, to keep the intellectual counterforce of ideas from at some point degenerating into something that's more um coercion, um, counterforce if we want to use the phrases we were just talking about. So, I think the two are intimately connected. I mean, actions follow thought right, and at a certain point, I think especially when when one is not achieving the goals that they want to achieve through a peaceful discussion or argumentation or trying to convince the other side that sometimes the next level of operations is something a little bit more physically imposing, if that makes sense? We go from the intellectual to the physical. </s><s>[INST] Yeah. So it too easily spills over into violence and one leads to the other often. So you kind of imply to perhaps a hopeful message. But let me ask you in the form of a question, do you think we'll always have war? [/INST] I think it goes to the fourth question to. So for example, um, what do you do? I mean, we're let's let's play with Nation States now, although I don't know that Nation States are something we should think of as a permanent constitution forever. Um, but how is one Nation states supposed to prevent another Nation state from acting in ways that it would see is either detrimental to the global community or detrimental to the interests of their own nation state? Um, you know, and I think I think we've had this question of going back to ancient times, but certainly in the 20th century, this has come up quite a bit. I mean, the whole Second World War argument sometimes revolves around the idea of what the proper counterforce should be. Can you create an entity, a league of Nations? The United Nations, a one world entity, maybe even that that alleviates the need for counterforce involving mass violence and armies and navies and those things. I think that's an open discussion, we're still having, </s><s>[INST] it's good to think through that because having us like a united nations, there's usually a centralized control. So there's humans at the top, there's committees and uh, usually like leaders emerge a singular figures that then can become corrupted by power. And it's just a really important. It feels like a really important thought experiment and something to really rigorously think through how can you construct systems of government that are stable enough to push us towards less and less war and less and less on stable? And another tough word, which is unfair of application of force? You know, as that's really at the core of the question that we're trying to figure out as humans as our weapons get better and better and better destroying ourselves. It feels like it's important to think about how we minimize the over application or unfair application of force. [/INST] There's other elements that come into play to you and I are discussing this at the very high intellectual level of things, but there's also a tail wagging the dog element to this. So think of the society of warriors, a tribal society from a long time ago. Um, how much do the fact that you have warriors in your society and that their reason for existing, what they take pride in what they train for, um, what their status in their own civilization. How much does that itself drive the responses of that society, right. Um, how much do you need war to legitimize warriors? Um, you know, that's the old argument that you get to and had this in the 20th century to that the creation of arms and armies creates an incentive to use them, right? And and that they themselves can drive that incentive as as a justification for their reasons for existence. You know? Um, that's where we start to talk about the interactivity of all these different elements of society upon one another. So when we talk about, you know, governments and war, well, you need to take into account the various things those governments have put into place in terms of systems and armies and things like that to protect themselves, right? For reasons we can all understand, but they exert a force on your range of choices, don't they? </s><s>[INST] It's true, you're making me realize that, uh, in my upbringing and I think I'm bringing of many warriors or heroes, you know, to me, I don't know where that feeling comes from, but to sort of die fighting is, uh, it's an honorable way to die. It feels like that [/INST] I've always had a problem with this because as a person interested in military history, the distinction is important. Um, and I try to make it at different levels. So at base level, the people who are out there on the front lines doing the fighting, uh, to me, those people can be compared with police officers and firemen and people that fire persons. Um, but but I mean, people that are involved in an ethical attempt to perform a task, which ultimately one can see in many situations as being a saving sort of task, right? Or or if nothing else, a self sacrifice for what they see as the greater good. Now, I draw a distinction between the individuals and the entity that they are part of a military. And I certainly draw a distinction between the military and then the entire, for lack of a better word, military industrial complex, that that service is a part of. Uh, I feel a lot less um moral attachment to uh, to those upper echelons than I do the people on the ground. The people on the ground could be any of us and have been in a lot of, you know, we have a very professional uh, sort of military now where it's a very uh, a subset of the population, but in other periods of time we've had conscription and drafts and and it hasn't been a subset of the population. It's been the population, right? And so it is the society oftentimes going to war, and I make a distinction between those warriors and the entities either in the system that they are part of the military or the people that control the military at the highest political levels. I feel a lot less moral attachment to them. And I have a much harsher about how I feel about them. I do not consider, uh, the military itself to be heroic and I do not consider the military industrial complex to be heroic, I do think that is a tail wagging the dog situation. I do think that draws us into looking at um, military endeavors as a solution to the problem much more quickly than we otherwise might. And to be honest, to tie it all together, I actually look at the, at the victims of this as these soldiers we were talking about. I mean, if you, if you set a fire to send firemen into to fight, </s><s>[INST] um, [/INST] then I feel bad for the firemen. I feel like you've abused the trust that you give those people right? So when, when people talk about war, I always think that the people that we have to make sure that a war is really necessary, uh, in order to protect are the people that you're going to send over there to fight that the greatest victims in our society of war are often the warriors. So I, in my mind, um, you know, when we see these people coming home from places like Iraq, a place where I would have made the argument and did at the time that we didn't belong to me, those people are victims. And I know they don't like to think about themselves that way because it runs totally counter to the ethos. But if you're sending people to protect this country's shore's, those are heroes. If you're sending people to go do something that they otherwise probably don't need to do. But they're there for political reasons or anything else you want to put in that's not defense related. Well then you've made victims of our heroes. And so I I feel like we do a lot of talk about our troops and our soldiers and stuff, but we don't treat them as valuable as we, as the rhetoric makes them sound. Otherwise we would be more, we would be much more careful about where we put them. If you're going to send my son and I don't have a son, I have daughters, but you're going to send my son into harm's way. I'm going to demand that you really need to be sending him into harm's way. And I'm going to be angry at you if you put him into harm's way, if he doesn't, if it doesn't warrant it. And so I have much more suspicion about the system that sends these people into these situations where they're required to be heroic, then I did the people on the ground that I look at as, um, either the people that are defending us, you know, in situations like this, you know, the Second World War, for example, or, or the people that, um, turn out to be the individual victims of a system where there's just a cog in the machine and the machine doesn't really care as much about them as as the rhetoric and the propaganda would insinuate. </s><s>[INST] Yeah. And uh, as my own family history, it would be nice if we can talk about. There's a gray area in, in the places that you're talking about. [/INST] It's a gray area in everything, </s><s>[INST] everything. But when that gray area is part of your own blood as it is for me, it's it's worth shining a light on somehow. [/INST] Sure, give me example what you mean. </s><s>[INST] So you did a program of four episodes of Ghosts of the Ost Front. So I was born in the soviet Union. I was raised in Moscow. My dad was born and raised in Kiev. My grandmother who just recently passed away was uh raised in Ukraine. She, it's a small city on the border between Russia and Ukraine. I have a [/INST] grandfather born in Kiev in </s><s>[INST] Kiev. The interesting thing about the timing of everything as you might be able to connect as she survived. She's the most badass woman I've ever encountered in my life and most of the warrior spirit I carry is probably from her. She survived polymer more the Ukrainian starvation of the 30s. She was a beautiful teenage girl during the Nazi occupation of so she survived all of that and of course family that everybody, you know, and so many people died the whole process. So, and one of the things you talk about in your program is that the gray area is even with the warriors, it happened to them just because you're saying now they didn't have a choice. So my my grandfather on the, on the other side, he was a machine gunner. Uh, that was in Ukraine, that that in the red army in the red Army and they threw uh like the statement was that there's, I don't know if it's obvious or not, but the rule was there's no surrender. So you you better die. So you I mean, you're basically, the goal was when he was fighting and he was lucky enough one of the only to survive by being wounded early on is there was a march of nazis towards against Moscow. And the whole goal in Ukraine was too slow every to slow them into the, into the winter. I mean, I view them as such a hero and he believed that he's indestructible, which is survivor bias and that, you know, bullets can't hurt him and that's what everybody believed. And of course, basically everyone that uh he quickly rose through the ranks. Let's just put it this way because everybody died. It was just bodies dragging these heavy machine guns, like always, you know, I was slowly retreating, shooting and retreating, shooting and retreating. And I don't know he was a hero to me. Like I always, I grew up thinking that he was the one that sort of defeated the Nazis, right? And but the reality that there could be another perspective, which is all of this happened to him by the incompetence of Stalin the incompetence, incompetence and uh men of uh the soviet Union being used like ponds in a in a ship really played game of chess. Right? So like one narrative as him as a victim as you're kind of describing. And it then somehow that's more paralyzing and that's more, yeah, I don't know. It feels better to think of him as a hero and as Russia, soviet union is saving the world. I mean, that narrative also is in the United States that that uh United States was key in saving the world from the nazis. It feels like that narrative is powerful for people. I'm not sure and I carry it still with me. But when I think about the right way to think about that war, I'm not sure if that's the correct narrative. [/INST] Let me suggest something. There's a line that that a marine named Eugene Sledge had said once. And I keep it on my phone because it's it's it makes a real distinction. And he said the front line is really where the war is and anybody even 100 yards behind the front line doesn't know what it's really like. Now. The difference is is there are lots of people miles behind the front line that are in danger, right? You can be in a medical unit in the rear and artillery could strike you planes because you could be in danger. But at the front line there are two different things. One is um that that at least. And I'm doing a lot of reading on this right now and reading a lot of veterans accounts, James jones who wrote Books like from here to eternity, fictional accounts of the Second World War, but he based them on his own service. He was at Guadalcanal for example, in 1942 and Jones had said that the evolution of a soldier in front line action requires an almost surrendering to the idea that you're going to live. You become accustomed to the idea that you're going to die. And he said, you're a different person simply for considering that thought seriously because most of us don't. But what that allows you to do is to do that job at the front line, right? If you're too concerned about your own life, Um you become less of a good guy at your job, right? The other thing that the people in the one in the 100 yards of the front line do that. The people in the rear medical unit really don't as you kill and you kill a lot, right? You don't just, oh, there's a sniper back here. So I shot him if we go from one position to another and we kill lots of people, Those things will change you and what that tends to do not universally because I've read accounts from Red Army soldiers and they're very patriotic, right? But a lot of that patriotism comes through years later as part of the nostalgia. And the remembering when you're down at that front 100 yards, it is often boiled down to a very small world. So your grandfather was your grandfather that the machine gun, he's concerned about his position and his comrades and the people who he owes a responsibility to. And it's a very small world at that point. And to me that's where the heroism is, right? He's not fighting for some giant world civilisational thing. He's fighting to save the people next to him and his own life at the same time because they're saving him too. And and that there is a huge amount of heroism to that. And that gets to our question about force earlier, why would you use force? Well, how bout to protect these people on either side of me right there lives um now is their hatred? Yeah, I hated the Germans for what they were doing. As a matter fact. I uh I got a note from a pole not that long ago and I have this tendency to refer to the nazis, right? The regime that was and he said, why do you keep calling them nazis? He says say say what they were they were Germans. And this guy wanted me to not absolve Germany by saying, oh it was this awful group of people that took over your country. He said, the Germans did this and there's that bitterness where he says, let's not forget, you know what they did to us and why and what we had to do back. Right. Um, so for me, when we talk about these combat situations, the reason I call these people heroic is because of they're fighting to defend things. We could all understand me if you come after my brother and I take a machine gun and shoot you. Um, and you're going to overrun me. I mean, you're gonna that becomes a situation where we talked about Counterforce earlier, um much easier to call yourself a hero when you're saving people or you're saving this town right behind you. And you know, if they get through your machine gun, they're going to burn these villages, they're gonna throw these people out in the middle of winter. These families, that to me is a very different sort of heroism than this Amorphous idea of patriotism. Patriotism is a thing that we often get um used with right people. People manipulate us through love of country and all this because they understand that this is something we feel very strongly, but they use it against us sometimes in order to whip up a war fever or to get people, I mean, there's a great line and I wish I could remember it in its entirety, determined during had said about how easy it was to get the people into a war. He says, you know, you just appeal to their patriotism. I mean there's buttons that you can push and they take advantage of things like love of country and the way we, the way we have a loyalty and admiration to the warriors who put their lives on the line, these are manipulate herbal things in the human species that reliably can be counted on to move us in directions that in a more um sober, reflective state of mind, we would consider differently. It gets the mean, you get this war fever up and people, people wave flags and they start denouncing the enemy and they start signing, you know, we've seen it over and over and over again in ancient times this happened. </s><s>[INST] But the love of country is also beautiful. So I haven't seen in America as much. So people in America love their country like this patriotism, strong in America, but it's not as strong as I remember. Even with my sort of being younger, the love of the soviet union [/INST] now, was it the soviet union? This requires a distinction Or was it mother Russia? </s><s>[INST] What it really was was the Communist Party. Okay, so it was it was a system in place, the system in place like loving. I haven't quite deeply psychoanalyzed exactly what you love. I think you love the that like populist message of the worker of the common man. So [/INST] let me let me draw the comparison then. Um and I often say this that that the United States, like the soviet union is an ideological based society, right? So you take a country like France, it doesn't matter which french government you're in now, the friendship in the french for a long time, right? Uh it's not based on an ideology, right? Whereas what unites the United States is an ideology freedom, liberty, the constitution, this is what draws, you know, it's the e pluribus unum kind of the idea right there, That out of many one. Well, what what binds all these unique, different people, the shared beliefs, this ideology, the soviet union was the same way because as, you know, the soviet union Russia was merely one part of the soviet union, and if you believe the rhetoric until Stalin's time, everybody was going to be united under this ideological banner someday, it it was was a global revolution. Um so ideological societies are different and to be a fan of the ideological framework and goal, I mean, I'm a liberty person, right? I would like to see everybody in the world have my system of government, which is part of a of a bias, right? Because they might not want that, but I think it's better for everyone because I think it's better for me at the same time when the ideology, if you consider and, you know, this stems from ideas of the enlightenment and there's a bias there. So my bias or toward the but you feel and this is why you say we're going to bring freedom to Iraq, we're gonna bring freedom to here, we're gonna bring freedom because we think we're spreading to use something that is just undeniably positive, we're going to free you and give you this. Um it's hard for me to wipe my own bias away from there, right? Because if I were in Iraq for example, I would want freedom, right? But if you then leave and let the Iraqis vote for whomever they want, are they going to vote for somebody that will, I mean, you know, you look at Russia now and I hear from Russians quite a bit because so much of my um my views on Russia and the soviet union were formed in my formative years and and you know, we were not hearing from many people in the soviet union back then, but now you do you hear from Russians today who will say your views on Stalin or archaic and cold. So so you try to reorient your beliefs a little bit. But it goes to this idea of if you gave the people in Russia a free and fair vote, will they vote for somebody who promises them a free and open society based on enlightenment democratic principles, or will they vote for somebody, we in the U. S. Would go what are they doing? They're voting for some strong man who's just you know, so um I think it's very hard to throw away our own biases and preconceptions and and you know it's an all eye of the beholder kind of thing. But when you're talking about ideological societies it is very different, difficult to throw off all the years of indoctrination into the superiority of your system. I mean listen in the soviet union Marxism one way or another was part of every classrooms, you could be studying geometry and they'll throw Marxism in there somehow because that's what united the society and that's what gave it a higher purpose and that's what made it in the minds of the people who were its defenders a superior morally superior system. And we do the same thing here. In fact most people do. But see you're still french no matter what the ideology or the government might be. So in that sense it's funny that there would be a Cold war with these two systems because they're both ideologically based systems involving peoples of many different backgrounds who are united under the umbrella of the ideology. </s><s>[INST] First of all that's brilliantly put, I'm in a funny position that uh in my formative years. So I came here when I was 13 is when I you know teenage is your first love or whatever as I fall in love, I fell in love with the american set of ideas of freedom and individuals. [/INST] Yes but </s><s>[INST] I also remember it's like you remember like maybe an ex girlfriend or something like that. I also remember loving as a very different human the the soviet idea like we had the national anthem which is still the, I think the most badass national anthem which is the soviet union, like saying we're the indestructible nation. I mean just the words are so like americans words are like, oh we're nice, like what we're freedom. But like a Russian soviet union national anthem was like we're bad motherfucker's, nobody will destroy us. I just remember feeling pride in a nation as a kid, like dumb not knowing anything because we all had to recite the stuff. It was, there's a uniformity to everything, There is pride underlying everything. I didn't think about all the destructive nature of The bureaucracy, the incompetence of you know, all the things that come with the implementation of communism, especially around the 80s and 90s. But I remember what it's like to love the that set of ideas. So in a funny place of like remember like switching the love because I'm you know, I kind of joke around about being Russian but you know, my my long term monogamous relationship is not with the idea of the american ideal. Like I'm stuck with it in my mind but I remember what it was like uh to love it and I think about that too when people criticize china or they criticize the current state of affairs with how Stalin is remembered and how Putin is to know that the you can't always wear the american ideal of individualism, radical individualism and freedom in analyzing the ways of the world elsewhere, like in china and Russia, that it does. If you don't take yourself too seriously as americans all do as I do. It's kind of a beautiful love to have for your government to believe in the nation to let go of yourself and your rights and your freedoms to believe in something bigger than yourself. That's actually uh that's a kind of freedom. That's you're actually liberating yourself. If you think like life is suffering, you're you're giving into the flow of the water, the flow the way of the world by giving away more power from yourself and giving it to what you would conceive as as the power of the people together together. We'll do great things and really believing in the ideals of what in that case, in this case, I don't even know what you would call Russia, but whatever the heck that is authoritarian, powerful state, powerful leader, believing that can be as beautiful as believing the american ideal. [/INST] Not just that, let me add to what you're saying and I'm very, I spend a lot of time trying to get out of my own biases. Uh It is, it is a fruitless endeavor long term, but you try to be better than you normally are one of the critiques that china and I always as an american, I tend to think about this as their government, right? This is a rationale that their government puts forward. But what you just said, you know, is actually if you can make that viewpoint beautiful is kind of a beautiful way of approaching it. The chinese would say that what we call human rights in the United States and what we consider to be everybody's birthright around the world is instead Western rights. That's the words they use Western rights. It's a it's a fundamentally Western oriented and I'll go back to the enlightenment, enlightenment based ideas um on what constitutes the rights of man. And they would suggest that that's not internationally and always applicable, right, that you can make a case. And again, I don't believe this if this runs against my own personal views, but that you could make a case that the collective well being of a very large group of people outweighs the individual needs of any single person, especially if those things are in conflict with each other, right? If you cannot provide for the greater good because everyone's so individualistic. Well then really what is the better thing to do right to suppress individualism? So everybody is better off? Um I think trying to recognize how someone else might see that is important if we want to. You know, you have talked about eliminating war. We talked about eliminating conflict. The first need to do that is to try to understand how someone else might view something differently than yourself. Um I'm famously one of those people who buys in to the ideas of, of traditional Americanism, right? And look what a lot of people who lived today. I mean they would seem to think that things like patriotism requires a belief in the strong military and all these things we have today, but that is a corruption of traditional Americanism, which viewed all those things with suspicion in the 1st 100 years of the republic, because they saw it as an enemy to the very things that americans celebrated right? How could you have freedom and liberty and individualistic expression if you had an overriding military that was always fighting wars and and and the founders of this country looked to other examples like europe for example and saw that standing militaries for example, standing armies were the enemy of liberty. Well, we have a standing army now. Um and and and one that is totally interwoven in our entire society. If you could, if you could go back in time and talk to john Quincy Adams, writerly President of the United States and show him what we have now, he would think it was awful and horrible and that somewhere along the line, the americans had lost their way and forgotten what they were all about. But we have so successfully interwoven This modern military industrial complex with the, the traditional uh benefits of the American system and ideology so that they become intertwined in our thinking. Whereas 150 years ago, they were actually considered to be at opposite polarities and a threat to one another. Um, so when you talk about the love of the nation, I tend to be suspicious of those things. I tend to be suspicious of government, I tend to tend to try very hard to not be manipulated. And I feel like A large part of what they do is manipulation and propaganda. And so, um I think a healthy skepticism of the nation state is actually 100% Americanism in the traditional sense of the word, but I also have to recognize as you so eloquently stated Americanism is not necessarily universal at all. And so I think we have to try to be more understanding cr the traditional american viewpoint is that if a place like china does not allow their people individual human rights, then they're being denied something, they're being denied. And 100 years ago they would have said their God given rights, man is born free. And if he's not free, it's because of something done to him, right? The government has taken away his God given rights. </s><s>[INST] I'm getting excited just listening to [/INST] that. But I mean, but I mean, I think, I think the idea that this is universal is in and of itself a bias now do I want freedom for everybody else. I sure do. But the people in the soviet union who really bought into that wanted the workers of the world to unite and not be exploited by, you know, the greedy, blood sucking people who worked them to death and pocketed all of the fruits of their labor. If you frame it that way, that sounds like justice as well, you know? So it is an eye of the beholder sort of thing. </s><s>[INST] I'd love to talk to you about Vladimir Putin sort of while we're in this feeling and wave of empathy and trying to understand others that are not like us. Yeah. One of the reasons I started this podcast is because I believe that there's a few people I could talk to some of it is ego, some of it stupidity. Is there some people I could talk to that? Not many others can talk to. The one person I was always thinking about was Vladimir Putin. Do you still speak the language? I speak the language very well. That makes [/INST] it even easier. I mean you might be you might be appointed for that job. </s><s>[INST] That's the context in which I'm asking you this question. What are your thoughts about Vladimir Putin from historical context? Have you studied him? Have you thought about him? [/INST] Yes. Uh studied as a, as a loaded word. Um here's here's and again I find it hard sometimes to not filter things through an american lens. So as an american, I would say that the Russians should be allowed to have any leader that they want to have. But what an american would say is, but there should be elections, right? So if the Russians choose Vladimir Putin and they keep choosing him, that's their business. Where as an american, I would have a problem is when that leader stops letting the Russians make that decision and we would say, well now you're no longer ruling by the consent of the governed, you've become the equivalent of a person who may be oppressing your people. You might as well be a dictator right now, there's a difference between a freely elected and re elected and re elected and re elected dictator, right? If that's what they want. And and look, i it would be silly to broad brush the Russians like it would be silly to broad brush anyone right? Millions and millions of people with different opinions amongst them all, but they seem to like a strong person at the helm. And listen, there's a giant chunk of americans who due to um in their own country. But an american would say as long as the freedom of choice is given to the Russians to decide this and not taken away from the right, it's one thing to say, he was freely elected, but a long time ago and we've done away with elections since then is a different story too. So my attitude on on Vladimir Putin is if that's who the Russian people want and you give them the choice right? If he's only there because they keep electing him. That's a very different story when when he stops offering them the option of choosing him or not choosing him. That's when it begins to look nefarious to someone born and raised with the mindset and the ideology that is an integral part of of yours, truly and that I can't, you know, you can see gray areas and nuance all you like, but it's hard to escape as you wish. And you you alluded to this too. It's hard to escape what was indoctrinated into your bones in your formative years. Uh it's like your bones are growing right and you can't go back. So to me this is so much a part of who I am that I have a hard time jettisoning that and saying, oh no, Vladimir Putin not being elected anymore. It's just fine. I'm too much of a product of my upbringing to go there. Does that make sense? </s><s>[INST] Yeah, absolutely. But of course there's like we were saying these gray areas, which is I believe I have to think through this, but I think there is a point of which Adolf Hitler became the popular choice in Nazi Germany in the 30s. There is a, in the same way from an american perspective you can start to criticize some in a shallow way, some in a deep way, the way that Putin has maintained power is by controlling the press. So limiting one other freedom that we americans value, which is the freedom of the press or freedom of speech that he it is very possible now things are changing now, but for most of his presidency, he was the popular choice. And sometimes by far and you know I have actually don't have real family in Russia who don't love Putin. The only people who write to me about Putin and not liking him are like sort of activists who are young, right. But like to me they're strangers. I don't know anything about them. People I do know and have a big family in Russia. They love Putin. [/INST] They do, they miss elections, would they want the choice to prove it at the ballot box? And and or or are they so in love with him that they wouldn't want to take a chance that someone might vote him out. </s><s>[INST] No, they don't think of it this way and they are aware of the incredible bureaucracy and corruption that is lurking in the shadows, which is true in Russia [/INST] everywhere </s><s>[INST] everywhere. But like there's something about the Russian, it's the remnants, it's corruption is so deeply part of the Russians. So the soviet system that even the overthrow of the soviet, the breaking apart of the soviet union and uh Putin coming and reforming a lot of the system. It's still deeply in there and and they're aware of that that's part of the like the love for Putin is partially grounded in the fear of what happens when the corrupt takeover, the greedy take over. And they they see Putin as the stabilizer is like hard like force that says [/INST] counterforce counterforce that get your </s><s>[INST] ship together. Like basically from the western perspective, Putin is terrible, but from from the Russian perspective, Putin is the only thing holding this thing together before ghosts if it collapses. Now, the from the Garry Kasparov has been loud on this. You know, a lot of people from the Western perspective say, well if it has to collapse, let it collapse, you know, that's easier said than done when you don't have to live through that. Exactly. And so anyone worrying about their family about and they also remember the The inflation and the economic instability and the suffering and the starvation that happened in the 90s with the collapse of the Soviet Union and they saw the kind of reform in the economic vibrancy that happened when Putin took power that they think like this guy is holding it together and they see elections as potentially being mechanisms by which the corrupt people can manipulate the system unfairly as opposed to letting the people speak with their voice. They somehow figure out a way to uh manipulate the elections to elect somebody uh like one of them Western revolutionaries. And so I think one of the beliefs that's important to the american system is the belief in the electoral system, that the voice of the people can be heard in the various systems of government, whether it's judicial, whether it's, uh, I mean, basically the assumption is that the system works well enough for you to be able to uh elect the popular choice. [/INST] Okay, so there's a couple of things that come to mind on that. The first one has to do with the idea of oligarchs. Um, there's a belief in political science, uh, you know, it's not the, the overall believe, but but that every society is sort of an oligarchy, really, if you break it down. Right? So what you're talking about are some of the people who would form an oligarchic class in Russia. And that Putin is the guy who can harness the power of the state to keep those people in check. The problem, of course, in a system like that, a strongman system, right? Where you have somebody who can, who can hold the reins and steer the ship when the ship is violently in a storm, is the succession. So if you're not creating a system that can operate without you, then that terrible instability and that terrible future that you that you justify the strongman for is just awaiting your future, right? I mean, unless unless he is actively building the system that will outlive him and allow successors to do what he's doing, then what you've done here is create a temporary, I would think a temporary stability here, because it's the same problem you have in a monarchy. Right? Um where where you have this one king and he's particularly good or you think he's particularly good, but he's going to turn that job over to somebody else down the road. And the system doesn't guarantee because no one's really worked on. And again, you would tell me if if Putin is putting into place, I know he's talked about it over the years putting into place a system that can outlive him and that will create the stability that the people in Russia like him for when he's gone. Because if the oligarchs just take over afterwards, then One might argue, well, we had 20 good years, you know, of stability. But I mean, I would say that if we're talking about a ship of state here, the guy steering the ship, maybe if you wanted to look at it from the Russian point of view has done a great job, maybe just saying, but the rocks are still out there and he's not going to be at the at the helm forever. So, one would think that his job is to make sure that there's going to be someone who can continue to steer the ship for the people of Russia after he's gone. Now, let me ask, because I'm curious, do you? And and and ignorant. So is he doing that, do you think, is he setting it up? So that when there is no Putin the state is safe </s><s>[INST] from the beginning, That was the idea whether one of the fascinating things. Now I read every biography, english written biography and Putin. So I haven't, I need to think more deeply. But one of the fascinating things is how do power change Vladimir Putin? He was a different man when he took power than he is today. I actually in many ways admire the man that took power. I think he's very different than Stalin and Hitler at the moment. They took power. I think Hitler and Stalin were both in our previous discussion already on the trajectory of evil. I think Putin was a humble, loyal, honest man when he took power. The man he is today is worth thinking about and studying. I'm not sure that that [/INST] that's an old line about absolute power corrupting. Absolutely, </s><s>[INST] But it's you know, it's kind of a line uh you know, it's a beautiful quote, you have to really think about it, you know, like what does that actually mean? Like one of the things I still have to do, you know, I've been focusing on securing the conversation. Right? So I've been having gone through a dark place yet because I feel like I can't do the dark thing for too long. So I really have to put myself in the mind of Putin leading up to the conversation, but for now my senses his he took power when Yeltsin gave him one of the big sort of acts of the new Russia was for the first time in its history, a leader could have continued being in power and chose to give away power. That was the George Washington [/INST] you were in the United States would look at that is absolute positive, a sign, a sign of good things. Yes. </s><s>[INST] And so that was a huge act. And uh Putin said that that that was the defining thing that will define Russia for the 21st century, that act, and he will carry that flag forward. That's why In rhetoric, he after two terms, he gave away about two [/INST] Medvedev, but it was a puppet, </s><s>[INST] right? Yeah. Yes. But it was like the still the story was being told. I think he believed it early on. I think he I believe he still believes it, but I think he's deeply suspicious of the corruption that looks in the shadows. And I do believe that somebody who thinks Clickbait journalism is broken. Journalists annoy the hell [/INST] out of me. Hey, journalism is working perfectly. Journalism is broken. Journalists make things work great. </s><s>[INST] So, I understand from Putin's perspective that journalism journalists can be seen as the enemy of the state, because people think journalists write these deep, beautiful philosophical pieces about criticizing the structure of government and the proper policy would, you know, the steps that we need to take to make a greater nation. No, they they're unfairly take stuff out of context. They uh, they're critical in ways that's like shallow, not interesting. They call you a racist or sexist or they make up stuff all the time. So I can put myself in the mindset of a person that thinks that it is okay to remove that kind of shallow uh fake news voice from the system. The problem is of course that is a slippery slope to then you remove all the annoying people from the system and then you change what annoying means, which annoying starts becoming a thing that like anyone who opposes the system. I mean, I get I get the the slippery, it's obvious that it becomes a slippery slope. But I can also put myself in the mindset of the people that it's okay to remove the liars from the system as long as it's good for Russia and [/INST] okay, so here in lies and this again, the traditional american perspective, because we've had yellow, so called yellow journalism since the founding of the Republic. That's nothing new. Um, but but the problem then comes into play when you remove journalists, even, you know, it's a broad brush thing because you remove both the crappy ones who are lying and the ones who are telling the truth to your left with simply the approved government. Journalists write the ones who are towing the government's line, in which case the truth as you see it is a different kind of fake news, right? It's the fake news from the government instead of the Clickbait news and oh yeah, maybe truth mixed into all that too in some of the outlets. The problem I always have with our system here in the United States right now is trying to tease the truth out from all the falsehoods. And look, I've got 30 years in journalism. My job used to be to go through before the internet, all the newspapers and and find that I used to know all the journalists by name and I could pick out, you know, who they were and and and and I have a hard time picking out the truth from the falsehood. So I think constantly, how are people who don't have all this background, who have lives or who are trained in other specialties? How do they do it? But if the government is the only approved outlet for truth, a traditional american and a lot of other traditional societies based on these ideas of the enlightenment that I talked about earlier would see that as a disaster waiting to happen or a tyranny in progress, Does that make sense? </s><s>[INST] It totally makes sense. And I would agree with you. I still agree with you, but it is clear that something about the freedom of the press and freedom of speech in today, like literally the last few years with the internet is changing and the argument, you know, you could say that the american system of freedom of speech is broken because the here's, here's the belief I grew up on and I still hold, but I'm starting to be sort of trying to see multiple views on it. My belief was that freedom of speech results in a stable trajectory towards truth. Always. So like truth will emerge. That was my sort of faith and belief that that yeah, there's going to be lies all over the place. But there will be like a stable thing that is true that's carried forward to the public now. It feels like it's possible to go towards the world where nothing is true or truth is, is something that groups of people convince themselves of and there's multiple groups of people. And the idea of some universal truth as I suppose is the better thing is uh, is something that we can no longer exist under. Like some people believe that the Green Bay Packers is the best uh football team and some people can think the patriots and they deeply believe it to where they call the other groups liars. Now. That's fun for sports. That's fun for favorite flavors of ice cream. But they might believe that about science about uh, various aspects of uh politics, various aspects of sort of uh, different policies within the function of our government and like that's not just like some weird things to complain about, but that would be the nature of things like truth is something we can no longer [/INST] have. Well lets and let me de romanticize the american history of this too because the american press was often just as biased just as I mean I always look to the 19 seventies as the high water mark of the american journalistic, the post Watergate era where it was actively going after um uh the abuses of the government and all these things. But there was a famous speech, very quiet though very quiet given by Katharine Graham who was a Washington post editor I believe. And I actually somebody sent it to me. We had to get it off of the journalism like a j store kind of thing. And she had a at a luncheon um assured that the to the government people at the lunch and don't worry this is not going to be something that we make a trend because the position of the government is still something that was carried. The newspapers were the water and the newspapers were the big thing up until certainly the late sixties, early seventies, the newspapers were still the water carrier of the government. Right? And they were the water carriers of the owners of the newspaper. So let's not pretend there was some angelic wonderful time. And I'm saying to me because I was the one who brought it up, let's not pretend there was any super age of truthful journalism and all that. And I mean you go to the revolutionary period in american history and it looks every bit as bad as today, right? Um </s><s>[INST] that's a hopeful message actually. So things may not be as bad as they as they look more [/INST] like a stock market and that you have fluctuations in the truthfulness or or believability of the press and there are periods where it was higher than other periods. The funny thing about the so called Clickbait era and I do think it's terrible, but I mean it resembles earlier eras to me. So I always compare it to when I was a kid growing up when I thought journalism was as good as it's ever gotten. It was never perfect. Um but it's also something that you see very rarely in other governments around the world and there's a reason that journalists are often killed regularly and a lot of countries and it's because they report on things that the authorities do not want reported on. And I've always thought that that was what journalism should do. But it's got to be truthful otherwise. It's just a different kind of propaganda. Right? </s><s>[INST] Can we talk about genghis khan genghis khan by the way? Is it genghis khan genghis khan, it's not [/INST] genghis khan, it's either genghis khan genghis khan. </s><s>[INST] So let's go with Genghis khan. [/INST] The only thing I'll be able to say with any certain last certain thing </s><s>[INST] I'll say about it. It's like, I don't know GIF versus Jif, I [/INST] don't know how, I don't know how it ever got started the wrong way. </s><s>[INST] So first of all your episodes on jangles con for many people are the favorite, it's fascinating to think about events that had so much like in their ripples had so much impact on so much of human civilization in your view, was he an evil man? This ghost? Our discussion of evil? Another way to put it is I've read he's much loved and much, many parts of the world like Mongolia and I've also read arguments that say that he was quite a progressive for the time. So where do you put him? Is he a progressive or is an evil destroyer of humans? [/INST] As I often say, I'm not a historian, which is why what I've tried to bring to the hardcore history podcast are these sub themes so each show has and they're not, I try to kind of soft pedal them so they're not always like really right in front of your face. Um, in that episode, the soft pedaling sub theme had to do with what we referred to as a historical arsonist and it's because some historians have taken the position that sometimes and most of this is earlier. So historians don't do this very much anymore, but these were the wonderful questions I grew up with. That blend, it's almost the intersection between history and philosophy and the idea was that sometimes the world has become so overwhelmed with bureaucracy or corruption or just stagnation that somebody has to come in, or some group of people or some force has to come in and do the equivalent of a forest fire to clear out all the deadwood so that the forest itself can be rejuvenated and and society can then move forward. And there's a lot of these periods where the historians of the past will portray these figures who come in and do horrific things as creating an almost service for mankind, right? Creating the foundations For a new world that will be better than the old one. It's a recurring theme. And so this was the sub theme of the, of the Cons podcast, because otherwise you don't need me to tell you the story of the Mongols, but I'm going to bring up the historical arsonist element. Um and but this gets to how the con has been portrayed right. If you want to say, oh yes, he cleared out the dead would have made for, for well then it's a positive thing. If you say my family was in the forest fire that he set, you're not going to see it that way. Um much of what Genghis khan is credited with on the upside, right? So things like religious toleration and you'll say, well he was religiously the Mongols were religious religiously tolerant. And so this makes them almost like a liberal reformer kind of thing. But this needs to be seen within the context of their empire, which was very much like the roman viewpoint, which is the romans didn't care at a lot of time what your local people worshiped, they wanted stability and if that kept stability and kept you paying taxes and didn't require the legionaries to come in and and then they didn't care right. And the cons were the same way, like they don't care what you're practicing as long as it doesn't disrupt their empire and cause them trouble. But what I always like to point out is, yes, but the con could still come in with his representatives to your town, decide your daughter was a beautiful woman that they wanted in the cons concubine and they would take them. So how liberal and empire is this, right? So so many of the things that they get credit for as though there's some kind of nice guys may in another way of looking at it just be a simple mechanism of control right away to keep the empire stable. They're not doing it out of the goodness of their heart. They have decided that this is the best and I love because the Mongols were What we would call a Pagan people. Now, I love the fact that they I think we call it the term we used had to do with like, like they were hedging their bets religiously right? They didn't know which God was the right one. So as long as you're all praying for the health of the con, we're maximizing the chances that whoever the gods are, they get the message right. Um So I think it's been portrayed as something like a liberal empire and the idea of Mongo universality universality is its more about conquering the world. And it's like saying you know, we're going to bring stability to the world by conquering it. Well what if that's Hitler right? He could make the same case or Hitler wasn't really the world conqueror like that because he wouldn't have been he wouldn't have been trying to make it equal for all peoples. But my point being that it kind of takes the positive moral slant out of it if their motivation wasn't a positive moral slant to the motivate and and the Mongols didn't see it that way. And I think the way that it's portrayed is like and I would like to use this this this analogy, but it's like um shooting an arrow and painting a bull's eye around it afterwards. Right? How how do we how do we justify and make them look good in a way that they themselves probably and listen, we don't have the Mongol point of view per se. I mean there's something called the secret history of the Mongols and there's things written down by Mongolian overlords through people like Persian and chinese scribes later we don't have their point of view, but it sure doesn't look like this was an attempt to create some wonderful place where everybody was living a better life than they were before. I I think that's that's later people uh putting a nice rosy spin on it, </s><s>[INST] but there's an aspect to it. Maybe you can correct me because I'm projecting sort of my idea of what it would take to to uh to conquer so much land is uh the ideology is emergent. So if I were to guess the Mongols started out as exceptionally as warriors who valued excellence and skill of killing, not even killing, but like the actual practice of war and you can start out small, you can grow and grow and grow and then in order to maintain the stability of the things over which of the conquered lands, you developed a set of ideas with which you can, like you said, established control, but it was emergent and it seems like the core first principle idea of the Mongols is just to be excellent warriors. That felt, that felt to me like the starting point, it wasn't some ideology like with Hitler and Stalin, with Hitler, the there was an ideology that didn't have anything to do with with war underneath it. It was more about conquering, it feels like the Mongols started up more organically, I would say it's emerging like this phenomenon started emergency and they were just like similar to the native americans was the command. She's like the different warrior tribes that Joe Rogan's currently obsessed with that, what led me to look into it more, they, they seem to just start out just valuing the skill of fighting, whatever the tools of war they had, which were pretty primitive. But just to be the best warriors that could possibly be make a science out of it. Is that is that crazy to think that there was no ideology behind it. In the beginning, I'm gonna back up a second. I'm [/INST] reminded of the lines set about the romans that they create a wasteland and call it peace. That is. But there's a lot of conquerors like that, right? Um where where you will sit there and listen historians forever. It's the trade, it's the famous trade offs of empire and they'll say, well look at the trade that they facilitated and look at the religion, all those kinds of things. But they come at the cost of all those peoples that they conquered forcibly and by force integrated into their empire. The one thing we need to remember about the Mongols that makes them different than say the romans and this is complex stuff and way above my pay grade. But I'm fascinated with it and it's more like the comanches that you just brought up is that the Mongols are not a settled society. Okay. They are they are, they come from a nomadic tradition now several generations later when you have uh kubla khan as, as the, as the emperor of china, it's beginning to be a different thing, right? And the Mongols. When their empire broke up the ones that were in settled the so called settled societies, right, Iran places like that, they will become more like over time the rulers of those places were traditionally and the Mongols and say like the cognitive the golden horde which is still in their traditional nomadic territories will remain traditionally more mongol. But when you start talking about who the Mongols were, I try to make a distinction there not some really super special people. They're just the latest confederacy in an area that saw nomadic confederacy. He's going back to the beginning of recorded history. The skip the ins the sar missions, the of ours, the huns, the Magyars. I mean these are all the nomadic, you know the nomads of the Eurasian steppe were huge, huge players in the history of the world until gunpowder nullified their, their traditional weapons system, which I've been fascinated with because their traditional weapons system is not one you could copy because you were talking about being the greatest warriors. You could be every warrior society. I've ever seen values that what the what the nomads had of the Eurasian steppe was. This relationship between human beings and animals that change the equation. It was how they rode horses. And societies like the byzantines which would form one flank of the step and then all the way on the other side you had china and below that you had Persia. These societies would all attempt to create mounted horsemen who used archery and they did a good job. But they were never the equals of the nomads because those people were literally raised in the saddle. They compared them to sent ours. Um The comanches, great example considered to be the best horse riding warriors in north America. Uh The command. She's always loved watching uh there's paintings, George Catlin, the famous uh painter who painted the comanches uh illustrated it. But the Mongols and the scythians and skip the ins and the of ours and all these people did it to where they would shoot from underneath the horse's neck hiding behind the horse. The whole way you look at a picture of somebody doing that and it's insane. This is what the byzantines couldn't do and the chinese couldn't do. And it was a different level of of harnessing a human animal relationship that gave them a military advantage that could not be copied. Right? It could be emulated but they were never as good. Right. That's why they always hired these people. They hired mercenaries from these areas because they were incomparable writes the combination of people who were shooting bows and arrows from the time. They were toddlers who were riding from the time. They were who rode all the time. I mean they were the huns were bow legged. The romans said because they were never they ate slept everything in the saddle. That creates something that is difficult to copy and it gave them a military advantage. You know, I I enjoy reading actually about when that military advantage ended so 17th and 18th century when the Chinese on one flank and the Russians on the other are beginning to use firearms and stuff to break this military power of these, of these various cons um the Mongols were simply the most dominating and most successful of the confederacy is, but if you break it down, they really formed the nucleus at the top of the pyramid of the apex of the food chain. And a lot of the people that were known as Mongols were really lots of other tribes, non Mongolian tribes that when the Mongols conquer you after they killed a lot of you, they incorporated you into their confederacy. Um and often made you go first, you know, we're gonna find somebody, we're gonna make these people go out in front and suck up all the arrows before we go in and finish the job. So to me and I guess a fan of the Mongols would say that the difference and what made the Mongols different wasn't the weapons system or the fighting or the warriors or the arm or anything, it was genghis khan and if you go look at the other really dangerous from the outside world's perspective, dangerous steppe nomadic confederacy is from past history was always when some great leader emerged that could unite the tribes and you see the same thing in native american history two degree to um you had people like Attila right? Or there's one called Tuman. You go back in history and these people make the history books because they caused an enormous amount of trouble for their settled neighbors. That normally, I mean chinese Byzantine and Persian approaches to the step people were always the same. They would pick out tribes to be friendly with, they would give them money, gifts, hire them and they would use them against the other tribes. And generally Byzantine especially in chinese diplomatic history was all about keeping these tribes separated. Don't let them form confederations of large numbers of them because then they're unstoppable. Attila was a perfect example of the huns were another large the Turks, another large confederacy of these people and they were devastating when they could unite. So the diplomatic policy was don't let them. That's what made the Mongols different as Genghis khan united them. And then unlike most of the tribal confederacy is he was able, they were able to hold it together for a few generations </s><s>[INST] to linger on the little thread they started pulling on this man, Genghis khan that was a [/INST] leader. </s><s>[INST] What do you think makes a great leader. Maybe if you have other examples throughout history and great again, let's lose that use that term loosely. [/INST] He's going to ask for a definition. </s><s>[INST] Great uniter of whether it's evil or good. It doesn't matter. Uh huh is there somebody who stands out to you alexander the grace, we're talking about military or ideologies, you know, some people bring up FDR or or I mean it could be the finding fathers of this country or we can go to uh was he man a man of the century up there, Hitler of the 20th century and Stalin and these people had really a mass, the amount of power that probably has never been seen in the history of the world. Is there somebody who stands out to you by way of trying to define what makes a great uniter, great leader in one man or a woman, maybe in the future. [/INST] It's an interesting question and I would have thought a lot about because let's take alexander the Great as an example because alexander fascinated the world of his time, fascinated ever since people have been fascinated with the guy, but alexander was a hereditary monarch, right? He was handed, the kingdom is fascinating, but he did not need to rise from nothing to get that job. In fact, he reminds me of a lot of other leaders of Frederick the Great for example, in Prussia, these are people who inherited the greatest army of their day, alexander unless he was an imbecile was going to be great, no matter what, because I mean, if you inherit the very mock you're going to be able to do something with it, right alexander's father may have been greater Philip. Uh, he Philip the second was the guy who, who literally did create a, a strong kingdom from a disjointed group of people that were continually beset by their neighbors. He's the one that reformed that army, uh, took things that he had learned from other greek leaders, like the theme and leader of team a ninja's. Um and and then laboriously over his lifetime stabilized the frontiers built this system. He lost an eye doing it. He, his leg was made lame. I mean this was a man who looked like he built the empire and lead from, from the front ranks, I mean um so and then, and then who may have been killed by his son, We don't know who assassinated Philip, but then handed the greatest army the world had ever seen to his son who then did great things with it. You see this, this pattern many times in my mind, I'm not sure alexander really can be that great when you compare him to people who arose from nothing. So the difference between what we would call in the United States, the self made man or the one who inherits a fortune. There's an old line that, you know, it's, it's a slur, but it's about rich people and it's, it's like he was born on, he was born on third base and thought he hit a triple, right? Um, Philip was born at home plate and he had to hit alexander started on third base and so I try to draw a distinction between them. Genghis khan is tough because there's two traditions, the tradition that we grew up with here in the United States and that I grew up learning was that he was a self made man, but there is a tradition and it may be one of those things that's put after the fact because a lot a long time ago, whether or not you had blue blood in your veins was an important distinction. And so the distinction that you'll often hear from Mongolian history is that this was a nobleman who had been deprived of his inheritance. So he was a blue blood. Anyway, I don't know which is true. Uh, there's certainly, I mean when you look at agendas condo, you have to go, that is a wicked amount of, of things to have achieved. Uh he's very impressive as a figure until is very impressive as a figure. Um Hitler is an interesting figure. He's one of those people, you know, the more you study about Hitler, the more you wonder where the defining moment was because um if you look at his life, Hitler was a relatively common soldier in the First World War. I mean he was brave, he got uh he got some decorations. In fact, the highest decoration he got in the First World War was given to him by a jewish officer and it was uh, he often didn't talk about that decoration, even though it was the more prestigious one because it would open up a whole can of worms you didn't want to get into. But Hitler's, I mean if you said who was Hitler today, one of the top things you're going to say is he was an anti Semite. Well then you have to draw a distinction between general regular anti Semi Semitism that was pretty common in the era and something that was a rabid level of anti Semitism. But Hitler didn't seem to show a rabid level of of anti Semitism until after or at the very end of the First World War. So if this is a defining part of this person's character and much of what we consider to be his, his evil stems from that. What happened to this guy when he's an adult, right, He's already fought in the war to change him. So, I mean it's almost like the old, there was always a movie theme. Somebody gets hit by by something on the head and their whole personality changes, right? I mean it almost seems something like that. So I don't think I call that necessarily a great leader. To me, the interesting thing about Hitler is What the hell happened to a nondescript person who didn't really impress anybody with his skills. And then in the 1920s is all of a sudden, as you said, sort of the man of the hour, right? So that to me is kind of, I have this feeling that Genghis Khan and we don't really know was an impressive human being from the get go and then he was raised in this environment with pressure on all sides. You start with this diamond and then you polish it and you harden it his whole life. Hitler seems to be a very unimpressive gemstone most of his life and then all of a sudden, so I mean, I don't think I can label great leaders and I'm always fascinated by that idea that I'm trying remember who the quote was by that great men, Lord Acton. So great men are often not good men. Uh and that in order to be great, you would have to jettison many of the moral qualities that we normally would consider, jesus or Gandhi or you know, martin these qualities that one looks at as, as the good upstanding moral qualities that we should all aspire to as examples, right? The buddha, whatever it might be. Um those people wouldn't make good leaders because what you need to be a good leader often requires the kind of choices that a true philosophical diogenes moral man wouldn't make. Um so I don't have an answer to your question, How about that? That's a very long way of saying, </s><s>[INST] I don't know, just linger a little bit, it does feel like from my study of Hitler that the time molded demand versus genghis khan where it feels like he, the man molded his time. [/INST] And I feel that way about a lot of those nomadic confederacy builders, that they really seem to be these figures that stand out as extraordinary for one in one way or another, remembering by the way that almost all the history of them were written by the enemies that they so mistreated, that they were probably never going to get any good press. They didn't write themselves. That's a </s><s>[INST] caveat. We should always have basically, [/INST] no matter where native american peoples or tribal peoples anywhere generally do not get the advantage of being able to write the history of their heroes. </s><s>[INST] Okay, I've uh have recently almost done with the rise in the fall of the third Reich, one of the historical descriptions of Hitler's rise to power. Nazis rise to power. There's there's a few philosophical things I'd like to uh, ask you to see if you can help, Like, one of the things I think about is uh, how does one Be a hero in 1930s, Nazi Germany, what does it mean to be a hero? What do heroic actions look like? I think about that, because I think about how I move about in this world today, you know, that we live in really chaotic, intense times where I don't think you want to draw any parallels between Nazi Germany and modern day in any of the nation's can think about, but it's not out of the realm of possibility that authoritarian governments take hold. Authoritarian companies take hold. And I'd like to think that I could be in my little small way and inspire others to take the heroic action before things get bad. And I kind of try to place myself in what would 1930s Germany look like. Is it possible to stop a Hitler? Is it even the right way to think about it? And how does one be a hero in it? I mean, you often talk about that, living through a moment in history is very different than looking at that history. Looking, you know, when you look back, I also think about it, would it be possible to understand what's happening that the bells of war are ringing? Uh, it seems that most people didn't seem to understand, you know, late into the 30s, that war is coming. That's fascinating on the United States side. Inside Germany, like the opposing figures, the german military didn't seem to understand this. Maybe, uh, the other country certainly France. And uh, England didn't seem to understand this, that kind of tried to put myself into nineties thirties, Germany as I'm jewish, which is another little twist on the whole, like, what would I do? What should one do? Do you have interesting answers? [/INST] So earlier, we had talked about Putin and we had talked about patriotism and love of country and those sorts of things in order to be a hero in Nazi Germany by our views here, you would have had to have been anti patriotic to the average Germans viewpoint in the 19 thirties, right? You would have to have opposed your own government and your own country. And that's a very it would be a very weird thing to go to people in Germany and say, listen, the only way you're going to be seen as, as, as a good german and a hero to the country that will be your enemies is we think you should oppose your own government. It's it's a strange position to put the people in a government and saying you need to be against your leader, you need to oppose your government's policies. You need to oppose your government. You need to hope and work for its downfall. That doesn't sound patriotic. It wouldn't sound patriotic here in this country. If you if you made a similar argument, um I will go away from the 1930s and go to the 1940s to answer your questions. So there's movements like the White Rose movement in Germany, which involved young people really, and and from various backgrounds, religious backgrounds, often who worked openly against the Nazi government at a time when power was already consolidated the gestapo was in full force and they execute people who are against the government and these young people would go out and distribute pamphlets and many of them got their heads cut off with guillotines for their trouble. And they knew that that was going to be the penalty. That is a remarkable amount of bravery and sacrifice and willingness to die. And almost not even willingness because they were so open about it. It's almost a certainty, right? Um that's incredibly moving to me. So when we talk and we talked earlier about sort of the human spirit and all that kind of thing. There are people in the german military who opposed and worked against Hitler for example. But to me that's almost cowardly compared to what these young people did in the White Rose movement, because those people in the in the Wehrmacht for example, who were secretly trying to undermine Hitler. They're they're they're not really putting their lives on the line to the same degree. Um and so I think when I look at heroes and listen, I remember once saying there were no conscientious objectors in Germany as a way to point out to people that you didn't have a choice, You know, you were going to serve in there. And I got letters from Jehovah's witnesses who said yes, there were, and we got sent to the concentration camps. Those are remarkably brave things. It's one thing to have your own set of standards and values. It's another thing to say, oh no, I'm going to display them in a way that with this regime, that's a death sentence and not just for me for my family, right in these regimes, there was not a lot of distinction made between father and son and wives. That's a remarkable sacrifice to make and far beyond what I think I would even be capable of. And so the admiration comes from Seeing people who appear to be more morally profound than you are yourself. Um, so when I look at this, I look at that that kind of thing. And I just say, Wow! And the funny thing is if you have gone to most average Germans on the street in 1942 and said, what do you think of these people? They're going to think of them as traitors who probably got what they deserved. So that's the eye of the beholder thing. It's the power of the state to um to so propagandized values and morality in a way that favors the state that you can turn people who today we look at is unbelievably brave and moral and crusading for righteousness and turn them into enemies of the people. Um, so I mean, in my mind, it would be people like that. </s><s>[INST] CIA, I think so, hero is a funny word. We romanticize the notion, but if I could drag you back to 19 thirties, Germany from 19 forties, I feel like the heroic actions that doesn't accomplish much is not what I'm referring to. So there's many heroes. I look up to that, uh, like David Goggins, for example, the guy who runs crazy distances. He runs for no purpose except for the suffering in itself. And I think his willingness to challenge the limits of his mind is heroic. I guess I'm looking for a different term, which is how could Hitler have been stopped. My sense is that he could have been stopped in the battle of ideas. Where people, millions of people were suffering economically were suffering because of the betrayal of World War One in terms of the love of country and how they felt they were being treated and charismatic leader that inspired love and unity that's not destructive could have emerged. And that's where the battle should have been fought. [/INST] I would suggest that we need to take into account the context of the times </s><s>[INST] that led to Hitler's [/INST] rise of power and created the conditions where his message resonated. That is not a message that resonates at all times, right. Um It is impossible to understand the rise of Hitler without dealing with the First World War and the aftermath of the First World War and the inflationary terrible depression in Germany and all these things and the dissatisfaction with the Weimar Republic's government, which was often seen as a, as something put into which it was put into place by the victorious powers. Hitler referred to the people that signed those agreements that signed the armistice as the november criminals. And he used that as a phrase which resonated with the population. This was a population that was embittered. and even if they weren't embittered, the times were so terrible and the options for operating within the system in a non radical way seemed totally discredited, right? You can work through the Weimar Republic, but they tried and it wasn't working anyway. And then the alternative to the nazis who were bully boys in the street were communist agitators. That to the average conservative Germans seem no better. So you have three options. If you're an average german person, you can go with the discredited government put in power by your enemies that wasn't working anyway. You could go with the nazis who seemed like a bunch of super patriots calling for the restoration of german authority or you could go with the communists and the entire thing seemed like a litany of poor options. Right? And in this realm, Hitler was able to triangulate if you will, um he came off as a person who was going to restore german greatness at a time when this was a powerful message. But if you don't need german greatness restored, it doesn't resonate. Right. Um So the reason that your love idea and all this stuff, I don't think would have worked in the time period is because that was not a commodity that the average german was in search of then Well, </s><s>[INST] it's interesting to think about whether greatness can be restored through mechanisms through ideas that are not. So from our perspective today, so evil, I don't know what the right term is, [/INST] but the war continued in a way. So remember that that when Germany, when Hitler is rising to power, the french are in control of parts of Germany, right? The Ruhr uh one of the main industrial heartlands of Germany was occupied by the french. So there's never this point where you're allowed to let the hate dissipate right every time, maybe things were calming down, something else would happen to stick the knife in and twist it a little bit more from the average Germans perspective. Right? Um the reparations, right? So if you say, okay, well, we're going to get back on our feet, the reparations were crushing these things prevented the idea of love or brotherhood and all these things from taking hold. And even if there were Germans who felt that way and they most certainly were, it is hard to overcome the power of everyone else. You know what I always say when people talk to me about humanity, is I believe on an individual levels were capable of everything and anything good, bad or indifferent, but collectively it's different, right? And in the time period that we're talking about here, messages of peace on earth and love, your enemies and and all these sorts of things were absolutely delusion and overwhelmed and drowned out by the bitterness, the hatred and let's be honest, the sense that you were continually being abused by your former enemies, there were a lot of people in the allied side that realize this and said, we're setting up the next war. This is I mean, they understood that you can only do certain things to collective human populations for a certain period of time before it is natural for them to want to. And you can see german posters from the region, Nazi propaganda posters that show them breaking off the chains of their enemies. And I mean, Germany awake, right, That was the great um slogan. So I think love is always a difficult option and in the context of those times it was even more disempowered than normal. </s><s>[INST] Well, this goes to the, just to linger in it for a little longer. The question of the inevitability of history, Do you think Hitler could have been stopped. Do you think this kind of force that you're saying that there was a pain and those building, there's a hatred that was building? Do you think there was a way to avert? I mean, there's two questions, could have been a lot worse and could it have been better In the trajectory of history in the 30s and 40s, [/INST] the most logical. See we had started this conversation brings a wonderful bow tie into the discussion and buttons it up nicely. We had talked about force and Counterforce earlier, uh, the most obvious and and much discussed way that Hitler could have been stopped has nothing to do with Germans um when he re militarized the Rhineland, everyone talks about what a couple of french divisions would have done, had they simply gone in and contested? And this was something Hitler was extremely, I mean, it might have been the most nervous time in his entire career because he was afraid that they would have responded with force and he was in no position to do anything about it if they did. So this is where you get the people who say um you know, and Churchill is one of these people to where they talk about uh that that you know, he should have been stopped militarily right at the very beginning, when he was weak. I don't think uh listen, there were candidates in the in the catholic center Party and others in the Weimar Republic that maybe could have done things and it's beyond my understanding of specific german history to talk about it intelligently. But I do think that had the french responded militarily to Hitler's initial moves into that area, that he would have been thwarted. And I think he himself believed if I'm remembering my reading um that this would have led to his downfall. So the potential, what I don't like about this is that it almost legitimizes military intervention at a very early stage to prevent worse things from happening, but it might be a pretty clear cut case, but it shows that we pointed out that there was a lot of sympathy on the part of the Allies for the fact that, you know, the Germans probably should have Germany back and this is traditional german land. And I mean, they were trying in a funny way, it's almost like the love and the sense of justice on the Allies part may have actually stayed their hand in a way that would have prevented much, much, much worse things later. But if the times were such that the message of a Hitler resonated than simply removing Hitler from the equation would not have removed the context of the Times. And that means one of two things. Either you could have had another one or you could have ended up in a situation equally bad in a different direction. I don't know what that means because it's hard to imagine anything could be worse than what actually occurred. But history is funny that way. And that Hitler always, everyone's favorite example of the difference between the Great Man theory of history and the trends and forces, theories of history, right? The times made a Hitler possible and maybe even desirable to some, if you took him out of the equation, those trends and forces are still in place. Right? So what does that mean? If you take him out and the door is still open to somebody else walk through it. </s><s>[INST] Yeah, it's mathematically speaking, the the probability of charismatic leaders emerge. I'm so torn on that. I'm uh at this point, [/INST] here's another way to look at it? The institutional um stability of Germany in that time period was not enough to push back? And there are other periods in german history. I mean, that Hitler Arose in Arisen in 1913. He doesn't get anywhere because Germany's institutional power is enough to simply quash that it's the fact that Germany was unstable anyway, that prevented a united front. That would have kept radicalism from getting out of hand. Does it make sense? </s><s>[INST] Yes, absolutely. A tricky question on this, just to stay in this a little a longer, because I'm not sure how to think about it is the World War Two versus the holocaust. We were we were talking just now about the way the history unrolls itself and could Hitler have been stopped and I don't quite know what to think about Hitler without the holocaust and perhaps in his thinking how essential the anti Semitism and the hatred of jews was it feels to me that, I mean, I don't, we were just talking about where did he pick up his hatred of the jewish people? There's their stories in Vienna and so on that it almost is picking up the idea of anti Semitism as a really useful tool as opposed to actually believing in this core? Do you think World War Two as it turned out and Hitler as he turned out would be possible without anti Semitism. Could we have avoided the holocaust or was it an integral part of the ideology of fascism and the nazis [/INST] not an integral part of fascism? Because Mussolini really, I mean, Mussolini did it to please Hitler, but it wasn't an integral part. What's interesting to me is that that's the big anomaly in the whole question, because anti Semitism didn't need to be a part of this at all. Right, Hitler had a conspiratorial view of the world. He was a believer that the jews controlled things, right? The jews were responsible for both bolshevism on one side and capitalism on the other. They ruled the banks in the United States was a jew ified country, right, bolshevism was a jew ified sort of a political, in other words, he saw jews everywhere, and he had that line about if the jews of europe, uh, force another war to Germany, they'll pay the price or whatever. But then you have to believe that they're capable of that the holocaust is a weird weird sidebar to the whole thing. And here's what I've always found interesting. It's a sidebar that week in Germany because look at the first World War, jews fought for Germany, right? Who was the most important? And this is a very arguable point, but it's just the first one that pops into my head, who was the most important jewish figure that would have maybe been on the german side, had the Germans had a non anti Semitic, Well, listen, that whole part of Yeah, but, but the whole, I should point out that is to say Germany or europe or Russia or any of those things were not anti Semitic is to do injustice to history, right? Programs every I mean that is that it's standard operating procedure, what you see in the hitlerian era is an absolute huge spike because the government has a conspiracy theory that the jews have. It's funny because Hitler both thought of them as weak and super powerful at the same time, right? And and and as an outsider people that we can I mean the whole idea of the blood and how that connects to Darwinism and all that sort of stuff is just weird, right? A real outlier. But Einstein, let's just play with Einstein if there's no anti Semitism in Germany or or none above the normal level, right? Um the baseline level um design stein leave along with all the other uh jewish scientists and I mean, and what does Germany have as as increased technological and intellectual capacity if they stay right, it's something that actually weakened that state. It's it's a tragic flaw in the hit larian worldview, but it was so, and I don't let me you had mentioned earlier, like maybe it was not integral to his character. Maybe it was a wonderful tool for power, I don't think so, somewhere along the line and really not at the beginning, this guy became absolutely obsessed with this conspiracy theory and jews and and he surrounded himself with people and theorists, I'm going to use that work really, really sort of loosely who believed this too. And so you have a ca ball of people who are reinforcing this idea that the jews control the world that he called it international jewelry was a huge part of the problem and because of that they deserve to be punished. They were an enemy within all these kinds of things. It's a nutty conspiracy theory that the government of one of the most, I mean, the big thing with Germany was culture, right? They were they were they were a leading figure in in culture and philosophy and all these kinds of things and that they could be overtaken with this wildly wickedly weird conspiracy theory and that it would actually determine thing. I mean, Hitler was taking vast amounts of german resources and using it to wipe out this race when he needed them for all kinds of other things to fight a war of annihilation. So that is the weirdest part of of the whole Nazi phenomenon. It's </s><s>[INST] the darkest possible silver lining to think about is that the holocaust may have been in the hatred of the jewish people, may have been the thing that avoided Germany Getting The Nuclear Weapons 1st. And s [/INST] Mhm Isn't that a wonderful historical ironic twist that if it weren't so over laid with tragedy 1000 years from now will be seen as something really kind of funny? Well, </s><s>[INST] that's, that's true. It's fascinating to think, as you've talked [/INST] the seeds of his own destruction, right? The tragic flaw </s><s>[INST] and my hope is this is a discussion I have with my dad is a physicist. Yeah, yeah. Is that evil inherently contains with it, that kind of incompetence. So my dad's discussions, he's a physicist and engineer. His belief is that at this time in our history, the reason we haven't had nuclear, like uh terrorist, uh, blow up a nuclear weapon somewhere in the world is that the kind of people that would be terrorists are simply not competent enough at their job of being destructive. So like there's a kind of, if you plot it, the more evil you are, the less able you are and by evil. I mean purely just like you said, uh if we were to consider the hatred of the jewish people is evil because it's sort of detached from reality, it's like, like just this pure hatred of something that's grounded on things, you know, conspiracy theories, if that's evil, then the more you sell yourself, the more you give into these conspiracy theories, the less capable you are actually engineering, which is very difficult, engineering nuclear weapons and effectively deploying them. So that's the, that's a hopeful message that the destructive people in this world are by their worldview, incompetent in creating the ultimate destruction. I don't agree with that? [/INST] Oh boy, I straight up don't agree with that. </s><s>[INST] So why are we still here? Why haven't we destroyed ourselves? Why haven't the terrorist blow has been many decades? Why haven't we destroyed ourselves to this point? [/INST] Well, when you say it's been many decades, many days, it's like saying in the, in the life of 100 and 50 year old person, uh, we've been doing well for a year. The problem, the problem with all these kinds of equations and it was Bertrand Russell, right, the philosopher who said so, he said it was, it's unreasonable to expect a man to walk on a tight rope For 50 years. I mean, the problem is, is that this is a long game. And let's remember that up until relatively recently, what would you say? 30 years ago, the nuclear weapons in the world were really tightly controlled. That was one of the real dangers in the fall of the Soviet Union. Remember the worry that that all of a sudden you were going to have bankrupt former soviet republic selling nuclear weapons to terrorists and whatnot, I would suggest. And here's another problem is that when we call these terrorists evil, it's easy for an american for example, to say that Osama bin laden is evil, easy for me to say that, but one man's terrorist is another man's freedom fighter, as the saying goes and two other people, he's not what Osama bin laden did. Um, and the people that worked with him, we would call evil genius, the idea of hijacking planes and flying them into the buildings like that and that he could pull that off and that still boggles my mind. I'm still, it's funny, I'm still stunned by that and yet, you know, the idea here's the funny part and I don't, I hesitate to talk about this because I don't want to give anyone ideas, but you don't need nuclear weapons to do incredibly grave amounts of danger really. I mean, what one can of gasoline and a big lighter can do in the right place and the right time and over and over and over again can bring down societies. This is the argument behind the importance of the stability that a nation state provides. So when we went in and took out Saddam Hussein, one of the great counter arguments from some of the people who said this is a really stupid thing to do is that Saddam Hussein was the greatest anti terror weapon in that region that you could have because they were a threat to him. So he took that and he did it in a way that was much more repressive than we would ever be right. And this is the old line about why we supported um right wing Death squad countries because they were taking out people that would inevitably be a problem for us if they did and they were able to do it in a way we would never be able to do supposedly were pretty good at that stuff. You know, just like the soviet union was behind the scenes and underneath the radar. But the idea that the stability created by powerful and strong centralized leadership allowed them, it's almost like outsourcing anti terror activities allowed them to for their own reasons. I mean you see the same thing in the serious situation with the assad's. I mean you can't have an ISIS in that area because that's a threat to the assad government who will take care of that for you and then that helps us by not having an ISIS. So um I would suggest one that the game is still on, on whether or not these people get nuclear weapons in their hands. I would suggest they don't need them to achieve their goals. Really, The crazy thing is if you start thinking like the joker in batman, the terrorist ideas, it's funny, I guess I would be a great terrorist because I'm just full of those ideas. You can do this. It's scary to think of how vulnerable we are. But the whole point </s><s>[INST] is that you as the joker wouldn't do the terrorist actions. That's the that's the theory. That's so hopeful to me with my dad. Is that all the ideas, your ability to generate good ideas. What forget nuclear weapons, how you can disrupt the power grid, how you can disrupt the attack? Our psychology attack, like with a can of gasoline, like you said somehow disrupt the american system of ideas like that coming up with good ideas there? [/INST] Are we saying evil people can't come up with evil genius ideas. </s><s>[INST] That's what I'm saying. We have this Hollywood story. [/INST] I don't think history backs that up. I mean, I think you can say with the nuclear weapons it does, but only because they're so recent, but I mean evil genius, I mean that's almost proverbial, </s><s>[INST] but that's okay. So to push back for the fun of it or [/INST] I don't need to I don't want you to leave this for the in a terrible mood because I pushed back on every hopeful idea. But I tend to be a little cynical about that </s><s>[INST] stuff. But but that goes to the definition of evil I think because I'm not so sure human history has a lot of evil people being competent. I do believe that they mostly like in order to be good at doing what may be perceived as evil, You have to be able to construct an ideology around which you truly believe when you look in the mirror, buy yourself that you're doing good for the world. And it's difficult to construct an ideology where destroying the lives of millions or disrupting the american system. I'm already contradicting myself as [/INST] I was saying to say people have done this already. </s><s>[INST] So, but but then it's the question of like about aliens with the the idea that if the aliens are all out there, why haven't they visited us? The same question? If it's so easy to be evil? Not easy if it's possible to be evil, why haven't we destroyed ourselves? And your statement is from the context of history, the game is still on and it's just been a few years since we've found the tools to destroy ourselves and one of the challenges of our modern time, we don't often think about this pandemic kind of revealed how soft we've gotten in terms of our deep dependence on the system. So somebody mentioned to me, you know what happens if power goes out for a day? What happens if power goes out for um a month over the person that mentioned this was a Berkeley faculty that I was talking with. He's an astronomer who was observing solar flares and it's very possible that a solar flare, they happen all the time to different degrees. [/INST] Yeah. </s><s>[INST] To knock out the power grid for months. So like, you know, just as a thought experiment, what happens if just power goes out for a week in this country, like [/INST] the electro magnetic pulses in the nuclear weapons and all those kinds of things? But maybe </s><s>[INST] that's an act of nature and even just the act of nature will reveal like a little the fragility of it all and then the evil can emerge. I mean the kind of things that might happen when power goes out, especially during a divisive time. [/INST] Well, you won't have food at baseline level. That would mean that the the the entire supplies chain begins to break down and then you have desperation and desperation opens the door to everything. </s><s>[INST] Can I ask a dark question [/INST] as opposed to the other things we've been talking about? </s><s>[INST] There's always a threat, a hopeful message. I think it will be a hopeful message on this one [/INST] too. They have the wrong </s><s>[INST] guess. Just saying, uh, if you were to bet money on the way that human civilization destroys itself or it collapses in some way, that is where the result would be unrecognizable to us as anything akin to progress. What would you say? Is it nuclear weapons? Is it some societal breakdown through just more traditional kinds of war? Is it engineered pandemics, nanotechnologies, that artificial intelligence? Is it something we can't even expect yet? Do you have a sense of how we humans will destroy ourselves or might we live forever? [/INST] I think what governs my view of this thing is the ability for us to focus ourselves collectively? Right. And that gives me the choice of looking at this and saying, what are the odds? We will do X versus why? Right. Um, so go look at the 62 Cuban missile crisis where we look at the potential of nuclear war and we stared right in the face of that to me, I consider that to be you want to talk about a hopeful moment, that's one of the rare times in our history where I think the odds were overwhelmingly that there would be a nuclear war and I'm not the super Kennedy worshiper that, you know, I grew up in an era where he was, especially amongst people in the Democratic Party. He was almost worshiped and I was never that guy. But I will say something john f Kennedy by himself, Um, probably made decisions that saved 100 million or more lives because everyone around him thought he should be taking the road that would have led to those deaths and to push back against that is when you look at it now, I mean, again, if you were a betting person, you would have bet against that, and that's rare, right? Um, so, so when we talk about how the world will end, um, the fact that one person actually had that in their hands meant that it wasn't a collective decision, it gave, remember I said, I trust people on an individual level, but when we get together, we're more like a herd and we devolve down to the lowest common denominator. That was something where the higher ethical ideas of a single human being could come into play and make the decisions that influence the events. But when we have to act collectively, I get a lot more pessimistic. So take what we're doing to the planet and we talk about it always now in terms of climate change, which I think is far too narrow. Uh, look at you, you know, and I always get very frustrated when we talk about these arguments about, is it happening? Is human? Just look at the trash, forget, forget climate for a second. We're destroying the planet because we're not taking care of it. And because what it would do to take care of it would require collective sacrifices. That would require enough of us to say, okay, and we can't get enough of us to say, okay, because too many people have to be on board. It's not john f Kennedy making one decision from one man, we have to have 85% of us or something around the world, not just you can't say we're going to stop doing damage to the, to the, to the world here in the United States, if china does it right. So the amount of people that have to get on board that train is hard. You get pessimistic hoping for those kinds of shifts, unless it's right, Krypton is about to explode. We have, and so I think if you're talking about a gambling man's view of this, that that's got to be the odds on favorite because it requires such a unified, I mean, and the systems maybe aren't even in place, right? The fact that we would need intergovernmental bodies that are completely discredited now on board and you would have to subvert the national interests of nation states, I mean, the the amount of things that have to go right In a short period of time where we don't have 600 years to figure this out, right? So to me that that looks like the most likely just because the things we would have to do to avoid, it seemed the most unlikely. Does that make sense? </s><s>[INST] Yes, absolutely. I I believe call me naive and just like you said with the individual, I believe that charismatic leaders, individual leaders will save us, like, [/INST] you don't get them all at the same time. What if you get a charismatic leader in one country? But what if you get a charismatic leader in a country that doesn't really matter that much? </s><s>[INST] Well, it's a ripple effect, so it starts with one leader and their charisma inspires other leaders, like, so it's uh it's like one and queen steps up and then the rest of the and start behaving and then there's like little other spikes of leaders that emerge, and then that's where collaboration emerges. I tend to believe that like, when you heat up the system and shit starts getting really chaotic, then the leader, whatever this collective intelligence that we've developed the leader will emerge? Like, do you think [/INST] there's just as much of a chance though that the leader would emerge and say the jews are the people who did all this, you know what I'm saying is that the idea that they would come up, you have a charismatic leader and he's going to come up with the rights or she is going to come up with the right solution as opposed to totally coming up with the wrong solution. I mean, I guess what I'm saying is you could be right, but a lot of things have to go the right way, </s><s>[INST] but my intuition about the evolutionary process that led to the creation of human intelligence and consciousness on earth, Mhm results in the the power of like if we think of it, just the love and the system versus the hate in the system that the love is greater. The human, the human kindness potential in the system is greater than the human hatred potential. And so the leader that is in the time when it's needed, the leader that inspires love and kindness will is more likely to emerge and we'll have more power. So you have the hitlers of the world that emerge, but they're actually in the grand scheme of history, are not that impactful. So it's weird to say, but not that many people died in World War Two, if you look at the full range of human history, you know, it's uh up to 100 million, whatever that is with natural pandemics too, you can have those kinds of numbers, but it's still a percentage, I figure what the percentage is, maybe 35% of the human population on earth. Maybe it's a little bit focused on a different region, but it's not destructive to the entirety of human civilization. So the, I believe that the, the charismatic leaders one time is needed that do good for the world in the broader sense of good are more likely to emerge than the ones that say kill all the jews. It's [/INST] Possible though. And this is just, you know, I've thought about this all of 30 seconds. But I mean, uh, it we're </s><s>[INST] Betting money here on the, on the 21st century who's going [/INST] to win? I think maybe you divided this into too much of a black and white dichotomy. This love and good on one side and this evil on another, let me throw something that might be more in the center of that linear a balancing act, self interest, which may or may not be good, you know, good, the good version of it we call enlightened self interest, write the bad version of it. We call selfishness, but self interest to me seems like something more likely to impact the outcome than either love on one side or evil on the other. Simply a question of what's good for me or what's good for my country or what's good from my point of view or what's good for my business. I mean, if you tell me, um, and I maybe I'm a coal miner or maybe I own a coal mine. If you say to me, we have to stop using coal because it's hurting the earth. I have a hard time disentangling that greater good question from my right now, good feeding my family question. Right? So I think, I think maybe it's going to be a much more banal thing than good and evil, much more a question of we're not all going to decide at the same time that the interests that we have are aligned. Does that make sense? Yeah, </s><s>[INST] totally. But I mean, I've looked at I mean rand and objectivism and kind of really thought like how bad or good can things go when everybody's acting selfishly? But I think we're just talking to ants here with microphones talking about. But like the question is when they when this spreads. So what what is, what do I mean by love and kindness? I think it's human flourishing on earth and throughout the cosmos, it feels like whatever the engine that drives human beings is more likely to result in human flourishing. And people like Hitler are not good for human flourishing. So that's what I mean by good is they is is there's uh I mean maybe it's an intuition that kindness is an evolutionary advantage. I hate those terms. I hate to reduce stuff to uh evolutionary biology always, but it just seems like for us to multiply throughout the universe. It's good to be kind to each other and those leaders will always emerge to save us from the hitlers of the world that want to kind of burn the thing down with a flamethrower. That's the intuition. [/INST] But let's talk about, you know, you brought up evolution several times. Let me play with that for a minute. Um I think going back to animal times, we are conditioned to deal with overwhelming threats right in front of us. So I have quite a bit of faith in humanity when it comes to impending doom right outside our door. Uh if Krypton is about to explode, I think humanity can rouse themselves to great and would give power to the people who needed it and be willing to make the sacrifices. But that's what makes, I think the pollution slash climate change slash you know, screwing up your environment, uh threats so particularly insidious is it happens slowly, right? It defies fight and flight mechanisms. It defies the natural ability we have to deal with the threat that's right on top of us. And it requires an amount of foresight that while some people would be fine with that, most people are too worried and understandably, I think too worried about today's threat rather than next generations threat or whatever it might be. So, I mean when we talk about when you said, what do you think the greatest threat is? I think with nuclear weapons, I think could we have a nuclear war we darn right? Could, but I I think that there's enough of inertia were against that because people understand instinctively if I decide to launch this attack against china and I'm India we're going to have 50 million dead people tomorrow. Whereas if you say we're going to have a whole planet of dead people in three generations, if we don't start now, I think the evolutionary, uh, way that we have have, have evolved mitigates maybe against that. In other words, I think I would be pleasantly surprised if we could pull that off. Does that make sense? Totally? I don't mean to be like, I'm not suspecting doom was </s><s>[INST] it's fun that way. I think we're both, maybe I'm over the top on the love, [/INST] maybe I'm over the top on the do. </s><s>[INST] So it makes, it makes for a fun chat. I think so, 11 guy that I've talked to several times just solely becoming a friend is a guy named Elon musk. He's a big fan of hardcore history, especially Jenkins Con a series of episodes, but really all of it, him and his, his girlfriend grimes, listen to it. I know, you know, you're on okay, awesome, so that's like relationship goals. Uh, like listen to hardcore history and the weekend with your loved one. Okay, uh, so let me, if I were to look at the guy from a perspective of human history, it feels like he will be a little speck that's remembered? [/INST] Oh absolutely. You </s><s>[INST] think about like the people, what will we remember from our time, Who are the people will remember whether it's the The Hitlers or the Einstein's who's going to be, It's hard to predict when you're in it, but it seems like Ellen would be one of those people remembered and if I were to guess what he's remembered for, it's the work he's doing with SpaceX and potentially being the person we don't know, but being the person who launched a new era of space exploration, if you look, you know, centuries from now, if we are successful as human beings surviving long enough to venture out into the october the stars, it's weird to ask you this, I don't know what your opinions are, but do you think humans will be a multi planetary species in the arc, a long arc of history? Do you think Ellen will be successful in his dream? And he doesn't, he doesn't shy away from saying it this way. Right. He really wants us to colonize mars first and then colonize other earth like planets in other solar systems throughout the galaxy. Do you have a hope that we humans will venture out towards the stars? [/INST] So here's the thing and this actually again dovetails do what we were talking about earlier. I actually, first of all, I toured SpaceX and it is when, you know, it's hard to get your mind around because he's doing what it took governments to do before. Okay, so, so it's incredible that we're watching individual companies and stuff doing this during a faster and cheaper. Yeah. Well, and, and, and pushing the envelope right faster than the government at the time we're moving. It's it's, it really is. I mean, there's a lot of people who I I think who think Ellen is overrated and you have no idea right? When you go see it, you have no idea. But that's actually not what I'm most impressed with. Um, it's Tesla, I'm most impressed with. And the reason why is because in my mind, we just talked about what I think is the greatest threat, the environmental stuff. And I talked about our inability maybe all at the same time to be willing to sacrifice our self interests in order for the, for the goal. And I don't want to put words in Elon's mouth. So you can, you can talk to him if you want to. But in my mind, what he's done is recognize that problem. And instead of building a car that's a piece of crap. But you know, it's good for the environment. So you should drive it. He's trying to create a car that if you're only motivated by your self interest, you'll buy it anyway and it will help the environment and help us transition away from one of the main causes of damage. I mean, one of the things this pandemic and the shutdown around the world has done is show us how amazingly quickly the earth can actually rejuvenate. We're seeing clear skies in places species come and you would have thought it would have taken decades for some of this stuff. So what if to name just one major pollution source? We didn't have the pollution caused by automobiles. Right? And, and if if you had said to me dan, what do you think? The odds of us transitioning away from that were 10 years ago? I would have said, well, people are going to do it because it's inefficient. It's this, it's that nobody wants to both. But what if you created a vehicle that was superior in every way so that if you were just a self oriented consumer, you'd buy it because you wanted that car. That's the best way to get around that problem of people not wanting to, I think he's identified that. And as he's told me before, you know, when the last time a car company was created, that actually, you know, blah, blah, blah, he's right. And so I happen to feel that even though he's pushing the envelope on the space thing, I think somebody else would have done that someday. I'm not sure because of the various things he's mentioned how difficult it is to start there. I'm not sure that the industries that create vehicles for us would have gone where he's going to lead them. If he didn't force them there through consumer demand by making a better car that people want it anyway, they'll follow, they'll copy they'll do all those things and yet who was going to do that? Um, so I hope he doesn't hate me for saying this, but I happen to think the Tesla idea may alleviate some of the need to get off this planet because the planet is being destroyed, right? And we're going to colonize mars probably anyway, if we live long enough. And I think the Tesla idea, not just Elon's version, but ones that follow from other people is the best chance of making sure we're around long enough to see mars colonize. Does that make sense? Yeah, </s><s>[INST] totally. And one other thing from my perspective, because I'm now starting a company. I think the interesting thing about Ellen as he serves as a beacon of hope, Like pragmatically speaking for people that sort of to push back on our doom conversation from earlier that a single individual could build something that allows us as self interested individuals to gather together in a collective way to actually alleviate some of the dangers that face our world. So like it gives me hope as an individual, that I could build something that can actually have impact that counter acts the the Stalin's and the Hitlers and all the threats that face uh that human civilization faces, that an individual has that power. I didn't believe that the individual has that power in the, in the halls of government. Like I don't feel like anyone presidential candidate can rise up and help the world unite the world. It feels like from everything I've seen and you're right with Tesla, it can bring the world together to do good. That's a really powerful mechanism of, you know, whatever you say about capitalism, that you can build companies that start, you know, it starts with a single individual. Of course, there's a collective that that grows around that, but the leadership of a single individual, their ideas, their dreams, their vision can catalyze something that takes over the world and does good for the entire world. [/INST] But if I think, but again, I think the genius of the idea is that it doesn't require us to go head to head with human nature, right? He's he's actually built human nature into the idea by basically saying, I'm not asking you to be, uh, an environmental activist, I'm not asking you to sacrifice to make it, I'm going to sell you a car, you're going to like better and by buying it, you'll help the environment that takes into account our foibles as a species and actually leverages that to work for the greater good. And that's the sort of thing that does turn off my little doom casters cynicism thing a little bit because you're actually hitting us where we live, right? You're you're you're not you can take somebody who doesn't even believe the environments a problem, but they want a Tesla. So they're inadvertently helping anyway. I think that's the genius of the idea. </s><s>[INST] Yeah. And I'm telling you that's one way to make love. Much more efficient mechanism of change than hey, [/INST] making it in yourself interesting to </s><s>[INST] make you suggest creating a product that, uh, at least two more love than hate. [/INST] You're gonna want to love your neighbor because you're gonna make a fortune. I'd get there. That's why I'm on </s><s>[INST] board. That's why yuan said love is the answer. That's I think, uh, exactly what he meant. Okay, let's try something difficult. You've recorded episode steering into the iceberg on your common sense program that has started a lot of conversations. It's quite moving. It was quite haunting. I [/INST] made a lot of angry emails </s><s>[INST] really. Of course [/INST] I did something I haven't done in 30 years. I endorsed a political candidate from one of the two main parties and there were a lot of disillusioned people because of that. </s><s>[INST] I guess I didn't hear it as an endorsement. I just heard it as a, the similar flavor of conversations you have in, in hardcore history. It's almost a speaking about modern times in the same voice as you speak about when you talk about history. So it was just a a little bit of a haunting view of the world today. I know we were just wearing our Doom [/INST] Doom Master put that right back on our, you know, </s><s>[INST] the, uh, I like the term doom castor is there, is there? How do we get love to win? What's the way out of this? Is there some hopeful line that we can walk to a to avoid something? And I hate to use the terminology, but something that looks like a civil war, not necessarily a war of force, but a division to a level where it doesn't any longer feel like a United States of America with the emphasis on United. Is there a way out? [/INST] I read a book a while back, I want to say George Friedman. The street for a guy wrote it was something called The Next 100 Years, I think it was called. And I remember thinking um I didn't agree with any of it. And one of the things I think he said in the book was that the United States was going to break up. I'm going from memory here. He might not have said that at all, but something was stuck in my memory about that. I remember thinking, um, but I think some of the arguments were connected to the differences that we had and the fact that those differences are being exploited. So we talked about media earlier in the lack of truth and we have a media climate that is incentivized to take the wedges in our society and make them wider and there's no countervailing force to do the opposite or to help, you know? So there was a famous uh memo from a group called project for a new american century and they took it down. But the way back machine online still has it. And it happened before 9 11 spawned all kind of conspiracy theories because it was saying something to the effect of uh and I'm really paraphrasing here. But you know that the United States needs another Pearl Harbor type event because those galvanized a country that without those kinds of events periodically is naturally geared towards pulling itself apart. And it's those periodic events that act as the countervailing force that otherwise is not there. Um, if that's true, then we are naturally inclined towards pulling ourselves apart. So to have a media environment that makes money off widening those divisions, which we do. I mean, I was in talk radio and and it has those people, the people that used to scream at me because I wouldn't do it. But I mean, we would have these terrible conversations after every broadcast where I'd be in there with the program director and they're yelling at me about heat. Heat was the worthy create more heat. Well, what is heat right here? This division? Right? And they want the heat, not because their political, they're not republicans or democrats either there. We want listeners and we want engagement and involvement. And because of the constructs of the format, you don't have a lot of time to get it. So you can't have me giving you like on a podcast an hour and a half or two hours where we build a logical argument And you're with me the whole way your audience is changing every 15 minutes. So whatever points you make to create interest and intrigue and engagement have to be knee jerk right now. Things they told me once that the audience has to know where you stand on every single issue within five minutes of turning on your show. In other words, you have to be part of a of a linear set of political beliefs. So that if you feel a about subject a then you must feel de about subject D. And I don't even need to hear your opinion on it, because if you feel that way about a you're going to feel that way about D. This is a system that is designed to pull us apart for profit, but not because they want to pull us apart, right? It's a byproduct of the Prophet. That's one little example of a 50 examples in our society that work in that same fashion. So what that project for a new American century document was saying is that we're naturally inclined towards disunity and without things to occasionally ratchet the unity back up again. So that we can start from the baseline again and then pull ourselves apart till the next Pearl Harbor that you'll pull yourself apart, which I think was I think that's what the George Friedman book was saying that I disagreed with so much at the time. Um, so in answer to your question about civil wars, we can't have the same kind of civil war because we don't have a geographical division. That's as clear cut as the one we had before. Right? You have to basically north south line and some border states, it was set up for that kind of split. Now we're divided within communities, within families, within gerrymandered voting districts and precincts, right? So you can't disengage we're stuck with each other. So there's a civil war now, for lack of a better word, what it might seem like is the late 19 sixties, early 19 seventies where you had the bombings and you know, let's call it domestic terrorism and things like that because that that would seem to be something that once again, you don't even need a large chunk of the country. Pulling apart 10% of people who think it's the end. Times can do the damage. Just like we talked about terrorism before and a can of gas and a big lighter. I've lived in a bunch of places and I won't give anybody ideas where a can of gas and a big lighter would take 1000 houses down before. You could blink right? Um, that terrorist doesn't have to be from the Middle East doesn't have to have some sort of a fundamentalist religious agenda. It could just be somebody really piste off about the election results. So once again, if we're playing an odds game here, everybody has to behave for this to work right. Only a few people have to misbehave for this thing to go sideways and remember for every action there's an equal and opposite reaction. So you don't even have to have those people doing all these things, All they have to do is start retribution cycle. </s><s>[INST] And there's an escalation [/INST] and it go and it creates a momentum of its own, which leads fundamentally if you follow the chain of events down there to some form of dictatorial government as the only way to create stability, right? You want to destroy the republican, have a dictator. That's how you do. And there are parallels to Nazi Germany, the burning of the Reichstag, you know, blah, blah, blah. I'm the doom caster again. Well, </s><s>[INST] and some of it could be manufactured by those seeking authoritarian power. Like [/INST] The Reichstag fire was or the Polish soldiers that fired over the border before the invasion in 1939, </s><s>[INST] uh, to fight the Devil's Advocate with an angels advocate, I would say, just as our conversation about Ellen, it feels like individuals have power to unite us to be that force of unity. So, you mentioned the media, I think you're one of the great podcast, there's in history, joe Rogan is uh, like a long form, whatever it's not podcasting, it's actually whatever [/INST] the very infrequent is what it is, no matter what it is. </s><s>[INST] But the basic process of it is you go deep and you stay deep and the listener stays with you for a long time. So I'm just looking at the numbers like we're Almost three hours in and I from previous episodes, I can tell you that about 300,000 people are still listening to the sound of our voice three hours in. So usually 300-500,000 people listen and [/INST] they to regulations. By the way, that's wonderful, joe </s><s>[INST] Rogan is what, like 10 times that. And so he has power to unite. You have power to unite. There's a few people with voices that it feels like they have power to unite. Even if you if you quote unquote, endorse a candidate and so on, they're still, it feels to me that speaking of, I don't want to keep saying love, but it's love and maybe unity more practically speaking that like sanity that like respect for those you don't agree with or don't understand. So empathy. Well, just a few voices of those can help us avoid the really importantly, not avoid the singular events like you said, of somebody starting a fire and so on, but avoid the escalation of it. The preparedness of the populist to escalate those events to uh, to to turn a singular event and a single riot or shooting or like even something much more dramatic than that. To turn that into something that creates like ripples they grow as opposed to ripples that fade away and so like I would like to put responsibility on somebody like you and uh me in some small way and joe being cognizant of the fact that a lot of very destructive things might happen in november and a few voices can save us is the feeling I have not by saying who you should vote for or any of that kind of stuff, but really by being the, the voice of calm that like calms the seas from or whatever. The analogy is from boiling up because I truly am worried about this is the first time this year when I, I sometimes I somehow felt that the american project will go on forever when I came to this country, I just believed and I think I'm young but like you know, I have a dream of creating a company that will do a lot of good for the world and I thought that America is the beacon of hope for the world and the ideas of freedom, but also the idea of empowering companies that can do some good for the world. And I'm just worried about this America that filled me, a kid that came from, our family came from nothing and from, you know Russia as it was soviet union as it was to be able to do anything in this new country. I'm just worried about it and it feels like a few people can still keep this project going. Like people like Ellen people like joe uh is there, do you have a bit of that? Hope [/INST] I'm watching this experiment with social media right now. I don't even mean social media really expand that out to. Um I mean I feel like we're all guinea pigs right now watching, you know, I have two kids and just watching and there's a three year space between the two of them. One is 18, the other's 15 And just you know, in when I was a kid, a person who was 18 and 15 would not be that different, just three years difference, more maturity but their life experiences, you would easily classify those two people as being in the same generation now because of the speed of technological change, there is a vast difference between my 18 year old and my 15 year old and not in the maturity question, just in what apps they use, how they relate to each other, how they deal with their peers, their social skills, all those kinds of things where you turn around and go, this is uncharted territory we've never been here. So it's going to be interesting to see what effect that has on society now as that relates to your question. The most upsetting part about all that is reading how people treat each other online and you know, there's lots of theories about this? The fact that some of it is just for trolling laughs that some of it is just people are not interacting face to face so they feel free to treat each other that way. Um, and I of course I'm trying to figure out how, how if this is how we have always been as people, right? We've always been this way, but we've never had the means to post our feelings publicly about it or if the environment and the social media and everything else has provided a change and changed us into something else. Um, either way when one reads how we treat one another and the horrible things we say about one another online, which seems like it shouldn't be that big of deal. They're just words, but they have a cumulative effect. I mean when you uh I was reading um Megan Markle who I don't know a lot about because it's it's too much of the pop side of culture for me to pay a lot. But I read a story the other day where she was talking about the abuse she took online and how incredibly overwhelming it was and how many people were doing it. And you think to yourself, okay, this is something that people who were in positions of what you were discussing earlier never had to deal with. Let me ask you something. And boy, this is the ultimate doom caster thing of all time to say when you think of historical figures that push things like love and peace and um and and creating bridges between enemies when you think of how what happened to those people, first of all, they're very dangerous. Every society in the world has a better time, easier time dealing with violence and things like that than they do. Nonviolence. Nonviolence is really difficult for governments to deal with. For example, what happens to Gandhi and jesus and martin Luther king And you think about all those people, right? When they're that day, it's ironic, isn't it that these people who push for peaceful solutions are so often killed, but it's because they're effective and when they're killed, the effectiveness is diminished. Why are they killed? Because they're effective? And and the only way to stop them is to eliminate them because they're charismatic leaders who don't come around every day. And if you eliminate them from the scene, the odds are you're not going to get another one for a while. I guess what I'm saying is the very things you're talking about which would have the effect you think it would write, they would destabilize systems in a way that most of us would consider positive. But those systems have a way of protecting themselves, right? And and so I feel like history shows the history is pretty pessimistic I think by and large. Um if only because we can find so many examples that just sound passive, but I feel like people who are dangerous to the way things are tend to be </s><s>[INST] removed. Yes, but there's two things to say. I feel like you're right that history, I feel like the ripples that love leaves in history are less obvious detect are actually more transformational. Like [/INST] anyone can make a case about, I mean if you want to talk about the long term value of a jesus or Gandhi yes, those people's ripples are still affecting people today. I agree. </s><s>[INST] And that's you feel those ripples through the general improvement of the quality of life that we see and throughout the generations like you feel the ripples through the girl but I would even if that's not true not, I tend to believe that and by the way that the company that I'm working on is a competitor is exactly attacking this, which is a competitor to twitter, I think I can build a better twitter as a first step. [/INST] There's a long story in there. I think a three year old child could build and that this is not to denigrate, I'm sure yours will be better than, but twitter is so listen, facebook too, they're, they're really awful platforms for intellectual discussion and meaningful discussion, but when I'm on it, so let me just say I'm part of the problem, we're new </s><s>[INST] to this. So it's not, it wasn't obvious at the time how to do, it's now now a three year old can do. I tend to believe that we live in a time where the tools that people that are interested in providing love. Like the weapons of Love are much more powerful. So like the one nice thing about technology is that allows anyone to build a company that's more powerful than any government. So that could be very destructive. But it could be also very positive. And that's I tend to believe that somebody like Elon wants to do good for the world, Somebody like me and then you like me could have more power than anyone. Government two and by power, I mean the power to affect change, which is different from the [/INST] government and I don't mean to interrupt you but I'll forget my train of thought, you know what I mean? How do you deal with the fact that already governments who are afraid of this are walling off their own internet systems as a way to create firewalls simply to prevent you from doing what you're talking about. In other words, if you know there's an old line that if voting really changed anything, they'd never allow it. If if love through a modern day successor to twitter would really do what you wanted to do and this would destabilize governments. Do you think that governments would would take countermeasures to squash that love before it got too dangerous. There's several </s><s>[INST] answers. One first of all, I don't actually to push back on something you said earlier. I don't think love is as much of an enemy of the state As as one would think [/INST] different states have different views. </s><s>[INST] I I think the states want power and I don't always think that love is intention with power. Like I think and and and I think it's not just about love, it's about rationality is reason, it's empathy. All of those things. I don't necessarily think there always have to be by definition in conflict with each other. So that's one sense is I feel like basically you can trojan horse love into behind behind. Uh, but you have to be good at it. This is the thing is you have to be conscious of the way these states think so the fact that china bans certain services and so on, that means the companies weren't eloquent. Whoever the companies are, weren't actually good at infiltrating. Like I think isn't that a song like Love is a battlefield? I think [/INST] it's all a gap editorial. </s><s>[INST] Yeah. It's all a game and you have to be good at the game. And just like Ellen we said, you know, with Tesla and saving uh, the environment. I mean that's not just by getting on a stage and saying it's important to save the environment is by building a product that people can't help but love and then convincing Hollywood stars to love it. Like there's there's a game to be played. [/INST] Okay, so let me let me build on that because I think there's a way to see this. I think you're right. And so it has to do with a story about the 19 sixties, in the vast scheme of things. The 19 sixties looks like a revival of neo romantic ideas. Right? I had a buddy of mine several years, well, Two decades older than I was, who was in the 60s, went to the protest and all those kind of things, and we were talking about it and I was romanticizing it, and he said, don't romanticize, because let me tell you most of the people that went to those protests and did all those things, all they were, there was to meet girls and have a good time and, you know, it was it wasn't so but it became in vogue to have all in other words, let's talk about your empathy and love. You're never gonna, in my opinion, grab that great mass of people that are only in it for them, they're interested in whatever. But if meeting girls for a young teenage guy requires you to feign empathy, requires you to read deeper subjects because that's what people are into. You can almost as a silly way to be trendy, you can make maybe empathy trendy love trendy solutions that are the opposite of that. Um the kind of things that people inherently will not put up with, in other words, the possibility exists to change the zeitgeist and reoriented in a way that even if most of the people aren't serious about it. the results are the same. Does that make sense? Absolutely. Okay, so we found a meeting of the month. </s><s>[INST] Yeah, exactly. Creating creating incentives that and encourage the best and the most beautiful [/INST] aspects of nature. Will </s><s>[INST] it all boils down to meeting girls and boys? [/INST] Once again, you're getting to the bottom of the evolutionary motivations and you're always on safe ground when you do </s><s>[INST] that. This is a little difficult for me. I've, you know, and I'm sure it's actually difficult for you to listen to me, you say complimenting you, but it's difficult for both of us. Okay, So, but uh you know, you and I as I mentioned to you, I think I might have been friends for a long time. It's just been one way. So like everyone, it's two way, it's too right now. So like that's the beauty of podcasting, you know, I mean now just been fortunate enough with this particular podcast that I see it in people's eyes when they meet me that they've been friends with me for for a for a few years now and and we become fast friends actually after we start talking, but it's one way in the vet and now, first moment uh you know, like there's something about, especially hardcore history that, you know, I do some crazy challenges and running and stuff. I remember in particular Probably don't have time, one of my favorite episodes, the painful Tainment one. Some [/INST] people hate that episode </s><s>[INST] because it's too real. [/INST] Uh, it's my darkest one. We wanted to set a baseline. That's the baseline. </s><s>[INST] But I remember listening to that and when I ran 22 miles for me, that was a long distance and that's [/INST] entertainment, Right? </s><s>[INST] Yeah. And it just pulls you in and there's something so powerful about this particular creation that's bigger than you actually, that you've created. [/INST] It's kind of interesting. I think anything that is successful like that, like Dylan stuff to, it becomes bigger than you and that's, that's what you're hoping for, right? </s><s>[INST] Absolutely. Didn't mean to interrupt you [/INST] apologize. I guess </s><s>[INST] one question I have, if you like, look in the mirror, but you also look at me, what advice would you give to yourself and to me and two other podcasters, maybe to joe Rogan about this journey that we're on? I feel like it's something special. I'm not sure exactly what's happening, but it feels like podcasting is special. What advice? And I'm relatively new to it. What advice do you have for for people that are carrying this flame and traveling in this journey? [/INST] Well, I'm often asked for advice by new podcasters. People just starting out. And so I have sort of a tried and true list of dues and don't stand, but I don't have, um, advice or suggestions for you or for joe joe doesn't need anything from me, joe's figured it out, right? I mean he </s><s>[INST] hasn't yet. He's still confused kid curious about the world. [/INST] That's, but that's the genius of it. That's what makes it work, right? That's what, that's what Joe's brand is, right. Um, I guess what I'm saying is is by the time you reach the stage that you're at or joe's at or they don't need, they have figured this out. The people that sometimes need help our brand new people trying to figure out what do I do with my first show and how do I talk to them? And I've standard answers for that. But you found your niche. I mean, you don't need me to tell you what to do. As a matter of fact, I might ask you questions about how you do what you do, right? Well, </s><s>[INST] there's uh, I guess there's specific things like we were talking off line about monetization. That's a fascinating one. [/INST] Very difficult. Uh, as an independent </s><s>[INST] and uh, one of the things that joe is facing with, I don't know if you're paying attention, but he joined Spotify With $100 million exclusivity, that one, I don't give a damn about money personally, but I'm single. So, and I like like living in a shady place, so [/INST] I </s><s>[INST] enjoy, so I guess makes it easy [/INST] to get the freedom right. </s><s>[INST] Freedom materials is slave not [/INST] saving for anybody's college. </s><s>[INST] Exactly. Okay. So at that point, but I also, okay, maybe it's romanticization, but I feel like podcasting is pirate radio and when I first heard about Spotify partnering up with joe, I was like, you know Funk? The man I, I said, I I even I drafted a few tweets and so on. Just like attacking Spotify. Then I calmed myself down that you can't lock up this special thing we have. Uh, but then I realized that maybe that these are vehicles for just reaching more people and actually respecting podcast, there's more and so on. So that's what I mean by it's unclear what the journey is Because uh, you also serve as a beacon for now. There's like millions, one million plus podcasters. I wonder what the journey is. Do you have a sense? Um, are you romantic in the same kind of way in feeling that because you have a roots in radio to do you feel that podcasting is pirate radio Or is this Spotify thing one possible avenue. Are you nervous about Joe as a fan, as a friend of Joe or is this it's a good thing for us. [/INST] So my history of how I got involved in podcasting is interesting. I was in radio. Uh, and then I started a company back in the era where the dot com boom was happening and everybody was being bought up and it just seemed like a great idea, right? Started. Um, I, I did it with seven other six other people and the whole goal of the company was, and we had, we had to invent the term, I'm sure everybody, I mean, there's other places that invented it at the same time, but what we were pitching to investors was something called amateur content. This is before Youtube, before podcasting, before all this stuff and I, my job was to be the evangelist and I would go to these people and uh, and, and sing the praises of all the ways that amateur content was going to be great. And I never got a bite. And they all told me the same thing. This isn't gonna take off because anybody who's good is already going to be making money at this. And I kept saying, forget that we're talking about scale here. If you have millions of pieces of content being made every week, A small percentage is going to be good, no matter what, right, 16 year olds will know what other 16 year olds like. I kept pushing this nobody bit. But the podcast grew out of that because if you're talking about amateur content in 1999, well then you're already where, you know, you're ahead of the game in terms of, of not seeing where it's going to go financially, but seeing where it's going to go technologically. And so when we started the podcast in 2005 and it was the political one, not hardcore history, um, which was an outgrowth of the old radio show. Um we didn't have any financial um, ideas, we were simply trying to get a handle on the technology and how you distribute it to people and all that. And it was years later we tried to figure out, okay, how can we get enough money to just support us while we're doing this? And, and the cheap in the easy way was just to ask listeners to donate like PBS kind of model and that was, that was the original model. Um, so then once we started down that we figured out other models and this advertising thing and we sell the old shows and so all these became ways for us to support ourselves. Um, but as, as podcasting matured and as more operating systems developed and phones were developed and all these kinds of things, every one of those developments, which actually made it easier for people to get the podcast actually made it more complex to make money off of them. So while our audience was building the amount of time and effort we had to put into the monetization side began to skyrocket. So to get back to your Spotify question to use just one example, there's a lot of people who are doing similar things um, In this day and age, you know, we just sell MP three files and all you had to have was an MP three player is cheap and dirty. Now every time there's an os upgrade something breaks for us. So we're having, I mean my choices are at this point to start hiring staff, more staff, you know, people don't, and then be a human resources manager. I mean the pirate radio side of this was the pirate radio side of this because you didn't need anybody, but you know, you are you and another, I mean, you could just do this lean and mean and it's becoming hard to do it lean and mean now. So if somebody like a Spotify comes in and says, hey, um, we'll handle that stuff for you in the past, I would just say f off, we don't need you, I don't mind. And I definitely am not making what we could make on this, but what we would have to do to make that is onerous to me, but it's becoming onerous to me day to day anyway. And so if somebody were to come in and say, hey, we'll pick that up for you, we will not interfere with your content at all. We won't, and in my case, you can't say we need to show a month because that ain't happening, right? So, I mean, everybody's, everybody's uh design is different, right? So it doesn't, you know, there's not one size fits all, but I guess as a long time pirate podcaster, um, there are, you know, we've been looking to partner with people, but nobody is right for us to partner with. I mean, so, so I'm always looking for ways to take that side of it off my plate because I'm not interested in that side. All I wanna do is the shows and they, you know, it's really at this point you shouldn't call yourself an artist because you know, that's something to be decided by others. But I mean what we're trying to do art and there's something very satisfying in that, but the part that I can't stand is the increasing amount of time the monetization question takes upon us. And so there's a case to be made, I guess is what I'm saying that if a partnership with some outside firm enhances your ability to do the art without dis enhancing your ability to do the art, it's um, the word I'm looking for here is it's um, it's enticing uh, I don't like big companies. Um, so I'm afraid of, of whatever strings might come with that. And if I'm joe Rogan and I'm talking about subjects that can make company public companies, you know, a little nervous. Um, I would certainly be careful. But at the same time, people who are not in this game don't understand the problems that literally, I mean, just all the operating systems, all the podcasters every time some new podcaster comes out makes it easier to get the podcast. That's something we have to account for on the back end and I'm not exactly the technological wizard of all time. So, um, I think it is maybe maybe the short answer is is that as the medium develops, it's becoming something that you have to consider not because you want to sell out, but because you want to keep going and it's becoming harder and harder to be pirate. Like in this environment. </s><s>[INST] The thing that convinced me, especially inside Spotify is that they understand, so if you walk into this whole thing with some skepticism as you're saying a big companies, then then it works because Spotify understands the magic that makes podcasting or they appear to in part at least they understand enough to respect joe Rogan and despite what I don't know if you, uh, so there's the internet and there's people with opinions on the internet. Yes. And they have opinions about joe and Spotify, but the reality is there's two things in private conversation with joe and in general there's, there's two important things. One, Spotify literally doesn't tell joe anything like all the people that think they Spotify somehow pushing joe in this direction of [/INST] that didn't insist upon that </s><s>[INST] it's in the contract, but also, you know, companies have a way of, even with the country to be, you know, marketing people, hey, I know we're not forcing. [/INST] Yeah, yeah, yeah, I hate that. </s><s>[INST] But with what you and joe are the same. And Spotify smart enough not to send a single email of that kind that's really smart and they leave, they leave them be there is meetings inside Spotify that like people about people complain. But those meetings never reached joe that, that never, that's a company stuff. And the idea that that Spotify is different than pirate radio. The difficult thing about podcasting is nobody gives a damn about your podcast. You're alone in this. I mean there's fans and stuff but nobody, nobody's [/INST] looking out for you. Yeah, </s><s>[INST] and the nice thing about Spotify is they want joe to joe's podcast to succeed even more. That's what joe talked about is that's the difference between Youtube and Spotify. Spotify wants to be the Netflix of podcasting and they like what Netflix does is they they, they don't want to control you in any way, but they want to create a platform where you can flourish [/INST] because your interests are aligned. The interests. Let me bring up, let me bring up something that let's make a distinction because not all companies who do this are the same and you brought up Youtube and Spotify, but to me, Youtube is at least more like Spotify than some of these smaller, the term is walled garden. Right? You've heard the term walled garden. Okay, so um I've been around podcasting so long now that I've seen rounds of consolidation over the years and they come in waves and then all of a sudden, so you'll get and I'm not going to mention any names, but up until recently the consolidation was happening with relatively small firms compared to people like Spotify. And the problem was, is that by deciding to consolidate your materials in a walled garden, you are walling yourself off from audience, right? Um so your choices, I'm gonna accept this amount of money from this company, but the loss is going to be a large chunk of my audience and that's a catch 22 because you're negotiating power with that company is based on your audience size. So signing up with them diminishes your audience size, You lose negotiating power, but when you get to the level of the Spotify to just pick them out, there's other players, but you brought up Spotify specifically these are people who can potentially potentially enhance your audience over time. And so the risk to you is lower because if you decide in a year or two, whatever the licensing agreements term is that you're done with them and you want to leave instead of how you would have been with some of these smaller walled gardens where you're walking away with a fraction of the audience you walked in with, you have the potential to walk out with whatever you got in the original deal plus a larger audience because their algorithms and everything are designed to push people to your content if they think you'd like. So it takes away some of the downside risk which which alleviates and if you can write an agreement like joe Rogan, I mean where you've protected your your freedom to, to put the content of the way you want. So if some of the downside risk is mitigated and if you eliminate the problem of trying to monetize and stay up with the latest tech, then it might be worth it. You know, I'm scared of things like that, but at the same time I'm trying to not be an idiot about it and I can be an idiot about it and when you've been doing it as independently for as long as I have, the inertia of that has a force all its own. But I'm I'm inhibited enough in what I'm trying to do on this other end that it's opened me at least listening to people. Um, but listen, at the same time, I love my audience and it sounds like a cliche, but they're literally the reason I'm here. So I want to make sure that whatever I do, if I can, is in keeping with A relationship that I've developed with these people over 15 years. Um, but like you said, no matter what you do, you are because see here's the thing, if you don't sign up with one of those companies to make it easier for them to get your stuff on this hand, they might yell at you for how difficult it is because the new, uh, new new operating system just updated, you can't get yourself. So either way you're opening yourself up to ridicule at this point, all of that makes it easier to go well if the right deal came along and we weren't screwing me and they weren't screwing my audience and blood was um, you know, I mean, again in this business, when you're talking about cutting edge technology, that is ever changing and as you said, a million podcasts and growing, I think you have to try to maintain flexibility and especially if they can mitigate the downside risk. I think you have to, I think you'd be an idiot to not at least try to stay up on the current trends and look, I'm watching joe, I'm going, okay, let's see how it goes for joe. You know, I mean, if, if he's like, this is terrible, I'm getting out of this, you go, okay, Those people are, you know, so Jos, jos put himself out as a guinea pig and I, and the rest of us, guinea pigs appreciate </s><s>[INST] as a huge as a fan of your shows and as a fan of netflix. The people there, I think I can speak for like millions of people in hope that the hardcore history comes to netflix or Spotify becomes the netflix of podcasting. That to Spotify, there's something at, it's best that they bring out the you said artists, so I can say it is, they bring out the best out of the artists, they removed some of the headache and somehow like they put at their best netflix, for example, is able to enforce and find the beauty and the power and the creations that you make even better than you like. They don't interfere with the creations, but they somehow, it's a branding thing probably to [/INST] interfering would be, that would be a no go from. That's right. Absolutely. That can't, that can't </s><s>[INST] help. But that's why netflix is masterful. They seem to not interfere with the talent as opposed to I could throw other people under the bus. [/INST] Like I'm a lot of places </s><s>[INST] under the bus that could be thrown. Absolutely. So I would love, I know there's probably people screaming yes right now in terms of hardcore history on netflix would be awesome. Um, I don't love asking this question, but it's asked probably the most popular question that's unanswerable. So let me try to ask it in a way that you would actually answer it, which is of course you said you don't release shows very often. And uh, the question is the requests and the questions is, well, can you tell dan to do one on the civil wars, Can you tell dan to do one on the polling Bonaparte? Can you can tell him to do one? You know every, every topic and you've spoken to this actually, your answer about the civil war is quite [/INST] interesting. I didn't know you knew what my answer, but the civil war </s><s>[INST] that you don't as a military historian you enjoy in particular when there's differences in the army as a contrast contrasts with the civil war, which like blew my mind when I heard you say is, you know, it's there's not an interesting, deep, intricate contrast between the two opposing [/INST] the roman civil wars which legionaries against legendary </s><s>[INST] is. And you've also said that you kind of, the shows you work on are ones where you have some roots of fundamental understanding about that period. And, and so like when you work on the show, it's basically like pulling at those strings further and like refreshing your mind and [/INST] learning, definitely done the research. </s><s>[INST] Wow, these are words [/INST] out of my mouth. Yeah, you're right. </s><s>[INST] So, but is there something like, like shower thoughts on reddit? Uh, is there some ideas that are like lingering in your head about possible future episodes? Is there things that whether you uh not committing to anything, but whether you're going to do it or not, is there something that's like, makes you think that would be interesting to uh, to pull at that thread a little bit? [/INST] Oh yeah, we have things we keep in our back pocket for later. So, uh, blueprint for Armageddon, the first World War series we did. That was in my back pocket the whole time. And when the centennial of the war happened, it just seemed to be the likely time to bring out what was that </s><s>[INST] was a hell of a series. That's probably one of my favorites, My [/INST] rear end man, </s><s>[INST] I have to take psychologically, I mean, [/INST] You know when you get to these, I think I'm guessing here, I think it's 26 hours. All pieces together. Think about and, and we don't do scripts, it's improvised. So think about what 20 I had somebody write on Twitter just yesterday saying um he said something like I'm not seeing the dedication here, you're only getting 2.5 shows out of here. And I wanted to say, man, you have no idea what the only people who understand really are other history podcasters and even they don't generally do 26 hours. You know, that was a two year endeavor. Um as I said, the first show we ever did was like 15 minutes. I could crank out one of those a month, but when you're doing, I mean the last show we did on the fall of the roman republic was 5.5 hours, that's a book, Right? Um and it was part six or something. So I mean you just do the math. Um and it </s><s>[INST] felt like you were sorry to interrupt on, on World War One. It felt like you were emotionally pulled in to it. Like it felt taxing. [/INST] I was gonna say that's a good thing though because you know, and I think we said during the show, that was the feeling that the people at the time happened. I think in at one point we said that this is starting to seem gruesomely repetitive now, you know, how the people at the time felt. So in other words that had any sort of inadvertently, because when you improvise a show, some of these things are inadvertent, but it had inadvertently created the right climate for having a sense of empathy with the storyline. And to me that those are the serendipitous moments that make this art and not uh some sort of paint by the numbers kind of endeavor, you know, And and that's to me, that wouldn't have happened had we scripted it out? </s><s>[INST] So it's mostly you just bring the tools of knowledge to the table and then in large part improvised, like, the actual warding. [/INST] I always say we make it like, they made things like spinal tap and some of those other things where um the material. So, I do have notes about things like, on page 4, 27 of this book, you have this quote, so that I know Aha, I'm at the point where I can drop that in. Um and sometimes I'll write notes saying, here's where you left off yesterday. So I remember, um but in the improvisation, you end up throwing a lot out. And so, um like, like, but it allows us to go off on tangents, like we'll try things like, I'll sit there and go, I wonder what this would sound like, and I'll spend two days going down that road and then I'll listen to and go, doesn't work. But that's, you know, like writers do this all the time. It's called Killing Your Babies, right? You can't get, but people go, so this guy goes, I'm not seeing the dedication. He has no idea how many things were throwing out. I did an hour and a half. I had an hour and a half into the current show about two months ago and I listened to it. I just went, you know what? It's not right, boom, out the window. There goes six weeks of work, Right? But here's the problem. You trust your sorry to interrupt. You. Trust your judgment on that. No, no. But, but here's, here's the, here's the thing. Um, our show is a little different than other people's joe Rogan called it evergreen content in other words. Uh, My Political Show is like a car you buy and the minute you drive it off the lot it loses half its value because it's not current anymore. These shows are just as good or just as bad. Five years from now as they are when we do. Although the standards on the internet changed when I listen to my old shows, I cringe sometimes because the standards are so much higher now. But um, when you're creating evergreen content, you have to audiences to worry about, you have the audience that's waiting for the next show and they've already heard the other ones and they're impatient and they're telling you on twitter where is it? But you have show the show is also for people five years from now who haven't discovered it yet and you don't care a wit for how long it took because they're going to be able to download the whole and all they care about is quality. And so what I always tell new podcasters is they always say I read all these things that it's very important to have a good release schedule. Well it's not more important than putting out a good piece of work and the audience will forgive me if it takes too long. But it's really good when you get it. They will not forgive me if I rush it to get it out on time and it's a piece of crap. So for us and this is why when you brought up a Spotify deal or anything else they can't interfere with this at all. Because my my job here as far as I'm concerned is quality. And everything else goes by the wayside. Because the only thing people care about long term. The only thing that gives you longevity is how good is it? Right? How good is that book? If you read J. R. R. Tolkien's work tomorrow, you don't care how long it took him to write it. All. You care is how good is this today And that's what we try to think too and I feel like if it's good if it's really good, everything else falls into place and takes care of itself. Um, </s><s>[INST] although sometimes to push back, sorry to interrupt, [/INST] I've done it to you 1000 times. So you can get me back. </s><s>[INST] Sometimes the deadline you, you know, some of the greatest, like movies and books have been, you think about like dusty Sk I forget which one knows from underground or something. He needed the money. So he had to write it real quick. Sometimes the deadline creates is powerful at taking a creative mind of an artist and just like slapping it around to force some of the good stuff out. Now. The problem with history of course, is there's there's different definitions of good, um, that like, it's not just about what you talk about, which is the storytelling, the richness of the storytelling. And I'm sure you're, you know, again not to compliment you too much, but you're one of the great storytellers of our time. That, that I'm sure if you put in a jail cell and forced at a, like somebody point a gun at you, you could tell one hell of a good story, but you still need the facts of history or not necessarily the facts, but you know, like making sure you painting the right full picture not perfectly [/INST] right. That's what I meant about the audience doesn't understand what a history podcast, you can't just riff and be wrong. So let me let me both both oppose what you just said and back up what you just said? So I have a book that I wrote, right and uh in a book you have a hard deadline, right? So harper Collins had a hard deadline on that book. So when I released it I was mad because I would have worked on it a lot longer, which is my style, right, get it right. But we had a chapter in that book entitled Pandemic Prologue question mark, and it was the book about the part about the black death in the 1918 flu and all that kind of stuff. And and I was just doing an interview with a spanish journalist this morning who said, did you ever think how lucky you got on that on that? You know? And first of all, lucky on a pandemic, it strikes you. But had I had my druthers, I would have kept that book working in my study for months more and the pandemic would have happened. And that episode that would have looked like a chapter I wrote after the fact I would have to rewrite the whole thing, it would've been. So that argues for for what you said at the same time, I I would have spent months more working on it because to me it didn't look the way I wanted it to look yet, you know, </s><s>[INST] can you drop a hint of the things that you're keeping on the shelves, [/INST] the alexander, the great podcast, I've talked around, I talked to somebody today said, do you know that the very first word in your very first podcast in the title? The very first thing that anybody ever saw with hardcore history is the, is the word alexander because the show is entitled Alexandre versus Hitler. I have talked around the career, I've done show after I talked about his mother in one episode, I talked about the funeral games after his death. I've talked around this, I've specifically left this giant alexandria in size hole in the middle because we're going to do that show one day and I'm going to lovingly enjoy talking about this crazily interesting figure of alexander the Great, so that's one of the ones that's on the back pocket list. And what we try to do is whenever this we're doing um Second World War in Asia and the pacific Now, I'm on part five, whenever the heck we finish this, the tendency is to then pick a very different period because we've had it and the audience has had it. Um so it's time. So, um I will eventually get to the alexander saga. </s><s>[INST] What about just one last kind of a little part of this is what about the other half of that first 10 minute, 15 minute episode, which is so you've done quite a bit about the World War, you've done quite a bit about Germany will you ever think about doing Hitler and the man, [/INST] it's funny because uh I talked earlier about how I don't like to go back to the old shows because our standards have changed so much with a long time ago. One of my standards for not getting five hour podcast done or or not getting too deeply into them was to flit around the interesting points, but we didn't realize we were going to get an audience that wanted the actual history. We thought we could just go with assume the audience knew the details and just talk about the weird stuff that only makes up one part of the show now. So we did a show called Nazi Tidbits and it was just little things about, you know, it's totally out of date now, like, you know, you can still buy them, but they are out of date um where we dealt a little with it. Uh you know, it would be interesting, but I'll give you another example, I mean history is not stagnant as you know, uh and we had talked about Stalin earlier and ghosts of the Austrian was done years ago and people will write me from Russia now and say, well your portrayal of Stalin is totally out of out of uh it's outdated because there's all this new stuff from the former soviet union and you do you turn around and go, okay, um there, right, And so when you talk about Hitler, it's very interesting to think about how I would do a Hitler show today versus how I did 1 10 years ago, um and you would think, well, what's new? I mean, it happened so long, but there's lots of new stuff and there's lots of new scholarship and and so, um yeah, I would think that would be an interesting one to do someday. I haven't thought about that, that's not in the back pocket, but uh but yeah, that'd be interesting. </s><s>[INST] I have a disproportionate amount of power because trapped you somehow in the room and [/INST] thereby </s><s>[INST] during the pandemic. So, like, my hope will be stuck in your head, but after alexander the Great, which would be an amazing podcast, I, I hope you do give a return to Hitler, The Rise and Fall of the Third Reich which to me, uh really [/INST] temporary book, basically. Yeah, </s><s>[INST] and I Exactly, is by a person who was there. Yeah, I I really loved that study of the Man of Hitler, and I would love to hear your the study of certain aspects of it, and perhaps even an episode that's, like more focus on a very particular period. I just feel like you can uh tell a story that it's funny, Hitler is one of the most studied people, and I still feel like this, all the stories, or most of the stories haven't [/INST] been told, Oh, and there's listen, I've got three books at home, I'm on all the publishers lists now, and they just the young Hitler, there's this Hitler, there's that, I mean, I've been reading these books and I've read about Hitler, I read The Rise and Fall of the Third Reich my mother thought I needed to go to a psychologist because I read it when I was six and she said there's something wrong with the boy and but she was </s><s>[INST] absolutely right, [/INST] but but you would think that that's something like that is pretty established fact. And yet there's new stuff coming out all the time. And needless to say, Germany has been investigating this guy forever and sometimes it takes years to get the translations. I took five years of german in school, I can't read any of it. So, um so I mean, and, and and he is, when you talk about fascinating figures, he's so, the whole thing is so twisted, lee weird. Um there was a, it came out a couple of years ago, somebody found a tape of him talking to uh General, I want to say it was General, um the Finnish General Manor home, Right? And and he's just in a very normal conversation of, of the sort we're having now and you know, the Hitler tape when you hear normally is ranting and raving and but this was a very sedate and I wish I had understood the german well enough to really get a feel because I was reading what Germans said, They said, wow, you can really hear the southern accent, you know, little things that only a native speaker would hear. And I remember thinking this is such a different side of this twisted character and you would think you would always, you would think that this was information that was out in, in, in in in the rise and fall of the third Reich there, but it wasn't. And so this, this, this is a goes along with that stuff about new stuff coming out all the time, alexander, new stuff coming out all the time really well, at least interpretations rather than factual data </s><s>[INST] and those color your, that those give depth to your understanding. [/INST] Yes, you and you want that because the historian biography, people, people love that. And that was a byproduct of my lack of credentials where we thought we're going to bring in um the historians and we call them audio footnotes right away for me to say, listen, I'm not a historian, but I'll quote this guy who is so you can trust him. But then we would quote other people who had different views and people didn't realize that that if they're not history majors, that historians don't always agree on this stuff and that they have disagreements and they loved that. So, so I I love the fact that there's more stuff out there because it allows us to then bring in um other points of view and sort of maybe three dimensional eyes or flesh out the story a little bit more </s><s>[INST] To ask questions. One really simple one, absurdly ridiculous and perhaps also simple first, who has been in a surreal, [/INST] I don't even know what you're talking about </s><s>[INST] very well. [/INST] How's that for an answer? Like asking me is harvey the white rabbit real. I don't know, there's carrots all around the production room, but I don't know what that means. </s><s>[INST] Well, a lot of people demanded that I prove I somehow figure out a way to prove the existence. [/INST] I said he was real. People would say no, he's not. And if I said he was if he wasn't real, they would say yes, he is. So it's a santa claus, easter bunny kind of vibe there. </s><s>[INST] I mean, what is real? Anyway, [/INST] that's exactly what I told him. It </s><s>[INST] exists. Okay. The most absurd question, I'm very sorry, very sorry. But then again, I'm not. What what what's the meaning of it all? You you study history of human history, Have you been able to make sense of why the hell we're here on this spinning rock? What does that even even make sense? What's the meaning of life? [/INST] What I look at some times that I find interesting is certain consistencies that we have over time, history doesn't repeat, but it has a constant and the constant is us now we change. I mentioned earlier the wickedly weird time we live in with what social media is doing to us as guinea pigs And that's a new element, But we're still people who are motivated by love, hate, greed, envy sex. I mean all these things that would have connected us with the ancients, right? That's the part that always makes history sound like it rhymes, you know? Um, and when you put the constant, the human element and you mix it with systems that are similar. So one of the reasons that the ancient roman republic is something that people .2 all the time. Um, as a, something that seems like we're repeating history because you have the two cons, you have humans just like you had then and you have a system that resembles the one we have here. So you throw the constant in with a system that is somewhat similar and you begin to see things that look like they rhyme a little. So for me, I'm always trying to figure out more about us. And when you show us in uh 500 years ago in Asia And 800 years ago in Africa, and you look at all these different places that you put the Guinea Pig in and you watch how the Guinea Pig responds to the different stimuli and challenges. I feel like it helps me flush out a little bit more who we are in the long timeline, not who we are today specifically, but who we've always been. Um, it's a personal quest. It's not meant to educate anybody else. It's, it's something that fascinates me. </s><s>[INST] Do you think there's uh in that common humanity throughout history of the guinea pig, is there a why underneath it all, or is it somehow like it feels like it's an experiment of some sort, [/INST] Oh, now you're into it, Elon musk. And I talked about this, the simulation thing, right? Nicb Ostrom, Sure, yeah, the idea that there's some, some kid and were the equivalent of an aliens and farm, you know, uh and we hope he doesn't throw a tarantula in just to see what happens. Um I think the wise elude us, and I think that what makes philosophy and religion and those sorts of things so interesting is that they grapple with the wise. Um but I'm not wise enough to to uh propose a theory myself, but I'm interested enough to read all the other ones out there. So um uh let's put it this way, I don't think there's any definitive y that's been agreed upon, but the various theories are fascinating. </s><s>[INST] Yeah, whatever it is, whoever the kid is that created this thing, the the ant farms kind of interesting [/INST] so far, a little bit, a little bit twisted and perverted in sadistic man, </s><s>[INST] that's what makes it fun, I think. But then again, that's the Russian perspective, [/INST] I was just gonna say </s><s>[INST] it [/INST] is the Russian perspective a little bit, what makes the Russians Russian history one day, I'll do some Russian history I took in college, Oh, that's the ant farm baby. That's an ant farm with a very, very frustrated young uh teenage alien kid </s><s>[INST] dan. I can't say I've already complimented you way too much. I'm a huge fan. This has been an incredible conversation. It's a huge gift. Your, your gift of humanity. I hope [/INST] you cut you often. Just say you've done a wonderful job. This has been fun for me. The questions and more importantly, the questions can come from anybody. The counter statements, your responses have been wonderful. You made this a very fun intellectual discussion for me. Thank you. </s><s>[INST] Let me have the last word and say, I agree with Ellen and despite the doom castor say that I think we've concluded definitively and you don't get a chance to respond that love is in fact the answer and the way forward. So thanks so much dan. Thank you for having me. Thanks for listening to this conversation with dan Carlin and thank you to our sponsors, athletic greens, the only one drink that I start every day with to cover all my nutritional bases, simply safe home security company. I used to monitor and protect my apartment magic spoon, low carb keto friendly cereal that I think is delicious and finally cash up the app. I used to send my need of friends for food and drinks, please check out these sponsors in the description to get a discount and to support this podcast. If you enjoy this thing, subscribe on Youtube, review it with five stars on Apple podcast. Follow on Spotify, Support on Patreon. I'll connect with me on twitter Elex Friedman, and now let me leave you with some words from dan Carlin Wisdom requires a flexible mind. Thank you for listening and hope to see you next time. [/INST] </s> |
<s>[INST] Yeah. And it was, I guess it's zero click because I didn't have to do anything. The only thing I well, you know, here's the thing I did, you know, basics of, you know, put it behind a firewall, I followed the instructions, but like I wasn't, I didn't really pay attention. So maybe there's like maybe there's a miss configuration of some sort that's easy to make, it's difficult. We have a personal naz on him. So I don't, I'm not willing to sort of say that I did everything I possibly could. Um, but I did a lot of reasonable stuff and they still hit it with zero clicks. I didn't have to do anything. [/INST] Yeah, well it's like a zero day and it's a supply chain attack. You know, you're getting hit from your supplier, you're you're getting hit because of your vendor. And it's also a new thing for ransomware groups to go to the individuals to pressure them to pay. There was this really interesting case, I think it was in Norway where there was a mental health clinic that got hit and the cyber criminals were going to the patients themselves to say pay this or we're going to release your psychiatric records. I mean, talk about hell. Um, in terms of whether to pay, you know, that is on the cheaper end of the spectrum from </s><s>[INST] the individual from the company. [/INST] Both, you know, we've seen for instance, there was an apple supplier in Taiwan, They got hit and the ransom demand was 50 million. You know, I'm surprised it's only 1.8 million, I'm sure it's going to go up. Um, and it's hard, you know, there's obviously governments and maybe in this case the company are going to tell you, we recommend you don't pay or please don't pay, but the reality on the ground is that some businesses can't operate? Some countries can't function. I mean, the under reported story line of colonial pipeline was after the company got hit and took the preemptive step of shutting down the pipeline because they they're billing systems were frozen. They couldn't charge customers downstream. My colleague David Singer and I got our hands on a classified assessment that said that as a country We could have only afforded to 2, 3 more days of colonial pipeline being down. And it was really interesting. I thought it was the gas and the jet fuel, but it wasn't, you know, we were sort of prepared for that. It was the diesel without the diesel, the refineries can function. And it would have totally screwed up the economy. And so there was almost this like national security economic impetus for them to pay this ransom. And the other one I always think about is Baltimore. When the city of Baltimore got hit, I think the initial ransom demand was something around 76,000. It may have even started smaller than that and Baltimore stood its ground and didn't pay. But ultimately the cost to remediate was $18 million. It's a lot for the city of Baltimore. That's money that could have gone to public school, education and roads and You know, public health and instead it just went to rebuilding these systems from scratch and so a lot of residents in Baltimore were like, why the hell didn't you pay the $76,000? So it's not obvious, you know, it's easy to say don't pay because why you're funding their R. And D. For the next go round. Um but it's too often it's too complicated. </s><s>[INST] So on the individual level just like you know the way I feel personally from this attack, have you talked to people that were kind of victims in the same way I was but maybe more dramatic ways or so on? [/INST] You know, in the same way that </s><s>[INST] violence hurts people. How much is this hard people in your sense? And the way you researched it, [/INST] the worst ransomware attack I've covered on a personal level was an attack on a hospital in Vermont. And you know you think of this as like okay it's hitting their I. T. Networks, they should still be able to treat patients. But it turns out that cancer patients couldn't get their chemo anymore because the protocol of who gets what is very complicated and without it the nurses and doctors couldn't access it. So they were turning Chemo patients away, cancer patients away. one nurse told us, I don't know why people aren't screaming about this, that the only thing I've seen that even compares to what we're seeing at this hospital right now was when I worked in the burn unit after the boston marathon bombing. They really put it in these super dramatic terms. And last year there was a report in the Wall Street Journal where they attributed an infant death, uh, to a ransomware attack because a mom came in and whatever device they were using to monitor the fetus wasn't working because of the ransomware attack. And so they attributed this infant death um, to the ransomware attack now on a bigger scale, but less personal when there was the not Peta attack. So this was an attack by Russia on Ukraine. Um, that came at them through a supplier attacks, software company in that case that didn't just hit any government agency or business in Ukraine that use this tax software. It actually hit any business all over the world that had even a single employee working remotely in Ukraine. So it hit mirrors the shipping company but hit Fizer hit Fedex but the one I will never forget is Merc. It paralyzed Merck's factories. I mean it really created an existential crisis for the company. Merck had to tap into the CDCs emergency supplies of the Gardasil vaccine that year because their whole vaccine production line had been paralyzed in that attack. Imagine if that was going to happen right now to fight sir or Madonna or johnson and johnson, you know, imagine I mean that would really create a global cyber terrorist attack essentially. And that's almost </s> |
<s>[INST] beautifully put. So the funny thing is uh I've uh believe I closed the previous episode with the Darwin quote about the power of poetry and music and life. [/INST] I think your quote. And again, I only heard once was Darwin basically saying if I were to live life again next time I would read more poetry and something about art every week or something like that. </s><s>[INST] It's so interesting for somebody who studied uh life a very cold, I would say genetic level to say that yeah, the highest form of living is is the art. But like on that, which made me realize that you write poetry and I uh forced you or maybe convinced you somehow to uh to maybe share if it's possible, if it's okay. Some of uh the poetry you've written yourself in your life. [/INST] So, again, being greek, a lot of my poems have been pretty miserable. Uh I always like to say that it's very hard for me to write a poem or that what I'm happy and I just have to be in a state of deep despair in order to write poems. But the first poem I ever wrote was in uh english class. I was I'm greek, I grew up increase, but it was in a french high school and I was taking english as a foreign language. So the english teacher basically asked us to write a poem in english. So this is basically what, what I'm going to embarrass myself and read from my 16 year old self, many, many years ago, can you give a little </s><s>[INST] bit more context about who you were in this moment? So just [/INST] so, so here's what's really interesting in terms of growing up, how do we grow up? Um it's very difficult to grow up if you're in the same school going from one class to the other and all your friends know you're inside out. It's very difficult to change. It's very difficult to grow up because they have a certain set of expectations for who you are and for how you're going to behave. So in many ways we kind of tend to get set in our ways and not change very much. I think something that helped me grow up is that when I was 11 years old, I was a kid in Greece in primary school when I was 12 years old, I was a kid in Greece in a first year of high school. When I was 13, I was in France. So basically moved countries and schools. The next year I moved schools again, because it was a transition in the french educational system from one school to the next, the next year after that, my family moved to new york in a french high school there, and the next year after that I'm moving to Emmett. Uh so basically between 11 and 19, every single year I actually had the opportunity to grow, I was not held by people who knew me and I could reinvent myself or reshape myself or reshape my, you know, sort of personality, my emotions, my, you know, as I was growing up, especially in such a transformative time of a kid's life From 11 to 17. </s><s>[INST] Okay, first of all it's so powerful that you think of it that way. Did you think of it that way at the moment because it's kind of a source, you said an opportunity to grow, it's kind of suffering. I mean you're being torn away from the thing, you know, into the thing you don't know. [/INST] So when we moved from south France to new york, I was piste piste, I I was taking these long bike rides in the countryside, jumping in friends, swimming pools and I had all these wonderful friendships going downtown and just staying by the fountains in the dim lit streets of exam province in the south of France, it was magical. And suddenly I moved to new york city, a city of cement of ugliness, like trash in the streets and every corner is horrible snow everywhere. Having never seen snow, like real snow in my life, I moved from Athens to south France to sell in new york. So I was piste but um whether I saw it as an opportunity for growth, I don't think so I don't think that I was that self reflective. It was just only now I I I saw it like that probably pretty early on, but not during those transitions. So basically during the transition, I was just a kid being a kid, you know, and um, maybe the time that I started seeing that way was maybe when I decided to stay at MIT as a professor after having been there as a student. And I kind of saw the struggle of getting professors do not see you as a kid when they're your peers. And I was very flattered when one of my friends basically told me, oh, I remember you in recitation when you first asked me a question, I said, wow, this kid help pay attention and </s><s>[INST] they will be appear. [/INST] So, so it's, it's, you know, certainly my perception was that many of them could not see me as anything but a kid, but it turns out that some of them saw me as something different than a kid even before I was actually their colleague. So it's kind of an interesting place because what I like to say about it is that people treat you as equal no matter what stage and they respect you for what you say, not for who you are when you're saying it. And if I'm wrong, my students will tell me they will have no reservation to just be bluntly, you know, sorry, I don't agree with that. </s> |
<s>[INST] been people who've been afraid of even acknowledging the gaps. Of course, there's, uh, I guess a colleague of yours, Michael Sandel, with, uh, with tyranny and merit, there's, uh, interesting, rigorous ways to kind of challenge ways on the flip side of that where obsessing with merit can go wrong also. [/INST] Yes. Uh, you mentioned Michael Sandel. He's a, uh, a wonderful colleague and he's a wonderful friend. I've known him a long time. I think he makes very important, uh, arguments, uh, about, uh, meritocracy. Um, I disagree with, uh, some of the points that he makes about meritocracy. You lean towards the, the importance of meritocracy. I think that, uh, yes. I think that, I think that there are values and meritocracy extremely important that in fact, you know, the, the, the movement from, you know, feudalism, the movement from status, the, the, the, the idea of, you know, I don't care who your father or mother was. I don't care from what part of town you come from. I don't care what your last name is. I don't care what your skull or of your skin is. Show me what you can do. And then somebody sits down. Ok, I'll show you what you can do. You know what I can do and they show it you're in. I think there's a lot to that and you know, the impulse, the sentiments behind that I resonate with that. I think that there's a lot there. What I want to do is I want to get rid of those features in society that deprive people of the, what you need to develop yourself, you know, sometimes those are psychological. Sometimes that's you know, you're not around people who've done things that give you the idea that you can do things. I want to get rid of that, but the idea of, you know, people. Um, the idea, by the way of a- uh, you know, distinguishing, you know, this is excellent and the people who are excellent, you know, they're here. And then there are people who are, are they excellent? No, they're not excellent. They're good. Uh, I wouldn't, I wanna, I'm not gonna, you know, close my </s><s>[INST] eyes to that distinction. And, uh, uh, highlight that distinction and yet at the same time, maintain a sense that, uh, their basic worth as a human being is equal. [/INST] Yes. So, uh, you know, uh, was it run BMC? What are the rap groups? No, you know, we're all written down on the same list. We're all written down on the same list. Yes. We're, you know, uh, so I want to recognize our fundamental humanity. Um, I don't think that that, I think that one can recognize our fundamental humanity and one can also recognize as far as I'm concerned that, um, we all collectively should make sure that we, we do all that we can to prevent people from sinking below a certain level and being, you know, in misery, um, you know, all for that, but I want to be careful about some of the attacks that I hear on meritocracy. So some of the people, including again, I have all the respect in the world for, for, for, for, for, for Michael Sandelli to, you know, it talks about the, the, the arrogance of the winners. Okay. I want to be, you know, I, I don't want the winners to be arrogant. That's right. Luck has a lot to do with things. You know, you were, you, you didn't have any control over the circumstances in which you were born in two. You were lucky that you were born healthy and that you were born with a, you know, well-working mind. You didn't have anything to do with that. That was pure luck. There's some people who don't have that walk. So don't, you know, you know, don't be, you know, Mr. Big stuff, okay. So I'm, you know, I'm against that sort of arrogance. You know, I'm entitled as if, as if I taught myself how to read. No, you didn't teach yourself how to read. There was people who did all sorts of things for you and you don't even know it. Okay. So, you know, I want to, you know, get rid of the arrogance, uh, have, have decent humility on all for that at the same time, you know, um, I want to be careful about the problem of envy. I want to be prob, I want to be careful about the problem of resentment. I want to be, I want to be careful about, you know, I've heard, you know. So let's not have, let's not give a trophy to the person who wins the race. Because to give a trophy to, to the person who wins the race will make the person who they defeated feel bad. No, no, no. No, no, no, I don't want that. I want to give a trophy to the person who wins the race because I think it's a good thing to valorize the best. </s><s>[INST] Yeah. It's a, it's a kind of celebration of, um, this whole human project that we're on. Yes. It's celebrating the best. You mentioned your father several times, so let me just linger on that. What, uh, what have you learned from, what have you learned about life from your father? [/INST] There's, I've been just such a lucky person. I mean, I, I feel like I've just lived an absolutely charmed life. And I live, I mean, the work that I do is what I love doing. Um, I would pay to do what I am paid to do. </s><s>[INST] Yeah. [/INST] I mean, it's, it's, you know, it's, it's great. And, um, I've been, I've been fortunate in so many ways. And one way in which I've been fortunate is, uh, my parents, my parents, um, Rachel Spann Kennedy, Henry Harold Kennedy, my mother born in Columbia, South Carolina. My father from, uh, uh, New Orleans, Louisiana, they were refugees from the Jim Crow South. Uh, they were people who put their all into their children. Um, I have an older brother of a younger sister. All three of us know beyond, you know, beyond any controversy that we were loved and dearly loved by our parents and they were great people. My father, um, very interesting man, very independent minded. He was perfectly willing to go his own way. And, uh, I learned much from him, including I learned, I learned things from him, even when I ultimately disagreed with him. So for instance, again, to go back to his pessimism. Yeah, he was pessimistic, thoroughly pessimistic. Um, but he was also, he was also willing to change in certain ways. In fact, both my parents, I mean, one of the most important things that happened to my parents was that I'd say when I was, let's say 10 years old, I was born in 1954. So in 1964, in 1964, I think my parents would have taken the position that, um, you definitely never under any circumstances trust a white person. If a black person trusts a white person, that person is a fool. Do not trust white people. All right. They are not to be trusted. And, um, it's the highly, highly, highly unusual one who is not prejudiced. Okay. So white people are not to be trusted and, you know, by and large are going to be your enemy. All right. So let's just face that. That's, that's was their, their point of view. I'd say that, I'd say that 10 years later, that point of view had been leavened somewhat. Um, I think, and you know, you say, well, what happened in those 10 years? Well, certainly in my life, uh, one of the things that happen in those 10 years is I, I was a student in various schools and I had a series of teachers. I've had wonderful black teachers. I've also had wonderful white teachers and my parents paid attention to who my teachers were and how my teachers treated me. And I think that they were affected by the way in which there were white people who really helped me and were on my side and were thoroughly on my side. And I think that that experience, uh, changed my parents in their general view. They, you know, skeptical. Yeah, but they were, um, the, the, the, the possibility, the possibility of a white person genuinely being the friend of a black person that they, they, they, that became alive to them and I give them a lot of credit because they were, they were adults and, you know, for an adult to change, that's a big deal, but </s> |
<s>[INST] I set the goal of reading one book a week. I said a classic book, but really what I mean is a book that really challenges you and really makes you think. So I look forward to seeing sort of using Blinkist to help me review the books, actually also choose the books and maybe help others that are interested in following along with my reading to get deeper and deeper insights into these different books. I think my perspective is on many books that read are nonstandard. I get lost on a single quote here and there and it just kind of takes me down this whole tangent of thought, these ideas that get inspired and get sparked and then I just construct this whole world from a single quote sometimes. But that's what makes it interesting. It's a very subjective experience, like appreciating art, appreciating books and so on. Anyway, you can claim a special offer for savings in blinkist.com slash Lex. This is the Lex Friedman podcast. To support it, please check out our sponsors in the description and now, dear friends, here's Batul Kachar. What is the phylogenetic tree or the evolution tree of life and what can we learn by running it back [/INST] and studying ancient gene sequences as you have? I think phylogenetic trees could be one of the most romantic and beautiful notions that can come out of biology. It shows us a way to depict the connectedness of life and all living beings with one another. It itself is an ever-evolving notion. Biologists like visualizations. They like these graphics, these diagrams </s><s>[INST] and tree of life is one of them. [/INST] So the tree starts the common ancestor. It's actually the other way around. It starts from the branches. It starts from the tip of the branch, actually. And then, the further, depending on what you collected to build the tree. So depending on the branches, depending on what's on the tip of the branch and I will explain what I mean. The root will be determined by what is really sitting </s><s>[INST] on the tip of the branch of the tree. At the end, so we could study the leaves of the tree by looking at what we have today and then start to reverse engineer and start to move back in time to try to understand what the rest of the tree, [/INST] what the roots of the tree looked like. Exactly. tree itself, by just taking a few steps back and looking at the entire tree itself, can give you an idea about the connectedness, the relatedness of the organisms or whatever again you use to create your tree. There are different ways. But in this case, I'm imagining entire diversity of life today is sitting on the tips of the branches of this tree. And we look at biologists, look at the tree itself. We like to think of it as the topology of the tree to understand when certain organisms or their ancestry may have merged over time. And depending on the tools you use, you might use this </s><s>[INST] tree to then reconstruct the ancestors as well. And so what are the different ways to do the reconstruction? So you can do that at the gene level, or you could do it at the higher complex [/INST] biology level. So in which way have you approached this fascinating problem? We approached it in every way we can. So the gene could be protein, the product of the gene, or species, or could be even groups of species. It totally depends on what you want to do with your tree. If you want to understand certain past events, whether an organism exchanged a certain DNA with another one along the course of evolution, you can build your tree accordingly. If you rather use the tree to reconstruct or resurrect ancient DNA, which is what we do, then in our case, for instance, we do both gene, protein, and species because we want to compare the tree that we create using this different information. </s><s>[INST] Okay, well, let me ask you the ridiculous question then. So how realistic is Jurassic Park? Can we study the genes of ancient organisms? And can we bring those ancient organisms back? So the reason I ask that kind of ridiculous sounding question is maybe gives us context [/INST] of what we can and can't do by looking back in time. Yeah, so dinosaurs or all these mammals, at least for us, is the exciting thing already happened by the time we hit to larger organisms or to eukaryotes. </s><s>[INST] Oh, to you, the fun stuff is before we got to the mammals. [/INST] The fun stuff is what people think is boring, I think, the phase that's two different times in the geologic history. One is the first life, past origin of life, how the first life looked like. And the second is why do we think that over certain periods of geologic time, no significant innovation happened to the degree of leaving no record behind. </s><s>[INST] So what do we not have a record of? The fun stuff to you is after the origin of life, which we'll talk about, after the origin. Well, if they're single-cell organisms, the whole thing with a photosynthesis, the whole thing with eukaryotes and multi-cell organisms. And what else is the fun stuff? The whole oxygen thing which mixes in with the origin of life, there's a bunch of different inventions all that has to do with this primitive [/INST] kind of looking organisms that we don't have a good record of. So I will tell you the more interesting things for us. One is the origin of life or what happened right following the emergence of life. How did the first cells look like? And then pretty much anything that we think shaped the environment and was shaped by the environment in a way that impacted the entire planet. That enabled you and I to have this conversation. We have very little understanding of the biological innovations that took place in the past of this planet. We work with a very limited set of, I don't want to even say data because they are fossil records. So let's say imprints, either that comes from the rock and the rock record itself, or what I just described, these trees that we create and whatever we can infer about the past. So we have two distinct ways that comes from geology and biology and they each have their </s> |
<s>[INST] The propagation of DNA. But what do you make of this unfortunate fact that we are mortal? Do you ponder your immortality? Does it make you sad? [/INST] I ponder it it makes me sad that I shall have to leave um and not see what's going to happen next. Um If there's something frightening about mortality apart from sort of missing, as I said, something more deeply darkly frightening. It's the idea of eternity. But eternity is only frightening if you're their eternity, but before we were born, billions of years before we were born and we would effectively dead before we were born. As I think it was Mark Twain said I was dead for billions of years before I was born and never suffered the smallest inconvenience. That's how it's going to be afterwards after we leave. So I think of it as really eternity is a frightening prospect. And so the best way to spend it is under a general anesthetic, which is what it'll be </s><s>[INST] beautifully put. Richard is a huge honor to meet you to talk to you. Thank you so much for your time. [/INST] Thank you very much. </s><s>[INST] Thanks for listening to this conversation with Richard Dawkins and thank you to our presenting sponsor cash app. Please consider supporting the podcast by downloading cash app and using culex podcast. If you enjoy this podcast, subscribe on youtube review with five stars on apple podcast. Support on Patreon are simply connect with me on twitter. Elex Friedman and now let me leave you with some words of wisdom from Richard Dawkins, we are going to die and that makes us the lucky ones. Most people are never going to die because they're never going to be born. The potential people who could have been here in my place, but who will in fact never see the light of day outnumber the sand grains of Arabia. Certainly those unborn ghosts include greater poets than Keats, scientists greater than Newton. We know this because the set of possible people allowed by our DNA so massively exceeds the set of actual people in the teeth of these stupefying odds. It is you and I in our ordinary nous that are here we privileged few who won the lottery of birth against all odds. How dare we wind at our inevitable return to that prior state from which the vast majority have never stirred. Thank you for listening, and hope to see you next time. [/INST] </s> |
<s>[INST] do it. So it's [/INST] all about the context and </s><s>[INST] the situation. Um, [/INST] for example, working </s><s>[INST] in Northern Yemen, you [/INST] couldn't film for </s><s>[INST] five minutes if you [/INST] didn't have paperwork because you'd be taken away. So you have </s><s>[INST] to make sure you have all those permissions [/INST] ahead of time. 50 ft from Syria. </s><s>[INST] Um, I would love to talk at least a little bit about this film. Um First, can you high level, can you tell what this documentary is about? Yeah, [/INST] it was early in </s><s>[INST] um the Syrian [/INST] uprising and um we returned to the Syrian </s><s>[INST] Turkish border with a Syrian [/INST] american orthopedic surgeon who </s><s>[INST] is volunteering [/INST] operating on </s><s>[INST] refugees as they float across the border from Syria into Turkey. [/INST] Um, and it was an attempt at the time before. A lot of films had come out about the conflict to um really show again </s><s>[INST] um [/INST] the effects of the war on civilians. Um, you've heard </s><s>[INST] me echoed that sentiment [/INST] multiple times now, </s><s>[INST] but it it, you [/INST] know, people knew there was there was a major conflict in Syria, but didn't really understand the form that that was taking and the impact it </s><s>[INST] was having. And [/INST] so we we embedded into </s><s>[INST] the at the [/INST] time. It was the only </s><s>[INST] clinic [/INST] in Turkey that was </s><s>[INST] sanctioned by the Turkish [/INST] government um to </s><s>[INST] treat Syrian refugees. [/INST] Um, and so we filmed there with surgeons </s><s>[INST] as they operated [/INST] on more victims. </s><s>[INST] And we [/INST] also went into Syria into some of the camps as well. </s><s>[INST] So in this film [/INST] there's a man </s><s>[INST] who crosses the border every day to retrieve the wounded and fair them [/INST] safety and care. </s><s>[INST] And you also mentioned [/INST] about heroism </s><s>[INST] in the United States. Um, can you tell me [/INST] about this man and </s><s>[INST] just people like him, like what's the heroic [/INST] action in </s><s>[INST] some of these places that you've visited? [/INST] So, in that instance, you know, I thought of him as </s><s>[INST] the Turkish Schindler, right? [/INST] Because he was human being who um of </s><s>[INST] his own volition [/INST] volition. And no one was paying him to do this. </s><s>[INST] But [/INST] he was spending much of his time. He was just a local businessman who really saw the need in the camps </s><s>[INST] Right across the border, 10-K [/INST] away, and </s><s>[INST] and and he [/INST] saw the medical need in particular, </s><s>[INST] and how [/INST] hard it was to get people in desperate medical conditions across the border where there was a </s><s>[INST] clinic just [/INST] right across the border. But because of the security and the layers of security, um, they couldn't get out by themselves. So he </s><s>[INST] took it upon himself [/INST] as a Turkish person to build relationships with the Turkish guards, which was relatively easy. And </s><s>[INST] then he [/INST] built relationships with sort of the guards in the no man's land between </s><s>[INST] the Syrian guards [/INST] and sort of those who lived in the middle area. And then also with the Syrian guards at </s><s>[INST] the camp [/INST] and he would drive out there daily and bring them food, </s><s>[INST] right? [/INST] Talk him up and build relationships. And so every day he would bring these guards food and build relationships with them. And what that meant was eventually right. He had this </s><s>[INST] avenue of [/INST] access to and from the camps </s><s>[INST] and so he started using [/INST] it and </s><s>[INST] he would [/INST] dr this avenue of </s><s>[INST] access [/INST] through the three layers of guards each day and then they would open the gates for him </s><s>[INST] because he had made [/INST] himself trustworthy in their eyes. And he would receive </s><s>[INST] the [/INST] most desperate medical cases that were coming from all over Northern Syria, right to </s><s>[INST] receive medical treatment. [/INST] And he would, </s><s>[INST] as you see in the film, he [/INST] would ferry them into the back of </s><s>[INST] his car, right? [/INST] And then drive them to </s><s>[INST] the hospital [/INST] where they would receive operations and then </s><s>[INST] he would [/INST] bring them back if they wanted after </s><s>[INST] they had healed and [/INST] recovered back to Syria. If they wanted to return at post recovery and you know, he didn't get paid </s><s>[INST] for that, he [/INST] was spending his own money to do it because he saw </s><s>[INST] other human beings [/INST] in need and </s><s>[INST] it's like we were talking about [/INST] earlier, </s><s>[INST] that's heroic, [/INST] right? That's selfless. That's that's aspirational for me, right? Here's here's someone who is spending their time on the planet doing something of value </s><s>[INST] and good to other human [/INST] beings. </s><s>[INST] I mean, if you [/INST] draw parallels to Schindler, </s><s>[INST] I feel like [/INST] the fascinating thing </s><s>[INST] about [/INST] Schindler's that </s><s>[INST] he's [/INST] kind of a flawed human </s><s>[INST] and it's not the kind of human that does these [/INST] things usually, but you just </s><s>[INST] can't help it. [/INST] And that's like the basic humanity, </s><s>[INST] despite [/INST] who </s><s>[INST] you are, the basic [/INST] humanity shines through. I think that, you know, the whims of </s><s>[INST] war test [/INST] people in those ways, </s><s>[INST] right? They, they [/INST] ask of you things that you may not </s><s>[INST] even [/INST] know we're going </s><s>[INST] to be asked of you and [/INST] then it speaks to who, who you are fundamentally as a human being. They </s><s>[INST] reveal who you are as a [/INST] human being. Just as you </s><s>[INST] said. [/INST] Um </s><s>[INST] let me ask a kind of stupid technical [/INST] question </s><s>[INST] about publications and movies [/INST] and so on. I've been um </s><s>[INST] recently [/INST] becoming good friends with thomas Tall </s><s>[INST] who was the producer, his [/INST] company legendary, finding some </s><s>[INST] of the big sort of blockbuster [/INST] films and so on. And so </s><s>[INST] obviously money is part [/INST] of filmmaking. That's </s><s>[INST] interesting. But also the release of movies [/INST] and me as a consumer, </s><s>[INST] you know, [/INST] with netflix, with Youtube, </s><s>[INST] you know, [/INST] that's one </s><s>[INST] of the reasons I'm a huge fan of [/INST] Youtube is, </s><s>[INST] it's like out [/INST] in the open access, especially historical access, </s><s>[INST] like over time, [/INST] you can look back </s><s>[INST] years later if you pay some money, you can watch some of the great films ever made. [/INST] Um </s><s>[INST] Youtube hulu netflix, I don't know what other services that are. HBO paramount plus paramount plus. Um [/INST] anyway, there's </s><s>[INST] all these platforms [/INST] Spotify </s><s>[INST] now. [/INST] It's uh, I understand they want to </s> |
<s>[INST] It really feels open. [/INST] It's because it it truly is. Yes, </s><s>[INST] what about, I mean just like asking about some open world uh very different one is the world of either Grand theft auto or or Red Dead redemption. [/INST] Both love, I would put G. T. A. Three grand theft auto three up there with the landmark kind of. Usher in the open world when that comes out on the Playstation two even though there was G. T. A. One and two. This was an all new thing with the mobster storytelling. Uh Vice </s><s>[INST] it [/INST] was then Vice City is kind of a fast follow which uh Could be my favourite one. </s><s>[INST] I [/INST] loved all the Grand theft, I think they're really phenomenally well made games. Same with Red Dead, the Red Dead Redemption one could be my favorite story. Like highly recommend finishing that game. </s><s>[INST] So you like both the story, you like the grittiness of the because they have they have a bit of the like I guess if you like the fall fall out there's the humor, the, I don't know, I don't know what it is, it's the lighthearted humor of it but also the brutality of human nature is in there too. But it's like uh and also some of the fun they create with the music when you drive and stuff like that, they create, they create a world, there's a tone, there's a very strong, [/INST] very strong tone. Um you know the satire on the world is just so well done. The gameplay is great. Um I think they've just done a a phenomenal job. </s><s>[INST] Is there any others that pop to mind [/INST] portal portal. Yeah </s><s>[INST] that's that's another weird creation. I [/INST] could just sit here and list games forever. </s><s>[INST] I'm enjoying this Heart [/INST] Stones a game. I love, I love all the time, like sports college football and say football was my favorites. Like I would say this is a great role. </s><s>[INST] You would actually keep getting [/INST] Role. It's a role playing game because I have all these characters, I have like, you know, 60 characters and they're all leveling up and then I have to play them and then the college ones like college football, they graduate so you lose your players and then they stopped making this series and I know the folks at ea and they will say I have bugged them when they're doing it. So it's finally coming back. </s><s>[INST] Nice. What would you say is the, is the, is the greatest sports game all the [/INST] time. Well, it's inside of football. I have to pick the year </s><s>[INST] versus [/INST] Oh yeah, yeah, there's more teams get to college, you know, fight song, there's more pageantry and the players turn over there only there for four seasons. So you have to the so you know, it's that there's it's more dynamic </s><s>[INST] so you like variety. So [/INST] What was the last 1, 2014 maybe it was </s><s>[INST] and you don't like FIFA and [/INST] like, look, FIFA is incredible. Just look, I'm a college football fan. They give you that fantasy if you like, if you like european football slash soccer. FIFA is incredible. I love that game too. </s><s>[INST] Have you been paying attention to the game design of that world, of those worlds [/INST] and the thing, people, I think with those kind of games, it is really like, or racing games Forza put up their love Forza, um play them all when you have to recreate something that's real in the real world. So it's cars or sports games, everybody knows how it should work. That's that's a really difficult task when people know how it should work, then you're gonna balance it for single player, the multiplayer parts of it. Um very, very competitive and, you know, in many respects, you're forced to put out a new version every year and I say forced in quotes because they're, you know, a count them as big updates. Um but it's a very, it's a much more difficult development process than I think. Um people understand and how hard those teams work and know a lot of people who do it and I think they just do, I've enjoyed them all. I buy madden every year. </s><s>[INST] So yeah, every single year. Yeah, they do refresh it, there's a feeling of freshness. I don't know what that is. Yeah. [/INST] Look, there's been years where it feels like less was done and more was done, but I, I enjoy it every year. </s><s>[INST] Yeah. Uh what is a perfectly productive day in the life of todd, howard look like, so uh maybe not perfectly, but just like a perfectly average productive, what, what are you, a morning person? Union person is a chaos is a pretty regular. Uh [/INST] I'm in a good, I'm in a good flow right now I'm still doing a lot of stuff. So there's things I'm like executive producing and then you know star field, I'm directing. So I sort of view that as that's an everyday thing. Um fortunately get to do a lot of stuff from, look at the tv show we're making and um this indiana jones game that's being developed at machine games, we have to look at that. Um but you know, the best really day or where I feel it's fulfilling is um get to play some of a game, the game will say Star Field, get to play from the star field, look at the problem set of what it is doing and then get in a room with the other developers that I work closely with and we solve that problem together. So that's the most rewarding thing when you can say, okay, what do we want this to do? What's the, what's the real player experience we want, what are all the pieces in front of us where you, you know, the actual tangible pieces as opposed to the beginning. The pie in the sky part is always fun, but it's like anything is possible that's fun, but it's not rewarding in the same way because you haven't solved something. Whereas these are the elements you have to play with. How do we make this all work together and you come out of at the end of the day, like now that feels great. </s> |