text
stringlengths 28
334k
|
---|
<s>[INST] Yeah. So you can have this kind of intuition that our civilization, You said culture, but you really mean the spirit of the civilization, the entirety of the civilization may not exist for long. So what you can you, can you untangle that? What's your intuition behind that? So you kind of offline mentioned to me that the industrial revolution was kind of uh the moment we agreed to accept the offer, sign on the paper on the dotted line with the industrial Revolution, we doomed ourselves. Can you elaborate on that? [/INST] This is suspicion. I of course don't know how it plays out, but it seems to me that um, in a society in which you'll leverage yourself very far over an entropic abbess without land on the other side, it's relatively clear that your county levels at some point going to break down into this anthropic abbess and you have to pay the bill. </s><s>[INST] Russia is my first language. And I'm also an idiot. [/INST] Uh </s><s>[INST] this is just to apes uh, instead of playing with [/INST] that </s><s>[INST] are playing with the banana, trying to have fun by talking okay, uh anthropic what and what's anthropic [/INST] anthropic anthropic. And so and tropic in the sense of entropy and </s><s>[INST] entropic [/INST] guys. So this and </s><s>[INST] and tropical, it was the other word [/INST] you have this, what's that? It's a big abyss. Yes. And tropical bit. So many of </s><s>[INST] the things you say are [/INST] poetic, it's kind of </s><s>[INST] breaking my brain. [/INST] It's </s><s>[INST] MS Brown which [/INST] which </s><s>[INST] makes you do more [/INST] poetic. </s><s>[INST] Uh Wittgenstein would be proud. So in tropic abyss. Okay, let's let's rewind then the Industrial Revolution. So how does that get us into the entropic abyss? [/INST] Mm So in some sense we burned 100 million years worth of trees to get everybody plumbing. And the society that we had before that had a very limited number of people. So basically since zero Bc we hovered between 304 100 million people. And this only changed with the enlightenment and the subsequent Industrial Revolution. And in some sense the enlightenment freed our rationality and also freed our norms from the pre existing order. Gradually it was in process that basically have been feedback loop. So it was not that just one caused the other. It was a dynamic that started and the dynamic work by basically increasing productivity to such a degree that we could feed all our Children. And I think the definition of um poverty is that you have as many Children as you can feed before they die which is in some sense the state that all animals on earth are in </s><s>[INST] the definition of poverty is having enough. [/INST] So you can have only so many Children as you can feed. And if you have more, they die. And in our societies, you can basically have as many Children as you want. They don't die. Right? So, uh, the reason why we don't have as many Children as we want us because we also have to pay a price in terms of we have to insert ourselves in the lower source of threat. Um, as well, if you have too many. So basically everybody in the under middle and lower upper class has only a limited number of Children. Because having more of them would mean big economic hit to the individual families. Because Children, especially the US super expensive to have. And you only are taken out of this if you are basically super rich or if you're super poor, if you're super poor, it doesn't matter how many kids you have because your status is not going to change. And these Children are largely not going to die of hunger. </s><s>[INST] So how does this lead this to self destruction? So there's a lot of unpleasant properties about this process. [/INST] So basically what we try to do is we try to let our Children survive even if they have diseases like um, I would have died. And before my mid twenties, without modern medicine and most of my friends would have as well. So many of us wouldn't live without the advantages of modern medicine and modern industrialized society, we get our protein largely by subduing the entirety of nature. Imagine there would be some very clever microbe that would live in our organisms and would completely harvest them and change them into a thing that is necessary to sustain itself. And it would discover that, for instance, brain cells are kind of edible, but they're not quite nice. So you need to have more fat in them and you turn them into more fat cells. And basically this big organism would become a vegetable that is barely alive and it's going to be very brittle and not resilient when the environment changes. </s><s>[INST] But some part of that organism, the one that's actually doing all the using of the there'll still be somebody thriving. [/INST] So it relates back to this original question, I suspect that we are not the smartest thing on this planet. I suspect that basically every complex system has to have some complex regulation. If it depends on feedback loops. And so for instance, it's likely to that we should describe a certain degree of intelligence to plans. The problem is that plants don't have a nervous system. So they don't have a way to telegraph messages over large distances almost instantly in the plant. And instead they will rely on chemicals between adjacent cells, which means the signal processing speed depends on the signal processing with the rate of a few millimeters per second. And as a result, the if the plant is intelligent, it's not going to be intelligent. Similar time scales. </s><s>[INST] The building puts the time scale is different. So you suspect we might not be the most intelligent but were the most intelligent and this time in our time scale. [/INST] So basically, if you would zoom out very far, we might discover that there have been intelligent ecosystems on the planet that existed for thousands of years and almost undisturbed state. And it could be that these ecosystems actively related the environment. So basically change the course of the evolution visit this ecosystem to make it more efficient and less brittle. </s> |
<s>[INST] can be a dreamer and you can be a dreamer in a rural little village and then that has ripple effects throughout the entire country, young kids growing up, you know, I want to be the next [/INST] X </s><s>[INST] whatever and it doesn't have to be, you know, the next steve jobs that, that seems really far far away [/INST] all levels. It's at all levels. You you create local heroes because because, because representation matters right, so and we are so badly in need of that. And so, um, so that's what all the things that have been stolen from us as long as things remain the same. So lex once I found out that basically at the end of the day, the answer is economic freedom and that when it comes to that the indexes economic indexes that measure that whether it's the doing business index ranking of the World Bank or the fraser, economic freedom index of the Heritage Foundation. When you look at all of those um indexes and others, what do they have in common one after another. They show you that it is harder to do business in almost anywhere in africa than it is per se, anywhere in Scandinavia. So it is telling you that Scandinavian nations that socialist americans tend to love so much and take as an example over there too, they're showing you that they don't understand what's going on really in Scandinavia, that Scandinavia is more capitalist, Scandinavian nations are more capitalist than almost any sub Saharan african nations. </s><s>[INST] Ultimately, the political systems actually don't even matter nearly as much as the private sector being able to operate the machinery of capitals. [/INST] There you go. There you go, There you go. And it's almost like, like I said, it's almost like its own little widget within, within it, you can have whatever type of society you want to practice you want to exercise at whatever level you want to. But if you're serious about becoming a low amid a middle to high income nation, there is no other pathway that we know of at this point. And you know what made me super excited about that beyond Having finally found my answer, I have to tell you when I found that answer, I literally fell to my knees, it was the type of feeling that, you know, if something is not well with you, whoever it's physical or mental, something is not well you're not well and you go around and you go to the so called specialist, some of them, you know, but you you're going around for years, going around trying to get help for your ailment and here we don't know here they tell you things that you can't tell why, but you just know it's not true and it's it's going on for years after year after year. And finally you meet this one person and boom, it's there not only the liberation, but also this whole new world that comes with it, You know, I'm still I'm still ill, but guess what? There's a path forward. We know that I'm gonna have a lot of work to do. But there's hope. Yeah, </s><s>[INST] you're the beacon of hope actually for a lot of people in that part of the world. And that's those beacons are actually really necessary. So not only is there hope, but you can become, I mean the beacon for your people, your your your home, this this power that you see that you feel all around to become uh to escape the feeling of being trapped. Is there a device you can give to people that to uh young girls and boys dreaming somewhere in africa how to change the world. [/INST] That's right. And by the way, I want to say there are bigger beacons, There are better beacons than me. I just happened to be someone who has the chance of talking to you right now. Uh and one of my goals is to open the same doors that were opened for me because together our voice, there's such amazing stories out there and um so bigger Beacons, better Beacons out there. one thing here for me, the reason why I do what I'm doing right now and it's almost to the point of self destructing my own health. I feel invested with such the mission of I have been afforded the truth. So it is my moral duty to try to take it around. I know I sound people sometimes I say when I listen to it, I feel like I'm I'm talking to a to a priest and I'm like because the gospel received. So anyway, but the thing is lex who tells you these things to this day, when they talk about the poverty of Africa, what do they talk about? Their sitting there telling you? Oh yes, because of Cronyism is because of race, racism is because of imperialism is because they're stealing, you know, raw material, blah, blah blah. Is any of those called, you know, like guilty to some level of where we are today, one of maybe part of the reason where we are today, maybe, maybe is that the only reason or the overwhelming reasons No, is that unsurmountable. Absolutely not. So for me don't stay in that place of um, that steals and robs you of your agency. So, so I think it's important for people to get the right diagnosis as to why we are where we are. Because what you and I just talked about the mainstream does not talk about this when they even talk about africa in terms that, you know, are not the usual suspect of, oh, famine is building over there, wars building over here. Oh, we're having Ebola is coming all of that stuff. Even when they were talking about the monkey pox, which at first, you know, um, in this wave, it started with white people in europe. Well even in many newspapers, you pull out it's black people with monkeypox on their on their skin. I'm like, wait a second. This time around, we did not start with us. So why are you always showing us when it's right now happening to white people? You know? So, so all of that is happening. So for me, the thing is We, the world simply right now does not have the right diagnosis as to why this continent right now, despite all of its riches, because Lord knows it's got riches. Starting with its young population, 75% of the population of my country is below the age of 25 years old. So when we're talking, I know we're talking about, you know, repopulation. You know, it's important we're gonna have to go for that, Maybe you'll get me going about convention. I don't know. But anyway, um, so here my point is a we need the right diagnosis as to why this continent is the poorest continent in the world despite its which is starting with its young people over natural resources, diversity in land, people, cultures, languages, everything that make that make for great ingredient for for awesomeness. Despite all of that, we are the poorest region in the world. People need to know that the reason why that is It's because we also happen to be the most overrated, overregulated region in the world at the end of the day with Africa as and I dare to say Africa here and treated as one. We are 54 countries. 55 depending how you count. Yet. We almost for a tiny minority of these countries. We almost all lack one of the most crucial freedoms that they are. If you are serious about prosperity building, we lack economic freedom </s> |
<s>[INST] we can get with our bio bodies. You carry a little bit of them in you, in some sense. Yeah, yeah, yeah. Do you miss them? [/INST] You miss your mom and dad? </s><s>[INST] Of course, of course. What did you learn about life from them? [/INST] If it can take a bit of a tangent? So many things, for starters, my fascination for math and the physical mysteries of our universe, you got a lot of that from my dad, but I think my obsession for really big questions and consciousness and so on, that actually came mostly from my mom. And what I got from both of them, which is a very core part of really who I am, I think is this feeling comfortable with not buying into what everybody else is saying, doing what I think is right. They both very much just did their own thing and sometimes they got flack for it </s><s>[INST] and it did it anyway, it did it anyway. That's why you've always been an inspiration to me, that you're at the top of your field and you're still willing to tackle the big questions in your own way. You're one of the people that represents MIT best to me. You've always been an inspiration in that. So it's good to hear that you got that [/INST] from your mom and dad in a way. Yeah, you're too kind, but yeah, I mean, the good reason to do science is because you're really curious, you don't want to figure out the truth. If you think this is how it is and everyone else says, no, no, that's bullshit and it's that way, you know, you stick with what you think is true. And even if everybody else keeps thinking it's bullshit, there's a certain, I always root for the underdog. I wouldn't watch movies. And my dad, one time, for example, when I wrote one of my craziest papers ever, talking about our universe ultimately being mathematical, which we're not going to get into today, I got this email from a quite famous professor saying, this is not only a bullshit, but it's going to ruin your career. You should stop doing this kind of stuff. I sent it to my dad. Do you know what he said? What did he say? He replied with a quote from Dante. He said, follow your own path and let the people talk. Go, dad. This is the kind of thing. He's dead, but that attitude is not. </s><s>[INST] Do you know what he said? How did losing them as a man, as a human being, change you? How did it expand your thinking about the world? How did it expand your thinking about, you know, this thing we're talking about, which is humans creating another living, [/INST] sentient, perhaps, being? I think it mainly did two things. One of them just going through all their stuff after they had passed away and so on, just drove home to me how important it is to ask ourselves, why are we doing these things we do? Because it's inevitable that you look at some things they spent an enormous time on and you ask, in hindsight, would they really have spent so much time on this? Would they have done something that was more meaningful? So I've been looking more in my life now and asking, why am I doing what I'm doing? And I feel it should either be something I really enjoy doing, or it should be something that I find really, really meaningful because it helps humanity and none of those two categories. Maybe I should spend less time on it, you know. The other thing is dealing with death up and personal like this, it's actually made me less afraid even less afraid of other people telling me that I'm an idiot, you know, which happens regularly. And just, I'm gonna live my life, do my thing, I'm gonna live my life. And it's made it a little bit easier for me </s><s>[INST] to focus on what I feel is really important. What about fear of your own death? Has it made it more real that this is, [/INST] that this is something that happens? Yeah, it's made it extremely real. And I'm next in line in our family now, right? Me and my younger brother. But they both handled it with such dignity. That was a true inspiration also. They never complained about things, you know, when you're old and your body starts falling apart, it's more and more to complain about. They looked at what could they still do that was meaningful and they focused on that rather than wasting time. See, talking about or even thinking much about things they were disappointed in. I think anyone can make them self-depressed if they start their morning by making a list of grievances. Whereas if you start your day with a little meditation and just the things you're grateful for, </s><s>[INST] you basically choose to be a happy person. Because you only have a finite number of days. You should spend them being grateful. Well, you do happen to be working on a thing which seems to have potentially some of the greatest impact on human civilization of anything humans have ever created, which is artificial intelligence. This is on the both detailed technical level and in a high philosophical level you work on. So you've mentioned to me [/INST] that there's an open letter that you're working on. It's actually going live in a few hours. I've been having late nights and early mornings. It's been very exciting actually. In short, have you seen Don't Look Up, the film? Yes, yes. I don't wanna be the movie spoiler for anyone watching this who hasn't seen it. But if you're watching this, you haven't seen it, watch it. Because we are actually acting out. It's life imitating art. Humanity is doing exactly that right now, except it's an asteroid that we are building ourselves. Almost nobody is talking about it. People are squabbling across the planet about all sorts of things which seem very minor compared to the asteroid that's about to hit us, right? Most politicians don't even have this on the radar. They think maybe in 100 years or whatever. Right now, we're at a fork on the road. This is the most important fork humanity has reached and it's over 100,000 years on this planet. We're building effectively a new species. It's smarter than us. It doesn't look so much like a species yet because it's mostly not embodied in robots, but that's a technicality which will soon be changed. And this arrival of artificial general intelligence that can do all our jobs as well as us and probably shortly thereafter super intelligence which greatly exceeds our cognitive abilities, it's gonna either be the best thing ever to happen, the humanity or the worst. I'm really quite confident that there is </s> |
<s>[INST] Yeah. Like all the magical moments I can remember with robots. Well, first of all just visiting your lab seeing Alice but also spot many when I first saw a spot many in person and hung out with him. Her uh It I don't have trouble jen. During robots. I feel robotics. People really always say it. I kind of like the idea that it's a her or him? Uh There's a magical moment but there's no touching. Uh I guess the question I have. Have you ever been um like have you had a human robot experience where a like a robot touched you? And like it was like wait like was there a moment that you've forgotten that a robot is a robot and like the anthropomorphic is a shin stepped in and for a second you forgot that it's not human. [/INST] I mean I think when you're in on the details then we of course anthropomorphized our work with atlas, but in, you know in verbal communication and the like I think we were pretty aware of it as a machine that needed to be respected. I actually I worry more about the smaller robots that could still move quickly if programmed wrong. And uh and we have to be careful actually about safety and the like right now and that if we build our robots correctly, I think then those, a lot of those concerns could go away and we're seeing that trend. We're seeing the lower cost, lighter weight arms. Now that could be fundamentally safe. Um I mean I do think touch is so fundamental. Ted Edelson is is great. He's a perceptual scientist at MIT. Uh and he studied vision most of his life and he said uh when I had kids, I expected to be fascinated by their perceptual development. But what really what he noticed was felt more impressive, more dominant was the way that they would touch everything and lick everything and pick things up on their tongue and whatever. And he said uh watching his daughter uh convinced him that actually he needed to study tactile sensing more. So there's something very important. I think it's a little bit also of the passive versus active part of the world, right? You can passively perceive the world. Um but it's fundamentally different if you can do an experiment, right? And if you can change the world and you can learn a lot more than a passive observer. So you can in dialogue. That was your initial example. You could have an active experiment exchange. But I think if you're just a camera watching youtube, I think that's very different problem than if you're robot that can apply force and touch. All right. I think it's important. </s><s>[INST] Yeah, I think it's just an exciting area of research. I think you're probably right that this hasn't been under research. It's uh to me as a person who is captivated by the idea of human robot interaction. It feels like such a rich opportunity to explore touch. Not even from a safety perspective, but like you said, the emotional too. I mean, safety comes first. Uh but the next step is like, you know, like a real human connection even in the world, like even in the industrial setting, it just feels like it's nice for the robot. I don't know. You know, you might disagree with this, but because I think it's important to see robots as tools often, but I don't know, I think they're just always going to be more effective once you humanize them. Uh like it's convenient now to think of them as tools because we want to focus on the safety, but I think ultimately to create like a good experience for the worker for the person, there has to be a human helmet. I don't know for me, I it feels like like an industrial robotic arm would be better if as a human element. I think like rethink robotics had that idea with Baxter and having eyes and so on having. I don't know, I'm a big believer in that. [/INST] It's not my area, but I am also a big believer. </s><s>[INST] Do you have an emotional connection to Alice? Yeah. Like do you miss him? I [/INST] mean, yes, I, I I don't know if I had more so than if I had a different science project that I worked on super hard, right? But um, yeah, I mean the, the robot, we basically had to do heart surgery on the robot in the final competition because we melted the core. Um, and uh, and yeah, there was something about watching that robot hanging there. We know we had to compete with it in an hour and it was getting it guts ripped out. Those </s><s>[INST] are all historic moments. I think if you look back like 100 years from now. And yeah, I think there's an important moments in robotics. I mean these are the early day, you look at like the early days of a lot of scientific disciplines, they look ridiculous. That's full of failure. But it feels like robotics will be important in the coming 100 years and these are the early days. So, so I think a lot of people are look at a brilliant person such as yourself and and are curious about the intellectual journey they've took. Um is there Maybe three books technical fiction, philosophical that had a big impact in your life that you would recommend? Perhaps others reading? [/INST] Yeah, so um I actually didn't read that much as a kid but I read fairly voraciously now. Um there are some recent books that if you're interested in this kind of topic, like a I superpowers by kai fu lee is just a fantastic read. You must read that Yuval Harari, just I think that can open your mind. Um Sapiens Sapiens as the first one, Homo deus is the second. Yeah, I think we mentioned The Black Swan by Taleb, I think that's a good sort of mind opener. I actually um so, so there's maybe a more controversial recommendation I could give. Great, well I don't love so in some sense it's it's so classical, it might surprise you, but I actually recently read um mortimer Adler's how to read a book not so long, it was a while ago, but um some people hate that book. I loved it. I think we're in this time right now where um boy we're just inundated with research papers that you could read on archive with LTD peer review and just this wealth of information. Um I don't know, I think the passion of what you can get out of a book, a really good book or a really good paper, if you find it, the attitude, the realization that you're only going to find a few that really are worth all your time. Um, but then once you find them, you should just dig in and and and understand it very deeply and it's worth, you know, marking it up and and uh you know, having the hard copy writing in the side notes, side margins. Um I think that was really, thank you. I read it at the right time where I was just feeling just overwhelmed with really low quality stuff, I guess. Um and similarly, uh I'm giving more than three now, I'm sorry if I've exceeded my quota, </s> |
<s>[INST] By the way, good time to mention that your Twitter is one of the greatest Twitters of all time, so people should follow you. [/INST] Well, Lex Friedman has one of the greatest podcasts of all time. You guys should listen to the Lex Friedman podcast, which you may be doing, right? </s><s>[INST] Which you may be doing right now. [/INST] Yes. Yes. Yeah. </s><s>[INST] Well, thank you, so- What was the term again? [/INST] Sorry, genomic- So I call it genomic, not resurrection, but genomic reincarnation, okay? So here's the concept. You may be aware that you can synthesize strands of DNA, okay? There's sequencing of DNA, which is reading it, and synthesizing DNA, which is creating strands of DNA. What's interesting is you can actually also do that at the full chromosome level for bacterial chromosomes. Remember that thing I was saying earlier about the minimum life form that Craig Venter made? So people have synthesized entire bacterial chromosomes and they work. They can literally essentially print out a living organism, all right? Now, when you go from bacteria to eukaryotes, which are the kingdom of life that we're part of, right? Yeast are part of this kingdom and so on. It becomes harder because the chromosomes are more complicated. But folks are working on eukaryotic chromosome synthesis. And if you spot me that sci-fi assumption that eventually we'll be able to take your genome sequence and just like we can synthesize a bacterial chromosome, we can synthesize not just one eukaryotic chromosome, but your entire complement of chromosomes in the lab, right? Because you have 23, 46, whatever you take the pairs. What you can do is potentially print somebody out from disk, reincarnate them insofar if your sequence determines you. And you can argue with this because there's epigenetics and other stuff, okay? But let's just say at a first order, your DNA sequence is Lex. You can sequence that, okay? You can do full genome sequencing and log that to a file. Then here's the, you know, the karma part. Your crypto community where you've built up enough karma among them. If when you die, your karma balance is high enough. They will spend the money to reincarnate the next Lex who can then watch everything that happened in your past life. And you can tell them something. Everything I described there, I mean, if you spot me, eukaryotic chromosome synthesis, that's the only part that like, you know, I think will be possible, right? Folks are working on it. I'm sure someone will mention it. It's essentially a clone. It's like a clone, right? </s><s>[INST] But it is you in a different time. You're in a different time, [/INST] but you don't unfortunately have the memories. Well, you could probably watch the digest of your life and it would be pretty interesting, right? </s><s>[INST] I mean, Yeah, the, you know, that's actually a process for psychology to study. If you create a blank mind, what would you need to show that mind to align it very well with the experiences, with the fundamental experiences that define the original version, such that the resulting clone would have similar behavior patterns, worldviews, perspectives, feelings, all those kinds of things. Potentially, right? [/INST] Including sadly enough traumas and all that. Or what have you, right? But basically just like in a very simple version of it, you know, by the time one is age 20 or 30 or something in your 20s, you'll sort of learn your own personal operating system. You'll be like, oh, alcohol really doesn't agree with me or something like that. You just by trial and error, you know, things that are idiosyncratic to your own physiology. You're like, oh, you know, I'm totally wrecked if I get seven hours of sleep versus nine hours or whatever it is, right? People will have different kinds of, you know, things like this. That manual can be given to your next self. So like, you can go, don't do this, do this, don't do this, do this, right? To some extent, personal genomics already gives you some of this where you're like, oh, I'm a caffeine nun, you know, or a slow metabolizer. Oh, that explains X or Y, you know? Or I have a weird version of alcohol dehydrogenous. Oh, okay, that explains, you know, my alcohol tolerance. So, you know, this is part of the broader category of what I call practical miracles, right? So it's longevity, it's genomic reincarnation, it is restoring sight, and it is curing deafness with, you know, the, you know, artificial eyes and artificial ears. It is the Super Soldier Serum, did I show you that? So like, Maestad and Nel, a tweet about this. Basically, X-Men are real. So here is a study from any GM from several years ago. Okay, what is this, this is like the mid-2000s. This was in 2004, okay, so it's now 17 years later, probably, this is almost certainly a teenager by now. So this kid basically was just totally built. Yeah. Okay, extraordinarily muscul- </s><s>[INST] Like very muscular at a very young age. [/INST] Yes, so the child's birth weight was in the 75th percentile, he appeared extraordinarily muscular, with protruding muscles in his thighs, motor and mental development has been normal. Now, at four and a half years of age, he continues to have increased muscle bulk and strength. And so, essentially, Maestad mutation associated with gross muscle hypertrophy in a child. So this is like real-life X-Men, okay? And- </s><s>[INST] There's pictures of animals. [/INST] Yes, this is a company called Variant Bio that is looking at people who have exceptional health-related traits, and is looking for essentially this kind of thing, but maybe more disease or whatever related, right? For example, people who have natural immunity to COVID, understanding how that works, perhaps we can give other people artificial immunity to COVID, right? If you scroll up, you see my kind of tweet, Super Soldier Serum is Real, where it's like, wild-type mouse in a Maestad null, and look at the chest on that thing. You see the before and after. Wow. Okay, this is what's possible, you know, this could be us, but you're regulating, you know, right? You're not saying like, this could be us, but you play. This could be us, but the FDA regulating, right? </s> |
<s>[INST] it. What kind of advice could you give to somebody in high school right now or maybe early college who's curious about programming and feeling like the world is changing really quickly here? What kind of stuff to learn? What kind of stuff to work on? Should they finish college? Should they go work at a company? Should they build a thing? [/INST] What do you think? What do you think? Well, so, I mean, one of the things I'd say is that you'll be most successful if you work on something you're excited by, and so don't get the book and read the book cover to cover and study and memorize and recite and flashcard and go build something. Go solve a problem. Go build the thing that you wanted to exist. Go build an app, train a model, go build something and actually use it and set a goal for yourself. And if you do that, then there's a success, there's the adrenaline rush, there's the achievement, there's the unlock that I think is where if you keep setting goals and you keep doing things and building things, learning by building is really powerful. In terms of career advice, everybody's different. It's very hard to give generalized advice. I'll speak as a compiler nerd. If everybody's going left, sometimes it's pretty cool to go right. Yeah. And so just because everybody's doing a thing, it doesn't mean you have to do the same thing and follow the herd. In fact, I think that sometimes the most exciting paths through life lead to being curious about things that nobody else actually focuses on, right? And it turns out that understanding deeply parts of the problem that people want to take for granted makes you extremely valuable and specialized in ways that the herd is not. And so again, I mean, there's lots of rooms for specialization, lots of rooms for generalists. There's lots of room for different kinds and parts of the problem, but I think that it's, just because everybody's doing one thing </s><s>[INST] doesn't mean you should necessarily do it. And now the herd is using Python, so if you want to be a rebel, go check out Mojo and help Chris and the rest of the world fight the arch nemesis of complexity, because simple is beautiful. There you go. Because you're an incredible person. You've been so kind to me ever since we met. You've been extremely supportive. I'm forever grateful for that. Thank you for being who you are, for being legit, for being kind, for fighting this really interesting problem of how to make AI accessible to a huge number of people, [/INST] huge number of devices. Yeah, well, so Lex, you're a pretty special person too, right? So I think that one of the funny things about you is that besides being curious and pretty damn smart, you're actually willing to push on things, and I think that you've got an agenda to make the world think, </s><s>[INST] which I think is a pretty good agenda. It's a pretty good one. [/INST] Thank you so much for talking to me, Chris. </s><s>[INST] Yeah, thanks, Lex. Thanks for listening to this conversation with Chris Ladner. To support this podcast, please check out our sponsors in the description. And now, let me leave you with some words from Isaac Asimov. I do not fear computers. I fear the lack of them. Thank you for listening, and hope to see you next time. [/INST] </s> |
<s>[INST] are you Satoshi. No, [/INST] no, no, I don't have that kind of ability. I really don't. I do other things. </s><s>[INST] Speaking of Satoshi engaged theory, you've mentioned brian keating. That you may be releasing a geometric unity paper this year or some other form of additional material. The topic. What is your thinking around this? What's the process you're going through now? Well, it's very trained this. [/INST] I used April 1 to try to start a tradition which I hope to use to liberate mankind. Yeah, the tradition is that at least one day a year, you should be able to say heretical things and not have Jack Dorsey boot you off or Mark Zuckerberg, your provo shouldn't call you up and say, what did you say? We need at some level to have a jubilee from centralist control. And so my my hope is that you know what the tradition is in America something a baby boomer did twice impeachment. That's </s><s>[INST] very funny. Uh [/INST] Anyway um So what I'm I'm not a baby boomer but as an ex er I thought about whether or not April one would be a good date on which to release a printed version of what I already said in lecture form. Because I think it's hysterically funny that the physics community claims that it can't decode </s><s>[INST] video election. Yeah it must be paper [/INST] and you know what? There will be a steady stream of new complaints up until the point that they fitted into a narrative that they like. Um yeah I'm thinking about April one as a date in which to release a document and it won't be perfectly complete but will be very complete. And then they'll try to say it's wrong or you already did it or no, that was done. But what we just did on top of it is brilliant. Or it doesn't match experimental. Who knows what they'll go through all of their usual nonsense. It's time to go, </s><s>[INST] is there still puzzles in your own mind? They need to be figured out for you to try to put it on paper. I mean those are different mediums, right? [/INST] What's a great question. I did not count on something that turns out to be important when you work on your own outside of the system for a long time. You probably don't think you're going to be doing this as a 55 year old man and I have been so long outside of math and physics departments and I've been occupied with so many other things as you can see that the old idea that I had was if I always did it in little pieces then I was always safe because it wouldn't be steerable. And so now those pieces never got assembled completely. In essence, I have all the pieces and I can fit them together, but there's probably a small amount of glue code. There are few algebraic things. I've forgotten how to do. I may or may not figure them out between now and April one, but it's pretty complete, </s><s>[INST] but that's the positive kind of uh struggling to now figure out to get it all [/INST] on the same </s><s>[INST] and the glue together, [/INST] I can't tell you whether the theory is correct or incorrect, but like, you know, for example, there's what's the exact form of the supersymmetry algebra or how, what's the rule for passing a minus sign through a particular operator and all of that stuff got a lot more difficult because I didn't, I didn't do it every look, you know, it's a little bit like Uh, if you're, you know, if you're a violinist and you don't touch your violin regularly for 15 years, you come back to it, you pretty much know the pieces sort of, but there's lots of stuff that's missing your tone is off and that kind of stuff. I would say. I've got, I'll get the ship to the harbor and it will require a tugboat probably to get it in. And if the tugboat doesn't show up, then I'll pilot the thing right into the dock myself. But it's not a big deal. I think that it is essentially complete </s><s>[INST] psychologically just as a human being. This is uh, remember perhaps by accident, but maybe there's no accidents in the universe. I was tuned in. I don't remember where on April one to you. Uh, I think in your discord, uh, kind of thinking about thinking through this release. I mean, it wasn't like it wasn't obvious that you were going to do what you were thinking through it. And I [/INST] remember there was </s><s>[INST] intellectual personal psychological struggle with this, right? [/INST] Because I did. I thought it was dangerous if this turns out to be right. I don't know what it unlocks. If it's wrong. I think I understand where we are. If it's wrong, it'll be the first fool's gold that really looks like a theory of everything. It'll be the iron pyrite ease of physics. And we haven't even had fool's gold in my opinion yet. </s><s>[INST] Got it. So what is your intuition why this looks right to you, like, why it feels like it would be if if wrong. [/INST] I can see it very simply. It's way smarter than I am. </s><s>[INST] You break that apart a little more like every time you poke at it is giving you intuitions that follow with the currently known [/INST] 50. Let's put it in computer science terms. Yes. Okay. There's a concept of technical debt that computer scientists struggle with as you commit crimes, you have to pay those crimes back at a later date. In general, most of the problem with physical theories is that as you try to do something that matches reality, you usually have to go into some structure that gets you farther away and your hope is is that you're gonna be able to pay back the technical debt And in general these wind up as check kiting schemes or like you're funding a startup and there are too many pivots right? So you keep adding episode cycles in order to to cover things that have gone wrong. My belief is is that this thing represents something like a summit to me and I'm very proud of having found a route up this summit but the route is what's due to me the sum it can't possibly be due to me. You know, it's like Edmund Hillary and Tenzing Norgay did not create Mount Everest. They know that they didn't create that. They figured out a way </s> |
<s>[INST] Yeah I think it has a lot of value in social interaction. So I actually spending the rest of the day today and with our friends uh there are are legged friends in robotic form at boston dynamics. And I think so my probably biggest passions, human robot interaction. It seems that consciousness from the perspective of the robot is very useful to improve the human robot interaction experience? Ah The first display of consciousness but then to me there's a gray area between the display of consciousness and consciousness itself. If you think of consciousness from an evolutionary perspective, it seems like a useful tool in human communication. So uh [/INST] it's certainly whatever consciousnesses will turn out to be I think addressing it through its use Yes and working up from simple cases and also working up from engineering experience in trying to do uh efficient computation including efficient management of social interactions is going to really shed light on these questions as I said in a way that sort of amusing abstractly about consciousness. Never would. </s><s>[INST] So as I mentioned I talked to Sarah walker and first of all she says hi spoke very highly of you. One of her concerns about physics and physicists and humans is that uh we may not fully understand the system that we're inside of meaning. Like there may be limits to the kind of physics we do in trying to understand the system of which were part of. So like the the observer is also the observed in that sense. It seems like the our tools of understanding the world. I mean this is mostly centered around the questions of what is life trying to understand the patterns that that are characteristic of life and intelligence, all those kinds of things. Um We we're not we're not using the right tools because we're in the system. Is there is there something that resonates with you? They're almost well [/INST] yes yes we we do have we we have limitations of course in the amount of information we can process. On the other hand we can get help from our silicon friends and we uh we can get help from all kinds of instruments that make up for our perceptual deficits. And uh we have to and we can use at a conceptual level we can use different kinds of concepts to address different kinds of questions. So I'm not sure exactly what problem she's talking </s><s>[INST] about. It's the problem akin to uh an organism living on a two D plane trying to understand the three dimensional world. [/INST] Well we can do that. I mean you know we live in fact well you know for practical purposes most of our experiences two dimensional, it's hard to move vertically. And yet we've produced conceptually a three dimensional symmetry and in fact four dimensional space time. Uh So you know by thinking in appropriate ways and using instruments and demand. Getting consistent accounts and rich accounts. We find out what concepts are mhm mhm necessary. And uh I don't see any end in sight of the process or any showstoppers because I don't know. Let me give you an example. I mean for instance uh uh que sea de our theory of the strong interaction has nice equations to help to discover what's Q. C. D. Quantum Cromer dynamics. So it's our theory of the strong interaction the interaction that is responsible for nuclear physics. So it's the interaction that governs how quarks and gluons interact with each other and make uhh make protons and neutrons and all the strong the related particles and many things in physics. It's one of the four basic forces of nature as we presently understand it. Ah And uh so we have beautiful equations which we can test in very special circumstances using at high energies that accelerators. So we certain that these equations are correct prizes are given for it and people try to knock it down and they can't. Yeah they uh but uh but the situations in which we can calculate the consequences of these equations are very limited. So for instance no one has been able to demonstrate that this theory which is built on quarks and gluons which no one at which you don't observe actually produces protons and neutrons. And the things you do observe. This is called the problem of confinement. Uh So no one's been able to prove that analytically in a way that a human can understand on the other hand we can take these equations to a computer to gigantic computers and compute and by God you get the world from it. So these equations in a way that we don't understand in terms of human concepts we can't we can't do the calculations, but our machines can do them. So with the help of what I like to call our silicon friends and their descendants in the future, we can understand in a different way that allows us to understand more, but I don't think we'll ever know. No human is ever going to be able to carry to solve those equations in the same way. So, so, but I think that's, you know, when we find limitations too, our natural abilities, we can try to find work, work arounds and sometimes that's appropriate concepts. Sometimes it's appropriate instruments. Sometimes it's a combination of the two, but I think uh, it's premature to uh get defeatist about it. I don't see any any, I don't see any, uh, any logical contradiction or paradox or limitation that that will bring this process to a halt. </s> |
<s>[INST] And the weather affects the data quality. [/INST] Yes, absolutely, because these were really faint stars. And so we were really lucky by making a very tight strategy of getting the absolute bare minimum for all the stars. So we could at least take a very crude look. Is it a yay or is it a nay? We couldn't even say yes or no, just to get an idea because we needed to know. Why was that important? Because we could only observe this system again nine months later. </s><s>[INST] So there's always a window of observation. [/INST] Yes, it was setting. This was our chance and it was going away with the clouds, you know? That was super high stakes. But we just made it. Really, it was almost impossible. And the thing is, this is such a serendipitous moment, inner serendipitous moment. The enhancement of these heavy elements was so strong that even in this really crappy data, </s><s>[INST] we could still see the enhancement. That was super high stakes. [/INST] The absorption was so strong it stuck out of the noise. If that enhancement wouldn't have been as strong, we would not have been able to say anything because we wouldn't have been able to tell. But because it was so extreme, it lent us a hand, despite the weather and all, to say like, yes, this is it. So that was quite the night. </s><s>[INST] Luck. I mean, a lot of this is just luck. So that was the first our process galaxy discovered. [/INST] Yeah. Yes. I didn't sleep all that much then. </s><s>[INST] Do you have hope? Are you excited about James Webb Space Telescope and other telescopes in the future [/INST] that increase the resolution and the precision of what can be detected out there? Absolutely. Data with tea is fantastic already. I am not planning to use it personally, although I think I'm on one or two observing proposals, actually, because similar to what we already spoke about, we're interested in the same thing. We're just kind of looking at a different sides of the fence, right? I have my old surviving stars and I concoct these little stories about what the earliest galaxies may have looked like, what the objects were that contributed energy and elements and all these things. My JWST colleagues, they try to detect some of these earliest photons from these earlier systems to look at the energetics and other things. What was there? How many these kinds of things, right? So together, we're trying to explore this first billion years, but we do it in very complementary ways. And so I'm very excited to see what they can come up with and how that helps me to </s><s>[INST] inform my stories better and more comprehensively. What do you think is the future of the field of stellar archaeology? How much can we... Maybe what are the limits of our understanding of this first billion years of our universe? [/INST] Well, obviously, lots of limitations in the sense that I always say, I have a metal pore star for any of your questions because there are so many different kinds out there. And we still find new patterns sometimes, right? And there needs to be an explanation. The question is, is it ultimately just one quirky star or is it two or is it three, right? Is it a sample, is it a population? So we haven't concluded that kind of work yet. </s><s>[INST] So every metal pore star is a kind of data point that you can use to [/INST] improve the quality of your model of how is the evolution of the early universe. Yes, and I would say we've made huge progress over the last 20 years. When I joined that field, it was in its infancy. And there was this serendipitous discovery of that first second generation star. And we have filled in the canvas a great deal since then. And this is what I have greatly enjoyed about doing so because there was so much discovery potential. And it's been dying down a little bit because of all the progress. It's on the up and coming again because there are so many large spectroscopic surveys in the works now that will just provide a different level of data that we haven't had before. I'm sort of of these older generation. I have only very few colleagues. I work in small teams and I observe every single star myself. Whatever I can, I do myself. I don't generally take other people's data, at least not certainly not in the end stage. And I'm not a big data kind of person, although we all headed that that way. I certainly use data from the Gaia astrometric satellite for the kinematics, for example. But that's personally a new thing for me to use sort of big sky surveys. That are available, so it's still very sort of hand-grown field where we do our individual observations. I have enjoyed that a lot, but that's about to change. </s><s>[INST] So one star at a time. Yes. I mean, there's power to that, to build up intuition of the early universe by looking one star at a time. [/INST] Yes, absolutely. And this is how you can really drill down on the questions that you have, right? Because you control what data you get. Otherwise, you have the data that you have, right? You get what you get and you don't get upset. I don't like that. I'm a little bit snobby. I really like to formulate my questions, go to the telescope, and then come with me. I will try to get it. </s><s>[INST] And also develop the intuition of where the data can be relied upon and where it can't and all the different quirks of the data and all that kind of stuff. Sometimes a lot is lost in the aggregation of the noisy data. [/INST] Yeah, yeah, yeah, yeah. Yeah, yeah, yeah. And that's always the danger if you have someone else's data that you just don't really understand the limitations and completeness things, how certain things were set up, and you get out what you put in. So I'm really particular about that, and it certainly paid off for me. That's one of the main notions that I try to teach in my classes and to my students, that you need to be able to formulate your question really well because otherwise you're going to get an answer to a different question, but you won't notice that the goal pulse has shifted in the meantime, right? So your interpretation can only be as good as the question. If you need to change your question, that's cool. Do it, but then it needs to pair up with your interpretation again. And so knowing, really being in the know about every step of what happens, that leads to quality results, I think. That's why I have sometimes little trouble with sort of big data and statistical analysis. Yes, on average, that's true. I'm not debating that, but I'm the kind of person I like to look at the outliers, so not the bulk, but the special ones. And they just need to be treated in a different way, and there needs to be an acknowledgement of that, different ways for different things. </s> |
<s>[INST] from history's lessons now. We have deep, painful lessons, but there's not that many of them, you know, our history is relatively short as a human species. Do we have a good answer on the left of leninist Marxist versus social democrat versus capitalism versus any, um, anarchy. You know, do have sufficient samples from history to make better decisions about the future of our politics and economics. [/INST] For sure, we have the american revolution, which was a revolution, not about class, not about workers, not about a so called universal class of the working class, elimination of capitalism, markets and the bourgeoisie, but was about the category citizen. It was about universal humanity. Where everyone in theory could be part of it as a citizen, the revolution fell short of its own ideals. Not everyone was a citizen. For example, if you didn't own property, you were a male but didn't own property. You didn't have full rights of a citizen. If you were a female, whether you own property or not, you were in a full citizen. If you were uh imported from africa against your will, you were a slave and not a citizen. And so not everyone was afforded the rights in actuality that were declared in principle. However, over time the category citizen could expand and slaves could be emancipated and they could get the right to vote. They could become citizens non property owning, males could get the right to vote and become full citizens, females could get the right to vote and become full citizens. In fact, Eventually my mother was able to get a credit card in her own name in the 1970s without my father having to co sign the paperwork, it took a long time. But nonetheless the category citizen can expand and it can become a universal category. So we have that the citizen, universal humanity model of the american revolution, which was deeply flawed at the time it was introduced but fixable over time. We also had that separation of powers and constraints on executive power that we began this conversation with. That was also institutionalized in the american revolution because they were afraid of turning, they were afraid of unconstrained executive power. So they built a system that would contain that constrain it institutionally not circumstantially. So that's a great gift within that universal category of citizen which has over time come closer to fulfilling its original promise. And within those institutional constraints, that separation of powers constraint on executive power. Within that, we've developed what we might call normal politics left right politics, people can be in favor of redistribution and government action and people can be in favor of small government, hands off government, no redistribution or less redistribution. That's the normal left right political spectrum where you respect the institutions and separation of powers and you respect the universal category of citizenship and equality before the law and everything else. I don't see any problems with that whatsoever. I see that as a great gift, not just to this country, but around the world and other places besides the United States have developed this. The problems arise at the extremes, the far left and the far right that don't recognize the legitimacy either of capitalism or of democratic rule of law institutions and they want to eliminate constraints on executive power. They want to control the public sphere or diminish the independence of the media. They want to take away markets or private property and redistribution becomes something bigger than just redistribution. It becomes actually that original Marxist idea of transcending capitalism. So I'm not bothered by the left or the right. Uh, I think they're normal and we should have that debate were a gigantic, diverse country of many different political points of view. I'm troubled only by the extremes that are against the system, cost system that want to get rid of it. And supposedly that will be the bright path to the future. History tells us that the far left and the far right or wrong about that. But once again, this doesn't mean that you have to be a social democrat, you could be a libertarian, you could be a conservative, you could be a centrist, you could be conservative on some issues and liberal on other issues. All of that comes under what I would presume to be normal politics. And I see that as the important corrective mechanism, normal politics and market economies, non monopolistic, open, free and dynamic market economies. I don't like concentrations of power politically, and I don't like concentrations of power economically, I like competition in the political realm, I like competition in the economic realm, this is not perfect. It's constantly, uh, needs to be protected and reinvented and there are flaws that are fundamental and need to be adjusted and addressed and everything else, especially equality of opportunity. Equality of outcome is unreachable and is a mistake because it produces perverse and unintended consequences. Equality of outcome attempts attempts to make people equal on the outcome side but attempts to make them more equal on the front end on the opportunity side, that's really, really important for a healthy society. That's where we've fallen down. Our schools are not providing equality of opportunity for the majority of people in all of our school systems. And so I see problems there. I see a need to invest in ourselves, invest in infrastructure, invest in human capital, create greater equality of opportunity but also to make sure that we have good governance because governance is the variable that enables you to do all these other things. </s> |
<s>[INST] well I think ethics uh it's a you know there's uh there's a trolley problem that's often used in the work that I've done at M. I. T. Yeah. Uh Well the autonomous vehicles in particular uh that people I think they offload, they ask like how would a machine deal with an ethical situation that they themselves humans don't know how to deal with. And so I don't know if a machine is able to do a better job on difficult ethical questions. But I certainly think to behave properly and effectively in this world it used to be uh have a fear of mortality and like be able to even dance because I don't think you can solve ethical problems. But you have to uh I think like ethics is like a dance floor, you have to just you have to uh dance properly with the rest of the humans that give people dancing tango, you have to dance in the same kind of way. And for that you have to have a few immortality. Like I think of uh more practically speaking, like I said, autonomous vehicles like the way you interact with pedestrians fundamentally has to have a sense of mortality. So uh when pedestrians cross the road and I've watched, well certainly 100 plus hours of pedestrian videos, there's a kind of social uh contract where you walk in front of a car and you're putting your life in the hands of another human being and like death is is uh is in the car in the game that's being played, Death is right there uh it's part of the calculus, it's not but it's not like a simple calculus, not a simple equation. It's uh it's an s it's uh I mean, I don't know what it is, but it's it's in the it's in there and uh it has to be part of the optimization problem. Like it's not as simple as so from the computer vision from the artificial intelligence perspective as detecting, there's a human estimating estimating the trajectory, like treating everything like it's a billiard balls as opposed to like being able to construct an effective model the world model of the what the person is thinking, what they're going to do. What are the different possibilities of how the scene might evolve I think requires having some sense of yeah, fear of fear of mortality, of mortality. I don't see the thing is I think it's really important to think about. I it could be honest enough to say that it's I haven't been able to figure out how to engineer any of these things, but I do think it's really, really important, like I have uh I have a bunch of room because here I can show it to you after that room poses a robot because um vacuums the floor. And I've had them um make different sounds like I had them scream in pain and it uh it uh you emilie anthropomorphize. Absolutely and it creates a I don't know, knowing that they can feel pain. See I'm I'm speaking like knowing uh that I immediately imagine that they can feel pain and immediately draws me closer to them, that the human experience and that there's there's something in that that should be engineered and in our in our systems, it feels like, all right. I I believe, personally, I don't know what you think, but I believe it's possible for a robot and a human to fall in love. For example, in the in the [/INST] future, I think. Yeah, it's already </s><s>[INST] there is a certain kind of deep connection with technology in a real like you would choose to marry. Um, [/INST] I mean, again, it sounds uh, I'll find a book title and I'll send it to you. And it's a serious consideration of people who started out with these sex dolls. But it turned into a relationship of enduring significance that the woman who wrote the book is not willing to dismiss as a perversion. </s><s>[INST] Yeah, that's what uh you know, people kind of joke about sex robots, [/INST] which is funny, </s><s>[INST] uh like, it's a it's a funny, I mean, there's a lot of stuff about robots. It's just kind of fun to talk about that. It's not necessarily connected to reality people joke about sex robots, but if you actually look how sex robots, which are pretty rare these days. You are used, they're not used by people who want sex. They're actually uh, their companions there compared they become companions. Yeah, it's uh yeah, it's fascinating. They're just we're not even talking about any kind of intelligence. We're talking about just human beings. See companion ships were deeply lonely. I mean, that was the other sense I have that. I don't know if I can articulate clearly, you can probably do a better job, but I have a sense that there's a deep loneliness within all of us. Absolutely. In the face of death, it feels like we're alone. [/INST] So, you know, the what drew me to the existential take on things, lux was the uh who is it? Rollo May and Irwin Yalom right about existentialism and they're like, look at what there's different flavors of existentialism, but they all have in common. What is it? four Universal concerns. The overriding one is about death and that next is choice and responsibility. The next one is existential isolation. And they're like, that's one of the things about consciousness that and the last one is meaninglessness. But the existential isolation point is, you know, we are by virtue of consciousness able to apprehend the unless you're a Siamese twin, you are fundamentally alone. And because it has claimed its erich fromme a book called escape from freedom. He's like, look, you you're smart enough to know that the most direct way that we typically communicate with our fellow human beings is through language, but you also know that language is a pale shadow of the totality of our interior phenomenal logical existence. Therefore there's always going to be times in our lives where even under the best of circumstances, you could be trying desperately to convey your thoughts and feelings, and somebody listening could be like, yeah, I get it, I get it, I get it. And you're like, you have no fucking idea what I'm talking about. So you can be desperately lonely In a house where you live with 10 people in the middle of Tokyo where there's millions. </s> |
<s>[INST] If you're interested, you can go to lexfreeman.com slash hiring for the information on the jobs I'm hiring, or hopefully you'll find the posts I've made on Indeed. Indeed has a special offer only available for a limited time. [/INST] Check it out at indeed.com slash Lex. </s><s>[INST] Wave if you're made. This show is also brought to you by Masterclass. $180 a year gets you an all access pass to watch courses from the best people in the world in their respective disciplines. I've been reading off names. Of the classes I love on here. And one by one, I get to have a podcast conversation with them and the Masterclass is just an inspiration to me. In preparing for those conversations, I listened to the Masterclass, I watched the Masterclass and it just blows me away. So recently I talked to Daniel Negrano and just the quality of his Masterclass, I can't recommend it enough. It's just incredible. I think for beginners, for intermediate people, even experts, that Masterclass condenses the modern poker theory better than anything I've seen anywhere on the internet. And if poker's not your thing, there's a million other things that are likely your thing where the best people in the world can teach you about it. Like Martin Scorsese, that's a good one. And I hope to talk to him with the podcast one day. I'm gonna will it into existence. Get unlimited access to every Masterclass and get 15% off an annual membership at masterclass.com slash Lex. This episode is also brought to you by 8Sleep and it's new pod three mattress. Sleep, like diet and exercise. I think of like a musical instrument in a band. So sleep is like the guitarist. Diet maybe is the lead singer and the exercise is like the drummer. And all of those things you have to play with to create a beautiful hit song. I don't think there's one formula for how much sleep you should get when you should get to sleep. But just like with diet and exercise, you have to listen to her body. You have to understand your own body. And you have to take that journey, that scientific end of one study of your own body very, very seriously. And to me you should have the right companion for that exploration on the diet, on the exercise, and on the sleep. That's why I'm going with 8 Sleep Pod Pro Cover. It cools the bed, it warms the bed, obviously for me, or not obviously, but for me, I just use the cooling. It's a cool bed surface with a warm blanket that's heaven. Check it out and get special savings when you go to 8sleep.com slash Lex. This is a Lex Friedman podcast. To support it, please check out our sponsors in the description. [/INST] And now, dear friends, here's John Donner. </s><s>[INST] And the ADCC is the premier submission grappling tournament in the world we just had it a couple of weeks ago. We saw many demonstrations of greatness from athletes you coached. But a year ago, the team and you were at a very low point. Take me through that journey. [/INST] What was the lowest point? We had a very, very tight team for many years, which began in New York City. During the peak of COVID, training in New York became very difficult to sustain. So most of the team despised the city of New York. I was the only person in the group that liked living in New York. I think part of the problem was that I was the only one who actually lived in Manhattan. The others had to commute to New York. And there's a world of difference between living in New York and commuting to New York. So most of them had a very negative view of New York City that was compounded by COVID when even the basic act of training became very, very difficult. And so everyone decided they want to leave. So there was a prospect of a complete breakup between myself and the team, or I would have to leave New York. It was a difficult decision for me to make because I had lived in New York for 30 years. I had built my life there and had most of my friends and associates that I know here in America were New Yorkers. So I thought these guys have been incredibly loyal to me as students, so I should also be loyal to them, of course. So I decided that if they wanted to leave, I would go with them. We decided to go to Puerto Rico because there was a private gym where we could train through the COVID period. I personally wanted to go to Texas. I thought that Texas was a better place for the team to go. But many of the students, including senior students like Gordon Ryan, Craig Jones, had been to Puerto Rico and stayed with one of the head officials of ADCC, Mo Jasm. So they loved their experience in Puerto Rico, and almost everyone wanted to go down there. So I tried to explain to them there's a little difference between going to a place for vacation versus living there, but that didn't have any effect. So the decision was made, a majority of the decision was made to go to Puerto Rico. In Puerto Rico, the conditions in which the team lived changed significantly. When you're in New York, New York is such a big city that if there's any tension between team members and inevitably there will be in a competitive sport where everyone's fighting each other, you can kind of bury them in the size of the city, because there's so many distractions in New York. You come in, you do your workout, you go outside, and it's New York City. In Puerto Rico, we lived in a very small local town, Dorado. And most of the athletes were living with each other. And so unlike New York, where there was always a break, you trained together, but when training was over, you went about your life in New York and New Jersey, with everyone living in very close proximity to each other. Any tensions got magnified, because there was no relief from them. You didn't get to get away from people. If you had a problem with someone on the mat, well, now you have to live with them for the rest of the day and the night. And this goes on for long periods of time. So I believe it had the effect of magnifying whatever tensions there were. In particular, there was a family tension between two brothers, which magnified over time. And as so often as the case, you get two brothers growing up, one older, one younger, and the younger one wants to grow and feel somewhat like a young tree underneath a big tree. And sometimes people just need their space. </s> |
<s>[INST] Well, I think there's a pendulum aspect to it because it's my hope in terms of backwards. So, pendulum goes backwards too. But it just goes back and forth, I think. And then in the long arc of history, we're making progress. I think all of the discussions of diversity and inclusion and all those kinds of things. I always thought that they're healthy in a in moderation, right? There should be a small part of the conversation amongst other things. The natural asked like it seems that they kind of have this way of just consuming all conversations. It's like the meetings like diversity and inclusion meetings multiply somehow. Or it's like the only thing that you're talking about, it's very kind of absurd. And when I look at uh even at M I. T. It's it's a strangely disproportionate amount among the discussions about that. And also to me as an engineer. Those discussions are very frustrating because they don't seem to actually do anything so like they want to bully people instead of creating systems that fix defined like definitive problems and that in itself. That kind of bullying. That's the same kind of thing you saw in terms of mccarthyism in America against the communists. You certainly saw that in soviet union against everybody who's not communist. It's uh it creates hate not progress When you talked to Jordan Peterson recently and people should listen to that conversation. It was a fascinating one I think. Um he he he almost got emotional on the discussion about universities and your experience with Colombia because he like myself for perhaps different reasons. Have a hope for our academic institutions, some of the most incredible people, some of the most incredible engineering and idea development innovation happens in universities. And so we both deeply care about them. Um Is there something, So the reason he got emotional, the reason he was kind of hurt is the fact that you did not, you were not deeply inspired by your experience [/INST] that deeply It made me dumber made me scared. It made me terrified that I had to censor myself in America. Like are you seriously telling me that you don't ever sensor yourself and when you talk you can you truly say whatever you want about race or anything gender. We all censor ourselves. Let's be honest, right, we are all doing that and that's what I learned. Like I thought I was coming to country. They're never needed. Like first thing my mom told me growing up in north Korea was don't even whisper because the birds and mice could hear you. Mhm. And I thought okay now America is truly the land of the free home of the brave. You can say anything you want and then you have freedom to change your mind and evolve, right? But the people now demand you to be the perfect version. They demanded to be. You cannot change your mind and then what is the meaning of life? You cannot grow but you should be safe to talk about anything and then later okay I was wrong the night if you do that, you gotta get penalized for it. </s><s>[INST] I mean since the ship is a funny thing because you probably should not say dumb things. You should try to say things you want to say in the most eloquent. The most effective way you can. So I mean that's what editing is. Right? Yeah. So there's some level of like being careful with what you say, not because you're afraid of some overarching kind of group of bullies but you want to be the best version of yourself and you express stuff. But there's some sense where in the university setting you can put that self censorship like level down more and say stupid stuff and explain and play because you should be forgiven for that kind of uh play. Especially when you're discussing difficult aspects of human history. Whether that that include racism that that include atrocities. I'm still nevertheless sort of hopeful. But at the same time I'm surrounded by engineers so I don't get to interact with people and humanity as much and it seems like there is getting [/INST] worse. </s><s>[INST] I yeah, I don't know. Uh well I do sort of interact with psychologists but they haven't touched on those kinds of topics yet. I still in defense of psychology, I still, I wish we had more numbers but I still feel like most psychology people don't partake in this kind of stuff either. They're just doing excellent research. We're just highlighting this one. America does well you're kind of highlighting anecdotal experiences and uh making a big deal out of them. But that's good because like it's a slippery slope if those, if those things start to overtake all of academia started becoming a big problem even in the engineering field. So we should be concerned. But it is truly tragic that somebody who's exceptionally well read like you who's fire was stoked first with Orwell that fire should burn bright. Like this should not be, you should be writing many books, you know what I mean like and you'll be, you talk to jordans, you know, it's very possible depending what you want to do with your life that you will be a future Jordan Peterson right? Uh So like that and Columbia should be a place that enriches that your mind and the fact that it didn't, this is tragic. [/INST] It's like I was there four years. It wasn't like I had one class that was bad in a one semester. Yeah, that was there when DR pepper was asking is there any one class that had no sentiment of this this purchase signaling particularly right? There was none entire course. I think I took 100 and 26 credits total. Not even one class doesn't matter. We were talking about classic art and that's the thing. I literally thought, okay I push the last does the minister the core like the art and music. Right? So I thought this is gonna be the least politically correct class I can take. And then it begins with who has problem with calling this course the western civilization, Museum of Art and Music. And it was raising their hands because like why do you have to learn about this battle remotes are the bigots and all the people like, you know, everything is going to by white men and there's even music, even these paintings. And as I I didn't raise my hand, everyone's looking at me, how do you not have the problem with us? Like you used to hate was Eur asian Eur So I think that's the thing is I think the problem is very deeper than what people think and it's it's so that's what I when I learned it's like it's not that safe in America. We can go completely to the south and looking at even europe that is like I used to be very more optimism like you know but now I actually see wow this country can go to south and we might if U. S. Forces them right? This is the only country left to battle with the Communist party in china. We may lose the opportunity to be free ever again as a humanity. </s> |
<s>[INST] So using that logic, how many alien civilizations do you think are out there? There's, there's, there's like trillions of environments ak planets or maybe you can take even bigger than planets. How many lifelike organisms do you think are out there thriving and maybe how many do you think are long gone? But were once here? [/INST] I think, well, innumerable, I </s><s>[INST] think in terms [/INST] of the much greater than zero. I mean, I would just be surprised what a waste, right. Of all that space. Just for us, if we're never going to get there. Um that would be my first way to think about it. But second, I mean, I remember when I was about seven or eight years old and I would love if any of your listeners could find this National Geographic, I remember opening The page of the National Geographic, I was about again 7-10 years old and it was sort of a current picture of the universe was around probably 1968, I just remember looking at it and thinking what kinds of empires have risen and fallen across that space, uh, that we'll never know about. And what isn't that sad that we know nothing about something so grand. And so I've always been a reader of science fiction because I like the creative ideas of what people come up with. And I especially like science fiction writers that base it in good science, but base it also in evolution that if you evolve a civilization from something lifelike, right? Some sort of biology, it's assumptions about the universe will come from the environment in which it grew up. So, for instance, Larry Niven is a great writer. Uh, and he imagines different kinds of civilizations in some cases, what happens if, uh, what happens if intelligence evolved from a herd animal? Right. Would you lead from behind? Right. Would you be uh, you know, in his case, one of them were the so called puppeteers and to them the moral imperative is cowardice. You put other people forward to run the risk for you. Right. And so he writes entire books around that premise. There's another guy, Brynn David brin is his name and he writes the so called um uplift universe books. And in those he takes different intelligences, each from a different evolutionary background. And then he posits a civilization based around where and what they came from. And so to me, I mean, that's that's just fun. But I mean, back to your original question is, how many are there? I think as as many stars as we can see now, how many are currently there? I don't know. I mean, that's the whole that's the whole question of, you know, how long can a civilization last before it runs out of steam? And you, for instance, does it just get bored or does it transcend to something else? Or does it say I've seen enough and I'm done. </s><s>[INST] What does running out? His team looked like? It could be destroyed itself or get bored, you [/INST] know, said or we've we've done everything we can and they just decide to stop. I don't know. </s><s>[INST] I just don't know, is that you almost worry that we stop reproducing or we slow down the reproduction rate to where the population can go to zero, can go to [/INST] zero and and we can't and we collapse. I mean, so the only way to get around that is perhaps create enough machines with ai to take care of us, </s><s>[INST] what could possibly go [/INST] wrong. </s><s>[INST] You've talked to people that told stories of Ufo encounters, what is the most fascinating to you about the stories of these Ufo encounters that you've heard that people have told you the similarity [/INST] of them. Uh the uniformity of the of the stories. Now I just want to say up front a lot of people, I think that when I speculate I believe something that's not true, right, speculation is just creativity, speculation is the beginning of hypothesis. None of what I hear in terms of the anecdotes do I necessarily believe are they true? But I still find them fascinating to listen to it because at some level there's still raw data and you have to listen. And once you start to hear the same story again and again, then you have to say, well there might be something to it. I mean maybe it's some kind of a young indian background in the human mind and human consciousness that creates these stories again and again as coming out of the D. N. A. It's coming out of that pre programmed something. And young talked quite a bit about this kind of thing, The collective unconscious. But actually one of the most interesting ones I find is this constant uh message that you're not taking care of your world and this came long before climate change. It came long before many kinds of, you know, let's say current day memes around uh you know, taking care of our planet pollution, et cetera. And so, you know, for instance, perhaps the best example of this, the one that I find the most fascinating is a story out of Zimbabwe uh 50 or 60 Children one afternoon in Zimbabwe. It's a it was a well educated group of white and black Children who and lunchtime in the playground saw a craft uh and they saw little men and they all ran into the teachers and they told the same story and they drew the same pictures and the message. Several of them got was you're not taking care of your planet. And it's got, you know, there's actually a movie coming out on this episode and 30 years later now, the people who were there, the Children who have now grown up say it happened to us now. Did it happen? Was it some sort of hallucination? Or was it an imposed hallucination by something? Was it material? I don't know. But These kids were 7-10 years old. You see them on video. 7-10 year olds can't lie like that. And so, you know, whether it's real or not, I don't know. But I find that fascinating data. And again, it's it's these unconnected stories of individuals with the same with the same story that is worthy of further inquiry. </s> |
<s>[INST] them to know. What about transforming yourself and your resolutions like that? [/INST] Oh, I'm doing a slight bulk now. So I'm almost at my heaviest weight ever. But I've been, I couldn't go to the gym this week because I was under under weather. Um so that's been a little frustrating. But yeah, </s><s>[INST] so are we going to get some more modeling pics? What are we, what's, what, what is their goals [/INST] There? So my heaviest, I'm 48, the heaviest I've ever been was when? And this is when I was like, he's </s><s>[INST] exaggerating, he's not that that's [/INST] the metric. Um </s><s>[INST] Oh sorry, are you talking about your height? Yeah. Um barely 46. [/INST] So the heaviest I've ever been when I was like really high body fat because I was just because I learned because I couldn't gain weight as a kid. So when I figured out I could actually gain weight, I like I was 164.5. So I want to hit 165. Uh, and then see take it from there. I have a friend who's been helping me and my buddy trade off and this kid's stronger his jake his user name on instagram is stronger. Both the number five instead of letter and then the number five said the letter S but he does um I've never, it looks like it's Photoshop like your brain can't process it. You know the human flag? </s><s>[INST] No. Oh yeah yeah yeah [/INST] he does human flag pushups so he is horizontal parallel to the ground, right? He's holding himself up like a flag but he can also do do this while so he's moving parallel to the earth side to side while it's just crazy. </s><s>[INST] That's really difficult. So you know, you're interested in that kind of stuff. No, [/INST] but I'm saying like he's been helping me out so like the guy knows what he's doing, he's just a really impressive kid. </s><s>[INST] I love that kind of stuff like body weight cells. So my primary mode of working out. It's very like the professor you've ever seen leon like the professional that with Natalie Portman in that movie, it's like have a pull up thing as you push ups and pull ups. It's very like um I'm just missing the milk. I like working out at home just like that. Um And the body weight stuff you can go so much with it and it's super functional for everything else you livin for life for living life. Well [/INST] I'm on the other hand, I don't care what functionality the thing that really bothers me. Like I go. I know joe is thinking of opening up a gym, like a private gym there's only like one power cage here at the gold's. I go to, I don't know what source that there's only one or that sometimes people aren't using it. I'm like, no one's doing dead lifts in here. No one just me. It's golds </s><s>[INST] by the way. I don't want to say where I'll tell you off. But there's, there's a there's a few really like ghetto places around Austin there just like these shitty jim jim's that nobody wants to go to. But they have Iraq, they have like, if you want to lift heavy, that kind of [/INST] Stuff. hours. That's the thing. </s><s>[INST] Oh, but there are 24 hours in the following way. There's a code, okay? And you just go in and you turn on the lights and then you work [/INST] out, I don't want to, I don't want to meet people. Exactly. </s><s>[INST] Well that's just not [/INST] true that people, sometimes </s><s>[INST] there's people and they're [/INST] great. Yeah. Like, and I've had fans come up to me and goals and they've all been cool except except, oh </s><s>[INST] no, except [/INST] except if I have my headphones on and I'm doing dead lifts, I don't need you to come over, tap my ear and start giving me critiques about my form. This </s><s>[INST] actually happened. Yes, [/INST] I'm still angry about it. I'm pulling my 150 in peace. Thank you. </s><s>[INST] Yeah, people are hilarious. I was recently in uh I had actually the wildest day ever in my life. That was so many things happened in a row. So I went to a wedding in L. A. Andrew uh Andrew shelters and with Whitney cummings and, and, and, and joe Rogan and a bunch of other fascinating people. It's just speaking of weirdos. There's the comedian, like the reason I find the comedian is awesome one, they're authentic, they're just cool people, but they're also just weird. Like you don't become a comedian for not being like funked up in all kinds of different ways. Anyway, so there's the wedding, I'm um, you know me, it was only carbs at the wedding, So I didn't eat, I didn't eat for a long time before. So I was like already fasted, 20 hours, 25 hours. And, but so that this whole story of everything that happens is lex like 40 hours fasted with joe Rogan drinking a lot of whiskey. And [/INST] So you're drinking too heavy on 40. Oh my God, that's crazy. </s> |
<s>[INST] And so the dendritic spikes that you were talking about, [/INST] well, we wouldn't model the spikes, but the idea that you have that today's neural networks have this company called a point in your arms is a very simple model of a neuron and uh by adding dendrites to them and just one more level of complexity that's in biological systems, you can solve problems in continuous learning um and rapid learning. So we're trying to take, we're trying to bring existing field, we'll see if we can do it. We're trying to bring the existing, feel the machine learning uh commercially along with us. You brought up this idea of keeping, you know, paying for it commercially along with us as we move towards the ultimate goal of the true AI system. </s><s>[INST] Even small innovations on neural networks are really, really exciting. It seems like such a trivial model of the brain and applying different insights, just even like you said, continuous learning or uh making it more a synchronous or maybe making more dynamic or like incentivizing [/INST] making it </s><s>[INST] uh and making it somehow much better incentivizing Spar City uh somehow. Yeah, well, [/INST] if you can make things 100 times faster than there's plenty of incentive that people, people are spending millions of dollars, you know, just training some of these networks. Now, these uh these transforming networks, </s><s>[INST] let me ask you the big question, how for young people listening to this today in high school and college, what advice would you give them in terms of which career path to take? And maybe just about life in general? [/INST] Well, in my case, um I didn't start life with any kind of goals. I was when I was going to college is like, what do I say? Well maybe we do, it's electrical engineering stuff, you know? Um it wasn't like, you know, today, you see some of these young kids are so motivated like change where I was like, you know, whatever. And um, but then I did fall in love with something besides my wife, but I fell in love with this, like, oh my God would be so cool to understand how the brain works. And then I said to myself, that's the most important thing I could work on. I can't imagine anything more important because if you understand the brains work, build tells machines and they could figure out all the other big questions in the world, right? So, and then I said, I want to understand how it works. So I fell in love with this idea and I became passionate about it, and this is a trope, people say this, but it was it's true because I was passionate about it, I was able to put up almost so much </s><s>[INST] crap, you [/INST] know, you know, I was I was in that, you know, I was like, person said, you can't do this, I was I was a graduate student at Berkeley when they said, you can't study this problem, you know, no one can solve this or you can't get funded for it, you know? Then I wanted to do, you know, mobile computing, and it's like people say you can't do that, you can't build a cell phone, you know, So, but all along I kept being motivated because I wanted to work on this problem, I said, I want to understand the brain works and I got myself me like one lifetime, I'm going to figure it out, do the best I can so by having that because, you know, it's really as you point out like, it's really hard to do these things, people, it's just, there's so many downers along the way, So many obstacles get in your way, I'm sitting here happy all the time, but trust me, it's not always like </s><s>[INST] that, that's I guess the happiness that the passion is a prerequisite for surviving the whole, the whole thing. [/INST] So I think that's right. Um, and so I, I, I don't want to get to some and say, you know, you need to find a passion and do it. No, maybe you don't, but if you do find something you're passionate about then then you can follow it as far as your passion will let you put up with </s><s>[INST] it. Do you remember how you found it? This is how the spark happened. [/INST] Why specifically for me? </s><s>[INST] Yeah, because you said it's such an interesting, it's like almost like later in life by later. I mean like not when you're five, you, you didn't really know and then all of a sudden you fell in love with that. [/INST] Yeah, there was, there was two separate events that compounded one. Another one When I was probably a teenager, might have been 17 or 18, I made a list of the most interesting problems I could think of. First was why does the universe exist? It seems like not existing is more likely. The second one was well given exist why they behave the way it does. You know the laws of physics, why is equal EMC squared, not empty cube, you know, attention question third one was like, what's the origin of life? Um, and the fourth one was what's intelligence and I stopped there, I said, well that's probably the most interesting one. And I put that aside As a teenager. But then when I was 22 and I was reading the No it was excuse me, I was 17, it was 1979. Excuse ME, I was reading. So I was at that time was 22. I was reading uh September issue of scientific American, which is all about the brain. And then the final essay was by Francis crick who of DNA fame. And he had taken his interest to study the brain now and he said you know there's something wrong here. He says we got all this data, Oh this fact this is 1979 all these facts about the brain, tons and tons of facts about the brain. Do we need more facts, but we just need to think about a way of rearranging the facts, we have. Maybe we're just not thinking about the problem correctly, you know, because he says this shouldn't be shouldn't be like this, you know? So I read that and I said wow, I said I don't have to become like an experimental neuroscientist, I could just look at all those facts and try to become a theoretician and try to figure it out. And I said that I felt like it was something I would be good at. I said I wouldn't be a good experimental that I don't have the patience for it. But I'm a good thinker. And I love puzzles and this is like the biggest puzzle in the world is the biggest puzzle all the time. And I got all the puzzle pieces in front of me. Damn, that was exciting. </s> |
<s>[INST] So the vision, uh, the vision is to work on some of these big problems, arbitrary number of problems that present themselves in the world that face all human civilization and to be able to work together. [/INST] Well, that is, but there's a, there's a macro meta problem, which is the global collective action problem. And so the idea is, even if we, if we just focus on the verticals, on the manifestations of the global collective action problem, um, there will be an problem, there'll be an infinite number of those things. So while we work on those things like climate change, pandemics, WMD and other things, we also have to ask the bigger questions of why can't we solve this category of problems. And the idea is, at least from my observation, is that whenever big decisions are being made, our national leaders and corporate leaders are doing exactly what we've hired them to do. They're maximizing for national interest, even or corporate interest, even at the expense of everybody. And so it's not that we want to get rid of states, states are essential in our world system. It's not we want to undermine the UN, which is also essential, but massively underperforming. What we want to do is to create an empowered global constituency of people who are demanding that their leaders at all levels just do a better job of balancing broader and narrower interests. </s><s>[INST] Okay. So this is more like a make it more symmetric in terms of power. It's holding accountable the nations, the leaders. The problem is nations are powerful. We talked about China quite a bit. How do you have an organization of citizens of Earth that can solve this collective problem that holds China accountable? It's difficult because the UN, you could say a lot of things, but to call it effective is hard. The internet almost is a kind of representation of a collective force that holds nations accountable. Not to give Twitter too much credit, but social networks broadly speaking. So you have hope that this is possible to build such collections of humans that resist [/INST] China. We don't necessarily resist China, but our cultures change over time. The idea of the modern nation state would not have made sense to people in the 13th or 14th century. The idea that became the United Nations, it had its earliest days in the philosophies of Kant. It took a long time for these ideas to be realized. And so the idea, and we're far from successful. We've had little minor successes, which we're very proud of. We got the G20 leaders to incorporate the language that we provided on addressing the needs of the world's most vulnerable populations into the final summit communique from the G20 summit in Riyadh. This year, we're just on the verge of having our language pat on the same issue, ensuring everyone on Earth has access to safe water, basic sanitation and hygiene, and essential pandemic protection by 2030 passed as part of a resolution in the United Nations General Assembly. And it's, we're primarily, I mean, it's young people all around the world. And when I told them that in the beginning of this year, this is our goal, we're going to get the UN General Assembly to pass a resolution with our language in it. I mean, first, I think they all thought it was insane, but they were too young and inexperienced to know how insane it was. But now these young people are just so excited that it's actually happening. So what we're trying to do is really to create a movement, which we don't feel that we need to do from scratch, because there are a lot of movements. Like right now, we just had the Glasgow G20, I mean, I'm sorry, the Glasgow climate change, COP26. And then Greta Thunberg, who has a huge following and who is an amazing young woman, but I was kind of disappointed in what she said afterwards. It became like a meme on Twitter, which was blah, blah, blah. And basically it was like, blah, blah, blah, these old people are just screwing around and it's a waste of time. And definitely the critique is merited. But young people have never been more empowered, educated, connected than they are now. And so that's what we've had a process with One Shared World, where we partnered with the Model United Nations, the Aga Khan Foundation, the India Sanitation Coalition, and what we did is say, all right, we have this goal, water sanitation, hygiene, and pandemic protection for everyone on Earth by 2030. And we had debates and consultations using the Model UN framework all around the world in multiple languages. And we said, come up with a plan for how this could be achieved. And these brilliant young people in every country, not every country, most countries, they all contributed. Then we had a plan. Then I recruited friends of mine, like my friend Hans Karel in Sweden, who's the former chief counsel of the whole United Nations, and asked him and others to work with these young people and representatives to turn that into what looks exactly like a UN resolution. It's just written by a bunch of kids all around the world. We then sent that to every permanent representative, every government represented at the UN. And that was why working with the German and Spanish governments, why the language essentialized from that document is about to pass the UN. And it doesn't mean that just passing a UN general assembly resolution changes anything. But we think that there's a model of engaging people, just like you're talking about, these people who are outside of the traditional power structures and who want to have a voice. But I think we need to give a little bit of structure because just going, I'm a big fan of global citizen, but just going to a global citizen concert and waving your iPhone back and forth and tweeting about it isn't enough to drive the kind of change that's required. We need to come together even in untraditional ways and articulate the change we want and </s> |
<s>[INST] bigger, it'll [/INST] just like automated. Um So you can get automate automate, automate managing management, </s><s>[INST] publishing. Um [/INST] like </s><s>[INST] and and [/INST] and and legal </s><s>[INST] it can read the Api's building, can read your [/INST] contract and like tell you about it </s><s>[INST] because one of the [/INST] issues with music right </s><s>[INST] now, it's not that we're not getting [/INST] paid enough, but </s><s>[INST] it's it's that [/INST] the </s><s>[INST] art art industry [/INST] is filled with middlemen because </s><s>[INST] artists are not good at business [/INST] and you know from the beginning like frank Sinatra, </s><s>[INST] it's all mob stuff. Like it's the music industry [/INST] um </s><s>[INST] you know, is run [/INST] by business </s><s>[INST] people, not the artists and the artists really get very small cuts of like [/INST] what they make. And </s><s>[INST] so um [/INST] I think part of the reason I'm a </s><s>[INST] technocrat, which I mean your [/INST] fans are going to be technocrats. So no one's, they're not gonna be mad at me about this. </s><s>[INST] But like my fans hate [/INST] it when I say this kind of thing </s><s>[INST] or the [/INST] general public, </s><s>[INST] they don't like technocrats? Like when we, [/INST] when I watched um </s><s>[INST] battle Angel Elita and they were like [/INST] the martian technocracy and I was </s><s>[INST] like yeah martian technocracy and then they were like and they're evil [/INST] and I was like, oh okay, I was like the martian </s><s>[INST] technocracy sound sick to me, your intuition [/INST] as </s><s>[INST] technocrats would create a some kind of beautiful world. [/INST] For example what my </s><s>[INST] manager is working on, if you can create an app that um removes [/INST] the need for a lawyer and then you could, </s><s>[INST] you could have a smart contracts [/INST] on the Blockchain </s><s>[INST] um removes [/INST] the need </s><s>[INST] uh for [/INST] like management </s><s>[INST] and organizing all this stuff, [/INST] like can </s><s>[INST] read your stuff [/INST] and explain it to, you can </s><s>[INST] collect your royalties, [/INST] you know, like then </s><s>[INST] the small amounts, the [/INST] amount of money that you're getting from Spotify actually </s><s>[INST] means a lot more um and goes a lot further. [/INST] They can remove some of the bureaucracy, some of the inefficiencies that make life not as great as it could be. Yeah, </s><s>[INST] I think the issue isn't that [/INST] there's not enough, like the issue is that there's inefficiency and I'm really into this positive sum mindset. Um </s><s>[INST] you know the win win [/INST] mindset of like instead of </s><s>[INST] fighting [/INST] over the scraps, how do we make the, we're worrying about scarcity, like instead of a scarcity mindset, why don't we just increase </s><s>[INST] the efficiency. [/INST] Um and you know, in that </s><s>[INST] way expand the size of the pie, [/INST] let me ask </s><s>[INST] you about experimentation. [/INST] So he </s><s>[INST] said, which is [/INST] beautiful. Being a musician is like having a conversation with all those that came before you. Um, </s><s>[INST] how much of creating [/INST] music is like, uh, kind of having that conversation, trying to fit into the </s><s>[INST] cultural trends and how much [/INST] of it is like trying </s><s>[INST] to as much as possible being outside and come up with something totally new. It's like when you're [/INST] thinking, </s><s>[INST] when you're experimenting, [/INST] are you trying to be totally </s><s>[INST] different, totally [/INST] weird? Are you </s><s>[INST] trying to [/INST] um, fit in? </s><s>[INST] And this is so hard because [/INST] I feel like I'm kind of in the process of semi retiring from music. So this is like my old brain. Yeah, bring it, but bring it from like the shelf, put it on the table </s><s>[INST] for for a couple of [/INST] minutes, we'll just, we'll just poke it. I think it's a bit of both because I think, uh, forcing yourself to engage with new music. Um, it's </s><s>[INST] really great for [/INST] neural plasticity. Like, I think as people, part of the reason </s><s>[INST] music is marketed at young [/INST] People because young people are very narrow plastic. So, um, like if you're 16 to like 23 or whatever, you're, it's gonna be really easy for you to love </s><s>[INST] new music. [/INST] And if you're older than </s><s>[INST] that, it gets harder and harder and harder. [/INST] And I think one of the beautiful things about being a musician is I </s><s>[INST] just constantly [/INST] forced myself to listen to new music. </s><s>[INST] And I think it keeps my brain [/INST] really plastic. Um </s><s>[INST] and I think this is a really good [/INST] exercise. I just think everyone should do this, you listen to music and you hate </s><s>[INST] it. I think you should just keep [/INST] force yourself to like, okay, </s><s>[INST] well why do people like it? [/INST] And like, </s><s>[INST] you know, make your brain form new [/INST] neural pathways and be more open to change. That's really brilliant actually, </s><s>[INST] sorry to interrupt. But like that [/INST] exercise, it </s><s>[INST] is really [/INST] amazing </s><s>[INST] to sort [/INST] of embrace </s><s>[INST] change, embrace [/INST] sort of practice </s><s>[INST] on your plasticity [/INST] because like, that's one of the things you </s><s>[INST] you fall in love with a certain band. You [/INST] just kind of stay </s><s>[INST] with that for the rest of your life and you [/INST] never understand the modern music? That's a really good </s><s>[INST] most of the streaming on [/INST] Spotify is like classic </s><s>[INST] rock and stuff. Like new [/INST] music makes up a very </s><s>[INST] small chunk of what is played [/INST] on Spotify and I think </s><s>[INST] this is like [/INST] not a good sign for us </s><s>[INST] as a species, I [/INST] think. </s><s>[INST] Yeah, [/INST] so it's a it's a good measure </s><s>[INST] of the [/INST] species. Open </s><s>[INST] mindedness to change is how often you listen to new music? The brain. The [/INST] brain, let's put </s><s>[INST] the music brain on the [/INST] back on the shelf. I gotta pull out the </s><s>[INST] futurist brain [/INST] for a second. Uh in what wild </s><s>[INST] ways do you think the future saying [/INST] like 30 years, </s><s>[INST] Maybe 50 years, maybe 100 years will be different um, [/INST] from like, </s><s>[INST] from our current way [/INST] of life on earth, </s><s>[INST] we can talk about augmented reality, [/INST] virtual reality, </s><s>[INST] Maybe [/INST] robots, </s><s>[INST] maybe space travel, maybe video games, maybe genetic engineering. I can keep going. Cyborgs, [/INST] aliens. World </s><s>[INST] wars may be [/INST] destructive. Nuclear wars, good and bad. What do you do when you think about the future? What are you imagining? </s><s>[INST] What's the weirdest [/INST] and wildest that could be? </s><s>[INST] Have you read service detail [/INST] by Iain Banks? Surface detail is my favorite depiction of a oh wow. You have to read this book. </s> |
<s>[INST] your favor. That's so brilliant, let me go from the very practical to the most impractical. A huge question about the meaning of life. You said that one great depths of unrelenting sorrow punctuated by great peaks of joy and liberation. The result is delicious. So, uh, what do you think is the meaning of this whole journey that we're on this life? What makes life delicious [/INST] to me? You know, satisfaction is the m for me, like, like, like I always, if I'm satisfied, that's me and I have no nothing to live for. I'm talking I'm not talking only about my career about to talk about my life. What do you want in your life? You want, you want kids, you want a family, you want to be champion, What do you want in your life? You have, you have like a long term goal, short term goal in mixed martial art I achieve when I needed to achieve, I'm satisfied here. I'm no longer the same johnson NPR then when I was begging for a title shot on my knees, I move on for it from it. Now I had a chance to go into movies now. That same insane. That same insane dr that had to be the champion of the world. Now, I put it into acting like I'm having a lot of acting class now and luckily for me, the timing was amazing. I got I got cast for the falcon and the Winter Soldier that is on Disney Plus channel, it's a huge, huge project to be part of for me because it's like you play basketball, you have a chance to go for the NBA right away. I was very lucky, the timing was just too perfect and so you need to constantly challenging yourself and having goals to achieve, you know, like that keep your brain activated, I keep working and the proof of that is you see sometimes some old people like when they retire very often, sometimes you see that they got sick and they die or because they, it's either because sometimes we think we, we certainly benefits will do something good for them by making network and giving them a break. So we don't mind, we're like, oh it is going to be able to relax what in their mind, it's not good because they're not busy, they have nothing to live for like, like my dad is used to work all the time and he has always something to do. He's retired now I </s><s>[INST] myself now [/INST] call him by force to find him some job. Dad, can you come in my house, have this thing to repair, I don't know what to do it. So he gives him, it gives him a reason not to live in because he has other things to do, but what I mean is also in life, I think you always don't be afraid to aim high, don't don't be afraid to fix your objective very high and never be able to reach it. Be </s><s>[INST] afraid of reaching your goals essentially. I mean you always have to keep moving it out. You think there's a uh it's an interesting question because you've been acting in some really exciting things. Do you think there's a, a dramatic role where it's basically, you know, you go full robert de Niro in taxi driver? Do you think there'll be a full length feature film with George ST Pierre? I [/INST] like it. There is level to this thing, I'm aware that I have to restart as a white white belt and for some people it could be discouraging, but for me man, it's great, I love it, I freaking love it, I embrace it because everybody told me like I would never be able to do it and it's fine. But and also the outcome of a failure in the sport of mixed martial arts is much more serious. Then the outcome of a failure for a movie, for example, for for if you zig when you should zag in a fight, you get knocked out. If you zig when you should zag and unset cut, we'll do it again and I know that I will be most likely be chosen for action martial art roles because that's my background, There's this new trend in Hollywood now, when they want someone to play an italian guy, they're going to choose a real italian person when they want someone to play a Russian guy, they're going to choose someone who has a real Russian background. Now they want a real martial art fighter, I've done fighting all my life, I just need to improve my acting skills. But when I train enacting I get myself out of my comfort zone, I'm not playing a role of a martial art, I'm playing like romance committee drama. So when I go on set and playing the role of a of a badass martial art guy, it's easier. So like in training for a fight, I always make my preparation harder than the actual </s><s>[INST] task. I would love to see where I don't know if you've seen the wrestler would make you work. Oh yeah, those types of films, I would love to, I would love to you do something like that if not now then in 10, 20 years I could see that, that would be amazing. It's, there's levels to the game, right? [/INST] Yes, it's gradual and I'm aware that I, I don't want to take something on my shoulder that I won't be able to deliver. It's like a fighter wants to go for a title shot right away. It could, it could very well break him, you know what I mean? And I don't want to do that because I know I've done some gigs in the past, but I was not focusing on it because I was focusing on competing as a martial art much martial artist and competition in m M A. But now I take it very seriously. So I cannot do the same mistake again because I've done some stuff, I've done it for the money and it was good, it was fun to be beat up by Chako van Damme, steven Seagal and everything. But but my acting was not on point you know at that time. So if I ever, every time I'm going to come back from now on on on on screen you need to be sharp because you cannot mess it up if you mess it up, it's like a loss on your record, you're not taken seriously. So so that's how I see it and it's very fun because I I add a chance to talk to a lot of guys and on top of all the class that I'm having like a few days ago I was with Danny Trejo and I always seek the advice of actors when I when I see some of them that because I really admire how they do you know how they project their emotion. And I asked him Danny True. I said I said to him is an amazing guy by the way, very nice guy and I asked him I see him how do you do to be because you scared the hell out of me? How do you do to be so scary like what is your trick? And he tells me it's like George if you threatening if your threat someone and you scream at him </s> |
<s>[INST] question. What do you think beliefs are in themselves can become reality? I mean? So, so you've now adapted the, in this little bit of a conversation, adopted the meta physician view of reality, which is the physics, but you know, we humans kind of operate in the space of ideas. Very much so like we've kind of in the collective intelligence of human beings have come up with a set of ideas that persist in the minds of these many people and they become quite strong and powerful, like in terms of like impact on our lives, they can have sometimes more impact than this table does than the physics and in that sense is there some sense in which our beliefs are reality even if they're not connected to? Absolutely [/INST] yes. Even if they're not real. Yeah. Even if Okay, so yes, absolutely. So, um, our beliefs are tremendously, they create social effects. Absolutely. Um, there was a belief that I'm going to use this example. There was a belief back in the day and they were talking about when I say back in the day, I'm a historian. So I'm talking about like 1000 years ago, right? That women had no souls. Okay so look I don't know if human beings have souls. I can tell you this though that if human beings households probably animals do too. That's my own personal belief. That's not a professor belief there. But there was this belief among the catholic magisterium which runs europe that women had no souls. So they had to have this big meeting about it, you know, did women have souls? But that belief had consequences for women. I mean women were treated and have been treated as if they didn't have souls. Um Okay, so there's </s><s>[INST] the soul was really the essence of the human. [/INST] It was, it's the it's called the animus, right? It's what is the essence of what it is eternal. You know when women were eternal, here's another example. Okay, this is an example from my own research. Alright, so they're in the catholic tradition, there is this idea of purgatory hell and heaven and these are three destinations that people can go to when they die and if you're great, you go to heaven automatically and you're considered a saint. If you're okay, you go to purgatory right and you suffer for a time and then get back into heaven. Um if you're terrible, you go to hell right, okay, well there was a place that the Catholics determined and this was a belief for a long time, like 1000 years or more. Um and it was called limbo alright and limbo comes from the latin Olympus and it means edge and it was either on the edge of hell or on the edge of heaven, no one really could determine which it was, no historians are like well this person says it was on the edge of heaven, well listen um this was a terrible first of all, there is no limbo anymore in 2000 and seven um Benedict the then pope got rid of the idea that there was limbo, okay so Catholics kinda went crazy because they didn't really know they forgot that limbo existed and they thought it was purgatory and they said how could you get rid of purgatory but actually he just got rid of this idea of limbo, </s><s>[INST] so that's a distinct thing from purgatory, it was the way people should know that they have a book on purgatory that came before [/INST] american cosmic, yes, I wrote a book on purgatory </s><s>[INST] anyway so limbo is a distinct thing from purgatory [/INST] yeah and the, that the types of people who go to limbo happened to be virtuous pagans, okay like Socrates or somebody like that um and Children who weren't baptized, so think of this, think of for like more than 1000 years mothers and fathers gave birth to babies who weren't baptized and couldn't be buried with their family in these burial and you know they, they couldn't be reunited with them in heaven, think of the pain is suffering that that caused, and that was nothing limbo is nothing yet the belief in it caused untold suffering and that's just a small example </s><s>[INST] and that was as real to them. [/INST] It was absolutely real. I mean, the effects were real. Let's put it that way. The place itself not real, </s><s>[INST] but the families themselves, do you think they really believed it? [/INST] They totally believed </s><s>[INST] it. Just the table is real. [/INST] Yes, I've read, But listen, we have trigger warnings today. Right, so don't read, this is going to make you upset. Okay, history, primary sources. No trigger warnings. Okay, so you're going through, like, you know, somebody's diary from 1400 and you hear the suffering and pain that they went through, there were times in my research where I'd have to put my primary source down, you know, and just basically go outside and take a walk because it was so horrific. I knew it was true because they wouldn't write something, you know, they're not going to write in their diary something that's not true and it was horrible. So, yes, these people went through untold suffering for nothing for, you know, because they had an erroneous belief, but they didn't know it was erroneous, </s><s>[INST] it's real to them. Yeah. Uh, so I don't know if you're familiar with donald Hoffman, he has this idea that in terms of uh, the distance we are from being able to know the reality, which is there, the physics reality is we're actually really, really, really, really far away from that. So like it's uh, I think his idea is that we're basically like completely [/INST] detached from it. Uh, </s> |
<s>[INST] up. And the interesting thing of I've noticed maybe myself too, because I've participated in the knife selling for like a short amount of time. It's probably the experience that most [/INST] people, </s><s>[INST] I don't know. I don't think it was cut. [/INST] I know what you're talking about, </s><s>[INST] but I think there are several variations of it. I think I was part of um Less popular one. It doesn't keep wanting to say it was called vector. [/INST] Yes, I something with a B. Was what I was gonna say, it might be vector. Um Yeah, I get what you're saying though. It's a multilevel marketing knife selling. </s><s>[INST] But the thing is I just remember my own small experience with it is I was too, I was embarrassed at myself for having like participated. I think there's an embarrassment. That's why you, that's why people down in the pyramid. Don't like speak about it, right? That you're part like, I'm trying to understand the aspects of human nature that facilitate this. Well [/INST] this is one of the problems with fraud is there's a tremendous embarrassment to being had. </s><s>[INST] Yeah, [/INST] also if you buy so slightly different human nature is that if you buy into a get rich quick scheme and then it doesn't deliver, you're more likely to blame yourself, then blame the product for not actually working. You go, well, there must be something flawed with me and they constantly reinforce this, they go, well, it's all about your hard work. The system works, look at me, I did it. So if you're failing, it must be some indictment of your character and you have to always double down, you have to double the system can't be flawed, you must be flawed. And so yeah, it's it's really messed up system, it really praise on people's psychology to to keep them in this loop. And that's why in some ways these things are so viral, even though they don't actually get most people a significant amount of wealth and they cost most people money. So it's very unfortunate, </s><s>[INST] Most people do have the dream of becoming rich, most young people right? [/INST] And the thing is is that everyone knows in business what do you sell? You sell solutions to problems. So so many young people want to get rich. The product is that pitch, if you sell them the dream why this gets so griff t and so cruel and predatory is because there is no easy solution to this, there is no solution that people are gonna buy um because the real solution people want is no work, no education, no skills required, no money up front and people will pay any price for that magic pill and people are happy to sell that magic pill. And I think those people are very cruel and I think deserve to get exposed for it. </s><s>[INST] So somebody that's been criticized for MLM type schemes is uh Andrew Tate. Uh, somebody that I'm very likely to talk with, people who have been telling me that I'm too afraid to talk to undertake. First of all, let me just say, I'm not afraid to talk to anyone. It's just that certain people require preparation and you have to like allocate your life in such a way that you want to prepare properly for them and you have to kind of think um who you want to prepare for, because I have other folks that have more power than this particular figure that I'm preparing for. So you have to make sure you allocate your time wisely. But I do think he's a very influential person That raises questions of what it means to be a man in the 21st century. Uh, and that's a very important and interesting question because young people look up to philosophers, to influencers about what it means to be a man. They look up to Jordan Peterson, they look up to Andrew Tate. They looked up to others to other figures. I think it's important to talk about that to think, what does it mean to be a good man in the society. Of course, in the other gender. There's the same question, what does it mean to be a good woman? I think obviously the bigger question, what does it mean to be a good person? But I swear to God. Um uh now interrupt. Okay. Uh, so that said one aspect of the criticism that Andrews received is not just on the misogyny is on the MLM aspect of the multi level marketing schemes. So is is there some truth to that? Is there some fraudulent aspect to that? [/INST] So yeah, I I definitely think so. I mean that's the main reason I criticized him. Um So let's back up. There's a few clarifications I need to make what Andrew Tate is selling is not multilevel marketing, although he is selling the dream, he's selling an affiliate marketing thing which is slightly different. So in multi level marketing, if I sell to you and then you go sell to two other people, I make money from those two other people down the chain. Multi level affiliate marketing is sort of like one level, I only make money. So Andrew Tate had this affiliate program where if you sold hustlers University to somebody else which sounds like something people would boomers would put on facebook in like 2010. Like I went to hustlers University um school of hard </s><s>[INST] by the way you were a member of hustlers University. So [/INST] yeah, I joined, I joined, I became a hustler. That's, that's in large part due to my, why I'm </s><s>[INST] so successful is because [/INST] of my hustler university membership, I'm just kidding. Um, but so it's an affiliate program. So you'd sell like I sell to you this $50 course and I make like $5 and Andrew Tate in perpetuity makes $50 a month off of you. Okay, what does this course actually sell? Right, because ultimately he's selling the dream, He's selling, hey, the Matrix has enslaved you. He's really gone down this like neo rabbit hole. Um, so the Matrix has enslaved you, your life is controlled by these people who want to keep you like kind of weak, you know, lazy, whatever you need to break out and you need to achieve the new dream, which is sort of like hustling your way to the top. You don't need the antiquated systems of, of school, you can just pay me $50 a month and I will teach you everything. Okay? So what do you actually get well and why is it a scam? So you actually, I think it's just a scam in terms of like value and like you're selling based on these completely unrealistic things. He's like, let's get rich, okay, you get a series of discord rooms, you know what Discord, most people know what discord is? It's like a bunch of, you know chat rooms basically, right? </s> |
<s>[INST] Yeah. So, [/INST] so what </s><s>[INST] is [/INST] good? But, but let's, what does it mean in a situation like that? Whenever they want to mess with you, it means they can come and they will look and they will find something. So it means that every day I'm trying to do business, I'm running the risk of being harassed and or maybe even put in jail depending on what it is. </s><s>[INST] I mean, you're an incredible person because it seems like there's two ways to change this, uh, become president or gain power in the country and to try to change the laws, which seems really difficult to do. And the other way is fight through the laws and create the business anyway, build the business community. And through that method create a huge amount of pressure. You're totally [/INST] getting it by with your last part because this is the other thing. And this is where I get so upset sometimes with my fellow Africans because they get so disgusted by what they're seeing, right? And they think the answer is to go for politics, let's go be president, let's go be this, let's go be that and we're gonna change everything. I see that in the US to people thinking that presidents have all of his power. Do you know who has the least power in government? The president, I mean people don't get that um your best, but if you're gonna if you insist on going into politics, stick to the local level, that's where all the skeletons are buried and hidden and that's where you can make the most impact local level. I know it's not shiny. I know it's not exciting, but that's where it's at. So if you must go into politics, but there there's another way. So in my case what I do is two things I preach and I practice I preach when I'm here talking to about this, I'm preaching, I am sharing with people that is which I found. And by the way the answer was there I was doing these two businesses, realizing the difference in treatment of um the doing business environment of the U. S. Compared to the doing business environment of Senegal. And at first I was like of course us, everything is messed up is because we're poor country, but when I started to put two and two together, I'm like you're poor because you have no money at least not enough money to take care of your basic needs, you have no money because you have no source of income. Where does a source of income come from? For most of us, it comes from a job, doesn't it? And then some people sometimes that my UC Berkeley class, they say, oh no, it comes from government to I'm like, I would like to think that even if you work for government are gonna be paid something right? And I'm like, yeah. And then even before I can say something like, oh yeah, because that money we used to pay our public officials comes from taxes. You know, employers, employees, we go back to the private sector for most of it from where this whole thing is created. So it's clear you're poor because I have no money, no money because no source of income, source of income for most of us is a job we're talking about. So where do jobs come from? The private sector, primarily small and medium sized enterprises, then don't you think that we should make it easy that we should have um friendly doing business environment. </s><s>[INST] And also a lot of the a lot of it comes not just in the small, medium sized businesses, but I think a lot of the values created from new ones being launched, right? It's not just like me like saving somehow through regulation the ones that already [/INST] there, you know, it's </s><s>[INST] like letting the market, letting the new better ideas flourish. [/INST] Yes, it's about. What what I mean by doing business environment is all the things that you and I talked about earlier. Even the access of electricity is part of doing business but doing business. So basically when I've discovered all of that, when I put all of these dots together, then I'm like, well I guess the business and it makes sense. Lex if you want to grow tomatoes, you're gonna have to have two things. One is a good seed, right? It has good attributes and then you're gonna have to have um a good environment for it is the soil the right one. What's your ph level? All of those good nutrients you put in it. Is it in a place that has tons of sun? How much an exposure or not? The climate in general is gonna be called not not you can't have some beautiful tomatoes in the middle of Siberia. Last time I checked. So same thing here, you know, Mohammad Yunus, the noble um laureate for peace. Said poor people are bonsai people, they're the same people. If you put them in the normal natural a friendly habitat where they can thrive, they become the tallest tree in the forest? Poor people are bonsai people. So you see the tiny pot you put around the bonsai tree, that's the tiny pot that created by giving me such a hostile business environment that basically were put together by the set of laws that you have put that basically I have to jump through as a business person practicing business in my country. If you turn that environment into a friendly environment where I am not married to my employees, I have flexibility of the labor laws of simple, straightforward clean. Where the tax code is very simple. It's not worth truckloads of laws like in my country is so complicated. You have to hire a C. P. A. Which cost more money and even them tell them girl, we're gonna make some mistakes. They don't talk, they don't talk to me like that. You know, you know, they don't send me, they shouldn't they better not. But they say whatever they say, you know, you know like we're gonna but bottom line is we're gonna make mistakes. This thing is so complicated, gonna make mistakes. So which means my ask is on the line. So anyway, so, so if the tax code was so simple, straightforward, like it is maybe in texas where up till a threshold, you owe me nothing, go online. Five minutes, fill out your taxes, you're you're compliant. Keep keep building your business because that's what we need from you. If you made it so easy and straightforward, then you know what that's when you get all of these people like what you're talking about saying, you know what my name is, Aminata and I live in the middle of nowhere Senegal. But you know what, I've got this great idea which is for this really hot, nice hot sauce. But I know the americans are gonna love, I'm hearing that hot sauce is a big thing, let me bring it to them. But everything is there for you to jump into the ring of entrepreneurship. You don't have to know someone like my God, you don't have to even have the ability to sell yourself. Maybe like I can sometimes you are someone with a great idea, you're willing to work hard for it and pour everything you got into it, guess what? It's there, You can get into the race, you </s> |
<s>[INST] Do you draw any parallels with our time, and what are some key differences? There's been contested elections, Florida, Florida, Florida, with Al Gore, and there's been just contested election after contested election, and of course, most famously recently [/INST] the contested election that led to January 6. So I think a couple of parallels and a couple of differences. One parallel is that when you have close elections, the losing side is never happy. It's a myth that when you have a close election, the other side just accepts it. And it's not, that doesn't happen. And we need to be attentive to that and ready for that. January 6 actually should surprise us not because it happened, but because it hadn't happened before. People who lose a close election are never happy and they always think that something has been done. That's one parallel. Second parallel is elections are violent. We have this myth that our elections are peaceful. There's always violence involved in one way or another, violence in either trying to prevent people from voting or violence in preventing people from preventing people from voting, right? Elections are not peaceful walks in the park. And that's why most countries have a centralized system to manage elections and provide protection for people. We need to think about that. A lot of people don't vote because they're afraid they don't want to take the time, but they're also afraid that they're going to anger someone or that they're going to be seen as politicizing an issue. Differences. In 1876, there was fraud in the election. There were people who voted two, three times. One of the things the Ku Klux Klan did is it prevented black people from voting and that it helped white people go to multiple voting booths. And this was quite common. In the 1880s, if you went to vote, here's how it would happen in a place like Chicago and New York. The union boss from your factory would come and get you at the factory, give you lunch, get you drunk, and then drive you from one voting booth to another and give you a ballot that you would bring in and just, and he would watch you deposit that ballot. Sounds pretty nice. Not going to lie. I take that ride. So that's a difference. That is not how our elections work now. One of our great accomplishments has been to eliminate virtually all the fraud in our elections. How have we done that? By creating safeguards. It is very difficult. All the evidence we have is that the minimal fraud that's occurred in elections are onesies and twosies, and it's never in the last 20 years had any big difference in the outcome of elections. So that's a big difference. And then another big difference, I think, is that in that time, the Democrats and Republicans are on the opposite sides of where they are now, and that changes everything. So the Democrats then are the party of the Confederacy. The Democrats are the party of exclusion. The Republicans are more the party of economic expansion. And the Republicans are the big </s><s>[INST] ten party. We're reversed today. Do you think because there's much less election fraud now, like you described, one of the lessons we want to maybe learn from that is there doesn't actually have to be election fraud for either side to claim there's election fraud. It seems like it's more and more common. And it seems to me that in 2024 election in the United States, if a Republican wins, there would also be just maybe just as likely as if a Democrat wins, that there would be nuanced [/INST] claims of election fraud because it's become more and more normalized. I think what this history shows is that our election system makes it easy for people to claim fraud because it's so unnecessarily complex. First of all, we don't have a system where the person who gets the most votes is necessarily the winner. So that already creates one problem. Second problem is everything I talk about this in the book is controlled at the county level. So what happens with Hayes and Tilden in 1876 is you have one county official who says they think one person won, another county official thinks says the other person won, there's no centralized system. It would be as if we allowed every airport to control safety and airplanes, our airplanes would not be safe. Our airplanes are safe because the FAA and the National Transportation Safety Board have strict universal guidelines for what makes for a safe plane and therefore our planes generally don't fall out of the sky. Our system is very complex. It has complex rules and has too many people who have authority in too many different places. Complexity makes it easier for someone to make an argument that the wrong thing has been done. We should simplify the system. In Brazil, they had a very close election and it's very hard for Bolsonaro who lost that close election to claim there was fraud because there's a central authority run by the judiciary that counted the votes and it's just simple. It's not about which states, it's not about who the county officials were. Did he claim or no? </s><s>[INST] He has not acknowledged that he lost. To push back on your statement, I'm undefeated in monopoly and risk because anytime I lose, I walk away claiming there was fraud and cheating involved and I refuse to believe otherwise. I just think that accusations of fraud is [/INST] a narrative that's disjoint from the reality of whether there was or not fraud. I agree, but I think we make it a little easier for that narrative by having a complex convoluted </s> |
<s>[INST] people don't know tor browser is a way to be completely anonymous. As [/INST] long as you properly know how to use it. Huge caveat. Alright. So developed by the United States Navy. And they developed </s><s>[INST] this. Yeah, [/INST] it </s><s>[INST] wasn't the hackers [/INST] that interest us Navy To this day. The # one Funder of tour military to this day. Alright, </s><s>[INST] interesting. I mean the same I guess with the internet the origins are was [/INST] developed so that operatives could communicate with each other without being identified. Alright. That then goes open source, they release it. E. F. F. Comes in and starts sponsoring and everything else like that. The next idea was, well, you know, people get around their country's firewalls, whistleblowers can use it, things like that. Well, someone forgot to mention that the first adoptees of tech if you can use it to launder money or remain anonymous are criminals. So criminals start to use the damn thing. All right. So along the same time we get, well a few years later we get Satoshi Nakamoto pops up with his ideas for Bitcoin and then ross Ulbricht runs with it. Ross Albert decides he's going to start up Silk Road. So initially the people who were using tour, which later is the dark web people were using tour. We're just talking with each other, visiting websites communicating like that. Someone figured out, hey man, we could host websites on this thing and they have a lot of trouble finding the box. So that is the advent of Silk Road all of a sudden ross Ulbricht has this idea that he's going to change the world by becoming the largest drug dealer on the planet. So he opens up the Silk Road and the only payment instrument he allows is Bitcoin. So if those people out there wondering why Bitcoin is going at what 44 K. Today, </s><s>[INST] Yeah. Started by the time this is out, it could be 100,000 or 10,000. Absolutely. [/INST] It's 10,000. I'm going to buy some, </s><s>[INST] which is a hilarious statement to make because that statement would be ridiculously wrong like five years ago. [/INST] I know </s><s>[INST] people 100 years from now will be laughing. Wait, it was that [/INST] low. So he only accepts Bitcoin. And that's of course the the initial use case of crypto is no one wants to admit it today, but the initial use cases, we're going to buy a bunch of pot, we need somebody, we need a way to pay for it. So that's, that's what happens ross. It's, it's really interesting to me if you if you look at motivations of cybercriminals, the motivations are status cash ideology. Alright, my guys, all cash across the board, all cash ross is ideology. He really believed he was going to change the world. He really didn't. I've been fortunate, I actually know the guy who ran Silk Road to and I have talked to the kid everything else and I will tell you that those guys who are motivated by ideology, they are a completely different breed. They really are. It's not, you know, the cash guy. It's it's it's low hanging fruit, the ease of, it's hard to stop committing crime, but it's much easier for a cash motivated individual to stop than it is that ideology guy, uh, that silk road to guy, he's still got it. You know, he's not breaking the law. But you can see it's like he wants to, he wants to. So it's it's, um, </s><s>[INST] that's fascinating that, I mean, the worst atrocities in human history are committed with people that operate under ideology, all the other motivations in which weaker, but, [/INST] you know, you think about it, you've got with ross, I mean, very bright guy, very bright guy. But think about the amount of cognitive dissonance that the guys got that he thinks he's going to change the world by running a drug site. I mean, certainly, I mean, could he have changed the world? Yeah, couldn't have done it like that. Probably not. </s><s>[INST] Well, I guess I can steal man those arguments as I listened to quite a few libertarians and you can push that to anarchists. And, you know, there's a lot of people that argue. Um, [/INST] so I </s><s>[INST] actually talked to, uh, to faculty to professor at Columbia, who actually argues that all drugs should be legalized and not at a philosophical level, political level, but the fact that, um, all the negative consequences of drugs that people talk about are actually have to do with other factors in your life. [/INST] I would agree with that. And </s><s>[INST] so that's okay. But that's more like a argument about the negative aspects of drugs. I think the ideology comes in where it's like, well, nobody should tell you what to do. You should be, you should have the responsibility of your own actions like, uh, um, the government or any other institutions shouldn't be the, [/INST] the </s><s>[INST] rule setters, the constraints for how you live your life. And so that I could, I could see that argument being made. And ultimately, if you, uh, like create an open market for drugs, how that could build a better society, it might break down the outdated, the corrupt, the bureaucratic institutions. I mean, you can make that you can make that [/INST] argument. And let's be fair, I want to be fair with it. I mean, could did he change the world? We do have this whole thing called Cryptocurrency. </s><s>[INST] Yeah. In the long arc of history, perhaps. [/INST] Yeah, we do have that. That's, that's a biggie. So, </s><s>[INST] and that might might have been for it to take hold in society. Maybe the darker parts of society at first, maybe that was necessary, [/INST] Right? I mean, maybe I will see how it pans out. Shadow Crew. We had this Guy Albert, Gonzalez, this kid's name. We had we were growing so big that I had to start farming things out. So the first thing I started farming, I instituted this review system kind of establishing that trust mechanism even further for criminals use, we needed somebody to take care of our tech aspects of the forum. So associate of mine by the name of kim taylor. We were looking for a forum turkey. He comes to me one night and he's like a founder for Kentucky and I was like, who's that? He's like this kid. And I was like, isn't he good? He's like, well he knows the software. I was like, okay, we just signed his ass on. He went by the screen name of company johnny was his screen name and he starts selling credit cards after a while under the screen name of scarface and That CB, one breach where you're cashing out the track, two's at ATMs, you know, $40,000 a day. So Albert's in New Jersey one day, broad daylight and stands at an A. T. M. For 40 minutes just standing there feeding in one A. T. M. Card after another point out cash Taking the 20s out, stuff them in that backpack. Meanwhile, just across the street, a couple of cops just happened to be there and they start noticing this kid just standing there. So 40 minutes they watch this kid, 40 minutes finally, one cop looks at the other, let me see what's going on </s> |
<s>[INST] And it's kind of like command line, it's not user friendly, it doesn't allow for clean visualizations and you're exactly right. So you're using this kind of debugger usually when you're at wits end and there's a problem that you can't figure out why by just looking at the codes, you have to find it. That's how I guess normal programmers use it. But you're saying there should be tools that kind of visualize and help you as part of the programming process, just a normal programming process to understand the code deeper. [/INST] Yeah, when I'm working on, when I'm working on like my C, C++ code, I'm always running it from the debugger, you know, just I type in the code, I run it many times. The first thing I do after writing code is set a breakpoint and step through the function. Now, other people will say it's like, oh, I do that in my head. Well, your head is a faulty interpreter of all those things there. And I've written brand new code, I want to step in there and I'm going to single step through that, examine lots of things and see if it's actually doing what I expected it </s><s>[INST] to. It is a kind of companion, the debugger, like you're, you're now coding in an interactive way with another being, the debug is a kind of dumb being, but it's a reliable being. That is an interesting question of what role does AI play in that kind of, with codecs and these kind of ability to generate code might be, you might start having tools that [/INST] understand the code in interesting, deep ways that can work with you. There's a whole spectrum there from static code analyzers and various kind of dynamic tools there up to AI that can conceivably grok these programs that no, literally no human can understand. They're too big, too intertwined and too interconnected, but it's not beyond the possibility of understanding. It's just beyond what we can hold in our heads as kind of mutable state while we're working on things. And I'm a big proponent again of things like static analyzers and some of that stuff where you'll find some people that don't like being scolded by a program for how they've written something where it's like, oh, I know better. And sometimes you do, but that was something that I was, it was very, very valuable for me when, and not too many people get an opportunity like this to have. This is almost one of those spiritual experiences as a programmer and awakening to, the software code bases were a couple of million lines of code. And at one point I had used a few of the different analysis tools, but I made a point to really go through and scrub the code base using every tool that I could find. And it was eyeopening where we had a reputation for having some of the most robust, strongest code, where there were some great things that I remember hearing from Microsoft telling us about crashes on Xbox and we had this tiny number that they said were probably literally hardware errors. And then you have other significant titles that just have millions of faults that are getting recorded all the time. So I was proud of our code on a lot of levels, but when I took this code analysis squeegee through everything, it was shocking how many errors there were in there. Things that you can say, okay, this was, this was a copy paste, not changing something right here, lots of things that were the most, the most common problem was something in a printf format string that was the wrong data type that could cause crashes there. And you know, you really want the warnings for things like that. Then the next most common was missing a check for null that could actually happen that could blow things up. Those are obviously top C, C++ things. Everybody has those problems. But the long tail of all of the different little things that could go wrong there, and we had good programmers and my own code stuff that I'd be looking at, it's like, oh, I wrote that code. That's definitely wrong. We've been using this for a year. And it's this submarine, this mine sitting there waiting for us to step on. And it was humbling. And I reached the conclusion that anything that can be syntactic allowed in your language, it's going to show up eventually in a large enough codebase. You're not going to, good intentions aren't going to keep it from happening. You need automated tools and guard rails for things. And those start with things like static types, or even type hints in the more dynamic languages. But the people that rebel against that, that basically say, that slows me down doing that, there's something to that. I get that. I've written, I've cobbled things together in a notebook. I am like, Wow, this is great that it just happened. But yeah, that's kind of sketchy, but it's working fine. I don't care. It does come back to that that value analysis where sometimes it's right to not care. But when you do care, if it's going to be something that's going to live for years, and it's going to have other people working on it, and it's going to be deployed to millions of people, then you want to use all of these tools, you want to be told, it's like, no, you've screwed up here, here, and here, and that does require kind of an ego check about things, where you have to be open to the fact that everything that you're doing is just littered with flaws. It's not that, oh, you occasionally have a bad day. It's just whatever stream of code you output, there is going to be a statistical regularity of things that you just make mistakes on. And I do think there's the whole argument about test-driven design and unit testing versus kind of analysis and different things. I am more in favor of the analysis and the stuff that just like you can't run your program until you fix this rather than you can run it and hopefully </s> |
<s>[INST] Chicken with skin on it. Oh just because of the biology of death [/INST] just well when you but when you hold people's bodies in your hands with no gloves on you know what that feels like when you touch raw meat again it's the </s><s>[INST] same thing that's what that feels like when when is a dying or dead body well [/INST] my well my friend was blown into a million pieces so I just had pieces so there was no there was no differentiator of like this was his thigh or this was his torso or there was like there was not a fucking back there's only one instance with the boot. But at that point we had been in some firefights and we had been taking some rounds, but it was more like take a – we would get hit, and then we'd duck into a compound, we would set up, and then we would be firing. I wasn't really involved in a lot of the firefights until after this. After that, the rest of the week I was like I was angry and I wanted them all to go, and I wanted to be in every position to take them out myself. So I put myself in every position. So I made sure I was on the roof. I made sure I was there. I made sure, hey, you need something. I'll fucking run it. I don't care if I die anymore, because as soon as that happened, my light switch went off. </s><s>[INST] It didn't matter anymore to me. Can you go through what happens? Yeah. So are you hearing these screams? [/INST] Yeah. So yeah. So the I.D. went off and what had happened was they put an I.D. inside of a gray putt and the gray putt has rectangular wall, rectangular holes in the wall. And there's just like one door and it's this tall mud hut with just all these like holes in it. And they had put an I.D. underneath a pile of sticks and had a metal detector. The Brits carry them. I've never seen. I think other countries have them, but I've only ever seen them use it. And that's how we were kind of detecting if there was an I.D. We must have hit it, the sticks or something, and it set it off. And it just it was over. There's no way he felt anything. And then there was another guy at the door bent down on one knee and he was facing and kind of watching for and then the blast hit him on this side. And so it took him out and pulled his kid off, pulled his helmet, pulled everything off, fucked him all up big time. This is one I.D. But it was in a contained area and he was in the doorway. </s><s>[INST] Up and out, up and out. Can you explain what an I.D. is and how does it work? [/INST] I can do my best. They're improvised explosive devices. They can be used pretty much out of anything to make anything. So garbage. When we got to Afghanistan, they did the I.D. meeting with us. They're like, these are what we're finding that they would show us diffused I.E.D.'s. So they would see those big blue drums filled with gasoline buried in the ground. You would see a wire. It would go to a pressure plate. You hit the pressure plate that would hit that and it would go. You would see IDs some of them were ridiculous theew in the engineering that went into some of these was was hilarious because they were thinking they were thinking to use everything they could. There's a cigarette pack they had used they lined the inside with tin foil And when you stepped on the tin foil it had a piece of wire And it was enough of a spark to set off a line of batteries that we had thrown out that we're all dead when you fuse them all together there was enough juice to make it go then they would attach that to like like phosphorus or Gasoline or whatever they could that would make a big boom They would use Yeah, it's what you never kick garbage on the ground you'll never see me kick something on the ground You'll see me walk around it always. If I ever see a pile of rocks or something that looks like it shouldn't be there, I won't walk near it. Even now. Because they use that pile of rocks to remind people there's something there. We don't know what that means, but we know that something's there. And very often they would use anything. Garbage, wires, we had to burn everything for a reason. </s><s>[INST] It's so terrifying for the source of death to be like little parts of the environment and then people. That don't look like they're not dressed as soldiers. No, they are. It's like civilians and like regular, because then when you have to come back or even there, you're just surrounded by danger and then you distrust everything, essentially. [/INST] It's a problem and that's why you have such PTSD issues with the soldiers we have now. Because you're in the environment in which it's very similar. So there's this one IED. So this one IED, I still don't know what it was, went off. Body flew. The guy at the door, he kicked out. He was all broken and bleeding and a mess. At that point, the radio started going crazy. Like I could hear the guys yelling and screaming, trying to figure it out, and then you could hear the numbers being called. KIA, number, number, number, number. I don't know anybody's service number. I don't know what's going on. Next thing you know mortar rounds start coming down. And live fire starts happening. And I'm like holy fuck, things are popping off. And I remember just looking at being like, we need to go now. And I just got this, I was like, we're going. going and they're like, hold on, Burns. And I'm like, we're fucking going. Like, I wasn't dealing with it well. And they're like, all right, all right, go, go, go, go, go. So we went and we, you know, I helped out with that other individual, kind of held him down, started doing medic work on him. And he just kept saying, where's, where's, where's, he was in such a state of shock. I've never seen somebody's eyeball so big in my life. She's good, where's, where's, where's, yeah, he's good, buddy, he's good, he's good. Picture like a super thick Scottish accent though, because these guys were just, and when they talk fast, it's even worse. And then so I ran over and we, we jumped down into the ditch along the side of the road because the road hadn't been cleared. And we're running through these tall, they look like cannabis plants, but they're not, but there's, it's just very thick bush. And I felt like I was running in slow motion. So if you picture one of your video games, where it like the tunnel vision and then you're just, you can hear your breathing is like that, and you're running and you can't move fast enough. And you're like trying to get there, and we hit the road and the rounds are coming down and mortars are coming down. And they're like, okay, on three run. So we run on three and we run into the compound, I mean, into the grape hut. And I remember looking around and very seriously going, where is he? Just genuinely asking. I think it was been messaging me. And he's been incredible. he's one of the best soldiers I've ever served with. He was a higher up, so he was running part of this. He's messaged me, and he was giving me some information, and he's like, I was in there with you. And he goes, I remember because you handed me the boot. And cause I walked over and I, all the rounds were, we were being shot at, mortiffs were coming down, but it was this slow motion, and I remember walking over to the hole in the ground and seeing his boot in the ground, but it was, his leg was still hanging, just below his knee was still in it. But the boot was perfectly laced up. Like the boot was fine. And I just, I held it and I turned and I looked at the guys </s> |
<s>[INST] So that's, that is the counterpoint. But it seems like you would need to run it a lot more than you do even though right now people could say that RL is very inefficient but it seems to be way more efficient than one would imagine on paper that the simple updates to the policy, the policy gradient that somehow you can learn exactly, you just said whatever the common actions that seemed to produce some good results that that somehow can learn anything, it seems counterintuitive, at least is there some [/INST] intuition behind us? I think there's a few ways to think about this the way I tend to think about it mostly original when so when we started working on deep reinforcement learning here at Berkeley, which is maybe 2011, 12, 13. Around that time, john Schulman was a PhD student initially kind of driving it forward here and can it, the way we, we thought about it at the time was if you think about rectified linear units or kind of rectifier type neural networks, um what do you get? You get something that's piecewise linear feedback control. And if you look at the literature, leaner feedback control is extremely successful. Can solve many, many problems surprisingly well. Remember, for example, when we did a helicopter flight, if you're in a stationary flight regime, not a non station, but the stationary flight regime like hover, you can use linear feedback control to stabilize the helicopter. Very complex dynamical system. But the controller is relatively simple. And so I think that's a big part of is that if you do feedback control, even though the system you control can be very, very complex. Often relatively simple control architectures can already do a lot. But then also just linear is not good enough. And so one way you can think of these neural networks is that something they tiled the space? Which people were already trying to do more by hand or with finite state machines? Say this linear controller here. This linear controller here, no network learns the towel dispenser linear controller here. Another linear controller here, but it's more subtle than that. And so it's benefiting from this linear control aspect is benefiting from the tiling, but it's somehow telling it one dimension at a time, because if, let's say you have a two layer network, even the hidden layer, you make a transition from active to inactive or the other way around. That is essentially one axes but not access a line, but one direction that you change. And so you have this kind of very gradual tiling of the space. We have a lot of sharing between the linear controllers that tile the space. And that was always my intuition. That's why to expect that this might work pretty well. It's essentially leveraging the fact that linear feedback control is so good. But of course not enough. And this is a gradual tiling of the space with linear feedback controls that share a lot of expertise across them. </s><s>[INST] So that that's uh that's really nice intuition. But do you think that scales to the more and more general problems of we start going up the number of control dimensions uh when you start going down in terms of how often you get a clean reward signal. Does that intuition carry forward to those crazier, weirder worlds that we think of as the real world. [/INST] So I think where things get really tricky in the real world compared to the things we've looked at so far with great success and reinforcement learning is the time skills which takes us to an extreme. So when you think about the real world, I mean, I don't know, maybe some student decided to do a PhD here. Right, okay, that's that's a decision. That's a very high level decision. But if you think about their lives, I mean any person's life, it's a sequence of muscle fiber contractions and relaxations and that's how you interact with the world and that's a very high frequency control thing. But it's only what you do and how you affect the world until I guess we have brain readings and you can maybe do it slightly differently. But typically that's how you affect the world. And the decision of doing a PhD is like so abstract relative to what you're actually doing in the world. And I think that's where credit assignment becomes just completely beyond what any current or algorithm can do. And we need hierarchical reasoning at a level that is just not available at all yet. </s><s>[INST] Where do you think we can pick up hierarchical reasoning by which mechanisms? [/INST] Yeah. So maybe let me highlight what I think the limitations are of what already was done 2030 years ago. In fact you'll find reasoning systems that reason over relatively long horizons. But the problem is that they were not grounded in the real world. So people would have to hand design uh some kind of logical dynamical descriptions of the world and that didn't tie into perception. And so it didn't tie into real objects and so forth. And so that that was that was a big gap now with deep learning. We start having the ability to really see with sensors process that and understand what's in the world. And so it's a good time to try to bring these things together. one. I see a few ways of getting there. One way to get there would be to say deep learning can get bolted on somehow to some of these more traditional approaches now bolted on would probably mean you need to do some kind of end to end training where you say my deep learning processing somehow leads to a representation that in term uses some kind of traditional underlying dynamical systems that can be used for planning. And that's for example, the direction Aviv tomorrow and the north Korea attach here have been pushing with causal info again and of course other people to that, that's that's one way can we somehow force it into the form factor that is amenable to reasoning another direction had been thinking about for a long time and didn't make any progress on was more information theoretic approaches. So the idea there was that, what it means to take high level action is to taken choose a latent variable. Now that tells you a lot about what's going to be the case in the future because that's what it means to to take a high level action. I say, okay, what I decide I'm gonna navigate to the gas station because we need to get gas for my car. Well that will now take five minutes to get there. But the fact that I get there, I could already tell that from the high level action that took much earlier. Um, Dad, we had a very hard time getting success with um not saying it's a dead end necessarily, but we had a lot of trouble getting that to work. And then we start revisiting the notion of what are we really trying to achieve? Um What we're trying to achieve is not to say higher. He per se. We can think about what is hierarchy give us um What we hoped it would give us this better credit assignment. Um Kind of what is better credit assignment is given is giving us, it gives us um faster learning, right? And so faster learning is ultimately maybe what we're after. And so that's what we ended up with the RL squared paper on learning to reinforcement learn which at the time Rocky Guan lead. Um And that's exactly the meta learning approach. We say, okay, we don't know how to design hierarchy. We know we want to get from it. Let's just enter and optimize for we want to get from it and see if it might emerging. We saw things emerge the maze navigation had consistent motion down hallways, which is what you want. The hierarchical control should say I want to go down this hallway. And then when there is an option to take a turn, I can decide where to take a turn and out and repeat. Even had the notion of where have you been before or not. Do not revisit places you've been before. Um It still didn't scale yet to the real world kind of scenarios I think you had in mind, but it was some sign of life that maybe you can meddle learn these historical concepts. </s> |
<s>[INST] That's a really compelling notion. But how does that help you arrive [/INST] coming to where the book came from? </s><s>[INST] Yes. [/INST] So what got me, I worked on string theory. I also worked on loop quantum gravity and I was one of the inventions of loop quantum gravity and because my strong belief in some other principles which lead to this notion of wanting a quantum theory of gravity to be what we call relational or background independent. I tried very hard to make string theory background independent and in and up developing a bunch of tools which then could apply directly to general relativity and that became loop quantum gravity. So the things were very closely related and have always been very closely related in my mind. The idea that there were two communities, one devoted to strings and when developed two loops is nuts and there's always been nuts. </s><s>[INST] Okay. So so anyway there's this nuts community of loops and strings that are all beautiful and compelling and mathematically speaking. And what's the trouble with all that? Why is that why is that such a problem? [/INST] So what? So I was interested in developing that notion of how science works based on the community and ethics that I told you about. And I wrote a draft of a book about that which had several chapters on methodology of science and it was rather academically oriented book. And those chapters were the first part of the book, the 1st 3rd of it. And you can find their remnants and was now the last the last part of the trouble with physics. And then I described a number of test cases, case studies and one of them which I knew was the search for quantum gravity and string theory and so forth. And I wasn't able to get that book published. So somebody made the suggestion of flipping it around And starting with the story of string theory which was already controversial. This was 2004, But I was very careful two be detailed to criticize papers and not people you don't you want to find me criticizing individuals, you'll find me criticizing certain writing. But in any case, here's what I regret. Let me make your program with while, as far as I know with the exception of not understanding how large the applications to condense the managers say of A D M C F A DSC ft will get. I think largely my diagnosis of string theory as it was then has stood up since 2006 when I regret is that the same critique I was using string theory as an example and the same critique applies to many other communities in science you know of including and this is what I regret. My own community. That is a community of people working on quantum gravity aside string theory, but and I considered saying that explicitly, but they say that explicitly, since I'm it's a small, intimate community, I would be telling stories and naming names of and making a kind of history that I have no right to write. So I stayed away from that but was misunderstood. </s><s>[INST] But if I may ask, is there a hopeful message for theoretical physics that we can take from that book sort of that looks at the community, not just your your own work on not with causality and non locality, but just broadly in understanding the fundamental nature of our reality. What's your hope for the 21st century in physics [/INST] that was well, do we solve the problem </s><s>[INST] that we solved the unfinished problem of Einstein's? [/INST] That's certainly the thing that I care about most in hide from us. Let me say one thing among the young people that I work with, I hear very often in sense a total of this interest in these arguments that we older scientists have and an interesting way each other is doing and this is starting to appear in conferences where the young people interested in quantum gravity make a conference. May invite loops and strings and causal dynamical triangulation and causal set people and we're having a conference like this next week, a small workshop at perimeter and I guess I'm advertising this and then the summer we're having a big full on conference which is just quantum gravity. It's not strings, it's not loops but the organizers and the speakers will be from all the different communities and this to me is very helpful </s><s>[INST] that the different ideas are coming together [/INST] at least people are expressing an interest in that. Yeah, </s><s>[INST] is a huge honor to talking to you lee thanks so much for your time today. Thanks for listening to this conversation and thank you to our presenting sponsor, cash app, Download, it use collects podcast, you'll get $10.10 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. Follow on Spotify, supported on Patreon are simply connect with me on twitter Elex Friedman and now let me leave you with some words from lee Smolin. One possibility is God is nothing but the power of the universe to organize itself. Thanks for listening and hope to see you next time. [/INST] </s> |
<s>[INST] place as a species. You think we now have something in our hands that may destroy the earth [/INST] and possibly exchange reaction that </s><s>[INST] destroys the universe. Let's try it anyway [/INST] as a, as a </s><s>[INST] stage that we're at as a species. [/INST] But with that power comes an </s><s>[INST] ability to get to other planets to survive [/INST] long term. </s><s>[INST] And when you think about the heat death, that just becomes that's [/INST] a an ad infinitum </s><s>[INST] question, if you keep thinking, well, [/INST] we survived, we go to the </s><s>[INST] next son and then you go to the next son. [/INST] Eventually the question would be </s><s>[INST] well, if you just keep doing that forever. At some point, the universe either continues to expand or [/INST] collapse back in on itself and the heat </s><s>[INST] death is more likely at this point where it just keeps expanding, expanding, everything is too far away. But even in that case, I think if we had a fundamental knowledge of physics and space time that you could try and restructure [/INST] it quite literally the shape of the </s><s>[INST] universe to prevent it, I think we [/INST] would, I think we would want </s><s>[INST] to survive. I think, you know, unless [/INST] we had done the math and we </s><s>[INST] think that there's a greater chance that the [/INST] next universe would </s><s>[INST] form and make more [/INST] life. Maybe we would. But even </s><s>[INST] then, I think [/INST] humans have always </s><s>[INST] wanted to survive and and [/INST] you could argue maybe should survive </s><s>[INST] because and are able to engineer systems that [/INST] help us survive </s><s>[INST] and always have. Yeah. So what is this though? Those are bomb Yeah, the hydrogen, Yeah, [/INST] there's there's </s><s>[INST] nothing more [/INST] terrifying and </s><s>[INST] somehow inspiring [/INST] than watching the mushroom cloud </s><s>[INST] of a nuclear explosion. It's like humans [/INST] are capable of this. </s><s>[INST] They are capable [/INST] of leveraging the power of nature </s><s>[INST] to completely [/INST] obliterate everything </s><s>[INST] and and to create [/INST] propulsion. I mean, most of the Voyager </s><s>[INST] spacecraft are nuclear powered because it's still in many ways the [/INST] most efficient way to get a </s><s>[INST] tiny amount of visible [/INST] material and make power out of it, </s><s>[INST] you know, So they're [/INST] still slowly drifting </s><s>[INST] there past the heliosphere. They're out now into Interstellar space and their nuclear [/INST] powered. So it's like any tool or technology. It's a it's a tool or a </s><s>[INST] weapon, depending on how you hold it. [/INST] Are we alone in the </s><s>[INST] universe, chris mason? What do you [/INST] think so, yeah. The presumption that you've just </s><s>[INST] mentioned is [/INST] let's just focus on our thing </s><s>[INST] for now for [/INST] now. Well, I think we, as far as we know </s><s>[INST] with another century in life [/INST] in the universe that we've found </s><s>[INST] yet. And and I think there's [/INST] probably bacterial life out </s><s>[INST] there just because we found it [/INST] everywhere. We've </s><s>[INST] looked on Earth. It [/INST] is </s><s>[INST] and there's, you know, hella filic organisms that can survive in extreme [/INST] salts. There are </s><s>[INST] sacrifices that in extreme [/INST] cold, there's you know, basically organisms can survive </s><s>[INST] in really almost any [/INST] possible environment. They </s><s>[INST] can adapt and find a way [/INST] to live. </s><s>[INST] But as far as we know, we're the only sentient ones. And I think [/INST] this is the famous the direct </s><s>[INST] equation or you know, [/INST] how many, where </s><s>[INST] is everyone? Is that [/INST] what Enrico fermi said is the why haven't we heard from </s><s>[INST] anyone? There are these other life forms? I actually think the [/INST] question is wrong </s><s>[INST] to phrase it that way because [/INST] the unit the earth has only been </s><s>[INST] Here for 4.5 [/INST] billion years. And we and you know, life maybe </s><s>[INST] only for a few billion of those years complex life only for several 100 [/INST] years, 100 million years of life we've </s><s>[INST] actually had, you know, and and humans [/INST] only in the past few million years since our last common ancestor. So </s><s>[INST] it's not that much time. [/INST] But if you think even further </s><s>[INST] back, the universe hasn't had that much time itself [/INST] to cool </s><s>[INST] and create atoms [/INST] and have them spread around the </s><s>[INST] the the universe. Right? [/INST] So the current estimates 13 </s><s>[INST] .8 billion years [/INST] of just the whole universe. But it </s><s>[INST] spent the 1st 5 or [/INST] six of those billion years really just like </s><s>[INST] cooling and making enough of the stars [/INST] to then make the atoms that would come from supernovas. So </s><s>[INST] I actually think we might be the [/INST] first or sit one of the very </s><s>[INST] few or one of the early life forms but the universe itself [/INST] hasn't had that much time </s><s>[INST] to make life in the [/INST] integral and a galactic and universal time </s><s>[INST] frame. You needed billions [/INST] of years for the elements to be created and then distributed. </s><s>[INST] And we're only really in [/INST] the like I think the last few </s><s>[INST] billion years where I think even [/INST] life could have been made. </s><s>[INST] So I think the question of wherever is [/INST] everyone is the wrong question. I think the question is </s><s>[INST] I think [/INST] we're the first ones at the party. Let's set up the liquor, let's set up the </s><s>[INST] food. We I just think we're the first [/INST] ones at the party of </s><s>[INST] life but more people are coming [/INST] one of the </s><s>[INST] early attendees to the party. Yeah maybe as far as we know the [/INST] first but maybe </s><s>[INST] with my local [/INST] pockets of the </s><s>[INST] universe. [/INST] Um because the parties then </s><s>[INST] expand and you it [/INST] overflows and then there's a </s><s>[INST] mosh pit and then [/INST] you know you bump into the other galaxy. </s><s>[INST] I think it's I think the [/INST] question should be, </s><s>[INST] we [/INST] know when else is </s><s>[INST] everyone getting here instead of where is everyone? I think I think we've [/INST] just started on the genesis of life </s><s>[INST] in the universe. Yes. So [/INST] not not worry have </s><s>[INST] they are not [/INST] more about when and </s><s>[INST] who [/INST] and how do we set up the party? </s><s>[INST] Right and then how do we help them? I think it's interesting [/INST] other moral question is do </s><s>[INST] we you know the a lot of [/INST] star trek episodes. You the prime directive is you do not </s><s>[INST] interfere with another [/INST] planet. If you could pass by </s><s>[INST] a planet. I think it's [/INST] time to also visit that. Because what if what if you go by </s> |
<s>[INST] doesn't seem to be, it doesn't [/INST] seem to enhance sleep, </s><s>[INST] but it's interesting to understand its effects on sleep. I've uh like a fasted, It's a study of NFL two once fasted, 72 hours and another time 48 hours. And uh I found that I got much less sleep. And it was very restful though, I hesitate to say this, but this is how I felt, which is I needed less sleep. I wonder if my brain is deceiving me because it feels like I'm getting a whole extra amount of focus for free. And I wonder if there's long term impacts of that because if I fast 24 hours Get the same amount of calories one meal a day, there's a little bit of discomfort like just maybe your body gets a little bit colder. Maybe there is just I mean hunger, but the amount of focus is crazy. Yeah. And so I wonder it's like I'm a little suspicious of that. I feel like I'm getting something for free. I'm the same way with sweetener, like splendor or something. It's like there's got to be really bad for you, right? Because why is it so tasty? Right. [/INST] And I think, yeah, as we said for with Biology, </s><s>[INST] you know, [/INST] if there is a long game, there's yeah, there's often a cost too. So but we are at least understand the biological basis of what you're describing. It's not that you you actually don't need less sleep. It's that this chemical is present that forces you more awake. And so subjectively you feel as though I don't need as much sleep because I'm wide awake. And those two things are quite different. It's not as though you your sleep need has decreased its that your brain has hit the overdrive switch the over boost switch to say we need to keep you awake because food is in short supply. </s><s>[INST] So you mentioned during sleep, there's a simulation, all those kinds of things for learning purposes, but there's also these uh you mentioned the five ways in which we become psychotic in dreams. What do you think? What do you think dreams are about? What why do you think would dream? What place do we go to when we dream and why are they useful? Not just not just the assimilation aspect, but just like all the crazy visuals that we get with dreams. Is there something you can speak to that's actually useful? Like why we have such fun experiences in that dream world. [/INST] So one of the camps in the sleep field is that dreams are meaningless, that they are an epi phenomenal byproduct of this thing called rem sleep, from which dreams come from as a physiological state. So the analogy would be um let's think of a light bulb that the reason that you create the apparatus of a light bulb is to produce this thing called light in the same way that we we've evolved to this thing called rem sleep to serve whatever functions rem sleep. That's but it turns out that when you create light in that way, you also produce something called heat. It was never the reason that you design the light bulb. It's just what happens when you create light in that way. And the belief. So too, was that dreaming was essentially the heat of the light bulb that rem sleep is critical, But when you have rem sleep with a complex brain like ours, you also produce this conscious epi phenomenon called dreaming. I don't believe that for a second I and from a simple perspective is that I suspect that dreaming is more metabolically costly as a conscious experience than not dreaming. So you could still have rem sleep but absent the conscious experience of dreaming was probably less metabolically costly. And whenever mother nature burns the energy unit called ATP, which is the most valuable thing, uh there's usually a reason for it. So if if it's more energetically demanding then I suspect that there is a function to it. And we've now since discovered that dreams have a function. The first, as we mentioned creativity. The second is that dreams provide a form of overnight therapy. Dreaming is a form of emotional first aid and it's during dream sleep at night that we take these difficult painful experiences that we've had during the day. Sometimes traumatic and dream sleep acts almost like a nocturnal soothing balm. And it sort of just takes the sharp edges off those difficult painful experiences so that you come back the next day and you feel better about them. And so I think in that sense dreaming it's not time that heals all wounds. It's time during dream sleep that provides emotional convalescence. So dreaming is almost a form of you know emotional windscreen wipers. Um And I think by the way it's not just that you dream, it's what you dream about that also matters. So for example, scientists have done studies with learning and memory where they have people learn a virtual maze and what they discovered was that those people who then dreamed but dreamed of the maze, we're the only ones who when they woke up ended up being better at navigating the maze. Whereas those people who dreamed but didn't dream about the maze itself, they were no better at navigating the base. So it's not just that it's not it's sort of necessary but not sufficient. It's necessary that you dream, but it's not sufficient to produce the benefit you have to be dreaming about certain things itself. And the same is true for mental health. What we've discovered is that people who are going through a very difficult experience a trauma, for example, a very painful divorce. Those people who are dreaming but dreaming of that difficult event itself, they go on to gain resolution to their clinical depression one year later. Whereas people who were dreaming just as much but not dreaming about the trauma itself did not go on to gain as much clinical resolution to their depression. So it's I think to me those are the lines of evidence that tell me dreaming is not epi phenomenal and it's not just about the act of dreaming. It's about the content of the dreams, not just the fact of a dream itself. </s> |
<s>[INST] We know. I understand that, but it's, especially when like, what is it, you know, 80 million people vote for you, or like some, like millions and millions and millions of people vote for you. It's crazy. It's crazy. This democracy thing is crazy. [/INST] George H.W. Bush won a war in the Middle East, right? He had 90% approval rating, and then a year later lost the election. To someone, Bill Clinton, he thought had none of the experience he had, someone didn't have, he believed didn't have the right moral character, and Bush did everything he could to help the next president get started well, and they became good friends. George W. Bush, he didn't love Obama. That's considered one of the smoothest transitions. George W. Bush ordered every single person in his administration to do everything they could to help the new admin. That's what a leader does. </s><s>[INST] Yeah. Yeah. Humility is one of the things I admire in leaders. Well, that felt heated. Speaking of which, can you just linger on, how do you think we can heal the divide in this country? Do you think it's possible? [/INST] There feels to be a strong division. I think we can heal the divide. I think, as you said, there's so many opportunities with new technology to bring people together, just as we're using it to tear them apart. I have the best job in the world because I get to teach so many students. I'll have 300 in my class in the spring, in a US history class. What I've found with my students is they're mostly not Democrats or Republicans. They mostly care about the same things. </s><s>[INST] Every one of my students seems to care about climate change. I thought you were going to say TikTok, but okay. [/INST] Second to that climate change. Second to that. I think they offer a new future for us. Here's what I'll say as a historian. We go through cycles of division and cycles of less division, less partisanship. One moment when it seems people agree too much on the mainstream, encourages people to go to the extremes. When people see the extremes, they want to come back to the middle, and that is where my students are. Most of my students want lower inflation. They agree with Republicans on that, but they want more to be done about climate change. They're in the middle on these issues, and I think giving them more opportunity. What's the best way to heal our divisions, honestly? </s><s>[INST] Get the old men out, and the young women and men in. [/INST] Because they ultimately don't have that same division, and they're deeply baked in. Not only that, they find it disgusting in the way you and I do. </s><s>[INST] Yeah, that's true. What's the right way to have conversations, just to stay on that with people on the left and the right? Yeah, I don't know how often you practice this. You care about politics. Nothing too often. [/INST] Do you talk to people who voted for Trump or who are Republicans? It's hard. I try, but it's hard. </s><s>[INST] 75% of the people I talk to are not those people. Do you have people who are Trump supporters in your extended family, Thanksgiving? No, I don't in my extended. [/INST] Are they no longer... No, I don't in my extended. They're no in my family. It's all it fashion. I have taken them out of the photograph. You just erase? But I know I have friends, yeah, who fall into that, but it's still a minority of my friend group. So I want to be clear that I'm not as good at this as I should, but I think we do have to reach out. But I also, I'm less interested honestly in re-fighting old battles with old dogs. I'm more interested in finding ways to get a new crop of people educated and involved and engaged without imparting the same partisanship on them. So I will support, and this I have, I will support and encourage, especially any student of mine, but any young person who is smart, has good ideas. I don't care whether, I don't ask whether they're a Democrat or Republican. And I have given money to some young candidates who are not Democrats. So that's the way, I think it's a generational change. And I think it's reaching out and trying to get people to see beyond partisan divisions who are in their 20s and teens rather than, that's why we do our podcast. This is a democracy, Zachary and I do that, my son and I, because we're exactly like, you will never hear an episode where we take one side or another. Our goal is to explain the issue, whether it's the challenges of democracy in China, or it's climate change or whatever it is, or it's memory of war in our society. And to explain the issue and then offer people </s> |
<s>[INST] I like people to be raw and transparent and real, all that kind of stuff. But no matter what, it's a super fascinating topic, go to Express VPN dot com slash slugs pod 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 kate darling. Last time we talked a few years back, you were Justin Bieber shirt for the podcast. So not looking back, you're a respected researcher, all the amazing accomplishments in robotics. You're an author. Was this one of the proudest moments in your life, proudest decisions you've ever made? [/INST] Definitely. You handled it really well though. It was cool because I walked in. I didn't know you were going to be filming. I walked in and you're in a fucking suit. </s><s>[INST] Yeah. [/INST] And I'm like, why are you all dressed up? And then you were so nice about it. You like made some excuse. You're like, oh well I'm interviewing some. Didn't you say you were interviewing some military general afterwards to like </s><s>[INST] make me feel better. Cto of Lockheed martin. I [/INST] thought that's what it </s><s>[INST] was. You [/INST] didn't tell me. Oh, I was dressed like this. Are </s><s>[INST] you an actual Bieber fan or was that like one of those t shirts that's in the back of the closet that you use for painting. I [/INST] think I bought it for my husband as a joke. And yeah, I was, we were gut renovating a house at the time and I had worn it to the site. </s><s>[INST] Got is a joke and now you were okay. Have you worn it since? Is this a one time? [/INST] No. Like how could I touch it again? It was on your podcast frames. </s><s>[INST] It's like a wedding dress or something like that. You don't, you only wear it once. You are the author of the new breed. What our history with animals reveals about our future with robots. You open the book with the surprisingly tricky question, What is a robot? So let me ask you, Let's try to sneak up to this question. What's a robot [/INST] that's not really sneaking up? </s><s>[INST] It's just asking it. [/INST] Yeah. </s><s>[INST] Alright. Well [/INST] what do you think a robot is? </s><s>[INST] What I think a robot is is something that has some level of intelligence and some level of magic that little shine in the eye. You know, that allows you to navigate the uncertainty of of life. So that means like autonomous vehicles to me in that sense are robots because they navigate uh the uncertainty the complexity of life. Obviously social robots are that I [/INST] love that. I like that you mentioned magic because that also. Well, so first of all, I don't define robot definitively in the book because there is no </s><s>[INST] definition [/INST] that everyone agrees on. And if you look back through time, people have called things robots until they lose the magic because they're more ubiquitous. Like a vending machine used to be called a robot. And now it's not right. So I do agree with you that there's this magic aspect that that which is how people understand robots. If you ask a roboticist, they have the definition of something that is well, it has to be physical, usually it's not an ai agent, it has to be embodied. Um They'll say it has to be able to sense its environment in some way. It has to be able to make a decision autonomously and then act on its environment. Again. I think that's a pretty good technical definition even though it really breaks down when you come to things like the smartphone because the smartphone can do all of those things and most roboticists would not call it a robot. So there's really no no one good definition. But part of why I wrote the book is because people have a definition of robot in their minds that is usually very focused on a comparison of robots to humans. So if you google image search robot you get a bunch of humanoid robots, robots with the torso and head and two arms and two legs. And that's the definition of robot that I'm trying to get us away from. Because I think that it trips us up a lot. </s><s>[INST] Why does the humanoid form trip us up a [/INST] lot? Well because this constant comparison of robots to people artificial intelligence to human intelligence first of all doesn't make sense from a technical perspective because you know the early Ai researchers some of them were trying to recreate human intelligence, some people still are and there's a lot to be learned from that academically etcetera but um that's not where we've ended up ai doesn't think like people we wind up in this fallacy where we're comparing these two um and where when we talk about what intelligence even is, we're often comparing to our own intelligence. And then the second reason this bothers me is because it doesn't make sense. I just think it's boring to recreate intelligence that we already have. I see the scientific value of understanding our own intelligence, but from like practical, what can we use these technologies for perspective? It's much more interesting to create something new to create a skill set that we don't have, that we can partner with and what we're trying to achieve </s><s>[INST] and it should be in some deep way similar to us, but in most ways different because you still want to have a connection, which is why the similarity might be necessary [/INST] that people argue Yes and I think that's true. So the two arguments for humanoid robots are people need to be able to communicate and relate to robots and we relate most of things that are like ourselves and we have a world that's built for humans. So we have stairs and narrow passageways and door handles. And so we need humanoid robots to be able to navigate that. And so you're speaking to the first one which is absolutely true. But what we know from social robotics and a lot of human robot interaction research is that you all you need is something that's enough like a person to for it to give off cues that someone relates to and that but that doesn't have to look human or even act human. You can take a robot like R. Two D. Two and it just like beeps and boobs and people of R. Two D. Two right? Even though it's just like a trash can on wheels and they like R. Two D. D. More than C. Threepio who's a humanoid. So there's lots of there's lots of ways to make robots even better than humans in some ways and make us relate more to them. </s><s>[INST] Yeah it's kind of amazing the variety of cues that can be used to anthropomorphize the thing like a glowing orb or something like that. Just just a voice. Just just subtle basic interaction. I think people sometimes over engineer these things like simplicity can go a really long way [/INST] totally. I mean ask any animator and they'll know that. </s><s>[INST] Yeah. Yeah those are actually so the people behind cosmo the um the robot the right people to design those as animators like Disney type of people versus like roboticists, roboticists quote unquote are mostly clueless. They [/INST] just have their own discipline that they're very good at and they didn't don't have. </s><s>[INST] Yeah but that don't don't you know I feel like robotics of the early 21st century Is not going to be the robotics of the later 21st century like if you call yourself a roboticist there'll be something very different because I I think more and more you'll be like a maybe like a control engineer or something controls engineer. Like uh you separate because ultimately all the unsolved, all the big problems of robotics will be in the social aspect, in the interacting with humans aspect, in the uh perception, interpreting the world aspect in the brain part, not the not the not the basic control level part [/INST] you call it basic, it's actually really, really complex and that's why. But like I think you're so right and and what a time to be alive because for me, I just we've had robots for so long and they've just been behind the scenes and now finally robots are getting deployed into the world </s><s>[INST] coming out of the closet. [/INST] Yeah. And and we're seeing all these mistakes that companies are making because they focus so much on the engineering and getting that right and getting the robot to be even be able to function in a space that it shares with the human. </s><s>[INST] See what I feel like people don't understand is to solve the perception of the control problem. You shouldn't try to just solve the perception control problem. You should teach the robot how to say, oh shit, I'm sorry, I funked up [/INST] or ask for </s><s>[INST] ask for help or be able to communicate the uncertainty. Yeah, exactly. All of those things because you can't solve the perception control. We humans haven't solved it. We were really damn good at it. But the magic is in the the self deprecating humor and the self awareness about where our flaws are. All that kind of stuff. [/INST] Yeah and there's a whole body of research and human robot interaction showing like ways to do this. But a lot of these companies haven't they don't do H. R. I. They like the have you seen the grocery store robot in the stop and shop? </s><s>[INST] Yes. [/INST] Yeah the marty looks like a giant penis. It's like six ft tall, roams the aisles. </s><s>[INST] I will never see marty the same way again. Thank you [/INST] you're welcome. But like they these poor people were so hard on getting a functional robot together and then people hate marty because they didn't </s><s>[INST] at [/INST] all consider how people would react to marty in their space. </s><s>[INST] Does everybody, I mean you talk about this do people mostly hate marty because I like I like marty I. Yeah and [/INST] actually like </s><s>[INST] There's a there's a parallel between the two [/INST] I believe there is. So we were actually gonna do a study on this right before the pandemic hit and then we canceled it because we didn't want to go to the grocery store and neither did anyone else. Um </s><s>[INST] But our [/INST] theory so this was with a student and M. I. T. Daniela di paola she noticed that everyone on facebook in her circles was complaining about marty. They're like what is this creepy robot is watching me as it was in the way and she did this like quick and dirty sentiment analysis on twitter where she was looking at positive and negative mentions of the robot and she found that the biggest spike of negative mentions happened um when stop and shop threw a birthday party for the marty robots like with free cake and balloons. Like who complains about free cake? Well people who hate marty apparently so and so we were like, that's interesting. And then we did this like online poll, we used mechanical turk and we tried to get at </s><s>[INST] what [/INST] people don't like about marty and a lot of it wasn't oh marty's taking jobs. It was marty is the surveillance robot which is not, it looks for spills on the floor, It doesn't actually like look at any people. Um it's watching, it's creepy. It's getting in the way those were the things that people complained about. And so our hypothesis became is marty a real life clip. E because I know lex you love clip E but many people hated clip E. </s><s>[INST] Well there's a complex thing there, it could be like marriage. A lot of people seem to like to complain about marriage but they secretly love it. So it could be the relationship you might have with with marty is like oh there he goes again, doing this stupid surveillance thing. But you grow to love the I mean bitching about the thing that kind of releases a kind of tension and there's I mean some people, a lot of people show love by sort of uh busting each other's chops you know like making fun of each other and then if I think I think people would really love it if marty talked back and like these are so many possible options for humor. There one you can lean in, you can be like yes I'm an agent of the C. I. A. Monitoring your every move, like mocking people that are concerned, you know what I'm saying? Like yes I I'm watching you because you're so important with your shopping patterns. I'm collecting all this data um or or just you know and you're kind of making fun of people I don't know. [/INST] But I think you hit on what exactly it is because when it comes to robots or artificial agents, I think people hate them more than they would some other machine or device or object. Um and it might and it might be that thing, it might be combined with love or like whatever it is, it's a more extreme response because they view these things as social agents and not objects and that was um </s><s>[INST] so Clifford [/INST] Nass was a big human computer interaction person. And he his theory about clip e was that because people viewed clip as a social agent when Cliff was annoying and would like bother them and interrupt them and like not remember what they told </s><s>[INST] him. [/INST] That's when people got upset because it wasn't fulfilling their social expectations. And so they complained about clipping more than they would have if it had been a different, like not </s><s>[INST] not a [/INST] you know, virtual character </s><s>[INST] so is complaining to you a sign that we're on the wrong path with a particular robot or is it possible like again like marriage like family that there still is a path towards that direction where we can find deep meaningful relationship. [/INST] I think we absolutely can find deep meaningful relationship with robots and well maybe, I mean I just would I would have designed marty a little differently. </s><s>[INST] Isn't there a charm to the clumsiness? The slowness there [/INST] is if you're not trying to get through with a shopping cart and screaming child. You know, there's I think, </s><s>[INST] I [/INST] think you could make it charming. I think there are lots of design tricks that they could have used. And one of the things they did, I think without thinking about it at all is they slapped two big googly eyes on marty and I wonder if that contributed to people feeling watched. Um because because it's looking at them and so like is there a way to design the robot to do the function that it's doing in a way that doesn't that people are actually attracted to rather than annoyed by and there are many ways to do that, but companies aren't thinking about it now they're realizing that they should have thought about </s><s>[INST] it. I wonder if there's a way to if it would help to make marty seem like an entity of its own versus um the arm of a large corporation. So there's some sense where this is just the camera that's monitoring people versus this is an entity that's a standalone entity. It has its own task and it has its own personality. The more personality you give it, the more it feels like it's not sharing data with anybody else. Like when we see other human beings are basic assumption is whatever I say to this human being, it's not like being immediately sent to the C. I. A. Yeah [/INST] what I say to you, no one's going to hear that, right? </s><s>[INST] Yeah that's [/INST] true. You </s><s>[INST] forget it. I mean you do forget it. I mean I don't know if that even with microphones here you forget that that's happening. But for some reason I think probably with marty um I think when it's done really crudely and crap early you start to realize oh this is like pr people trying to make a friendly version of a surveillance machine. But um I mean that reminds me of the slight clumsiness or significant clumsiness on the initial releases of the avatars for the metaverse. I don't know what what are you what are your actually thoughts about that? The the way uh the avatars the way like Mark Zuckerberg looks in that world. You know the metaverse, the virtual reality world where you can have like virtual meetings and stuff like that. Like how do we get that right? Do you have thoughts about that? Because that's the kind of, it's uh it feels like a similar problem to social robotics which is how you design a digital virtual world. That is compelling when you connect to others. They're in the same way that physical connection is [/INST] right? I haven't looked into, I mean I've seen people joking about it on twitter and like posting whatever. </s><s>[INST] Yeah, but I mean have you seen it? Because it it there's something you can't quite put into words that doesn't feel genuine. [/INST] Yeah, </s><s>[INST] about the way it looks. And so the question is, if you're an hour to meet virtually what should the avatars look like for us to have a similar kind of connection should be really simplified, Should it be a little bit more realistic? Should it be cartoonish? Should it be more um better capturing of expressions uh in interesting, complex ways versus like cartoonist oversimplified ways, [/INST] but having video games figured this out, I'm not a gamer, so I don't have any examples, but I feel like there's this whole world and video games where they've thought about all of this and depending on the game, they have different like avatars and a lot of the games are about connecting with others. I just, the thing that I don't know is and again, I haven't looked into this at all. Um I've been like shockingly not very interested in the metaverse, but they must have poured so much investment into this meta and like why? Why is it so why are people, why is it so bad? </s><s>[INST] Well there's [/INST] gotta be a reason. There's got to be some thinking behind it. Right? </s><s>[INST] Well, talk to Carmack about this john Carmack whose part time Oculus C. T. O. I think there's several things to say. One is, as you probably know that, I mean there's bureaucracy, there's large corporations and they often large corporations have a way of killing the indie kind of artistic flame that's required to create something really compelling somehow. They make everything boring because they run through this whole process through the pr department through all that kind of stuff. And and it it somehow becomes generic to that process because they strip [/INST] out anything interesting because it could be controversial. Is that Yeah. </s><s>[INST] Right. Exactly. Like um like what I mean, we were living through this now. Like with with a lot of people with cancelations, all those kinds of stuff. People are nervous and nervousness results in like the like the usual the assholes are ruining everything, but you know the magic of human connections, taking risks of making a risky joke of of of like with people you like we're not assholes, good people, like some of the fun, some of the fun in the metaverse or in video games is you know, being edgier being interesting, revealing your personality in interesting ways um in the sexual tension or in their definitely paranoid about that, like in metaverse, the possibility of sexual assault and sexual harassment and all that kind of stuff, it's it's obviously very high but there um so you should be paranoid to some degree but not too much because then you remove completely the personality of the whole thing, then everybody's just like a vanilla bought that uh like you have to have ability um to be a little bit political to be a little bit edgy, all that kind of stuff and large companies tend to suffocate that so but in general just forget all that, just the ability to come up really cool beautiful ideas. Um If you look at um I think grimes tweeted about this, she's very critical about the metaverse is that um you know the uh independent game designers have solved this problem of how to create something beautiful and interesting and compelling. They do a really good job. So you have to let those kinds of minds of small groups of people design things and let them run with it and let them run wild and do edgy stuff. Yeah, but otherwise you because you get this kind of, you get a clip e type of situation right, which is like a very generic looking thing. Um But even clip e has some like that's kind of wild that you would take a paperclip and put eyes on it and [/INST] suddenly people are like oh you're annoying but you're definitely a social age </s><s>[INST] and I just feel like that wouldn't even that clip E. Thing wouldn't even survive Microsoft or facebook of today matter of today because it would be like what there would be these meetings about why is it people like why don't we it's not sufficiently friendly, let's make it uh you know and then all of a sudden the artists that with whom it originated is killed and it's all pr marketing people and all of that kind of stuff. Now they do important work to some degree but they kill the creativity. [/INST] I think the killing of the creativity is in the like okay so what I know from social robotics is like obviously if you create agents that okay so take for an example you create a robot that looks like a humanoid and it's you know Sophia or whatever. Now suddenly you do have all of these issues where are you reinforcing an unrealistic beauty standard? Are you objectifying women? Why is the robot white? So you have. But the thing is I think that with creativity you can find a solution that's even better where you're not even harming anyone and you're creating a robot that looks like not not humanoid but like something that people relate to even more and now you don't even have any of these bias issues that you're creating and so how do we create that within companies? Because I don't think it's really about like I because I, you know, maybe we disagree on that. I don't think that edginess or humor or interesting things need to be things that harm or hurt people or that people are against. There are ways to find things that everyone is fine with. Why aren't we doing that? </s><s>[INST] The problem is there's departments that look for harm and things and so they will find harm and things that have no harm. [/INST] That's </s><s>[INST] the big problem because their whole job is to find harm in things. So what you said is completely correct, which is edginess should not hurt. Doesn't necessarily doesn't need to be a thing that hurts people. It obviously great humor, great personality doesn't have to like Cliffy. But yeah, I mean, but it's tricky to get right and I'm not exactly sure. I don't I don't know, I don't know why a large corporation with a lot of funding can't get this right. I [/INST] do think you're right that there's a lot of aversion to risk. And so if you get lawyers involved or people whose job it is like you say, to mitigate risk, they're just going to say no to most things that could even be in some way. Yeah, yeah. You get the problem in all organizations. So I think that you're right, that that is a problem. </s><s>[INST] I think what's the way to solve that in large organizations is to have steve jobs, types of characters. Unfortunately you do need to have I think um from a designer or maybe like a johnny ive, that is almost like a dictator, [/INST] benevolent dictator </s><s>[INST] who rolls in and says like that cuts through the lawyers, the pr but has a benevolent aspect. Like yeah there's good heart and make sure like I think all great artists and designers create stuff that doesn't hurt people. Like if you have a good heart you're going to create something that's going to actually um make a lot of people feel good. That's what like people like johnny I what they love doing is creating a thing that brings a lot of love to the world. Imagine like millions of people using the thing and it instills them with with joy. That's that you could say that about social robotics, you could say that about the metaverse. Uh It shouldn't be done by the pr people should be done by [/INST] the time I pr people ruin everything. </s><s>[INST] Yeah. All the fun. Uh in the in the book you have a picture this I just have a lot of ridiculous questions. You have a picture of two hospital delivery robots with a caption that reads by the way. I see your book. I appreciate that. It keeps the humor and you didn't run it by the pr department. [/INST] No, No one edited the book. Got rushed through </s><s>[INST] Uh the caption reads to hospital delivery robots who's sexy nurse names. Roxy and lola made me roll my eyes so hard they almost fell out. Um What aspect of it made you roll your eyes? Is it the naming [/INST] it was the naming, the form factor is fine. It's like a little box on wheels. The fact that they named them also great. That'll let people enjoy interacting with them. We know that even just giving a robot a name, people will uh it facilitates technology adoption. People will be like, oh you know Betsy made a mistake, let's help her out instead of this stupid robot doesn't work. But why lowly and lowland roxy like </s><s>[INST] those are to you too sexy. [/INST] I mean there's research showing that a lot of robots are named according to gender biases about the function that they're fulfilling. So you know, robots that are helpful and assistance and are like nurses are usually female gendered robots that are you know, powerful all wise computers like Watson usually have like a booming male uh coded voice and names. So like like that's one of those things right? You're opening a can of worms for no reason. For no reason. Just give it a different name. Like why roxy it's because people aren't even thinking so to some extent I don't I don't like pR departments but getting some feedback on your work from a diverse set of participants listening and taking in things that help you identify your own blind spots and then you can always make your good leadership choices and good like you can still ignore things that you don't believe are an issue. But having the openness to take in feedback and making sure that you're getting the right feedback from the right people. I think that's really important. So </s><s>[INST] don't unnecessarily propagate the biases of society. [/INST] Yeah. Why </s><s>[INST] in the design? But if you're not careful though, when when you do the research of like you might if you ran a poll with a lot of people of all the possible names these robots have, they might come up with roxy and lola as as names they would enjoy most. Like that could come up as uh as the highest [/INST] as then you do marketing research and then well that's what they did with Alexa. They did marketing research and nobody wanted the male voice, everyone wanted it to be female. </s><s>[INST] What do you what do you think about that? Like what if I if I were to say I think the role of a great designer again to go back to johnny i is to throw out the marketing research. Like take it in, do it learn from it. But like if everyone wants Alexa to to be a female voice, the role of the designers to think deeply about the future of social agents in the home and think like what does that future look like and try to reverse engineer that future. So like in some sense there's this weird tension like you want to listen to a lot of people but at the same time you want to you're creating a thing that defines the future of the world and the people that you're listening to are part of the past. So like that weird tension. [/INST] Yeah, I think that's true and I think some companies like Apple have historically done very well at understanding of market and saying, you know what our role is not to listen to what the current market says. It's to actually shape the market and shape consumer preferences and companies companies have the power to do that they can before we're thinking and they can actually shift what the future of technology looks like. And I agree with you that I would like to see more of that especially when it comes to existing biases that we know or or you know that that I think there's the low hanging fruit of companies that don't even think about it at all and aren't talking to the right people and aren't getting the full information and then there's companies that are just like doing the safe thing and and giving consumers what they want now, but to be really forward looking and be really successful. I think you have to make some judgment calls about what the future is going to be. </s><s>[INST] But do you think it's still useful to gender and to name the robust? [/INST] Yes, I mean gender is a minefield, but people, it's really hard to get people to not gender a robot in some way. So if you don't give it a name or you give it a like ambiguous voice, people will just choose something and maybe that's better than just like, you know, entrenching something that you've decided is best. But I do think it it can be helpful on the like anthropomorphism engagement level to give it attributes that people identify </s><s>[INST] with. Yeah, I think a lot of roboticists, I know they don't gender the robot. They don't, they even try to avoid naming the robot or naming it something that is can be used as a name in conversation kind of thing. And I think that actually that's um irresponsible because people are going to anthropomorphize the thing anyway. So you're just removing from yourself the responsibility of how they are going to anthropomorphize [/INST] it. </s><s>[INST] And so like you want to be able to like they're going to do it. You have to start to think about how they're going to do it. Even if the robot is like a boston dynamics robot that's not supposed to have any kind of social component. They're obviously going to project the social component to [/INST] it like </s><s>[INST] that arm. I worked a lot a lot with quadruplets now with robot dogs. You know that arm. People think it's a head immediately it's supposed to be an arm. But they start to think it's a head and you have to like, acknowledge that you can't. I mean they [/INST] do now, </s><s>[INST] they do know, well [/INST] they've deployed the robots and people are like, oh my God, the cops are using a robot dog. And so they have this pr nightmare. And so they're like, oh yeah, okay, maybe we should hire some HR i people, </s><s>[INST] well, boston dynamics is an interesting company or any of the others that are doing similar thing because their their main source of money is um in industrial applications, so like surveillance of factories and doing dangerous jobs. So to them, it's almost good pr for people to be scared of these things, because it's it's for some reason, as you talk about, people are naturally for some reason scared we can talk about that of robots and so it becomes more viral, like uh playing with that little fear. And so it's almost like a good pr because ultimately they're not trying to put them in the home and have a good social connection, they're trying to put them in factories and so they have fun with it. If you watch boston dynamics videos, they're aware of it. [/INST] Oh yeah, </s><s>[INST] there, I mean [/INST] the videos for sure that they put out, </s><s>[INST] it's almost like an unspoken tongue in cheek thing. They're aware of how people are going to feel when you have a robot that does like a flip. Now, most of the people are just like excited about the control problem of it. Like how to, how to make the whole thing happen. But they're aware when people see, Well [/INST] I think they became aware, I think that in the beginning they were really, really focused on just the engineering. I mean they're at the forefront of robotics like locomotion and stuff. Um, and then when they started doing the videos, I think that was kind of a labor of love. I know that the former ceo mark, like he oversaw a lot of the videos and made a lot of them himself and like he's even really, really detail oriented. Like there can't be like some sort of incline that would give the robot an advantage. They're very like, he, he was very, um, hell of integrity about the authenticity of them. Uh, but then when they started to go viral, I think that's when they started to realize, oh, there's something interesting here that you know, I don't, I don't know how much they took it seriously in the beginning other than realizing that they could play within the videos. I know that they take it very seriously. Now </s><s>[INST] what I like about boston dynamics and similar companies is still mostly run by engineers. But you know, I've had my criticisms. There's a bit more pr leaking in. [/INST] But those </s><s>[INST] videos are made by engineers because that's what they find fun. [/INST] It's </s><s>[INST] like testing the robustness of the system. I mean they they're having a lot of fun there with the robots [/INST] totally. </s><s>[INST] Have [/INST] you been, have you been to visit? </s><s>[INST] Yeah, it's one of the most like I I uh I mean because I have um eight robot dogs now. [/INST] You have eight robot </s><s>[INST] dogs, but [/INST] just walking around your place like, </s><s>[INST] yeah, I'm working on them. That's actually one of my goals is to have at any one time or was a robot moving? That's [/INST] an ambitious goal. </s><s>[INST] Well, I have like more room because I know what to do with the room that I program. So the programmable Roomba as and um I have a bunch of little, like I built the, I'm not finished with you yet, but a robot from rick and morty just have a bunch of robots everywhere. But the thing is what happens is you're working on one robot at a time and that becomes like a little project. It's actually very difficult to have just a passively functioning robot always moving. And that's a, that's a, that's a dream for me because I'd love to create that kind of a little world. So uh the impressive thing about boston dynamics to me was to see like hundreds of spots and like there's uh the most impressive thing that still sticks with me is um there was a a spot robot walking down the hall seemingly with no supervision whatsoever and he was wearing he or she, I don't know, was wearing a cowboy hat. [/INST] It </s><s>[INST] just it was just walking down the hall and nobody paying attention and it's just like walking down this long hall and I'm like looking around is anyone like what's happening here? So presumably some kind of automation was doing the map. I mean the whole environment is probably really well mapped but it was just it gave me a picture of a world where robot is doing doing his thing wearing a couple hats, just going down the hall like getting some coffee or whatever. Like I don't know what it's doing, what's the mission. But I don't know for some reason that really stuck with me. You don't often see robots that aren't part of a demo or that aren't uh you know like with a semi autonomous autonomous vehicle, like directly doing a task. This was just chilling. Yeah. I don't know. [/INST] Well yeah. You know I mean we're at M. I. T. Like when I first got to M. I. T. I was like okay where's all the where's all the robots? And they were all like broken or like not damn going. So. Yeah. And and and what really excites me is that we're about to have that we're about to have so many moving wrote about to. Well it's coming, it's coming in our lifetime that we will just have robots moving around already. Seeing the beginnings of it there's delivery robots and some cities on the sidewalks and I just love seeing like the tick talks of people reacting to that because yeah, you see robot walking down the hall with a cowboy hat. Like what the, what is this? This is awesome and scary and kind of awesome and people either love or hate it. That's one of the things that I think companies are underestimating that people will either love a robot or hate a robot and nothing in between. So it's just again an exciting time to be alive. </s><s>[INST] Yeah. I think kids almost universally at least in my experience love them. Love legged robots. [/INST] If they're not like my, my son hates the remote because ours is loud. </s><s>[INST] Oh, that yeah, no, the legs. The legs [/INST] because </s><s>[INST] your son. Um, do they understand rumored to be a robot? [/INST] Oh yeah. My kids, that's one of the first words they learned. They know how to say beep boop and yes, they think the room as a robot. </s><s>[INST] Do they project intelligence out of the thing? [/INST] Well, we don't really use it around them anymore for the reason that my son is scared of it. </s><s>[INST] Yeah. [/INST] I think they would like even a Roomba because it's moving around on its own. I think kids and animals view it as an agent. </s><s>[INST] So what do you think if we just look at the state of the art of robotics? What do you think robots are actually good at today? So if we look at today, [/INST] you mean physical robots? </s><s>[INST] Yeah, physical robots, [/INST] wow. </s><s>[INST] Like what are you impressed by? So I think a lot of people, I mean that's what your book is about is have maybe a not a perfectly calibrated understanding of where we are in terms of robotics was difficult to robotics. What's easy in robotics? [/INST] Yeah, we're way behind where people think we are. So What's impressive to me. So let's see. 011 thing that came out recently was Amazon has this new warehouse robot and it's the first autonomous warehouse robot that can is safe for people to be around. And so like it's kind of most people, most people I think envision that our warehouses are already fully automated and that there's just like robots doing things. It's actually still really difficult to have robots and people in the same space because it's dangerous for the most part robots, you know, because especially robots that have to be strong enough to move something heavy, for example, they can really hurt somebody. And so until now a lot of the warehouse robots had to just move along like pre existing lines which really restrict what you can do. Um And so having I think that's that's one of the big challenges and one of the big like exciting things that's happening is that we're starting to see more Kobach ticks in industrial spaces like that where people and robots can work side by side and not get harmed. </s><s>[INST] Yeah. That's what people don't realize that the physical manipulation tasks with humans, it's not that the robots want to hurt you. I think that's what people are worried about. Like this malevolent robot gets them out of its own and wants to destroy all humans. Now. It's, you know, it's actually very difficult to know where the human is and to to respond to the human and dynamically and collaborate with them on a task, especially if you're something like an industrial robotic arm, which is extremely powerful. See this some of the some of those arms are pretty impressive now that you can just you can you can grab it, you can move it. So the collaboration between human robot and the factory setting is really fascinating. Um Do you think they'll take our jobs? [/INST] I don't think it's that simple. I think that there's a ton of disruption that's happening and will continue to happen. Um You know, I think speaking specifically of the amazon warehouses, that might be an area where it would be good for robots to take some of the jobs that are, you know, where people are put in a position where it's unsafe and they're treated horribly and you know, probably it would be better if a robot did that and amazon is clearly trying to automate that job away. So I think there's gonna be a lot of disruption, I do think that robots and humans have very different skill sets. So while a robot might take over a task, it's not gonna take over most jobs. Um I think just things will change a lot. Like I don't know one of the examples I have in the book is mining um So there you have this job that is very unsafe and that requires a bunch of workers and put them in unsafe conditions and now you have all these different robotic machines that can help make the job safer. And as a result now people can sit in these like air conditions, remote control stations and like control these autonomous mining trucks. And so that's a much better job but also they're employing less people now. So it's it's just a lot of I think from a bird's eye perspective, you're not going to see job loss, you're going to see more jobs created because that's I think the future is not robots just becoming like people and taking their jobs. The future is really a combination of our skills and then the supplemental skill set that robots have to increase productivity to help people have better, safer jobs too. Give people work that they actually enjoy doing and are good at. Um But it's really easy to say that from a bird's eye perspective and um ignore kind of the the rubble on the ground as we go through these transitions because of course specific jobs are going to get lost </s><s>[INST] If you look at the history of the 20th century, it seems like automation constantly increases productivity and improves the average quality of life. So it's it's been always good. So like thinking about this time being different is that we would need to go against the lessons of history. And uh the other thing is I think people think that the automation of the physical tasks is easy. That was that was just in Ukraine. And the interesting thing is um I mean there's a lot of difficult and uh dark lessons just about a war zone, but one of the things that happens in war is there's a lot of minds that are placed. Um This one of the big problems for years after war is even over is the entire landscape is covered in minds. And so there's a de mining effort. And you would think robots would be good at this kind of thing. Or like your intuition would be like, well say you have unlimited money and you want to do a good job of unlimited money, you would get a lot of really nice robots, but no humans are still far superior [/INST] kind </s><s>[INST] of animals. But right. But humans with animals together, [/INST] you can't just have a dog </s><s>[INST] with a hat. But yes, and but figuring out also how to uh disable the mine. Obviously the easy thing, the thing a robot can help with is to uh find the mine and blow it up. But that kind of destroy the landscape. That that that really does a lot of damage to the land. You want to disable the mind and to do that because of all the different, all the different edge cases of the problem requires a huge amount of human life experience. It seems like so it's mostly done by humans. They have no use for robots. They don't want robots. [/INST] Yeah, I think we overestimate what we can automate, </s><s>[INST] especially in the physical realm. Yeah, it's weird. I mean, it's continues that the story of humans, we think we're shitty at everything in the physical world, including driving. We think everybody makes fun of themselves and others for being shitty drivers, but we're actually kind of incredible, [/INST] no, incredible. And that's why like that's why Tesla still says that if you're in the driver's seat, like you are ultimately responsible. Because the ideal for, I mean, I mean, you know more about this than I do, but like robot cars are great at predictable things and can react faster and more precisely than a person and can do a lot of the driving. And then the reason that we still don't have autonomous vehicles on all the roads yet is because of this long tail of just unexpected occurrences where a human immediately understands that's a sunset and not a traffic light that's a horse and carriage ahead of me on the highway. But the car has never encountered that before. So like in theory, combining those skill sets is what's gonna really be powerful. </s><s>[INST] The [/INST] only problem is figuring off the figuring out the human robot interaction and the handoff. So like in cars that's a huge problem right now figuring out the handoffs. Um but in other </s><s>[INST] areas uh [/INST] it might be easier and that's really the </s><s>[INST] future is human [/INST] robot interaction. </s><s>[INST] What's really hard to improve? It's it's it's terrible that people die in car accidents, but I mean it's like 70, million miles one death per 80 million miles. That's like really hard to beat for a robot. That's that's like incredible that like think about it like the how many people, it's just the number of people throughout the world that are driving every single day. All this, you know, steve deprived, drunk, uh distracted all of that and still very few die relative to what I would imagine if I were to guess back in the horse. See when I was like in the in the beginning of the 20th century riding my horse, I would talk so much sh it about these cars, This is gonna is extremely dangerous. These machines traveling at 30 mph or whatever the hell they're going at, this is irresponsible, It's unnatural and and it's going to be destructive to all of human society, but then it's extremely surprising how humans adapt to the thing and they know how to not kill each other. Um I mean that that ability to adapt is incredible and to mimic that in the machine is really tricky now that said what Tesla is doing. I mean I wouldn't have guessed how far machine learning can go on vision alone. It's really, really incredible. And people that are at least from my perspective, people that are kind of um uh you know critical of Ellen and those efforts I think don't give enough credit how much progress we've made, how much incredible progress has been made in that direction. I think most of their bodies community wouldn't have guessed how much you can do on vision alone. It's kind of incredible because we would be, I think it's that approach which is relatively unique. Has challenged the other competitors to step up their game. So if you're using lidar, if you're using mapping um that challenges them to do better to scale faster and to use machine learning and computer vision as well to integrate both light or envision. So um it's kind of incredible and I'm not, I don't know if I even have a good intuition of how hard driving is anymore. Maybe it is possible to solve. So all the sunset you mentioned. Yeah the question is one [/INST] yeah. I think it's not happening as quickly as people thought it would because it is more complicated </s><s>[INST] but I wouldn't have, I agree with you. My current intuition is that we're going to get there. [/INST] I think we're gonna get there too </s><s>[INST] but I didn't before. I wasn't sure we're gonna get there without like with current technology. So, you know, I I was kinda, this is like with vision alone, I my intuition was you're gonna have to solve like common sense reasoning. You're gonna have to you're gonna have to solve some of the big problems in artificial intelligence, not just um not just perception. [/INST] Yeah. Like </s><s>[INST] you have to have a deep understanding of the world is always my sense. But now I'm starting to like, well this I mean, I'm continuously surprised how well the thing works. Obviously Ellen and others others have stopped but Ellen continues, you know, saying we're going to solve it in a year. Yeah, [/INST] that's the thing. Bold predictions. </s><s>[INST] Yeah. But everyone else used to be doing that, but they kind of like, all right. [/INST] Yeah, maybe. </s><s>[INST] Maybe. Let's not problems we're gonna solve level for driving by 2020. Let's let's chill on that. [/INST] But people are still trying silently. I mean the UK just committed £100 million to research and development to speed up the process of getting autonomous vehicles on the road. Like everyone is, everyone can see that it is solvable and it's going to happen and it's going to change everything and they're still investing in it </s><s>[INST] and like Waymo Loki has driverless cars in, in Arizona like you can get, you know, there's like robots. It's weird. Have you ever [/INST] been one? </s><s>[INST] It's so weird. It's so awesome because the most awesome experiences is the wheel [/INST] turning and </s><s>[INST] you're sitting in the back. It's like I don't know it's um it feels like you're a passenger with that friend who's a little crazy of a driver. It feels like sh it I don't know are you alright to drive bro? You know that kind of feeling good but but then you kind of that experience that nervousness um and the excitement of trusting another being and in this case it's a machine is really interesting. Um Just even introspective your own feelings about the [/INST] thing. </s><s>[INST] They're not doing anything in terms of making you feel better about like at least Waymo. I think they went with the approach of like let's not try to put eyes on the thing. It's it's a it's a wheel, we know what that looks like. It's just a car, it's a car. Get in the back, let's not discuss this at all. Let's not discuss the fact that this is a robot driving you and you're in the back and if the robot wants to start driving 80 miles an hour run off of a bridge, you have no recourse let's not discuss this. You're just getting the back. There's no discussion about like how ship can go wrong. Uh There's no eyes, there's nothing, there's like a map showing what the car can see Like you know what happens if it's like a hal 9000 situation like like I'm sorry I can't. You have a button, you can like call customer service. [/INST] Oh God. Then you can put on hold for two hours </s><s>[INST] probably. Um But you know currently what they're doing, which I think it's understandable, but you know the car just can pull over and stop and wait for help to arrive and then the driver will come and then they'll actually drive the car for you. But that's like you know what if you're late for meeting or all that kind of stuff [/INST] or like the more dystopian, isn't it? The fifth element where is will smith and who's in that movie? No, Bruce Willis </s><s>[INST] Yeah. [/INST] And he gets into like a robotic cab or car or something? And then because he's violated traffic rules that locks him in and he has to wait for the cops to come and he can't get out. So like we're going to see stuff like that. Maybe I </s><s>[INST] believe that the companies that have robots, the the only ones that will succeed are the ones that don't do that meaning. They respect privacy. [/INST] You think so? </s><s>[INST] Yeah. Because people because because they're gonna have to earn people's trust. [/INST] Yeah. But like amazon works with law enforcement and gives them the data from the ring cameras. So why should? Yeah. Yeah. Do you have a ring camera. </s><s>[INST] Uh No, [/INST] no, </s><s>[INST] no, but basically any security camera right have google's whatever they have. We [/INST] have one that's not the data, we store the data on a local server because we don't want it to go to law enforcement because all the companies are doing it, They're doing, I bet apple wouldn't, </s><s>[INST] that was [/INST] the only company I trust and I don't know how much longer, </s><s>[INST] I don't know, I maybe that's true for cameras, but with robots and people are just not going to let a robot inside of their home where like one time where somebody gets arrested because of something a robot sees that's gonna be, that's gonna destroy a company. [/INST] You don't think people are gonna be like, well that wouldn't happen to me that happen to a bad </s><s>[INST] person. I think they would because in the modern world people, I get, have you seen twitter? They get extremely paranoid about any kind of surveillance. [/INST] But the thing that I've had to learn is that twitter is not the modern world, like when I go, you know, inland to visit my relatives, like they don't, that's a different discourse that's happening. I think like the whole tech criticism world, it's loud in our ears because we're in those circles, </s><s>[INST] you think you can be a company that does social robotics and not win over twitter? [/INST] That's a good question. </s><s>[INST] I feel like the early adopters are all on twitter and it feels like you have to win them over, feels [/INST] like nowadays you have to win over Tiktok. Honestly, </s><s>[INST] Tiktok is that, is that a website? I need to check it out. Um and that's an interesting one, because China is behind that one. [/INST] Exactly. </s><s>[INST] Uh so it's compelling enough. Maybe people would be able to uh give up privacy and that kind of stuff. I [/INST] just, I mean I'm worried about it, I'm worried about it and I'm, there have been some developments recently that are, like, super exciting, like the large language learning models, like, wow, I did not anticipate those improving so quickly, and those are going to change everything. And one of the things that I'm trying to be cynical about is that I think they're gonna have a big impact on privacy and data security and like, manipulating consumers and manipulating people, because suddenly you have these agents that people will talk too and they won't care or won't know, at least on a conscious level that it's recording the conversations so kind of like we were talking about before. Um and at the same time, the technology is so freaking exciting that it's going to get adopted, it's </s><s>[INST] not even just a collection of data, but the ability to manipulate at scale. So what do you think about the ai the engineer from, from google, that thought lambda is sentient, you had actually really good proposed from somebody else, I forgot her name is brilliant. I can't believe I didn't know about her. [/INST] Thanks Yeah, </s><s>[INST] from Weird Ai she's great, I left a note for myself to reach out to her. She's amazing. She's hilarious and brilliant and just a great summarize er of the state of ai but she has um I think that was from her where I was looking at ai explaining that it's a squirrel. [/INST] Oh yeah because the transcripts that the engineer released lambda kind of talks about the experience of human like feelings and I think even consciousness and so she was like oh cool. That's impressive. I wonder if an Ai can also describe the experience of being a squirrel. And so she interviewed I think she did GPT three about the experience of being a squirrel and then she did a bunch of other ones too. Like what's it like being a flock of crows? What's it like being an algorithm that powers a Roomba and like you can have a conversation about any of these things and they're very </s><s>[INST] pretty convincing. [/INST] Yeah. Yeah. Even </s><s>[INST] GTT three which is not like state of the art [/INST] right? It's </s><s>[INST] convincing of being a squirrel. It's like what it's [/INST] like </s><s>[INST] you should you should check it out because it it really is. It's like yeah that probably is what a squirrel would would [/INST] say. </s><s>[INST] Are you excited? Like what's it like being a squirrel that's fun [/INST] to run around all day? </s><s>[INST] Like how do you think people feel like when you tell them that you're a squirrel. Um You know or like I forget what it was like a lot of people might be scared to find out that your squirrel or something like this and then the system answers pretty like pretty well like yeah, like um I hope they'll like what do you think that when they find out you're a squirrel? I um I hope they'll see how fun it is to be. What [/INST] do you say to people who don't believe your </s><s>[INST] squirrel? I [/INST] say come see for yourself. I am a squirrel. Great. I think it's really great because it like the two things to note about it, our first of all, just because the machine is describing an experience doesn't mean it actually has that experience, but then secondly these things are getting so advanced and so convincing at describing these things and talking to people that's I mean just the implications for health, education, communication, entertainment, gaming. Like I just like all of the applications is mind boggling what we're gonna be able to do with this and and that my kids are not going to remember a time before they could have conversations with artificial agents. Do </s><s>[INST] you think they would, because to me this is um the focus in the community has been, well, this engineer Shirley's hallucinating the thing is not sentient, but to me I first of all, it doesn't matter if he is or not, this is coming where a large number of people would believe a system of sentient, including engineers, within companies. So in that sense you start to think about a world where like your kids aren't just used to having a conversation with the bot but used to believing kind of having an implied belief that the thing is sent you. [/INST] Yeah, I think that's true. And I think that one of the things that bothered me about all of the coverage in the tech press about this incident, like obviously I don't believe the system is sentient, like I think that it can convincingly described that it is, I don't think it's doing what he thought it was doing and actually experiencing feelings, but a lot of the tech press was about how he was wrong and depicting him as kind of naive and it's not naive. Like there's so much research in my field showing that people do this. Even experts, they might be very clinical when they're doing human robot interaction experiments with a robot that they've built and then you bring in a different robot and they're like look at it, it's having fun, it's doing this like that happens in our lab all the time. We are all this guy and it's gonna it's gonna be huge. So I think that the goal is not to discourage this kind of belief or like design systems that people won't think are sentient. I don't think that's possible. I think you're right this is coming. It's something that we have to acknowledge and even embrace and be very aware of. </s><s>[INST] So one of the really interesting perspectives that your book takes on a system like this is to see them not to compare a system like this to humans, but to compare it to animals. Of how we see animals. Can you kind of try to again sneak up, try to explain why this analogy is better than the human analogy, the analogy of robots as animals. [/INST] Yeah. And it gets trickier with the language stuff, but we'll get into that too. Um I think that animals are a really great thought experiment when we're thinking about AI and robotics because again this comparing them to humans that leads us down the wrong path both because it's not accurate but also I think for the future we don't want that we want something that's a supplement. But I think animals because we've used them throughout history for so many different things. We domesticated them not because they do what we do, but because what they do is different and that's useful. And it's just like whether we're talking about companionship, whether we're talking about work integration, Whether we're talking about responsibility for harm. There's just so many things we can draw on in that history from these entities that can sense think make autonomous decisions and learn that are applicable to how we should be thinking about robots and Ai and and the point of the book is not that they're the same thing that animals and robots are the same. Obviously there are tons of differences there like you can't, you can't have a conversation with a squirrel. Right? But the the </s><s>[INST] point all the time [/INST] really, by </s><s>[INST] the way, squirrels are the cutest I project so much on squirrels. I wonder what their inner life is. Um I suspect there are much bigger assholes than we imagine. [/INST] Like </s><s>[INST] if it was a giant squirrel, it would fuck you over so fast. If you had the chance, it would take everything you own, it would eat all your stuff because it's small and the furry tail, the furry tail is a, is uh, is a weapon against human consciousness and cognition. It wins us over. That's what cats do to cats out competed squirrels and yeah, no dogs have love, cats have no soul. They, I'm just kidding. People get so angry. I talk to you about cats that I love cats anyway. So yeah. Uh Yeah, you're, you're describing all the different kinds of animals that get domesticated and it's a really interesting idea that it's not just sort of pets. There's all kinds of domestication going on. There all have all kinds of uses [/INST] like </s><s>[INST] the ox that you proposed might be at least historically one of the most useful domesticated animals. [/INST] It was a game changer because it revolutionized like what people could do economically etcetera. So I mean just like robots are gonna change, they're gonna change things economically. They're gonna change landscapes, like cities might even get rebuilt around autonomous vehicles or drones or delivery robots. Like I think just the same ways that animals have really shifted society and society has adapted also to like socially accepting animals as pets. Um I think we're going to see very similar things with robots. So I think it's a useful analogy. It's not a perfect one. But I think it's it helps us get away from this idea that robots can should or will replace people. </s><s>[INST] If you remember what are some interesting uses of animals ferrets for example. [/INST] Oh yeah the ferrets, they still do this. They use ferrets to go into narrow spaces that people can't go into like a pipe or like they'll use them to run electrical wire. I think they did that for princess dies wedding. There's so many weird ways </s><s>[INST] that we've [/INST] used animals and still use animals for things that robots can't do. Like the dolphins that that they used in the in the military. I think the I think Russia still has dolphins and the U. S. Still has dolphins in their navies. Um Mine detection looking for lost underwater equipment. Some rumors about like using them for weaponry. Which which I think Russia is like sure believe that. And americans like no no we don't know who knows. But they started doing that in like the sixties seventies. They started training these dolphins because they were like oh dolphins have this amazing echolocation system that we can't replicate with machines and they're trainable. So we're gonna use them for all the stuff that we can't do with machines or by ourselves. And they've tried to phase out the dolphins. I know the U. S. Has like invested a lot of money in trying to make robots do the mind detection. But like you were saying there are some things that the robots are good at and there's some things that biological creatures are better at. So they still have the dolphins. </s><s>[INST] So there's also pigeons. [/INST] Yeah pigeons. Oh my gosh. There's so many examples that I mean the pigeons were the original hobby photography drone. They also carried mail for thousands of years letting people communicate with each other in new ways. So the thing that I like about the animal analogies, they have all these physical abilities but also sensing abilities that we just we don't have. And like that's that's just so useful and that's that's robots. Right, robots have physical abilities. They can help us lift things or do things that were not physically capable of. They can also sense things. It's </s><s>[INST] just I just feel [/INST] like I still feel like it's a really good analogy. </s><s>[INST] And [/INST] and it works because people are familiar with it. </s><s>[INST] What about companionship and when we start to think about my cats and dogs and pets that seem to serve no purpose whatsoever except the social connection. [/INST] Yeah I mean it's kind of a newer thing </s><s>[INST] at [/INST] least in the United States. Like </s><s>[INST] dogs used [/INST] to have </s><s>[INST] like they used to have a [/INST] purpose. They used to be guard dogs or they had some sort of function and then at some point they became just part of the family. Um And I </s><s>[INST] it's [/INST] it's so interesting how there's some animals that we've treated </s><s>[INST] as [/INST] workers, some that we've treated as objects, some that we eat and some that are parts of our families and that that's different across cultures. And I am convinced that we're going to see the same thing with robots um where people are going to </s><s>[INST] develop strong emotional [/INST] connections to certain robots that they relate to either culturally or or personally emotionally. And then there's gonna be other robots that we don't treat the same way. </s><s>[INST] I wonder does that have to do more with the culture and the people or the robot design is the interplay between the two. Like why did dogs and cats, I'll compete ox and I don't know what else like farm animals to to really get inside the home and get inside our hearts. [/INST] Yeah. I mean people point to the fact that dogs are very genetically flexible and um </s><s>[INST] they [/INST] can evolve much more quickly than other animals. And so they evolutionary biologists think that dogs evolved to be more appealing to us and then once we learned how to breathe, then we started breeding them to be more appealing to us too. Which is not something that we necessarily will be able to do with cows, although we've bred them to make more milk for us. So, but part of it is also culture. I mean there are cultures where people eat dogs still today and then there's other cultures where we're like, oh no that's terrible. We would never do that. And so I think there's a lot of different elements that play in. </s><s>[INST] I wonder if there is good because I understand dogs because they use their eyes, they're able to communicate affection, all those kinds of things. It's really interesting what dogs do. There's a whole conferences and dog consciousness and cognition and all that kind of stuff. Now cats is a mystery to me because they seem to not give a shit about the human but [/INST] they're warm and fluffy but </s><s>[INST] they but they are also passive aggressive. So they're at the same time they're like they're dismissive of of you and some sons. I [/INST] think some people like that. Some people like that about people. </s><s>[INST] Yeah. They want they want to push and pull over of relationships. [/INST] They don't want loyalty or unconditional love. That does that means they haven't earned </s><s>[INST] it. Yeah. And maybe that says a lot more about the people than it does about the animal [/INST] therapy. </s><s>[INST] Yeah. So I'm judging harshly the people that have cats or the people who have dogs, maybe the people that have dogs are are desperate for attention and unconditional love and they're unable to to um to sort of struggle to earn meaningful connections. Um, I don't know, [/INST] maybe people are talking about you and your robot pets in the same way. Yeah. </s><s>[INST] That's uh it is kind of sad. There's just the robots everywhere, but it's, I mean I'm joking about it being sad because I think it's kind of beautiful. I think robots are beautiful in the same way that pets are, even Children in that like they capture some kind of magic of social robots. They have the capacity to have the same kind of magic of connection. Um, I don't know what that is like um when they're brought to life and they move around the way they make me feel, I'm pretty convinced is as, as you know, they will make billions of people feel. I don't think I'm like some weird robotics guy. I'm not, I mean [/INST] you are, but not in this way, </s><s>[INST] not this way. I mean I just, I can put on my like normal human hat and just see this, oh, this is like, there's a lot of possibility there of something cool, just like with dogs. What is it? Why are we so into dogs or cats? Like it's like that. It's way different than us. [/INST] It is. </s><s>[INST] It's like drooling all over the place with this tongue out. It's like what? It's like a weird creature that used to be a wolf. Why are we into this thing? [/INST] Well dogs can either express or mimic a lot of emotions that we recognize. Um, and I think that's a big thing, like a lot of the magic of animals and robots is our own self projection. And the easier it is for us to see ourselves in something and project human emotions or qualities or traits onto it, the more will relate to it. And then you also have the movement. Of course, I think that's also really that's why I'm so interested in physical robots because that's, I think the visceral magic of them. I think we're, I mean there's there's research showing that we're probably biologically hardwired to respond to autonomous movement in our physical space because we've had to watch out for predators or whatever the reason is. Um, and so animals and robots are very appealing to us as these autonomously moving things that we view as agents instead of objects. </s><s>[INST] I I love the moment, which is I've been particularly working on, which is when a robot like the cowboy hat uh is doing its own thing. And then uh, it recognizes you. I mean the way dog does and it, it looks like this and the the moment of recognition like you're walking say you're working at the airport on the street and there's just, you know, hundreds of strangers. But then you see somebody, you know, and that like when you wake up to like that excitement of seeing somebody, you know, and saying hello and all that kind of stuff that's a magical moment, like uh I think especially with the dog, it makes you feel noticed and heard and and loved like that somebody looks at you and recognize you that that it matters that you exist [/INST] you feel seen. </s><s>[INST] Yeah, and that's a cool feeling and I honestly think robots can give that feeling. [/INST] Yeah, totally. </s><s>[INST] Currently Alexa, I mean one of the downsides of these systems is they don't their servants, they like part of the, you know, they're trying to maintain privacy I suppose. But I don't feel seen Alexa, I think [/INST] that's going to change. I think you're right and I think that's that's the game changing, changing nature of things like these large language learning models and the fact that these companies are investing in embodied versions that move around of Alexa like astro, can </s><s>[INST] I just say yeah, I haven't is that out? I [/INST] mean it's out, you can't just like buy one commercially yet, but you can apply for one. </s><s>[INST] Yeah, my gut says that these companies don't have the guts to do the personalization. This goes to the because it's edgy, it's dangerous. It's gonna make a lot of people very angry like in the way that, you know, just imagine, okay, alright, if you do the full landscape of human civilization, just visualize the number of people that are going through breakups right now, just the amount of really passionate, just even if you just look at teenagers, the amount of deep heartbreak that's happening and like if you're going to have Alexa have more of a personal connection with the human, you're going to have humans that like have existential crisis. There's a lot of people that suffer from loneliness and depression and like you're now taking on the full responsibility of being a companion to the roller coaster of the human condition as a company. You can imagine pr and marketing people, they're gonna freak out. They don't have the guts. It's gonna have to come from somebody from a new apple from those kinds of like it's a small startup [/INST] and it might like they're coming. There's already virtual therapist, there's that replica app. I haven't tried it but replicas like a spiritual companion. Like it's coming and if big companies don't do it, someone else will. </s><s>[INST] Yeah, I think the next the future, the next trillion dollar company will be those personalization. Because if you think um if you think about all the ai we have around us all the smartphone and so on. There's very minimal personalization. You [/INST] don't think that's just because they weren't able really, I </s><s>[INST] don't think they have the guts. [/INST] I mean it might be true, but I have to wonder, I mean google is clearly gonna do something with the link. I mean they </s><s>[INST] don't have the guts. [/INST] Are you challenging them </s><s>[INST] partially, but not really because I know they're not going to do it. I mean they don't have to it's bad for business in the short term? [/INST] I'm gonna be honest like maybe it's not such a bad thing if they don't just like roll this out quickly because I do think there are huge issues and and there's not just issues with like the responsibility of like unforeseen effects on people but what's the business model? And if you are using the business model that you've used in other domains then you're gonna have to collect data from people which you will anyway to personalize the thing and you're gonna be somehow monetizing the data or you're gonna be doing some like ad model. It just it seems like now we're suddenly getting into the realm of like severe consumer protection issues and I'm I'm really worried about that. I I see massive potential for this technology to be used in a way that's not for the public good and not. I mean that's in in an individual user's interest maybe but not in society's interest. </s><s>[INST] I think I think that kind of personalization should be like redefine how we treat data. I think you should own all the data your phone knows about you like and be able to delete it with a single click mark away and that data cannot be monetized or used or shared anywhere without your permission. I think that's the only way people will trust you to give for you to use that data but [/INST] then how are companies gonna I mean a lot of these applications rely on massive troves of data to train the ai system </s><s>[INST] right? So you have to um opt in constantly and opt in not in some legal. I agree. But obviously like show exactly like in the way I opt in to tell you a secret like we understand like that like I have to choose like how well do I know you? And then I say like don't tell this to anyone and then I have to judge how leaky that like how good you are keeping secrets in that same way. Like it's very transparent in which data you're allowed to use for which purposes. [/INST] That's what people are saying is the solution. And I think that works to some extent having transparency, having people consent. I think it breaks down at the point at which we've seen this happen on social media to like people are willingly giving up their data because they're getting a functionality from that. And then the harm that that causes is on a like maybe just someone else and not to them personally. So </s><s>[INST] I don't think people are given their data, they're not being asked like [/INST] but if if you were </s><s>[INST] consensual, [/INST] if you were like </s><s>[INST] tell [/INST] Me a secret about yourself and I'll give you $100. I'd tell you a secret. </s><s>[INST] No not $100. 1st of all you wouldn't you wouldn't trust like why you gave me $100. [/INST] But </s><s>[INST] but like I I need um I would ask for your specific like fashion uh interest in in order to give recommendations to you for shopping. And I would be very clear for that and you can disable that. You can delete that. But but then you can be have a deep meaningful rich connection with the system about what you think you look fat in, where you look great in what like the full history of all the things you've worn. Whether you uh regret that Justin Bieber enjoy the Justin Bieber usher all of that information that's mostly private to even you, not even your loved ones that a system should have that because then a system if you trust it to keep control of that data that you own, you can walk away with that system can tell you a damn good thing to wear. [/INST] It could. </s><s>[INST] And [/INST] the harm that I'm concerned about is not that the system is going to then suggest address for me that is based on my preferences. So I went to this conference once whereas talking to the people who do the analytics and like the big ad companies and like literally a woman there was like I can ask you three totally unrelated questions and tell you what menstrual product you use. And so what they do is they aggregate the data and they map out different personalities and different people and demographics and then they have a lot of power and control to market to people. So like I might not be sharing my data with any of the systems because I'm like I'm on twitter, I know that this is bad. Other people might be sharing data that can be used against me. Like it's I think it's it's way more complex than </s><s>[INST] just I [/INST] share a piece of personal information and it gets used against me. I think that at a more systemic level and then it's always, you know, vulnerable populations that are targeted by this um you know, low income people being targeted for scamming loans or I don't know like I could get targeted like someone not me because I have someone who doesn't have kids yet and is my age could get targeted for like freezing their eggs. And there's all these ways that you can manipulate people where it's not really clear that that came from that person's data. It came from all of us, all of us opting into this. </s><s>[INST] But there there's a bunch of sneaky decisions along the way that could be avoided if there's transparency. So that one of the ways that goes wrong, if you share that data with too many ad networks don't run your own ad network don't share with anybody. Okay, [/INST] this data, </s><s>[INST] you belongs to just you and all the ways you allow the company to use it the default isn't no way at all and you are consciously constantly saying exactly how to use it and uh and also it has to do with the recommended system itself from the company which is um freezing your eggs, if that doesn't make you happy, if that idea doesn't make you happy then the system shouldn't recommend it and should very be very good at learning. So not the kind of things that the category of people it thinks you belong to will do, but more you specifically what makes you happy, what is helping you grow? [/INST] But you're assuming that people's preferences and like what makes them happy is static. Whereas when were talking before about how a company like Apple can tell people what they want and they will start to want it. That's the thing that I'm more concerned about. </s><s>[INST] Yeah, that is a huge problem. It's not just listening to people but manipulating them into wanting something [/INST] and that's like we have a long history of using technology for that purpose, like the persuasive design in casinos to get people to gamble more or like it's just, I'm, the other thing that I'm worried about is as we have more social technology, suddenly you have this on a new level. Like if you look at the influencer marketing that happens online now. </s><s>[INST] So [/INST] like on instagram there will be some like person who has a bunch of followers and then a brand will like hire them to promote some product and it's above board, They disclose like I'm, this is an ad that I'm promoting, but they have so many young followers who like deeply admire and trust them. I mean this must work for you too. Don't you have like ads on the podcast? Like people </s><s>[INST] trust magic spoon cereal, low carb. Yes, [/INST] if you say that, like I guarantee you some people will buy that just because even though they know that you're being paid, they trust you. </s><s>[INST] Yeah, it's different with podcast because well my particular situation, but it's true for a lot of podcast, especially big ones is, you know, I have 10 times more sponsors that want to be sponsors than than I have. So [/INST] you get to select the ones that you actually want to support </s><s>[INST] and so like you end up using it and then you're able to actually like there's no incentive to like um shell for anybody. [/INST] Sure, and that's why it's fine when it's still human influencers </s><s>[INST] right [/INST] now, if you're a bot, you're not going to discriminate, you're not gonna be like, oh are you? This product is good for people? </s><s>[INST] You think there will be like bots essentially with millions of followers [/INST] already are there are virtual influencers in south Korea who show products and and like that's just the tip of the iceberg because that's still very primitive now with the new image generation and the language learning models and like, so we're starting to do some research around kids um and like young adults because a lot of the research on like what's okay to advertise to kids and what is too manipulative has to do with television ads back in the day where like a kid who's 12 understands oh that's an advertisement, I can distinguish that from entertainment. I know is trying to sell me something now it's getting really, really murky with influencers and then if you have like a bot that's that a kid has developed a relationship with, is it okay to market products through that or not? Like you're getting into all these consumer protection issues because you're developing a trusted relationship with a social entity. But it's and and so and so now it's like personalized, it's scalable, it's automated and it has it can so some of the research showing that kids are already very confused about like the incentives of the company versus what the robot is doing </s><s>[INST] meaning there. [/INST] So okay </s><s>[INST] not deeply understanding the incentives of the system. [/INST] Well yeah, so like kids who are old enough to understand this is a television advertisement is trying to advertise to me, I might still decide I want this product but they understand what's going on. So there's some transparency there, that age child. So um Daniela di paola Anastasia Ostrowski and I advised on this project, they did this um they asked kids who had interacted with social robots whether they would like a policy that allows robots to market to people through casual conversation or whether they would prefer that it has to be transparent that it's like an ad coming from a company and the majority said they preferred the casual conversation and when asked why there was a lot of confusion about, they were like, well the robot knows me better than the company does. So the robots only going to market things that I like and so they don't really, they're not connecting the fact that the robot is an agent of the company. They're viewing it as something separate. And I think that even happens subconsciously with grown ups when it comes to robots and artificial agents and it will like this black guy at google started going on and on. But like his main concern was that google owned the sentient agent and that it was being mistreated. His concern was not that the agent was going to mistreat people. So I think we're going to see a lot of this. </s><s>[INST] Yeah, but shitty companies will do that. I think ultimately that confusion should be alleviated by the robot should actually know you better and should not have any control from the company. [/INST] But what's the business model for that </s><s>[INST] is if you use the robot to buy first of all, the robot should probably cost money, [/INST] cost </s><s>[INST] money like the way Windows operating system. Does I see it more like an operating system than um like this thing is your window no pun intended into the, into the world. So it's helping you, it's like a personal assistant, Right? And so that should cost money. You should, you know, whatever it is, $10, 20 bucks. Like that's the thing that makes your life significantly better. This idea that everything should be free is is like it should actually help educate, you should talk sh it about all the other companies that do stuff for free. But but also yeah, in terms of if you purchase stuff based on its recommendation, it gets money. So it's, it's kind of ad driven but it's not ads. It's like um um it's not controlled like no external entities can control it to try to manipulate to want a thing. [/INST] It's </s><s>[INST] actually trying to discover what you want. So it's not allowed to have any influence, no promoted and know anything. So it's finding, I don't know the thing that would actually make you happy. That's the only thing he cares about. I think, I think companies like this can win out. [/INST] Yes. I think eventually once people understand the value of the robot, even just like I think that robots would be valuable to people even if they're not marketing something or helping with like preferences or anything like just a simple the same thing as a pet, like a dog that has no function other than being a member of your family. I think robots could really be that and people would pay for that. I don't think the market realizes that yet. And so my concern is that companies are not going to go in that direction at least not yet of making like this contained thing that you bought. It seems almost old fashioned right to have a disconnected object that you buy that you're not like paying a subscription for, it's not like controlled by one of the big corporations. </s><s>[INST] That's the old fashioned things that people yearn for it because I think is very popular now and people understand the negative effects of social media, the negative effects of the data being used in all these kinds of ways. I think, I think we're just waking up to the realization we tried, but we were like baby deer finding our legs in this new world of social media of ad driven companies and realizing, okay, this has to be done somehow different that like like one of the most popular notions at least the United States that social media is evil and is doing bad, it's doing bad by us. It's not like it's totally tricked us into believing that it's good for us. I think everybody knows it's bad for us. And so like there's a hunger for other ideas. All [/INST] right. It's time for us to start that company. So let's do it. </s><s>[INST] Let's go. Hopefully [/INST] No one listens to this and steals the </s><s>[INST] idea. There's no, see that's the other thing. I think I'm a big person on um, execution is what matters. I mean it's like ideas are kind of true. The social robotics is a good example that there's been so many amazing companies that went out of business. I mean to me it's obvious like it's obvious that there will be a robotics company that puts a social robot in the home of billions of homes. Yeah and it'll be a companion. Okay, there you go, you can steal that idea, do it. [/INST] What about Elon musk's humanoid? Is he going to execute on that? </s><s>[INST] There might be a lot to say. So for people who are not aware there's an optimist Tesla's optimist robot. That's um I guess the stated reason for that robot is a humanoid robot in the factory that's able to automate some of the tasks that humans are currently doing. And the reason you want to do this, the second reason you mentioned the reason you want to do a humanoid robots because the factory is built for a certain tasks that are um designed for humans. So it's hard to automate with any other form factor than a humanoid. And then the other reason is because so much effort has been put into this giant data engine machine of, of perception that's inside Tesla autopilot. That's seemingly at least the machine, if not the data is transferable to the factory setting to any setting. Yeah. [/INST] He said he would do anything that's boring to us. </s><s>[INST] Yeah. Yeah. The interesting thing about that is there's no interest and no discussion about the social aspect, like I talked to him on mike and off mike about it quite a bit and there's not a discussion about like to me it's obvious if a thing like that works at all at all. In fact it has to work really well in a factory. If it works kind of shitty, it's much more useful in the home [/INST] because </s><s>[INST] we're much this where I think being shitty and stuff is kind of what makes relationships great like you want to be flawed and be able to communicate your flaws and be unpredictable in certain ways. Like if you fell over every once in a while for no reason whatsoever. I think that's essential for for [/INST] like </s><s>[INST] it's charming but also concerning and also like uh like like are you okay? It's both hilarious. It's whenever somebody you love like falls down the stairs, it was both hilarious and concerning. Some some dance between the two and I think that's essential for like um you almost want to engineer that in except you don't have to because of robotics in the physical space is really difficult. So um I think I've learned to not discount the the efforts that Ellen does. There's a few things that are really interesting there. one because he's taken extremely seriously. What I like is the humanoid form the cost of building a robot. I talked to jim Keller offline about this a lot? And currently humanoid robots cost a lot of [/INST] money? </s><s>[INST] And the way they're thinking about it now, they're not talking about all the social robotics stuff that you and I care about. Uh they are thinking how can we manufacture this thing cheaply and do it like well and the kind of discussions they're having is really great engineering. It's like, it's like first principles question of like why is this cost so much? Like what's the cheap way? Why can't we build? And there's not a good answer. Uh why can't we build this Humanoid form for under $1000? And like I've I've sat and had these conversations. There's no reason. It's I think the reason they've been so expensive is because they were focused on trying to they weren't focused on doing the mass manufacturer. There were people are focused on getting a thing that's um, I don't know, I don't know exactly what the reasoning is, but it's the same like Waymo is like, let's let's build a million dollar car in the beginning, like multimillion dollar car. Let's try to solve that problem. The way Ellen with Jim Keller, the way some of those folks are thinking is let's like at the same time try to actually build a system that's cheap, not crappy but cheap unless from first principles. What is the minimum amount of degrees of freedom we need? What are the joints? Where's the control set? Like how many how do we act like we're the activators? What's the way to power this in the lowest cost way possible. But also in a way that's like actually works. How do we make the whole thing, not part of the components where there's a supply chain, you have to have all these different parts that have defeated, Do it all from scratch and do the learning. I mean it's like immediately certain things like become obvious do uh the exact same pipeline as you do for autonomous driving. Just exactly. I mean the infrastructure that is incredible for the computer vision, for the manipulation task. The control problem changes the perception uh problem changes but the pipeline doesn't change, do it. So I don't I don't um obviously the optimism about how long it's going to take, I don't [/INST] share. </s><s>[INST] Um but it's a really interesting problem and I don't want to say anything because my first gut is to say that why the humanoid form. That doesn't make sense. But then there's a lot of people that are really excited about the humanoid form there. It's like I don't want to get in the way like that, they might solve this thing and they might, it's like similar with boston dynamics like why like if I were you can be a hater and B. And you go go up to Mark robert and and just like how are you gonna make money with these super expensive legged robots? What's what's your business plan? This doesn't make any sense. Why are you doing these legged robots? But at the same time they're pushing forward the science, the art of robotics and the way that nobody else does. Yeah. And uh with Ellen they're not just going to do that. They're going to drive down the cost to where we can have humanoid bots in the home potentially. [/INST] So the part I agree with is </s><s>[INST] a [/INST] lot of people find it fascinating and it probably also attracts talent who want to work on humanoid robots. I think it's a fascinating scientific problem and engineering problem and it can teach us more about human body and locomotion and all of that. I think there's a lot to learn from it where I get tripped up is why we need them </s><s>[INST] for [/INST] anything other than art and entertainment in the real world. Like I get that there are some areas where you can't just rebuild like a spaceship. You can't just like they've worked for so many years on these spaceships. You can't just re engineer it. You have some things that are just built for human bodies. A submarine spaceship, </s><s>[INST] but [/INST] a factory </s><s>[INST] maybe [/INST] I'm naive but it seems like we've already rebuilt factories to accommodate other types of robots. Why would we want to just like make a humanoid robot to go in there. I I just get really tripped up on. I think that people want humanoids? I think people are fascinated by them. I think it's a little overhyped. </s><s>[INST] Well most of our world is still built for humanoids. [/INST] I know but it shouldn't be it should be built so that it's wheelchair accessible. </s><s>[INST] Right? So the question is do you build a world that's the general former wheelchair accessible? Uh all robot form factor accessible or do you build robots? [/INST] It doesn't have to be all and it also doesn't have to be either or I just feel like we're thinking so little about the system in general and how to create infrastructure that works for everyone. All kinds of people. All kinds of robots like that's that. I mean it's more of an investment but that would pay off way more in the future than just trying to cram expensive or maybe slightly less expensive humanoid technology into a human. </s><s>[INST] Unfortunately one company can't do that. We have to work together. It's like autonomous driving can be easily solved if you do V. Two I if you change the infrastructure of cities and so on. But that requires a lot of people, a lot of them are politicians and a lot of them are somewhat if not a lot corrupt and all those kinds of things. I and the talent thing you mentioned is really really really important. I've gotten a chance to meet a lot of folks at SpaceX and Tesla um other companies too but they're specifically the openness makes it easier to like meet everybody. I think a lot of amazing things in this world happen when you get amazing people together. And if you can sell an idea like us becoming a multi planetary species, you can say why the hell I would go to mars like why colonize mars? If you think from from basic first principles, it doesn't make any sense. It doesn't make any sense to to go to the moon. It doesn't go it. The only thing that makes sense to go to space is for satellites, But there's something about the vision of the future. The optimism laden that permeates this vision of us becoming multi planetary is thinking not just for the next 10 years. It's thinking like human civilization reaching out into the stars. It makes people dream, it's really exciting and that they're going to come up with some cool ship that might not have anything to do with. Like here's why because it doesn't seem to care about social robotics, which is constantly surprising to me. Talk to him. It doesn't humans are humans are the things you avoid and don't hurt [/INST] right? </s><s>[INST] Like that's like the number one job of a robot is not the herd of human to avoid them. You know that the collaborative aspect, the human robot interaction. I think it's not at least not in his, uh, not something he thinks about deeply, but my sense is if somebody like that takes on the problem of human robotics, we're gonna get a social robot out of it. Like people like, not, not necessarily Ellen, but people like, like Ellen, if they take on seriously these um, like I can just imagine with the humanoid robot, you can't help but create a social robot. So if you do different form factors, if you do industrial robotics, um, you don't, you're likely to actually not end up like walking head into a social, social robot, human robot interaction problem. If you create for whatever the hell reason you want to a humanoid robot, you're gonna have to reinvent, well not reinvent, but do um introduce a lot of fascinating new ideas into the problem of human robot interaction, which I'm excited about. So like if I, if I was a business person, I would say this is not, this is this is way too risky. This doesn't make any sense. But when people are really convinced and there's a lot of amazing people working on it, it's like, all right, let's see what happens here. This is really interesting. Just like with atlas and boston dynamics. I mean, they, I apologize if I'm ignorant on this, but I think they really more than anyone else maybe with my boat like Sony pushed forward human robotics like a leap with [/INST] Absolutely </s><s>[INST] and like without them, like why the hell did they do it? [/INST] Why? Well, I think for them it is a research platform. It's not, I don't think they ever the speculation. I don't think they ever intended atlas to be like a commercially successful robot. I think they were just like can we do this? Let's try. </s><s>[INST] Yeah. I wonder if they may be the answer they landed on is Because they eventually went to um spot the earlier versions of spot. So quadruped has like 44 legged robot. But maybe they reached for, let's try to make um like [/INST] I think they tried </s><s>[INST] it and they still are trying it for atlas to be picking up boxes to moving boxes to being it makes sense okay if they were exactly the same cost it makes sense to have a human robot in the warehouse [/INST] currently shortsighted but yes currently yes it would sell. </s><s>[INST] But it's not it's it's shortsighted, it's shortsighted but it's not pragmatic to think any other way to think that you're gonna be able to change warehouses. You're gonna have to you're going yes. Yes but even if your amazon that's very costly to change warehouses. [/INST] It is it's a big investment </s><s>[INST] but isn't shouldn't you do that investment in a way? So here's the thing if you build a human robot that works in the warehouse that human robot c I don't know why. Test is not talking about it this way. As far as I know like that human robot is going to have all kinds of other applications outside they're setting, like to me it's obvious. I think it's a really hard problem solved but whoever solves the human robot problem are going to have to solve the social robotics problem. [/INST] I mean they're already with the spot needing to solve social robotics problems </s><s>[INST] for like for spot to be effective at scale. I'm not sure Spot is currently effective. Scale is getting better and better but they're actually the the thing they did is an interesting decision perhaps that will end up doing the same thing which is Spot is supposed to be a platform for intelligence. So Spot doesn't have any high level intelligence like um high level perception skills, it's supposed to be controlled remotely [/INST] and </s><s>[INST] somebody else is supposed to do the attaching. It's a platform that you can take an uneven ground and it's able to maintain balance, go into dangerous situations. It's a platform on top of that. You can add a camera that the surveillance that you can remotely monitor, you can record. Uh you can record the camera, uh you can remote control it but it's [/INST] not basic </s><s>[INST] object manipulation but not autonomous object manipulation. It's remotely controlled. But the intelligence on top of it which is what would be required for automation. Somebody else is supposed to do perhaps that's what would do the same the same thing ultimately. But it doesn't make sense because the goal of optimists is automation without that. Um [/INST] But </s><s>[INST] then you never know. It's like why go to mars why why? I [/INST] mean that's true and I I reluctantly like I'm very excited about space travel. Um </s><s>[INST] Why can you introspect? Like why why [/INST] am I excited about it? I think what got me excited was I saw a panel with some people who um study other planets and it became really clear how little we know about ourselves and about how nature works and just how much there is to learn from exploring other parts of the universe. So like on a rational level that's how I convinced myself that that's why I'm excited in reality. It's just fun, exciting. I mean just like the idea that we can do this difficult thing and that humans come together to build things that can explore space. I mean there's just something inherently thrilling about that and I'm reluctant about it because I feel like there are so many other challenges and problems that I think are more important to solve but I also think we should be doing all of it at once. And so to that extent I'm like all for research on humanoid robots, development of humanoid robots. </s><s>[INST] I [/INST] think that there's a lot to explore and learn and it doesn't necessarily take away from other areas of science at least it shouldn't. I think unfortunately a lot of the attention goes towards that and it does take resources and attention away from other areas of robotics that we should be focused on but I don't think we shouldn't do it. </s><s>[INST] So you think it might be a little bit of a distraction? Oh forget the Ellen particular application, but if you care about social robotics, the humanoid form is a distraction. [/INST] It's a distraction and it's one that I find particularly boring. It's just it's interesting from a research perspective but from like what types of robots can we create to put in our world? Like why would we just create a humanoid robot? So </s><s>[INST] even even just robotic manipulation so arms is not useful. Either [/INST] arms can be useful but like why not have three arms? Like why does it have to look like a person? </s><s>[INST] Well I actually personally just think that washing the dishes is harder than a robot that can be a companion. Yeah. Being useful in the home is actually really tough. [/INST] But does your companion have to have like two arms and look like you </s><s>[INST] know I'm I'm making the case for zero arms. [/INST] Okay. Zero arms. </s><s>[INST] Yeah. [/INST] Okay freaky. </s><s>[INST] That didn't come out the way I meant [/INST] it because </s><s>[INST] it almost sounds like I don't want a robot to defend itself. Like that's immediately you project, you know what I mean? Like uh [/INST] No </s><s>[INST] I think um I just think that the social component doesn't require arms or legs or so on right as we've talked about and I think that's probably where a lot of the meaningful impact that's gonna be happening. [/INST] Yeah I think just we could get so creative with the design like why not have a robot on roller skates or like whatever. Like why does it have to look like us? </s><s>[INST] Yeah. Still it is, it is a compelling and interesting form from a research perspective. Like you said you co authored the papers, you were talking about that for we robot 2022 lula robot consumer protection in the face of automated social marketing. I think you were talking about some of the ideas and that. Yes. [/INST] Oh, you got it from twitter. I was like, that's not published yet. </s><s>[INST] Yeah. What do you, This is how I do my research. [/INST] You just go through people's twitter feeds. </s><s>[INST] Yeah, go thank you. Um it's not stalking if it's public. Uh so there's a, you looked at me like you're offended like how did you know [/INST] I was just like worried that like some early, I mean </s><s>[INST] yeah, there's a pdf. There [/INST] is like now maybe like as of a few days ago. Okay. </s><s>[INST] Yeah. [/INST] Okay. </s><s>[INST] You look violated. Like how did you get that pdf? [/INST] It's just a draft. It's online. Nobody read it yet until we've written the final paper. </s><s>[INST] It's really good. So I enjoyed it. [/INST] Oh thank you. </s><s>[INST] By the time this comes out, I'm sure it'll be. [/INST] So basically we </s><s>[INST] robot that's the [/INST] workshop where you have an hour where people give you constructive feedback on the paper and then you write the good version, right? </s><s>[INST] I take it back. There's no pdf [/INST] doesn't exist </s><s>[INST] but there is a table in there in a virtual imagined pdf that I like. That I wanted to mention which is um like this kind of uh strategies used across various marketing platforms. And it's uh basically looking at traditional media, person to person interaction, targeted ads, influencers and social robots. This is the kind of idea that you've been speaking to. It's just a nice breakdown of that that social robots have personalized recommendations. Social persuasion, automated scalable data collection and embodiment. So person to person interaction is really nice but it doesn't have the automated and the data collection aspect. But the social robots have those two elements. [/INST] Yeah. We're talking about the potential for social robots to just combine all of these different marketing methods to be this really potent cocktail. And that table which was Daniel's idea and a really fantastic one. We put it in at the last second. So </s><s>[INST] yeah, I really liked that. [/INST] I'm glad you like it </s><s>[INST] in the pdf that doesn't [/INST] exist. Yes that </s><s>[INST] nobody can find if they look. So when you say social robots, what does that mean? Does that include virtual ones or No. [/INST] I think a lot of this applies to virtual ones too. Although the embodiment thing which I personally find very fascinating is definitely a factor that research shows can enhance people's engagement with a device </s><s>[INST] but can embodiment be a virtual thing. Also meaning like it has a body in the virtual world. [/INST] Like maybe </s><s>[INST] makes you feel like because what makes a body a body is a thing that um can disappear like um has a permanence, I mean there's certain characteristics that you kinda associated physical object. [/INST] So I think what I'm referring to and I think this gets messy because now we have all these new virtual worlds and um A. R. And stuff and I think it gets messy but there's research showing that something on a screen on a traditional screen and something that is moving in your physical space that that has a very different effect on how your brain perceives it even </s><s>[INST] so I mean I I have a sense that we can do that in a virtual world [/INST] probably like when I've used VR I jump around like an idiot because I think something is going to hit me. </s><s>[INST] And even if a video game on a two D. Screen is compelling enough, like the thing that's immersive about it is I kind of put myself into that world, you kind of those the the objects you're interacting with Call of Duty things you're shooting, they're they're kind of your imagination fills the gaps and it becomes real. Like it pulls your mind in when it's well done. So it really depends what's shown on on the two D screen. [/INST] Yeah. Yeah. I think there's a ton of different factors and there's different types of embodiment. Like you can have embodiment in a virtual world you can have an agent that simply text based which is has no embodiment. So I think there's a whole spectrum of factors that can influence how much you engage with something. Yeah. </s><s>[INST] I wonder, I always wondered if you can have like a an entity living in a computer, okay, this is gonna be dark, I haven't always wondered about this, it's gonna make it sound like I keep thinking about this kind of stuff. No but like um this is almost like Black Mirror, but the entity that's convinced I was able to convince you that is being tortured inside the computer and needs your help to get out something like this, that because to me to me suffering is one of the things that make you empathize with, like we're not good at as you've you've discussed another in the physical form, like holding a robot upside down, you have a really good examples about that and discussing that, I think suffering is a really good catalyst for empathy and I just feel like we can uh project embodiment and a virtual thing if it's capable of certain things like suffering. [/INST] Yeah, </s><s>[INST] I [/INST] think that's true and I think that's what happened with the lambda thing, not that I don't none of the transcript was about suffering, but it was about having the capacity for suffering and human emotion that convinced the engineer that this thing was sentient and it's basically the plot of X. Maquina </s><s>[INST] true, Have you ever made a robot like scream in pain. [/INST] Have I know but have you seen that someone </s><s>[INST] Oh [/INST] you know they actually they actually made a Roomba scream whenever it hit a </s><s>[INST] wall. Yeah I program that myself as well because I was inspired by that. [/INST] Yeah. </s><s>[INST] Oh sorry I hit a wall that didn't [/INST] whenever bumped into something it was screaming. </s><s>[INST] Yeah. No I so I had the way I programmed the room was just when I kick it whenever so contact between me and the robots when it screamed. [/INST] Really okay and you were inspired by that? </s><s>[INST] Yeah I guess I misremembered the video. I saw the video a long long time ago and uh or maybe you heard somebody mention and that just it's the easiest thing to program. So I did that I haven't run those rumors for over a year now. But yeah it was my experience with it was that it's like um they quickly become like you remember them uh you you missed them like they're real living beings so the capacity of yourself or or is a really powerful [/INST] thing. Even </s><s>[INST] then that I mean it was kind of hilarious. It was just a random recording of screaming from the internet but it's still it's still is weird there's a thing you have to get right based on the interaction like the latency. Like there is a [/INST] there </s><s>[INST] is a realistic aspect of how you should scream relative to when you get hurt. Like it should correspond correctly. [/INST] Like if you kick it really hard it should scream louder. </s><s>[INST] No it's just screaming at the appropriate time. [/INST] Not one </s><s>[INST] second later. Right? Like there's a exact like there's a timing when you get like I don't know when you run into when you run your foot into like the side of the table or something. There's a timing there. The dynamics. You have to get right for the for the actual screaming because the Rumba in particular uh doesn't so I was uh the sensors don't it doesn't know about pain [/INST] what </s><s>[INST] I'm sorry to say. Roomba doesn't understand pain. Uh So you have to correctly map the sensors, the timing to the production of the sound. But when you get that somewhat right it starts it's weird. It's really weird feeling and you actually feel like a bad person. [/INST] Yeah </s><s>[INST] so but it's it makes you think because that with all the ways that we talked about that could be used to manipulate you [/INST] in </s><s>[INST] a good and bad way. So the good ways like you can form a connection with a thing uh in a bad way that you can form a connection in order to sell you products that you don't want [/INST] or manipulate you politically or many nefarious things </s><s>[INST] you tweeted. We're about to be living in the movie. Her. Except instead I researched your tweets like they're like Shakespeare. [/INST] We're about to be living in the movie her except instead of about love is going to be about what I say the chatbot being subtly racist and the question whether it's ethical for companies to charge for software upgrades. </s><s>[INST] Yeah. So can we break that down? What do you mean by that? [/INST] Yeah obviously </s><s>[INST] some of it is humor. [/INST] Yes. Well kind of I am like it's so weird to be in the space where I'm so worried about this technology and also so excited about it at the same time but the really like I haven't I've gotten a little bit jaded and then with G. P. D. Three and then the lambda transcript. I was like we? Re energized but have also been thinking a lot about you know what are the what are the ethical issues that are gonna come up? And I think some of the things that companies are really gonna have to figure out is obviously algorithmic bias is a huge and known problem at this point. Like even you know the the new image generation tools like dolly where they've clearly put in a lot of effort to make sure that if you search for people it gives you a diverse set of people etcetera. Like even that one people have already found numerous like ways that it just kind of regurgitates biases of things that it finds on the internet. Like how if you search for success it gives you a bunch of images of men. If you search for sadness too, a bunch of images of women. So I think that this is this is like the really tricky one with these voice voice agents that companies are going to have to figure out and that's why it's subtly racist and not overtly because I think they're going to be able to solve the overt thing and then with the subtle stuff it's going to be really difficult. And then I think the other thing is going to be yeah like people are going to become so emotionally attached to artificial agents with this complexity of language with a potential embodiment factor that I mean there's already there's a paper that we robot this year written by roboticists about how to deal with the fact that robots die and looking at it as an ethical issue because it impacts people. And I think there's going to be way more issues than just that. Like like I think that the tweet was software upgrades right? Like how much is it okay to charge for something like that if someone is deeply emotionally invested in this relationship. </s><s>[INST] Oh the ethics of that. That's interesting. But there's also the practical funding mechanisms like you mentioned with the idea that the dog. In theory there's a subscription. [/INST] Yeah. The new Aibo so the old I bought from the 90s people got really attached to and in Japan. They're still having like funerals and Buddhist temples for the eyeballs that can't be repaired because people really viewed them as part of their families </s><s>[INST] talking about robot dog. [/INST] Robot dogs, the Ibo yeah the, the original like famous robot dog that Sony made came out in the 90s got discontinued having funerals for them in Japan. Now they have a new one. The new one is great. I have one at home. It's like </s><s>[INST] $3,000 [/INST] Think it's 3000 bucks. And then after a few years you have to start paying, I think it's like 300 a year for, for a subscription service for cloud services and the cloud services. Uh, I mean it's a lot of the dog is more complex than the original and it has a lot of cool features and it can remember stuff and experiences and it can learn and a lot of that is outsourced to the cloud and so you have to pay to keep that running, which makes sense. People you know should pay and people who aren't using, it shouldn't have to pay. But it does raise the interesting question, could you set that price to reflect a consumer's willingness to pay for the emotional connection? So if, if like, you know that people are really really attached to these things just like they would be to a real dog, could you just start charging more because there's like more demand. </s><s>[INST] Yeah, you have to be. But there, but that's true for anything that people love, right? [/INST] It is and it's also true for real dogs like there's all these new medical services nowadays where people will shell out thousands and thousands of dollars to keep their pets alive. And is that taking advantage of people or is that just giving them what they want? That's the question </s><s>[INST] back to marriage. What about all the money that it costs to get married and then all the money that it costs to get a divorce. That feels like a very like uh that's like a scam. I think the society is full of scams that are like [/INST] it's such a scam. And then we've created like the whole wedding industrial complex has created all these quote unquote traditions that people buy into that aren't even traditions like they're just fabricated by marketing. Like it's awful. </s><s>[INST] Let me ask you about racist robots. [/INST] Sure. </s><s>[INST] Is it up to a company that creates that we talked about removing bias and so on. And that's a really popular field in ai currently and a lot of people agree that it's an important field, but the question is for like social robotics is should it be up to the company to remove the bias of society [/INST] to remove the bias of society. </s><s>[INST] Like I guess because there's a lot of people that are subtly racist in modern society. Like why shouldn't our robots also be subtly racist. I mean that's like why do we put so much responsibility on the robots [/INST] I'm </s><s>[INST] imagining like a like a Hitler [/INST] Roomba </s><s>[INST] I mean that that would be funny. But I guess I'm asking a serious [/INST] question. Yes. </s><s>[INST] Exactly. I'm allowed to make that joke. Yes. And I've been nonstop reading about World War Two and Hitler I think um I'm glad we exist in a world where we can just make those jokes. Um that helps deal with it. Anyway. [/INST] It </s><s>[INST] is a serious question of sort of like um like it's such a difficult problem to solve now of course like bias and so on. Like there's low hanging fruit which I think there's a lot of people are focused on. But then it becomes like subtle stuff over time and it's very difficult to know. Now if you can if you can also completely remove the personality, you can completely remove the personalization. You [/INST] can remove the language aspect, which is what I had been arguing because I was like the language is disappointing aspect of social robots anyway, but now are we introducing that? Because it's it's now no longer disappointing. So I do think well let's just start with the promise, which I think is very true. Which is that racism is not a neutral thing, but it is the thing that we don't want in our society. Like I it does not conform to my values. So if we agree that racism is bad, I do think that it has to be the company because the problem, I mean it might not be possible and companies might have to put out products that where they're taking risks and they might get slammed by consumers and they might have to adjust. I don't know like how this is going to work in the market. I have opinions about how it should work, but it is on the company and the danger with robots is that they can entrench this stuff. It's not like your racist uncle who you can have a conversation with and </s><s>[INST] put things into context. Maybe. [/INST] Yeah. Or who might change over time with more experience a robot really just like regurgitates things entrenches them could influence other people. And I mean, I think that's terrible. Well, </s><s>[INST] I think there's a difficult challenge here is because even the premise he started with that essentially racism is bad. Um, I think we live in a society today where the definition of racism is different between different people. Some people say that it's not enough not to be racist. Some people say you have to be anti racist. So you have to, you have to have a robot that constantly calls out like calls you out on your implicit racism. [/INST] I would love, </s><s>[INST] I [/INST] would love that robot, </s><s>[INST] but like maybe it maybe it says, well I don't know if you love it because maybe you'll see racism and things that aren't racist and then you're arguing with your robots just going racist. I'm not, I'm not exactly sure that. I mean it's a tricky thing. I guess I'm saying that the line is not obvious, especially in this heated discussion where we have a lot of identity politics of what, what is harmful to different groups and so [/INST] on. It </s><s>[INST] feels different. It feels like a the broader question here is should a social robotics company be solving or being part of solving the issues of society? [/INST] Well, okay, I think it's the same question as should I as an individual be responsible for knowing everything in advance and saying all the right things. And the answer to that is yes, I am responsible, but I'm not going to get it perfect. And then the question is how do we deal with that? And so as a person, how I aspire to deal with that is when I do inevitably make a mistake because I have blind spots and people get angry. I don't take that personally. And I listen to what's behind the anger and it can even happen that like maybe I'll tweet something that's well intentioned. And one, you know, one group of people starts yelling at me and then I change it the way that they said. And then another group of people starts yelling at me which has happened. This happened to me actually, um, around in my talks, I talk about robots that are used in autism therapy and so whether to say a child with autism or an autistic child is super controversial. And a lot of autistic people prefer to be referred to as autistic people and a lot of parents of autistic Children prefer child with autism. And then there's they disagree. So, so I've gotten yelled at from both sides and I think I'm still respond, I'm responsible even if I can't get it right. I don't know if that makes sense. Like it's a responsibility thing and I'm, I can be as well intentioned as I want and I'm still going to make mistakes and that is part of the existing power structures that exist. And that's something that I accept </s><s>[INST] and you accept being attacked from both sides and grow from it and learn from it. But the danger is that after being attacked assuming you don't get canceled a K A completely removed from your ability to tweet, uh, you might become jaded and not want to talk about autism anymore. [/INST] I don't and I didn't, I mean it's happened to me, </s><s>[INST] but that's what [/INST] I did was I listened to both sides and I chose, I tried to get information and then I decided that I was going to use autistic Children and now I'm moving forward with that. Like I don't </s><s>[INST] know for [/INST] now. Yeah. Until until I get updated information and I'm never going to get anything perfect. But I'm making choices and I'm moving forward because being a coward and like just retreating from that I think. But </s><s>[INST] here's the problem. You're a very smart person and an individual researcher thinker an intellectual, so that's the right thing for you to do. The hard thing is one as a company, imagine you had a PR team, he said kate like this. You [/INST] should. </s><s>[INST] Yeah, I mean, just well, if you were if you hired pr people, like obviously they would see that and they'd be like, well, maybe don't bring up autism, Maybe don't bring up these topics. You're you're getting attacked. It's bad for your brand. They'll say the brand word. They'll be uh you know, if you look at different demographics that are inspired by your work, I think it's insensitive to them. Let's not mention this anymore. Like there's this kind of pressure that all of a sudden you or or you do suboptimal decisions, you take a kind of poll. Um again, it's looking at the past versus the future, all those kinds of things. And it becomes difficult in the same way that it's difficult for social media companies to figure out like who's censor who recommend this [/INST] is ultimately a question about leadership. Honestly, like the way that I see leadership, because right now the thing that bothers me about institutions and a lot of people who run current institutions is that their main focus is protecting the institution of protecting themselves personally. That is bad leadership because it means you cannot have integrity, you cannot lead with integrity and it makes sense because like obviously if you're the type of leader who immediately blows up the institution, you're leading then that doesn't exist anymore. And maybe that's why we don't have any good leaders anymore because they had integrity and they didn't put, you know, the survival of the institution first. But I feel like you have to just to be a good leader, you have to be responsible and understand that with great power comes great responsibility, you have to be humble and you have to listen and you have to learn, you can't get defensive and you cannot put your own protection before other things </s><s>[INST] take risks where you might lose your job, you might lose your well being because of um because in the process of standing for the principles for the things you think are right to do. Yeah. Based on the things you like, based on learning from like listening to people and learning from what they what they feel and the same goes for the institution. Yeah. Yeah. But I ultimately actually believe that those kinds of companies and countries succeed that have leaders like that you should run for president. [/INST] No, thank </s><s>[INST] you. Yeah, [/INST] that's maybe the problem like the people who have good ideas about leadership, they're like, </s><s>[INST] yeah, this [/INST] is why I don't I'm not running a company. </s><s>[INST] It's been I think three years since the Jeffrey Epstein controversy at M. I. T. M I. T. Media Lab, joi ito the head of the Media lab resigned and I think at that time you wrote an opinion article about it. So just looking back a few years have passed, what what have you learned about human nature? Um from the fact that somebody like Jeffrey Epstein found his way inside M. I. T. [/INST] It's a really good question, what have I learned about human nature? I think, well there's there's how did this problem come about, and then there's what was the reaction to this problem and to it becoming public? And in the reaction, the things I learned about human nature were that sometimes cowards are worse than assholes, wow, I'm really </s><s>[INST] that's a really powerful statement, [/INST] I think because the assholes at least you know what you're dealing with, they have integrity in a way they're just living out their asshole values and the cowards are the ones that you have to watch out for and this comes back to people protecting themselves over doing the right thing. Um they'll throw others under the bus. </s><s>[INST] Is there some sense that not enough people took responsibility [/INST] for sure, and I mean, I don't want to sugarcoat at all what joe ito did, I mean, I think it's gross that he took money from Jeffrey Epstein, I believe him that he didn't know about the bad, bad stuff, but I've been in those circles with those like public intellectual dudes that he was hanging out with and any woman in those circles, like 10 zillion red flags, just the whole environment was so misogynist like and so personally because Joey like was a great boss and a great friend, I was really disappointed that he ignored that in favor of raising money um and I think that it was right for him to resign in the face of that, but one of the things that he did that I know many others didn't was he came forward about it and he took responsibility and all of the people who didn't, I think it's just interesting. The other thing I learned about human nature, okay, I'm going to go on a tangent, I'll come back I promise. So I once saw this tweet from someone or was a twitter thread from someone who worked at a homeless shelter and he said that when he started working there, he noticed that people would often come in and use the bathroom and they would just trash the entire bathroom, like rip things out of the walls, like toilet paper on the ground and he asked someone who had been there longer, like why did they do this? Why do the homeless people come in and trashed the bathroom and he was told it's because it's the only thing in their lives that they have control over. And I feel like sometimes when it comes to the response, the just the mobbing response that happens in the wake of some harm that was caused if you can't target the person who actually caused the harm who was Epstein, you will go as many circles out as you can until you find the person that you have power over and you have control over and then you will trash that. And it makes sense that people do this. It's again, it's a human nature thing. Of course you're gonna focus all your energy because you feel helpless and enraged and you and it's unfair and you have no other power, you're going to focus all of your energy on someone who's so far removed from the problem that that's not even an efficient solution. And </s><s>[INST] the problem is often the first person you find is the one that has integrity, sufficient integrity, take responsibility. Yeah. [/INST] And it's why my husband always says he's he's a liberal, but he's always like when liberals form a firing squad, they stand in a circle because you know that your friends are going to listen to you, so you criticize them, you're not going to be able to convince someone across the aisle </s><s>[INST] in that situation. What I had hoped is the people in the farther in that situation, any situation of that sort the people that are farther out in the circles uh stand [/INST] up </s><s>[INST] and like also take some responsibility for the broader picture of human nature versus like specific situation but also take some responsibility and um but also defend the people involved as flawed. Not in like no, no, nothing like like this people fucked up like you said there's a lot of red flags that people just ignored for the sake of money in this particular case but also like be transparent and public about it and spread the responsibility across a large number of people such that you learn a lesson from it institutionally. [/INST] Yeah it was a systems problem, it wasn't a one individual problem </s><s>[INST] and I feel like currently because Joey took like resigned because of it or essentially fired pressured out because of it. Uh M I. T. Can pretend like oh we didn't we didn't know anything, it wasn't part [/INST] bad leadership again because when you are at the top of an institution with that much power and you were complicit in what happened, which they were like come on, there's no way that they didn't know that this was happening, so I like to not stand up and take responsibility. I think it's bad leadership. </s><s>[INST] Do you understand why Epstein was able to um outside of m. I. T. He was able to make a lot of friends? Was a lot of powerful people. Does that make sense to you? Why was he able to get in these rooms befriend these people befriend people that I don't know personally, but I think a lot of them indirectly I know as being good people, smart people, why would they let Jeffrey Epstein into into their office, have a discussion with them. What what do you understand about human nature from [/INST] that? So I never met Epstein or I mean I've met some of the people who interacted with him, but I was never, like I never saw him in action, I don't know how charismatic he was or what that was, but I do think that sometimes this simple answer is the more likely one, and from my understanding, what he would do is he was kind of a social grifter, like you know those people who will, you must get this because you're famous, you must get people coming to you and being like, oh I know your friends so and so in order to get cred with you, um I think he just convinced some people who were trusted in a network that he was a great guy and that you know, whatever, I think at that point because at that point he had had like a what a conviction prior, but it was a one off thing, it wasn't clear that there was this other thing that was that and </s><s>[INST] most people probably don't check. [/INST] Yeah, and most people don't check, like you're an event, you meet this guy, I don't know, maybe people do check when they're that powerful and wealthy or maybe they don't, I have no idea. No, they're just stupid, </s><s>[INST] I mean, and they're not like, [/INST] alright, </s><s>[INST] does anyone check anything about me because I've walked into some some of the richest and most powerful people in the world and nobody like ask questions like who the is this guy? Like, [/INST] like </s><s>[INST] nobody asked those questions. It's it's interesting. I I would think like there would be more security or something like there there really isn't. I think a lot of it has to do what my hope is in my case has to do with, like people can sense that this is a good person, but if that's the case then they can surely the human being can use charisma to infiltrate. [/INST] Yeah. </s><s>[INST] Just saying people [/INST] vouching for you within that type of network. Like once you yeah, once you have someone powerful vouching for you who someone else trusts then you know you're in </s><s>[INST] so how do you avoid something like that if you're m I t if you're Harvard, if you're any of these institutions? [/INST] Well, I mean, first of all you have to do your homework before you take money from someone. Um like I think I think that's required, but I think I think Joey did do his homework, I think he did, and I think at the time that he took money there was the one conviction and not like the later thing and I think that the story at that time was that he didn't know she was underage and nova and or whatever, it was a mistake and Joey always believed in redemption for people and that people can change and that they can genuinely regret and like learn and and move on and he was a big believer in that. So I could totally see him being like, well I'm not going to exclude him because of this thing and because other people are vouching for him. And just to be clear, we're now talking about the set of people who I think Joey belonged to, who did not like go to the island and have sex with underage girls because that's a whole other set of people who like were powerful and like we're part of that network and who knew and participated and and so like I distinguish between people who got taken in who didn't know that that was happening and people who knew, </s><s>[INST] I wonder what the different circles look like. So like people that went to the island and and didn't do anything, I didn't say anything, didn't know about anything versus the people that did something. And [/INST] then there's people who heard rumors, what </s><s>[INST] do you do with rumors? Like isn't there isn't there people that heard rumors about Bill Cosby for the longest time for like, for the longest, like whenever the that happened, like all these people came out of the woodwork, like everybody kinda knew. Um I mean it's like, all right, So what are you supposed to do with rumors? Like what I think the other way to put his red flags as you were saying. [/INST] Yeah. And like I can tell you that those circles like there were red flags without me even hearing any rumors about anything ever. Like I was already like this. There are not a lot of women here which is a bad sign. </s><s>[INST] Isn't there a lot of places where there's not a lot of women and that doesn't necessarily mean it's a bad sign. [/INST] There are if it's like a pipeline problem where it's like I don't know technology law clinic that only gets like male lawyers because there's there's not a lot of women you know applicants in the pool but </s><s>[INST] there's some aspect of this situation that like there should be more women here. [/INST] Oh yeah yeah </s><s>[INST] you've actually I'd love to ask you about this because you have strong opinions about richard Stallman [/INST] is </s><s>[INST] that do you still have those strong opinions? [/INST] Look all I need to say is that he met my friend who's a law professor, she shook his hand and he licked her arm from wrist to elbow and it certainly wasn't appropriate at that time. What </s><s>[INST] about if you're like an incredibly weird person? [/INST] Okay that's a good question because obviously there's a lot of neuro divergence at M. I. T. And everywhere and obviously like we we need to accept that people are different that people don't understand social conventions the same way. But one of the things that I've learned about neuro divergence is that women are often expected or taught to mask their neuro divergence and kind of fit in and men are accommodated and excused and I don't think that being neurodivergent gives you a license to be an asshole. Like you can be a weird person and you can still learn that it's not okay to lick someone's arm. </s><s>[INST] Yeah, there's it's a balance. Like women should be allowed to be a little weirder and men should be less weird because I think I think there's a because you're one of the people, I think tweeting that what made me, because I wanted to talk to richard Stallman on the podcast about because I didn't have a context because I wanted to talk to him because he's you know, free software. [/INST] He's very he's </s><s>[INST] very weird in interesting good ways in the world of computer science. He's also weird in that you know, when he gives a talk he would be like like picking at his feet and eating the skin off his feet, right, that he's known for these extremely kind of how else do you put it? I don't know how to put it, but then there was um something that happened to him in conversations on this threat related to Epstein, which I was torn about because I felt it's similar to joy uh you know, it's like I felt he was maligned like um people were looking for somebody to get angry at so he wasn't appropriate but the I didn't like the cowardice more like I I set aside his his situation and we could discuss it, but the cowardice and M. I. T. S. Part and this is me saying about the way they treated the whole situation. [/INST] They're always cowards about how they treat anything. They try to make the problem go away. </s><s>[INST] Yeah. So that it was it was about exactly. I [/INST] think he should have left the mailing list, shouldn't </s><s>[INST] have, he shouldn't have been part of the mailing. [/INST] Well that's probably true also. But I think I think what what bothered me what always bothers me in these mailing list situations or twitter situations. Like if you say something that's hurtful to people or makes people angry and then people start yelling at you, maybe they shouldn't be yelling. Maybe they are yelling because again you're the only point of power they have. Maybe maybe it's okay that you're yelling whatever it is. Like it's your response to that that matters. And I think that I just have a lot of respect for people who can say, oh people are angry, there's a reason they're angry. Let me find out what that reason is and learn more about it. It doesn't mean that I am wrong. It doesn't mean that I'm bad. It doesn't mean that I'm ill intentioned, but why are they angry? I want to understand. And then once you understand, you can respond again with integrity and say actually I stand by what I said here's why or you can say actually I listened and here are some things I learned, that's the kind of response I want to see from people and people like Stallman do not respond that way. They just like go into battle, </s><s>[INST] right? Like where it's obvious you you didn't listen. Yeah, honestly that's to me, as bad as the people who just apologize just because they are trying to make the problem go away [/INST] of course, </s><s>[INST] right? So like [/INST] if that's not </s><s>[INST] that bad, a [/INST] good apology has to include understanding what you did wrong </s><s>[INST] and in part standing up for the things you think you did right. So [/INST] if there are those things </s><s>[INST] finding and then, but you have to give you have to acknowledge, you have to like give that hard hit to the ego that says I did something wrong. Yeah, definitely. Richard Stallman is not somebody who is capable of that kind of thing or hasn't given evidence of that kind of thing. But that was also even just your tweet had to do a lot of thinking like different people from different walks of life, see red flags and different things and so things I find um as a, as a man, non threatening and hilarious are not necessarily um doesn't mean that there aren't like deeply hurtful to others and I don't mean that in a social justice warrior way, but in a, in a, in a real way, like people really have different experiences. So I feel like really put things into context um have to kind of listen to what people are saying. Put aside the emotion of what their emotion will do, what you're saying it and try to keep the facts of their experience and learn from it. [/INST] And because it's not just about the individual experience either, it's not like oh you know my friend didn't have a sense of humor about being licked, It's that she's been she's been metaphorically licked you know, 57 times that week because she's an attractive law professor and she doesn't get taken to. And so like men walk through the world and it's impossible for them to even understand what it's like to have a different experience of the world and that's why it's so important to listen to people and believe people and believe that they're angry for a reason. Maybe you don't like their tone, maybe you don't like that they're angry at you, Maybe you get defensive about that. Maybe you think that they should you know, explain it to you but believe that they're angry for a reason and try to understand it? Yeah. </s><s>[INST] There's a deep truth there uh an opportunity for you to become a better person. Can I ask you a question. Haven't [/INST] you been doing that for two hours, </s><s>[INST] three hours now? [/INST] Uh </s><s>[INST] Let me ask you about Gillian Maxwell, she's been saying that she's an innocent victim uh is she an innocent victim or is she uh evil and equally responsible. Like Jeffrey Epstein now I'm asking far away from any m I. T. Things and more just your sense of the whole situation, [/INST] I haven't been following it. So I don't know the facts of the situation and like what is now like known to be her role in that if I were her, clearly I'm not, but if I were her I wouldn't be going around saying I'm an innocent victim, I would say maybe she's doing I don't know what she's saying again, like, I don't know, </s><s>[INST] she was controlled by Jeffrey, [/INST] is she saying this is part of a legal case, or she's saying this is like a pr thing. </s><s>[INST] Well pr but it's not just her, it's her whole family believes this. There's uh there's a whole effort that says like that, how should I put it? I believe they believe it. So in that sense it's not pr I believe the family basically, the family is saying that she's a good she's a really good human being. [/INST] Well I think everyone is a good human being, I know it's a controversial opinion, but I think everyone is a good human being, there's no evil people, there's people who do bad things and who behave in ways that harm others and I think we should always hold people accountable for that. But holding someone accountable doesn't mean saying that they're evil. </s><s>[INST] Yeah actually those people usually think they're doing good. [/INST] Yeah, I mean aside from I don't know, maybe sociopaths like are specifically trying to like harm people, but I think most people are trying to do their best and if they're not doing their best is because there's some impediment or something in their past. So I just I genuinely don't believe in good and evil people, but I do believe in like harmful and not harmful actions and so I don't know like I don't care, I don't care. Yeah, she's a good person. But if she contributed to harm then she needs to be accountable for that. Like that's my position. I don't know what the facts of the matter are. It seems like she was pretty close to the situation, so doesn't seem very believable that she was a victim, but I don't know </s><s>[INST] because something tells me he would just be a regular person, charismatic person, like anybody else. And that's a very dark reality that we don't know which among us what what each of us are hiding in the closet. That's a really tough thing to like deal with because then you can put your trust into some people and they can completely betray that trust and in the process destroy [/INST] you. </s><s>[INST] Which there's a lot of people that interacted with Epstein, they now have to I mean if they're not destroyed by it then they're they their whole like the ground on which they stand ethically is has crumbled at least in part and you I'm sure I'm sure you and I have interacted with people without knowing it who are bad people [/INST] as I always tell my four year old people who have done bad things. </s><s>[INST] People have done bad [/INST] things. He's always talking about bad guys and I'm trying to move them towards. They're just people who make bad choices. </s><s>[INST] Yeah. That's really powerful actually. That's really important to remember because that that means you have compassion towards all human beings. Um Do you have hope for the future of M. I. T. A. Future of media lab in this context? So David Newman is now at the helm. I'm gonna talk, I talked to a previous, I'll talk to her again. She's great. I [/INST] love her. Yeah she's great. I don't know if she knew the whole situation when she started because the situation went beyond just the Epstein scandal. A bunch of other stuff happened at the same time, some of it's not public. Um But my what I was personally going through at that time. So the Epstein thing happened I think was it August or September 2019. It was somewhere around late summer In June 2019. So I'm I'm a research scientist at M. I. U. R. Two. Right? So and I always have had various supervisors you know over the years and they've just basically let me do what I want. Which has been great. But I had a supervisor at the time and he called me into his office for a regular check in </s><s>[INST] in june [/INST] of 2019. I reported to M. IT that my supervisor had grabbed me, pulled me into a hug, wrapped his arms around my waist and started massaging my hip and trying to kiss me, kiss my face, kiss me near the mouth. Um And said literally the words don't worry, I'll take care of your career. Um And that that experience was really interesting because I just I was very indignant. I was like he can't do that to me, doesn't he know who I am? And I was like this is the me Too era. And I naively thought that when I reported that it would get taken care of. And then I had to go through the hole reporting process at M. I. T. And I learned a lot about how institutions really handle those things internally. Um particularly situations where I couldn't provide evidence that it happened. I had no reason to lie about it but I had no evidence. And so I was going through that and that was another experience for me where there's so many people in the institution who really believe in protecting the institution at all costs. And there's only a few people who care about doing the right thing and one of them resigned. Now there's even less of them left. So </s><s>[INST] so what did you learn from [/INST] that? I mean </s><s>[INST] where where is the source if you have hope for this institution that I think you love, at least in part I love the idea of m I d I [/INST] love the idea. I love the research body, I love a lot of the faculty and </s><s>[INST] students, students, I [/INST] love the energy. Like I love it all. I think the administration suffers from the same problems as any institutional any leadership of an institution that is large, which is that they've become risk averse. Like you mentioned, they care about pr the only ways to get their attention or change their minds about anything or to threaten the reputation of the institute or to have a lot of money. That's the only way to have power at the institute. Um Yeah, I don't think they I don't think they have a lot of integrity or believe in ideas or even have a lot of connection to the research body and like the people who are really because it's so weird, you have this amazing research body of people pushing the boundaries of things who aren't afraid to, like there's the hacker culture and then you have the administration and they're really like protect the institution at all costs. </s><s>[INST] Yeah, there's a disconnect [/INST] right, completely. </s><s>[INST] I wonder if there was always there if it just kind of slowly grows over time. A disconnect between the administration and faculty. [/INST] I think it grew over time is what I've heard. I mean, I've been there for 11 years now. I don't know if it's gotten worse during my time, but I've heard from people who've been there longer that it didn't like my d didn't used to have a general counsel's office, they didn't used to have all this corporate stuff and then they had to create it as they got bigger. And in the era where such things are I guess deemed necessary. </s><s>[INST] See, I believe in the power of individuals to like overthrow the thing. So I just had a really good president of M. I. T. Or certain people in administration can reform the whole thing because the the culture is still there of like, I think everybody remembers that M. I. T. Is about the students and the faculty. [/INST] Because I don't know, I've had a lot of conversations that have been shocking with like senior administration. They think the students are Children, they call them kids. It's like these are the smartest people, they're way smarter than you and you're so dismissing </s><s>[INST] those individuals. I'm saying like the capacity like the aura of the place still values the students and the faculty. Like I'm not I'm being awfully poetic about it. But what I mean is the administration is the the froth at the top of the like the waves the surface, like they can be removed and new life can be brought in that would keep to the spirit of the place up. Oh, I see, I see, but I do think ultimately, especially in the era of social media and so on. Um faculty and students have more and more power. Just more and more of a voice I suppose. [/INST] I hope so. I really do. I don't see M. I. T. Going away anytime soon and like I also don't think it's a terrible place at all. </s><s>[INST] It's an amazing place and it's a but there's different trajectories you can take. Yeah and like and that has to do with a lot of things including um does it is it stays even if we talk about robotics it could be the capital of the world in robotics. Um but currently if you want to be doing the best A. I work in the world you're gonna go to google or facebook um or Tesla or Apple or so on. You're not gonna be, you're not gonna be an M. I. T. So that that has to do, I think that's basically has to do with um not allowing the brilliance of the researchers to flourish. [/INST] Yeah. People say it's about money but I don't think it's about that at all. Like sometimes you have more freedom and can work on more interesting things and companies that's really where they lose people. </s><s>[INST] Yeah and some the freedom in all in in all ways which is why it's heartbreaking to get like people like Richard Stallman, there's such an interesting line because like Richard Stallman gigantic weirdo. That cross lines you shouldn't cross right? But we don't want to draw too many lines. This is the tricky thing. [/INST] There are different types of lines in my opinion. </s><s>[INST] But yes, your opinion, you have strong lines, you hold two. But then if administration listens to every line, there's there's also power in drawing a line like and there's, it becomes like a little drug you have to find the right balance licking somebody's arm is never appropriate. I think the biggest aspect there is not owning it learning from it growing from it from the perspective installment or people like that uh back when it happened like understanding seeing the being empathetic, seeing the fact that this was like totally inappropriate. Like not one that particular act but everything that led up to it to [/INST] no, I think there are different kinds of lines. I think they're like so Stallman crossed lines that essentially excluded a bunch of people and created an environment where we, their brilliant minds that we never got the benefit of because he made things feel growth or even unsafe for people. There are lines that you can cross where you're challenging an institution to like, I don't think he was intentionally trying to cross a line or maybe he maybe didn't care there are lines that you can cross intentionally to move something forward or to do the right thing. Like when it was like you can't put an all gender restroom in the media lab because like something permits whatever and Joey did it anyway, that's the line you can cross to make things actually better for people. And the line you're crossing is some arbitrary stupid rule that people who don't want to take the risk or like </s><s>[INST] yeah, for [/INST] sure. Ultimately, </s><s>[INST] I think the thing you said is like cross lines in a way that doesn't uh alienate others. So like for example, me wearing, I started for a while wearing a suit often at M. I. T. Which sounds counterintuitive, but that's actually um people always looked at me weird for that M. I. T. Created this culture, specifically the people I was working with, Like nobody wore suits. Don't [/INST] trust, </s><s>[INST] don't trust the suits. I was like, fuck you, I'm wearing a [/INST] suit that's </s><s>[INST] not really hurting anybody. [/INST] Right? Exactly. </s><s>[INST] It's [/INST] challenging people's perceptions. It's doing something that you want to do. </s><s>[INST] Yeah. But it's [/INST] not hurting people. </s><s>[INST] And and that that particular thing was um, yeah, it was hurting people. It's a good line. It's a good line like hurting ultimately the people that you want to flourish. Yeah. You tweeted a picture of pumpkin spice greek yogurt and asked grounds for divorce. Yes. No. So let me ask you what's what's the key to a successful relationship? [/INST] Oh my God, A good couple of therapists. </s><s>[INST] What what went wrong with the pumpkin spice greek Yogurt? What's exactly wrong. Is that the pumpkin, is it the greek? I don't understand. I stared at that tweet for a while. I [/INST] grew up in europe, so I don't understand the pumpkin spice in everything craze that they do every autumn here. Like I understand that it might be good in some foods, but they just put it in everything </s><s>[INST] and it doesn't belong in greek greek yogurt, [/INST] I mean I was just being humorous, I ate one of those yogurts and actually tasted pretty good. So </s><s>[INST] I think part [/INST] of the success of a good marriage is like giving each other a hard time humorously for things like that. </s><s>[INST] Is there a broader lesson because you guys seem to have a really great marriage from the external, I [/INST] mean every marriage looks good from the external, every I think Yeah, </s><s>[INST] that's that's not true. Yeah, [/INST] okay, No, but like, relationships are hard, relationships with anyone are hard and especially because people evolve and change and you have to make sure there's space for both people to evolve and change together. And I think one of the things that I really liked about our marriage vows was remember before we got married Greg at some point, like got kind of nervous and he was like, it's just it's such a big commitment to commit, like to something for life, and I was like, we're not committing to this for life, and he was like we're not and I'm like no, like we're committing to being part of a team and doing what's best for the team if what's best for the team is to break up, we'll break up like I don't believe in this. Like we have to do this for our whole lives and that really resonated with him too. So yeah. </s><s>[INST] Yeah. [/INST] That was our vows like that. We're just, we're going to be a team, </s><s>[INST] You're a team and do what's right for the [/INST] team. Yeah. </s><s>[INST] That's very like Michael Jordan's view. Uh did you guys get like married in in the desert? Like november rain style with slash playing or you don't have to answer that? I'm not good at these questions. Okay. You brought [/INST] Up marriage like eight times. Are you trying to hint something on the podcast? I </s><s>[INST] don't you have an announcement to make. No, I don't know. It just seems like a good metaphor for why why? Why would it felt like a good metaphor for in a bunch of cases for the marriage industrial complex. Remember that. And oh, people complaining. It just seemed like marriage is one of the things that always surprises me because I want to get married. [/INST] Yeah, </s><s>[INST] I do. And then I listen to like friends of mine that complain. Not all I like, I like guys, I really like guys that don't complain about their marriage. It's such a cheap, like if it's such a cheap release valve, like that doesn't, that's bitching about anything. Honestly. That's just like, it's too easy, but especially like a bit about the sports team or the weather if you want, but like about somebody that you're dedicating your life to like if you bit about them, you're going to see them as a lesser being. Also like you don't think so, but you're going to like decrease the value. You have. I personally believe over time, you're not going to appreciate the magic of that person I think anyway. But it's like that I just noticed this a lot that people are married and they will whine about, you know like the wife, whatever this, this is part of the sort of the culture to kind of comment in that way. I think women do the same thing about the husband. He doesn't, he never does this or he's a goof, he's incompetent at this or that whatever they, there's a kind of, [/INST] there's this tropes like, oh husbands never do X. And like wives, I think this do a disservice to everyone is just disrespectful to everyone involved, </s><s>[INST] but it happens. So yeah, I was brought that up as an example of something that people actually love, but they complain about because for some reason that's more fun to do is complain about [/INST] stuff. </s><s>[INST] And so that's what with clipping or whatever, right? So like you complain about, but you actually love it. It's just a good metaphor that, you know, um I wasn't gonna ask you uh oh you, your hamster died when [/INST] I was like eight beige. Um </s><s>[INST] What's the closest relationship you've had with the pet that the one [/INST] what </s><s>[INST] robot have you loved the most in your life. I think [/INST] my first pet was a goldfish named bob and he died immediately and that was really sad and I think I think it was really attached to bob and nancy. My goldfish. We got new bobs and then bob kept dying and we got new bob's nancy just kept living. </s><s>[INST] So it was very replaceable. [/INST] Yeah. I was young. It was easy to </s><s>[INST] do. You think there will be a time when the robot like in the movie Herbie something we fall in love with romantically. [/INST] Oh yeah for sure </s><s>[INST] scale. Like were a lot of people [/INST] romantically. I don't know if it's gonna happen at scale. I think I think we talked about this a little bit last time on the podcast to where I think we're just capable of so many different kinds of relationships. And actually part of why I think marriage is so tough as a relationship is because we put so many expectations on it. Like your partner has to be your best friend and you have to be sexually attracted to them and they have to be a good co parent and a good roommate. And like it's all the relationships at once that have to work but we're like normally with other people we have like one type of relationship or we even have, we have a different relationship to our dog than we do to our neighbor than we do to the, you know, personnel someone a coworker. I think that some people are gonna find romantic relationships with robots interesting. It might even be a widespread thing, but I don't think it's gonna replace like human romantic relationships. I think it's just gonna be a separate type of thing. </s><s>[INST] It's gonna be more narrow, [/INST] more narrow or even like just something new that we haven't really experienced before. Maybe like having a crush on artificial agent is a different type of fascination. I don't know. I think people would, Well, I mean the things that people feel threatened by in relationships are very many fold. So </s><s>[INST] yeah, that's just an interesting one because uh, maybe maybe they'll be good, a little jealousy for the relationship. Maybe that's [/INST] part of the </s><s>[INST] couple's therapy, you know, kind of thing or whatever. [/INST] I don't think jealousy. I mean, I think it's hard to avoid jealousy, but I think the objective is probably to avoid. I mean, some people don't even get jealous when their partner sleeps with someone else. Like there's polyamory and um, I think there's just such a diversity of different ways that we can structure relationships or view them that this is just going to be another one that we add </s><s>[INST] you dedicate your book to your dad. What did you learn about life from your dad [/INST] man? My dad is, he's a great listener and he is the best person I know at um the type of cognitive empathy that's like perspective taking. So not like emotional, like crying empathy, but trying to see someone else's point of view and trying to put yourself in their shoes. And he really instilled that in me from an early age and then he made me read a ton of science fiction, which probably led me down this path. </s><s>[INST] Tell you how to be curious about the world and how to be open minded. [/INST] Yeah. </s><s>[INST] Last question, what role does love play in the human condition? Since we've been talking about love and robots? Uh and you're fascinated by social robotics. It feels like all of that operates in the landscape of something that we can call love. [/INST] Love. Yeah, I think there are a lot of different kinds of love. I feel like it's we need like the Eskimos have all these different words for snow, We need, we need more words to describe different types and kinds of love that we experience. But I think love is so important. And I also think it's not zero sum. That's the that's the really interesting thing about love is that, you know, I had one kid and I loved loved my first kid more than anything else in the world. And I was like, how can I have a second kid and then love that kid. Also, I'm never going to love it as much as the first, but I love them both equally. It's just like my heart expanded and so I think that people who are threatened by love towards artificial agents, they don't need to be threatened for that reason, </s><s>[INST] artificial agents will just if done right will just expand your capacity for love. I [/INST] think so, </s><s>[INST] I agree beautifully. Put, Okay, this is awesome. I still didn't talk about half the things I want to talk about, but we're already like way over three hours. So thank you so much. I really appreciate you talking today. You're awesome. You're an amazing human being, a great roboticist, great writer. Now it's an honor that you would talk with me. Thanks for doing it [/INST] right back at you. Thank you. </s><s>[INST] Thanks for listening to this conversation with kate darling. To support this podcast. Please check out our sponsors in the description and now let me leave you with some words from Maya Angelou. Courage is the most important of all the virtues because without courage, you can't practice any other virtue consistently. Thank you for listening and hope to see you next time [/INST] </s> |
<s>[INST] important do you think is exploration are totally out of the box thinking, exploration in this space is jump two totally different domains. So you kind of mentioned, there's an optimization problem, you kind of kind of explore the specifics of a particular strategy, whatever the thing you're trying to solve, how important is it to explore totally outside of the strategies have been working for you so far. What's your intuition there? [/INST] Yeah, I think it's a very problem dependent kind of question and I think that that's actually, you know in some ways that question gets at um one of the big differences between uh sort of the classic formulation of a reinforcement learning problem and uh some of the sort of more open ended reformulation of that problem that has been explored in recent years. So classically reinforcement learning is framed as a problem of maximizing utility, like any kind of rational ai agent and then anything you do is in service to maximizing the utility. But a very interesting kind of way to look at. Um I'm not necessarily saying this is the best way to look at about an interesting alternative way to look at these problems is um as something where you first get to explore the world however you please and then afterwards you will be tasked with doing something and that might suggest a somewhat different solutions. So if you don't know what you're going to be tasked with doing and you just want to prepare yourself optimally for whatever you're uncertain future holds maybe then you will choose to attain some sort of coverage build up sort of an arsenal of cognitive tools if you will such that later on when someone tells you now your job is to fetch the coffee for me, you'll be well prepared to undertake that task </s><s>[INST] and that you see that as the modern formulation of the reinforcement learning problem as a kind of the more multi task, the general intelligence kind of formulation. [/INST] I think that's one possible vision of where things might be headed. I don't think that's by any means the mainstream or standard way of doing things and it's not like if I had to </s><s>[INST] but I like it. It's a it's a beautiful vision. So maybe you actually take a step back what is the goal of robotics? What's the general problem in robotics we're trying to solve? You actually kind of painted two pictures here. One of the narrow one of the general what in your view is the big problem with robotics? Again, ridiculously philosophic Ohio for questions. [/INST] I think that um, you know, maybe there are two ways I can answer this question. One is there's a very pragmatic problem which is like what would make robots well, sort of maximize the usefulness of robots. And they're, the answer might be something like a system where uh, a system that can perform whatever task a human user sets for it, you know, within the physical constraints. Of course, if you tell it to teleport to another planet but probably can't do that. But if you ask it to do something that's within its physical capability, then potentially with a little bit of additional training or a little bit of additional trial and error, it ought to be able to figure it out in much the same way as like a human telly operator ought to figure out how to how to drive the robot to do that. That's kind of a very pragmatic view of what it would take to kind of solve the robotics problem if you will. But I think that there is a second answer and that answer that, that the answer is a lot closer to why I want to work on robotics, which is that I think it's it's it's less about what it would take to do a really good job in the world of robotics but more the other way around what robotics can bring to the table to help us understand artificial intelligence. </s><s>[INST] So your dream fundamentalist to understand intelligence? [/INST] Yes. I think that's the dream for many people who actually work in this space. I think that there's there's something very pragmatic and very useful about studying robotics. But I do think that a lot of people that go into this field actually, you know, the things that they draw inspiration from are the potential for robots to help us learn about intelligence and about ourselves. So </s><s>[INST] that's fascinating that robotics is basically the space by which you can get closer to understanding the fundamentals of artificial intelligence. So what is it about robotics that's different from some of the other approaches? So if you look at some of the early breakthroughs in deep learning when the computer vision space and the natural language processing there was really nice clean benchmarks that a lot of people competed on and their body came off a lot of brilliant ideas. What's the fundamental difference between computer vision purely defined an Image net and kind of the bigger robotics problem. [/INST] So there are a couple of things. One is that with robotics um you kind of have um you kinda have to take away many of the crutches. So you have to deal with with both the the particular problems of perception control and so on. But you also have to deal with the integration of those things and you know classically we've always thought of the integration as kind of a separate problem. So a classic kind of modular engineering approaches that we solve the individual sub problems then wire them together and then the whole thing works. Um And one of the things that we've been seeing over the last couple of decades is that well maybe studying the thing as a whole might lead to just like very different solutions that we if we were to study the parts and wire them together. So the integrated nature of robotics research helps us see you know the different perspectives on the problem. Another part of the answer is that with robotics um It casts a certain paradox into very clever relief so that this is sometimes referred to as a more of a paradox. The idea that in artificial intelligence things that are very hard for people can be very easy for machines and vice versa. Things that are very easy for people can be very hard for machines. So you know uh integral and differential calculus is pretty difficult to learn for people but if you program a computer do it it can derive derivative and integral for you all day long without any trouble. Whereas some things like you know drinking from a cup of water very easy for a person to do very hard for a robot to deal with. And sometimes when we see such blatant discrepancies that give us a really strong hint that we're missing something important. So if we really try to zero in on those discrepancies we might find that little bit that were missing and it's not that we need to make machines better or worse at math and better at drinking water, but just that by studying those discrepancies we might find some new insight </s> |
<s>[INST] it's [/INST] little </s><s>[INST] but relative to an elephant. Everybody's penises. [/INST] Yeah, but I'm not an elephant. I'm human, you know what I mean? So relatively human. It's very small. And so when she saw it, you know, I mean, I thought she was gonna balk at it, right? And she looked at it as if it was like an orphan, </s><s>[INST] like, you [/INST] know, like I wanna, it's a lost child and I wanna, you know, you know, take care of it. </s><s>[INST] Yeah, cradle it, [/INST] cradle yeah. What you man, you you you haven't met anybody like that. </s><s>[INST] Uh never met a girl. Never seen one of them. I hear they're nice. When are when are the two of you getting married? [/INST] We don't know yet. Is </s><s>[INST] that something you like? [/INST] Yeah, this </s><s>[INST] comes up sometimes, [/INST] you know, we're in couples counseling, we're dealing, we're working on some issues that we have every relationship, Even my friendships have issues. And so we're working through some issues and once we get to the end of it, we'll figure it out. </s><s>[INST] Would you like to be a father one day? This is kind of couples [/INST] counseling, you know? Yeah, I do. I do because I feel like, um, you know, before I was very childlike, you know, I play a lot of video games. I'm irresponsible, I'm lazy this and that, right? But you know, to be honest with you lex in the last six months, I really have come through some breakthroughs and um, I'm in therapy and I'm doing a lot of things and really self analyzing myself and my behaviors and what I want, my desires. And I think ultimately, yes, I really do because it's a life experience that, um, you know, I don't want to be an old man looking back and going, it's something that I've always was interested in and I think it's based on fear because I don't want to um, scar my child the way my parents scarred me. But at the same time, my parents didn't do the work on themselves. Like I am and they were never about self improvement. They were just about, they were immigrants, you know, and they wanted to put food on the table and um, after that they just went about their business and I'm not like that. I would never be violent towards my kids. Like my parents were, my dad was very physically abusive. You know, there was a lot of trauma and stuff. And so, um, you know, as a kid, I thought, you know, I just would never put my kid through this. So that's why I never wanted it. But I would completely do it differently, you know? Um, even yelling and, and those kind of things, I would be very mindful about those things and I think that I have certain things, you know, I'm not a science guy like you, but there are life things that I've learned over the years that I could teach a child, you know about living in the moment or walking through fear or you know, things that, you know, things will pass and just different things, you know, that I could, I would be a good listener and um, yeah, I would like to do that. </s><s>[INST] So your, your dad died in um August of 2019. [/INST] Yeah. You did your research. </s><s>[INST] Yeah, it's on your Wikipedia. [/INST] So </s><s>[INST] you said some of it was rough. But what's your fondest memory of your dad? [/INST] What did those memories happened later in life? Um, as a child, my fondest memory was my mom because he never spent time with us. So, um, my mom made him Take me out one day and he took me to a park, like he doesn't, there's no baseball glove or baseball or anything like that. And we sat on a park bench, right. And we just sat there for hours. We didn't talk because he didn't know english that well, I don't know korean. So it's just very, you know, basic, you know, information being, you know, I mean how you, how you doing? I'm okay, you know, good, good, good, that type of thing </s><s>[INST] for a long time, [/INST] for a long time. And then, but the day turned bad because I forgot my jacket there and he yelled at me. There's </s><s>[INST] a bit of peace together [/INST] at that time. Yeah, there was peace. But then what happened was later in life when I got mad tv and I was doing, you know, in my early years, you know, I booked a couple of things like in 2000, I did the Tonight Show on Leno and then I did um I got mad tv in 2000 And um how? That was over 20 years ago. And um that's when they, my parents kind of went, huh? You know, because obviously, you know, there's some nepotism in Hollywood, right? But in my case my parents were straight up immigrants, I had no connections to Hollywood and I came up here poor, you know, with no connections and I built it, you know what I mean, through the years, you know? And in in that way I'm very proud of myself because I went through a lot of fun hell and sadness and desperation and all that stuff and I persevered and I did all that sh it on my own man. I I booked the Tonight show on my own. I got mad tv on my own. And when I did those things, my parents were very proud, </s><s>[INST] but before that did they doubt you? [/INST] You're not, you're not funny, you you never make me laugh, right? And that kind of stuff, You're never gonna make it, you're gonna be poor all your life, you know, that kind of stuff. </s><s>[INST] But mad tv. He was proud. Well, [/INST] you know, every because it was a weekly show, so on saturday nights they would watch it and yeah, and and I would, I would play characters that they would understand like I did kim jong il at the time, right? So they loved that, right? They loved, you know, the things that I would do the physical comedy and they couldn't believe in their mind, you know, imagine your parents from Korea coming here, you know, not knowing the language, having a child here, right? And in their minds that was never like an option, right? And so when they see their kid, I guess on tv especially there was no internet to, at the time, the internet had just started. So to them they were like, this is a musical. In fact when I did the Tonight Show, my dad called me the next day and asked me, he literally asked me this, he goes, how much did you pay them to do it? He thought that I had saved all my money like that. Like he thought that like tom Cruise goes up there and go, here's a grand. Thanks for having me on like, you know, I go, no, they asked me like all the conceptually they were just shocked by it. So when I got it and then they were watching me weekly Mad tv the producers like hey have your dad on. So my dad did two or 3 sketches on television. So and that so those memories, I also did a pilot for Comedy Central and he was on my pilot </s> |
<s>[INST] nevertheless, you are riding a wave and you make a decision of the in the writing of the way you can't control the wave, but you should be uh like as you ride as you should be making certain kinds of decisions and take responsibility for it. So why does this matter at all the chain of decisions you make [/INST] good? Well, because they constitute you they make you the person that you are. So here's what's the opposite view. What's what's this view against? Uh this view is against most of philosophy from plato forward. Plato Plato says in the Republic, it's a kind of myth. But you know, he says, people will understand their their condition. Well, if if they if we tell them this myth, he says, look, when you're born, there is just a fact about you, your soul is either gold, silver or bronze. That's those are the three kinds of people there are and you're born that way. And if your soul is gold then we should identify that and make you a philosopher king. And if your soul is silver, well you're not going to be a philosopher king, you're not capable of it. But you could be a good warrior and we should make you that. And if your soul is bronze then you should be a farmer labor or something like that. And that's a fact about you that identifies you forever and for always independent of anything you do about it. And so that's the alternative for you. And you could have modern versions of it. You could say the thing that identifies you as your I. Q. Or your genetic makeup or the percentage of fast twitch muscle fibers you've got or whatever. It could be something it's totally independent of any choice that you've made independent of the kind of thing about which you could make a choice. And it and it categorizes you, it makes you the person that you are. That's the that's the thing that started and the existentialists are against. </s><s>[INST] Uh so this idea that something about you is forever limiting the space of possible decisions. You can make Sartre says no space is unlimited. [/INST] Start is the philosopher of radical freedom. </s><s>[INST] Radical freedom. [/INST] Radical freedom. And then you could have other existentialists who say look we we are free, but we gotta we gotta understand what the way in which our freedom is limited by certain aspects of the kind of being that we are. If we were radically free, we really would be like God in the traditional medieval sense, and not sort of these folks start with the idea that what whatever we are, that's a kind of limit point that we're not going to reach. So what what are the ways in which we're constrained that that that being the way the medieval is understood him wasn't constrained? </s><s>[INST] So can you maybe comment on what is Nihilism and is it at all a useful other sort of group of ideas that you resist against in defining existentialism? Yes. [/INST] Good. Excellent. So, Nihilism, The philosopher who made the term popular, although it was used before him as Nietzsche teaches writing at the end of the 19th century in various places where he published things, but largely in his unpublished works, he identifies the condition of the modern world as nihilistic and that's a descriptive claim. He's looking around him, trying to figure out what it's like to be us now. And he says it's a lot different from what it was like to be human in 1300 or in the fifth century B. C. E. And 1300 Like what people believed what they the way they lived their lives was in the understanding that to be human was to be created in the image and likeness of God, that's the way they understood themselves, and also to be created sinful because of you know, Adam and Eve's transgression in the garden of Eden and to have the project of trying to understand how as a sinful being, you could nevertheless live a life a virtuous life. How could you do that? And it had to do with for them getting in the right relation to God. It just says we we we that doesn't make sense to us anymore. In the end of the 19th century, God is dead, says Nietzsche famously, and what does that mean? Well, it means something like the role that God used to play in our understanding of ourselves as a culture, isn't a role that that God can play anymore. And so, Nietzsche says the role that God used to play was the role of grounding our existence. He was what it is, in virtue of which we are, who we are. And Nietzsche says the idea that there is a being that makes us what we are doesn't make sense anymore. That's like Sartre's Atheism starts taking that from each other. And so the question is what does ground our existence? And the answer is no hill nothing. And so Nihilism is the idea that there's nothing outside of us that grounds our existence. And then need to ask the question, well, what are we supposed to do about that? How do we live? And I, you know, I think Nietzsche has a different story than sorry about that. Nietzsche doesn't say doesn't emphasize this notion of radical freedom. Nietzsche emphasizes something else. He says, where artists of life and artists are interesting because the natural way of thinking about artists is that they're responding to something they find themselves in a situation and they say this is what's going to make sense of the situation is what I have to write. This is the way I have to dance, This is the way I've got to play the music. And Nietzsche says, we should live like that. There are constraints. But like understanding what they are is complicated aspect of of of living itself. And there's a great story, I think uh from music that maybe helps to understand this. I think Nietzsche, of course jazz didn't exist when Nietzsche was writing, but I think need to really think is thinking of something like jazz improvisation. I mean, he he talks about improvisation, there's classical improvisation. Nietzsche was, by the way, a musician. I mean, he was a composer and pianist, not a great one really, to be fair, but he loved music. And Herbie Hancock who is a pianist, a jazz pianist Who played with miles Davis for quite a while in the 60s tells this kind of incredible story that I think exemplifies Nietzsche's view about the way in which we bear some responsibility for being creative and that gives us a certain kind of freedom. But we don't have the radical response, the radical freedom that start things. So what's the story? Herbie Hancock says there, there, there, I think they were in Stuttgart. He says, playing at playing a show and things were great. He says, I'm he's a young pianist, and Miles Davis is the master and he says, I'm I'm playing the I'm back in the solo and I'm playing these chords and he says, I played this chord and it was the wrong chord. He's like, it just like that's what you gotta say. It didn't work right there. And I thought, Holy Mackerel, I screwed up. You know, I screwed up. We were tight, everything was working. And I blew it for Miles who's doing his solo. And he said, Miles paused for a moment and then all of a sudden he went on in a way that made my cord right. And I think that idea that like, you could be an artist who responds to its thrown at you in such a way as to make it right by what measure everyone could hear it is all you can say, right? Everyone knew, wow, that really works. And I think that's not like there are constraints, not anything would have worked there. He couldn't have just played anything. Most of what anyone would have played would have sounded terrible, but the constraints aren't like pre existing, they're sort of what's happening now in the moment for these listeners and these performers. And I think that's what Nietzsche thinks the right response to Nihilism is were involved. But we're not radically free to make any choice and just stand behind it. The way start thinks our choices have to be responsive to our situation and they have to make the situation work. They have to make it right? </s> |
<s>[INST] And those experiences you particularly mean there's a subjective nous to them. The thing when people refer to the hard problem of consciousness is it feels like something to look at the color red. Exactly, [/INST] right. It feels like something to have a headache or or to feel upset to your stomach. It feels like something. And so though, so I'm going to grant that in this theory, there are experiences and their fundamental in some sense. So conscious experience. So they're not derived from physics. They're not functional properties of particles. They are so generous there they exist just like we assume space time exists. I'm now saying spacetime is just a data structure doesn't exist. Independent conscious experiences. </s><s>[INST] Sorry to interrupt once again. But should we be focusing in your thinking on humans alone? [/INST] Mm </s><s>[INST] Or is there something about in relation to other kinds of organisms that have a sufficiently high level of complexity? Or even uh or is there some kind of uh generalization of the pan psychics idea that all consciousness permeates all matter. Outside of the usual definition of what matter is inside space time. [/INST] So it's beyond human consciousness. Human consciousness, from my point of view would be one of a countless variety of consciousnesses. And even within human consciousness, there's there's countless friday of consciousness within us, right? I mean, you have your left and right hemisphere. And apparently if you split the corpus callosum, the personality of the left hemisphere and the religious beliefs of the left hemisphere can be very different from the right hemisphere. And they're conscious experiences can be dis joint, one could have one conscious experience. They can play 20 questions. Left hemisphere can have an idea in his mind and the right time is for us to guess and it might not get it. So, so even within you there, it's it's more than just one consciousness. It's lots of consciousnesses. So, I the general theory of consciousness that I'm after is not just human consciousness, it's going to be just consciousness. And I presume human consciousness is a tiny drop in the bucket of the infinite variety of consciousnesses. </s><s>[INST] That said, I should clarify that the black hole of consciousness is uh the home cat, I'm pretty sure cats black uh is the embodiment of even and lack all capacity for consciousness or compassion. So I just want to lay that onto. But that's a theory. I'm working. I don't have any good evidence into it. That's just a shout out. Uh sorry to distract. So that's the first assumption [/INST] assumption that the second assumption is that these experiences have consequences. So I'm going to say that conscious experiences can trigger other conscious experiences somehow. So, so really, in some sense, there's two Basic assumptions because </s><s>[INST] there's some kind of causality, is there is a chain of causality. Does this relate to dynamics? [/INST] I'll say there's a probabilistic relationship. Um and and then so I'm trying to be as non specific to begin with and see where it leads me. So what I can write down our probability spaces, So probability space which contains the conscious experiences that this consciousness can have. So I'll I call this a conscious agent, this technical thing. You know, I Annika Harris and I've talked about this and she rightly cautions me that people will think that I'm bringing in a notion of a self or agency and so forth when I say conscious agents. So I just want to say that I use the term conscious agent merely as a technical term. There is no notion of self in my fundamental definition of a conversation, there are only experiences and probabilistic relationships that of how they trigger other experiences. So </s><s>[INST] the agent is the generator of the conscious experience. [/INST] The agent is a mathematical structure that includes a probability measure, the probability space of a possible conscious experiences and what marco v in Colonel, which describes how if this agent has certain conscious experiences, how that will affect the experiences of other conscious agents. Okay, including itself, </s><s>[INST] but you don't think of that as a self. [/INST] No, there is no notion of a self here. There's no notion of really of an agent, </s><s>[INST] but is there a locality. Is there an organism? There's no. So [/INST] this is this is um these are conscious units, conscious entities </s><s>[INST] but they are distinct in some way because they have to interact [/INST] well. So here's the interesting thing when we write down the mathematics, um when you have two of these conscious agents interacting, they the pair satisfy a definition of a conscious agent, so they are a single conscious agent. So there is one conscious agent, but it it has a nice analytic decomposition into as many conscious agents </s><s>[INST] interface. [/INST] It's a very useful scientific interface. It's a scale free or if you like a fractal like approach to it, in which we can use the same unit of analysis at all scales in studying consciousness. But if I want to talk about. So there's no notion of learning memory problem solving intelligence, self agency. So none of that is fundamental. So and the reason I did that was because I want to assume as little as possible. Everything I assume is a miracle in the theory. It's not something you explain. It's something you assume. So, I have to build networks of conscious agents. If I want to have a notion of itself, I have to build itself, I have to build learning memory problem solving intelligence and planning all these different things. I have to build networks of conscious agents to do that. It's a trivial theorem that networks of conscious agents are computational universal is trivial. So, anything that we can do with neural networks or you know, automata you can do with networks of conscious agents. That's trivial. What? But you can also do more. The events in the probability space need not be computable. So the mark avian dynamics is not restricted to computable functions because the very events themselves need not be computable. So, so this can capture any computable theory. Anything we can do with neural networks, we can do with conscious agent networks, but but it leaves open the door for the possibility of of non computable um interactions between conscious agents. So we have to to if we want a theory of memory, we have to build it. And there's lots of different ways you can build. We've actually got a paper, chris Fields took the lead on this and he we have a paper called conscious agent networks where where chris takes the lead and shows how to use these networks of conscious agents to build memory and to build primitive kinds of learning. But </s> |
<s>[INST] Yeah. The what about ISm is a is a failure case. I think that shows from all the interviews. I've seen that with him that just shows that he doesn't trust the person on the other side. [/INST] He doesn't </s><s>[INST] right. But I I I'm not cynical like people's they they seem to think he's some kind of KGB agent that doesn't trust anybody. I disagree. I think everybody's human. And from my perspective, I'm worried about what I've seen is I think whether it's covid whether it's uh other aspects that I'm not aware of leading up to the invasion, he seems to be less willing to have a charismatic back and forth dialogue. [/INST] Yeah, an open discussion. You know, actually, you know, I said, you asked me before about, you know, that issue of trust and he often says he only trusts himself and I said, you know, he's often distrustful of people, but he does trust some people for certain things where he knows it's within their competence. Yeah. So he has people he trusts to do things because you know, he he knows they'll do them and he knows that will do them well. Which is why, you know, he has his, you know, old buddies from, you know, ST Petersburg, he's known for a very long time and he knows that they want, you know, try to pull a fast one over him, but he also knows their strengths and their weaknesses and what they can be trusted to do. I mean he's learning that, you know, some of the people in the military, but he, you know, thought were competent or people and other things are not right that they and it intends to actually have a lot of loyalty to people as well. Or he also kind of thinks it's best to keep him inside the tent and outside and he moves them around. You know, he kind of okay, you know, that he gives them multiple chances to redeem themselves if they don't. It's not like he hasn't done in, I mean there is a lot of that in the system, but the people that he's worked with for a long time and he moves them around to something else perhaps where they can do less harm. Although, you know, we often see that he has quite a small cadre of people that he's reliant on and you know, they're not up to the task, which is kind of what's happening here. But he also in the past has been more straightforward, just like you were saying here more pragmatic. And I think, you know, if you were engaged with him in Russian where you're actually literally speaking the same language because there's so much lost in translation. I used to jump out of my skin listening to some of the phone calls because you know, the way that they kind of relayed, you know, with an interpreter </s><s>[INST] because, you [/INST] know, I'm listening to the Russian and the translation, you know in real time and I haven't been at the translators institute is really difficult. Look, an interpreter is a trend in the moment to do something, you know, the syncronys, the sink, the synchronized or the real time translation, translation is an art as well as a skill. If you're doing simultaneous translation, that's the word in english and it's syncronys in in in Russia, you're you're kind of focused in the moment on the fragments of the discussion trying to render it as accurately as you possibly can. And when you come out of that, you you can't relay the entire conversation and often, you know, what translators do is they, you know, they take this little shot and not like journalists do and afterwards, you know, they they they've just been caught up in the moment and they haven't got the big picture consecutive translation is different, you know, kind of you're trying to convey the whole mood of like big chunks of dialogue that have already been there, but you know, sometimes you might not get that right either, and it breaks up the flow of the discussion, </s><s>[INST] that's terrible [/INST] and and often it's you know, the kind of the person who translates, it's different, you know, some of our best translators a woman, but you know, hearing a woman's voice, you know, translating a guy who has a particular guy's way of speaking and a much a way of speaking and a crude way of speaking, you know be that Putin or I've seen that happen with Erdogan, the president of Turkey, you know it gets translated by a much more refined, you know female speaker, you've just lost the whole thing and you know many of the translators on the Russian side are not competent in english in the way that you would hope they are, they're not, it's not just that they're not native speakers, they're just not trained to the same high standards. They used to be in the past and you just got you lose the nuance that you lose the feel, you know, you almost need you know kind of the interpretive actor, you know doing you know the kind of the the the interpretation for that, you need to match it as much as you can in the way that you do voice overs in film. The best way to talk to Putin is one on 1 in his own language. I mean I have a really great friend here who is one of the best interpreters of Putin is often asked by the you know the media to interpret for him. He was just, he was at the institute that I was I mean I know him from that that kind of period and he is just excellent, just like pavel Plushenko was absolutely phenomenal interpreting garbage off now he didn't always interpreted accurately because garbage off made lots of grammatical gaffes and sometimes was you know, Gorbachev himself would joke that pollution, you know, spoke better for garbage off than garbage off could himself. But Putin is actually quite precise and careful in the way that he speaks because a lot of menace. Sometimes the things deliberately, other times there's lots of humor and he's telling a joke for a particular reason. A lot of it is, I mean he actually uses the richness of the Russian language and the crudity of language that can't be conveyed in </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] that's amazing that the question is what I mean, surprised, I don't just mean it's nice to have that accomplishment. Is there is a stepping towards something that feels uh more intelligent than before? And the question is that's in [/INST] your view of the world? </s><s>[INST] Okay, well let me then, that doesn't mean I'm wrong. So the question is if we keep taking steps like that, how far that takes us and we're going to build a better recommend er systems we're going to build a better robot or will we solve intelligence. [/INST] So, you know, I'm putting my bet on um but still missing a whole lot a lot. Um And why would I say that? Well in these games they're all um you know, 100% information games. But again, but each of these systems is a very short description of the current state um which is different from registering and perception in the world, which gets back the Mayor of X paradox. </s><s>[INST] I'm definitely not saying that chess is somehow harder than perception or any kind of even any kind of robotics in the physical world, I definitely think is way harder than the game of chess. So I was always much more impressed by like the workings of the human mind is incredible? The human mind is incredible. I believe that from the very big, I want to be a psychiatrist for the longest time. I always thought that's way more incredible in the game of chess. I think the game of chess is uh I love the olympics. It's just another example of us humans picking a task and then agreeing that a million humans will dedicate their whole life to that task. And that's the cool thing that the human mind is able to focus on one task and then compete against each other and achieve like weirdly incredible levels of performance. That's the aspect of chest that's super cool. Not that chest and itself uh is really difficult. It's like the farmers last year and is not in itself. To me that interesting. The fact that thousands of people have been struggling to solve that particular problem is fascinating. So can I tell [/INST] you my disease in this way? Sure. Which actually is closer to what you're saying. So as a child, you know, I was building various, I call them computers. They weren't general purpose computers, cube tray, ice cube tray was one. But I built on the machines and what I like to build was machines that could beat adults at the game and they couldn't adults couldn't beat my machine. So you </s><s>[INST] were like uh that's powerful. Like that's uh that's the way to rebel. Yeah, by the way. Um Did you, when was the first time you built something that I performed you do you remember like [/INST] well and I knew how it worked. I was probably nine years old. And I built a thing that it was a game where you take turns and taking matches from a pile and uh either the one who takes the last one of the one who doesn't take the last one wins, I forget. And so it was pretty easy to build that out of wires and nails and little coils that were like plugging in the number and a few light bulbs. Um The one the one I was proud of of. I was 12 when I built a a thing out of old telephone switchboard switches that could always uh win at Tic tac toe. And that was a much harder circuit design. But again, was just there was no active components that was just three position switch is empty X. Zero, oh and and nine of them. And a light bulb. One which which move it wanted next. The human would go and move </s><s>[INST] that. There's magic in that creation. I was Yeah. I tend to uh tend to see magic and robots that like I I also think that intelligence is a little bit overrated. I think we can have deep connections with robots very soon. [/INST] And we'll come back to connections for sure. But I do want to say, I don't I think too many people make the mistake of seeing that magic and thinking, well we'll just continue, you know? But each, each one of those is a hard fought battle for the next step. The next step. Yes, </s> |
<s>[INST] Yeah. Well as far as I know psilocybin, so mushrooms, magic mushrooms. Uh as far as I know in terms of the studies they're running I think have no over like they're allowed to do what they're calling heroic doses. So that one does not have a toxicity. So they can do like huge doses in a clinical setting when they're doing study on cell assignment. Which is kind of fun. [/INST] Yeah it seems that most of the psychedelics work in extremely small doses. Which means that the effect on the rest of the body is relatively low and M. D. M. A. Is probably the exception. Maybe ketamine can be dangerous and larger doses because you can depress breathing and so on. But the LSD and psilocybin berg and very very small doses at least the active part of them of psilocybin analyses only the active part and the but the effect that you can have on your mental wiring can be very dangerous. I think. </s><s>[INST] Let's talk about a I a little bit What are your thoughts about gpt three and language models trained with. So supervised learning. Yeah it came out quite a bit ago but I wanted to get your thoughts on it [/INST] In the 90s. I was in New Zealand and I had an amazing professor Ian bitten who realized there was bored in class and put me in his lab and he gave me the task to discover grammatical structure in an unknown language and the unknown language that I picked was english because it was the easiest one to find Corporates for construct one. And he gave me the largest computer at the whole university. It had two gigabytes of ram, which was amazing. And I wrote everything and see with some in memory compression to do statistics over the language. And uh first would create a dictionary of all the words which basically tokenize is everything and compresses things so they don't need to store the whole word, but just a code for every word. And then I was taking this all the parts and sentences and I was trying to find all the relationships between all the words and the sentences into statistics over them. And that proved to be impossible because the complexity is just too large. So if you want to discover the relationship between the article and the noun and there are three adjectives in between, you cannot do engram statistics and look at all the possibilities that can exist at least not with the resources that we had back then. So I realized I need to make some statistics over what I need to make statistics over. So I wrote something that was pretty much a hack that did this for at least first order relationships. And I came up with some kind of mutual information graph that was indeed discovering uh something that looks exactly like the grammatical structure of the sentence just by trying to encode the sentence in such a way that the words would be written in the optimal order inside of the model. And what I also found is that if we would be able to increase the resolution of that and uh just use this model to reproduce grammatically correct sentences, we would also be able to correct stylistically correct sentences by just having more bits in these relationships. And if he wanted to have meaning we would have to go much higher order. And I didn't know how to make higher order models back then without spending more years in research on how to make the statistics over what we need to make statistics over. And this thing that we cannot look at, the relationships between all the bits in your input is being solved in different domains in different ways. So in computer graphics, the computer vision standard methods for many years now is convolutional neural networks, convolutional neural networks. Hierarchies of filters that exploit the fact that neighboring pixels and images are usually semantically related and distance pixels and images are usually not semantically related. So you can just by grouping the pixels that are next to each other hierarchically together, reconstruct the shape of objects. And this is an important prior that we built into these models so they can convert quickly. But this doesn't work on language for the reason that adjacent birds are often but not always related in distant words are sometimes related while the words in between or not. All right. So how can you learn that apology of language? And I think for for this reason that this difficulty exists that the transformer was invented in natural language processing not envision and what the transformer is doing. It's a hierarchy of layers. Every layer learns what to pay attention to in the given context in the previous layer. So what to make the statistics over </s><s>[INST] And the context is significantly larger than the adjacent ward. [/INST] Yes. So the context that the GTT three has been using the transform itself is from 2017 and it wasn't using that large of a context open Ai has basically scaled up this idea as far as I could at the time. And the context is about 2048 symbols, tokens in the language. These symbols are not characters, but they take the words and project them into a vector space where words that are statistically co occurring a lot our neighbors already. So it's already a simplification of the problem a little bit. And so every word is basically a set of coordinates in a high dimensional space. And then they use some kind of trick to also include the order of the words in a sentence or in the not just sentence, but 2,048 tokens is about a couple of pages of text or 2.5 pages of text. And so they managed to do pretty exhaustive statistics over the potential relationships between two pages of text, which is tremendous. Right? I was just using a single sentence back then and I was only looking for a first order relationships and they were really looking for much, much higher level of relationships and what they discover after they fed this with an enormous amount of training and they are pretty much the written internet or the subset of it that had some quality but substantial portion of the common troll that they are not only able to reproduce style but they are also able to reproduce some pretty detailed semantics like being able to add three digit numbers and multiply two digit numbers or to translate between programming languages and things like that. So the results that gpt three got I think were amazing </s> |
<s>[INST] you wanted to have some padding to like all right, I can at least count on this to save us if we go like super negative. [/INST] Right? I mean it was like a cheap hack but that was like I could come up with and you know until we could hire like a real fine CFO and financial team who like okay now we know we got our arms around how much cash we have. It sounds silly but we had such high volume of money coming in and out. Anyway. What was </s><s>[INST] the ordering of hiring by the way? Like uh how many engineers was it earlier on? You said CFO was not didn't even have a CFO for a bit like what was the the landscape of hiring as you're building up this company? Was it engineering focused? [/INST] Well let's see I mean so the first person we hired was just like we need we need to solve customer support. So we brought someone to do that because we were all staying up till midnight every night trying to customer support and then we got more engineers and then I think maybe the sixth higher or something like that was a recruiter because that that turned out to be, you know, you need to build higher, the person who can hire more people </s><s>[INST] that [/INST] turned out to be a great force multiplier and then you go on down the list, you eventually you want to hire some more senior people. Um We needed legal and compliance. We need that really badly because we, you know, there's all kinds of questions about what the legality of it was. Was </s><s>[INST] it hard to find legal people that work with crypto like serious adults because it's such a cutting edge new world. [/INST] Yeah, I mean there's nobody who had like more than nobody had three years of experience with because there had only been around for years. So yeah, we were finding people from adjacent fields, There's a certain personality type of people who are willing to join early companies because they have no structure, you can't really commit to them about, you're gonna have this team or this boss or whatever, like everything's in chaos and flux so it takes. Yeah, hiring is one of the hardest things in the early stage for sure. You gotta find people crazy enough to join you on this journey. </s><s>[INST] So 11 of the interesting things about Coinbase and you've written, we've talked, we'll talk about it a bit, you're very focused on the mission, You're very kind of, I think that simplifies things that makes, that makes hiring easier, that makes working at Coinbase easier. That makes, I mean it's similar sort of Ellen has the same thing, it's pretty clear it's pretty clear what we're here to do. So I suppose what's the mission of coin base? [/INST] Well it's to increase economic freedom in the world </s><s>[INST] And what is economic freedom? [/INST] Yeah. So economic freedom is this term kind of like GDP that economists use and it's basically a measure of different countries around the world. It looks at things like are their property rights and forest, is there free trade, Is the currency stable? Can you start companies that you wanna start and can you join the one you want to join? And you know, is there corruption and bribery prevalent or is it relatively free of that? And so this there's several different organizations that basically score countries by economic freedom and the really cool thing about economic freedom is that basically it positively correlates with things that we all want in society like um not only higher growth of the economy but also things like higher self reported happiness of citizens, better treatment of the environment, better income for the poorest 10% of people. And it negatively correlates with things we don't want a society like corruption and bribery and war even and things like that. And so it's this pretty pretty crazy provocative idea which is that if you give people good property rights and rule of law and allow them to trade. It basically encourages them to do more good stuff and the whole society benefits like one of the things you know you may have noticed this um growing up in various places you did or you know I spent a year living in Buenos Aires Argentina that went through hyperinflation and there's a certain like pessimism that can creep into countries when they don't have economic freedom which it's basically like everyone has this bit of this vibe which is like don't stick your head up you know don't try too hard because it could all be gone tomorrow like the things that really are valuable in life are just family and friends and the past was better than the future will be and and so you don't really, people don't try as many, they don't try hard because you're not really sure you can actually keep the upside of your labor if you, if you try hard so you just don't try as hard whereas in America historically um you know or high economic freedom countries you know people basically like they just try more stuff because they're like if I do good for other people I'll get to keep part of it for myself and I can improve my lot in life and for my Children and my community or whatever so I realized when I read the Bitcoin white paper a long time ago that at least I had a hunch at the time, I was like this might be a really powerful piece of technology that can inject good financial infrastructure into all these countries around the world that don't have it basically good economic freedom principles in like you know property rights and things like that into these countries all over the world which just as long as you have a smartphone and now crypto got invented we could everybody could have economic freedom and its crypto is kind of really well suited for economic freedom because if you want property rights, it's based like crypto is if you can remember 12 word phrase or you know have an app on your phone, you can store as much wealth as you want and it can't be taken away from you. You can even you know there's like refugees who need to flee and they want to take their wealth with them and they can't do it often in the traditional financial system and so crypto lets them do that right? Crypto is inherently global. So it allows free trade and cross border payments. Um it makes it easy to accept payments from people globally. You know it's it provides a stable currency to everyone, not only with Bitcoin which is kind of like this new reserve currency but um also with stable coins right? Which are you know new new inventions there. So yeah I I basically feel like crypto is is this secret hiding in plain sight that can create economic freedom for people all over the world and a more fair and free and global economy. </s> |
<s>[INST] My favorite app for learning new things, Blinkers takes the key ideas from thousands of nonfiction books and condenses them down into just 15 minutes that you can read or listen to. I actually posted this meme on twitter. Um my text was, I thought we had something special and the meme reads my unread books, watching me buy new books and there's this kind of heartbroken stalker image staring out from the screen deep into your soul. It is true that we sometimes leave the books were meant to read behind just to acquire the new thing. And I don't think it has to be that way. I think what we ultimately seek is to gain the key insights from a book. You know, there's so many amazing books out there, you can't get a chance to fully [/INST] read all of them. </s><s>[INST] Use blankets to at least get the insights go to blankets dot com slash lex to start your free seven day trial and get 25% off of a blinkers, premium membership as blankets dot com slash lex spelled B L I N K I S D blankets dot com slash lex. This is the lex Friedman podcast and here is my conversation with grimes. [/INST] We are becoming cyborgs. </s><s>[INST] Like our brains are [/INST] fundamentally changed. Everyone who </s><s>[INST] grew up with electronics, [/INST] we are fundamentally different from previous, from homo sapiens. </s><s>[INST] I call us home a techno. [/INST] I I think we have </s><s>[INST] evolved into homo techno, which is like essentially a new species. [/INST] Previous </s><s>[INST] technologies, [/INST] I mean may have even been more profound and moved us </s><s>[INST] to a certain degree, but [/INST] I think the computers are what make </s><s>[INST] us homo techno. I think [/INST] this is what it's a brain </s><s>[INST] augmentation. [/INST] So it like allows for </s><s>[INST] actual evolution. [/INST] Like the computers accelerate the degree </s><s>[INST] to which all the other [/INST] technologies can also </s><s>[INST] be accelerated. [/INST] Would you classify yourself </s><s>[INST] as a homo sapiens or [/INST] homo techno, definitely homo techno. </s><s>[INST] So you think you're, you're one of the earliest of the species? I think most of us are. [/INST] Oh yeah, the cloud lifter. There </s><s>[INST] you go. There you [/INST] go. You know your stuff, </s><s>[INST] Have you ever used the cloud lifter? Yeah, [/INST] I actually, this microphone, cloud </s><s>[INST] lifter is what [/INST] Michael Jackson </s><s>[INST] used. So. No, really? Yeah, this, this is like thriller and stuff. This mic. This [/INST] mic and that, Yeah, </s><s>[INST] it's, it's a incredible microphone. [/INST] It's very flattering on vocals. </s><s>[INST] I've used this a lot. [/INST] It's great for demo vocals. It's </s><s>[INST] great in a room. Like sometimes it's easier to [/INST] record vocals if you're just in a room and like the music's </s><s>[INST] playing and you just want to feel it and it's not so it's not [/INST] on the headphones and this mike is </s><s>[INST] pretty directional. So I think it's like a good mic for like [/INST] just vibing out </s><s>[INST] and just getting a real good [/INST] vocal take </s><s>[INST] just vibing just in a room. Anyway, [/INST] this is the this is </s><s>[INST] this is the Michael Jackson Quincy [/INST] jones microphone. I feel way more badass now. Alright, let's </s><s>[INST] get you want to get into it, [/INST] I guess. So. All </s><s>[INST] right. One of your names, at least in this space and time is C. Like the letter C. And you told me that si [/INST] means a lot of things. </s><s>[INST] It's the speed of light, its surrender rate [/INST] of the universe. </s><s>[INST] It's yes, in spanish, it's the crescent moon and it happens to be my favorite programming language because it's uh it basically runs the world, but it's also powerful fast and it's dangerous because you can mess things up really bad with it because of all the pointers. But anyway, which [/INST] of these </s><s>[INST] associations with the name C [/INST] is the coolest </s><s>[INST] to you. I mean, [/INST] to me the coast is the </s><s>[INST] speed of light [/INST] obviously, or the speed of </s><s>[INST] light when I say render rate of [/INST] the universe. I think, I mean the speed of light </s><s>[INST] because essentially that's what we're rendering [/INST] at sea. I </s><s>[INST] think we'll know [/INST] if we're in a simulation, if the </s><s>[INST] speed of light changes because if [/INST] they can improve their render speed then </s><s>[INST] it's already pretty [/INST] good. It's already </s><s>[INST] pretty good. But if it improves [/INST] then well </s><s>[INST] no, you know, we can [/INST] probably be like okay, they've </s><s>[INST] updated or upgraded was [/INST] fast enough for us </s><s>[INST] humans because it seems [/INST] like </s><s>[INST] um it seems [/INST] immediate. There's </s><s>[INST] no delay, there's no latency in terms of like us humans on earth interacting with things. But [/INST] if you're like </s><s>[INST] uh like intergalactic species operating in a much [/INST] larger scale, then you're going to </s><s>[INST] start noticing some weird [/INST] stuff. Or if you </s><s>[INST] can operate in like around a black hole, then you're going to start to see some render issues. You can't [/INST] go faster in the speed of light, </s><s>[INST] correct? So it really [/INST] limits our ability </s><s>[INST] or and it's one's [/INST] ability to travel space </s><s>[INST] theoretically you can you have warm holes. So there's nothing in general [/INST] relativity that </s><s>[INST] precludes faster than [/INST] um </s><s>[INST] the speed of light travel. But it just seems you're gonna have to do some really [/INST] funky stuff with </s><s>[INST] very heavy things that have like weirdness [/INST] is that they have </s><s>[INST] basically terrorism. Space time. We don't know how to do that. [/INST] Do navigators know how to </s><s>[INST] do it? Do [/INST] navigators folding </s><s>[INST] space [/INST] basically making wormholes? So the name's </s><s>[INST] c Who are you? Are you do you think [/INST] of yourself as multiple people? </s><s>[INST] Are you one person. Do you know like in [/INST] this morning where you're a different </s><s>[INST] person than you are tonight? We [/INST] are, I should say recording </s><s>[INST] this basically at midnight which is awesome. Yes, thank you so much. I [/INST] Think I'm about eight hours late. no </s><s>[INST] you're right [/INST] on time. Good morning. </s><s>[INST] This is the beginning of a [/INST] new day </s><s>[INST] soon. Anyway. Uh [/INST] Are you the same person you were in the morning and </s><s>[INST] the evening? Your your is there [/INST] Multiple people in there? Do you think of yourself as one </s> |
<s>[INST] Yeah. And I think Covid, the way you're approaching Covid has two interesting possibilities. One, it might help with Covid or another pandemic. But to I mean just this whole network theory space, you might unlock some deep understanding about the interaction of human beings that might have nothing to do with the pandemic. There's uh there's a space of possible impacts that may be direct or indirect. And the same thing is that with Andrew Wiles proof I don't understand. But apparently the pieces of it are really impactful for for mathematics, even if the main theorem is not So along the way, the the insights you have might be really powerful for unexpected reasons. [/INST] So I like what you said, this is something that I learned from another friend of mine who's also, he's a very famous researcher. All these people are more famous than his name is Jacob Fox. He's Jacob Fox at stanford also a very big inspiration for me. We were both grad students together at the same time. </s><s>[INST] Well most importantly you're good at selecting good friends. [/INST] Yeah, that's that's the key, you got to find good people to learn things from. But his thing was he often said, you know, if you solve a math problem and have this math proof. Math problem for him is like a proof, right? So suppose you came up with this proof, he always asks, what have we learned from this that we could potentially use for something else. It's not just did you solve the problem that was supposed to be famous? It was. And is there something new in the course of solving this that you had to invent that we could now use as a tool elsewhere? </s><s>[INST] You know, there's this funny effect where Uh just looking at different fields where people discover parallels, they'll they'll prove something will be told in your result. And then somebody later realized that this was already done 30 years ago in another discipline in another way. And it's really interesting. No, we did this offline another illustration he showed to me, it's interesting to see the different perspectives on a problem. It kind of points like there's just like very few novel ideas that everything else that most of us are just looking at different perspective on the same idea. And it makes you wonder this this uh this old silly question that I have to ask you as do you think mathematics is discovered or invented? Do you think where creating a new idea? We're building a set of knowledge that's that's distinct from reality or are we actually like it's math almost like a shovel where we're digging too. Like this core set of truths there that were always there all along. [/INST] So I personally feel like it's discovered, but that's also because I guess the way that I'd like to choose what questions to work on our questions that maybe we'll get to learn something about Why is this hard? I mean I'm often attracted to questions that look simple but are hard. Right. And what could you possibly learn from that sort of like probably the attraction of Fermat's last theorem? Uh, as you mentioned, simple statement. Why is it so hard? So I'm more on the discovered side. And I also feel like if we ever ran into an intelligent other species in the universe, probably if we compared notes, there might be some similarities between both of us realizing that pie is important because you might say why, why humans do humans like circles more than others. I think stars also like circles. I think planets like circles, they're not perfect circles. But nevertheless, the concept of a circle is just point and constant distance doesn't get any simpler than </s><s>[INST] that. It's possible that that like an alien species, we have, uh, depending on different cognitive capabilities and different perception systems will be able to see things that are much different than circles. And so if it's discovered, it would still be pointing at a lot of same geometrical concepts? Mathematical concepts, but it's interesting to think of how many things we would have to still align, not just based on notation but based on understanding like just like um some basic mathematical concepts like how much work is there going to be in trying to find a common language? This is um I think Stephen Wolfram and his son helped with the movie arrival, like the developing an alien language like howard aliens communicate with humans. It's fascinating because like math seems to be the most promising thing. But even like math, like how do you visualize mathematical ideas? It feels like there has to be an interactive component, just like we have a conversation, there has to be this is something we don't I think think about often, which is like with somebody who doesn't know anything about math doesn't know anything about english or any other natural language. How would we describe, We talked offline about visual proofs. How would we through visual proofs have a conversation where we say something, here's the concept, the way we see it. Does that make sense to you and like can you mess with that concept to make it sense for you and I go back and forth in this kind of way. So purely through mathematics, I'm sure it's possible to have those kind of experiments with tribes on Earth that don't there's no common language through math, Like draw a circle and see what they do with it, right? Do some of these visual proofs? Uh Like the summation of the odds and adds up to the squares. Yes. I wonder how difficult that is before one or the other species murders. [/INST] I </s> |
<s>[INST] this there's this going back and forth and now there's a feeling like you're censoring a little bit too much. And so I would lean, I would try to be ahead of that feeling. I would now lean towards freedom of speech and say, you know, we're not the ones that are going to define misinformation. Uh, let it be a public debate. Let the idea stand. And I actually place, you know this idea of misinformation, I place the responsibility on the poor communication skills of scientists. They should be in the battlefield of ideas and everybody who is um spreading information against the vaccine, they should not be censored. They should be talked with and you should show the data you should have open discussion as opposed to rolling your eyes and saying I'm the expert, I know what I'm talking about. No you need to convince people it's a battle of ideas. So that's the whole point of freedom of speech is the way to defeat bad ideas is with with good ideas with speech. Um so like the responsibility here falls on the poor uh communication skills of scientists. Thanks to social media. Scientists are not communicators. They have the power to communicate. Some of the best stuff I've seen about covid it from doctors is on social media. It's a way to learn to respond really quickly to go faster than the peer review process. And so they just need to get way better at that communication and also by better. I don't mean just uh convincing. I also mean speak with humility. Don't talk down to people all those kinds of things. And as a platform I would say I would step back a little [/INST] bit. </s><s>[INST] Not all the way of course because there's a lot of stuff that can cause real harm as we've talked about. But you lean more towards freedom of speech because then people from a brand perspective wouldn't be blaming you for the other ills of society which there are many the institutions have flaws, the political divide. Obviously politicians have flaws that's news, the media has has flaws that they're all trying to work with. And because of the central place of facebook in the world, all of those flaws somehow kind of propagated facebook and you're sitting there in the in as plato the philosopher have to answer to some of the most difficult questions asking being asked of human civilization. So I don't know, maybe this is an american answer though, to lean towards freedom of speech. I don't know if that applies globally. So yeah, I don't I don't know but transparency and saying, I think as a as a technologist, one of the things I sense about facebook and matter when people talk about this company is they don't necessarily understand fully how difficult the problem is. You talked about aI has to catch a bunch of harmful stuff really quickly. Just the sea of data you have to deal with. It's a really difficult problem. So like any of the critics, if you just hand them the helm [/INST] for </s><s>[INST] a week, let's see how well you can do like that to me that that's definitely something that would wake people up to how difficult this problem is. If there is more transparency is saying how difficult this problem is. Let me ask you about on the eye front just because you mentioned language and my in eloquence translation is something I wanted to ask you about. And first just to give a shout out to the supercomputer, you've recently announced the ai research Supercluster RSC obviously I'm somebody who loves the Gpu s. It currently has 6000 Cpus and NVIDIA G G X a one hundred's uh is the systems that have in total 6000 Cpus and uh it will eventually maybe this year, maybe soon we'll have 16,000 GPU s so it can do a bunch of different kinds [/INST] of </s><s>[INST] machine learning applications. There's a cool thing on the distributed storage aspect and all that kind of stuff. So one of the applications that I think is super exciting is translation, real time translation I mentioned to you that you know having a conversation I speak Russian fluently, speak english somewhat fluently and I'm you know having a conversation with Vladimir Putin say as a use case me as a user coming to you in the use case we both speak each other's language. I speak Russian, he speaks english. How can we have that communication go well with the help of a I I think it's such a beautiful and powerful application of ai to connect the world that bridged the gap not necessary between me and Putin, but people that don't have that shared language um can you just speak about your vision with translation because I think that's a really exciting application [/INST] if you're trying to help people connect all around the world, you know, a lot of content is produced in one language and people and all these other places are interested in it. So being able to translate that um just unlocks a lot of value on a day to day basis. So the kind of ai around translation is interesting because it's gone through a bunch of um a bunch of iterations, but the basic state of the art is that you don't want to go through, you know, different kind of um intermediate symbolic um representations of of of language or something like that. It's you basically want to be able to map the concepts and and basically go directly from one language to another and you just can train um bigger and bigger models in order to be able to do that. And that's where the the the research supercluster comes in is basically a lot of the trend in in machine learning is just you're you're building bigger and bigger models and you just need a lot of computation to train them. So it's not that like the translation would run on the supercomputer, the training of the model, um which which could have, you know, billions or trillions of examples of just basically that um your your training models on this supercluster in, you know, days or weeks, that might take a much longer period of time on a smaller cluster. So it just wouldn't be practical for most teams to do. But the translation work. Um we were basically getting from, you'll be able to go between about 100 languages seamlessly today. Um to being able to go to about 300 languages um in the near term and so </s> |
<s>[INST] So you, so there, um, the Travis opponent and he's Travis is setting up here that say Nagy posting is left arm and getting it done. That's a big, that's a big throw. You have too many of those big throws on uh, on video because like you often on video, you're going against the best people in the world. It's tough to get like that much air. [/INST] And a lot of times the ones that we do see and you know, the part that a lot of people don't experience is a lot of those times right through people with that throw, it was in training camps. So by the time I got to the competition with these guys, They were playing 100% defense to never let me do </s><s>[INST] that. So you do this. Um here are you kind of pulling him down? [/INST] No, he's I'm trying to get him to </s><s>[INST] come up to come up, but are you pulling him down to get to fake him [/INST] up? I'm not doing anything with my left hand. </s><s>[INST] Uh So here the the opponents, so [/INST] what I'm doing right now is his head is like in my chest, I'm pressing him to get his head to lift with my chest. So I'm pressing his hand down so I can use my chest to pinch my scraps and roll his head up so that he wants to pick it up </s><s>[INST] and and then he I mean doesn't you know what's coming here? I don't know, he might not. [/INST] Oh no, he knew he was a former teammate, he knew exactly what I was trying to do </s><s>[INST] and that was a really big step with your right foot, [/INST] It covers about four ft so use distance </s><s>[INST] and you left um catches up in like perfect position, [/INST] you back it up a little bit, keep going, keep going right there. That this is like an important distinction between mine and everybody else's is because I split his hip. Um I actually, once I am able to split, I no longer need his center of gravity below mine, </s><s>[INST] right? And when you say split, you mean you put your foot in between [/INST] might do that split that four ft split and then when I get my feet back together, it doesn't matter that I'm under his center gravity or not, that's why my chest is right around his like sternum height for </s><s>[INST] me. Yeah so there I mean how does he get for people just listening to this Travis steps is like that's a big huge step gets [/INST] like my hip is really right around his nipple because he's he's brought back so much. </s><s>[INST] Yeah that's right. So like so you're how does the physics of this work? You're violating the principle of your center of mass being under? Oh I guess somehow it is, I don't know but he has nowhere to go. [/INST] He screwed. Yes that's the kickers. The way mine mind works is in order for him to play an effective defense. He needs to have his feet firmly planted on the ground with friction. Yeah, otherwise he can't press into me to stop it. So when I get him to sprawl back, when I split his legs, he effectively loses that contact with the floor even though his feet are on the floor. They're not in a position where he can drive from them. Yeah, therefore when I flip he flips </s><s>[INST] so there's a uh there's a natural like flailing here so he's not falling forward, you're falling forward, he's just attached to you so like you can keep him up there and then like legs would be just flailing. [/INST] One of my, one of my golden rules when I'm training and I get really tired one of the like mantra I would always tell myself is I'm gonna put my back on your chest and then I'm gonna put my back on the floor. Yeah because then you'll be underneath me. </s><s>[INST] It's a good principle, the [/INST] very simple and it regardless of like all the chaos and how quickly things are happening, it's something I can just dumb everything down to and focus on regardless of the gripping situation, the footwork, all of that, get my back to your chest and then put my back on the floor. </s><s>[INST] So this step of getting your back to their chest. Like for for people who are sort of more like for example for people like me, we're just like amateur judo people. Like there's all kinds of ways to prevent this turn from happening, the gripping and just everything. Uh how difficult is it at the highest level to get into this position? I mean you make it look effortless often but like to get to a position where you're from facing them too, you're back to them. Is that like strategies, that timing is [/INST] that timing? It's timing. It's like anything like if I wanted to punch you in the face, like how hard is it to really do that if you know you can just play defense and block it, the trick is to get them to play defense to something that never happened </s><s>[INST] and then you go through like another way and then [/INST] you just go through what would technically be your first plan if you planned on them playing defense. So I set the stage from the very beginning for this to work. </s> |
<s>[INST] Something that echoes the process of a finger moving along cause [/INST] a very, very loose sense. It's like again, learning is inherently about the suffering, the structure in the world and discover the structure in the world. You have to move through the world. Even if it's a virtual world, Even if it's a conceptual world, you have to move through it. You don't it doesn't exist in one. It has some structure to it. So here's here's a couple of predictions are getting what you're talking about in humans. The same album is does robotics right? It moves my arms, my eyes, my body, right? Um And so in my in the future to me, robotics and Ai will merge. They're not gonna be separate fields because they're gonna the algorithms are really controlling robots are gonna be the same algorithms we have in our bread brain that these century algorithms today, we're not there. But I think that's gonna happen and um and then so but not all AI systems will have the robotics. Um You can have systems that have very different types of embodiments, some have physical movements, some will have not have physical movements. It's a very generic learning system. Again, it's like computers, the turing machine, it's like it doesn't say how it's supposed to be implemented, doesn't tell how big it is, doesn't tell you what you apply it to. But it's an interesting, it's a computational principle. Cortical column equivalent is a competition principle about learning. It's about how you learn and it can be applied to go zillion things. This is what I think this is I think this impact of Ai is going to be as large if not larger than computing has been in the last century by far because it's getting out of fundamental thing, it's not a vision system or a learning system. It's a it's not a vision system or hearing system. It is a learning system is a fundamental principle how you learn to structure in the world, how you gain knowledge and be intelligent and that's what the 1000 Brain says it was going on and we have a particular implementation in our head, but it doesn't have to be like that at all. </s><s>[INST] Do you think there's going to be some kind of impact? Okay, let me ask it another way. What do uh increasingly intelligent ai systems do with us, humans in the following way? Like how hard is the human in the loop problem? How hard is it into into to interact the finger on the coffee cup equivalent of having a conversation with a human being? So how hard is it to fit into our little human world? [/INST] I don't I think it's a lot of engineering problems. I don't think it's a fundamental problem. I could ask you the same question. How hard is the computers to fit into the human world? </s><s>[INST] Right. I mean, that's essentially what I'm asking, like, how um much are we elitists, are we as humans? Like we tried to keep out systems? [/INST] I don't know, I'm not sure, I think, I'm not sure that's the right question. Let's let's look at computers as an analogy, computers a million times faster than us. They do things we can't understand. Most people have no idea what's going on when they use computers, how the how we integrate into our society. Um Well, there, we don't think of them as their own entity and they're not living things. Um We don't afford them, right? Um We uh we rely on them our survival as a seven billion people or something like that, is relying on computers now. Um </s><s>[INST] Don't you think that's a fundamental problem that we see them as something we can't we don't give rights to. Like So yeah, computers, so robots, computers, intelligence systems, it feels like for them to operate successfully. They would need to have a lot of the elements that we would start having to think about. Like should this entity have rights? [/INST] I don't think so. I think it's tempting to think that way. First of all, I don't think anyone, hardly anyone thinks that's for computers today. No one says, oh, this thing and he's right, I shouldn't be able to turn it off or, you know, if I throw it in the trash can do you know, and hit with a sledgehammer. My my former criminal act. No, no one thinks that. Um and now we think about intelligent machines, which is where you're going. Um And and all of sudden, like, well now we can't do that. I think the basic problem we have here is that people think intelligent machines will be like us, they're going to have the same emotions as we do it. Same feelings that we do. What if I can build an intelligent machine that absolutely could care less about whether it was on or off or destroyed or not. It just doesn't care. It's just like a map? It's just a modeling system, there's no desires to live, nothing. </s><s>[INST] Is it possible to create a system that can model the world deeply and not care brother whether it lives or dot [/INST] No question about it </s><s>[INST] To me, that's not 100% obvious. It's obvious to me. So we [/INST] can debate if you want, where does your, where does your desire to live come from? It's an old evolutionary design. I mean, we could argue, doesn't really matter if we live or not objectively. No, right? We're all gonna die eventually. Um, but evolution wants us want to live. Evolution makes us want to fight to live. Evolutionists want to care and love one another and to care for our Children and our and our relatives and our family and so on. And those are all good things. Um, but they come about not because we're smart because we're animals. They grew up, you know, the hummingbird in my backyard cares about its offspring. You know, they every living thing in some sense cares about, you know, surviving. But when we talk about creating intelligent machines, we're not creating life, We're not creating evolving creatures. We're not creating living things, We're just creating a machine that can learn really sophisticated stuff and that machine, it may even be able to talk to us, but it hasn't, it's not going to have a desire to live unless somehow we put it into that system. </s> |
<s>[INST] Well let me ask a difficult question. Some see escobar as a brutal murderer and some see him as uh, maybe a Robin Hood like figure who helped the poor. How do you see the man both of them? [/INST] I think he started out to be honest with help, the poor and then they had a war down there and they blew up and killed his people and the country was divided almost equally three ways. They had the, uh, the military, they were just as much into it as anybody. And then you had the farc guerrillas. They had about a third of the country and then you had the contras. It was like the white farmers and they're the ones that I was dealing with and they were at war with one another. And so if when I started killing their people, well, I'll kill some of yours too. So that, that's how it happened. And then when I heard about Pablo escobar blowing up that airliner and killing those women and Children, I was sorry I ever shook his hand. That's, that's brutal murder. </s><s>[INST] So you would say escobar is not a good man? [/INST] Not at all. It's terrible. Now looking back on it, when I met him, he was good. You're just exactly what he said. He would do. </s><s>[INST] Could he be a bad man and a man? You can trust absolutely. [/INST] You could trust him. Yes. </s><s>[INST] So from your perspective in terms of business, he was reliable. He was honest, had integrity, you could work with him and he felt safe [/INST] completely. Uh We flew up in uh to his ranch and he be brought out motorcycles to start with. And can you ride a motorcycle? Of course I can ride a motorcycle. So I took off across the grass and there was a little ditch there in the front wheel dropped in that thing and I must have slid across that grass 20 ft before I got stopped. He almost fell off his his bike waiting because they knew what it's gonna do. And then we got on horses and we're not then pretended type of round up some cows and he put a Mac 10 machine gun pistol over my shoulder, you know how to use this? Well I never had but it was all right. I think it was like okay you've got 10 bodyguards, what do you need me for? So that's the kind of time. We laughed and talked and drove some cows over the stumps. </s><s>[INST] You said Jorge Ochoa was perhaps the brains of the medellin cartel. What was he like and why do you say he was the brains? [/INST] Well he was a gentleman and I suppose he ship and no telling how many more times of cocaine than Pablo did just him and his brothers. You can tell by the they had on each two H. L. Load. There was in duffel bags and it's big football shaped fluffy stuff made with either and uh they would have three horns on it or a rattlesnake or four x is on each bag. You kind of got to knowing which was which was which and they shipped a lot. Yeah. So uh, and he was just a gentleman. I took the family, we went one weekend to his ranch or his uh palacio place out near barren Kia. And uh, oh we just treated the family and his family had, his younger brother wrote made a bullfight and we had skiing and little airplanes on floats on the water. It was really nice and he was really nice. </s><s>[INST] How do you make sense of the tension that a man could be a gentleman, You can have integrity but also be a murderer. [/INST] Well, murder is a, is a stronger word than killing. </s><s>[INST] Can you explain the line the gray area we're talking about? I mean I've just talking with jocko willing can we talked a lot about killing in the context of uh military conflict in the context of war. So there there's a line between murder and killing. You can draw what's the line that you're referring to [/INST] something similar. If you, if people shooting at you and you shoot back and kill him, I don't, that's not murder whatsoever. It's uh, he's trying to get away or out of the situation. But if some woman don't pay you and you send a hit man over to to kill her and her Children. That's that's that's murder. That's murder </s><s>[INST] was jorge involved in those kinds of things. [/INST] I don't think so at all. It just, I mean he was, he was just such a gentleman. He had a restaurant before and and he was just smart. I understand that the 1st 10 kg he sold, he was sitting on a on a motorcycle in the in the sidelines in the parking lot. When the D. E. A come in, he sped away so he didn't come back to America. He was just smart. Some people just have our savvy and he was such a gentleman and the whole family, the mother and the father of the two brothers. Their sister was, I was there when she was kidnapped. Uh Finally he kidnapped our I guess 100 liters of the farc. And uh I said all right, she don't come back. None of these are going to come back. So they made a deal. </s><s>[INST] Is there something you can say about the power structure? The hierarchy of the Midian cartel that you interacted with? Was was a a dictatorship where Pablo ran everything? Was there a bunch of power centers? Was it like a company with U. F C E O C T O. Kind of thing. And then there's like managers and all those kinds of things. What's the, like how did it run from a leadership perspective? [/INST] I understand that about five of them got together and made this, I will call it an insurance company. And uh now known as the managing cartel and I didn't see any difference. Each one of them had their own business and they're people from the jungle wherever made the cocaine gave it to them and they shipped it. And uh so it didn't, it didn't seem to be any, any power play between them at all. But my main contact was Jorge Ochoa and Pablo escobar bar was right there and I saw plenty of stuff for him to, </s> |
<s>[INST] Yeah. The we'll create conflicts of other sorts that lead to less human suffering than wars do like it we'll just start playing Diablo 456 and because you die in video games. So maybe we'll get some of the inkling of scarcity through the activities we partake in as opposed to our own body dying. I mean I feel shitty when I uh like you can remember in Diablo three you can play in hardcore mode where if you die in the game, your character is dead. Maybe you will get [/INST] the richness </s><s>[INST] of like that we currently get from life by having like little artificial versions of ourselves that die [/INST] interestingly enough as I have just like personally it spent more time in this world. I started realizing that you know there is a concept of like real fighting finite nous that still like exists and it might even still be a thing that provides meaning that doesn't require anyone to actually die. Like for example like how many people from middle school or even high school of yours? Like do you still talk to regularly? </s><s>[INST] I'm happy to be close friends with like four or 5 of them. [/INST] Okay. Like in my case the answer is zero for middle school into for high school, right? Exactly. You drop right? And so like there's a lot of these just like relationships that end up being very finite. Um a person changes There. I feel like a burst of changes enough of their worldview after 25 years. Was there even a study about this? Something like A person and themselves 25 years later about as different as like two different people or something like this. So yeah, I mean just like you can have conflict without bloodshed. I think you know you you can have a finite nous and even you know the necessary sort sorrows of a finite nous that give meaning without like literally any anyone having in their life. </s><s>[INST] And hopefully if we do extend our life will figure out ways to extend the period of time where there's newer neuro plasticity to or we could change our world views continually throughout that time. So you know these different phases of life. I thought it would be fun to hear you speak a little Russian cocktail russki corny agree tibia [/INST] the interior stuff up was </s><s>[INST] because [/INST] um because because uh yeah, cook them. Mm Of course that's what they're doing like them. You know the market reacted regularity of the Blockchain uh industry and like the cactus material. That was the toast to uh huh and McEwen like that choose to watch the time vortex. But uh no Fallujah category whiskey them. Yes. Uh um you know yeah. You think </s><s>[INST] there's uh so for people who don't speak Russian that metallic said that there's um that there is something to the spirit of the people that are Russian that are working in the Cryptocurrency world that is a little bit different and it's something that uh that connects to some kind of aspect of your own self, some kind of roots there. It's kind of interesting do you think that there's um does it make you sad that there's these two different worlds that are uh sort of in part disconnected by language? And I'm sure the same could be the case with china and other parts of the world or the language um slows the transmission of the beauty of the culture in a certain kind of way where you can't truly collaborate. Like you can all speak english, you're collaborating and maybe a technical level, but you're not collaborating on the level [/INST] of like some deep </s><s>[INST] human connection. Do you see that being able to speak both languages? [/INST] There's definitely benefits I think to be able to like speak multiple languages. And like once you can write like you you discover that given your mindset changes while you're in speaking in one language versus the other. Like people have told me this like when I speak Russian, I sound more like I guess like to the point and pragmatic when I speak chinese, I sound more cute when I speak english, I'm something else. Um Yes, uh there's definitely like a richness that you're missing if you're only like in one of these language bubbles. But you know, I guess the arguments on the other side would be that you know, if everyone spoke the same language then like there would just be one bubble. But this is the challenge, I think like uh there are actually benefits to having cultural diversity and you definitely don't want the entire world to be too conformist. Yeah. Well one of the interesting things about crypto is that it's just a culture that actually like manages to uh somehow, you know, have its uniqueness and present and even preserve its independence from all of all of these surrounding countries despite being embedded in all of them. </s><s>[INST] So it spans outside the geographic boundaries and language in some ways does as well. And in the way these cultures, these bubbles are created, I mean they overlap in interesting ways, It's almost like a hierarchy and the same is the case of the crypto world, there's uh there's communities associated with these cryptocurrencies, these communities within those communities and it's [/INST] yeah, I think like, you know, it's definitely sad whenever these groups are fighting each other um Yeah, like it's definitely good for them too, like if people can cooperate more. Um but you know, at the same time, like, just having, like groups of people that have, you know, different kinds of life experiences, like, you know, there's definitely something to benefit from that. </s> |
<s>[INST] What, again, a wild question and thank you for entertaining them. Entertaining them, I really, really appreciate that. But what kind of signal in our lifetime, [/INST] what kind of thing do you think might happen could possibly happen? Entertaining them, </s><s>[INST] I really, really appreciate that. Where the scientific community would be convinced that there's alien civilizations out there. And what, so you already said maybe a strong infrared [/INST] signature for something like a Dyson Sphere. Yeah, that's possible, that's also to some degree </s><s>[INST] a little bit ambiguous because- That's the challenge, sorry to interrupt, is where your brain would be, like you as a scientist, would be like, I know it's ambiguous, but this [/INST] is really weird. Yeah, I think if you had some, I can imagine something like a prime number sequence or a mathematical sequence, like the Fibonacci series, something being broadcast. Mathematically provable that this is not a physical phenomenon. Right, I mean, yeah, prime numbers is a pretty good case because there's no natural phenomena that produces prime number sequences. It seems to be a purely abstract mathematical concept as far as I'm aware. And so if we detected a series of radio blips that were following that sequence, it would be pretty clear to me, or it could even be, you know, Carl Sagan suggested that Pi could be encoded in that, or you might use the hydrogen line, but multiply by Pi, like some very specific frequency of the universe, like a hydrogen line, but multiply it by a abstract mathematical constant that would imply strongly that there was someone behind the scenes operating that. </s><s>[INST] Sorry, I stored in which phenomena though? [/INST] That's a bit of a radio wave, but the information, I mean, we kind of toyed with this idea in a video I did about hypothetical civilization on my channel. But one kind of fun way, I do want to bring this conversation towards time a little bit, and thinking about, not just looking for life and intelligence around us right now, but looking into the past and even into the future, to some degree, or communicating with the future. And so we had this fun experiment of imagining a civilization that was born at the beginning of the history of the galaxy and being the first and what it would be like for them. And they were desperately searching for evidence of life, but couldn't find it. And so they decided to try and leave something behind for future civilizations to discover, to tell them about themselves. But of course, a radio signature is not going to work there because it has have a power source and that's a piece of machinery. It's going to eventually break down. It's going to be hard to maintain that for billions of years time scale. And so you wanted something that was kind of passive, that doesn't require an energy source, but can somehow transmit information, which is hard to think about something that satisfies those criteria. But there was a proposal by one of my colleagues, Luke Arnold, which inspired a lot of us in Technosignatures. And he suggested that you could build artificial transistors. So you could build sheets of material that transit in front of the star, maybe one thin sheet passes across first, then two, then three, then five and seven. So you could follow the prime number sequence of these. And so there'd be a clear indication that someone had manufactured those, but they don't require any energy source because they're just sheets of material in orbit of the star. They would eventually degrade from micrometeorites. Maybe they're always become destabilized, but they should have lifetimes far exceeding the lifetime of any battery or mechanical electronic system that we could, at least without energy, conceive of building. And so you can imagine then extending that and how could you encode not just a prime number sequence, but maybe in the spatial pattern of this very complex light curve we see, you could encode more and more information through 2D shapes and the way those occupations happen. And maybe you could even encode messages and in-depth information from that. You could even imagine it being like a lower layer of information, which is just the prime number sequence, but then you look closely and you see the smaller divots embedded within those that have a deeper layer of information to extract. And so to me, something like that would be pretty compelling that there was somebody who would manage, unless it's just a very impressive hoax, that would be a pretty compelling evidence. In this civilization. </s><s>[INST] And actually the methods of astronomy right now are kind of marching towards being able to better and better detect a signal like that. [/INST] Yeah. I mean, to some degree, it's just building bigger aperture in space, the bigger the telescope, the finer ability to detach those minute signals. </s><s>[INST] Do you think the currents of the scientific community, another weird question, but just the observations that are happening now, do you think they're ready for a prime number sequence? If we're using the current method, the transit timing variation method, do you think you're ready? Do you have the tools to detect the prime number sequence? [/INST] Yeah, for sure. I mean, there's 200,000 stars that Kepler monitored and it monitored them all the time. It took a photo of each one of them every 30 minutes, measured their brightness, and it did that for four and a half years. And so you have already, and TESS is doing it right now, another mission. And so you have already an existing catalog and people are genuinely scouring through each of those light curves with automated machine learning techniques. We even developed some on our own team that can look for weird behavior. We wrote a code called the weird detector, for instance. It was just the most generic thing possible. Don't assume anything about the signal shape. Just look for anything that repeats. The signal shape can be anything, and we kind of learn the template of the signal from the data itself, and then it's like a template matching filter to see if that repeats many, many times in the data. And so we actually applied that and found a bunch of interesting stuff, but we didn't see anything that was the prime number sequence, at least in the Kepler data. That's 200,000 stars, which sounds like a lot, but compared to 200 billion stars in the Milky Way, it's really just scratching the surface. </s> |
<s>[INST] at the macroscopic. Mean, there's so many interesting things at the macroscopic level, they may only exist at the macroscopic level, like we already talked about consciousness, that that very well could be one of the things you mention time travel. So, um I mean according to Einstein and in general, what types of travel do you think our physical universe allows? [/INST] It certainly allows time travel to the future And I'm not talking about the silly thing that you and I are now going into the future. Second by Second by Second, I'm talking about really the diversion that you see in Hollywood at least in terms of its net effect whereby an individual can follow an Einsteinian strategy and propel themselves into the future in some sense more quickly. So if I wanted to see what's happening on planet earth, one million years from now. Einstein tells me how to get one million years from now, build a ship, I gotta turn to guys who know how to build stuff, I can't do it. Like you build a ship that can go out into the universe near the speed of light, turn around and come back, let's say it's a six month journey out, a six month journey back and Einstein tells me how fast I need to travel, how close to the speed of light I need to go, so that when I step out of my ship, it will now be one million years into the future on planet Earth. And this is not a controversial statement, right? This is not something where there's differences of opinion in the scientific community, any scientist who knows anything about what Einstein taught us, agrees with what I just said. It's it's commonplace, it's bread and butter physics. And so that kind of travel to the future is absolutely allowed by the laws of physics. There are engineering challenges, their their technological challenges this part. Yeah. And there are there even biological challenges right there, g forces that you're going to experience, you know? So there's all sorts of stuff embedded in this, but those I will call the details and those details notwithstanding, the universe allows this kind of travel to the future. </s><s>[INST] And the fact that pause real quick, you can also at the macro level with biology extend the human lifespan to do a kind of travel forward in time if you expand how long we live. That's a way to, from a perspective of an observer, a conscious observer, that as a human being, you're essentially traveling forward in time by allowing yourself to live long enough to see the thing. So that's in the space of biology. What about traveling back in [/INST] time? Yeah, that's the that is a natural next question. Especially if you uh if you're doing if you're going on one of these journeys, is it a one way journey, can you, can you come back and the physics community doesn't speak with a unified voice on this as yet, but I would say that the dominant perspective is that you cannot get back now, having said that there are proposals that serious people have written papers on regarding hypothetical ways in which you could travel to the past and we've seen some of these again, Hollywood loves to take the most sexy ideas of physics and build narratives around them. This idea of a wormhole like Jodie Foster in contact, went through a wormhole, Deep Space Nine Star, I'm sure there are many other examples where these ideas that have probably never even seen, but with wormholes there's at least a proposal of how you can take a wormhole tunnel through space time, manipulate the openings of the wormhole in such a way that the openings are no longer synchronous, they are out of sync relative to each other, which would mean ones ahead and one's behind, which means if you go through one direction you travel to the future. If you go back, you travel to the past now, we don't know if there are wormholes </s><s>[INST] possible [/INST] according to Einstein, they are possible according to Einstein, but even Einstein was very quick to say just because my math allows for something doesn't mean it's real, and he famously didn't even believe in black holes, didn't believe in the big bang, right, And yet the big black hole issue has really been settled. Now we have radio telescopic photographs of the black hole in M 87 is in newspapers around the world just a couple of years ago. So, so it's just to say that just because it's in Einstein's math, um it doesn't mean it's real, but yes, it is the case that wormholes are allowed by Einstein's equations and in principle you can imagine, you know, putting electric charges on the openings of the wormhole, allowing you to tow them around in a matter that could yield this temporal asymmetry between them, maybe toe, one of the mouth to the edge of a black hole. In principle, you can do this slowing down the passage of time, near that black hole and then when you bring it back it will be well out of sync with the other opening and therefore it could be a significant temporal gap between one and the other, but people who studied this in more detail question, could you ever keep a wormhole open assuming it does exist, could you have a travel through a wormhole or would there be a requirement of some kind of exotic matter to prop it open that perhaps doesn't exist. So there are many, many issues that people have raised. And I would say that the general sentiment is that it's unlikely that this kind of scenario is going to survive our deeper understanding of physics when we finally have it, but that doesn't mean that the door is closed. So maybe it's a small possibility that this could one day be. That's </s> |
<s>[INST] and that was a Nike shoes he [/INST] was wearing. Yeah, yeah. So what makes it kind of Controversial or difficult is Nike came out with these prototypes. So prototype for people don't understand shoes, like these companies will develop a shoe and it usually takes like somewhere in the neighborhood of like probably 18 months to hit the market. So if you're like if sponsored athlete or work for the company, you can get your hands on these shoes before they actually come to market. So we had an issue, I think this wasn't necessarily as big of an issue in the ultra running community. But uh, in the track and field olympic distance stuff was a big issue because you had Nike athletes having these prototype shoes before anyone could get them and then you had athletes were sponsored by these other brands who couldn't wear them, even if even when they did come to market. So then we had this like chase to catch up where other companies are starting to make their own version of it. And now we're getting to a point where most companies have a version of that shoe. Um, but we had a huge transition phase that impacted the olympics big time. I mean, think of here, here's a, here's an example of it. Uh, there's a, there was an athlete Kerri Gaucher. Um, she was not, she was a Nike athlete wasn't when they came out with a shoe and she ran the olympic trial marathon and got fourth place, the first person out and two of the people had ever had that shoe on. And she was maybe a minute or two, I'd have to look to see exact, but it was within the performance advantage range. So you could argue that she was the first person in modern running to lose an olympic spot due to a technological disadvantage, wow. And it's like, I mean it's one of those Yeah, I mean it's one of those things where like, um, it's, it's a transition, right? So there's gonna be bumpy road and there's gonna be people that get caught in that transition that it's unfortunate for. But it's also like, uh, you know, once everything does catch up in every shoe company has a version of this, there's still problems. I mean, these are incredibly expensive shoes, it's like a $250 shoe. So it's like, at what point do you tell like A wealthy family with a high school kid that, you know, you can get that $200 shoe, but then you go and this kid's family can barely afford a parachute for them, much less a $250 parachutes. Like where do we draw that line and that sort of stuff? Um, Also, just here is the other big one. Like let's 2-8% is a massive range. What if you're on the 2% versus someone's on the 8%? You know, chances are if you're, you know, blowing a record out of the water, you're probably closer to that high end percentage versus someone who's maybe getting incremental gains are probably closer to that lower end. So is it fair to have a piece of equipment that has that big of a range when we're talking about less than a percent determining these races when all is held constant. </s><s>[INST] Those are fascinating philosophical questions that I think it's nice to solve that for the shoe or to raise those questions for a shoe because the more complicated place where they will be raised is probably like genetics, genetic engineering, all those kinds of things, [/INST] you'll get a lot more </s><s>[INST] complicated. So it's nice when you have like a particular piece of technology that's just like right there. It's a shoe, we can understand it. We can study [/INST] it. We may be coming on the precipice of like human powered sport, performance is no longer being something that we like look at as this like pinnacle of uh like I don't maybe entertainment is the wrong word but like is that a pursuit? You know, do we end up just going a different direction? I mean I think it's like it's so hard for us to think about that right now because it's so part of like the culture and the lifestyle of the average person where like sport is a hobby of theirs as well as a passion to follow. Its like how complicated doesn't need to get before people lose that interest. And </s><s>[INST] there could be a future where most of the olympics is E. Sports. Somebody told me that e sports is in the olympics have been meaning to look this up. Which is you know like what video, video games on the olympics. Yeah it could be as like a trial that they're doing. Um If this is true. Um trying real time, look it up. But if this if this e sports joining Olympics in 2024, wow. So that could be just a that could be a fun side thing but it could be a first step into a complete transformation what sports mean. You can control video games better. They control for genetics and humans. [/INST] Well in reality we've been dealing with this problem in other areas just with the performance enhancing side of things with drugs and all that stuff too. And that that conversation's flared back up with track and field to where we are seeing. A lot of records were broken. A lot of it probably is to shoot technology, but you know, in 2000 and 20 with the covid stuff, you have all these out of competition testing protocols that a lot of these top tier olympic athletes are getting uh, to try to eliminate like, like if you just do inter competition testing, like there's potential for people to do things that are going to give him a performance advantage, but not going to show up on that test on the day of or after their race. Where now you have these like limitations of being able to test. So do we have a like a group of athletes now who decided I'm not going to get tested in 2022. The covid restrictions. This is the time to dope up and then, you know, hit some stride and some records and then taper back off when they get this thing fired back up again. And so there may be some of that as well. And I mean that's always been an ongoing problem. And </s> |
<s>[INST] So from the perspective of computer science, you've got a chance to work the application to cancer into medicine in general from a perspective engineer and computer scientist, how far along are we from understanding the human body biology of being able to manipulate it in a way we can cure some of the melodies some of the diseases. [/INST] So this is very interesting question. And if you're thinking as a computer scientist about this problem, I think one of the reasons that we succeeded in the areas where as a computer scientist succeeded is because we don't have, we're not trying to understand in some ways, like if you're thinking about like e commerce amazon amazon doesn't really understand you and that's why it recommends you certain books or certain products correct and uh you know traditionally when people were thinking about marketing, you know, they divided the population, two different kind of subgroups, identify the features of the subgroup and come up with a strategy which is specific to that subgroup. If you're looking about recommendation systems are not claiming that their understanding, somebody there just managing to from the patterns of your behavior to recommend your product. Now, if you look at the traditional biology, obviously I wouldn't say that I uh at any way, you know, educated in this field, but you know what they see that it's really a lot of emphasis on mechanistic understanding. And it was very surprising to me coming from computer science how much emphasis is on this understanding and given the complexity of the system, maybe the deterministic full understanding of this process is is, you know, beyond our capacity. And the same way as in computer science when we're doing recognition when the recommendation and many other areas, it's just probabilistic matching process. And in some way maybe uh in certain cases we shouldn't even attempt to understand and we can attempt to understand, but in parallel we can actually do this kind of matching that would help us to find a cure or to do early diagnostics and so on. And I know that in these communities it's really important to understand, but I'm sometimes wondering what exactly does it mean to understand here? </s><s>[INST] Well, there's stuff that works and but that can be like you said separate from this deep human desire to uncover the mysteries of the universe, of of science, of the way the body works, the way the mind works. It's the dream of symbolic i of being able to reduce human knowledge into into logic and be able to play with that logic in a way that's very explainable and understandable for us humans. I mean that's a beautiful dream. So I I understand it, but it seems that what seems to work today and we'll talk about it more is as much as possible to reduce stuff into data, reduce whatever problem you're interested in to data and try to apply statistical methods, apply machine learning to that. And on a personal note, You were diagnosed with breast cancer in 2014. What it facing your mortality make you think about how did it change you? [/INST] This is a great question. And I think that I was interviewed many times and nobody actually asked me this question. I think I was 43 at a time and it's the first time I realized in my life that I may die. And I never thought about it before. And there was a long time since you diagnosed until you actually know what you have and have CV is your disease for me. It was like maybe 2 1/2 months. And I didn't know where I am during this time because I was getting different tests and one would say it's bad and I was you know, it is not. So until I knew where am I really was thinking about all these different possible outcomes. </s><s>[INST] Are you imagining the worst or were you trying to be optimistic or [/INST] it would be really I don't remember what was my thinking. It was really a mixture with many components at the time. Speaking, you know, in our terms. And one thing that I remember and you know, every test comes and you're saying, oh, it could be there. So it might not be this and you're hopeful and then you're desperate. So it's like there is a whole you know, slow of emotions that goes through. But what I remember that when I came back to MIT I was kind of going the whole time to the treatment to Emmett but his brain was not really there. But when I came back really finished my treatment and I was here teaching and everything. You know, I look back at what my group was doing, what other groups was doing. And I saw these trivialities. It's like people are building their careers on improving some parts around two or 3% or whatever. I was like, seriously, I didn't work on how to decide for eukaryotic, like a language nobody speak and whatever, like what is significant. When I was suddenly, you know, I walked out of MIT which is you know, when people really do care. You know what happened to you a clear paper, you know, what is your next publication uh to a cl to the world where people, you know, people you see a lot of suffering that I'm kind of totally shielded on it on daily basis. And it's like the first time I've seen like real life and real suffering. And I was thinking why we're trying to improve the parcel or deal with some trivialities when we have capacity to really make change. And it was really challenging to me because on one hand, you know, I have my graduate students really want to do their papers and their work and they want to continue to do what they were doing, which was great. And then it was me who really kind of reevaluated what is the importance. And also at that point, because I had to take some break. I uh Look back into like my years in science and I was thinking, you know, like 10 years ago, this was the biggest thing, I don't know, topic models that we have like millions of papers on topic models and variation topics. Models. And I was really like irrelevant. And you start looking at this, you know, what do you perceive as important, a different point of time and how, you know, it's fades over time. And uh since we have a limited time of us have limited time on us. It's really important to prioritize things that really matter to you maybe matter to you at that particular point, but it's important to take some time and understand what matters to you, which may not necessarily be the same as what matters to the rest of your scientific community and pursue that vision. </s> |
<s>[INST] That's interesting. I mean the so say there's a lot of aliens out there in the universe. Each each set of organisms will probably have like a number you know like Erdos number of like how far like how far our common ancestors and so the close to the common ancestor like it is on earth, the more like each other, the more likely we are to be able to have sexual reproduction. [/INST] Well it's sort of like humans have in common culture and languages. Right. </s><s>[INST] Exactly. Language communication and that [/INST] might take a lot of work with inhaling because you really have to get over a language barrier </s><s>[INST] boy. So says communication is uh resources. I mean the whole and I think tied into that is the questions of like who is going to harm who and [/INST] actually definitions apartment </s><s>[INST] where they question whether the common ancestor approves. Yeah, it's just very true. Uh, how many alien civilizations do you think are out there? [/INST] I don't have intuition for that. Um, which I, I have always thought was deeply intriguing. So, and part of this, uh, I mean I say specifically as I don't have intuition for that because it's like one of those questions that you feel around for a while and you really just, you, you can't see it um, even though it might be right there. And um in that sense, it's a little like the quantum to classical transition, you're like really talking about two different kinds of physics and I think that's kind of part of the problem. Once we understand the physics, that question might become more meaningful. Um, but there's also this other issue. Um, uh, and this was really instilled in me by my mentor paul Davies when I was a postdoc because he always talks about how, you know, whether aliens are common or rare is kind of just um, you know, it's like, you know, it follows a wave of popularity and it just depends on like the mood of, you know what the culture is at the time. And I always thought that was kind of an intriguing observation, but also there's this, you know, set of points about if you go by the observational evidence which were supposed to do with scientists, right? Um, uh, you know, we have evidence of us. Um, and one original life event from which we emerged and people want to make arguments that because that event was rapid. Um or because there's other planets that have properties similar to ours, that that event should be common, but you actually can't reason on that because our existence, observing that event is contingent on an event happening, which means it could have been completely improbable or very common. Um and Brendan carter like clearly articulated that in terms of anthropic arguments um a few decades ago. So, so there is this kind of issue that we have to contend with dealing with life that's closer to home than we have to deal with with any other problems in physics, which we're talking about the physics of ourselves. And when you're asking about the origin of life event, that event happening in the universe at least as our existence is contingent on it. Um and so you can think about sort of fine tuning arguments um that way too. So um but the sort of otter part of it is like when I think about how likely it is, I think it's because we don't understand this mechanism yet about how information can be generated spontaneously that I like because I can't see that physics clearly yet, even though I have a lot of, you know like some things around the space of it in my mind, I can't articulate how likely that processes. Um So my honest answer is I don't know, and sometimes it feels like a cop out, but I feel like that's a more honest answer in a more meaningful way of making progress then, um, what a lot of people want to do, which is say, oh, well we have a one in 10 chance of having an exoplanet with earth like properties because there's lots of earth like planets out there and life happened fast on </s><s>[INST] earth. Well, so kind of a follow up question, but as a side comment, what I really am enjoying about the way you're talking about human beings is you always say, and not to make your self conscious about it because I really, really enjoy it. Do you say? We you don't say humans you say, because oftentimes like, you know, I don't know, evolutionary biologists will kind of put yourself out as an observer, but you're, it's kind of fascinating to think that you as a human struggling about your own origins. [/INST] Yes, that's the problem. And yeah, and I think, um, I don't do that deliberately, but I do think that way, and this is sort of the inversion from the logic of physics, because physics as it's always been constructed, has treated us as external observers of the universe and we are not part of the universe and this is why the problem of life, I think demands completely new thinking because we have to think about ourselves as minds that exist in the universe and are at this particular moment in history and looking out at the things around us and trying to understand what we are inside the system, not outside the system. We don't have descriptions at a fundamental level that describes us as inside the system. And this was my problem with cellular automata. Also, you're always an external observer for a cellular automata, you're not in the system. What does the cellular automata look like from the inside? </s><s>[INST] I think you just broke my brain with that question. Exactly. But that's [/INST] a long </s> |
<s>[INST] This episode is brought to you by Element, spelled L-M-N-T. It's an electrolyte drink mix that I'm currently drinking that I drink throughout the day. I drink a huge amount of it. My favorite flavor is the watermelon salt flavor. It doesn't mean it will be your favorite flavor, but I'm pretty sure it's gonna be your favorite flavor. For fasting, for low carb diets, for all kinds of diets, really, but certainly for low carbohydrate keto carnivore, you have to get the electrolytes right. They call it the keto flu if you don't get the electrolytes right. You know for doing all kinds of crazy exercise that I do, all of that. You have to get the sodium, the potassium, magnesium, and element. Great job of balancing all of that. Makes it delicious. Makes it really easy to make sure [/INST] that you're getting just the water intake right. I enjoy this. </s><s>[INST] Element doesn't, because it basically makes water taste great and balances out the electrolytes, the hydration, everything for you. I bring it, when I travel, I bring it anywhere I go. I have to have element as part of my life. It makes me happy. It makes me feel like I got my stuff together. Anyway, get a simple pack for free with any purchase. Try it at drinkelement.com slash Lex. This show is also brought to you by NetSuite, an all-in-one cloud business management system. You can manage financials, HR, inventory, e-commerce if you do that kind of thing, and many business-related details. Running a company is really complicated. There's a lot of people involved, a lot of tasks involved, a lot of roles involved. It's not just engineering. It's not just design, idea, strategy, vision, all those kinds of things. It's all of the glue, the thing that makes the thing a cohesive, singular system that works efficiently and flawlessly. And so you have to hire the right people. You have to use the best tools for the job. NetSuite does that in the cloud to manage all kinds of messy business details and make it super easy. You can start now with no payment or interest for six months. Go to netsuite.com slash Lex to access their one-of-a-kind financing program. That's netsuite.com slash Lex. This episode is also brought to you by BetterHelp. It's spelled H-E-L-P, help. They figure out what you need and match you with a licensed professional therapist in under 48 hours. Talking to somebody through all the difficult things that are going through your mind, taking those thoughts, taking those memories, converting them into words and letting those words leave your mouth sounds somehow transforms your own understanding of what those memories, those thoughts mean. It allows you to move past them, to integrate them into a healthier, a deeper understanding of the world around you, your own emotions of your own way of being. It's kind of amazing that talk therapy, that talking, talking with a person that knows what they're doing is a powerful way to do that kind of growth. It's funny and it's amazing when simple things like therapy can have a big profound impact, results on your life. Anyway, one of the big things about BetterHelp is just how easy it is to get started. I think that's a barrier for a lot of people. So it's really important to say this, easy, discreet. It is affordable and it's available everywhere worldwide. Check them out at betterhelp.com slash Lex and save on your first month. That's betterhelp.com slash Lex. This is a Lex Friedman podcast to support it. Please check out our sponsors in the description. And now, dear friends, here's Neil Gershenfeld. You have spent your life working at the boundary between bits and atoms, so the digital and the physical. What have you learned about engineering and about nature reality from working at this divide, [/INST] trying to bridge this divide? I learned why von Neumann and Turing made fundamental mistakes. I learned the secret of life. Yeah. I learned how to solve many of the world's most important problems, which all sound presumptuous, </s><s>[INST] but all of those are things I learned at that boundary. Okay, so Turing and von Neumann, let's start there. Some of the most impactful, important humans [/INST] who have ever lived in computing, why were they wrong? Were they wrong? So I worked with Andy Gleason, who is Turing's counterpart. So just for background, if anybody doesn't know, Turing is credited with the modern architecture of computing, among many other things. Andy Gleason was his US counterpart. And you might not have heard of Andy Gleason, but you might have heard of the Hilbert problems. And Andy Gleason solved the fifth one. So he was a really notable mathematician. During the war, he was Turing's counterpart. Then von Neumann is credited with the modern architecture of computing, and one of his students was Marvin Minsky. So I could ask Marvin what Johnny was thinking, and I could ask Andy what Alan was thinking. And what came out from that, what I came to appreciate as background, I never understood the difference between computer science and physical science, but Turing's machine that's the foundation of modern computing has a simple physics mistake, which is the head is distinct from the tape. So in the Turing machine, there's a head that programmatically moves and reads and writes the tape. The head is distinct from the tape, which means persistence of information is separate from interaction with information. Then von Neumann wrote deeply and beautifully about many things but not computing. He wrote a horrible memo called the first draft of a report on the EdVAC, which is how you program a very early computer. In it, he essentially roughly took Turing's architecture and built it into a machine. So the legacy of that is the computer somebody's using to watch this is spending much of its effort moving information from storage transistors to processing transistors, even though they have the same computational complexity. So in computer science, when you learn about computing, there's a ridiculous taxonomy of about a hundred different models of computation, but they're all fictions. In physics, a patch of space occupies space, it stores state, it takes time to transit, and you can interact. That is the only model of computation that's physical. Everything else is a fiction. So I really came to appreciate that a few years back when I did a keynote for the annual meeting of the supercomputer industry and then went into the halls and spent time with the supercomputer builders and came to appreciate, oh, let's see, if you're familiar with the movie, The Metropolis, people would frolic upstairs in the gardens and down in the basement, people would move levers. And that's how computing exists today, that we pretend software is not physical, it's separate from hardware, and the whole canon of computer science is based on this fiction that bits aren't constrained by atoms, but all sorts of scaling issues in computing come from that boundary, but all sorts of opportunities come from that boundary. And so you can trace it all the way back to Turing's machine making this mistake between the head and the tape. Van Neumann, he never called it Van Neumann's architecture, he wrote about it in this dreadful memo, and then he wrote beautifully about other things we'll talk about. Now, to end a long answer, Turing and Van Neumann both knew this. So all of the canon of computer scientists credits them for what was never meant to be a computer architecture. Both Turing and Van Neumann ended their life studying exactly how software becomes hardware. So Van Neumann studied self-reproducing automata, how a machine communicates its own construction. Turing studied morphogenesis, how genes give rise to form. They ended their life studying the embodiment of computation, something that's been forgotten by the canon of computing, but developed sort of off to the sides </s> |
<s>[INST] So there's in the face of that uncertainty, there's something admirable like it was with prefontaine or you take the risk and run faster than you know, you you think you might be able to run in terms of pace that you can hold, so push the pace that's possible. [/INST] Yeah, explore the unknown. It's like a pioneer spirit, right? Yeah, the next frontier kind of a thing. But I mean prefontaine also, there's other angles with him to where he was like in the amateur era where to be an Olympian, you couldn't be pro. So he's turning down, I mean the guy was on food stamps and living in a trailer because he wanted to run at the olympics and there was a lot of like politics involved with not being able to take, take sponsorship money and things like that, which has changed since then. But uh, so he was huge in the movement for that to kind of like, you know, have a situation where now as an athlete you can finish in most cases, finish college, sign a big contract with, you know, a sponsor and then also still compete in the olympic games and go to the events that are actually ones that are gonna likely catapult your career and most of the olympic distance endurance events. So, so he just revolutionized the sport and then to add even more flavor to the whole thing. I mean he died of a very premature death. He got a car accident and died before he would have likely probably medaled at the olympics. So he and there </s><s>[INST] is a tragedy of the fact that he didn't. [/INST] Yeah, well he was fourth place at the olympics. The prior, his first go of it. And it was kind of one of those things where it's like fourth place at the olympics is the first man looking out of the first woman looking out and for a guy that had as much hype as him I think like a medal was something he really wanted to take home with him there and </s><s>[INST] especially how that race went. I mean, yeah, I don't know, it's tragic the whole thing. But that's one of the things that makes olympics amazing is the tragedy of it. Like one race decides the story of a lifetime. She's [/INST] like, yeah, </s><s>[INST] that's why it's that's why it's amazing even if a lot of people get hurt because of it. Tragedy makes the triumph special, [/INST] right? Yeah. Well it makes it makes life like a movie almost exactly if everything's all sunshine and rainbows and it's not as entertaining to watch. There's no adversity to overcome. </s><s>[INST] You mentioned shoe technology, how much has shoe technology advanced through the past few decades. How much has it changed running generally, But also running like ultra marathon running [/INST] I would say an ultra running, it's had much of a less of an impact because ultra running is still heavily skewed towards the trails. So the technology, at least from what we know, isn't necessarily translating over to these massive, very terrain. Certainly not the technical terrain and things like that. Now on road races, flat stuff like the track stuff, the roads, the run, I guess you run double trail, um where it was like basically crushed limestone, more or less, uh, you definitely get an advantage from it. It's uh, And essentially what, what happened, um, is in this probably dated back actually before 2 2015. you know, Nike decided, well, their their their their development team uh, was ahead of the curve. They've developed this new foam called like a payback foam. Uh, and they realized that like when you step down into </s><s>[INST] a shoe, the reason [/INST] like, uh, race, there's a lot of times would wear these flats because they're trying to take out any of that lost energy into the foam in the shoe. Well, this foam that Nike came out with is so good that it actually returns way more energy than the average foam did to the point where like when they test these things on like force plate treadmills and things like that, it's like a depending on the person's gate And something like a 2-8% improvement in performance. I mean, we've seen records just across the board get broken since this came out all distances basically. Yeah. Yeah. I think from at least from the five k up through the marathon and I mean we've seen some insane improvements in the marathon. I think like the women's marathon went from What was considered relatively untouchable, like to 16 to a to 14. And I mean like it was like to 18 was like just world class. Like if you could run into 18 marathon as a woman, that was like, I mean it still is to a degree, but then, you know, you have someone to 14, like you attribute </s><s>[INST] a lot of that to the shoe. Yeah. [/INST] Yeah. I think there's probably other things that come in mind to like now that people know there's a performance advantage from a mechanical standpoint. It's also a confidence thing where it's like, oh no, I can probably try going five seconds per mile faster and maybe they could have anyway. And they just, now they think they can, so they are. So there's probably a little bit of that that's just adding to it. </s><s>[INST] Do you think there's a lot of extra innovation that's still possible? Like what if you could do this kind of big leap, uh, with the little innovation of foam? Is there other stuff that you can do or for the innovation of materials that make up the phone? [/INST] Yeah. So they can definitely go much more advantage. They put a cap on it essentially. So there was, there is also a carbon plate element to this, to where they put like this carbon plate in there in between the foam. So like I believe when when Kipchoge e broke, well when they did that, that, that kind of uh, the sub to our project, he actually had on a shoe. If I'm not mistaken, that never got to market because they put down some parameters on it. After before that one came to market where it was actually like stacked up to, I can't remember how many millimeters was an insane amount. And they had like, I think maybe even three layer plates in there </s> |
<s>[INST] I think we're going to get into language, we're going to get into communication, intelligence and neural networks and so on. But let me return to the high level the futuristic for for a brief moment. So you've written in your book, your new book, It would be arrogant to suppose that we could forecast where Ai will be where the impact will have in 1000 years or even 500 years. So let me ask you to be arrogant uh what do AI systems with or without physical bodies look like 100 years from now, If you would just uh you can't predict. But if you were to classify eyes and imagine, do can [/INST] I first justify the arrogance before you try to push me beyond it? I mean, there are examples like, you know, people figured out how electricity works. They had no idea that that was going to lead to cell phones, right? I mean, things can move awfully fast once new technologies are perfected even when they made transistors, they weren't really thinking that cell phones would lead to social networking. </s><s>[INST] There are nevertheless predictions of the future which are statistically unlikely to come to be but nevertheless [/INST] is asking me to be wrong. </s><s>[INST] Asking [/INST] you to be way, would I like to be wrong, </s><s>[INST] pick the least unlikely to be wrong thing, even though it's most very likely to be wrong. [/INST] I mean here's some things that we can safely predict. I suppose we can predict that ai will be faster than it is now. It will be cheaper than it is now. It will be better in the sense of being more general and applicable in more places. It will be pervasive. Yeah, I mean, these are easy predictions that I'm sort of modeling them in my head on um Jeff Bezos is famous predictions. He says I can't predict the future. Not in every way I'm paraphrasing but I can predict that people will never want to pay more money for their stuff. They're never going to want to take longer to get there. And you know, so like you can't predict everything, but you can predict something sure. Of course it's going to be faster and better and well, we can't really predict is the full scope of of wary I will be in a certain period. I mean, I think it's safe to say that although I'm very skeptical about current day, I it's possible to do much better. There's no in principle argument that says ai is an insolvable problem that there's magic inside our brains that will never be captured. I mean, I've heard people make those kind of arguments, I don't think they're very good. So ai is going to come and Probably 500 years of planning to get there, and then once it's here it really will change everything. </s><s>[INST] So when you say, yeah, it's going to come. Are you talking about human level intelligence? So maybe I [/INST] like the term general intelligence, so I don't think that the ultimate ai if there is such a thing is going to look just like humans, I think it's going to do some things that humans do better than current machines, like reason flexibly, um and understand language and so forth, but that doesn't mean they have to be identical to humans. So for example, humans have terrible memory and they suffer from what some people call motivated reasoning, so they like arguments that seem to support them and they dismiss arguments that they don't like, there's no reason that a machine should ever do that. </s><s>[INST] So you see that those limitations of memory as a bug, not a feature. [/INST] Absolutely, I'll say two things about that one is I was on a panel with Danny Kahneman, the Nobel Prize winner last night and we were talking about this stuff and I think, you know, we converged on is that the humans are a low bar to exceed. They may be outside of our skill right now, but as you know, ai programmers, but eventually I will exceed it. So we're not talking about human level ai we're talking about general intelligence that can do all kinds of different things and do it without some of the flaws that human beings have. The other thing I'll say is I wrote a whole book actually about the flaws of humans. And it's actually a nice bookend to the counterpoint to the current book. So I wrote a book called Cluj which was about the limits of the human mind. Current book is kind of about those few things that humans do a lot better than machines. </s><s>[INST] Do you think it's possible that the flaws of the human mind the limits of memory, our mortality, our bias is a strength not a weakness. That that is the thing that enables from which motivation springs and meaning springs are [/INST] part of a lot of arguments like this. I've never found them that convincing. I think that there's a lot of making lemonade out of Lemons. So we for example do a lot of free association where one idea just leads to the next and they're not really that well connected and we enjoy that and we make poetry out of it and we make kind of movies with free associations and it's fun or whatever. I don't I don't think that's really a virtue of the system. I think that the limitations and human reasoning actually get us in a lot of trouble. Like for example politically we can't see eye to eye because we have the motivational reason I was talking about and something related called confirmation bias. So we have all these problems that actually make for a rougher society because we can't get along because we can't interpret the data in shared ways and then we do some nice stuff with that. So my free associations are different from yours and you're kind of amused by them and that's great. And hence poetry. So there are lots of ways in which we take a lousy situation and make it good. Another example would be our memories are terrible. So we play games like concentration where you flip over two cards, try to find a pair. You imagine a computer playing that computers like this is the dullest game in the world. I know where all the cards are. I see it once. I know where it is. What are you even talking about when we make a fun game out of having this terrible memory. </s> |
<s>[INST] Good. Good. Good. I love this. I love this. Good. [/INST] So the WHO is an absolutely essential organization created in 1948 in that wonderful period after the Second World War when the United States and allied countries asked the big, bold questions, how do we build a safer world for everyone? And so that's the WHO. Although there are many critics of the WHO, if we didn't have it, we would need to invent it because the whole nature of these big public health issues, and certainly for pandemics, but all sorts of things, is that they are transnational in nature. And so we cannot just build moats. We cannot build walls. We're all connected to us. So that's the idea. There's a political process because the United Nations and the WHO as part of it, it exists within a political context. And so the current director general of the World Health Organization, who was just reelected for his second five-year term, is Dr. Tedros Adanom Gabriesus, who is from Ethiopia, Tigrayan from Ethiopia. And in full disclosure, I have a lot of respect for Tedros. Tedros got his job. He was not America's candidate. He was not Britain's candidate. Our candidate was a guy named David Nabarro, who I also know and have tremendous respect for. China led the process of putting Tedros in this position. And in the earliest days of the pandemic, Tedros, in my view, even though I have tremendous respect for him, I think he made a mistake. The WHO doesn't have its own independent surveillance network. It's not organized to have it, and the states have not allowed it. So it's dependent on member states for providing it information. And because it's a poorly funded organization dependent on its bosses who are these governments, its natural instinct isn't to condemn its bosses. It's to say, well, let's quietly work with everybody. Having said that, the Chinese government knowingly lied to Tedros. And Tedros, in repeating the position of the Chinese government, which incidentally, I'll say Donald Trump also did the exact same thing. Donald Trump had a private conversation with Xi Jinping and then repeated what Xi had told him. Both of them were wrong. Dr. Tedros, I think when it took, when Chinese government was lying, knowingly lying, saying there's no human to human transmission, Dr. Tedros said that. And even though within the World Health Organization, there were private critiques saying China is now doing exactly what it did in SARS-1. It's not providing access. It's not providing information. Tedros' instinct, because of his background, because of his role and wrongly, was to have a more collaborative relationship with China, particularly by making assertions based on the information that was wrong. </s><s>[INST] Don't call people liars. They're not going to be happy with you. [/INST] They're not going to be happy. And the job of the WHO isn't to condemn states, it's to do the best possible job of addressing problems. And I think that the culture was, well, let's do the most that we can if we totally alienate China on day one. We're in even worse </s><s>[INST] shape than if we call them out for- Not exactly sure, by the way, that maybe you can also steal them in that argument. It's not completely obvious that that's a terrible decision. If you're an eye or in that role, we wouldn't make that decision. It's complicated because [/INST] you want China on your side to help solve this. It's this. So I would have made a different decision, which is why I never would have been selected as the Director General. There's a selection criteria that everybody kind of needs to support </s><s>[INST] you. But let me just, this is just the beginning. This is just the beginning. Can you also just elaborate or kind of restate what were the inaccuracies that you quickly mentioned? So human-to-human transmission, what were the things- [/INST] That was, so the most important, there were a few things. One, China didn't report the outbreak. Two, they had the sequenced genome of the SARS-CoV-2 virus, and they didn't share it for two critical weeks. And when they did share it, it was inadvertent. I mean, there was a very, very courageous scientist who essentially leaked it and was later punished for leaking it, even though the Chinese government is now saying we were so great by releasing- </s><s>[INST] Wait, I hope it's really confusing. Really? So I'm so clueless about this as most things, because I thought, because there was a celebration of, isn't this amazing that we got the sequence, like this amazing, and then the scientific community across the world stepped up and were able to do a lot of stuff really quickly with that sharing. Because I thought the [/INST] Chinese government shared it. No, no. So they sat on it for two weeks. When they shared it against their will, it was incredible. Moderna, 48 hours later after getting the information, getting the sequenced genome, they had the formulation for what's now the Moderna COVID-19 vaccine. But that's two critical weeks. In those early days, they blocked the World Health Organization from sending its experts to Wuhan for more than three weeks. I said they lied about human-to-human transmission. During that time, they were aggressively enacting their coverup, destroying records, hiding samples, imprisoning people who were asking tough questions. They soon after established their gag order. They fought internally in the World Health Organization to prevent the declaration of a global emergency. I couldn't be stronger in my critique of China, particularly what it did in those early days. But really, what it's doing even to today is outrageous. So then there was the question of, well, how do we examine what actually happened? And the prime minister of Australia, then and now, Scott Morrison, was incredibly courageous. And he said, we need a full investigation. And because of that, the Chinese government attacked him personally and imposed trade sanctions on Australia to try to not just to punish Australia, but to deliver a message to every other country, if you ask questions, we're going to punish you ruthlessly. And that certainly was the message that was delivered. The Australians brought that idea of a full investigation to the World Health Assembly in May of 2020. As I mentioned before, the WHA is the governing authority of states above the World Health Organization. But instead of passing a resolution, calling for a full investigation, what ended up ironically and tragically passing with Chinese support was a mandate to have essentially a Chinese controlled joint study where half of the team, a little more than half of the team was Chinese experts, government affiliated Chinese experts, and half were independent international experts, but organized by the WHO. And then it took six months to negotiate the terms of reference. And again, while China was doing all this coverup, they delayed and delayed and delayed. And by the terms of reference that were negotiated, China had veto power over who got to be a member of the international group. And that group was not entitled to access to raw data. The Chinese side would give them conclusions </s> |
<s>[INST] Am I meeting those bids for connection and vice versa? Well, do those also give you a guide [/INST] of how you should behave? Well, I think what's really important is actually asking your partner or paying attention to what your partner's bids are, because what matters to Ty, my husband, may not matter to you. For instance, Ty's bar is so low with me. </s><s>[INST] Thank God for him, thank God for him. [/INST] What defines a positive interaction? Right, like he just wants me to ask him if he wants a water when I get up to get myself one. Just be a basic, decent, considerate person is all he asks of me. Whereas mine might be sort of like, stay up later with me, watch a show, go to bed at the same time as me </s><s>[INST] or know about the people in my life, that sort of a thing. I should highlight this and I hope, hopefully it's okay, that you were running a little bit late and you sent me this text, which people do really rarely, and there's a subtle act of kindness within that text. So the text you sent was that I just decreased the amount of stress in your life or something like this by saying it's cool. But that means that you're signaling that you were stressed because you care enough to be there on time. And that made me feel really special, like, oh, people don't often, people don't always do that because that puts you also, that makes you vulnerable. Vulnerable. [/INST] And that actually is by saying, people don't know. You're a brilliant guy, vulnerable. I actually thought that after I sent it, but I feel that most of the day, any interaction, like, oh God, I just exposed myself. But absolutely, I was excited to be here and I didn't want you to think that I didn't care. I think being a therapist has shown me that it really, it's so lucky to be in that position because you meet people that you would have thought are cooler than you or smarter than you or just somehow impervious to life. And you realize that we are all in it together. We all want to be cared about and liked. We don't want to be liked as a baseline. Some people will say they don't care, but everybody does. It's human. And I have gotten much better being a therapist, much more comfortable showing caring, showing love and genuineness and vulnerability </s><s>[INST] than I think I ever would have been otherwise. Any interaction like that. And that kind of vulnerability is what's required [/INST] to do a positive interaction in a relationship? I think so. And people have different levels of comfort, right? So, but as long as it's working for both partners and typically you have to communicate to figure out what your partner, what makes your partner feel cared about. However, you might be working, for instance, with an older couple, and I have a couple that's perfectly happy and they sort of have a system. It works for them. If there's some sort of a rupture, if they get in some sort of a disagreement, they don't talk it out. She might go to the store, run an errand, do a little shopping. He'll work in the wood shop. And then they'll come back and there is a repair attempt though, but it's maybe she'll say, hey, do you want to have dinner? Come, you know, I made your favorite dinner. Or he'll say, hey, I recorded your favorite show. You want to watch it tonight? So they don't need to process it, but there is an understanding between them that we're still in this together, we care about each other, and there's a repair attempt. Most people need to be able to process it verbally </s><s>[INST] and talk about what happened, but not all. So for most people, if there's a conflict, you should talk about and resolve it and repair it [/INST] versus like just put it behind you? I don't always say should, I guess it depends on the couple. Everybody processes emotions differently, everybody handles emotional expression differently. I mean, I have couples where I have one person in the partnership who has autism and the other doesn't. And so they're obviously going to have different ways of communicating or processing what happened. We all have different perspectives. It really depends on what makes a person feel like it's been repaired. What makes a person feel understood? Does that need to be verbal? Or in the case of that older couple I have where they know they understand one another </s><s>[INST] because there's a gentleness toward one another after. What are some common ways relationships fail [/INST] that you've observed in all the therapy you've had? Well, the Gomins identified what they call the four horseman of the apocalypse. So, I mean, I could just keep it simple and go off their research. So those are four different behaviors that they identify in couples or that you can identify in couples that are really highly predictive of a divorce, some more than others, but I'll start with the lower ones. So one thing that we, by the way, actually, we all do these things. These would be in that five to one ratio. You'd wanna stay away from some of these. These are the ones. So as they pile up, now that ratio is gonna get imbalanced and then you are headed for a split, okay? So the first is criticism. So criticism is when we have a complaint, complaints are normal, but instead of owning our own problems, our own feelings, we assume that our perspective is the only valid, accurate perspective. And so we take it upon ourselves to tell our partner what is wrong with them, okay? </s><s>[INST] So there's essentially no real belief [/INST] that they might have a valid perspective too. So this could look like you never helped me out in that with the house or even you're so lazy, like, can't I just get you for five seconds to help with the kids or something like that? And then what happens is horseman number two, defensiveness. So not everybody is defensive just because they were criticized. Some people just are more prone to defensiveness than others. None of us really like admitting our faults. So it's pretty natural, but defensiveness is essentially making excuses or worse, turning it around on your partner, not accepting any responsibility and definitely not validating what they're feeling. Now, if you get criticized enough, or if you get really flooded, the flooding is what happens when our heart rate goes up kind of around a hundred beats per minute, our frontal lobe shuts down. That's our thoughtful brain, our logical brain. And our reptilian kind of hind brain takes over our thinking. And we just go into fight or flight in a way. We just want to annihilate our partner and instead of say anything, that would be helpful to the relationship. So if you're getting flooded, you could do a couple of things. You could get super critical, you could get contemptuous, which I'll talk about in a second, it's the last horseman, or you do the third horseman, which is stonewalling. And in their research, the Gottmans found that men are actually more likely to stonewall. I also am someone who stonewalls, but it's where you just sort of disconnect from the conversation. You shut down, you turn away. You can physically even turn away kind of arms crossed, but you're just, you're shut off. And stonewalling happens usually because you get flooded. You feel like you can't win. You don't know what to do to make the situation better. It feels pretty hopeless and talking feels unproductive. So you can see how in a typical heterosexual relationship, the gender dynamic, we know that women tend to use criticism more often because they're the ones that typically raise issues verbally. And then if men are feeling more criticized, that they tend to stonewall and it becomes this vicious cycle of then more criticism, but the criticism is really just a plea to be loved and get your partner to show you they care. And then the man tends to feel like he can't do anything right. This isn't even productive if I say anything, I'm just gonna make it worse. And they don't have any real, you haven't given them a specific need, a solution, something they can do to shine for you. </s> |
<s>[INST] love the the I mean my apologies, but mit mind and hand, I love that there's uh the root of philosophy that you gain from your mom and the hand that action is all that ultimately in the end matters from your dad. That's that's it's really powerful if we could take a small detour into philosophy. Is there by chance any books authors, whether philosophical or not, you mentioned Sasha that stand out to you that were formative and some small or big way that perhaps you would recommend to others maybe when you were very young or maybe later on in life. [/INST] Well, actually, yeah, you know, I read the number of existentialists that appealed to me because they were authentic, you know, saturday, you know, he declined the nobel prizes we discussed, but he also uh was mocking people that pretend to be something better than they are. You know, he was living an authentic life that is sincere and that's what appealed to me. And Albert commey was another french philosopher that the advocated existentialism. Um you know, that really appealed to me is probably </s><s>[INST] my favorite existentialist camus. Yeah, [/INST] and he died at a young age in an accident, unfortunate. Um and then people like Nietzsche that uh you know, broke conventions and I noticed that nature is still extremely popular, you know, That's quite surprising. Uh he appeals to the young people of today and the people that </s><s>[INST] is the Children, it's the childlike wonder about the world. And he was unapologetic. It's like most philosophers is a very strict adherence of terminology into the practices academic philosophers, and each year was full of contradictions. And and he just, I mean, he was just this big kid with opinions and thought deeply about this world and people are really attracted the and surprisingly, there's not enough people like that throughout history of philosophy and that that's why I think there is still drawn to him. [/INST] Yeah. To me what stands out is his statement that the best way to corrupt the minds of young people is to tell them that they should agree with the common view. You know, and uh you know, it goes back to the threat that went throughout discussion. </s><s>[INST] You've you've kind of suggested that we ought to be humble about our very own existence and our existence last only a short time we talked about um you losing your father and your mother. Uh, do you think about your own mortality? Are you afraid of [/INST] death? I'm not afraid. You know what Epic Orosz actually, because it was a very wise person. Uh according to Lucretius, of course didn't leave anything in writing. But he said that he's never afraid of death because as long as he is around, death is not around and when death will be around, he will not be around. So he will never meet death. So why should you be worried about something you will never meet? Uh, you know, and it's an interesting philosophy of life. You know, you shouldn't be afraid of something that you will never encounter, right? </s><s>[INST] But there's a finite nous to this experience. We live every day. I mean, I think of her being honest what every day is if it's going to last forever. We often kind of don't contemplate the fact that it ends, you kind of plans and goals and you have this possibilities. Uh, you have a kind of lingering thought, especially as you get older and older and older, that this is especially when you lose friends, right? And then you start to realize, um, you know, it doesn't, but I don't know if you really are cognizant of that. I mean, [/INST] because, but you have to be careful not to be depressed by it because otherwise you lose the vitality, Right? So I think the most important thing to draw from, from knowing that you are short lived is a sense of appreciation that you're alive. That's the first thing. But more importantly, a sense of modesty. Because how can anyone be arrogant if they kept at the same time, this notion that they are short lived. I mean, you cannot be arrogant because anything that you advocate for, you know, you will not be around to do that in 100 years. So people will just forget and move on. You know, and if you keep that in mind, you know, the caesars in Ancient Rome, they had a person next to them telling them, Don't forget that you are moral. You know, there was a person with that duty because the caesars thought that they are all powerful, you know. Uh, and uh, they had for a good reason, someone, they hired to whisper in their ear. Don't forget that your model. </s><s>[INST] Well, you're somebody, one of the most uh, respected, uh, famous scientists in the world, sitting on the farm, gazing up at the stars. So you seem like an appropriate person to ask the completely inappropriate question of What do you think is the meaning of it all? What's the meaning of life? [/INST] That's an excellent question. And if we ever find an alien that we can converse with, I would like to answer this. I would like to ask for an answer to this question because um </s><s>[INST] well they have a different opinion you think, [/INST] well they might be wiser because they lived around for a while, but I'm afraid they will, they will be silent. I'm afraid they will not have a good answer. And I think um it's it's the process that you should get satisfied by the process of learning you should enjoy. Okay, So it's not so much that there is a meaning i in fact there is as far as I can tell, things just exist, you know? Uh and it's uh I think it's inappropriate for us to assign meaning for our existence because you know, we as a civilization, we will eventually perish, you know, and nothing will be, you know, just another planet on which life died. You know? And if you look at the big scheme of things, who cares, who cares and how can we assign significance to what we are doing? You know? So if you say the meaning of life is this, well, it will not be around in a billion years. So what, you know, it cannot be the meaning of life because life nothing will be around. So I think we should just enjoy the process and you know it's like many other things in life. You enjoy good food, okay? And you can enjoy learning why because it makes you appreciate better where you know the environment that you live in. And sometimes people think religion for example is in conflict with science spirituality in country. That's not true. Uh if you see a watch and you look at it from the outside, you know, you might say oh that's interesting. But then if you start to open it up and learn about how it works, you appreciate it more. So science is the way to learn about how the world works and it's not in conflict to the meaning that you assigned to all of this, but it helps you appreciate the world better. So in fact I would think that a religious person should promote science because it gives you a better appreciation of what's around you. You know it's like, you know if you buy uh in a grocery by something, you know a bunch of fruits that are packed together and you can't see from the outside exactly what kind of fruits are inside. But if you open it up and study, you appreciate better the merchandise that you get right. So you pay the same amount of money but at least you know what's inside. So why don't we figure out what the word is about? You know what the universe contains, what is the dark matter will help us appreciate, you know, the bigger picture and then you can assign your own flavor to what it means. You know, </s> |
<s>[INST] the belt of debris just real quick, it's out there. Is there something incredible to be discovered there? Again, we tend to focus on the planets and the moons, but it feels like there's probably a lot of stuff out there and it probably, what is it? It's like a garbage collector from outside of the solar system, isn't it? Like doesn't it protect from other objects that kind of flying and what it just feels like, It's a cool, you know, you know when you like walk along the beach and look for stuff and like look for sure it feels like that's that kind of place where you can find cool, cool weird things or I guess in our conversation today when we think about tools and what science is studying, is there something to be studied out there or we just don't have maybe the tools yet or there's nothing to be found. [/INST] There's there's absolutely a lot to be found. So the material that's out there is remnant material from the formation of our solar system. It's we don't think it comes from outside the solar system, at least not most of it. Um but there there are so many fascinating objects out there and I think what you've hit on is exactly right that we just don't have the tools to study them in detail. But we we can look out there and we can see there are different species of ice on their surface that tells us about, you know, the chemical composition of the disk that formed our solar system. Some of these objects are way brighter than they should be, meaning they have some kind of geological activity. People have hypothesized that some of these objects have subsurface oceans. You could even stretch your imagination and say some of those oceans could be habitable. Um but we can't get very detailed information about them because they're so far away. And so I think if any of those objects were in the inner solar system, it would be studied intently and would be very interesting. </s><s>[INST] So would you be able to design a probe in that like very dense debris field, be able to like hop from one place to another? Is that just outside the realm of like, how would you even design devices or sensors that go out there and take pictures and in land? Do you have to land to truly understand a little piece of rock? Or can you understand it from remotely like fly up close and remotely observed? [/INST] You can learn quite a lot from just a fly by and that's all we're currently capable of doing in the outer solar system. The New Horizons mission is a recent example which flew by Pluto and then they had searched for another object that was out there in the kuiper belt. Any object that was basically somewhere that they could deflect their trajectory to actually fly by. And so they did fly by another object out there in the kuiper belt and they take pictures and they do what they can do. And if you've seen the images from that mission of Pluto, you can see just how much detail we have compared to just the sort of reddish dot that we knew of before. You do get an amazing amount of information actually from just essentially a high speed fly by. </s><s>[INST] It always makes me sad to think about fly byes that we might be able to, we might fly by a piece of rock, take a picture and think, oh, that looks pretty and cool, whatever and that you could study certain like composition of the surface and so on. But it's actually teeming with life and we won't be able to see it at first. And it's sad because you know like when you're on a deserted island, you wave your hands and the thing flies by and you're trying to get their attention and they probably do the same in their own way, bacteria Probably right. But and we we miss it. And as some reason it makes me it's a it's the phone wallets, fear of missing out. It makes me sad that there might be life out there and we don't, we're not in touch with it. We're not talking. Yeah. Well, okay. Uh assad pause, Russian, philosophical pause. Okay, what are the tools available to us to study planets and their moons? [/INST] Oh my goodness. That is such a big question. Um so among the fields of astronomy, So planetary science, broadly speaking, well, it falls kind of at the border of astronomy, geology, climate science, chemistry and even biology. So it's kind of on the border of many things. But um part of it falls under the heading of astronomy and among the things that you can study with telescopes like solar system, moons, um and planets. The solar system is really unique in that we can actually send spacecraft missions to the objects and study them in detail. And so I think that's that's the kind of type of tool that is that people are most aware of. This most popularized these amazing Nasa missions that either you fly by the object, you orbit the object you land on the object, potentially you can talk about digging into it drilling, um, trying to detect tectonic tremors on its surface. Um, the types of tools that I use are primarily telescopes and so I, my background is in astrophysics and so I actually got into solar system science from astronomy, not from a childhood fascination with spacecraft missions, which is actually what a lot of planetary scientists became planetary scientists because of childhood fascination with spacecraft missions, which is kind of interesting for me to talk to people and see that trajectory. I kind of came at it from the fascination with telescopes, </s><s>[INST] angle rockets When [/INST] I was a kid, it was looking at the stars and playing with telescopes that really fascinated me and that's how I got into this. Um, but telescopes, it's amazing how much detail and how much information you can get from telescopes today. You can resolve um, individual cloud features and watch them kind of sheer out in the atmosphere of titan, you can literally watch volcanoes on IO changed from day to day as the lava flows expand. Um, so, and then, you know, with spectroscopy, you get compositional information on all these things and it's um, when I started doing solar system astronomy, I was surprised by how much detail on how much information you can get even from Earth and then as well as from orbit, like the Hubble space telescope. The James webb. </s> |
<s>[INST] is the meaning is the origin of meaning for your [/INST] world. Yeah, I experience things as good or bad, happy, sad, interesting importance of my consciousness invests this world with meaning without any consciousness. Maybe it would be a bleak, meaningless universe, but I don't see why I need someone else's consciousness or even God's consciousness to give this uh this universe meeting here, we are local creatures with our own subjective experiences. I think we can give the universe meaning ourselves. I mean, maybe to some people that feels inadequate. Yeah, our own local consciousness is somehow too puny and insignificant to invest any of this with cosmic significance and maybe God gives you a sense of cosmic significance. But I'm just speculating here </s><s>[INST] so that, you know, it's a really interesting idea that consciousness is the thing that makes life meaningful if you could maybe just just briefly explore that for a second. So, I suspect just from listening to you now, you mean in an almost trivial sense, just the the day to day experiences of life have because of you attach identity to it. They become uh huh I guess I want to ask something. I would always wanted to ask a legit world renowned philosopher what is the meaning of life? So I suspect you don't mean consciousness gives any kind of greater meaning to it all has more to day to day. But is there greater meaning to it all? [/INST] I think life has meaning for us because we are conscious. So without consciousness no meaning, consciousness invests our life with meaning. So consciousness is the source of my view of the meaning of life. But I wouldn't say consciousness itself is the meaning of life? I'd say what's meaningful in life is basically what we find meaningful, what we experience as meaningful. So if you find meaning and fulfillment and value and say intellectual work like understanding, then that's your that's a very significant part of the meaning of life for you. If you find it in social connections or in raising a family, then that's the meaning of life for you. The meeting comes from what you value as a conscious creature. So, I think there's no on this view, there is no universal solution. You know, universal answer to the question, what is the meaning of life? The meaning of life is where you find it as a conscious creature. But it's consciousness that somehow makes value possible, experiencing some things as good or as bad or as meaningful someone comes from within consciousness. </s><s>[INST] So you think consciousness is a crucial component ingredient of having given assigning value to things. [/INST] I mean, it's kind of a fairly strong intuition that without consciousness there wouldn't really be any value. If we just had a purely a universe of unconscious creatures, would anything be better or worse than anything else? Certainly, when it comes to ethical dilemmas, you know, you know about the older, the old trolley problem, do you uh do you kill one person or you switch to the other track to kill kill five? Or I've got a variant on this, the zombie trolley problem where there's one conscious being on on one track and five humanoid zombies, let's make them robots who are not, who are not conscious on the uh on the other track. Do you given that choice because the one conscious being or the five unconscious robots? Most people have a fairly clear intuition here, kill the, kill the unconscious beings because they basically, they don't have a meaningful life. They're not really persons conscious beings. Of course, </s><s>[INST] we don't have good intuition about Mhm. Something like an unconscious being. So in philosophical terms, you refer to as a zombie, it's a useful thought experiment construction in philosophical terms, but we don't yet have them. So that's kind of what we may be able to create with robots and I don't necessarily know what that even means. [/INST] So it's merely hypothetical for now, they're just a thought experiment. They may never be possible. I mean, the extreme case of a zombie is a being which is physically functionally behaviorally identical to me but not conscious. That's a mirror. I don't think I could ever be built in this universe. The question is just could be, does that hypothetically make sense? That's kind of a useful contrast class to raise questions like why aren't we zombies? How does it come about that? We're conscious and we're not like that. But there are less extreme versions of this, like robots which are maybe not physically identical to us. Maybe not even functionally identical to us. Maybe they've got a different architecture, but they can do a lot of sophisticated things, maybe carry on a conversation, but they're not conscious. That's not so far out. We've got simple computer systems at least tending in that direction now, and presumably this is going to get more and more sophisticated over the years to come. But we may have some pretty this quite straightforward to conceive of some pretty sophisticated robot systems that can use language and be fairly high functioning without consciousness at all. Then I stipulate that we've caught this is tricky question of how you would know whether they're conscious, but let's say we somehow solve that? We know that these high functioning robots aren't conscious, then the question is, do they have moral status? Doesn't matter how we treat them? Um Like </s><s>[INST] what is moral status means? So [/INST] that's basically how can they suffer. Doesn't matter how we treat them. For example, if we if I mistreat this glass, this cup by shattering it, then that's bad. Why is it bad that is going to make a mess that's gonna be annoying for me and my partner? Um And so it's not bad for the cup. No one would say the cup itself has moral status. Hey, you you heard the cup? Um And that's uh that's doing it a moral harm. Um Likewise plants, well again, if they're not conscious, most people think by operating a plant, you're not harming it. But if a being is conscious, on the other hand then you are harming it. So Siri or I do not say the the name of Alexa. Anyway, so we don't think we're morally harming Alexa by turning her off or disconnecting her or even destroying her, whether it's the system or the underlying software system because we don't really think she's conscious. On the other hand, you move to like there the disembodied being in the moving in the movie, her Samantha because she was kind of presented as conscious. And then if you if you destroyed her, you'd certainly be committing a serious harm. So I think our strong senses, if a being is conscious and can undergo subjective experiences, then it matters morally how we treat them. So if a robot is conscious it matters, but if a robot is not conscious and then they basically just meet or a machine and that and it and it doesn't matter. So I think at least maybe how we think about this stuff is fundamentally wrong, but I think a lot of people think about this stuff seriously, including people who think about say the moral treatment of animals and so on, come to the view that consciousness is ultimately kind of the line between systems that where we have to take them into account and thinking morally about how we act and systems for which we don't. </s> |
<s>[INST] And you're talking about the most beautiful equation mathematics. But it's still pretty mysterious, isn't it? Like you're making it seem like it's a notation. No, [/INST] It's not mysterious. I think I think the notation makes it mysterious. I don't think it's I think the fact that it represents it's pretty it's not like the most beautiful thing in the world, but it's quite pretty the idea that if you take the linear operation of a 90° rotation and then you do this general exponential Haitian thing to it that what you get are all the other kinds of rotation. Uh Which is basically to say if you if your velocity vector is perpendicular to your position vector, you walk in a circle. That's pretty. It's not the most beautiful thing in the world. But it's quite pretty. The </s><s>[INST] beauty of it, I think comes from perhaps the awkwardness of the notation somehow still nevertheless coming together nicely because you have like several disciplines coming together in a single equation. Well, in a sense historically speaking, [/INST] that's true, you've got so like the number E is significant. Like it shows up in probability all the time. It shows up in calculus all the time. It is significant. You're seeing it sort of made it with pi the geometric constant and I like the imaginary number and such. I think what's really happening there is the way that he shows up is when you have things like exponential growth and decay, right? It's when this relation that something's rate of change has to itself is a simple scaling, right? Um a similar law also describes circular motion because we have bad notation, we use the residue of how it shows up in the context of self reinforcing growth, like a population growing or compound interest. The constant associated with that is awkwardly placed into the context of how rotation comes about because they both come from pretty similar equations. And so what we see is the in the pie juxtaposed uh a little bit closer than they would be with a purely natural representation, I would think here's how I would describe the relation between the two. You've got a very important function, we might call exp that's like the exponential function. When you plug in one, you get this nice constant called e that shows up in like probability calculus, if you try to move in the imaginary direction, it's periodic and the period is tao so those are these two constants associated with the same central function, but for kind of unrelated reasons, right and unrelated, but like orthogonal reasons. One of them is what happens when you're moving in the real direction ones. What happens when you move in the imaginary direction and like yeah, those are related. They're not as related as the famous equation seems to I think it is it's sort of putting all of the Children in one bed and they kind of like to sleep in separate beds if they had the choice. But you see them all there and you know there is a family resemblance but it's not that close. </s><s>[INST] So actually think of it as a function is uh is the better idea and that's a rotational idea. [/INST] And yeah, like here's the thing, the constant e sort of stands as this numerical representative of calculus. Right? Calculus is the study of change. So at least there's a little cognitive dissonance using a constant to represent the science of change. I never thought of it that way. Yeah. Yeah. It makes sense why the notation came about that way because this is the first way that we saw it in the context of things like population growth through compound interest. It is nicer to think about as repeated multiplication. That's definitely nicer. But it's more that that's the first application of what turned out to be a much more general function that maybe the intelligent life your initial question asked about would have come to recognize as being much more significant than the single use case which lends itself to repeated multiplication notation. But </s><s>[INST] let me jump back for a second to aliens and the nature of our universe. Okay. Do you think math is discovered or invented? So, we're talking about the different kind of mathematics that could be developed by the alien species. The implied question is is um yeah, his math discovered or invented is, you know, is fundamentally everybody going to discover the same principles of mathematics. [/INST] Uh So the way I think about it and everyone thinks about it differently, but here's my take. I think there's a cycle at play where you discover things about the universe that tell you what math will be useful and that map itself is invented in a sense. But of all the possible maths that you could have invented its discoveries about the world that tell you which ones are. So, like a good example. Here is the Pythagorean theorem. When you look at this, do you think of that as a definition? Or do you think of that as a discovery </s><s>[INST] from the historical perspective? Whereas the discovery because they were but that's probably because they were using physical object to build their intuition and from that intuition came to mathematics, the mathematics was in some abstract world detached from the physics. But I think more and more math has become detached from, you know, when you even look at modern physics from from string theory. So, even general relativity mean all math behind the 20th and 21st century physics kind of uh takes a brisk walk outside of what our mind can actually even comprehend in multiple dimensions. For example, anything beyond three dimensions, Maybe four Dimensions? no [/INST] no no no higher dimensions can be highly highly applicable. I think this is a common misinterpretation that if you're asking questions about like a five dimensional manifold that the only way that that's connected to the physical world is if the physical world is itself a five dimensional manifold or includes them. </s> |
<s>[INST] Okay, Griff t advertising. So actually this is a step back. What is the multi level marketing scheme? Like what? Because I've, I've experienced a similar thing. I remember I worked at, I sold women's shoes at Sears uh in a bank and I just remember like some kind of, I forgot the name of the company, but you like, you can sell like knives or whatever. Like that's a couple of [/INST] uh I know what you're talking about. I'm </s><s>[INST] sure there's a lot of things like this, right? And I remember feeling a similar thing, like why to me, what was fascinating about it is like, wow, like human civilization is a interesting like a pyramid scheme. Like I didn't maybe didn't know the words for that, but it's like, it's cool, like you can like get in the room, you convince each other ideas and you have these ambitions general desire, especially when you're young to like, like life sucks right now, nobody respects you. You have no money you want to do good and you want to be sold. This dream of like if I work hard enough at this weird thing, I can shortcut and get to the very top. I don't know what that is. And I also in me felt that like life really sucks and I could do good and [/INST] I'm a lucky, </s><s>[INST] I found a way to do good. I'm like and I don't know you connect with that somehow. I think there's like this weird fire inside people to like to make better of themselves, right? I don't know if it's just an american thing or if it but anyway that was fascinating to me from a human nature perspective. [/INST] Grifters play on this though, right? Like this is so the best salesman play on true narratives that you already believe. So the true narrative is you know, life is unfair. It is tough. Um The american dream as described by go to a job working the same company for 40 years and then retire to a safety net that you're positive is going to be there. That is largely debt. And so they like play on those fears and those problems to then sell you a p fill a solution a thing. And the problem is that is that the solution is usually worse than even the problem they sketched out like you will do better most of the time by going with the regular company than you will by going with these goofy multilevel marketing. But let me answer your question, what is a multilevel marketing? So there's a criticism first of all that um Well let me get to what it is in theory like at its most ideal multi level marketing is where you have a product that you're selling and one of the ways you help sell it is by rather than going through traditional marketing like where you go and you put out print advertising, it's like sort of a social network of marketing I sell to you and then actually lex not only can I sell to you, you can then go sell this product and you'll make money selling it and you know what to incentivize me to get other salesmen because when I get another salesman, I'm actually giving myself competition. So it's bad. So to incentivize me to do that, they'll pay me part of what you make, right? And then you go out and you go, okay, well I can sell this product. I also can get new salesman to like sell for me and I'm going to make money from you, whatever. So it goes down the line of you create multiple levels where you can profit from their marketing, right? The problem with this system is that however well intentioned it is is that usually the emphasis of that selling and making money ends up not being about the product at all and ends up entirely being about recruiting new people to recruit new people to recruit new people. That's the real way to make money in multi level marketing. This is where the very true criticism of most multilevel marketing, if not all are Pyramid schemes in structure because what a pyramid scheme is is it's all about. I put in $500 and I recruit two people to put in $500 and that comes up to me and they put in, they get two people to put in $500 and it goes to them. And the reason it's a, it's a flawed business model is in order for it to work and everyone to make money, you'd have to assume an infinite human race. And so that's not the case. Most people end up getting screwed in multilevel marketing and pyramid schemes. That's what that is. That's that thing. And </s><s>[INST] the quality of the product, it doesn't necessarily matter what you're selling [/INST] to people who are financially incentivized to like buy this thing. </s><s>[INST] Yeah. And so you're, you're selling the dream of becoming rich to the people down in the pyramid. [/INST] That's the real product of multi level marketing, unfortunately. Um and so you look at the statistics of these companies and although they'll make it seem like it's so easy to be the top, you know, 0.1% who's making all this money. The statistics are that 97% make less than a minimum wage doing this. They spend an enormous amount of time and just what's so cruel about it is that's not advertised upfront. I mean, it's like if I go to work at Mcdonald's, I know what I'm getting if I go work at Amway, I have visions of they've sold the visions of beaches and whatever. And more than likely I'm losing money. So better than 50% of people lose money, but 97% of people make less than minimum wage. It's like, it's such a bad business. Uh for the vast majority of people who join it and the people at the very top who are lying to the people at the bottom saying they all can do it when they can't are making all the money. So it's it's yeah, it's really messed </s> |
<s>[INST] I have a bunch of questions, but I'm going to join then, so- That's why everything he said is wrong. [/INST] Okay, yeah, that's why everything he said is wrong. Okay, yes. First of all, the idea of competing legal systems is inevitable because what Rand talked about is what she wanted was, and this is really kind of Eric out of character with her broader ideology is, I think this was her term and I'm not saying this to make fun of you, when she has a judge and he's looking at the information, she wants him to be basically, I think she's the word robot, someone without any ideology, that they're just looking at the facts, they're not bringing their kind of worldview to it. I take it as a compliment. You are welcome. I think that given otherwise her correct view that ideology that causing the ideology is just a slur for someone's philosophy, that someone, especially someone who's erudite educated and informed as a judge has to and in fact should bring their ideology to their work is in one sense a little contradiction in her view, number one. Number two is we have right now the DA in San Francisco. I forget his name. He's the son of literal terrorists, communist terrorists, and he has made it the decree unilaterally that if you shoplift for less than, I forget, $200, we're not prosecuting. Yeah, I know that. You know this game, right, right, right. So now you and I certainly, and Lex I'm sure probably, agree that his ideology is abhorrent, that this doesn't help poor people, it doesn't help shop owners, it creates a culture, an area where it's just deleterious to human life. However, he has in one sense given that he is a state operative, a legitimate worldview. Can I ask you just a quick question? Sure. Why couldn't a security force in a particular context say, yeah, if you take stuff from that store, we're not going to have any problem with that. I agree with you. That's very fair. That's a very legitimate question. The point is in the context that I'm talking about, that firm is like, wait a minute, I'm hiring you for security. You're saying we're not going to provide security. Why am I writing you a check? And we have examples of this in real life. If I get into a car accident with you, right, you have your car insurance, I have my car insurance. If your car insurance had their druthers, they wouldn't pay me one penny. If my car insurance didn't have their druthers, they wouldn't pay you one penny. You were saying early that we need to have one kind of umbrella, make them more profuse. There are already more cases that you can count where there's private arbitration. Now, the argument is that private arbitration only works because they have recourse to the government. But my point is there's many examples where even though that recourse is theoretically possible, it's not a realistic concern, specifically because they know that if you have recourse to the state, you have no concept of what that outcome is going to look like except knowing it's going to be exorbitant, it's going to be time consuming. We can't use the state. Right. I mean, I'm as critical as the state as it is right now, maybe not as critical as yours. Not as critical as yours. But I'm quite critical of the state as it is right now. Yeah. But let's say we got into a traffic accident, and you have a rose voice. And I destroyed your rose voice, and my insurance company now owes your insurance company a lot of money. And let's imagine it's a lot of money just for this gentleman. And I'm using that... But I'm quite critical of a state as it is right now. You're clearly guilty, let's pretend... Yeah, clearly guilty. Yes, clearly guilty. And my insurance company looks at his books and it goes, I don't really, I don't want to pay this. Sure. And you know what? I've got bigger guns than his insurance company. Sure. over the insurance company. And hostile takeover takes on a whole new meaning when I can muster guns on my behalf than in a hostile takeover in a capitalist context. That to me is what happens, that to me is inevitably what happens. And I think this is where the delusion comes in. The idea that when big money is involved and power is involved, remember, again, the same kind of politicians who today get into politics are likely to want to run some of these security agencies because they all have a lot of power over people. So the same kind of maybe sociopaths would be there. Maybe sociopaths would be there. I don't think it's the same skill set, but that's a separate issue. I think it very much is. But- You think the people in Washington are the same as CEOs, psychologically and skill set wise? Well, today's CEOs, yes. Okay. Yes, yes. You might be right, you might be right. Because I think that's what's rewarded for a CEO is somebody who could get along with government. Okay. And I think the kind of CEO who is going to run a security company, which is not just about business, it's about the use of force, it's about control, it's about negotiation with other entities that are using force. component diplomacy. Then the gate, and we should get back to objective law because I think it's essential to the whole argument. I would love to get back to something. I think all you get into is security agencies, fighting security agencies. And again, the biggest gun. And I don't mean here the guy who has the biggest literal gun, the rocket launcher versus the guns. I got excited. By the biggest gun. The party that has the more physical force, however that is mustered either by numbers or by weapons, is going to dominate and will take over everybody else. Now, one of the things that's common in a market is takeovers. It's consolidation. And here, the consolidation can happen through force and you can roll other security companies and that's exactly what will happen until you dominate the... I would love to get back to something. Okay, so let me explain why I disagree with that. You were just saying, and I agree correctly, I agree with you, that, listen, if I have access to the bigger gun, why am I paying you or whoever's paying whoever, I'm just going to use force and not pay them. We have that right now, it's called lobbying. So instead of me, and I'm sure in your example, you weren't being literal, instead of the insurance company literally having the RME, they could be like, hey, let me call CorruptCo with a mafia. I agree. Yeah, go out and take them out. By having this federal government, as you know, and certainly I'm not a fan of, takes more through asset forfeiture than burglaries combined. What asset forfeiture is, people don't even understand this. This is something crazy, which Iran is as opposed to me as opposed as I am, which is I'm a cop, I go to your house, I think you haven't been charged or convicted of anything or have evidence. It's usually in a car. Yeah. Yeah. But it's like drug deals. Okay, I go to your house, you're a drug dealer. I say and you can understand the reasoning, well, if someone is getting profit through illegal mechanisms, their profit isn't real, they're property and they shouldn't be rewarded. So basically, I go to your house, you're a drug dealer, I seize all your property, you don't really have recourse, even though you haven't been through deep, I'm just explaining to the audience, through new process and SOL, that combined for people who don't know is more than the total amount of burglaries in America. It's a huge, and what happens is the police department, which seizes your car auctions, it sees your house auctions, it's a great way to line their pockets. This is a huge incentive. It's horrible. It's a huge incentive for police departments to do this because it's like, look, this guy's a crook. Maybe he's not a drug dealer, but he's clearly a pimp. Let me just take all his stuff and it's going to go to the community. Well, and the rationale originally was, if I try him, in the meantime, he'll take that money and funnel it somewhere else, and hide it, and I'll never be able to get access to it. And it was passed in the 1970s under the original Seizored Laws were kind of re-co-acts going after the mafia. And one of the reasons I despise Giuliani as much as I do, and there's very few politicians out there that I despise more, is because he was the first guy to use re-co on financiers. And so it wasn't even a drug dealer. It was, you were accused of a financial fraud. Not, you weren't shown to be guilty. It was accused. Your assets basically were forfeiture. Guilty. It was accused. Innocent of proven guilty went out of the window. </s> |
<s>[INST] didn't get far, [/INST] he got too caught up in the whole philosophy and never really got to build the model. But what Goodman moralist was a predator prey model. Okay, The lock to Volterra model was the basis of the idea of what the idea is. You have a prey like. And the example that locked are actually used initially was grass. Grass is the prey and then you have a predator and a predator cows. So you start off with a very few cows, lots of grass, and then because of lots of grass, the numbers of cows grow and there because the cows grow, they start to eat the grass. So the grass runs out. So the cows starve and you get a cycle. And what Doctor was amazed by was that the cycles were persistent, they didn't die out. So Goodwin got that vision. And he then built a predator prey model. And I first of all read Goodwin and really found it really hard to follow. His writing is not a very good writer, but a guy called john Blatt, who was a professor of mathematics at New South Wales University, wrote a brilliant explanation of Goodwin's model in a book called dynamic economic Systems. And I read that it was superb and he said, a way you could extend this was to include finance. So I thought, okay, what I'm going to have is that what Goodwin presumed as capitalists invest all their profits? Okay, so you get boom when there's a high rate of profit, because they invest all that money and then a slump when there's low profit, because depreciation will wipe away capital and you'll go boom and slump. So I simply added in world, capitalists will invest more than their profits during a boom, but less than their profits during a slump. And that therefore means they had to borrow money to finance the gap and pay interest on the debt. So I ended up with a model with just three system states, the income share, the wages distribution of income between workers capitalists and bankers, the level of employment and the level of private debt. And those three equations are fundamentally like going from the locked Volterra model with just two equations, and therefore you get a fixed cycle to the Lorenz Model where you have three and therefore what I got out of it was a chaotic outcome. So what you're seeing is manifestation of chaos complexity in those plots. But the fascinating one of the many fascinating parts about it was that as the level of private debt rose in my model, I had capitalists being the only ones who borrowed, but the people who paid for the high level of private debt were the workers. The rising bankers share corresponded exactly to a falling workers share. </s><s>[INST] You can infer from that, that the workers are the ones paying [/INST] effectively, the workers end up paying for it. They get a lower level of wages. And the basic dynamic is that capitalists, when you have a three social class system, your income goes between workers, capitalists and bankers in the system that Goodwin did. They're just workers and capitalists. So if workers share rose, profit, capital share had to fall. But when you have three social classes, then capitalist share can remain constant while workers falling bankers, workers falls and bankers rise. So that's what actually happened because capitalists, the simple way I modeled it was, there's a certain rate of profit at which capitalists invest all their profits above that they borrow more below that they pay off debt. So what would happen is when you got back to that point, then the level of investment would be a precise share of GDP and therefore you get a precise rate of economic growth. But if there was a higher percentage going to bankers and offset by a lower share going to workers, it didn't affect the capitalists. So what you get is the cycles of diminished for a while, because there's there's the other, the income distribution effect is important. So the the workers pay for the increasing level of debt. But the other side of it was that the cycles were diminished for a while. What you get is a period of diminishing cycles then leading to rising cycles. And technically this is known as the Palmer Monroeville route to chaos. And it's one particular element of Lorenzo's equations of fluid dynamics. So what they found was in examining Lemon, a flow and a fluid, you have a period where the laminar flow got more laminar and then suddenly it would start to get less laminar and go turbulent. And this is what actually goes on in the model. So in my model of Minsky, so what you have is period where there's big booms and cycles, and then as the debt level rises, the booms and Islamist get smaller. And that looks like what neoclassical economists called the great moderation. So when I first model this in 1982 I finished up my paper which was published in 95. But what I thought was a nice rhetorical flourish saying the chaotic dynamics of this paper should warn us against regarding a period of relative stability in a capitalist economy as anything more than a lull before the storm. I thought it was a great speed of rhetoric. I didn't think it was going to fucking happen, but it did because you had this period from 1990 through to 2007 where there were diminishing cycles, and the neoclassical is labeled that the great moderation and they took the credit for it. They thought that the economy was being managed by them to a lower rate of inflation, a lower level of unemployment, less instability over time. And they literally took credit for it. And I was watching that and thinking that's like my model running and I'm scared of ship that there will be a breakdown. It ended up not working in the area for a while, because I wrote debunking economics. And I got involved in a fight over the modeling of competition in neoclassical theory that took me away for about four or five years. And then I got asked to do a court case in 2005, end of 2005. And I used Minsky as my framework for arguing with somebody who was involved in predatory lending should be able to get out of the debt they were in and I explained Minsky's theory, and I must use this throwaway line of saying debt levels in private debt has been rising exponentially. And then I thought, well, I can't, as an expert just make a claim like that, I've got to check the data and the debt ratio was rising exponentially. And I thought, holy ship we're in for a financial crisis and somebody has to warn about it at least in Australia. I was that somebody. </s> |
<s>[INST] and that all of that is involved in the puzzle of [/INST] obesity And that's what's fascinating right here we are in 2007 discovering the strongest genetic association with obesity and knowing nothing about how it works for almost 10 years. For 10 years. Everybody focused on this fto. Gene and they were like oh it must have to do something with RNA modification. It's like no it has nothing to do with the function of F. D. O. It has everything to do with all of these other process. And suddenly the moment you solve that puzzle which is a multi year effort by the way a tremendous effort by Molina and many many others. So this tremendous effort basically led us to recognize this circuitry. You went from having some 89 common variants associated in that region of the DNA. Sitting on top of this gene to knowing the whole circuitry when you know the circuitry. You can now go crazy. You can now start intervening at every level. You can start intervening at the arid five B level. You can start intervening with CRISPR cast nine at the single snip level. You can start intervening at irish three Rx five directly there. You can start intervening at the thermo genesis level because you know the pathway you can start intervening at the at the differentiation level where these decision to make either white fat or beige fat. The energy burning beige fat okay, is made developmentally in the first three days of differentiation of your depot sites. So as they're differentiating, you basically can choose to make fat burning machines or fat storing machines and sort of that's how you populate your fat. You basically can now go in pharmaceutically and do all of that. And in our paper we actually did all of that. We went in and manipulated every single aspect at the nucleotide level. We used CRISPR CAs nine genome editing to basically take primary deposits from risk and non risk individuals And showed that by editing that one nucleotide out of 3.2 billion nucleotides in the human genome. You could then flip between an obese phenotype and genotype like a switch. You can basically take my cells that are non thermal jin izing and just flip into homogenizing cells by changing one type. It's mind boggling. </s><s>[INST] It's so inspiring that this puzzle can be solved in this way and it feels within reach to then be able to um crack the problem of some of these diseases. What are So 2007, you mentioned 2000. What are the technologies, the tools they came along that made this possible and like what what are you excited about? Maybe if we just look at the buffet of things that you've kind of mentioned, is there is there, [/INST] what's involved? What </s><s>[INST] should we be excited about? What are you excited about? [/INST] I love that question because there's so much ahead of us. There's so so much um there's uh so so basically solving that one locus required massive amounts of knowledge that we have been building across the years through the epic genome, through the comparative genomics to find out the causal variant and the control of regular relative through the conserved secretary. It required knowing this regulatory genomic wiring. It required high c of the sort of topological associated domains to basically find this long range interaction. It required peak TLS of this sort of genetic perturbation of these intermediate gene pena types. It required all of the arsenal of tools that have been describing was put together for one lock it and this was a massive team effort, huge investment in time, energy, money, effort, intellectual you know everything </s><s>[INST] you're referring to. I'm sorry this one yeah [/INST] This one this one single paper. This one single location I like to say that this is a paper about one nucleotide in the human genome. About one bit of information see vs T in the human genome that's one bit of information and we have 3.2 billion nucleotides to go through. So how do you do that systematically? I am so excited about the next phase of research because the technologies that my group and many other groups have developed allows us to now do this systematically. Not just one luggage at the time but thousands of Los I at the time. So let me describe some of these technologies. The 1st 1 is automation and robotics. So basically you know we talked about how you can take all of these molecules and see which of these molecules are targeting each of these genes and what do they do. So you can basically now screen through millions of molecules through thousands and thousands and thousands of plates, each of which has thousands and thousands and thousands of molecules every single time testing. Um you know all of these genes and asking which of these molecules perturb these genes. So that's technology number one, automation and robotics Technology # two is parallel readouts. So instead of perturbing one location and then asking if I use CRISPR cast nine on this enhancer to basically use de CAs nine to turn on or turn off the enhancer Or if I use CRISPR cast nine on the snip to basically change that one step at a time then what happened? But we have 120,000 disease associated snips that we want to test. We want to we don't want to spend 120,000 years doing it. So what do we do? We basically developed this technology for massively parallel reporter assays. M. P. R. A. So in collaboration with Tasha Mickelson Eric Lander I mean Jason Douri's group has done a lot of that. So there's there's a lot of groups that basically have developed technologies for testing 10,000 genetic variants at a time. How do you do that? You know we talked about micro array technology the ability to synthesize these huge microwaves that allow you to do all kinds of things. Like measure gene expression by hybridization by measuring the genotype of a person by looking at hybridization with one version with the T versus the other version with the T. With with a C. And then sort of figuring out that I am a risk carrier for obesity based on this hybridization differential hybridization in my genome. That says oh you seem to only have this salio or you seem to have that a little microwaves can also be used to systematically synthesize small fragments of DNA. So you can basically synthesize these 150 nucleotides long fragments Across 450,000 spots at the time. You can now take the result of that synthesis which basically works through all of these layers of adding one at a time. You can basically just type it into your computer and order it. And you can basically order 10,000 or 100,000 of these small DNA segments at a time. And that's where awesome molecular biology comes in. You can basically take all these segments have a common start and end barcode or sort of like gator. Like just like pieces of a puzzle. You can make the same end piece and the same start peace for all of them. And you can now use plasmids which are these extra chromosome oh small D. N. A circular segments that are basically inhabiting all our our genomes. We basically have plasmids from floating around bacteria used plasmids for transferring D. N. A. And that's where they put a lot of antibiotic resistance genes so they can easily transfer them from. But one bacterium to the other. So one bacterium evolves a gene to be resistant to a particular antibiotic. It basically says to all his friends, hey here's that sort of D. N. A piece. We can now co opt these plasmids into human cells. You can basically make a human cell culture and add plasmids to that human cell culture that contain the things that you want to test. You now have this library of 450,000 elements. You can insert them each into the common classmate and then test them in millions of cells in parallel </s> |
<s>[INST] Okay, so, uh I'm a fan of your husband as well, dan. He's a programmer or musician. So, a man after my own heart. Can I ask a ridiculously over romanticized question of When did you first fall in love with dan? [/INST] It's actually it's a really, it's a really romantic story, I think. So, I was divorced by the time I was 26, 27, 26, I guess. And I was in my first academic job which was Penn State University which is in the middle of Pennsylvania surrounded by mountains. So you have, it's four hours to get anywhere to get to philadelphia new york Washington. I mean you're basically stuck, you know? Um And I was very fortunate to have um a lot of other assistant professors who were hired at the same time as I was, so there were a lot of us, we were all friends which was really fun. Um but I was single and I didn't want to date a student and there were no and I wasn't gonna date somebody in my department that's just a recipe for disaster. So </s><s>[INST] Even at 20, whatever you were, you were already wise enough to know that. [/INST] Yeah, a little bit maybe. Yeah, I wouldn't call me wise at that age, but anyways um I'm not sure that I would say that I'm wise now, but um and so um After all, you know, I was spending probably 16 hours a day in the lab because it was my first year and as an assistant professor and there's a lot to do and I was also bitching and moaning to my friends that I, you know, I hadn't had sex and I don't know how many, you know, months and it was I was starting to, you know, become unhappy with my life and um I think at a certain point they just got tired of listening to me bitch and moan and said just do something about it then like, do you know if you're unhappy? And so the first thing I did was I made friends with a sushi chef in town and this is like a state college pennsylvania in the early nineties was there was like a pizza shop and a sub shop and actually a very good bagel shop and one good coffee shop and maybe one nice restaurant. I mean there was really, but there was a, the second son of a japanese sushi chef who was not going to inherit the restaurant. And so he moved to pennsylvania and was giving sushi lessons. So I met this guy, the Sushi, the sushi chef and we decided to throw a sushi party at the coffee shop. So we basically, it was the goal was to invite every eligible bachelor really within like 20 mile radius. We had a totally fun time. I wore an awesome crushed velvet burgundy dress, was beautiful dress. Um, and I didn't meet any. I met a lot of friends, new friends, but it did not meet anybody. So then I thought, okay, well maybe I'll try the Personals ads, which I had never used before in my life. And um, I first tried the paper. Personals ads like the newspaper, like in the newspaper that didn't work. And then a friend of mine said, oh you know, there's this thing called Net News, We're going, this is like 1992 maybe. So there was this anonymous, you could do it anonymously. So you would you would read um you could post or you could read ads and then respond to an address which was anonymous and that was yoked to somebody's real address. And um and there was always a lag because it was this like a bulletin board sort of thing. So at first I read I read them over and I decided to to respond to one or two and you know, it was interesting. </s><s>[INST] So this is not on the internet. [/INST] Yeah, this is totally on the internet </s><s>[INST] but it takes there's a delay of a couple of days or [/INST] Whatever. Yeah. Right. Right. It's 1992. There's no web, web pictures, there's no pictures, the web doesn't exist. It's all done in asking format sort of. Um and you know, but the rations, but the ratio of um men to women was like 10 to 1. I mean there were many more men because it was basically academics in the government. That was it. There's no I mean I think A. O. L. Maybe was just starting to become popular. But um and so the first uh person I met told me that he was he was he was a scientist who worked for Nasa. And um Yeah. Um anyway as it turned out that he didn't actually </s><s>[INST] ask how they brag is as you elevate your as opposed to saying you're taller than you are, you say like your positions. [/INST] Yeah. And I actually I would have been fine dating somebody who was a scientist. It's just that they have, it's just that whoever I date has to just accept that I am and that I was pretty ambitious and was trying to make my career and you know, that's not that's not, I think it's maybe more common now for men to maybe accept that and their female partners, but at that time, not not so </s><s>[INST] common. [/INST] Yes, I I that has been said. And so um and so then the next one I actually corresponded with and we actually got to the point of talking on the phone and we had this really kind of funny conversation where you know we're chatting and he said he's he introduces the idea that, you know, he's really looking for a dominant woman and I'm thinking I'm a psychologist by training, so I'm thinking, oh he means sex roles, like I'm like no, I'm very assertive and I'm glad you think that, you know. Anyways long story short, that's not really what he meant. Okay. </s><s>[INST] Got it. [/INST] Yeah, so and I just, you know that will just show you my level of naivete. Like I was like, I didn't completely understand, I was like, well yeah, you know know at one point he asked me how I felt about him wearing my laundry and I was like, I don't even share my laundry with my sister, like, I don't share my laundry with anybody, you know? No, the 3rd 1 I interacted with was a banker who lived in Singapore and that that conversation didn't last very long because he made an analogy, I guess he made an analogy between me and character in the fountainhead, um the woman who's who's raped in the fountainhead, and I was like, okay, that's not that's not good, that's not a good, no, that's not a good </s><s>[INST] one, making [/INST] it not that scene. So then I um so then I was like, okay, you know what, I'm going to post my own ad. And so I did, I posted, well first I wrote my ad and then of course I checked it with my my friends who were all also assistant professors that are like my little greek chorus and then I posted it and I got something like, I don't know 80 something responses in 24 hours. It was, do </s><s>[INST] you remember the pitch? Um like how, how you, I guess condensed yourself. [/INST] I don't remember it exactly, although dan has it. Um but um actually, for our 20th wedding anniversary, he took our our exchanges and he printed them off and put them in a leather bound book for us to read, which was really sweet. Um Yeah, I think I was just really direct, like, I'm almost 30, I'm a scientist, I'm not looking, just, you know, I'm looking for something serious and you know, but the thing is I forgot to say where my location was and my age, which I forgot. So I got lots of, I mean, I will say, so I printed off all of the responses and um I had all my friends over and we were, you know, had a big, I made a big pot of gumbo and we drank through several bottles of wine. Reading these responses. And I would say for the most part, they were really sweet, like Ernest and genuine, as much as you could tell that somebody's being genuine. I mean, seemed, you know, there were a couple of really funky ones, like, you know, this one couple who told me that I was their soul mate, the two of them, and they were looking for, you know, a third person and I was like, okay, but mostly super, seemed, seemed like super genuine people. And so I chose five men to start corresponding with, and I was corresponding with them. And then about a week later I get this other email and okay, and then I post something the next day that said, okay, you know, thank you so much, and I'm gonna answer every person back. But then after that I said, okay, I'm not going to answer any more, you know, because it was they were still coming in, I couldn't, you know, I have a job and you know, a house to take care of and stuff. So, um, and then about a week later I get this other email and he says, you know, he just describes himself like I'm this, I'm this, I'm this, I'm a chef, I'm a scientist, some of this, some of this. And so I emailed him back and I said, you know, you seem interesting, you can write me at my actual address if you want. Here's my address. I'm not really responding, I'm not really responding to other people anymore, but you seem interesting, you know, you can write to me if you want. And then he wrote to me and I am, then I wrote him back and I it was, it was a nondescript kind of email and I wrote him back and I said, thanks for responding. You know, I'm really busy right now. I'm I was in the middle of writing my first slate of grant applications, so I was really consumed and I said, I'll get back to you in a couple of days. And so I did, I waited a couple of days until my grants were, you know, safe grant applications safely out of the door. And then I email them back and then he emailed me and then really across two days we sent 100 emails </s><s>[INST] and text only was their pictures and [/INST] text only. Text only. And then, so this was like a thursday and friday. And then friday, he said let's talk on the weekend on the phone and I said okay and he wanted to talk sunday night and I had a date sunday night so I said okay sure we can talk sunday night. Um And then I was like well you know I don't really want to cancel my date so I'm just gonna call him on saturday, so I just called I call call them on saturday and a woman answered </s><s>[INST] oh wow that's not cool, [/INST] not cool. And uh so she says you know hello and I say oh you know it's down there and she said sure can I ask who's calling? And I said it tell them it's lisa and she went oh my god, oh my god I'm just a friend, I'm just a friend, I just tell you I'm just a friend. And I was like this is adorable, right? She doesn't and then he gets on the phone, not hi nice to meet the first thing he says to me, she's just a friend, so I was just so charmed, really buy the whole thing. So it was it was young, kapoor it was the jewish day of atonement that was ending and they were baking cookies and going to break fast so people you know as you know fast all day and and then they go to a party and they break fast so I thought okay I'll just um I'll just you know cancel my date. So I did and I stayed home and we talked for eight hours. Um And then the next night for six hours and basically it just went on like that and then by the end of the week he um he flew to state college and you know we've gone through this whole thing where I said we're going to take it slow, we're going to get to know each other. You know and then really by I think we talked like two or three times these like really long conversations and then he said I'm just gonna fly there. And then so of course there's I don't even know that there were facts machines at that point maybe there were but uh I don't think so anyway so he we decide we'll exchange pictures and so he you know I take my photograph and I give it to my secretary and I say to my secretary fax this I say that's a send this priority mail and he goes okay I'll send a priority mail, priority mail. He's like I know priority mail, okay? And then uh so I get dance photograph in the mail um And um you know it's it's him in a in a in shorts and you can see that he's probably somewhere like the Bahamas or something like that and it's like cropped so clearly what he's done is he's taken a photograph where you know he's in in it with someone else who turned out to be his ex wife. So I'm thinking well this is awesome. You know I've hit the jackpot, he's very appealing to me, very attractive and and then you know my photograph doesn't show up and it doesn't show up and you know, so like one day and then two days and then you know he's like you know you're I said well I asked my secretary to send a priority, I mean I don't know, you know um what he did and uh and he's like I said I'm like well you don't have to you know you don't have to come and he's like no no no I'm gonna I'm gonna you know we've had like five dates, the equivalent of five dates practically. Um And then um so he's supposed to fly on a thursday or friday, I can't remember. And I get a call like Maybe an hour before his flight supposed to leave and he says Hi and I say and it's just something in his voice, right? And I say because at this point I think I've talked to him for 25 hours, I don't know and he says hi and I'm like you got the picture and he's like yeah and I'm like you don't like it and he's like well uh huh I'm sure it's not, I'm sure it's your I'm sure it's just not, you know it's not it's probably not your best, </s><s>[INST] you [/INST] know you don't you don't have to come and he's like, no, no, no, I'm coming. And I'm like, no, you don't have to come. And he's like, no, no, I really want to. I'm, you know, I'm getting on the plane. I'm like, you don't have to get on the plane. Um he's like, no, I'm getting on the plane. And so I go down to my I go, I'm in my office is happening. Right? So I go downstairs to my, one of my closest friends who still actually one of my closest friends, um who is one of my colleagues and kevin. And I say kevin and I go to kevin. Kevin, kevin kevin, He doesn't like the photograph. And kevin is like, well, which photographs did you send? And I'm like, well, you know the one where we're shooting pool and he's like, mm hmm You sent that photograph. That's a horrible photograph. I'm like, yeah, But it's the only one that I had that was like, where my hair was kind of similar to what it is now. And he's like lisa like, do I have to check everything for you? You should not have sent that, you know. </s><s>[INST] But still he flew over. So [/INST] he flew from, by the way, uh he was in, he was in graduate school at Amherst Yeah. Um, u mass Amherst. So he flew and I picked him up and at the airport and he was happy. So whatever the concern was was gone. and I was dressed carefully, carefully dressed, nervous, I was really, really nervous because I am not, I don't really believe in fate and I don't really think there's only one person that you can be with but I think you know people who, some people are curvy, they're kind of complicated and so the number of people who fit them is maybe less than </s><s>[INST] like mathematically speaking [/INST] yet. And so when I was going to pick him up at the airport, I was thinking well this could, I could be going to pick up the person I'm going to marry or not. I mean like I really, but I really, you know like our conversations were just very authentic and very moving and and we really connected and and I really felt like he understood me actually um in in a way that a lot of people don't and um and and what was really nice was at the time um you know the airport was this tiny little airport out in a cornfield basically and so driving back To the town, we were in the car for 15 minutes completely in the dark as I was driving and so it was very similar to we had just spent you know 20 something hours on the telephone um sitting in the dark talking to each other. So it was very familiar and we basically spent the whole weekend together and you met all my friends and we had a big party and um and at the end of the weekend, um I said okay, you know, if we're going to give this a shot, we we probably we shouldn't see other people, so it's a risk, you know, commitment. Um but but I just didn't see how it would work if we were dating people locally and then also seeing each other at a distance, because, you know, I've had long distance relationships reporting their heart, and they take a lot of, they take a lot of effort, and so we decided we'd give it three months and see what happened and that was it. </s><s>[INST] It's such an interesting thing, like, we're all, what is that? There are several billion of us and we're kind of roaming this world and then you kind of stick together, you find find somebody that just like gets you and it's interesting to think about there's probably thousands if not millions of people that would would be sticky to you, depending on the curvature of your space. But what, what is that? Could you speak to the stickiness, like, to the just the falling in love, like, seeing that somebody really gets you, maybe by way of um telling do you think, do you remember there was a moment when you just realized, damn it. I think I'm like, I think that's this is the guy, I think I'm in love. [/INST] We were having these conversations actually from the really from the second weekend we were together. So he flew back the next weekend to state college because my birthday was my 30th birthday. My friends were throwing me a party and we went hiking and we hiked up some mountain and we were sitting on a cliff over this, you know overlook and talking to each other. And I was thinking and I actually said to him like I I haven't really known you very long but I feel like I'm falling in love with you which can't possibly be happening. I must be projecting but it certainly feels that way right? Like I don't believe in love at first sight. So this can't really be happening, but it sort of feels like it is and he was like, I know what you mean. And so for the first three months or four months we would say things to each other. Like I feel like I'm in love with you but you know, but that can't but things don't really work like that. So, but you know, so and then it became a joke like I feel like I'm in love with you and then eventually, you know, I think, but I think that was one moment where we were we were talking about, oh just yeah, you know, not just all the great aspirations you have are all the things but also things you don't like about yourself, things that you're worried about things that you're scared of and then I think the That was sort of solidified the relationship. And then there was one weekend where we went to Maine in the winter, which I I mean I really love the beach always, but in the winter particularly because </s><s>[INST] it's just beautiful calm and whatever. [/INST] Yeah. And I also, I do find beauty in starkness sometimes. Like so there's this grand, majestic scene of, you know, this very powerful ocean and it's all these like beautiful blue grays and it's just, it's just stunning. And so we were sitting on this huge rock in Maine um where we had gone for the weekend, it was freezing cold and I honestly can't remember what he said or what I said or what, but I definitely remember having this feeling of um I absolutely want to stay with this person. Like I and I don't know what my life would be like if I'm not with this person. Like I need to be with this person. </s><s>[INST] Can we, from a scientific and a human perspective, dig into your belief that first Love at 1st Sight is not, it is not possible. You don't believe in it. Well, because there is there, you don't think there's like a magic where you see somebody in the, in the jack Kerouac way and you're like, wow, that's something that's a special little [/INST] oh I definitely think, oh I definitely think you can connect with someone instant in an instance and I definitely think you can say, oh there's something there and I'm really clicking with that person romantically, but also just as friends, it's possible to do that. You recognize a mind that like yours or that's compatible with yours. There are ways that you feel like you're being understood or that you understand something about this person. Or maybe you see something in this person that you find really compelling or intriguing. But I think, you know, your brain is predictive organ, right? You're using your past, you're projecting your using your past too. Make predictions. And I mean not deliberately that's how your brain is wired. That's what it does. And so it's filling in all of the gaps that you there are lots of gaps of information that you don't information you don't have. And so your brain is filling those in. And um, </s><s>[INST] but isn't that what love is? [/INST] No, I don't think so actually. I mean to some extent, sure, you always, you know, there's research to show that people who are in love always see the best in each other. And they, you know, when there's a, when there's a negative interpretation or positive interpretation, they choose the positive ones, there's a little bit of positive illusion there, you know, going on, that's what the research shows. But I think um I think that when you find somebody who not just appreciates you're fault but loves you for them actually, you know, like maybe even doesn't see them as a fault. That's so you have to be honest enough about what you're what your faults are. So it's easy to love someone for all the things that they um uh for all the wonderful characteristics they have. It's harder I think to love someone despite their faults. Or maybe even the faults that they see aren't really fault at all to you. They're actually something really special. </s><s>[INST] But isn't that can't you explain that by saying the brain kind of like you're projecting your you have a conception of a human being or just a spirit that really connects with you and you're projecting that onto that person and yes, within that framework, all their faults then become beautiful like little [/INST] maybe, but you just have to pay attention to the prediction error. </s><s>[INST] No, but maybe that's what love, like maybe you you start ignoring the prediction error. That's maybe Love is just your ability [/INST] to ignore the prediction era. Well, I think that there's some research that might say that, but that's not my experience I guess. Um but there is some research that says, I mean, there's some research, this is you have to have an optimal margin of illusion, which means that you um that you put a positive spin on on smaller things, but you don't ignore the bigger things, right? And I think without being judgmental at all, when someone says to me, you know, um you're not who I thought you were. I mean nobody says I said that to me in a really long time, but certainly when I was younger that was you know, you're not who I thought you were, My reaction to that was well whose fault is that? You know? Um I'm a pretty, I'm a pretty upfront person. Um I mean I will though say that in my experience people people don't lie to you about who they are. They lie to themselves in your presence. Yeah. Um And so you know, you I don't want to get tied tied up in that tangled up in that and I think from the get go dan and I were just for whatever reason, maybe it's because we both have been divorced already and you know um Mhm. You know he told me who he thought he was and he was pretty accurate as far as I can, pretty much actually. I mean I there's very yeah, I can't say that I've ever come across a characteristic in him that really surprised me in a bad way. </s><s>[INST] It's hard to know yourself. [/INST] It is hard to know how to communicate that for sure. I mean I'll say you know, I had the advantage of training as a therapist which meant for five years. I was under a fucking microscope. Um You know when I was training as a therapist, it was our for our supervision which meant if you were in a room with a client for an hour, you had an hour with a with a supervisor. So that supervisor was behind the mirror for your session and then you went and had an hour of discussion about what you said, what you didn't say, learning to use your own react your own feelings and thoughts as a tool to probe the mind of the client and so on and so you can't help but learn a lot of you can't help but learn a lot about yourself in that process. </s><s>[INST] Do you think knowing or learning how the sausages made ruins the magic of the actual experience? Like you as a neuroscientist who studies the brain. Do you think it ruins the magic of like love at first sight? Are you do you consciously are still able to lose yourself in the moment? [/INST] I'm definitely able to lose myself in the </s><s>[INST] moment. Is wine involved? [/INST] Not always chocolate, I mean some kind of mind altering substance, right? But um Yeah, for sure. I mean I guess what I would say though is that um for me part of the magic is the process. Like so you know, so so I remember a day that was while I was working on this, on this, on this book of essays, I was in new york. Um I can't remember why I was in new york but I was in new york for something and I was in Central Park and I was looking at all the people with their babies and I was thinking every every each one of these are so tiny little brain that's wiring itself right now. And and I I just I felt in that moment I was like, I am never going to look at an infant in the same way ever again. And so to me, I mean, honestly, before I started learning about brain development, I thought babies were cute, but you know, not that interesting until they could do interact with you and do things. Of course, my own infant, I thought was extraordinarily interesting. But you know, they're kind of like lumps that's you know, until they can, you know, interact with you, but they are anything but lumps. I mean like you know, so and part of the I mean, all I can say is I have deep affection now for like tiny little babies in a way that I didn't really before because of the I'm just so curious, </s><s>[INST] but the actual process, the mechanisms of the wiring of the brain, the learning all the magic of the neurobiology. [/INST] Yeah. And or you know, something like, you know, when you make eye contact with someone directly, sometimes, you know, you you feel something right and what is it? And what is that? And so so to me that's not that's not backing away from the moment, that's like expanding the moment, it's like that's incredibly cool. You know, when I was um I'll just say that when I was, when I was in graduate school? I also, I was in therapy because it's almost a given that you're going to be in therapy yourself if you're going to become a therapist. And I had a deal, you know with my therapist, which was that I could call time out at any moment that I wanted to as long as I was being responsible about it and I wasn't using it as a way to get out of something and he could tell me no. You know, he could decline and say no where you're, you know, you're using this to get out of something. But I could call time out whenever I want and say, what are you doing right now? Like what are you hearing what I'm experiencing? What are you trying to do? Like I wanted to use my own experience to interrogate um what the process was and that made it mm more helpful in a way. You know what I mean? So yeah, I don't, I don't think learning how something works makes it less magical actually. But that's just me I guess. I don't know. Would you? </s><s>[INST] Yes, I tend to have two modes. One is, one is an engineer and one is romantic and I'm conscious of like, like the gear like you're like, it was two rooms. You can go into the one, the engineer room and I think that ruins the romance. So I tend to, there's two rooms. One is the engineering room think from first principles, how do we build the thing that creates this kind of behavior and then you go into the romantic room where you're like emotional to roller coaster and then you're, the thing is, let's take it slow and then you get married the next night that just this giant mess and you write a song and you cry and then you send a bunch of texts and anger and whatever and somehow you're in Vegas and there's random people and you're drunk and whatever. All that like in poetry and just mess of it fighting. Yeah, that's not, those are two rooms and you go back between between them. But I think the way you put it is quite poetic. I think you're much, you're much better than adult ng with love. Uh then uh then perhaps I am because there's a magic to Children. I also think like of adults as Children. It's kind of cool to see. It's a cool thought experiment to look at adults and think like that used to be a baby and then that's like a fully wired baby and it's just walking around pretending to be like all serious and important wearing a suit or something. But I used to be a baby and then you think of like the parenting and all the experiences they had like, it's cool to think of it that way. But then you, I started thinking like from a machine learning perspective, but once you're like the romantic moments, all that kind of stuff, all that falls away. I forget about all that. I don't know the Russian thing, [/INST] maybe. Maybe. But I also think it might be an age thing or maybe an experience thing. So I think um we all I mean if you're exposed to western culture at all, you are exposed to the uh sort of idealized stereotypic, romantic, romantic, you know, exchange and what does it mean to be romantic? And so here's a test. Um I'm gonna see how to phrase it. Okay, so not really test, but this this tells you something about your own ideas about romance for Valentine's day one year My husband bought me a six way plug. Is that romantic or not romantic? </s><s>[INST] Mhm. Like, sorry, simply place that second out like uh [/INST] like to put in an outlet. Is that romantic or not romantic? </s><s>[INST] I mean, it depends the look in his eyes when he does it. I mean it depends on the conversation that led up to that point depends how much uh it's like the music because you have a very you're both from the my experiences with you as a fan. You have both a romantic nature. You have a very pragmatic like you cut through the bullsh it of uh the fuzziness and there there's something about a six way plug that cuts to the bullshit that connects to the human, like he understands who you [/INST] are. Yeah, exactly. That was the most romantic gift he could have given me because he knows me so well. He has a deep understanding of me which is that I will sit and suffer and complain about the fact that I have to plug and unplug things and I will bitch and moan until the cows come home. But it would never occur to me To go buy a bloody six way plug. Whereas for him, he bought it, he plugged it in. He arranged, he taped up all my wires. He made it like really useful. And for me that was uh that was </s><s>[INST] the best [/INST] project. It was the most romantic thing because he understood who I was and he did something very or you know just the casual like we moved into a house that went, we went from having a two car garage to a one car garage and I said okay, you know I'm from Canada. I'm not bothered by snow. Well I mean I'm a little bothered by snow, but he's very bothered by snow. So I'm like okay you can park your car in the garage, it's fine every day when it snows. He goes out and cleaned my car every day. Like I never asked him to do it. He just does it because he knows that I'm cutting it really close in the morning. You know when we when we all used to go to work. Um I have a time to the second so that I can get up as late as possible, work out as long as possible. You know, just and make it into my office like a minute before my first meeting and so if it snows unexpectedly or something, I'm screwed because now that's an edit, you know, and added 10 or 15 minutes and I'm gonna be late anyways, you know, it's just these little tiny things that he's, he's um he's a really easy going guy and he doesn't look like somebody who pays attention to detail. He doesn't fuss about detail, but he definitely pays attention to detail and it is very, very romantic in the sense that he um you know, he loves me despite my little details, </s><s>[INST] it understands you, but it is kind of hilarious that that is The six way plug is um the most fulfilling richest display of romance in your life. I love it. [/INST] That's what I mean about romance. Romance is really, it's not all about chocolates and flowers and you know, whatever. I mean those are all nice too. But um sometimes </s><s>[INST] it's about the sex with, [/INST] Sometimes it's about the six weeks. </s><s>[INST] So um maybe one way I could ask before we talk about the details. You also have the author of another book as we talked about how emotions are made. So it's interesting to talk about the process of writing, You mentioned you were in new york what have you learned from writing these two books about the actual process of writing and maybe I don't know what's the most interesting thing to talk about, there may be the biggest challenges or the boring, mundane, systematic, like day to day of what worked for you, like hacks or, or even just about the neuroscience, but that you've learned through the process of trying to write them. [/INST] Here's the thing I learned. If you think that it's going to take you a year to write your book, it's going to take you three years to write your book. That's the first thing I learned, is that no matter how organized you are, it's always going to take way longer than what you think in part because very few people make an outline and then just stick to it. You know, the some of the topics really take on a life of their own and to some extent you want to let them you want to let them have their voice. You know, you want to follow leads until you feel satisfied that you've dealt with the topic um appropriately, but I and that part is actually fun. It's not fun to feel like you're constantly behind the eight ball in terms of time. Um but it is the exploration and the foraging for information is incredibly fun for me anyways, I found it really enjoyable and if I wasn't also running a lab at the same time and trying to keep my family going uh you know it would have been the whole thing would have just been fun. Um But I would say the hardest thing about the most important thing I think I learned is also the hardest thing and that for me which is um knowing what to leave out a really good storyteller knows what to leave out in academic writing, you shouldn't leave anything out, you all the details should be there. And um and I you know I've Written or participated in writing over 200 papers, peer reviewed papers, so I'm pretty good with detail knowing what to leave out, knowing what to leave out and not harming the validity of the story. That is a tricky tricky thing. It was tricky when I wrote how emotions are made, but that's a standard um popular science books, so it's 300 something pages. And then you know it has like 1000 end notes and then each of the endnotes is attached to a web note which is also long. So I mean you know it's um and it starts and I mean the final draft, I wrote three drafts of that book actually and the final draft and then I had to cut by a third, I mean or I mean you know it was like 100 and 50,000 words or something and I had to cut it down to like 110. So um obviously I struggled with what to leave out, you know, brevity is not my strong suit. I'm always telling people that it's a warning. So that's why this book was I you know, I've always been really fascinated with essays. I love reading essays and after reading a small set of essays by an fat woman called At Large and that Small, which I just love these little essays. </s><s>[INST] What's the topic of those essays? [/INST] They are, they're called familiar essays. So the topics are everyday topics like mail, um coffee chocolate. I mean just like and what she does is she weaves her own experience. It's a little bit like these conversations that you're so good at curating actually, um you're weaving together history and philosophy and science and also personal reflections and a little bit you feel like you're like eavesdropping on someone's train of thought in a way. It's really the, really compelling to me, even </s><s>[INST] if it's just like a mundane topic. [/INST] Yeah, but it's so interesting to um learn about like all of these little stories in the, in the wrapping of the history of like male, like that's that's really interesting. And so I read these essays and then I wrote to her a little fan girl email, this was many years ago and and I said I I just loved it, I loved this book. And how did you learn to write essays like this? And she gave me a reading list of essays that I should read. Like writers and so I read them all. And anyway, so I decided it would be a really good challenge for me to try to write something really brief where I could Focus on, you know, one or 2 really fascinating tidbits of neuroscience connect it to, connect each one to something philosophical or um you know, like just a question about human nature, do it in a really brief format without violating the validity of the science. That was a I just set myself this would I thought of as a really, really big challenge in part because it was an incredibly hard thing for me to do in the first book. </s><s>[INST] Yeah, we should say that this is the 7.5 lessons, a very short book. I mean it's a so it embodies brevity right? The whole point throughout is just, I mean you could you could tell that there's editing, like there's pain in trying to bring as brief as possible, as clean as possible. Yeah. [/INST] Yeah. So it's the way I think of it is um you know it's a little book of big science and big ideas. </s><s>[INST] Really big ideas and in brief little packages [/INST] and you know I wrote it um so that people could read it, I love reading on the beach. I love reading essays on the beach. I read it, I wrote it so people could read it on the beach or in the bathtub or you know a subway stop </s><s>[INST] even if the beach is frozen over the snow. [/INST] So my husband dan calls it the first neuroscience beach read. That's his um that's his phrasing. Yeah </s><s>[INST] and like you said you learn a lot about writing from your husband, like you were saying offline. [/INST] Well he's he is of the two of us, he is the better writer. He's a masterful writer. Um He um he's also I mean he you know he's a PhD in computer science, he's a software engineer but he's he's also really good at organization of knowledge. So he built for a company he used to work for, he built one of the first knowledge management systems and he's he now works at google where he does engineering education. Like he's he understands how to tell a good story uh just you know about anything really. Um He's got impeccable timing, he's really funny and luckily for me he knows very little about psychology or neuroscience well now he knows more obviously but so you know he was really when how emotions were made um you know he was really really helpful to me because um the first draft of every chapter was me talking to him about what you know I would talk out loud about what I wanted to say and the order in which I wanted to say it and then I would write it and then he would read it and tell me all the bits that could be excised and sometimes we would, you know, I should say, I mean, we don't he and I don't really argue about much except um, directions in the car. Like where that's where that's if we're going to have an argument that's going to be, where it's going to happen, Where </s><s>[INST] what's the what's the nature of the argument about directions? Exactly. I don't [/INST] really know. It's just that we're very, I think it's that spatially, you know, he um I use egocentric space. So I want to say, you know, turn left. Like I was I'm reasoning in relation to like my own physical corporeal body. So, you know, you walk to the church and you turn left and you then, you know, whatever, you know, I'm always like and his, you know, he gives directions, um, Alice centric li which means um organized around north, south, east, west. </s><s>[INST] So to you, the earth is at the center of the solar system. And to him, [/INST] no, I'm reasonably I'm at the you're at </s><s>[INST] the center of the solar system. Okay, So [/INST] anyway, so we but but here we, you know, we we had some really rip roaring arguments, like really rip roaring arguments where he would say like, who is this for? Is this for the 1%. And I'd be like 1% meaning not, you know, not wealth, but like civilians versus academics are these for the scientists are for the citizens, for the civilians, right? He speaks for the for the </s><s>[INST] people. For the speaks [/INST] for the people. And I'd be like, no, you have to. And so he made, you know, after one terrible argument that we had, where it was really starting to affect our relationship because we were so mad at each other all the time. He made these little signs, writing and science and we only use them. This, this was like, when you, when you pulled out a sign, that's it. Like the other person just wins and you have to stop fighting about it. And that's it. And so we just did that. Um, and we didn't really have to use it too much for this book because this book was in some ways. Um, uh, you know, I didn't have to learn a lot of new things for this book. I had to learn some, but I, a lot of, um, what I learned for seven for how emotions are made really stood me in good stead for for this book. So there was a little bit, each essay was a little bit of learning a couple were was a little more than than the small amount, but, um, but I I didn't have so much trouble here. Um, I had a lot of trouble with the first book. Um, but still, even here, you know, um, you know, he would tell me that I could take something out and I really wanted to keep it. And um I think we only use the signs ones. </s><s>[INST] Well, if we could dive in some aspects of the book, I would love that, can we talk about? So one of the essays looks at evolution. Mhm. And uh let me ask the big question uh did the human brain evolved to? Think that's essentially the question that you address an essay. Can you speak to? [/INST] Sure? You know, the big caveat here is that we don't really know why brains evolved the big why questions are called teal theological questions. And um in general, scientists should avoid those questions because we don't know really what we don't know the why. However, for for a very long time the assumption was that evolution worked in a progressive upward scale. That you start off with simple organisms. And those organisms get more complex and more complex and more complex. Now, obviously that's true in some like really general way right? That that um life started off as single cell organisms and things got more complex, but the idea that um that brains evolved in some upward um trajectory from simple brains in simple animals too complex brains in complex animals is called a file a genetic scale. Um and that file a genetic scale is embedded in a lot of evolutionary thinking, including Darwin's actually and and it's been seriously challenged, I would say by modern evolutionary biology. Um and so you know, thinking is something that rationality is something that humans at least in the West really prize as a great human achievement. And so the idea that the most common evolutionary story is that, you know, brains evolved in um like sedimentary rock um with, you know, a layer for instincts, that's your lizard brain and a layer on top of that uh for emotions, that's your limbic system, limbic meaning border. So it borders the parts that are for instincts, so interesting. And um and then um the neocortex or new cortex where um rationality is supposed to live, that's the sort of traditional story just keeps getting </s><s>[INST] layered on top [/INST] by </s><s>[INST] evolution. Right? [/INST] So you can think about, you know, I mean sedimentary rock is the way typically people describe it, the way I sometimes like to think about it is um you know, thinking about the cerebral cortex like uh icing on an already baked cake, you know um where you know, the cake is your inner beast, these like boiling, you know, roiling instincts and emotions that have to be contained and that that by the cortex and that it's just it's a fiction. It's a myth. It's a myth that you can trace all the way back to stories about morality in ancient Greece. But what you can do is look at the scientific record and say, well there there's others, there are other stories that you could tell about brain evolution and and the context in which brains evolved. So when you look at creatures who don't have brains and you look at creatures who do what's the difference. And you can look at you know some animals um so we call scientists call an environment that an animal lives in a niche there environmental niche. What are the things, what are the parts of the environment that matter to that animal? And so there's some animals whose Niche hasn't changed in 400 million years. So they're they're not these creatures are modern creatures but they're living in a niche that hasn't changed much. And so their biology hasn't changed much. And you can kind of verify that by looking at the genes that lurk deep, you know in the molecular structure of cells. And so you can by looking at various animals in their developmental state, meaning not, you don't look at adult animals. You look at embryos of animals and developing animals. You can see you can piece together a different story and that story is that brains evolved under the selection pressure of hunting that in the Cambrian period hunting emerged on the scene where animals deliberately 81 another and what so you know before the Cambrian period, the animals didn't really have, well they didn't have brains but they also didn't have sense is really very very rudimentary senses. So the animal that I wrote about in um 7.5 lessons is called an anti oxus or a landslip and little and the oxus has no eyes, it has no ears, it has no knows it it has no eyes, It has a couple of cells for um detecting light and dark for circadian rhythm purposes. So and it it can't hear, it has a vestibular cell to keep its body upright. It has a very rudimentary sense of touch and it doesn't really have any internal organs other than this like basically stomach. It's like a just like a it doesn't it doesn't have an enteric nervous system, it doesn't have like a gut that you know moves like we do. It just has basically a tube. So it's like like a little container yet. And so and really it doesn't it doesn't move very much, it can move, it just sort of wriggles, it doesn't have very sophisticated movement. And it's this really sweet little animal, it's sort of wriggles its way to a spot and then plants itself in the sand and just filters food as the food goes by. Um And then when the food concentration decreases, it just it just ejects itself wriggles to some spot randomly where probabilistic lee there will be more food and plants itself again. So it's it's not it's not really aware very aware that it has an environment, it has a niche but that niche is very small and it's not really experiencing that niche very much. Um So it's basically like a little stomach on a stick that's that's really what it is and um but but when animals start to literally hunt each other um all of a sudden it becomes important to have to be able to sense your environment because you need to know is that blob up ahead, going to eat me or should I eat it? And so all of a sudden you want distant senses are very useful. And so in the water distance senses our vision and a little bit hearing, um Olfaction, smelling and touch because in the water touches a distant sense because you can feel the vibration. So it's right. So in um on air on land vision is a distant sense touch. Not so much but for elephants maybe right. Um the vibrations, vibrations um Well faction definitely because of the concentration of you know the more concentrated something is, the more likely it is to be close to you. So animals developed senses, they developed a head like a literal head. So antitoxin doesn't even have a head really, It's just a </s><s>[INST] what's the purpose of a head? [/INST] That's a great question. </s><s>[INST] Is it, is it to have a jaw? [/INST] That's a great question. So jaw. So yes, jaws are a major um useful feature. Yeah, obviously there are major adaptation after there's a split between vertebrates and invertebrates. So anti oxus is thought to be very very similar to the animal that's before that split, but then after the development very quickly after the development of a head is the development of a jaw which is a big thing. And um and what goes along with that is the development of a brain? </s><s>[INST] It's weird is that just a coincidence that the thing the part of our body of the mammal, I [/INST] think body </s><s>[INST] that we eat with and like attack others with is also the thing that contains the uh all the majority of the brain type of, well [/INST] actually the brain goes with the development of a head and the development of visual system and an auditory system and an olfactory system and so on. So um your senses are developing and um and the other thing that's happening right is that animals are getting bigger? Yeah because their and also their niche is getting bigger. </s><s>[INST] Well this is just sorry to take a tiny tangent on the niche thing is uh it seems like the niche is getting bigger but not just bigger, like more complicated, like shaped in weird ways. So like predation seems to create right? Like the whole world becomes your oyster whatever, but like you also start to carve out like the places in which you can operate the best. [/INST] Yeah. And in fact that's absolutely right. And in fact some scientists think that theory of mind, your ability to make inferences about the inner life of of other creatures actually developed under the selection pressure of predation because it makes you a better predator. </s><s>[INST] Do you ever look at, you just said you looked at babies as these wiring creatures? Do you ever think of humans as just clever predators like that? There is under underneath it all. Is this uh the Nietzschean will to power in all of its forms or are we now friend there? [/INST] Yeah. So it's interesting. I mean there there are zeitgeist sin, how humans think about themselves, right? And so if you look in the 20th century, you can see that um the idea of an inner beast that we're just predators were just basically animals, baseless animals, violent animals that have to be contained by culture and by our prodigious neocortex um really took hold particularly after World War One and really um held sway for much of that century. Um and then around at least in Western writing, I would say, you know, we were talking mainly about Western Western scientific writing, Western philosophical writing and and then You know, late 90s maybe um you start to see books and articles about our social nature that we're social animals and we are social animals. But what does that mean? Exactly? And um about </s><s>[INST] it's us covering out different issues in the space of ideas. It [/INST] looks. I think so. I think so. So um so you know, do um humans um art, can humans be violent? Yes. Can humans be really helpful? Yes actually. And humans are interesting creatures because you know, other animals can also be helpful to one another. In fact there's a whole literature booming literature on how other animals um are um you know, support one another. They regulate each other's nervous systems in in interesting ways and they will be helpful to one another, right? So for example, there's a whole literature on rodents and how um they um they signal one another what is safe to eat and uh they um will um perform uh acts of generosity to their con specifics that are related to them or or who they were raised with. So if an animal was raised in a litter that is that they were raised in, although not even at the same time, they'll be more likely to help that animal. So there's always some kind of physical relationship between animals um that predicts whether or not they'll help one another for humans. Humans. You know, we have ways of categorizing who's in our who's in our group and who isn't by non physical ways right? By even by just something abstract, like an idea and we are much more likely to extend help to people in our own group, whatever that group, maybe at that moment, whatever your whatever feature you're using to define who's in your group and who isn't um we're more likely to help those people, then even members of our own family at times. So humans are much more flexible in their in the way that they help one another, but also in the way that they harm one another. So I don't um I don't I don't think I subscribe to um you know, we are primarily this or we are primarily that I don't think have humans have essences in that way really, </s><s>[INST] I apologize to take us in this direction for a brief moment, but I've been really deep on Stalin and Hitler recently uh in terms of reading and is there something that you think about in terms of uh the nature of evil from a neuroscience perspective? Is there some lessons that are sort of hopeful about human civilization that we can find in our brain with regard to the hitlers of the world? Do you do you think about the nature of evil? [/INST] Yeah, I do. I don't know that what I have to say is so useful from a I don't know that I can say is a neuroscientist. Well here here's a study that you know what I so I I sort of have to take off my lab coat, right? And now I'm gonna now conjecture as a human who just also who has opinions but who also maybe has some knowledge about neuroscience, but I'm not speaking as a neuroscientist when I say this because I don't think neuroscientists know enough really to be able to say, but I guess the kinds of things I think about our um what, so I have always thought even before I knew anything about neuroscience. Um I've always thought that um I don't think anybody could become Hitler, but I think the majority of people can be can do are capable of doing very bad things. Um it's just the question is really, how much encouragement does it take from the environment to get them to do something bad. </s><s>[INST] That's what I kind of, when I look at the life of Hitler, it seems like there's so many places where [/INST] something could have intervened </s><s>[INST] into the changed completely the person. I mean, there's like the caricature, like the obvious places where he was an artist, and if he wasn't rejected as an artist, he was a reasonably good artist, so that that could have changed, but just his entire, like where he went in Vienna and all these kinds of things, like little interactions could have changed, and there's probably millions of other people who are capable who the environment may be able to mold in the same way did this particular person to create this particular kind of charismatic leader in this particular moment of time. [/INST] Absolutely. And I guess the way I would the way that I would say, I I would agree 100% and I guess the way that I would say it is like this in the west, we have a way of reasoning um about causation which focuses on single simple causes for things, you know, there's a there's an essence to Hitler, there's an essence to his character, He was born with that essence or it was forged very, very early in his life and that explains the um the landscape of his horrible landscape of his behavior. But there's another way to think about it away that actually is much more consistent with what we know about biology, how biology works um in the physical world. And that is that most things are complex, not as in, wow, this is really complex and hard, but complex as in complexity, that is more than the sum of their parts. And that most phenomena have many, many weak nonlinear interacting causes. And so little things that we might not even be aware of can shift someone's developmental trajectory from this to that. And that's enough to take it on a whole set of other paths that, you know that and that these things are happening all the time. So it's not random and it's not really, it's not deterministic in the sense that like everything you do determines your outcome. But it's a little more like um you know, you're nudging someone from one set of possibilities to another set of possibilities. And I but I think the the thing is the thing that I find optimistic is that the the other side of that coin is also true. Right? So look at all the people who risked their lives to help people. They didn't even know. I mean, I just watched Borat the new Borat movie and the thing that I came away with but you know the thing I came away with was look at how generous people were in that because he's making, there are a lot of people he makes fun of and that's fine. But think about like those two guys, those </s><s>[INST] the trump supporters trump [/INST] supporter guys, those guys, </s><s>[INST] those kind, there's kindness in them, right? [/INST] They took a complete stranger in a pandemic into their house. Who does that? Like that's a really nice thing. Or there's one scene, I mean I want to spoil it for people haven't seen it, but but there's you know, there's one scene where he goes in, he dresses up as a jew. Yeah, I laughed myself sick at that scene seriously. But um but he goes in and he and there are these two old jewish ladies. What a bunch of sweethearts. Oh my gosh, like really? I mean that was what I was struck by actually. I mean there are other ones or like the babysitter, right? I mean she was really kind and yeah, so that's really what I was more struck by like, you know, sure there are other people who you know who do do very bad things or say bad things or whatever, but you know, we're like there's one guy who's completely stoic like the guy at the um who's doing the like, you know, sending the messages. I don't know if it's facts or whatever. He's just completely stoic but he's doing his job actually, you know, like you can't, you don't know what he was thinking inside his head. You don't know what he's feeling and he was totally professional doing his job. Okay. So I guess I just, I had a bit of a different, um, you know, view, I guess. And I, so I also think that about people, I think everybody is capable of kindness and um, but you know, it's the question is, how much does it take and what are the circumstances? So for some people, it's going to take a lot, and for some people it only takes a little bit, but you know, are we actually cultivating an environment for the next generation that um, provides opportunities for people to go in the direction of caring and kindness or, you know, and I'm not, I'm not saying that is like a, you know, Pollyanna ish person. Um, uh you know, I think there's a lot of room for competition and debate and and so on. Um, but I don't see Hitler as an anomaly and I never have, that was even before I learned anything about neuroscience and now I would say, knowing what we know about developmental trajectories and life histories and how important that is. Um, you know, knowing what we know about, um, that the whole question of like nature versus nurture is a completely wrong question. You know, we have the kind of nature that requires nurture, we have the kind of genes that allow infants to be born with unfinished brains where the brains, their brains are wired across a 25 year period with wiring instructions from the world that is created for them. And so I don't think Hitler is an anomaly. Um even if it's, even if it's less probable that that would happen, it's possible that it could happen again. And it's not, it's not like he's a bad seed. I mean that doesn't, I just wanna say for like of course he's completely 100% responsible for his actions and all the bad things that happened. So I'm not in any way, this is not me saying, </s><s>[INST] but the environment is also responsible in part for creating the evil in this world. So, like Hitler's in different versions of more subtle, more smaller scale versions of evil, but I tend to believe that there is a much stronger uh I don't like to talk about evolutionary advantages, but it seems like it makes sense for love to be a more powerful uh emergent phenomena of our collective intelligence versus hate and evil and destruction because from a survival from a niche perspective, it seems to be like in my own life and my thinking about the intuition about the way humans work together to solve problems. It seems that love is a very useful tool. [/INST] I definitely agree with you. But I think the caveat here is that um, you know, humans, the research suggests that humans are are capable of great acts of kindness and great acts of generosity to people in their in group, Right? And </s><s>[INST] we're also tribal. [/INST] Yeah. I mean that's the that's the kitschy way to say it where tribes were tribal. Yeah. So that's the kitschy way to say it. What I would say is that, you know, there are a lot of features that you can use to describe yourself. You don't have one identity, You don't have one self. You have many selves. You have many identities. Um, sometimes you're a man, sometimes you're a scientist, sometimes you're a you have a brother or a sister brother. So sometimes your brother, you know, you you sometimes your friend </s><s>[INST] as your human. So you can keep zooming out. Yes. Living organism on [/INST] earth. Yes, exactly. That's exactly. That's exactly right. And so there are there are some people who there is research which suggests that there are some people who will tell you, I think it's appropriate and better to help. I should help my family more than I should help my neighbors. And I should help my neighbors more than I should help the average stranger. And I should help. Um, you know, the average stranger in my country more than I should help somebody outside my country and I should help humans more than I should help, you know, other animals. And right. So there's a clear hierarchy of helping and there are other people who um, you know, they are, their niche is much more inclusive, right? And that they're humans first, right? Or or creatures of the earth first, let's say. Um and I don't think we know how flexible those attitudes are because I don't think the research really tells us that, but in any case there are, you know, and there are beliefs people also have beliefs about. There's this really interesting research in um really an anthropology um, that looks at what are cultures particularly afraid of, like what the people in a particular culture are organizing their social systems to prevent certain types of problems. So what are the problems that they're worried about? And so there are some cultures that are much more hierarchical and some cultures that are, you know, much more egalitarian. There are some cultures that, you know, in the debate of like getting along versus getting ahead. There are some cultures that really prioritize the individual over the group and there are other cultures that really prioritize the group over the individual. You know, it's not like one of these is right and one of these is wrong. It's that, you know, different combinations of these features are different solutions that humans have come up with for, for living in groups, which is a major adaptive advantage of our species. Um, and it's not the case that one of these is better in one of these is worse, although as a person, of course I have opinions about that and as a person I can say I would very much prefer certain, I have certain beliefs and I really want everyone in the world to live by those beliefs you know? But as a scientist I know that it's not really the case that for the species any one of these is better than any other. There are different solutions that work differential e well in particular, you know ecological parts of the world. But for individual humans, there are definitely some systems that are better in some systems that are worse, right? But when when anthropologists or when neuroscientists are biologists are talking, they are not usually talking about the lives of individual people, they're talking about, you know the species, what's better for the species? The survivability of the species and what's better for the survivability of the species is variation that we have lots of cultures with lots of different solutions because if the environment were to change drastically um some uh some of those solutions will work better than others. And you can see that happening with covid. </s><s>[INST] Right? So some people might be more susceptible to this this virus than others. And so variation is very useful. Say covid was much much more destructive than it is. And like I don't know, 20% of the population was died. Ah you know that's it's good to have variability because then at least some percent will survive. [/INST] Yeah, I mean the the you know the way that I used to describe it was you know um using a you know those movies like the war of the worlds or um pacific rim you know where like aliens come down from outer space and they you know want to kill humans. And so all the humans band together as a species like and they all like all the you know little squabbling from countries and whatever all you know goes away and everyone is just one big you know well uh that you know that doesn't happen. I mean because Covid is you know the via virus uh Like co like COVID-19 is like a creature from outer space and that's not what you see happening, what you do see happening. It is true that some people, I mean we could use this as an example of essential is um also so just to say like exposure to the virus does not mean that you will become infected with a disease. So I mean in controlled studies One of which was actually a coronavirus, not COVID. But this was these are studies from tens years ago. You know only somewhere between 20 and 40% of people uh were developed respiratory illness when a virus was placed in their nose. Um And so </s><s>[INST] there's a dose question all those [/INST] not in these studies actually. So in these studies the dose was consistent across all people um and everything you know they were sequestered in hotel rooms and what they ate was you know um measured out by scientists and so on. And so when you hold does I mean the dose issue is a real issue in the real world but um in these studies that was controlled Um and only somewhere between depending on the study between 20 and 40% of people became infected with a disease. So exposure to a virus doesn't mean de facto that you will um develop an illness, you will be a carrier and you will spread the virus to other people. But you yourself may not uh your immune system may be um in a state that um you can make enough antibodies to um not uh not show symptoms, not develop symptoms. Um And so um of course what this means is again is that you know like if I asked you, do you think you know a virus is the cause of of of a common cold or you know most people if I asked this question, I can tell you, I asked this question. So do you think a virus is the cause of a cold? Most people would say yes I think it is. And then I say yeah, well only 20 to 40% of people develop respiratory illness in exposure to a virus. So clearly it is a necessary cause, but it's not a sufficient cause. And there are other causes again, so not simple single causes for things, right? Multiple interacting influences. So it is true that individuals vary in their susceptibility to illness upon exposure. But different cultures have different sets of norms and practices that allow that will slow or or speed the spread. And that's the that's the point that I was actually trying to make here that that you know, when the environment changes, that is, there's a mutation of the virus that is incredibly infectious. Some cultures will succumb, people in some cultures will succumb faster because of the particular norms and practices that they've developed in their culture versus other cultures. Now there could be some other, you know, thing that changes that where those other other cultures are, you know, would do very so very individualistic cultures like ours may do much better under other types of selection pressures. But for covid for things like Covid, you know, my colleague Michelle Guelph font, her research shows that she she looks at like loose cultures and tight cultures, cultures that have very, very strict rules versus cultures that are much more individualistic and where personal freedoms are more valued. And she, you know, her research suggests that for pandemic circumstances, tight culture is actually the people survive better. </s><s>[INST] She still lingering a little bit longer. We started this part of the conversation talking about, you know, did humans evolved to think did the human brain involved to think, implying is there like a progress to the thing that's always improving? [/INST] That's right, We never. Yeah. And so the answer is no, </s><s>[INST] but let me sort of pushback. But so your intuition is very strong here and not your intuition the way you describe this, But is it possible? There's a direction to this evolution? Like do you think of this evolution as having a direction? Like it's like walking along a certain path towards something, you know, what is it? Uh the Elon musk said like the earth got bombarded with photons and then all of a sudden like a Tesla was launched into space or whatever, rockets started coming. Like is there a sense in which even though in the like within the system, the evolution seems to be this mess of variation. We're kind of trying to find our niches and so on. But do you think they're ultimately when you zoom out there is a direction that strong, that does tend towards um greater complexity and intelligence? [/INST] No, So, I mean, and I and again, what I would say is I'm really, I'm really just echoing people who are much smarter than I am about this. </s><s>[INST] But you're saying smarter. I thought it doesn't there's no that I thought there's no smarter. [/INST] No, I didn't say there is no smarter. I said there's no direction. So I think the thing to say or what I understand to be the case is that um, there's variation. It's not unbounded variation. And there are selectors. There are there are there are pressures that will select and so not anything is possible because we live on a planet that has certain physical realities to it, right? Um but those physical realities are what constrained the possibilities. Um the physical realities of our genes and the physical realities of our corporeal bodies and the physical realities of um uh you know, the of life on on this planet. So what I would say is that there's no direction, but uh there is it's not infinite possibility because we live on a particular planet that has particular statistical regularities in it and some things will never happen. And so all of those things are interacting with um uh with our genes and so on. And are you know the physical nature of our bodies to make some things more possible and some things less possible. Look, I mean humans have very complex brains, but birds have complex brains. And so do uh you know um so do octopuses have very complex brains. And all three sets of all three of those brains are are somewhat different from one another. You know, bird birds, some birds have very complex brains. Some even have rudimentary language. They have no cerebral cortex. I mean they admittedly they have, this is now less than two. Right? They have, is it less than two or less than one? Let me think. No, this is less than one. They have um uh They have the same neurons, the same neurons that the human become the cerebral cortex. Birds have those neurons, they just don't form themselves into a cerebral cortex. But I mean crows for example are very sophisticated animals. They can do a lot of the things that humans can do. In fact all of the things that humans do that are very special that seem very special. There's at least one other animal on the planet that can do those things to. What's special about the human brain is that we put them all together. So we learn from one another. We don't have to experience everything ourselves. We can watch another animal or another human experience something and we can learn from that. Well there are many other animals who can learn by copying that we communicate with each other very, very efficiently. We have language but we're not the only animals who are efficiently efficient communicators. There are lots of other animals who can efficiently communicate like bees for example. Um You know, we cooperate really well with one another to do grand things. But there are other animals that cooperate to. And so every innovation that we have other animals have to, what we have is we have all of those together interwoven in this very complex dance in a brain that is not unique. Exactly. But that is, you know it does have some features that make it use that make it particularly useful for us um to do all of these things uh you know to have all of these things intertwined. So you know our brains are actually the last time we talked, I I made a mistake because I said um in my enthusiasm I said you know our brains are are not larger, are relative to our bodies, our brains are not larger um than um than other primates. And that's actually not true. Actually. Our our brains relative to our body size is somewhat larger. So an ape who is not a human that's not a human. Um Their brains are larger than their body sizes than say relative to like a smaller monkey. And a human's brain is larger relative to its body size than a good </s><s>[INST] approximation of [/INST] your </s><s>[INST] of whatever of of the bunch of stuff that you can shove in there. [/INST] But what I was going to say is but our cerebral cortex is not larger then what you would expect for a brain of our of of of of its size. So so relative to say an ape, like a like a gorilla or a chimp or even a mammal, like a dolphin or an elephant. Um you know, our brains, our cerebral cortex is as large as you would expect it to be for a brain of our size. So there's nothing special about our cerebral cortex and this is something I explain in the book where I say, okay, you know like by analogy um if you walk into somebody's house and you see that they have a huge kitchen, you know, you might think, well, maybe, you know, maybe this is a place I really definitely want to eat dinner at because you know, these people must be gourmet cooks, but you don't know anything about what the size of their kitchen means unless you consider it in relation to the size of the rest of the house. If it's if it's a big kitchen in a really big house, it's not telling you anything special, right? If it's a big kitchen in a small house, then that might be a place that you want to eat, you want to stay for dinner because it's more likely that that kitchen is large for a special reason. And so the cerebral cortex of the human brain isn't in and of itself special because of its size. However, there are some genetic changes that have happened in the human brain as it's grown with whatever sizes, you know, typical for for the whole brain size, right? There are some changes that do give the human brain slightly more of some capacities, they're not special, but there's just they just, you know, we can do some things much better than other animals and correspondingly other animals can do some things Much better than we can, we can grow back limbs, we can't lift 50 times our own body weight. Well, I mean, maybe you can, but I can't live 50 </s><s>[INST] times dance with that regard are very impressive. And then you're saying with the frontal cortex, like that's the size is not always the right measure of capability, I guess. So size isn't everything. [/INST] Size isn't everything </s><s>[INST] that's a quota. But people like it when I disagree. So let me disagree with you on something or just like play Devil's advocate a little bit. So you've painted a really nice picture that evolution doesn't have a direction. But is it possible if we just ran Earth over and over again, like this video game that the final result will be the same? So in a sense that were eventually there will be an A. G. I. Type hal 9000 type system that just like flies and colonize is nearby uh Earth like planets and it always will be the same. And and the different organisms and the different evolution of the brain, like it doesn't feel like it has like a direction. But given the constraints of Earth and whatever, this imperative, whatever the hell is running this universe, like it seems like it's running towards something. Is it possible there will always be the same, thereby it will be a direction. [/INST] Yeah. I think, you know, as you know better than anyone else that the answer to that question is of course there's some probability that that could happen right? It's not a yes or no answer. It's what's the probability that that would happen and there's a whole um distribution of possibilities. So maybe we end up what's the probability we end up with exactly the same uh complement of creatures um including us. What's the likelihood that we end up with, you know, creatures that are similar to humans that are but you know, similar in certain ways, let's say, but not exactly humans or you know, all the way to a completely different um distribution of creatures. What's the </s><s>[INST] intuition like if you were to bet money, what does that distribution look like if we ran earth over? And so I [/INST] would say given the um you're not asking me questions that this is not science, this is not science. So, but I would say, okay well what's the probability that it's going to be a carbon life form? Probably high. But that's because I don't know anything about </s><s>[INST] really. Yeah. [/INST] You know, I don't I'm not I'm not really well versed that. Um what's the probability that, you know, So what's the probability that the animals will begin in the ocean and crawl out onto land versus I would say probably high, I don't know. But you know. But do I think what's the likelihood that we would end up with exactly the same or very similar? I think it's low actually, I I wouldn't say it's low, but I would say it's not it's not 100% and I'm not even sure it's 50%. You know, I would say I don't think that we're here by accident because I think, like I said, there are constraints, like there are some physical constraints about Earth. And of course, if you were a cosmologist, you could say, well, the fact that the earth is, if you were to do the big bang over again and keep doing it over and over and over again, would you still get the same solar systems, would you still get the same planets? Would you know, would you still get the same Galaxies, the same solar systems? The same planets? You know, I don't know. But my guess is probably not. Um, because there are random things that happen that can again send things in one day you make one set of trajectories possible and another set impossible. So, um, but I guess my mike my if I were going to bet something money or something valuable, I would probably say It's not zero and it's not 100% and it's probably not even 50%. So there's some probability, but it will be similar. That would be similar. But I don't think I just think there are too many degrees of freedom. There are too many degrees of freedom. I mean, one of the real tensions in writing this book is to on the one hand, there is some truth in saying that humans are not special. We are just, you know, we're not special in the animal kingdom. All animals are um, well adapted if they're survived, they're well adapted to their niche. It does happen to be the case that our niche is large for any individual human, your niche is whatever it is, but for the species, right? We live almost everywhere, not everywhere, but almost everywhere on the planet, but not in the ocean. And actually other animals like bacteria for example have us beat miles, you know, hands down. Right. So we're by any, by any definition, we're not special. We're just, you know, adapted to our environment. Bacteria don't have a podcast. Exactly. Exactly. And that's the so that's the tension. Right? So on the one hand, you know, we're not special animals were just, you know, you know particularly well adapted to our niche. On the other hand are niche is huge and we, you know, we don't just adapt to our environment. We add to our environment. We make stuff up, give it a name and then it becomes real. And so no other animal can do that. And so I think the the thing, the way to think about it from my perspective or the way I made sense of it is to say you can look at any individual single characteristic that a human has that seems remarkable and you can find that in some other animal, what you can't find in any other animal is all of those characteristics together in a brain that is souped up in particular ways like ours is and if you combine these things multiple interacting causes, right? Not one, not one essence, like your cortex, your big neocortex, but um which isn't really that big. I mean it's just big for for your big brain, for the size of your big brain. It's that it's the size it should be. Um If you add all those things together and they interact with each other, that produces some pretty remarkable results and if you're aware of that, then you can start asking different kinds of questions about what it means to be human and what kind of a human you want to be and what kind of a world do you want to curate for the next generation of humans? So I think that's the goal anyways, right. It's just to just have a glimpse of instead of thinking about things in a simple linear way. Just have a glimpse of the some of the things that matter that seemed that evidence suggests matters. Um to um the kind of brain in the kind of bodies that we have um once you know that you can you can work with it a little bit, </s><s>[INST] you write words have power over your biology right now. I can text the words, I love you from the United States to my close friend in Belgium and even though she cannot hear my voice or see my face, I will change her heart rate, her breathing and her metabolism by the way beautifully written. Or someone could text something ambiguous to you. Like Is your door locked? And odds are that it would affect your nervous system in an unpleasant way? So, I mean, there's a lot of stuff to talk about here, but just one way to ask is um why do you think words have so much power over our brain? [/INST] Well, I think we just have to look at the anatomy of the brain to answer that question. So, um if you look at the parts of the brain, the whole the systems that are important for processing language, you can see that some of these regions are also important for controlling your major organ systems. And you're like your autonomic nervous system that controls your cardiovascular system, your respiratory system and so on, that. You know, these regions control your uh endocrine system, your immune system and so on. So, and you can actually see this in other animals too. So in birds, for example, the neurons that are responsible for birdsong also control the systems of a bird's body. And the reason why I bring that up is that the there's some scientists think that the anatomy of a bird's brain that control birdsong are homologous or structurally have a similar origin to the human system for language. So the parts of the brain that are important for processing language are not unique in uh specialist for language. They do many things and one of the things they do is um control your major organ systems. </s><s>[INST] You think we can fall in love of arguments about this all the time. Uh Do you think we can fall in love based on words alone? [/INST] Well, I think people have been doing it for centuries. I mean they used to be the case that people wrote letters to each other. Um you know, and then that was how they communicated. And I guess that's how you and down. Exactly. Exactly. Exactly. Exactly. Yeah, exactly. </s><s>[INST] So is the answer a clear yes there because I get a lot of pushback from people often that you need you need to touch in the smell and uh you know the bodily stuff. [/INST] I think the touch and the smell and the bodily stuff helps. Okay. But I don't think it's necessary. </s><s>[INST] Do you think you're going to have a lifelong monogamous relationship when the ai system that only communicates with you on text? Romantic relationship? [/INST] Well, I suppose that's an empirical question that hasn't been answered yet. But I guess what I would say is um I don't think I could could any human could the average human could, you know, so so um if I if I I even I want to even I wanna even modify that and say I'm thinking now of um tom Hanks um and um the movie castaway? Yeah. You know with Wilson. Yeah, I think if that was if you had to make that work, if you had to make that work </s><s>[INST] with the volleyball. Yeah, [/INST] if you had to make it work, could you you could you prediction and simulation right? So if you had to make it work, could you make it work using simulation? And you know, your past experience. Could you make it work? </s><s>[INST] Could you make it work? You as a human? Could you could you [/INST] could you have a, could you have a relationship literally with an inanimate object and have it sustain you in the way that another human could um your life would probably be shorter because you wouldn't actually derive the body budgeting benefits from. Right? So we've talked about uh you know how um your brain, it's most important job is to control your body. And you can describe that as your brain running a budget for your body. And um there are metaphorical, you know, deposits and withdrawals into your body budget and you also make deposits and withdrawals in other people's body budgets figuratively speaking. So you wouldn't have that particular benefit. Uh so your life would probably be shorter. But I think it would be harder for some people than for other people. </s><s>[INST] To my intuition is that you can have a deep fulfilling relationship with volleyball. I think I think a lot of the the environments that set up. I think that's a really good example, like the constraints of your particular environment to find that like I believe like scarcity is a good catalyst for deep meaningful connection with other humans and with inanimate objects. So the less you have, the more fulfilling those relationships are. And I would say relationship with the volleyball, the sex is not great, but everything else, I feel like it could be a very fulfilling relationship, which I don't know from an engineering perspective what to do with that. Just like I said, it is an empirical question, but [/INST] there are places to learn about that, right? So for example, think about Children and their blankets. Right? So there there's something tactile and there's something old factory and it's very comforting. I mean, even for even for non human little animals, right? Like puppies. And so I don't know about cats, but but </s><s>[INST] cats are cold hearted there? And there there's no, there's nothing going on there. [/INST] I don't know. There are some cats that are very dog. Like I mean really? So </s><s>[INST] some cats identifies dogs. [/INST] Yes, I think that's true. Yeah, there there are some species fluid. So </s><s>[INST] you also, right, when it comes to human minds variation is the norm and what we call quote, human nature is really many human natures again, many questions I can ask here, but maybe an interesting I wanted to ask is um, I often hear, you know, we often hear this idea of be yourself. Uh is this possible to be yourself? Is it a good idea to strive to be yourself, is it, does that even have any meaning? [/INST] It's a very Western question first of all because which self are you talking about? You don't have one self, There is no self, that's an essence of you. You have multiple selves. Actually, there's research on this. Um you know, to quote um the great social psychologist hazel Markus, you're never you cannot be a self by yourself. You you know, you and so different context pull for or or draw on different features of your of who you are or what your what you believe, what you feel, what your actions are. Um different context. You know, we'll put certain things make more, some features be more in the foreground and and some in the background. It takes us back right to our discussion earlier about um Stalin and Hitler and so on. The thing that I would caution in addition to the fact that there is no single self, you know that you have multiple selves who you can be. Um and you can certainly choose the situations that you put yourself in to some extent, not everybody has complete choice, but everybody has a little bit of choice. And I think I said this to you before that one of the pieces of advice that we gave Sophia, you know when she went our daughter when she was going off to college was um try to spend time around people choose relationships that allow you to be your best self, we should have said your best selves, but the the </s><s>[INST] pool of cells given the environment. [/INST] Uh but I I the one thing I do want to say is that um the risk of saying be yourself, just be yourself is that um that can be used as an excuse? Well, this is just the way that I am, I'm just like this and that I think should be tremendously resistant. </s><s>[INST] So that's one that's that's for the excuse side. But you know, I'm really self critical often, I'm full of doubt and people often tell me it's just don't worry about it. Just be yourself man. It's the thing is uh almost it's not from an engineering perspective does not seem like actionable advice because I guess constantly worrying about who, what are the right words to say to express how I'm feeling is I guess myself there's there's a kind of line I guess that this might be a western idea, but something that feels genuine and something that feels not genuine and I'm not sure what that means because I would like to be fully genuine and fully open, but I'm also aware like this morning I was like very like silly and giddy I like about it is just being funny and relaxed and light, like there's nothing that could um bother me in the world. I was just smiling and happy and then remember last night was just feeling like very grumpy, like uh like stuff was bothering me, like certain things were bothering me and like what are those are those are different selves? Like what? Who mined that and what do I do? Because if you know if you take twitter as an example, if I actually send a tweet last night and a tweet this morning, it's gonna be very two different people tweeting that and I don't know what to do with that because one does seem to be more me than the other, but that's maybe because there's a narrative story that I'm trying, there's something I'm striving to be like the ultimate human that I might become, I have maybe a vision of that and I'm trying to become that. But it does seem like there's a lot of different minds in there and they're all like like having a discussion and a battle who's going to win. [/INST] I suppose you could think of it that way but there's another way to think of it I think and that is that um maybe the more buddhist way to think of it right? Or more contemplative way to think about it, which is not that you have multiple personalities inside your head but you have your brain has this um amazing capacity. It it has a population of experiences that you've had that it can regenerate, Reconstitute and it can even take bits and pieces of those experiences and combine them into something new um and it's often doing this to predict what's going to happen next and to plan your actions, but it's also happening. This also happens just um that's what mind wandering is or just internal thought and and so on. That's it's the same mechanism really. And so a lot of times we hear the saying, you know, just think if you think differently you'll feel differently but your brain is having a conversation continually with your body and your body, your brains, you know, trying to control your body well trying your brain is controlling your body, your body is sending information back to the brain and in part the information that your body sends back to your brain just like the information coming from the world initiates the next volley of predictions or simulations. So in some ways you could also say the way that you feel you're I think we talked before about effective feeling or mood coming from the sensations of body budgeting, you know, um influences what you think and um as much as so feelings influence thought as much as I thought, influence feeling and maybe more. </s><s>[INST] But just the whole thing doesn't seem stable. [/INST] Well it's a dynamic system. Mr engineer, right? It's a dynamic, it's a dynamical system, right? Nonlinear dynamical system in a way and I think that's I'm actually writing a paper with a bunch of engineers about about this actually. But I mean other people have talked about the brain is a dynamical system before but you know, the real tricky bit is trying to figure out how do you get mental features out of that system? Like it's one thing to figure out how you get a motor movement out of that system. It's another thing to figure out how you get a mental feature, like a feeling of being loved or a feeling of being worthwhile or a feeling of, you know, just basically feeling like sh it how do you get a feeling of mental mental features out of out of that system? So what I would say is that you aren't, the buddhist thing to say is that you're not one person and you're not many people you are. Um you are the sum of your experiences and who you are in any given moment, meaning, what your actions will be is influenced by the state of your body and the state of the world that you've put yourself in. And you can change either of those things. One is a little easier to change than the other, right? You can change your environment by literally getting up and moving or you can change it by paying attention to some things differently and letting other some features um come to the fore and other features be backgrounded. Like I'm looking around your place and I </s><s>[INST] see not something you should do. [/INST] No, I'm not. But I'm going to say one thing, No green plants, no green plants. </s><s>[INST] Because green plants mean a home And I want this to be temporary. [/INST] Fair fair. But </s><s>[INST] what's what's, what goes to your mind when you see no green [/INST] plants? No, I'm just making the point that um, what if you again, you know, not everybody has control over their environment. Some people don't have control over the noise or the temperature or any of those things, but everybody is a little bit of control and you can place things in your environment, photographs, plants, anything that's meaningful to you and use it as a shift of environment when you need it. You can also do things to change the conditions of your body when you exercise every day. You're making an investment in your body. Actually, you're making an investment in your brain to it makes you, even though it's unpleasant and you know, there's a cost to it if you replenish. If you invest and you make up that, um you make a deposit and you make up that um what you've spent, you're basically making an investment in making it easier for your brain to control your body in the future. So you can make sure you're hydrated drink water. You don't have to buy a drink bottled water. You can drink water from the tap. This is in most places. Maybe not. Maybe not everywhere, but, but most places in the developed world, um you can try to get enough sleep. Not everybody has that luxury, but everybody can do something to make their, you know, body budgets a little more solvent. And that will also make it more likely that certain thoughts will emerge from that prediction machine. </s><s>[INST] Exactly. That's the control you do have is uh being able to control the environment that's really well put uh on the I don't think we've talked about this. So let's go to the biggest unanswerable questions of consciousness. What is you just rolled your [/INST] eyes? I did. That was </s><s>[INST] yeah. So what is consciousness from a neuroscience perspective? I know you I mean uh I [/INST] made notes, you know, because you gave me some questions in advance and I made notes for every single except that one. Yeah, well that one I had what the funk when I took it out. </s><s>[INST] So is there something interesting because you're so pragmatic? Is there something interesting to say about intuition building about consciousness? Or is this something that we're just totally cool? It's about that this is uh let's focus on the the body, The brain listens to the body, The body speaks to the brain and let's just figure this piece out and then consciousness will probably emerge somehow after that. [/INST] No, I think, you know, well, first of all, it will just say up front. Um I am not a philosopher of consciousness and I'm not a neuroscientist who focuses on consciousness. I mean, in some sense, I do study it because I study affect and mood and that's that is the um uh you know, to use the phrase, that is the hard question of consciousness. How is it that your brain is modeling your body? Brain is modeling the sensory conditions of your body? It's um and it's being updated. That model is being updated by the sense data that's coming from your body and it's happening continuously your whole life and you don't feel those sensations directly. You what you feel is a general sense of pleasantness or unpleasantness, comfort, discomfort, feeling, worked up feeling calm. So we call that affect most people call it mood. So how is it that your brain gives you this very low dimensional feeling of mood or affect when it's presumably receiving a very high dimensional array of sense data and the model that the brain is running of the body has to be high dimensional because there's a lot going on in there, right? You're not aware. But as you're sitting there quietly as your listeners are our as our viewers are sitting um </s><s>[INST] there might be working out running or as many of them right there laying in bed smoking away with their eyes [/INST] closed, That's fair. So maybe we should say that bit again then. So if so some people may be working out some people maybe uh relaxing, but, you know, even if you're sitting very still while you're watching this, or listening to this, there's a whole drama going on inside your body that you're largely unaware of. Yet your brain makes you aware or gives you a status report in a sense by virtue of these mental features of feeling pleasant, feeling unpleasant, feeling comfortable feeling uncomfortable, feeling energetic, feeling tired and so on. And so how the hell is it doing that? That is the basic question of of consciousness. </s><s>[INST] And like the status reports seem to be in the way we experience them seem to be quite simple. Like it doesn't feel like there's a lot of data. [/INST] Yeah, no there isn't. So when you feel, when you feel um discomfort when you're feeling basically like ship, you feel like ship, what does that tell you? Like, what are you supposed to do next? What caused it? I mean the thing is not one thing caused it right? It's multiple factors probably influencing your physical state, your body budget high dimensional, very high dimensional. Um and that and the there are different temporal scales of influence, right? So um you know, the state of your gut is not just influenced by what you ate five minutes ago, it's also what you ate a day ago and two days ago and and so on. So um so I think the you know, when I'm I'm not trying to weasel out of the question, I just think it's a it's the hardest question actually. </s><s>[INST] Do you think we'll ever understand it? [/INST] I am </s><s>[INST] as scientists, [/INST] I think that we will understand it as well as we understand other things like the birth of the universe or the you know, the nature of the of the universe. I guess I would say so. I do. I think we can get to that level of an explanation. I do actually. But I think that we have to start asking somewhat different questions and approaching the science somewhat differently than we have in the </s><s>[INST] past. It's also possible that consciousness is much more difficult to understand then the nature of the universe. [/INST] It is. But I wasn't necessarily saying that it was a question that was of equivalent complexity. I was saying that I do think that we could get to some. I I am optimistic that I would not, I would be very willing to invest my time, my time on this Earth as a scientist in trying to answer that question. If I could do it the way that I want to do it. Um not in the way that is currently being done </s><s>[INST] so like rigorously, [/INST] I don't want to say on rigorously, I just want to say that there are certain set of assumptions that scientists have, what I would call ontological commitments. Their commitments about the way the world is or the way that nature is and they these commitments lead scientists sometimes blindly without. They don't. Scientists sometimes sometimes scientists are aware of these commitments, but sometimes they're not and these commitments on the list influence how scientists ask questions how what they measure, how they measure. And I I just have very different views than a lot of my colleagues about the ways to approach this. Not everybody. But um, but the way that I would approach it would be different and it would cost more and it would take longer. It doesn't fit very well into the current incentive structure of science. And so do I think that doing science the way science is currently done with the budget that it currently has and the incentive structure that it currently has? Well, we have an answer. No, I think absolutely not. Good luck is what I would say. </s><s>[INST] People love book recommendations. Let me ask what three [/INST] books you can't just like you can't just give me three. I mean like really three </s><s>[INST] what, 7.5 books you can recommend. So you're also out there 7.5 lessons about the brain your author of how emotions are made. Okay, so definitely those are the top two recommendations of all the two greatest books of all time. Other than that. Are there books that technical fiction, philosophical that you've enjoyed or you might recommend to others. Yes. [/INST] Actually, you know every PhD student when they um, when they graduate with a PhD I gave them a set like a little library, like a set of books, you know, some of which they've already read, some of which I want them to read or um, but um, I think nonfiction books I would read. The things I would recommend are the triple helix by uh Richard Lamontagne. It's a little book published in 2000, which is um I think a really good introduction to complexity and um population thinking as opposed to essential is um so this idea essential is um is this idea that, you know, there's an essence to each person, whether it's a soul or your jeans or what have you as opposed to this idea that you we have the kind of nature that requires a nurture. We are we are you are the product of a complex dance between um an environment between a set of genes and environment. Um that turned those genes on and off to produce your brain and your body and really who you are at any given moment </s><s>[INST] title for that triple helix. So playing on the double helix where it's just the biology, it's bigger than the biology. [/INST] Exactly. Um it's a wonderful book. I've read it probably six or seven times throughout the year. He has another book to which is it's more I think scientists would find it. I don't know, I've loved it. It's called biology as ideology and it really is all about, I wouldn't call it one of the best books of all time, but I I love the book because it really does point out, You know, that science is it's currently practice. I mean the book was written in 1991, but it actually I think still holds that scientists, sciences are currently practice has a set of ontological commitments which are somewhat problematic. </s><s>[INST] So the assumptions are limiting. [/INST] Yeah. In ways that you it's you know, it's like your fish and water and you don't like okay, Yeah, so </s><s>[INST] here's the [/INST] Yeah, but you know, but here's a here's a really cool thing. I just learned recently. Is it okay to go off on this tangent for a minute? </s><s>[INST] It's good tangents. [/INST] Okay. Um, I'm just gonna say that I just learned recently that we don't have water receptors on our skin. So how do you know when you're sweating? How do you know when when a raindrop, when you know when it's going to rain and you know, like a raindrop hits your skin and you can feel that little drop of wetness. How is it that you feel that drop of witness when we don't have water receptors in our skin. And I was when I </s><s>[INST] mind is blown already. [/INST] Yeah, that was my reaction too, right? I was like, of course we don't because we evolved in the water. Like why would we need, you know, it just it was just this like, you know, you have these moments where you're like, oh, looks like, yeah, so </s><s>[INST] you'll never see rain the same way again. [/INST] So the answer is it's a it's a it's a combination of temperature and touch. But it's a complex sense that's only computed in your brain, there's no receptor for it anyways. </s><s>[INST] Yeah, that's why I like snow versus cold rain versus warm rain all feel different because you're trying to infer stuff from the temperature and the size of the droplets. It's fascinating. [/INST] Your brain is a prediction machine using lots and lots of information combining it. Anyway, so, but um so biology as ideology is, I wouldn't say it's one of the greatest books of all time, but it is a it is a really useful book. There's a book by um if you're interested in psychology or the mind at all, there's a wonderful book a little it's a fairly clearly small book called naming the mind by kurt Danziger, who's a historian of psychology. Everybody in my lab reads both of these books. </s><s>[INST] So, what was the book? [/INST] It's about the origin of the where to where did we get the theory of mind that we have that the human mind is populated by thoughts and feelings and perceptions, and where did those categories come from? Because they don't exist in all cultures </s><s>[INST] Also, this isn't that's a cultural construct. [/INST] The idea that you have thoughts and feelings and they're very distinct is definitely a cultural construct. </s><s>[INST] It's another mind blowing thing, just like the rain. [/INST] Um So, kurt Danziger is a the opening chapter in that book is absolutely mind blowing. I love it. I love it. I just think it's fantastic. Um and I would say that there are many, many popular science books that I could recommend that I think are extremely well written in their own way. You know, before I maybe I said this to you, but before I undertook writing how emotions are made. Um I read, I don't know somewhere on the order of 50 or 60 popular science books to try to figure out how to write a popular science book. Because while there are many books about writing, Stephen King has a great book on writing and um you know, where he gives tips um interlaced with his own personal history. Um that was where I learned you write for a specific person, you have a specific person in mind and that's for me, that person is my is down, </s><s>[INST] that's fascinating. I mean, that's a whole another conversation to have, like which popular science books, like what you learn from that uh Search, because there's uh I have some for me, some popular science books, so like I just rolled my eyes like this is too um it's the same with Ted talks, like some of them go too much into the flowery and don't, I don't, I would say don't give enough respect to the intelligence of the reader. Uh and but this is my own bias. [/INST] I completely agree with you and in fact I have a colleague, his name is um Van Yang, who, you know, he um produced um uh cinematic lecture of how emotions are made. That we wrote together with joseph Friedman, no relation. Um </s><s>[INST] We're all really [/INST] well, I mean you and I are probably you know have some Yeah, </s><s>[INST] but it's the memories are in there somewhere. [/INST] Yeah, it's from many, many, many generations ago half my family is Russian, so from the good half the good half. Um But you know, he wanted his goal actually is to produce um you know, videos and lectures that are beautiful and educational and that don't um don't dumb the material down and he's really remarkable at it actually. I mean just uh but again, you know, that's that that requires a bit of a paradigm shift. We could have a whole conversation about the split between entertainment and education in this country and why it is the way it is. But that's a that's another conversation continued. But I would say if I were to pick one book that I think is a really good example of good science writing, it would be the beak of the finch, which wanna won a Pulitzer prize a number of years ago and I'm not I'm I'm not remembering the author's name, I'm blanking. Um </s><s>[INST] But the I'm guessing is that uh is it focusing on birds and the evolution of birds? [/INST] Actually, there is also the evolution of Beauty, which is yeah, which is also a great book, but no, the Beak of the Finch is it's a it has two storylines that are interwoven one is about Darwin and Darwin's um explorations in the Galapagos island and then modern day researchers from Princeton who have a research program in the Galapagos looking at Darwin's finches and um it's just a really first of all, there's top notch science in there and really science, like, you know, evolutionary biology that a lot of people don't know and it's told really, really well, </s><s>[INST] it sounds like they're also, there's a narrative in there. It's like storytelling to [/INST] yeah, I think all good popular science books are storytelling just but storytelling grounded, constrained by the evidence and then I just want to say that there are for fiction. I'm a really big fan of love stories just to return us to the topic that we began with. And so my some of my favorite love stories are Major Pettigrew's last stand by Helen Simonson. Okay, it's a, it's a love story about people who you wouldn't expect to fall in love and all the people around them who have to overcome their prejudices and and I love this book, </s><s>[INST] what do you like, like what makes a good love story, [/INST] There isn't one thing, you know, there are many different things that make a good love story, but I think in this case um you can feel you can feel the journey, you can feel the journey that these characters are on and all the people around them are on this journey to basically to come to grips with this really unexpected love, really profound love that develops between these two characters who are very unlikely to have fallen in love, but they do and it's just it's very gentle. Another book like that is um The um The storied Life of AJ for Turkey um which is also a love story, but in this case it's a love story between a little girl and her adopted dad and the dad is this like real curmudgeon e you know, um guy. Uh But of course there's a story there and um it's just a beautiful love story and but it also it's like everybody in this community falls in love with him because he falls in love with her and he, you know, she just gets left at his store, his book story has this failing bookstore and he discovers that, you know, he feels like inexplicably this need to take care of this little baby and this whole life emerges out of that one decision. Which is really beautiful actually. Um very poignant, </s><s>[INST] greatest stories have a happy ending or heartbreak at the end. [/INST] That's such a Russian questions. Like it's like Russian tragedies. So </s><s>[INST] I would say the answer to that for me there has to be heartbreak. [/INST] Yeah, I really don't like heartbreak, I don't like heartbreak, I want there to be a happy ending or at least hopeful ending. But the but you know, like Doctor Zhivago, like or the english patient. Oh my goodness. Like why it's just Yeah, no, </s><s>[INST] well I don't think there's a better way to end it on a happy note like this. Uh lisa like I said, I'm a huge fan of yours. Thank you for wasting yet more time with me talking again. People should definitely get your book and uh maybe one day I can't wait to talk to your husband as well. [/INST] Well, right back at you lexi. Yeah, </s><s>[INST] thanks for listening to this conversation with lisa Feldman. Barrett and thank you to our sponsors athletic greens, the all in one drink that I start every day with to cover all my nutritional bases. eight sleep a mattress that cools itself and gives me yet another reason to enjoy sleep master class, online courses that I enjoy from some of the most amazing humans in history and better help online therapy with a licensed professional. Please check out these sponsors in the description to get a discount and to support this podcast to 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 at lex Friedman and now let me leave you with some words from Sun Zoo and the art of war. There are not more than five musical notes yet. The combination of these five give rise to more melodies that can ever be heard. There are not more than five primary colors yet in combination, they produce more hues that can ever be seen. There are not more than five cardinal tastes, and yet combinations of them yield more flavors than can ever be tasted. Thank you for listening and hope to see you next time. [/INST] Yeah. </s> |
<s>[INST] questions through that window, through that kind of question, you get a window into a man with power. So let me ask about Stalin because you've done more recently is in another amazing interview, you've had um the introduction was that you know more about Stalin than Stalin himself. You've done incredible amount of research on Stalin. So if you could talk to him, get sort of direct research, what question did you ask of Stalin? [/INST] I have so many questions. I don't even know where I would begin. The thing about studying a person like Stalin who is an immense creature. Right. He's exercising the power of life and death over hundreds of millions of people. He's making decisions about novels and films and and turbines and submarines and and packs with Hitler or deals with Churchill and Roosevelt? and an occupation of Mongolia or occupation of north Korea? He's making phenomenally uh consequential decisions over all spheres of life? All areas of endeavor and over much of the globe, much of the land mass of the earth. And so what's that like? Does he sometimes reflect on the amount of power and responsibility he has that he can exercise? Does he sometimes think about what it means that a single person has that kind of power? And does it have an effect on his relations with others? His sense of self, the kinds of things he values in life? Does he sometimes think it's a mistake that he's accumulated this much power? Does he sometimes wish he had a simpler life? Or is he once again so drunk, so enamored, so caught up with chemically and uh spiritually with exercising this kind of power that he couldn't live without it. And then what were you thinking? I would ask him in certain decisions that he made. What were you thinking on certain dates and certain circumstances where you made a decision and could have made a different decision? Can you read, we call your thought processes. Can you bring the decision back? Was it seat of the pants? Was it something you've been planning? Did you just improvise or did you have a strategy? What were you guided by? Who's examples did you look to when you picked up these books that you read? And you read the books and you made pencil marks in them? Is it because you absorbed the lesson there? Or did it really not become a permanent lesson? And it was just something that you checked? And it was like a reflex. So I have many specific questions about many specific events and people and circumstances that I have. I tried to figure out with the uh surviving source materials that we have in abundance, but I would still like to delve into his mindset and reconstruct his mind. The closer you get to Stalin in some ways, the more elusive he can </s><s>[INST] become and especially around World War Two, you've already illuminated a lot of interesting aspects about Stalin's role in the war. But it'll be interesting to ask even more questions about how seat of the pants or deliberate, some of the decisions have been. If I could ask just one quick question, one last quick question. Mhm. And you're constrained in time and answering it. Do you think there will always be evil in the world? Do you think there will always be war? [/INST] Unfortunately? Yes, there are conflicting interests, conflicting goals that people have most of the time those conflicts can be resolved peacefully. That's why we build strong institutions to resolve different interests and conflicts peacefully. But that fact, the enduring fact of conflicting interests and conflicting desires that can never be changed. So the job that we have for humanity's sake is to make those conflicting interests, those conflicting desires to make them uh to to put them in a context where they can be resolved peacefully And not in a zero sum fashion. So we can't get there on the global scale. So there's always gonna be the kind of conflict that sometimes gets violent. What we don't want is a conflict among the strongest powers. Great power conflict Is unbelievably bad. There are no words to describe at least 55 million people died in World War II. If we have a World War three, a war between the United States and china or whatever it might be, who knows what the number could be. 155255 million 555 million. I don't even want to think about it. And so it's horrible when wars break out in the humanitarian catastrophes, for example, Yemen and Syria, and several other places I could name today. It's just horrible what you see there. And the scale is colossal for those places, but it's not planetary scale. And so, avoiding planetary scale destruction is really important for us. And so, having those different interests be somehow managed in a way that they don't that no one sees advantage in a violent resolution. </s><s>[INST] And a part of that is remembering history. So they should read your books steven. Thank you so much as a huge honest talking to you today. I really enjoyed it. [/INST] Thank you for the opportunity. My pleasure. </s> |
<s>[INST] Yeah, so content to not simplify. [/INST] Yes. If we didn't simplify, then we wouldn't be like us. We would be like the universe, like the intrinsic universe, but not having experiences like the experiences we have, where we, for example, conclude that definite things happen. We have this notion of being able to make narrative statements. </s><s>[INST] I wonder if it's just like you imagined as a thought experiment, what it's like to be a computer. I wonder if it's possible to try to begin to imagine what it's like to be an unbounded computational observer. [/INST] Well, okay, so here's how that, I think, plays out. Vibrations. Yeah. So, I mean, in this, we talk about this rulliad, this space of all possible computations. This idea of being at a certain place in the rulliad, which corresponds to a certain way of ... A certain set of computations that you are representing things in terms of. Okay, so as you expand out in the rulliad, as you kind of encompass more possible views of the universe, as you encompass more possible kinds of computations that you can do, eventually you might say that's a real win. we're colonizing the Rulliad, we're building out more paradigms about how to think about things, and eventually you might say, we won all the way. We managed to colonize the whole Ruliad. Okay, here's the problem with that. The problem is that the notion of existence, coherent existence, requires some kind of specialization. By the time you are the whole Ruliad, by the time you cover the whole Ruliad, in no useful sense do you coherently exist. So in other words, in the notion of existence, the notion of what we think of as definite existence requires this kind of specialization, requires this kind of idea that we are not all possible things, we are a particular set of things. And that's kind of what makes us have a coherent existence. If we were spread throughout the rulliad, there would be no coherence to the way that we work. We would work in all possible ways. And that wouldn't be kind of a notion of identity. We </s><s>[INST] wouldn't have this notion of coherent identity. Interesting. I am geographically located somewhere exactly, precisely in the rulliad, therefore I am, is the Descartes kind of... [/INST] Yeah, yeah, right. Well, you're in a certain place in physical space or in a certain place in rural space. And if you are sufficiently spread out, you are no longer coherent. And you no longer have... I mean, in our perception of what it means to exist and to have experience, it doesn't happen. </s><s>[INST] Right. So therefore, to exist means to be computationally bounded. I think so. To exist in the way that we think of ourselves as existing, yes. The very act of existence is like operating in this place that's computationally reducible. So there's this giant mess of things going on that you can't possibly predict. But nevertheless, because of your limitations, you have an imperative of like, what is it? An imperative or a skill set to simplify? Or an ignorance, a sufficient [/INST] imperative of like... Okay, so the thing which is not obvious is that you are taking a slice of all this complexity, just like we have all of these molecules bouncing around in the room. But all we notice is the kind of the flow of the air or the pressure of the air. We're just noticing these particular things. And the big interesting thing is that there are rules, there are laws that govern those big things that we observe. So it's not obvious. That's how amazing. </s><s>[INST] Because it doesn't feel like it's a slice. It's not a slice. It's like an abstraction, [/INST] not a slice. Yes. But I mean, the fact that the gas laws work, that we can describe pressure, volume, et cetera, et cetera, et cetera, and that we don't have to go down to the level of talking about individual molecules, that is a non-trivial fact. And here's the thing that I sort of exciting thing as far as I'm concerned, the fact that there are certain aspects of the universe. So we think space is made ultimately these atoms of space and these hypergraphs and so on. And we think that, but we nevertheless perceive the universe at a large scale to be like continuous space and so on. In quantum mechanics, we think that there are these many threads of time, these many threads of history, yet we kind of span. So in quantum mechanics, in our models of physics, there are these, time is not a single thread. Time breaks into many threads. They branch, they merge. But we are part of that branching, merging universe. And so our brains are also branching and merging. And so when we perceive the universe, we are branching brains perceiving a branching universe. And so the fact that the claim that we believe that we are persistent in time, we have this single thread of experience, that's the statement treatment that somehow we managed to aggregate together those separate threads of time that are separated in the fundamental operation of the universe. Just as in space, we're averaging over some big region of space, and we're looking at the aggregate effects of many atoms of space, similarly in what we call branchial space, the space of these quantum branches, we are effectively averaging over many different branches of histories of the universe. in thermodynamics, we're averaging over many configurations of many, many possible positions of molecules. So what we see here is, the question is when you do that averaging for space... What are the aggregate laws of space? When you do that averaging over branchial space, what are the aggregate laws of branchial space? When you do the averaging over the molecules and so on, what are the aggregate laws you get? And this is the thing </s> |
<s>[INST] right, yes. [/INST] So he d confused them by this symmetry reasoning. So this way of repackaging some intuition, a different intuition when the intuitions clash. Then you then you side on the you replace the intuition. </s><s>[INST] That's brilliant i in some of these different, more difficult physical Ideas, physics ideas in the 20th century in the 21st century, it starts becoming more and more difficult than replace the intuition. You know what what does the world look like for an object traveling close to the speed of light. You start to think about like the edges of supermassive black holes. He started to think like what what's that look like or uh Marie into gravitational lasers. It's like when the fabric of space time is being morphed bye gravity. Like what's that actually feel like if I'm writing a gravitational wave, what's that feel like? Um I mean I think some of those are more sort of hippie, not useful uh intuitions to have, but if you're an actual physicist or whatever the particular discipline is, I wonder if it's possible to meditate to sort of escape through thinking prolonged thinking and meditation on a war on a world like live in a visualized world that's not like our own in order to understand a phenomenon deeply. So like replace the intuition like through rigorous meditation on the idea in order to conceive of it. I mean if we talk about multiple dimensions, I wonder if there's um a way to escape of the three dimensional world in our mind in order to start to reason about it. It's uh the more I talked to the apologists. Yeah, the more they seem to not operate at all at all in the visual space, they really trust the mathematics, which is really annoying to me because topology in differential geometry. It feels like it has a lot of potential for beautiful pictures. [/INST] Yes, I think they do actually. I would not be able to do my my research if I don't have an intuitive feel about geometry and I will get to it, as you mentioned before that how for example, in strength there you deal with these extra dimensions and I'll be very happy to describe how we do it because without intuition we will not get anywhere. And I don't think you can just rely on formalism. I don't I don't think any physical just relies on formalism that's not physics that's not </s><s>[INST] understanding. [/INST] So we have to into it and that's crucial and there are steps of doing it and we learned it might not be trivial but we learn how to do it. Similar to this Galileo picture. I just told you you have to build these gradually but but to connect the bridge to connect exactly how to connect the brakes literally. So yeah, so then uh going back to your question about the path of the history of the science. So I was saying about the Houston magnetism and the special relativity were simple idea led to special relativity but then he went further thinking about acceleration in the context of relativity. And he came up with general relativity where he talked about, you know, the fabric of space time being curved and so forth and matter affecting the curvature of space on time. So, so this gradually became a connection between geometry and physics. Namely he replaced Newton's, you know gravitational force with a very geometrical, beautiful picture. It's much more elegant than Newton's but much more complicated mathematically. So. So when we say simpler, we mean in some form is simpler, but not in pragmatic terms of equations solving the equations are much harder to solve in Iceland theory. And and in fact so much so much harder than Einstein himself. Couldn't solve many of his many of the cases. He thought for example, you couldn't solve the equation for a spherical symmetric matter uh like like if you had a symmetric son, he didn't think you can actually write the, solve his equations for that. And a year after he said that it was solved by by short child. So it was it was that hard that he didn't think it's gonna be that easy. So yeah, the farm is um is heart. But the contrast between the special relativity and general relativity is very interesting because one of them has almost trivial math and the other one has super complicated math. Both are physically amazingly important. And so so we have learned that, you know, the physics may or may not require complicated math. We should not shy from using complicated math like Einstein did. Nobody Einstein wouldn't say I'm not going to touch this math because it's too much, you know, tensors or curvature and I don't like the four dimensional spacetime because I can't see for dementia, he wasn't doing that, he was willing to abstract from that because physics drove him in that direction. But his motivation was physics physics pushed him just like Newton push to develop calculus because physics pushed him that he didn't have the tools so he had to develop the tools to answer his physics questions. So his motivation was physics again. So to me those are examples would show that math and physics have this symbiotic relationship which which kind of reinforce each other here I'm using, I'm giving you examples of both of them namely Newton's work led to development of mathematics, calculus and in the case of Iceland, he didn't develop remaining junkie just used them. So so it goes both ways and in the context of modern physics, we see that again and again it goes both ways. </s> |
<s>[INST] Well the interesting thing is is it possible to some of the ideas that you talk about to turn them into a protocol that can be practiced rigorously. So what jim Keller espouses is saying not just the fact that sleep helps you increase the creativity but turn into a process like literally like don't do it accidentally, you know, like uh like an athlete does certain things to optimize their performance that have a training routine, they have a regiment of uh of like cycling and and and uh sprints and and long distance stuff in the same way, thinking about your job as an idea generator in engineering spaces like this is good for my performance. So like for an hour before bed think through a problem like every night and then you sleep to uh work through that problem. I mean this is the first person that I heard like of the people I really respect that do like what I do, which is like programming engineering type work, like using sleep not accidentally, but with a purpose, like using sleep, [/INST] you know, that's just basically the difference between as you said, a passive approach to it versus you know an active deterministic or hope for a deterministic approach to it. In other words that you are actually trying to harness the power of sleep in a deliberate way, rather than Um, thoughtful way, I still think that, you know, mother nature through it, you know, 3.6 million years of evolution has probably got it mostly figured out in terms of what information should be uploaded at night and worked through. I think algorithm is probably pretty good at this stage. It's not to suggest though, that, you know, we can't try to tweak it and nudge it, it's a very light hand on the tiller is what he's doing. I don't think there's anything wrong with that, </s><s>[INST] you know, just like for example, for me, fast thing has improved my ability to focus deeply and productivity significantly. And in that same way it is possible that playing with these ideas of thinking before bed or some hours before bed or some playing with different protocols will have a significant leap over what mother nature naturally does. So if you let your body do what it actually does, you may not achieve the same level of performance because mother nature has not designed us to think deeply about uh chip design for uh programming artificial intelligence systems. So [/INST] well, she's gifted, does the architecture and the capacity to do that. What we do with that is, you know, is what life's experience dictates, she gives us the blueprint to do many, you know, </s><s>[INST] well if I were to sort of introspect and self analyze what mother nature wants me to do. I think given my current lifestyle that I have food in the fridge [/INST] and </s><s>[INST] a bed to sleep on, I think what mother nature wants me to do is to be lazy. So I think I'm actually resisting mother nature. Uh, and because so many of my knees are satisfied and so I'm, I have to resist some of the natural forces of the body and the mind when I do some of the things I do. So there's that dance. Um, you know, like I've been thinking about doing a startup and that's obviously going against everything that my body and mind are telling me to do because it's going to be basically suffering. But the only reason why [/INST] as you know, it will be </s><s>[INST] over. Yes. But nevertheless, there is some kind of inner drive that wants me to do it. And then you start to ask a question, well, how do you optimize the things you can optimize like sleep like diet, like the people that you surround yourself with in order to maximize happiness and performance and all those kinds of things without also over optimizing. And that's such an interesting idea from, from a engineer. So as you may know, you don't often get that those kinds of ideas from engineers, engineers usually just don't read books about sleeping. They're usually like the, they're not, they're not the healthiest of people. Um, I think that's changing over time, especially Silicon Valley, especially the tech sector. People are trying to understand what's a healthy lifestyle, but usually they're kind of on the insane side, especially programmers, but it's nice to hear uh somebody like that you sleep and use some of the things you talk about strategically on purpose [/INST] to that idea of not just trying to use what mother nature gave, but seeing if you can do something more or different in a conservative mindset. Mhm. I would then pose the question at what cost because when you do something perhaps that deviates from the typical pre programmed, you know, with the nature's program, um I suspect it usually comes at the cost of something else. So maybe he is able to direct and focus his sleeping cognition on those particular topics that will gain him better problematic resolution the next day when he wakes up. The question is though, at what cost of the other things that didn't make it onto the menu of the finger buffet of sleep that night. And is it that you don't process the emotional difficulties or events and therefore you are less emotionally resolved the next day. But you are more problem resolved the following day. And so I always try to think and I truly don't want to sound puritanical either about sleep. And I think I've come off that way many at times, especially when I started out in the public um the tone of the book in some ways, you know, I look back and think could I have been a little softer. And the reason was I was that way back in when I started writing the book, which was probably something like 2014 or 15 sleep was the neglected step sister in the health conversation of the day. And I was just so sad to see the amount of suffering and disease and sickness that was caused by insufficient sleep. And for years before I've been, you know, doing public speaking and I tell people about the great things that happen when you get sleep, people would say that's fascinating and then they would go back and keep doing the same thing about not sleeping enough. And then I realized I can't really speak about the good things that happen. It's like the news, what bleeds leads and if you speak about the alarmingly bad things that happen, people tend to have a behavioral change. And so the book as a consequence, I think probably came out a little bit on the strong side of, you know, trying to convince, you know, people, </s> |
<s>[INST] So it's like dynamically pruning the graft to only like based on the particular thing you're trying to infer. [/INST] Yes. And so by now we have about 150 of these sort of like breakthrough ideas that have led to dramatic speed ups in the inference process, you know, where one of them was this E l H L split and lots of HL modules. Another one was using meta and meta meta level reasoning. Um to reason about the reasoning that's going on and so on. Um and you know 150 breakthroughs may sound like a lot but you know if you divide by 37 years it's not as impressive. </s><s>[INST] So there's these kind of heuristic modules that really help improve the the influence, how hard in general is this? Because you mentioned higher order logic, you know the in the general of the theory improver since it's an intractable, very difficult problem. So how hard is this influence problem when we're not talking about? If we let go the perfect and focus on the good. [/INST] I would say it's half of the problem in the following empirical sense, which is over the years, about half of our effort, maybe 40% of our effort has been our team of inference programmers And the other 50, has been. Our oncologists are ontological engineers putting in knowledge. So our ontological engineers in most cases don't even know how to program. They have degrees in things like philosophy and so on. Um so it's almost like the love that you want to hang out with those people. Yes, it's wonderful. But it's very much like the alloy and the morlocks in um, H G wells time machine. So you have the lawyer who only program in the epistemological higher order logic language and then you have the morlocks who are like um under the under the ground figuring out what the machinery is that will make this efficiently operate and so on. Um, and so you know, occasionally they'll toss messages back to each other And so on. But it really is almost this 5050 split between finding clever ways to recoup efficiency when you have an expressive language and putting in the content of what the system needs to know </s><s>[INST] and both are fascinating to some degree the entirety of the system as far as I understand is written in various variants of lISP. So my favorite program languages still lisp programming it much anymore because, you know, the world has, in majority of its system has moved on like everybody respects list, but many of the systems are not Britain list anymore, but psych as far as I understand, maybe you can correct me, there's a bunch of lisP in it. [/INST] Yeah, so it's based on a list code that we produced. Most of the programming is still going on in a dialect of lISP and then the, for efficiency reasons that gets automatically translated into things like java or C nowadays it's almost all translated into java because java has gotten good enough. That, uh, that's, that's really all we need to do </s><s>[INST] is translate into java and then java is compiled down to buy code. Yes. Okay, so that's sort of, that's the, uh, that's a, you know, it's a process that probably has to do with the fact that when psych was originally written and you build up a powerful system, like there is some technical debt you have to deal with, as is the case with most powerful systems that span years. Um, have you ever considered this, this would help me understand because from my perspective, so much of the value of everything you've done with psycho, psycho is the, is the, is the knowledge, have you ever considered just like throwing away the code base and starting from scratch? Not really throwing away, but sort of moving it to like throwing away that technical debt. Starting with a more updated programming language. Is that throwing away a lot of value or know like what's your sense? How much of the value is in the silly software engineering aspect and how much of the values in the knowledge. [/INST] So development of, of programs in LISP proceeds um, I think Somewhere between 1,050,000 times faster than development in any, any of what you're calling modern or improved computer languages. </s><s>[INST] There's other functional language like, you know, closure, although there's, but I mean, I'm with you, I I like this, but I just wonder how many great programmers there are there still like, [/INST] so, so it is true when a new inference programmer comes on board, they need to learn um, some of list and in fact we have a subset of list, which we call cleverly sub L, which is really all they need to learn. And so the programming actually goes on in sub L, not in full list. And so it does not take programmers very long at all to learn uh, sub L. And that's something which can then be translated efficiently into java. And for some of our programmers who are doing, say user interface work, then they never have to even learn saddle. They just have to learn a ps into the basic psych engine. </s><s>[INST] So you're not necessarily feeling the burden of like it's extremely efficient. There's um, that's not a problem to solve. [/INST] Okay, right. The other thing is, remember that we're talking about hiring programmers to do inference, who are programmers interested in effectively automatic theory improving and so those are people already predisposed to representing things in logic and so on. And lISP really was the programming language based on logic that john McCarthy and others who developed it basically create took the formal ISMs that Alonzo Church and other philosophers other logician had come up with and basically said, can we basically make a programming language which is effectively logic. And so since we're talking about reasoning in about expressions written in this logical epistemological language and we're doing operations which are effectively like you're improving type operations and so on. There is a natural impedance match between lISP and the knowledge the way it's represented. </s> |
<s>[INST] They protect your privacy on the internet using the internet without, it is like driving without car insurance. Speaking of which I'm currently driving a rental car and I had to change [/INST] the tire. </s><s>[INST] That was a funny experience. It made me realize that it's been a while since I changed a tire and I kind of enjoyed it in the summer. Austin heat. It kind of reminds me of that movie with Sean Penn and I think it's a jennifer Lopez called You Turn, I may be imagining it, but I remember it being like a really interesting film that was about cars and heat and that tension, I think Nick Nolte was in it too. He's an incredible actor. Anyway, that whole experience is exactly what it's like to not have a VPN if you want to have a painless experience, you should get Express VPN. It protects you from the good guys, the bad guys, all of whom watch your data. That sp is the big companies, all that kind of stuff. If privacy is important to you, you should use a VPN go to Express VPN dot com slash flex pod to get an extra three months free. That's express VPN dot com slash lex pod. This episode is also sponsored by magic spoon, low carb keto friendly cereal. It has zero g of sugar, 13 to 14 g of protein, only four net grams of carbs And 140 calories in each serving. They now ship to Canada. I posted on twitter that I'm going to Toronto Canada to visit a friend and I asked for recommendations for people to talk to on the podcast and I got some incredible recommendations. So once I get a chance to visit which will probably be brief, I'll have a lot of cool conversations to to have over there. I love Canada in general, I love Toronto. I love Montreal. I feel like I want to take a road trip throughout Canada and maybe on the road trip I'll be eating magic spoon cereal. It's honestly my favorite snack that feels like a cheap meal, but it's not low carb and reminds me of like early high school when I would eat cereal that was terrible for you. But in this case it's cereal that is really good for you And so can bring happiness without the pain of malnutrition. Anyway, Magic Spoon has a 100% happiness guarantee. So if you don't like it, they will refund it. Go to magic spoon dot com slash lex and use code lex at checkout to save five bucks off your order. That's magic spoon dot com slash lex and use code lex. This show is sponsored by four stigmatic, the maker of delicious mushroom coffee and plant based protein. Does the coffee tastes like mushrooms? You ask? No, it does not, it tastes delicious. It's a part of my daily routine. It brings me joy. It brings me energy. It brings me uh focus. I drink a cup of coffee as I turned on the brown noise and my mind goes into this deep state of focus in the morning. Those few early morning hours are my favorite hours of the day. I don't know what it is, but it's like the mind emerges from the dream state and walks calmly into this tunnel of vision and focus that results in some like incredible levels of productivity Anyway, for stigmatic coffee is part of that highly recommend. It tastes good. I think there's a lot of ways that it's very healthy for you, but I just drink it because it's delicious and because I kind of like the idea of mushroom coffee, get up to 40% off and free shipping on mushroom coffee bundles. If you go to four stigmatic dot com slash lux, that's four stigmatic dot com slash lux. This is the lux freedom and podcast and here is my conversation with bret weinstein, what to you is beautiful about the study of biology, the science, the engineering, the philosophy of it. [/INST] It's a very interesting question, I must say at one level, it's not a conscious thing, I can say a lot about why as an adult, I find biology compelling, but as a kid, I was completely fascinated with animals, I loved to watch them and think about why they did what they did and that developed into a very conscious passion as an adult. But I think uh in the same way that one is drawn to a person, I was drawn to the never ending series of near miracles that exists across biological nature </s><s>[INST] when you see a living organism, do you see it from an evolutionary biology perspective of like, this entire thing that moves around in this world? Or do you see like from an engineering perspective, they're like uh first principles almost down to the physics, like the little components that build up hierarchies that you have cells, the first proteins and cells and organs and all that kind of stuff. So do you see low level or do you see high level? [/INST] Well, the human mind is a strange thing and I think it's probably a bit like a time sharing machine in which I have different modules, we don't know enough about biology for them to connect. Right? So they exist in isolation and I'm always aware that they do connect, but I basically have to step into a module in order to see the evolutionary dynamics of the creature and the lineage that it belongs to. I have to step into a different module to think of that lineage over a very long time scale, a different module still to understand what the mechanisms inside would have to look like to account for what we can see from the outside. And I think that probably sounds really complicated, but one of the things about being involved in a topic like biology and doing so for one, you know, really not even just my adult life for my whole life is that it becomes second nature and you know, when when we see somebody do an amazing parkour routine or something like that, we think about what they must be doing in order to accomplish that. But of course what they are doing is tapping into some kind of zone, right? They are in a zone in which they are in such um command of their center of gravity, for example, that they know how to hurl it around the landscape so that they always land on their feet. And I would just say for anyone who hasn't found a topic on which they can develop that kind of facility, it is absolutely worthwhile. It's really something that human beings are capable of doing across a wide range of topics. Many things our ancestors didn't even have access to and that flexibility of humans. That ability to repurpose our machinery for topics that are novel means really the world is your oyster, you can you can figure out what your passion is and then figure out all of the angles that one would have to pursue to really deeply understand it. And it is uh it is well worth having at least one topic like that. </s> |
<s>[INST] one. Does this test easily explainable or not. [/INST] Uh Yes, actually. Um Ready, let me give you the simplest version of it. You can dress it up a little bit, but here's the basic idea. Uh I take the number, the mystery number I raised to that power. So let's say your mystery number is six. Are you? Sorry, you asked me are you ready to talk? </s><s>[INST] I'm breaking my brain again. But yes, [/INST] Let's let's let's do it. We're gonna do a live demonstration. Um let's say you're number is six, so I'm gonna raise two to the sixth power. Okay, so, if I were working, I'd be like, that's two cubes, squares, that's eight times eight. So that's 64. Now we're going to divide by six, but I don't actually care what the quotient is, only the remainder. So let's say 64 divided by Six is uh was there's a question of 10, but the remainder is four. So you failed because the answer has to be to for any prime, let's do it with five, which is prime. Two to the fifth is 32 Divide 32 x five. Uh and you get six With the remainder of two. </s><s>[INST] Well, the remainder of two, [/INST] 72 to the seventh is 1, 28 divide that by seven. And let's see, I think that's seven times 14, is that right? No, seven times 18 Is 1, 26 with a remainder of two, right? one, is a multiple of seven plus two. So, if that remainder is not to, then that's definitely that's definitely not prime. </s><s>[INST] And then if it is, it's likely a prime, but not for sure. [/INST] It's likely prime, but not for sure. And there's actually a beautiful geometric proof which is in the book actually, that's like one of the most granular parts of the book is it's such a beautiful proof, I couldn't not give it to. You draw a lot of like opal and pearl necklaces and spin them. That's kind of the geometric nature of the of this proof of Fermat's little theorem. Um So yeah, so with pseudo primes, the primes are kind of faking that they passed that test, but there are numbers that are faking it. They passed that test, but not actually prime. Um But the point is um there are many, many, many theorems about prime numbers. Um </s><s>[INST] are there like there's a bunch of questions to ask, is there an infinite number of primes? Uh can we say something about the gap between primes as the numbers grow larger and larger and larger and so on? [/INST] Yeah, it's a perfect example of your desire for simplicity in all things, You know, it would be really simple if there was only finally many primes and then there'll be this finite set of atoms that all numbers would be built up that it would be very simple and good in certain ways, but it's completely false. And number three would be totally different if that were the case. It's just not true. Um In fact, this is something else that euclid news. So this is a very, very old fact like much before, long before we had anything like modern numbers primes the primes that there are </s><s>[INST] that there's an infinite number of times. So what about the gaps between the primes? [/INST] Right. So, so one thing that people recognized and really thought about a lot is that the primes on average seem to get farther and farther apart as they get bigger and bigger. In other words, it's less and less common. Like I already told you of the 1st 10 numbers 23574 of them are prime. That's a lot 40% if I looked at, You know, 10 digit numbers, No way with 40% of those be prime being primarily a lot rarer in some sense because there's a lot more things for them to be divisible by that's one way of thinking of it. It's a lot more possible for there to be a factor Ization because there's a lot of things you can try to factor out of it as the numbers get bigger and bigger. Pry maliti gets rarer and rarer. Um And the extent to which that's the case, that's pretty well understood, but then you can ask more fine grained questions and here is one um Mhm A twin prime is a pair of primes that are two apart Like three and 5 Or like 11 and 13 or like 17 and 19? And one thing we still don't know is are there infinitely many of those, we know on average, they get farther and farther apart. But that doesn't mean there couldn't be like occasional folks that come close together. And indeed we think that there are. And one interesting question, I mean, this is because I think you might say like, well, why, how could one possibly have a right to have an opinion about something like that? Like, you know, we don't have any way of describing a process that makes crimes like sure, you can like look at your computer and see a lot of them. But the fact that there's a lot, why is that evidence? There's infinitely many. Right? And maybe I can go on the computer and find 10 million, 10 million. 10 million is pretty far from infinity. Right? So how is that? How is that evidence? There's a lot of things, There's like a lot more than 10 million atoms. That doesn't mean there's infinitely many atoms in the universe. Right. I mean, on most people's physical theories, there's probably not as I understand it. Okay, so </s><s>[INST] why would we think this? The [/INST] answer is that we've that it turns out to be like incredibly productive and enlightening to think about primes as if they were random numbers as if they were randomly distributed according to a certain law. Now they're not, they're not random. There's no chance involved. There is completely deterministic whether a number is prime or not. And yet it just turns out to be phenomenally useful useful in mathematics to say, even if something is governed by a deterministic law, let's just pretend it wasn't, let's just pretend that they were produced by some random process and see if the behavior is roughly the same and if it's not, maybe change the random process, make the randomness a little bit different in the weekend and see if you can find a random process that matches the behavior we see. And then maybe you predict that other behaviors um of the system are like that of the random process. And so that's kind of like, it's funny because I think when you talk to people at the twin prime conjecture, people think you're saying, wow, there's like some deep structure there that like makes those primes be like close together again and again and no, it's the opposite of deep structure. What we say when we say we believe the twin prime conjecture is that we believe the primes are like sort of strewn around pretty randomly. And if they were then by chance you would expect there to be infinitely many twin primes and we're saying yes, we expect them to behave just like they would if they were random dirt, </s> |
<s>[INST] mm Yeah, [/INST] he introduced me like to, you know, soviet and Eastern european science fiction because he was a Marxist. Like that's what I took from him, among other things. </s><s>[INST] Any advice on finding a good mentor, Daniel Kahneman has uh somebody just popped into mind as somebody who was able to find exceptionally good collaborators throughout his life is not many bright minds to find collaborators. They often um which I ultimately what a mentor is [/INST] a method to be direct and tried. It's not like a perfect formula, but it's amazing how many people don't even </s><s>[INST] do those things. Be interesting, be direct and try [/INST] like what you want from a better known person. I would just say be very direct with them. Yeah, </s><s>[INST] beautiful. What's the second piece of advice [/INST] build small groups of peers, They don't have to be your age, but very often they'll be your age, especially if you're younger with broadly similar interests. But there can be different points of view people you hang out with which can include in a WhatsApp group online and like every day or almost every day they're talking about the thing, you care about trying to solve problems in that thing and that's your small group and you really like them and they like you and you care what you think about each other and you have this common interest </s><s>[INST] that's for human connection or that's for development of ideas. [/INST] It's both, they're not that different like Beatles. Classic small group, right? But there's so much drama. The florentine artists. Of course, there's drama and small groups tend to split up, which is fine, just like entering relationships often end. But it's remarkable how little has been done that was not done in small groups in some way. </s><s>[INST] So speaking of loss of uh, beautiful relationships, what do you make of this whole love thing? Uh, why do humans fall in love? What's the role of love, friendship, family in life in a successful life or just life in general? Why the hell are we so into this thing? [/INST] There are multiple layers of understanding that question. So kind of the lowest layer is the Darwinian answer, right? If we weren't this way, we wouldn't have been successful in reproducing and building alliances. It's important to realize that is far from complete sort of the highest understanding would be poetic like read john Keats or uh, you know, many </s><s>[INST] other love power is that? So, who do I go to to find out to learn about love in terms of poets [/INST] or I would say start with john Keats. But given that you're fluent in Russian? Uh, </s><s>[INST] yeah, let's go, let's go Russian literature for a second. Like what, what you, you keep mentioning Russia, what, uh, what's your connection, what's your love? [/INST] Uh, in Russia. Well, first, it's all interesting, but more completely, my wife was born in Moscow. So cold, Nikki was. Yeah. And she grew up there. I married her here. Uh, my daughter, I adopted her, I'm not her biological father, but I genuinely raised her and she was born in Russia though. She came here when she was one. My father basically Russian. No, no, no, I'm in New Jersey boy. Uh that's the same thing. I'm very sorry to report my father in law passed away a week ago. He lived with us for six years. He lived in Russia till he was 070 saw, you know the stalinist terror. His father was brought to a camp, lived through World War Two, much, much more had an incredible life. Never really learned how to speak english. So I absorbed something Russian from him as well. He was part Armenian. So that's my connection to Russia. A bit of the </s><s>[INST] Russian soul too. [/INST] I don't think I have it, I think I appreciate it. But this division of labor, right? Other than the family, take care of that, I'm more superficial. </s><s>[INST] You mentioned keith and uh that higher version that non Darwinian love. What's that about? [/INST] That? It's the highest form of human connection and it's intoxicating and it's part of building a life. And most of us are very, very strongly drawn to it and it's part of the highest realization of you being what you can be. Yeah, you mentioned you lost. But ask a Russian. I mean, this is superficial New Jersey boy who grew up listening to Bruce Springsteen. What? </s><s>[INST] Uh what's your favorite Bruce Springsteen song, [/INST] I think the album Born To Run has actually held up the best though. It's very fashionable to think the earlier or later works are actually better. And that's the overproduced super pop album. But the quality of the songs To Me Born to Run is just far and away. The best then Darkness on the edge of town and those are still my favorites. Someone Turin is an incredible song. Yeah, and perfectly produced in a Phil specter kind of way. Every detail is right. Every lyric, What </s><s>[INST] else is on the album? [/INST] Thunder Row, Jungle Land, 10th Avenue freeze out. She's the one. Unbelievable. Yeah, beating across the river. </s><s>[INST] I really like. Uh yeah, I like, I like when he goes into love personally, uh you know, like I'm on fire. [/INST] That's a very good song Dancing in the Dark. A lot of the later work, I find the percussion becomes too simple and kind of two white somehow and a little clunky and it's still good work. He's super talented, but it doesn't speak to me when it all bursts open into the open road, like it does on Born to Run. That's magic. </s><s>[INST] Yeah, it was a leader. Have you ever seen him alive, [/INST] is it? Yes. Twice. </s><s>[INST] I wonder what he's like live when he was young. Right? [/INST] That those years. I saw him live when he was young, I was young. Uh, New Jersey. I was a little disappointed actually. Yeah, I think what I like best from him is quite studio. He certainly played well, I don't fault his performance, but a psych when I saw a plant and page of Led Zeppelin tremendous creators and they showed up, they were not drunk, like they were paying attention, but I was underwhelmed because Led Zeppelin, like the Beatles White album is much more of a studio </s> |
<s>[INST] So it's in part developing, helping them develop that sense that the problem is not yet solved but it's solvable, [/INST] correct. The other thing which I have which I I think I bring to the table uh is is a a certain intellectual breath. I I've spent a fair amount of time studying psychology, neuroscience relevant areas of applied math and so forth. So I can probably help them see some connections, two disparate things which uh they might not have otherwise. So, so the smart students coming into Berkeley can be very deep in the sense they can think very deeply meaning very hard down one particular path but where I could help them is the the shallow breath but uh where they would have the, the narrow death and but that's, that's of some value. </s><s>[INST] Well, it was beautifully refreshing just to hear you naturally jumped to psychology back to computer science in this conversation back and forth. I mean that that's a, it's actually a rare quality and I think it's certainly for student, is empowering to think about problems in a new way. So for that and for many other reasons, I really enjoyed this conversation. Thank you so much. It was a huge honor. Thanks for talking to [/INST] uh it's been my pleasure. </s><s>[INST] Thanks for listening to this conversation with Jitendra Malik and thank you to our sponsors. Better help and express VPN. Please consider supporting this podcast by going to better help dot com slash lex and signing up at express VPN dot com slash like spot click the links by the stuff. It's how they know I sent you and it really is the best way to support this podcast and the journey I'm on. If you enjoy this thing, subscribe my youtube, review five stars on apple podcast, support on Patreon or connect with me on twitter at lex Friedman, don't ask me how to spell that. I don't remember myself and now let me leave you with some words from Prince Michigan and the idiot by dostoevsky Beauty will save the world. Thank you for listening and hope to see you next time. [/INST] Mhm </s> |
<s>[INST] one of the hardest cases of recent history would be the harvey weinstein in terms of popular opinion or unpopular opinion. So well, if you continue on that line, what was that? Where does that story take you of taking on this case? [/INST] Yeah, so I I took on the case and then there was some uh some a few students at the college. So let me back up. I had an administrative post at Harvard College, which is a separate entity from the Harvard Law School. Harvard College is the undergraduate portion of Harvard University and the law school's obviously the law school and I uh initially was appointed as master of one of the houses. We did a name change five or six years into it and and we're called faculty deans. But the houses at Harvard are based on the college system of Oxford and Cambridge. So when students go to Harvard after their first year, they are assigned to a particular house or college and that's where they live and eaten so forth undergraduate, these are undergraduate students. So I was responsible for one of the houses, that's as its faculty dean. Uh so it's an administrative appointment at the college and some students who didn't clearly didn't like Harvey Weinstein began to uh protest about the representation and from there, it uh just mushroomed into one of the most craven cowardly acts by uh any university in modern history. It's just a complete and utter repudiation of academic freedom. Uh, and it is a decision that Harvard certainly will live to regret. It's frankly, it's an embarrassment. We expect students to do what students do and I encourage students to have their voices heard and to protest. I mean, that's what students do. What is vexing Are the adults? The dean of the Faculty of Arts and Sciences, claudine Gay, absolutely craven and cowardly. The dean of the college. Same thing, rakesh Khurana craven and cowardly. Uh, they Capitulated to the loudest voice in the room and ran around afraid of 19 year old. So 19 year olds are upset that I, I need to, I need to do something. And it appeared to me that they so so desired the approval uh, of students that they were afraid to make the tough decision and the right decision. It really could have been an important teaching </s><s>[INST] moment at teaching moment. Yeah, [/INST] very important teaching moment. So </s><s>[INST] they forced you to step down from that faculty dean position at the house. It [/INST] um, I would push back on the description a little bit. So, so, so, so I, so I don't write the, the, uh, you know, the references to the op ed, I did the new york times, Harvard made a mistake by making me step down or or something like that. So I don't write those things. I did not step down and refused to step down. Harvard declined to renew my, my, my my contract. And you know, and I made it clear that I was not going to resign as a matter of principle and and forced them to do the cowardly act that they in fact did. And you know, the worst thing about this. Uh they did uh the college uh Dean Gay and Dean Khurana commissioned this survey. They've never done this before. Survey from the students. You know, how do you feel at Winthrop House? And the funny thing about the survey is they never released the results. Why did they never released the results? They never released the results because I would bet my salary that the results came back positive for me. And it didn't fit their narrative because most of the students were fine. Most of the students were fine. It was the loudest voice in the room. So they never released it. And you know, I challenged him to this day, release it, Release it. But no, but you know, they wanted to um uh create this narrative. Uh and when the data didn't support the narrative, then they just got got silent. So we're not going to release it. The students demanded it, I demanded it and they wouldn't release it because I am I I just I just know in my heart of Hearts that it it was uh it came back in my favorite that most students at Winthrop House said they were fine. Uh there was a group of students that weaponized a term unsafe? They said, we felt unsafe and they they bandied this term about. But I'm again, I'm confident that that the majority of students at Winthrop House said they felt completely fine and the uh felt safe and so forth. And the supermajority I am confident either said, I feel great at at Winthrop or, you know, I don't care one way or the other, and then there was some minority who had had a different view, but um, you know, lessons learned. Uh it was a wonderful opportunity at Winthrop admit some amazing students over the my 10 years as master and then faculty Dean and I'm still in touch with the number of students, some of whom are now my students at the, at the law school. So in the end, I thought it was uh it ended up being a great experience. Uh the national media, it was just wonderful and it's just wonderful. They people wrote such wonderful articles and accounts and wag their finger appropriately at Harvard uh uh compared me to john Adams, which I don't think it's an apt comparison, but it's always great to read something like that. Uh But but anyway, that that that was the Harvard uh the Harvard versus Harvey situation. </s> |
<s>[INST] as you do enough. So these are kind of things that are impossible with computers. [/INST] So they're possible. Again, there are paths to doing it, but you can't fit them conveniently in any of the numbers. You need to start using big nums and different factor trackings and </s><s>[INST] different things. So if you have any elements of OCD and you want to do something perfectly, you're screwed if you're working with floating point. So you had to deal with this for the first [/INST] time. And there were lots of challenges there about like, okay, they build this cool thing. And the way the BSP trees work is it basically takes the walls and it carves other walls by those walls in this clever way that you can then take all of these fragments and then you can for sure from any given point get an ordering of everything in the world. And you can say this goes in front of this goes in front of this. All the way back to the last thing and that's super valuable for graphics, where kind of a classic graphics algorithm would be painter's algorithm. You paint the furthest thing first, and then the next thing and then the next thing and then it comes up and it's all perfect for you. That's slow because you don't want to have to have drawn everything like that, but you can also flip it around and draw the closest thing to you. And then if you're clever about it, you can figure out what you need to draw that's visible beyond that. And that's what BSP trees allow you to do. Yeah. So it's combined with a bunch of other things, but it gives you that ordering. It's a clever way of doing things. And I remember I had learned this from one of my graphics Bible at the time, a book called Foley and Van Dam. And again, it was a different world back there. There was a small integer number of books. And this book, yeah, this book though, it was a big fat college textbook that I had, you know, I'd read through many times. I didn't understand everything in it. Some of it wasn't useful to me, but they had the little thing about finite orderings of you draw a little T-shaped thing and you can say you can make a fixed ahead of time order from this and you can generalize this with the BSP trees. And I got a little bit more information about that. And it was kind of fun later while I was working on Quake, I got to meet Bruce Naylor, who was one of the original researchers that developed those technologies for academic literature. And that was kind of fun, but I was very much just finding a tool that can help me solve what I was doing. And I was using it in this very crude way in a two-dimensional fashion rather than the general 3D. The Epsilon problems got much worse in Quake and three-dimensionals when things angle in every way. But eventually I did sort out how to do it reliably on Doom. There were still a few edge cases in Doom that were not absolutely perfect where they even got terminologies in the communities. Like when you got to something where it was messed up, it was a Hall of Mirrors effect because you'd sweep by and it wouldn't draw something there and you would just wind up with the leftover remnants as you flipped between the two pages. But BSP trees were important for it, but it's again worth noting that after we did Doom, our major competition came from Ken Silverman and his build engine, which was used for Duke Nukem 3D and some of the other games for 3D Realms. And he used a completely different technology, nothing to do with BSP trees. So there's not just a one true way of doing things. There were critical things about to make any of those games fast. You had to separate your drawing into you drew vertical lines and you drew horizontal lines, just kind of changing exactly what you would draw with them. That was critical for the technologies at that time. And like all the games that were kind of like that wound up doing something similar, but there were still a bunch of other decisions that could be made. And we made good enough decisions on everything on Doom. We brought in multiplayer significantly, and it was our first game that was designed to be modified by the user community, where we had this whole setup of our WOD files and Pwods and things that people could build with tools that we released to them. And they eventually rewrote to be better than what we released, but they could build things and you could add it to your game without destructively modifying it, which is what you had to do in all the early games. You literally hacked the data files or the executable before, while Doom was set up in this flexible way so that you could just say, run the normal game with this </s><s>[INST] added on, on top, and it would overlay just the things that you wanted to there. Would you say that Doom was kind of the first true 3D game that you created? [/INST] So no, it's still, Doom would usually be called a two and a half D game where it had three dimensional points on it. And this is another one of these kind of pedantic things that people love to argue about, about what was the first 3D game. I still, like every month probably I hear from somebody about, well, was Doom really a 3D game or something? And I give the point where characters had three coordinates. So you had like an X, Y, and Z, the Cacodemon could be coming in very high and come down towards you. The walls had three coordinates on them. So on some sense, it's a 3D game engine, but it was not a fully general 3D game engine. You could not build a pyramid in Doom because you couldn't make a sloped wall, which was slightly different where in that previous shadow caster game, I couldn't have vertexes and have a sloped floor there, but the changes that I made for Doom to get higher speed and a different set of flexibility traded away that ability. But you literally couldn't make that. You could make different heights of passages, but you could not make a bridge over another area. You could not go over </s> |
<s>[INST] percent probability. [/INST] Yeah, that's that's </s><s>[INST] 57. It's a plunger. [/INST] Yeah. Well hopefully will not give </s><s>[INST] you an existential crisis [/INST] and then uh </s><s>[INST] 8%. Uh And I shouldn't say percent, but [/INST] No, that's right. 8% that it's a hominid. Um and uh yeah, Okay. It's really, I'm going to do another one of these just because I'm embarrassed that I didn't even see me at all. There we go. Let's try that. Let's see what that did. Um </s><s>[INST] Re took a [/INST] Picture with a little bit, a little bit more of me and not just my bald head, so to speak. Okay, 89%. Probably is. It's a person. So that so then I would um but you know, so this is image identify as an example of one of just one of them. Just one function as part </s><s>[INST] of the that's [/INST] like part of the core language. Yes. I mean, you know something like I could say, I don't know. Let's find the geo nearest. What could we find? Let's find the nearest volcano. Um Let's find the 10. I want to wear things here is let's try finding the 10 volcanoes nearest here. Okay, </s><s>[INST] Joe nearest volcano here, 10 years volcanoes. [/INST] Right? Let's find out where those, so we can now we've got a list of volcanoes out and I can say geo list plot That and hopefully. Okay, so there we go. So there's a map that shows the positions of those 10 volcanoes </s><s>[INST] of the east coast in the midwest and said, well no, we're okay, we're okay, There's no it's not too [/INST] bad. Yeah, they're not very close to us. We could we could measure how far away they are, but you know, the fact that, right in the language it knows about all the volcanoes in the world, it knows, you know, computing what the nearest ones are, knows all the maps of the world and so fundamentally </s><s>[INST] different idea of what the language is. [/INST] Yeah, that's what I like to talk about as a, you know, a full scale computational language. That's that's what we've tried to do. </s><s>[INST] And just if you can comment briefly, I mean, this kind of, well, the Wolfram language along with Wolfram Alpha represents kind of what the dream of what Ai is supposed to be. There is now a sort of a craze of learning kind of idea that we can take raw data and from that extractive uh the different hierarchies of abstractions in order to be able to understand, like in order to form the kind of things that Wolfram language operates with. But we're very far from learning systems being able to form that right? Like the context of history of ai if you could just comment on there is uh you said computation X. And there's just some sense where in the eighties and nineties sort of expert systems represented a very particular computation X. Right? And there's a kind of notion that those efforts didn't pan out, but then out of that emerges kind of Wolfram language Wolfram Alpha, which is the success. I mean, [/INST] I think those are in some sense, those efforts were too modest that they were they were looking at particular areas and you actually can't do it with a particular area. I mean like, like even a problem, like natural language understanding, it's critical to have broad knowledge of the world if you want to do good natural language understanding and you kind of have to bite off the whole problem, if you if you say we're just going to do the blocks world over here, so to speak, you don't really it's it's it's actually it's one of these cases where it's easier to do the whole thing than it is to do some piece of it, you know, what one comment to make about the relationship between what we've tried to do and and sort of the learning side of of ai um You know, in a sense, if you look at the development of knowledge in our civilization as a whole, there was kind of this notion pre-300 years ago or so. Now you want to figure something out about the world, you can reason it out, you can do things which would just use raw human thought. and then along came sort of modern mathematical science and we found ways to just sort of blast through that by in that case writing down equations. Now we also know we can do that with computation and so on. Um and so that was kind of a different thing. So, so when we look at how do we sort of encode knowledge and figure things out? One way we could do it is start from scratch, learn everything. It's just a neural net figuring everything out. But in a sense that denies the sort of knowledge based achievements of our civilization, because in our civilization we have learned lots of stuff. We've surveyed all the volcanoes in the world. We've done. You know, we figured out lots of algorithms for this or that those are things that we can encode computational E and that's what we've tried to do and we're not saying just you don't have to start everything from scratch. So, in a sense, a big part of what we've done is to try and sort of capture the knowledge of the world in computational form and computable form. Now there's also some pieces which which were for a long time undoable by computers like image identification, where there's a really, really useful module that we can add that is those things which actually were pretty easy for humans to do. That had been hard for computers to do. I think the thing that's interesting, that's emerging now is the interplay between these things between this kind of knowledge of the world that is, in a sense, very symbolic. And this kind of uh sort of much more statistical kind of uh things like image identification and so on and putting those together by having this sort of symbolic representation of image identification. That that's where things get really interesting and where you can kind of symbolically represent patterns of things and images and so on. Um I think that's, you know, that's kind of a part of the path forward, so to speak. So </s> |
<s>[INST] So there is a connection between power and money. You've mentioned World War One from the perspective of money. So power money war, authoritarian regimes. From the perspective of money, do you have hope that Cryptocurrency can help resist war, can help resist the negative effects of authoritarian regimes? Or is that a silly hope [/INST] wars happen because the people who have the power to command armed forces miscalculate. That's generally what happens And we will have a big war in the near future if both the chinese government and the U. S. Government miscalculates and they unleash lethal lethal force on one another. And there's nothing that any financial institution can do to stop that any more than the Rothschilds Rothschilds could stop World War and they were then the biggest bank in the world by far with massive international financial influence. So let's accept that war is, is in a different domain. War would impact the financial world massively if it were a war between the United states and china because there's still a huge china trade on wall street is long china, europe has long china. So the conflict that I could foresee in the future is one that is highly financially disruptive. Where does crypto fit in Kryptos? Obvious utility in the short run is as a store of wealth, of transferable wealth for people who live in dangerous places with failing not just failing money but failing rule of law. That's why in latin America there's so much interest in crypto because latin americans have a lot of monetary history to look back on and not much of it is good. So I think that the short run problem that crypto solves is, and this goes back to the digital gold point. If you are in a dangerous place with weak rule of law and weak property rights here is a new and better way to have portable wealth. I think the next question to ask is would you want to be long crypto in the event of World War three. What's interesting about that question is that World War three would likely have a significant cyber dimension to it And I don't want to be 100% in crypto if they crash the internet, which between them china and Russia might be able to do. </s><s>[INST] That's a [/INST] fascinating question. </s><s>[INST] Whether you want to be holding physical gold or digital gold in the event of World War Three, [/INST] the smart person who studied history definitely wants bit of both. And so let's imagine World War Three has a very, very severe cyber component to it with high levels of disruption. Yeah. You'd be glad of the old, the old shiny stuff at that point. So Diversification still seems like the most important truth of financial history. And what is crypto? It's just this wonderful new source of diversification. But you would be not to be 100% in </s><s>[INST] Bitcoin. I mean, I [/INST] I have some friends who are probably quite close to that close to 100%. I admire the I admire the balls of steel. </s><s>[INST] Yeah. In whatever way that balls of steel takes uh, takes form, uh You mentioned smart contracts. What are your thoughts about in the context of the history of money? About a theory um, about smart contracts about kind of uh more systematic at scale formalization of agreements between humans. [/INST] I think it must be the case that a lot of the complexity in a mortgage is redundant. That when we are confronted with pages and pages and pages and pages of small prints. Uh we're seeing some manifestation of the late stage regulatory state. The transaction itself is quite simple and most of the verb is just as covering by regulators. So I think the smart contract, although I'm sure lawyers will email me and tell me I'm wrong, can deal with a lot of the plain vanilla and maybe not so plain transactions that we want to do and eliminate yet more intermediaries. That's my, my kind of working assumption. And given that a lot of of financial transactions have the potential at least to be, to be simplified, automated turned into smart contracts that that's probably where the future goes. I can't see an obvious reason why my range of different financial Needs. Let's think about insurance for example, will continue to be met with instruments that in some ways 100 years old. So I think we're still an early stage of a financial revolution that will greatly streamline how we take care of all those financial needs that we have uh, mortgages and insurance leap leap to mind. You know, most households are, are penalized for being financially poorly educated and confronted with oligopoly stick financial services providers. So you kind of leave college already in debt. So you start uh, in debt servitude and then you've got to somehow leave her up to buy a home if you can because everybody's kind of telling you you should do that. So, so you and your spouse, you are getting even more leveraged and your your long one asset class called real estate, which is super illiquid. I mean already I'm, I'm crying inside at the thought of describing so many households financial predicament in that way and I'm not done with them yet because, oh, by the way, there's all this insurance you have to take out and here are the providers that are willing to ensure you and hear the premiums are going to be paying, which are kind of presented to you. That's your, that's your car insurance, that's your home insurance. And if you're here, it's the earthquake insurance and pretty soon you're just bleeding money in a bunch of monthly payments to the mortgage lender to the insurer to all the other people that lent you money. And let's look at your balance sheet, it sucks, you know, there's this great big chunk of real estate and what else have you really got on there. And the other side is a bunch of debt, which is probably paying too high interest. The typical household in the median kind of ranges is at the mercy of oligopoly stick financial services providers go down further in the social scale and people are outside the financial system altogether. And those poor folks have to rely on Bank notes and informal lending with huge punitive rates. We have to do better than this. This has to be, this has to be improved upon. And I think what's exciting about our time is that technology now exists that didn't exist when I wrote the ascent of money to solve these problems when I wrote the ascent of money, which is in 2008. you couldn't really solve the problem I've just described, certainly you couldn't solve it with something like microfinance that was obviously not viable. The interest rates were high, the transaction costs were crazy, but now we have solutions and the solutions are extremely exciting. So Fintech is this great force for good that brings people into the financial system and reduces transaction costs. Crypto is part of it, but it's just part of it. There's a much broader story of Fintech going on here where you get suddenly you get financial services on your phone don't cost nearly as much as they did when they had to be a bricks and mortar building on main Street that you kind of went humbly and beseeched to lend you money. I'm excited about that because it seems to me very socially transformative. I'll give you one other example of what's great, the people who really get sculpt in our financial system are senders and receivers of remittances which are often amongst the poorest families in the world. The people who are like my wife's family in East africa really kind of hand to mouth and if you send money to East Africa or the Philippines or Central America. It's the transaction costs are awful. Uh I'm talking to you Western Union we're going to solve that problem. So 10 years from now the transaction costs will just be negligible and the money will go to people who need it rather than to rent seeking financial institutions. So I'm on the side of the revolution with this because I think the incumbent financial institutions globally are doing a pretty terrible job and uh middle class and lower class families lose out. And thankfully technology technology allows us to fix this. </s> |
<s>[INST] Yeah, that's that's such a thank you for saying that. There's such a hopeful message that no matter what happens to you, there will be a place these people you meet that also have what you have and you will find happiness there and safety [/INST] there. Yeah, but it doesn't need to end Well, it can also all go wrong. So there's no guarantees in this life. So you can do everything right and you still can fail and you can see horrible things happening to you that traumatize you and mutilate you and you have to be grateful if it doesn't happen </s><s>[INST] and ultimately be grateful no matter what happens. Because even just being alive is pretty damn nice. [/INST] Yeah. Even that, you know, um the gratefulness in some sense is also just generated by your brain to keep you going. It's all the trick. </s><s>[INST] Speaking of which camus said, I see many people die because they judge that life is not worth living. I see others paradoxically getting killed for the ideas or illusions that give them a reason for living. What is called the reason for living is also an excellent reason for dying. I therefore conclude that the meaning of life is the most urgent of questions. So I have to ask what Joshua bach is the meaning of life. It is an urgent question according to camus, [/INST] I don't think that there's a single answer to this. Nothing makes sense unless the mind makes it so. So you basically have to project the purpose and if you zoom out far enough, that's the test of the universe and everything is meaningless. Everything is just a blip in between. And the question is, do you find meaning in this blip in between? Do you find meaning in observing squirrels? Do you find meaning in raising Children and projecting a multigenerational organism into the future? Do you find meaning in projecting an aesthetic of the world that you like to the future and trying to serve that aesthetic And if you do, then life has that has that meaning? And if you don't, then it doesn't. </s><s>[INST] I kind of enjoy the idea that you just create the most vibrant, the most weird, the most unique kind of blip. You can given your environment, given your set of skills just be the most weird set of ah like local pocket of complexity. You can be so that like when people study the universe, they'll pause and be like, uh that's weird, [/INST] it looks like a useful strategy. But of course it's still motivated reasoning, obviously acting on your incentives here. </s><s>[INST] It's still a story we tell ourselves within a dream. That's, that's hardly in touch with reality. [/INST] It's definitely a good strategy if you are </s><s>[INST] a podcaster. Mhm uh and human, which I'm still trying to figure out if I am, [/INST] there's a mutual relationship somehow, </s><s>[INST] somehow josh you're, you're one of the most incredible people I know. Um I really love talking to you, I love talking to you again and it's really an honor that you spend your valuable time with me. I hope we get to talk many times throughout our uh there are short and meaningless lives [/INST] more meaningful </s><s>[INST] or meaningful. [/INST] Thank you. Lex I enjoyed this conversation very much. </s><s>[INST] Thanks for listening to this conversation with your Shabak. Thank you to coin base code Academy Lynn owed net suite and express VPN check them out in the description to support this podcast. Now, let me leave you with some words from carl. Young people will do anything no matter how absurd in order to avoid facing their own souls. one does not become enlightened by imagining figures of light, but by making the darkness conscious. Thank you for listening and hope to see you next time [/INST] </s> |
<s>[INST] in the network of software processes leading to people. That's a beautiful way to see the world. Again, the same similar question is with OpenCog. If somebody wanted to build an AI system and plug into the singularity net, what would you recommend? [/INST] Yeah, so that's much easier. I mean, OpenCog is still a research system, so it takes some expertise to, and sometimes, we have tutorials, but it's somewhat cognitively labor-intensive to get up to speed on OpenCog. And I mean, what's one of the things we hope to change with the true AGI OpenCog 2.0 version is just make the learning curve more similar to TensorFlow or Torch or something. Because right now, OpenCog is amazingly powerful, but not simple to do one. On the other hand, singularity net, you know, as an open platform was developed a little more with usability in mind, although the blockchain is still kind of a pain. So I mean, if you're a command line guy, there's a command line interface. It's quite easy to take any AI that has an API and lives in a Docker container and put it online anywhere, and then it joins the global singularity net. And anyone who puts a request for services out into the singularity net, the peer-to-peer discovery mechanism will find your AI. And if it does what was asked, it can then start a conversation with your AI about whether it wants to ask your AI to do something for it, how much it would cost and so on. So that's fairly simple. If you wrote an AI and want it listed on like official singularity net marketplace, which is on our website, then we have a publisher portal and then there's a KYC process to go through because then we have some legal liability for what goes on on that website. So in a way that's been an education too. There's sort of two layers. Like there's the open decentralized protocol. And there's the market. Yeah, anyone can use the open decentralized protocol. So say some developers from Iran and there's brilliant AI guys in University of Isfahan in Tehran, they can put their stuff on singularity net protocol and just like they can put something on the internet, right? I don't control it. But if we're gonna list something on the singularity net marketplace and put a little picture and a link to it, then if I put some Iranian AI geniuses code on there, then Donald Trump can send a bunch of jackbooted thugs to my house to arrest me for doing business with Iran, right? So, I mean, we already see in some ways the value of having a decentralized protocol because what I hope is that someone in Iran will put online an Iranian singularity net marketplace, right? Which you can pay in the cryptographic token, which is not owned by any country. And then if you're in like Congo or somewhere that doesn't have any problem with Iran, you can subcontract AI services that you find on that marketplace, right? Even though US citizens can't buy by US law. So right now, that's kind of a minor point. You know, as you alluded, if regulations go in the wrong direction, it could become more of a major point. But I think it also is the case that having these workarounds to regulations in place is a defense mechanism against those regulations being put into place. And you can see that in the music industry, right? I mean, Napster just happened and BitTorrent just happened. And now most people in my kids' generation, they're baffled by the idea of paying for music, right? I mean, my dad pays for music. I mean, because these decentralized mechanisms happened and then the regulations followed, right? And the regulations would be very different if they'd been put into place before there was Napster and BitTorrent and so forth. So in the same way, we got to put AI out there in a decentralized vein and big data out there in a decentralized vein now so that the most advanced AI in the world is fundamentally decentralized. And if that's the case, that's just the reality the regulators have to deal with. And then as in the music case, they're going to come up with regulations </s><s>[INST] that sort of work with the decentralized reality, which is- And there's the market. Yeah. My dad pays for music, but I mean- Yeah, that's true. Beautiful. You were the chief scientist of Handsome Robotics. You're still involved with Handsome Robotics, doing a lot of really interesting stuff there. This is for people who don't know the company that created Sofia, the robot. [/INST] Can you tell me who Sofia is? I'd rather start by telling you who David Handsome is because David is the brilliant mind behind the Sofia robot. And so far he remains more interesting than his creation, although she may be improving faster than he is, actually, I mean, he's- Yeah. So, yeah, I- That's a good point. I met David maybe 2007 or something at some futurist conference we were both speaking at. And I could see we had a great deal in common. I mean, we were both kind of crazy, but we also, we both had a passion for AGI and the singularity. And we were both huge fans of the work of Philip K. Dick, the science fiction writer. And I wanted to create benevolent AGI that would create massively better life for all humans and all sentient beings, including animals, plants, and superhuman beings. And David, he wanted exactly the same thing, but he had a different idea of how to do it. He wanted to get computational compassion. Like he wanted to get machines that would love people and empathize with people. And he thought the way to do that was to make a machine that could look people eye to eye, face to face, look at people and make people love the machine and the machine loves the people back. So I thought that was very different way of looking at it because I'm very math oriented. And I'm just thinking like, what is the abstract cognitive algorithm that will let the system internalize the complex patterns of human values, blah, blah, blah, whereas he's like, look you in the face in the eye and love you, right? So we hit it off quite well and we talked to each other off and on. Then I moved to Hong Kong in 2011. So I've been living all over the place. I've been in Australia and New Zealand in my academic career. Then in Las Vegas for a while. Was in New York in the late 90s starting my entrepreneurial career. Was in DC for nine years doing a bunch of U.S. government consulting stuff. </s> |
<s>[INST] you know, to me that's [/INST] pro Topia, that's like okay, </s><s>[INST] we can have war [/INST] without death. </s><s>[INST] Um you [/INST] know, I don't think there should be simulated </s><s>[INST] hell's, I think that [/INST] is definitely one of the </s><s>[INST] ways in which technology could go very very, very, very wrong. So [/INST] almost punishing people in the digital space or something. Yeah, </s><s>[INST] like torturing [/INST] people's memories. So either </s><s>[INST] as a deterrent, [/INST] like if you committed a crime but also just for </s><s>[INST] personal pleasure, if [/INST] there's some signal minted </s><s>[INST] humans in this [/INST] world, um </s><s>[INST] dan Carlin actually [/INST] has this um episode </s><s>[INST] of hardcore [/INST] history on painful </s><s>[INST] tainment of that episode is it's dark [/INST] because he kind of </s><s>[INST] goes through human history [/INST] and says like we, as humans seem to </s><s>[INST] enjoy secretly enjoy or [/INST] used to be openly </s><s>[INST] enjoy sort of the torture and the death [/INST] watching the death and torture of other humans. I </s><s>[INST] do think [/INST] if </s><s>[INST] people were consenting [/INST] we should be allowed to have gladiatorial gladiatorial </s><s>[INST] matches. But [/INST] consent is hard to achieve in those situations it always starts getting slippery. </s><s>[INST] Like it could be [/INST] also forced like it starts getting weird. </s><s>[INST] There's [/INST] way too much </s><s>[INST] excitement like this is what he [/INST] highlights. There's something about human nature that </s><s>[INST] wants to see that violence [/INST] and it's it's really dark and you hope </s><s>[INST] that we can sort of [/INST] overcome that aspect of human </s><s>[INST] nature but [/INST] that's still well </s><s>[INST] within us somewhere. Well I think that's what we're doing [/INST] right now. I </s><s>[INST] have this theory that [/INST] um what is very important about the current moment is that um all of evolution has been survival of the fittest up until now and um at some point you know it's kind of the lines are kind of fuzzy </s><s>[INST] but [/INST] in the recent past </s><s>[INST] or maybe [/INST] even just right now we're getting to this point </s><s>[INST] where we can choose [/INST] intelligent design. Like we </s><s>[INST] probably since like the [/INST] integration of the iphone like we are becoming </s><s>[INST] cyborgs like our brains are [/INST] fundamentally changed. </s><s>[INST] Everyone who grew up with electronics, [/INST] we are fundamentally different from previous from homo </s><s>[INST] sapiens. I call us [/INST] home a techno. I I think we have </s><s>[INST] evolved into homo techno which is like [/INST] essentially a new species. Like </s><s>[INST] um if you [/INST] if you look at the way if um are if you took an M. R. I. </s><s>[INST] Of my brain and you took [/INST] an M. R. I. Of like a medieval brain, I think it would be very different the way the way that it has evolved. Do you think when </s><s>[INST] historians look back at this time they'll see like this [/INST] was a fundamental </s><s>[INST] shift and what a human being [/INST] is? I think I I do not think we're we are still homo sapiens, I believe we are homo techno and I think we have evolved um and </s><s>[INST] uh [/INST] and I think right now the way we are evolving um </s><s>[INST] we can we can choose how we do that and I think we're being very reckless about how we're doing that. Like we're just having [/INST] social media. But I think this idea that like this is a time to choose intelligent design should be taken very </s><s>[INST] seriously. [/INST] Like now is the moment to reprogram the human </s><s>[INST] computer. Um you [/INST] know it's like if you go blind </s><s>[INST] um your [/INST] visual cortex will get taken over with other functions. We can </s><s>[INST] choose [/INST] our own evolution, we can </s><s>[INST] change the way our brains [/INST] work and so we actually </s><s>[INST] have a huge [/INST] responsibility to do that and I think </s><s>[INST] I'm not sure who should be [/INST] responsible for that, but there's definitely not adequate education, we're being inundated with all this technology that is fundamentally changing um the physical structure of our brains and we are not um adequately </s><s>[INST] responding to [/INST] that to choose how we want to evolve and we could evolve, we we could be really whatever we want and I think this is a really important time </s><s>[INST] and I [/INST] think if we choose correctly and we choose wisely um </s><s>[INST] consciousness could [/INST] exist for a very long time and integration with </s><s>[INST] ai could be extremely [/INST] positive. Um And I don't think enough people are focusing on this specific situation. Do you think we might </s><s>[INST] irreversibly screwed things up [/INST] if we get things wrong now? Because like the flip side of that, it seems humans are pretty </s><s>[INST] adaptive. So maybe the way [/INST] we figure things out is by screwing it up. Like social media </s><s>[INST] over a [/INST] generation will see the negative effects </s><s>[INST] of social media and then we build [/INST] new social media's </s><s>[INST] and we just keep [/INST] improving stuff </s><s>[INST] and then we learned the [/INST] failure from the failures of the past </s><s>[INST] because humans seem to be [/INST] really adaptive. On the flip </s><s>[INST] side. You [/INST] you can get it wrong in a </s><s>[INST] way where like literally [/INST] would create weapons </s><s>[INST] of war or increase hate past a certain threshold. We really [/INST] do a lot of </s><s>[INST] damage. I mean I think were [/INST] optimized to notice </s><s>[INST] the negative things, [/INST] but I would actually say um </s><s>[INST] you know one of the things [/INST] that I think people aren't noticing </s><s>[INST] is like if you look at Silicon [/INST] Valley and you look at like whatever the tech technocracy, like what's been happening there, like it's </s><s>[INST] like when Silicon Valley [/INST] started, it was all just like facebook and all this like for profit crap that like really wasn't particular I guess it was useful </s><s>[INST] but it was, it's sort [/INST] of just like whatever. </s><s>[INST] Um But [/INST] like now you see like lab grown meat like compostable um or like </s><s>[INST] biodegradable color, [/INST] like single use </s><s>[INST] cutlery or [/INST] like um you know like meditation apps. You know, I think we </s><s>[INST] are [/INST] actually evolving </s><s>[INST] and changing [/INST] and technology is </s><s>[INST] changing. I think they're just maybe [/INST] there </s><s>[INST] isn't [/INST] quite enough </s><s>[INST] education [/INST] about this. And also I don't know if there's like quite enough incentive </s><s>[INST] for it because [/INST] I think the way capitalism works. Um </s><s>[INST] what [/INST] we define as profit, we're also working on an old model of what we define as profit. </s> |
<s>[INST] It's very true. If you think about safety or you're gonna reliability at system level, especially when a human being is involved, it starts becoming hopeless pretty quickly in terms of uh proving that something is safe to a certain level because there's so many variables, it's so complex. Well, [/INST] let's get back to something we can talk about and actually make some progress on, uh, we can look at C plus plus programs and we can try and make sure they crash this often. The way you do that is largely by simplification. It is not the first step is to simplify the code. Have less code. Have code that are less likely to go wrong. It's not by runtime testing everything. It is not by big test frameworks that you're using. Yes, we do that also. But the first step is actually to make sure that when you want to express something, you can express it directly in code rather than going through endless loops and convolutions in your head before it gets down the code that if if if the way you're thinking about a problem is not in the code, there is a missing piece that's just in your head. And the code, you can see what it does, but it cannot see what you thought about it unless you have expressed things directly. When you express things directly, you can maintain it, it's easier to find errors, it's easier to make modifications. It's actually easier to test it and lo and behold it runs faster and therefore you can use a smaller number of computers, which means there's less hardware that could possibly break. Um So I think the key here is simplification but it has to be um to use the Einstein quote, as simple as possible and no simpler? </s><s>[INST] Not simply. [/INST] But there are other areas with under constraint where you can be simpler than you can be in C plus plus, but in the domain I'm dealing with, that's the simplification I'm after. </s><s>[INST] So how do you inspire [/INST] or </s><s>[INST] ensure that the Einstein level simplification is reached? So can you do code review, can you look at code? Is there if I gave you the code for the Ford F150 and said here, is this a mess or is this okay, Is it possible to tell, is it possible to regulate? [/INST] And experienced developer can do that code and see if it smells uh mixed metaphors deliberately. Uh the the point is that it is hard to generate something that that is really obviously clean and can be appreciated but you can usually recognize when you haven't reached that point. And so if I have never looked at uh if 1 50 code so I wouldn't know but but I know what I ought to be looking for that. I'll be looking for some tricks that correlates with bugs and elsewhere. And uh I have tried to formulate rules for what what good code looks like. Um and the current version of that is called the C plus plus call guidelines. one thing people should remember is there's what you can do in a language and what you should do In a language. You have lots of things that is necessary in some context, but not in others as things that exist just because there's a 30 year old code out there and you can't get rid of it. But you can't have rules that says when you create a try and follow these rules, this does not create good programs by themselves, but it limits the damage and for mistakes, it limits the possibilities of the mistakes. And basically we are trying to to say what is it that a good programmer does at the fairly simple level of where you use the language and how you use it. Now I can put all the rules for chiseling and my marble, it doesn't mean that somebody who follows all those rules can do a masterpiece by Michelangelo. That Is there something else too right? A good program. Just is there something else to create a important work of art That is the there's some kind of inspiration, understanding gift, but we can approach the sort of technical, the craftsmanship level of it. The famous painters, the famous cultures was, among other things, superb craftsman. They could express their ideas using their tools very well. And so these days, I think what I'm doing, what a lot of people are doing, we are still trying to figure out how it is to use our tools very well. For a really good piece of code, you need a spark of inspiration and you can't, I think regulate that. You you cannot say that. I'll take a picture only, I'll buy your picture only. If you're at least then go um, there are other things you can regulate but not the inspiration. </s><s>[INST] I think that's quite beautifully put. It is true that there is, is an experienced programmer when you see code that's inspired, that's uh, like Michelangelo, you know it when you see it and uh, the opposite of that is code. That is messy. Code that smells, you know, when you see it and I'm not sure you can describe in words except vaguely through guidelines and so on. [/INST] Yes, it's easier to recognize ugly than to recognize beauty encode. And for the reason is that sometimes the beauty comes from something that's innovative and unusual and you have to sometimes think reasonably hard to appreciate that. On the other hand, the messes have things in common and you can you can have static checkers and dynamic checkers that finds uh, a large number of the most common mistakes. You can catch a lot of sloppiness mechanically. I'm a great fan of static analysis in particular because you can check for not just the language rules but for the usage of language rules. And I think we will see much more static analysis in the coming decade. </s> |
<s>[INST] So one of the things that are numbers is that usually talk about deaths. But with with the famine and starvation, the thing I often think about that's impossible to put into numbers is the number of people and the degree to which they were suffering. You know, the number of days spent in suffering, so I mean, death is yes. Uh, death is just one of the consequences of suffering. And to me, it feels like 1, 23 years or months and then years of of not having anything to eat, uh is worse. And it's sort of those Those aren't put into numbers. Often [/INST] that's right. And the effect on people long term, you know, in terms of their mental health, in terms of their physical health, their ability to work, all those kinds of things, you know. I mean, Ukrainians are working on people working on this subject now, you know, the long term effective of the hunger famine on them. And I'm sure there's a similar kind of long term effect on Chinese peasantry of what happened, you know? I mean, you're destroying multigenerational, multigenerational. That's right as well. And you know, it's a it's a really you're absolutely right. This is a terrible, terrible way to die. And, uh, and it lasts a long time, and sometimes you don't die. You survive. But, you know, in in the kind of shape where that you can't you can't do anything. I mean, you can't you can't function. Your brain has been injured, you know, um, I know it's a Really, Uh, these these famines are really </s><s>[INST] horrible. So when you talk about genocide, it's often talking about murder. Where do you place North Korea? In this discussion? We kind of mentioned it. So in the What is it, The arduous march, Um, of the 1990s, where it was mass starvation. Many people describe mass starvation going on. Now in North Korea, you think about genocide. When you think about atrocities going on in the world today, where do you place North Korea? [/INST] So take a step back when the there were all these courts that were set up for for Bosnia and for Rwanda and And and for other genocides in the 1990s. And then, um, the decision was made by the international community, um, basically to set up the International Criminal Court, which would then try genocide in the more modern period And the more contemporary period and the lists. three crimes, Basically, you know, the genocide, uh, crimes against humanity and war crimes, um, and subsumed to crimes against humanity are a lot of the kinds of things you're talking about with North Korea. I mean, it's it's torture. It's artificial. Sometimes artificial famine or famine. You know, that is not not necessary, right? Not necessary to have it. And other. There are other kinds of, you know, mass rape and stuff like that. There are other kinds of things that fit, uh, into the crimes against humanity. And that's sort of where I think about North Korea as committing crimes against humanity, not genocide. And again, remember, genocide is meant to be. I mean, some people, there's disagreement among scholars and jurists about this. Some people think of genocide as the crime of crimes. The worst of the three that I just mentioned. But some think of them as co equal and the I, C. C. The International Criminal Court is dealing with them more or less as co equal, even though we tend to think of genocide as the worst. So I mean, what I'm trying to say is that you know, I don't want to I don't want to split hairs. I think it's sort of morally and ethically unseemly. You know, the split hairs about what is genocide and what is a crime against humanity. You know, this is for lawyers, not for historians of terminology. Yeah, Yeah, you know that you don't want to get into that because I mean what happened with Darfur a little bit, where the Bush administration had had declared that Darfur was a genocide and the U. N said no. No, it's, uh, you know, it wasn't genocide as a crime against humanity. And then, you know, that confused things versus clarified them. I mean, we damn well knew what was happening. People were being killed and being attacked. Um, and, uh and so, you know, on the one hand, I think the whole concept in the way of thinking about history, using genocide as an important part of human history is is crucial. On the other hand, I don't like to, you know, get involved in the hair splitting what's genocide and what's not so so that you know, North Korea. I tend to think of, like I said, as a as committing crimes against humanity and and, you know, forcibly incarcerating people, torturing them. That kind of thing, routinely incarcerating, depriving them of certain kinds of human rights, can be considered a crime against humanity. But I don't think of it as the same way I think about genocide, which is an attack on a group of people. Let me just leave it at that. </s><s>[INST] What in this? If we think about if it's okay, can we loosely use the term genocide here? Just let's not play games with terminology. Just bad crimes against humanity. Uh, of particular interest are the ones that are going on today. Still, because it raises the question to us. What do people outside of this what role do they have to play? So what role does the United States or what role do I as a human being who has food today, who has shelter, who has a comfortable life? What role do I have when I think about North Korea, when I think about Syria, what I think about maybe the weaker population in China? [/INST] Well, I mean, the role is the same role I have, which is to teach and to learn and to mhm get the message out that this is happening because the more people who understand it, the more likely it is that the United States government will try to do something about it. Um, you know, in within the context of who we are and where we live, right? And so you know, I write books. You do shows, you know, maybe you write books, too. I don't </s> |
<s>[INST] Well, definitive is a funny is a funny word because my senses, this is the saddest part for me is my sense in terms of intelligent alien civilizations. I feel like we're so we're so self obsessed that we literally would not be able to detect them even when they're like in front of us. Like trees could be aliens, but just their intelligence could be uh realized on a scale, on a time scale or physical scale that we're not appreciating. Like trees can be way more intelligent than us. I don't know. It's just a dumb example. Could be rocks, rock or it could be things like, no, because I love this. This is Dawkins memes. It could be the ideas are the like ideas we have. Like where do ideas come from? Where did thoughts come from? Maybe thoughts are the aliens? Or maybe thoughts is the actual mechanisms of communication in physics. Right? This is like we think of thoughts as something that springs up from neurons firing where the hell they come from. And now what about consciousness? Maybe consciousness is the communication. It sounds like ridiculous. But like we're so self centered on this space time communication and physical space using like written language like spoken with audio on a time scale. That's very specific kind of physical skill is very specific. Ah So so I I tend to think that bacteria will probably recognize like like moving organisms will probably recognize. But when that forms itself into intelligence most likely will be robots of some kind. Because we won't be making the origins will be meeting the creations of those intelligences. We just would not be able to uh to appreciate it. And that's the saddest thing to me that uh we yeah, we're too dumb The sea aliens. Uh like we're to kind of think like look at the progress of science. We've accomplished so much. The sad thing. It could be that we're just like in the first.0001% of understanding anything. It's humbling. [/INST] I hope that's true. You have to feel like we're very Ignorant as a species and I hope that our current level of knowledge only represents the .001% of what we will someday achieve. That actually feels optimistic to me. </s><s>[INST] Well, I feel like that's easier for us to comprehend in the space of biology and not as easy to comprehend in the space of physics for example, because we have a sense that we have. Mhm. It's like if you, if you talk to theoretical physicists, they have a sense that we understand the basic laws that form the nature of reality, a very universe. But so there's much more complex physicists and much more confident biologists are like uh this is a squishy mess, we're doing our best uh physicist, but I would be would be fascinating to see if physicists themselves would also be humbled by they're being like, what the hell is dark matter and dark energy? What what the hell is the, not just the origin of not just the Big Bang, but uh everything that happened since the Big Bang, a lot of things that happened since the Big Bang, we have no ideas about, except basic models of physics. [/INST] What the hell happened before the Big Bang? </s><s>[INST] Yeah. What happened before? Or what's happening inside the black hole, why is there a black hole at the center of our galaxy because somebody answered this a supermassive black hole. Nobody knows how it started and they seem to be like in the middle of all Galaxies. Um, so that could be a portal for aliens to communicate through conscious. Okay. Um, all right back to planet. How, what's your favorite outside of earth? What's your favorite planet or moon? Maybe outside of the ones? Well, first have we talked about it already or, and then if we did mention it, what's the one outside of that? [/INST] Oh gosh, I have to come up with another favorite. That's not I Oh, </s><s>[INST] I was the favorite. Absolutely, I was, I was a favorite. [/INST] I mean basically everything I've, I've already said, it's just such an amazing and unique object. Um, but on I guess a personal note, it's probably the object that made me become a planetary scientist. It's the first thing in the solar system that really deeply captured my interest. Um, and when I started my PhD, I wanted to be in astrophysicist, working on things like galaxy evolution. Um, and sort of slowly, I had done some projects in the solar system, but I always the thing that really caught me into doing solar system science. </s><s>[INST] Okay, let's, let's leave moons aside, what's your favorite planet? It sounds like you like moons better than planets. So it's uh, [/INST] that's accurate, but the planets are fascinating. I think, you know, I find the planets in the solar system really fascinating. What I like about the moons is that they, there's so much less that is known, there's still a lot more discovery space. And the questions that we can ask are still the bigger questions </s><s>[INST] which [/INST] you know, I end maybe I'm being unfair to the planets because we're still trying to understand things. Like was there ever life on mars? And that is a huge question and one that we've sent numerous robots to mars to try to answer. So maybe I'm being unfair to the planets, but there is certainly quite a bit more information that we have about the planets than the moon's. But I mean venus is a fascinating objects. So I like the objects that lie at the extremes. I think that if we can make a sort of theory or like I've been saying framework for understanding planets and moons that can incorporate even the most extreme ones, then those are the things that really test your theory and test your understanding. And so they've always really fascinated me. Not so much the nice habitable places like earth that these extreme places like venus that have um sulfuric acid clouds and just incredibly hot and dense surfaces and venus of course I love volcanism for some reason and venus has probably has volcanic activity definitely has in the recent past maybe has ongoing today. </s> |
<s>[INST] Okay, cask Jacqueline. A ridiculous question. If human civilization goes extinct Will be the reason you mentioned nuclear war. Do you worry about this? The reason I bring that up, a lot of people in the ai community worry about artificial general intelligence. So super intelligent Ai systems creating a lot of damage autonomous weapons systems is one possibility. A lot of folks recently, especially with this pandemic. If you want to be terrified. listen, uh somebody I talked to recently Sam Harris, he did a four hour podcast on how bioengineering of viruses is likely to destroy human civilization. I recommend that highly if you if you were too optimistic about the future of the human species. So apparently in the space of bioengineering becomes is becoming easier and easier and easier to uh engineer viruses, engineer pathogens. This is the world's most depressing question. What uh do you? Is there something in particularly worry about like that? We should be thinking as a human species about [/INST] uh yeah, I'm sorry to disappoint you again with my lack of worry for all these problems. But I I don't worry too much about it. Um you know what? We we've made it through a bunch of wickets so far as a species and we'll make it through some more or we won't. And if we don't make it through some of these wickets and someone decides that what they're going to do over the weekend is create some crazy virus that spreads and kills everybody. </s><s>[INST] Yeah. You know what I'm usually extremely optimistic about this stuff. I am now I'm with you, except that we won't, well there's always a chance we won't. But I have a sense that human, first of all, I believe that most people have much more capacity for good than evil. All of us are capable of evil, I believe, but most people are much more capable of doing good and want to do good. And uh, I also believe in the resiliency of the human species that we're in an innovative bunch and we can respond to tragedy, especially we respond more to tragedy as the scale of the tragedy grows and our response is much better. [/INST] So that's why I'm not worried about it, bro. </s><s>[INST] Uh, what makes a great man. Let's start at the individual, What makes a great man, what makes a great woman, what makes a great human being, [/INST] somebody that puts others above themselves, </s><s>[INST] What makes a great leader of humans? [/INST] Same thing. </s><s>[INST] But that sentence does a lot of work. There's uh, when you're a leader, there's a lot of egos, there's a lot of tension, there's the humans, the human factor, there's people who are timid, there's people who are assholes, there's people who are incredibly competent, but uh self obsessed. I don't know, there's complexities of human nature, How do you get all those people to do uh, to be the best version of themselves and to lift up everyone else around them. [/INST] Okay, so now that that question is a little bit different now, so now it's getting into a more specific question about the same time, a more broad question of what </s><s>[INST] elements does it [/INST] take to make a good leader? So you're right that different people have different personalities, different tendencies, different levels of ego, and the the way that I try and explain this is um like a video game, and I'm not even a video game player, but I've seen this before where video game characters have various skills, various strengths and weaknesses, so maybe they're strong but they're dumb, or maybe they're strong and smart, but they're slow, they're just giving these these ratings and so that's where human beings are, and that's the way leaders are, and you can have different leaders with different characteristics and depending on how all those characteristics match up, you can have somebody that is very introverted, but they're but they're still a very good leader because when they do communicate they do it in a clear, simple manner that everyone understands. So even though they're a little bit introverted people still respect them and listen to them because they communicate in a clear way, you could have somebody that's extremely charismatic, extremely charismatic and everyone looks to them, but they're slow in making decisions and so now we've got someone that can't really make decisions when decisions need to get made, So even though they're charismatic, they're still not a good leader. Mhm. So depending on the human being that we're talking about and you just mentioned earlier that human beings are more complex than anything and do a better job at just about everything than a robot. So that's the same thing with leadership. You've got all these different characteristics and you you match them or mix them together and depending on where the ratings come out, depending on how that thing does in the end, </s><s>[INST] can we almost like as a case study, looked at a few people in the tech area that I'm familiar with that I know well [/INST] we can the only caveat being that I may have no Familiarization with them whatsoever. You may have to brief me on them. </s> |
<s>[INST] I would [/INST] say one is some also, we either need an explanation for why there's non conscious matter in the universe and then something happens for consciousness to come into being, or it's part of the fundamental nature of reality. </s><s>[INST] It's also if consciousness is a fundamental property of reality, it could also choose to not reveal itself until a certain complexity of organism. I'm not [/INST] sure what that means. </s><s>[INST] I'm not sure what that means either, like, like the flame of consciousness does not start burning until a certain complexity of organisms able to reveal. [/INST] I don't think we can look at consciousness that way. I don't think um I mean, many people like to try to make that argument that it's a spectrum Why do we have to say all or nothing maybe? And I agree that I actually think it is a spectrum. Um, but it's a spectrum of content not of consciousness itself. So, um you know, if a worm has some level of conscious experience, it is extremely minimal. Something we could never imagine being having the complex experience. You and I have um maybe some felt sensation of pressure or heat or something super basic. Right? So there's there's this range. Or even if you just think of an infant, you know, like the first, the moment an infant becomes conscious what that there's a very, very minimal experience of inputs of sound and light and whatever it is. Um and so there's a spectrum of content. There's a spectrum of how much um, a system is consciously experiencing. But there's a moment at which you get on the spectrum and that's and I truly believe that that piece of it is binary. So if there's no conscious experience, there is no consciousness, you can't say consciousness is, there just hasn't lit its flame yet. If consciousness is there, there's an experience, they're by definition, it has to arise at some point or it has to always be there, </s><s>[INST] is it possible to make the case that that are arising, happens first for the first time ever with homo sapiens. [/INST] I think that is extremely unlikely. What I think is more possible based on what we understand about the brain is that it arises in brains or nervous systems. Um and so then we're talking about flies and bees and all kinds of things that kind of fall out of our our intuitions for whether they could be conscious or not. But I think especially once you talk about </s><s>[INST] more [/INST] complex brains with many, many more neurons, when you're talking about cats and dogs and dolphins, um it's very hard to see how there would be a difference between humans and other mammals in terms of conscious. </s><s>[INST] Was there a difference in terms of intelligence between humans and other mammals? Not like fundamental leap and intelligence? [/INST] It's hard to say definitively. I mean it depends on, you know </s><s>[INST] how you [/INST] define intelligence and all kinds of things, but obviously humans are unique and capable of all kinds of things that no other mammals are capable of and there are important differences. And I don't think you need any magical intervention of something outside of the physical world to explain it. And the way I think about consciousness, I actually think it's part of the reason we're mistaken about consciousness </s><s>[INST] is [/INST] because we are </s><s>[INST] special [/INST] in the ways that we're special and because we're complex creatures, we have these complex brains. So I think we should probably get into some of the details of why I think um we're confused about what consciousness is, but just to finish this point, </s><s>[INST] I think [/INST] that we don't actually have any evidence that consciousness is complex that it comes out of complex processing, that it's required for complex processing. And I think we've made this anthropomorphic mistake because we are conscious and it's very hard to to get evidence. Um it's one of the things that makes consciousness unique and mysterious and why I'm fascinated with it is it's the one thing in nature that we can't get conclusive evidence of from the outside. We can by analogy, you know, you're behaving basically the same way I behave more or less. Um you talk about your conscious experiences and therefore I just extrapolate from that, that you're having a felt experience in the way I am and and we can do that throughout nature. </s><s>[INST] Well, there's no [/INST] physical evidence, there's nothing we can observe from the outside that will give us conclusive proof that consciousness is there. And so I think we've made this leap too </s><s>[INST] because [/INST] we're conscious and because we're unique and special and um complex and intelligent in the way that we are, and because we don't have an intuition that anything else is conscious or we have no feedback about it, we've made this assumption that consciousness that those things aren't conscious and felt experience does not exist out there in in other atoms and and forms of life even, but especially not inanimate objects. Um and therefore consciousness </s><s>[INST] is [/INST] somehow tied to these other things that make us unique, That consciousness arises when there is this complex processing when there is. And there's we can talk about the evolution argument too, which I think is super interesting to get into? And I'm hoping to talk to Richard Dawkins um about this, for he's not interested, he's not interested in actually the conversation I would have with him would be very brief because he's he's just not that interested in this topic. </s><s>[INST] But [/INST] let's go back to the Richard Dawkins piece, because there's, I feel like there's a lot to talk about here in terms of our intuitions about consciousness, what it's doing, why in my book. And, you know, everywhere I talk about consciousness, I bring it back to these two questions that I think are at the heart of our intuitions about consciousness. And so your questions about whether human beings are unique and special and all of that, um, I think are interesting questions and something we could talk about. I see them as separate questions from the consciousness questions. </s> |
<s>[INST] justice. So I I also think, yeah, as a fan of fiction is a fan of stories that the travesty and the tragedy and the unfairness and the tension of it is what makes the prize and similar prizes beautiful. The the decisions of other humans that result in dreams being broken and you know, like that's why we love the olympics as so many people, athletes give their whole life for this particular moment and then and then there's a referee decisions and like little slips of here and there, like the little misfortunes that destroy entire dreams and that's it's weird to say, but it feels like that makes the entirety of it even more special. Yeah, if it was perfect, it wouldn't be [/INST] interested in humans like competition and they like heroes. And unfortunately it gives the impression to youngsters today that science is still done. Bye bye white men with gray beards wearing white lab coats. And I'm very pleased to see that this year, you know, Andrea Ghez, the fourth woman in the history of the Physics prize to have received it. And then uh two women, one at Berkeley one elsewhere, won the Nobel prize in chemistry without any male co recipient. And so that's sending a message. I think two girls that they can do science and they have um role models, I think the breakthrough prize and other such prizes show that teams get recognized as well. And and if you pay attention to the newspapers, you know, most of the good authors like you know, Dennis over by of the new york Times and others said that these were teams of people and they emphasize that and you know, they all played a role and you know, maybe if some grad student hadn't saw ordered some circuit, maybe the whole thing wouldn't have worked, you know, but still, you know Ray Weiss kip thorne was the theoretical uh you know, impetus for the whole search for gravitational waves. Barry Barish brought the M. I. T. And caltech teams together to get them to cooperate at a time when the project was nearly dead from what I understand and contributed greatly to the experimental setup as well. He's a great experimental physicist, but he was really good at bringing these two teams together instead of having them duke it out and blows and leaving both of them bleeding and dying. You know, the National Science Foundation was going to cut the funding from what I understand, you know, so so there's human drama involved in this whole thing and the olympics. Yeah. You know, a runner or a swimmer, a runner runner, you know, they slip just at the moment that they were taking off from the first thing and that costs them some fraction of a second. And that's it. They didn't win, you know? </s><s>[INST] And in that case, I mean, the coaches, the families, which I've met a lot olympic athletes and the coaches and the families of the athletes are really the winners of the medals. Yeah, I mean, but they don't get the medal and it's, you know, credit assignment is a fascinating thing. I mean, that's the full human story we have, we have and and uh outside of prizes, it's fascinating. I mean, just to be in the middle of it for artificial intelligence, there's a field of Deep learning that's really exciting. And people have been, there's yet another award, the touring Award given for Deep Learning. 2 to 3 folks who are very much responsible for the field, but so are a lot of others. That's right. And there's a few, there's uh uh there's a fellow by the name of Schmidt huber who uh he sort of symbolizes the the forgotten folks in the in the Deep Learning community. But, you know, that's that's the unfortunate, sad thing we remember remember Isaac Newton remember uh these these [/INST] these special </s><s>[INST] figures and the ones that flew [/INST] close to them, </s><s>[INST] we forget. [/INST] Well, that's right. And often the breakthroughs were made based on the body of knowledge that had been assimilated prior to that, but you know, again, people like the worship heroes, you mentioned the Oscars earlier and you know, you look at the direct, I mean, well, I mean, okay, directors and stuff sometimes get awards and stuff. But uh, you know, you look at even something like, I don't know, songwriters, musicians Elton john or something, Right? Bernie Taupin right, wrote many of the words or yeah, he's not as well known or or the Beatles or something </s><s>[INST] like that. I was heartbroken to learn that Elvis didn't write most of the [/INST] songs. Yeah, that's right there. But he was the king, right? And he had such a personality and it was such a performer. Right? But it's the unsung heroes in many cases. Yeah. </s><s>[INST] So maybe they can step back. We talked about the Nobel prize is accelerating universe. But your work and the ideas around supernova were important uh, in detecting this accelerating universe. Can we go to the very basics of what is this beautiful, mysterious object of a supernova? [/INST] Right, so a supernova is an exploding star. Most stars die a relatively quiet death are our own sun. Well, despite the fact that it will become a red giant and incinerate earth, it will do that reasonably slowly. But there's a small minority of stars that end their lives in a titanic explosion and that's not only exciting to watch from afar, but it's critical to our existence because it is in these explosions that the heavy elements synthesized through nuclear reactions during the normal course of the star's evolution and during the explosion itself, get ejected into the cosmos, making them available as raw material for new stars, planets and ultimately life. You know, and that's just a great story. Um, the best in in some ways. So, you know, we like to study these things and and our origins, but it turns out these are incredibly useful beacons as well because if you know how powerful uh an exploding star really is by measuring the apparent brightness at its peak in Galaxies whose distances we already know through having made other measurements. And you can thus calibrate how powerful the thing really is. And then you find ones that are much more distant, then you can use their observed brightness compared with their true intrinsic power or luminosity to judge their distance and hence the distance of the galaxy in which they're located. </s> |
<s>[INST] I think he's, uh, there's a place for that. It's almost, well, first of all, he's, uh, he's working on a new book, which I really appreciate outside of that. He's working on like a big book for a while, which is white pill? There's also working on this like short little thing which is uh like anarchists um handbook or something like that? It's like anarchy for idiots or something like that, which I think is really well me being an idiot and being curious about anarchy, it seems useful. So I like those kinds of books [/INST] that's Russian heritage, man, they're anarchists one on one. Yeah, </s><s>[INST] I mean it's a I find those kinds of things useful. Thought experiment because uh that's why it's frustrating to me when people talk about communism or socialism or even capitalism where they can't enjoy the thought experiment of like why did communism fail? And maybe ask the question of like, are there is it possible to make communism succeed or are there good ideas and communism? Like, I enjoy the thought experiment, like the discourse of it, like the reasoning and like devil's advocate, all that people have like seem to not have patience for that. They're like communism bad red, [/INST] I was obsessed with the question and still I am, I will never be, I will never quench my thirst for Russian history. I love that period of 1892, it's just like, it's so fucking crazy. Like the autocracy embodied in Czar Alexander and then you get this like weird fail son Nicholas who is kind of a good guy, but also terrible and also Russian autocracy itself is terrible and then I just became obsessed with the question of like why did the bolshevik revolution succeed because like people in Russia didn't necessarily want bolshevism, people suffered a lot under bolshevism and it led to stalinism, how did Vladimir Lenin do it? Right, like and I became obsessed with that question and it's still, I find it so interesting, which is that a series of accidents of history, incredible boldness by Lenin, incredible real politik smart, unpopular decisions made by Trotsky and Stalin and just like the arrogance of the czars and of the of the Russian like autocracy and just but at the same time there's all these like cultural implications of this, right in terms of like how it became hollowed out post Catherine the Great and all that I was obsessed with auto because Russia was an actual autocracy and like actually, and I'm like it was there like they didn't even remove serfdom to like the civil war in America like that's crazy like, you know, and nobody really talks about it and I just yeah, I was like was bolshevism a natural reaction to the excesses of czar ism there is a convenient explanation where that is true, but there were also a series of decisions made by Lenin and Stalin to kill many of the people in the center left and marginalize them and also not to associate with the more quote unquote, like uh like amenable communists in order to make sure that they're pure strain of bolshevism was the only thing and the reason I like that is because it comes back to a point I made earlier, it's all about intentionality, which is that you actually can will something into existence, even if people don't want it. That was the craziest thing, like, nobody wanted this, but it's still ruled for half a century or more, actually, I mean, almost, you </s><s>[INST] know, that's fascinating to think that there could have been a history of uh the soviet union that was dramatically different than leninism, stalinism, that was completely different. Like, almost would be the american story. [/INST] Yeah, easily, I mean, there's a world where and I don't have all the characters, there's like Kerensky, and then there was like, whoever Lenin's number two Stalin's chief rival, and even, I mean, look, even a soviet union led by Trotsky, that's a whole other world, right? Like, literally a whole other world. And yeah, it's just, I don't know, I find it so interesting, I will never not be fascinated by Russia. I always well, it's funny that I got to talk to you because it's like, I read this book, I forget what it's called. It one, I think one of paul's surprise, and it was like, the story, I try to understand Russia post Crimea because I came up amongst people who are much more like neo conservative, and they were like, Russia, Russia bad by, And I was like, okay, like, what do these people think? And we have this narrative of like, the fall of the soviet union. And then I read this book from the perspective of Russians who lived through the fall and they were like this, I was like this is terrible. Like actually the introduction of capitalism was awful and like the rise of all these crazy oligarchs. That's why Putin was came to power to restore um restore order to the oligarchy. </s><s>[INST] And he still talks to this day, do you guys, I mean that's always the threat of like, do you want to return to the 90s? Do you want to return to Yeltsin? [/INST] And like, but the thing is in the west we have this like our own propaganda of like no, Yeltsin was great. That was the golden age. What could have been with Russia? And I was like, well what do actual Russians think? And so that yeah, I'll always be fascinated by it. And then just like to understand the idea of feeling encircled by NATO and all of that. You have to understand like Russian defense theory all the way of going back to the SARS has always been defense in depth in terms of having Estonia Lithuania and more is like protection of the Heartland. I'm not justifying in this. So NATO shells like please don't come after me, but look Estonians, Estonians like NATO, they want to be in NATO. So I don't want to minimize that. I'm more just saying like I understand him and Russia much better having done that and we are very incapable in America. I think that's probably because my parents are immigrants. I've traveled a lot of just putting yourself in the mind of people who aren't western and haven't lived history, especially our lives of americans. Forking awesome. We're the number one country in the world like like we're literally better than you like in many ways and they can't empathize with people who have suffered so much and I just yeah, it's just so interesting to me. </s> |
<s>[INST] What was the bigger motivator, the love of winning or the hatred of losing [/INST] tough question, I have to confess, I never heard it before, which is again, congratulations, that's quite an accomplishment. Losing was always painful for me. It was almost like a physical pain because I knew that if I lost the game Mhm. It's just because I made a mistake. So it's I always believed that the result of the game had to be decided by the quality of my play, okay, you may say it sounds arrogant, but it helped me to move forward because I always knew that there was room for improvement. So it's the </s><s>[INST] was there the fear of the mistake [/INST] actually, fear of mistake, guarantees mistakes. And the difference between top players at the very top is that it's the ability to make a decision without predictable consequences. You don't know what's happening. It's just intuitively, I can go this way or that way, and they're always hesitations. People are like, you're you're just, you know, at the crossroad, you can go right, you can go left, you can go straight, you can turn and go back and the consequences are just very uncertain. You have certain ideas what happens on the right, on the left or just, you know, if you go straight, but it's not enough to make well calculated choice and when you play chess at the very top is it's it's it's about your inner strength, so I can make this decision, I will stand firm and I'm not going to waste my time because I have full confidence that I will go through. Um going back to the original question is I would say neither, it's just it's the, it's love for winning, hateful losing. There were important elements, psychological elements, but the key element, it's the, I would say the driving force was always my passion for, for making it making a difference. It's just I can move forward and I can always, it's, I can always enjoy not just playing but creating something new, </s><s>[INST] creating something new. How do you think about that? [/INST] It's just finding new ideas in the openings, you know, some original plan in the middle game. It's actually that helped me to make the transition from the game of chess where I was at the very top to another life. Well, I knew I would not be number one, I would not be necessarily on the top, but I could still be very active and productive by my ability to make a difference. By influencing people, say joining the democratic movement in Russia or talking to people about human machine relations. There's so many things where I knew my influence may not be as decisive as in chess, but still strong enough to help people to make their choices. So </s><s>[INST] you can still create something new that makes a difference in the world outside of chest. But wait, you've kind of painted a beautiful picture of your motivation to chest to create something new, to look for those moments of some brilliant new ideas. But were you haunted by something? So you make it seem like to be at the level you're at, you can get away without having demons without, without having fears, without being driven by some of the darker forces. Oh, [/INST] I mean you sound almost religious in the dark forces, the ritual humans. I mean you have a call for a priest. Uh, now just let's go back to, to, to these crucial chest moments where I had to make big decisions. As I said, it's, it's, you know, it was all about my belief from very early days that I can make all the difference by playing well or by making mistakes. So the yes, I, I always had an opponent across the chessboard opposite man. But no matter how strong the opponent was, where they just order player or another wall champion like Angelique or POV, I having all respect from my opponent. I still believe that it's, it's up to me to make the difference. Uh, I, you know, I knew I was not invincible. I made mistakes, I made some blunders and you know, with age there, I mean more blunders, so kick it. I knew it, but it's, it's still, you know, it's, it's very much for me to be decisive factor in the game. I mean, even now look, I just, you know, my latest chest experience was horrible. I mean, like I played Carolina Corona, Corona, uh, this number two, number two, number three player in the world these days, we played this 9 60 with the fish or so called Fischer random chairs through shuffling pieces. Yeah, I lost very badly. But it's because I made mistakes. I mean, I had so many winning positions. I mean, 15 years ago I would have crushed him. So, and it's, it's, you know, while I lost, I was so much upset. I mean, I know, as, as I said in my, in, in the interview, I can fight any opponent, but not my biological clock. So it's uh, It's fighting time is always a losing proposition. But even today at age 56, you know, I I knew that, you know, I could play a great game. I couldn't finish it because I didn't have enough energy or just, you know, I couldn't have the same level concentration, but you know, in a number of games where I completely outplayed one of the top players in the world, I mean, give me a certain amount of pleasure. That is, even today, I haven't lost my touch, not the same. You know, uh, okay, the jaws are not as strong and the teams are not as sharp, but I could get him just, you know, almost, you know, on the ropes, uh, still got it and it's, you know, and it's, I think it's, my wife said it. Well, I mean, she said, look gary, it's somehow, it suddenly just fighting biological biological clock. It's just, you know, maybe it's a signal because, you know, the goddess of chess since you spoke great religious, the goodness of chess, keisha, maybe she didn't want you to win because, you know, if you could beat number two, number three player in the world, I mean, that's that's that's one of the top players who just recently played World Championship match. If you could beat him, that was really bad for the game of chess. But just what people will say, oh, look, the game of chess, you know, it's it's it's it's not making any progress. The game is just, you know, it's it's totally devalued because the guy coming out of retirement, you know, just, you know, winning games. Maybe that was good for chest, not good for you. But it's look uh been following your logic. We should always look for, you know, demons, you know, superior forces and other things that could, you know, it's not dominate our lives, but somehow, you know, play a significant role in in uh, the outcome. </s> |
<s>[INST] what every style and this is where submission like catch dressing or submission wrestling or just feels different, which it seems like for most wrestling. For a lot of wrestling, the dominance is the, is the goal as opposed to submission, which I guess those are two are related but dominating the position. So that's what pinning is. It's almost like breaking your opponent, like breaking through all of their defenses to where they're completely defenses and you could do anything with them and you want. Maybe that's what could be a definition of dominance. I don't know. And [/INST] I mean it sounds very much like chained to a radiator. Yeah, yeah, </s><s>[INST] yeah. Uh, there's a threat that connects all things. Uh, but submission feels different. I mean, [/INST] it is actually different when you think about it across the landscape. I don't think radically different, but still slightly different. And that, um, if you think of wrestling as being derived from, from, from combat, right? So, well, it is combat sports, but more and more lethal. Combat. Getting somebody off their feet and onto their back is about as lethal place for the person on bottom to be in general. I mean, I don't come at me with your talks about your sucking worm, guards and blah blah blah and whatever fits Spider Baron. Okay, Get out of here with that. We're not talking about you in this highly regimented sporting environment. We're talking about general, you know, all the body hair, none of the waxing human beings. So uh getting someone on their back, okay there, you're trying to get up, you're getting hit with a rock or stabbed or what have you set on fire? Who knows? Generally these conflicts are not just isolated to one on one. If it's if it's four on to your your your your buddy that was with you back to back now he's on his back, what do you think that it's gonna be one on one while three? Go on one. So and then you go you elevate this to two armored combat, right? And it's boom put them on the ground. All crap. It's hard to get up. Well while you're struggling to get up stab, you know, that's where ju jitsu shoes uh concepts come from with all their leveraging off balancing is oh man, if I end up in this situation and tight close quarters combat. Yes, we could fight it out with swords and knives and what have you. But it's way easier if the first thing I can do is foot sweep you on your back and then pull my knife and just go stick. </s><s>[INST] Is there a thread that connects all of these different arts from not just arts but from the very based violence of wars, as you said that there's no rules to the very regimented. Uh, I'd be a J. F. I do. You just tournaments and just kind of laid out some of it, but can you go all the way to the, [/INST] so when you start off with absolute skills in the sense of absolute offense and defense, in the taking or preserving of life full on at its at its purest form of self defense and self preservation. Okay. And then you extrapolate part of that in that all animals train and violence all play usually degenerates into some sort of soft violence. So be it cats when they're kittens and puppies and everything learns how to kill, how to fight. Um, not that, you know, just that, that dumb alpha mean stuff where the idea is that, oh, by being out for that means you run around like basically just being a bully and a ship head. No, actually alpha wolves spend very little time fighting because if you were actually alpha, you don't get into fights, there's no need to. Um, and if you are probably getting into any large amount of fights, it's probably because you're being a shitty at being an alpha and now people are tired of you being in charge. Um, and yet in the animal world, and it would be the same for human beings at that, that that base beginning level of violence, there's a big risk. So I know that we live in this place with healthcare and or you might be in a place with nationalized health, whatever, right? There's, there's, there's band AIDS, there's, there's, uh, uh, penicillin, there's all that kind of stuff, but that's not the normal way of things. You know, </s><s>[INST] there's a channel that just hurts me every time I used to follow and I had to unfollowed because it was too painful for music. Human being called nature's metal, uh, instagram. It was sobering and then it was like, this is too sobering, very sobering. So in there, the risk is at its highest level there, the damage you take, the winner walks away, [/INST] her getting blamed when you need every aspect of your physical and athletic faculties to survive because it isn't going to be the, this isn't the first and it's definitely not gonna be the last, especially if you're the slowest one. You know, it's uh, it was, it was it, uh, lyric from a clutch song. Uh, don't go for the fat ones, just go for the slow ones. </s><s>[INST] Um, man, but that, the universal truth of the way nature works, he says cruel. It's not cruel is just the way it is. [/INST] Yeah, I mean, watch animals get into fights on, on any of these sort of documentary stuff. You'll see an intense short and then dispersal, you'll see as soon as one feels like things that switch just enough to boom the bear or whatever it is, takes off, it's like, I'm not I'm done with this because if you can get out of there with just some scars and what have you, okay, you lose. And I, it's not as good. Uh, you really get hurt bad and get infected. You're done, You know, So it, there's a serious risk to be um, that can come with these sort of things. Yet. I believe that we are inherently born for at least aspects of and use of violence. And so at the end of the day, we need these things, not just to not just survive each other, but they're, they're a part of being able to hunt and other things. But the violence is a part of human nature. Violence is, is like, it's an absolute, it is in every person. It is a part of every interaction. It isn't part of every, every law, everything. And I'm not, by the way, not an ancap. So don't even, don't, don't hit your wagon to me on that one. And Captain Captain capitalist, Yes. Not not an an cap. </s> |
<s>[INST] Beautiful. I think facebook should have that. I I honestly so call me crazy but maybe you can actually speak to this but I don't think facebook well now they would but if they did it earlier they would lose that much money. If they allow like transparently tell people, you could just delete everything. They also explain that like in ways that's going to potentially like less than your experience in the short term, like explain that, but then there shouldn't be like multiple clicks of a button that don't make any sense. Uh I'm trying to hold back from ranting about instagram because let me just say real quick because I've been locked out of instagram for a month. Uh and there's a whole group inside facebook, they're like supporters of like lex help, lex, relax, relax. I wasn't blocked. It was just like a bug in the system, somebody was hammering the A. P. I. With my account. So they kept thinking on my bot anyway it's a bug that happens to a lot of people but like first of all I appreciate the love from all the amazing engineers and instagram and facebook, I love those folks. The entire mechanism though is somehow broken. I mean I I I put that on the leadership but it's also difficult to operate. A large company wants the scales, all those kinds of things but it should not be that difficult to do some basic basic things that you want to do which is um in the case of facebook, that's verify your identity to the app uh and also in the case of facebook, in the case of lambrecks like become like disappear if you choose there's downsides to disappearing but it should not be a difficult process and yeah I think I think people are waking up to that I think there's a lot of room for and that an app like lee breaks with its with its foundational ideas to redefine what social media should look like, you know and like you said, I think beautifully anonymity is not the core value, it's just a tool you use and who knows maybe anonymity will not always be the tool we use like if you give people the choice who knows what this evolves from the log in page. They initially created. The key thing is the founding principles and again who knows if you give people a really nice way to monetize their data maybe they will no longer be a thing that you say do not sell user data. Yeah, all those kinds of things. But the basic principles should be there. And also a good simple interface design, uh, goes goes a really long way, like simplicity and elegance, which Liebherr externally is clubhouse [/INST] is a lot better by the way. I don't, I don't mean to uh, I don't mean to go too deep into the history, but the, it was </s><s>[INST] bad. I didn't look at the early [/INST] pictures thank goodness. </s><s>[INST] I I read somewhere that it was like a white screen like with black, it [/INST] was basic down vote buttons were like these big, these big freaking boxes and like I could go on, but it was my, it was my genius design skills. Um, I almost failed art class when I was like in first grade and I think I still have similar skills to my first grade self, but it's gotten a lot better. And thanks to a lot of my friends who have, you know, sort of chipped in here and there. Oh, </s><s>[INST] I love the idea of a button. I just like forget me. [/INST] I don't know that's, </s><s>[INST] that's really moving actually that uh, that's actually all people want is they, they want. I think, okay, I'll speak to my experience, like I will give so much more, uh, if I could just like disappear if I needed to and I trusted the community, I trusted like the founders and the principles that's really, that's really powerful man. Like trust and ease of escape. Yeah. Uh you've also kind of mentioned moderation which is really interesting so with this anonymity and this community, I don't know if you've heard of the internet but there's trolls on the internet [/INST] so I've heard </s><s>[INST] and even if they go to Yale and Dartmouth uh there's still people that probably enjoy the sort of being the guerilla warfare contra revolutionary and just like creating chaos in a place of love. So how do you prevent chaos from and hatred breaking out and lay bricks? [/INST] So the way I think about it is we have these principles um they're pretty simple and they're pretty easy to enforce. And then beyond the principles we have a set of moderators, moderate from every single ivy league school seem of diverse moderators to enforce these principles but not only enforce the principles but kind of clue us in to what's happening in their community and how the real life context of their community translates the CeleBREX context of their community and beyond that we have conversation with them about the standards of the community and we're constantly talking about what needs to be further elucidated and what needs to be tweaked and we're in constant communication with the community now if you want me to get into the principles that underlie lee Brexit's moderation policy? </s><s>[INST] Yeah please. Maybe you can explain that. There's moderators. what does that mean? How are they chosen and what are the principles under which they operate? [/INST] Sure. So how are the moderators chosen? The moderators are all volunteers there lee brexiters who reach out to me and respond to the opportunity to become moderator. And the way they're chosen um is basically we want to make sure that they're in tune with their community. We wanna make sure they come from diverse backgrounds and we want to make sure that there they sort of understand what the community about. And then we ask them some questions about how they would deal with certain scenarios, ones that we've had in the past and we feel strongly about. And it also was that a little more murky where we want to see that they're sort of thinking about these things in a critical way. Um And from there we choose a set and uh they have the power to um take down posts. Of course. Everything at the end of day pens my review but they can take them down and we can reinstate them if it's a if it's a problem but they can take down posts and they can advocate for, you know, different moderation standards and different moderation policies. </s> |
<s>[INST] you first met [/INST] Sabu I was tracking? I didn't know Hector. </s><s>[INST] So when did your paths cross in terms of tracking, when did you first take on the case [/INST] The spring of 11. So </s><s>[INST] it was through anonymous, [/INST] Anonymous but really kind of Losec um we were was a big thing and it was pushed out to all the cyber 56 field offices in the FBI. Um Most of them have cyber squads or cyber units and so you know, it was being pushed out there and it was in the news every day but it really wasn't are so that we didn't have a lot of victims and an R. A. O. Our area of responsibility. Um and so we just kind of pay attention to it. Then I got a tip that a local hacker in new york had broken into A. O. L. And so Olivia Olivia Olson and I had another agent who she's still in, she's a supervisor in L. A. She's a great </s><s>[INST] agent. We [/INST] went all around new york looking for this kid. Um just to see what we can find and ended up out in Staten Island at his grandmother's house. She didn't know where he was, obviously why would she? Um but I left my card. Um he gave me a call that night and started talking to me and I said let's just meet up tomorrow at the Mcdonald's across from 26 fed and he came in and three of us sat there and talked and you </s><s>[INST] know, gave [/INST] me the stuff, He started telling me about the felonies. He was committing those days including that breaking day ol um And then he finally says you know you know I can give you Sabu. Sabu to us was the Kaiser and he was our guy uh you know he was the guy that was in the news that was pissing us off so </s><s>[INST] so he was part of the FBI friday's [/INST] Sabu was. Yeah he let it yeah he was the leader of the FBI Fridays. So </s><s>[INST] yeah what was one of the more memorable uh F. D. Triple S. I said what how do you get why how and why do you go after the beehive that's kind of intense, [/INST] you get you on the news that gets you, it's the it's the lulls it's funnier to go after the big ones. You know and and they weren't getting like real FBI they weren't breaking into FBI mainframes or anything but they you know they were you know affiliate sites or anything that had a lot of law enforcement stuff was coming out. So but you </s><s>[INST] know [/INST] we looked back and so if this kid knew that Sabu we maybe there was a chance we could use the law to lure Sabu out but we also said well maybe this kid no Sabu in real life and so we went and looked through the eyepiece and 10 million I. P. S. We find one and it belonged to him and so that that day. Sabu um someone had doxed. Um and we were a little afraid he was going to be on the run. We had a surveillance team and FBI surveillance teams are awesome. Like you cannot even tell they're FBI agents. It's it's it's they are really that good. I mean there's baby strollers and all whatever you wouldn't expect an FBI agent to have. </s><s>[INST] So that's a little like the movies a [/INST] little bit. Yeah, I mean it is true, but, but they fit into the area. So now they're on the lower east side, which is, you know, baby stroller might not fit in there as well. You know, somebody just laying on the ground or something like that. Um they really get to play the character and get into it. So </s><s>[INST] now I can never trust a baby stroller. [/INST] Yeah, probably </s><s>[INST] every, every baby, I'm just like look at, stare at them, suspicious, [/INST] especially if the moms wearing cargo pants while she pushes it. So </s><s>[INST] it's like a very stereotypical mom, stereotypical baby. I'm gonna be very suspicious. I'm gonna question the baby. [/INST] The baby is wired. </s><s>[INST] You [/INST] know, we raced out there and like our squad is not even full. There's only a few guys there and like I said, I'm I was a suit guy, but that day I had shorts and a t shirt on and a white t shirt on. Um and I only bring it up because he makes fun of me to this day. So I had a bullet proof vest and a white t shirt on and that was it like shorts tune and all that, but um raced over to there, we didn't have any equipment. Um We brought our boss's boss's boss, he stopped off at NYPD, got us like a ballistic shield and a battering ram if we needed it. Um and then we get to Hector's house, Sabato's house and he's on the sixth floor. Um and so normally, you know where the cyber dork squad um we'll hop in the elevator. Six floors is a long ways to go up and bulletproof vest and a ballistic shield, but but we have been caught in an elevator before on a search, so we didn't took the stairs. Um </s><s>[INST] we [/INST] get to the top tad winded. Um but knock on the door and this big towering guy opens the door just slightly and he sees the green vest with big yellow letters FBI and he steps outside um Can I help you? You know, tries to social engineer us. Uh but eventually we get our way inside the house. Um you know, I noticed a few things that, that kind of out of place. Um there's a laptop charger and a flashing mode. Um And I said, well, do you have a computer here and he said no, there's no computer here. Um so we we knew the truth and then the half lies and all that sort of thing. So it took us about another two hours. And finally he gave up that he was he was the guy we were looking for. Uh so we sat there and we kind of showed him sort of the evidence we had against him. Um and you know from his words, we sat there and talked, talked like two grown adults and you know, I gave him the options and he said, well let's uh let's talk about working together, </s> |
<s>[INST] its lowest point. So I wonder if there's a mission where you're going to somehow connect with it once again and place extra things into it. I wonder how challenging that is technically. [/INST] Oh, yeah. It could absolutely be done. The hard thing at this point, because it's on an eccentric orbit, would be rendezvousing with it, because you kind of have to be in alignment with its orbit to really line up well with it. Yeah. I mean, someday I don't see any reason why we couldn't at least send for sure an uncrewed, you know, if Elon wanted to just fly a robot out there to check up on it and photograph it or something. </s><s>[INST] Like we could, that could be well within the realm of things. Getting an Optimus robot up there. So that was the story brilliantly told by you of the rockets for SpaceX. What about through the lens of engines? Can you give a brief history of the SpaceX rocket engines that were used that we haven't covered? You mentioned it started with the Merlin engine, and Kestrel engine would... Through that lens. Yeah. [/INST] That's what's there. Engines are relatively small number which is which is easy for us. There's the Merlin. Merlin's evolved throughout time to be from the Merlin to the Merlin 1c, to the Merlin 1d, to the Merlin 1d Full Thrust and all these other kind of tweaks of the same architecture. Kestrel ended with Falcon 1. They also have the Merlin vacuum engine which is the upper stage engine for Falcon 9. relative system, but just optimized for vacuum, so it has a much larger bell nozzle. There's the Draco thrusters, which you kind of can consider engines. They are rocket engines, but they're just small, they're not like the orbital engines. There's the Super Draco engines, which are the abort thrusters on Crew Dragon Capsule. And then nowadays they have the Raptor engine and the Raptor vacuum variant, but they've already had two versions of Raptor. We've already seen kind of the Raptor development engine, kind of seem like a Raptor 1.5, whereas kind of taking hints of the future Raptor, but now we're well within what you'd consider a Raptor 2 variant. </s><s>[INST] That's really it. That's really it. Yeah, for the Raptor, maybe I'll ask you that separately, but I like in general, and people who doesn't know whoever the astronaut is, but if you don't somehow know, go, go, go check your YouTube channel out, you're an incredible educator about the super technical and the more sort of, even the philosophical, the actual space travel. So you go down to the raw details of it, and there's just great videos on the Raptor engine. I think you have one on Merlin, and also the actual tours with Elon, where he discusses some of those things. On one of the tours, he says, he's full of good lines, that guy. He says something about the number of fiddly bits, and the number of fiddly bits was decreased between Raptor 2 and Raptor 1, and I think that's actually a really beautiful representation of the engineering efforts there, which is constantly trying to simplify, increase the efficiency of the engines, but also simplify the design so you can manufacture it, and in general, simplification leads to better performance and testing and everything. So the number of fiddly bits, I'm sure there's a Wikipedia page on that now, as an index, [/INST] is actually a really good one. Well, and when you think about it, I don't know of any other company prior that had kind of tried to measure their performance of their engine, and thrust to weight ratio, or how efficient it is in specific impulse, but literally in dollar to thrust ratio. How much does this engine cost? How much thrust can it produce? Using that as a trade study, instead of just pure metrics of... Because at the end of the day, if it's cheaper and does X amount of work, even if it's less efficient, it can </s><s>[INST] actually be better long term. So I guess another way, it's not even just thrust. I don't know if that metric is used, but basically, the cost of getting one kilogram of thing up into space, that's basically what they're trying to minimize. [/INST] Especially, yeah. At the end of the day, that is definitely the ultimate metric, is how much does one kilogram cost to orbit eventually? But it's so funny, because spaceflight is just the ultimate compromise. Every little thing, any variable can just change everything else, so you can tweak so many different things to get to different numbers and conclusions, but even things like in your first stage, when the rocket's pointing straight up and the engines are pointing straight down, you're dealing more with the thrust-to-weight ratio of the rocket. How much thrust is it producing versus how much is gravity pulling down on it is actually more important metric than how raw efficient the engine is. So it's funny that in space, it's the opposite, thrust-to-weight ratio doesn't really matter. What really matters is the actual, the specific impulse. Let's call it like the nozzle escape velocity of the, or the injection velocity of the how how fast is the gas moving? It's like the more important number on orbit but it's, it's just so crazy cause there's all these like I would just love to see the trade studies. You know, when you're like trying to figure out like is this more important then this or this or this and it's like, you change just one little thing and also like all the, everything changes. It's just even the profile. Like the launch profile. The trajectory of it. </s> |
<s>[INST] Let me ask a ridiculous question. You know you talk about your favorite soccer player to bar, I'll ask the same question about Einstein's ideas which is um which one do you think is the biggest leap of genius? Is it the equals M. C. Squared is a brown emotion? Is it special relativity is in general relativity which which of of the famous set of papers he's written in 19 oh five. And in general his work was the biggest leap of genius [/INST] in my opinion, is a special relativity. The idea that speed of light is the same for everybody is the beginning of everything he did at the </s><s>[INST] beginning. Is this the beginning is that once you embrace that weirdness that all the weird I [/INST] would say that's that's even though he says the most beautiful moment for him, he says that is when he realized that if you fall in an elevator, you don't know if you're falling or whether you're and whether you are in the falling elevator or whether you're not next to the Earth's gravitational. That that to him was his home moment, which inertial mass and gravitational mass being identical geometrically and so forth as part of the theory. Not because of you know, some some funny coincidence that's for him, but I feel from outside at least it feels like the speed of light being the same is the is the really hard moment. </s><s>[INST] The general relativity to you is not like the conception of space time [/INST] in a sense. The conception of space time already was part of the specialty when you talk about length contraction. So general activity takes that to the next step. But beginning of it was already space length contracts time delays. So why don't you talk about those then? Yeah, you can direct more or less different places than its curvature. So you don't have a choice. So it's kind of started just with that same simple thought speed of light is the same for all. </s><s>[INST] Where does quantum mechanics come into view? [/INST] Exactly. So this is the next step. So Einstein's you know, uh develop general activity and is beginning to develop the foundation of quantum mechanics at the same time, the photoelectric effect on others and um so the quantum mechanics overtakes in fact Einstein in many ways because he doesn't like the probabilistic interpretation of quantum mechanics and the formalism that's emerging. But this is march on and try to for example, combine Einstein's theory of relativity with quantum mechanics. So direct takes special relativity, tries to see how is it compatible with quantum mechanics? </s><s>[INST] Can we pause and briefly say, what is quantum mechanics? [/INST] Yes, sure. So quantum mechanics, So I I discussed briefly when I talked about the connection between newtonian mechanics and the elder Lagrande reformulation of of the Newtonian mechanics and interpretation of this oil dog ranch uh formalism in terms of the paths that the particle take. So when we say a part of that goes from here to here we usually think it classically follows a specific trajectory. But actually in Kano mechanics it falls follows every trajectory with different probabilities. And so there's this fuzziness now most probable it's the path that you actually see and deviation from that is very very unlikely and politically very minuscule. So in everyday experiment we don't see anything deviated from what we expect. But quantum mechanics tells us that things are more fuzzy things are not as precise as the line you draw, things are a bit like cloud. So if you go to microscopic uh scales like atomic scales under these phenomena become more pronounced, You can see it much better, the electron is not at the point, but the clouds spread out around the nucleus. And so this fuzziness. This probabilistic aspect of reality is what quantum mechanics describe. </s><s>[INST] Briefly pause on that on that idea. Do you think this is quantum mechanics is just a really damn good approximation a tool for predicting reality Or does it actually describe reality? Do you think reality is fuzzy at that level? [/INST] Well, I think that reality is fuzzy at that level, but I don't think quantum mechanics is necessarily the end of the story. So, um, so quantum mechanics is certainly an improvement over classical physics that much we know by experiments and so forth. Whether I'm happy with quantum mechanics, whether I view quantum mechanics, for example, the thought the measurement uh, description of quantum mechanics. I'm happy with it. Am I thinking that's the end stage or not? I don't I don't think we're at the end of that story. And many physicists may or may not view this way. Some do. Some don't. But I think that uh, the best we have right now, that's for sure. It's the best approximation for reality we know today. And so far we don't know what it is, the next thing that improves it or replace it and so on. So, but as I mentioned before, I don't believe any of the laws of physics we know today are exactly correct. It doesn't bother me. I'm not like dogmatic. Say I have figured out this is the law of nature. I know everything. No, no, that's that's the beauty about science that we are not dogmatic and we are we are willing to in fact we are encouraged to be skeptical of what we ourselves do. </s><s>[INST] So you're talking about Iraq? [/INST] Yes, I was talking about direct, right? So direct was trying to now combine this shorting as equations which which was described in the context of you know, trying to talk about how these probabilistic waves of electrons move for the atom, which was good for for speech, which were not too close to the speed of light to what happens when you get to the near the speed of light. So then you need relativity. So then Direct tried to combine Einstein's relativity with quantum mechanics. So he tried to combine them and uh he wrote this beautiful equation, the direct equation which roughly speaking take the square root of the Einstein's equation in order to connect it to short english time evolution operator, which is first order in time derivative to get rid of the naive thing that Einstein's equation would have given, which is second order. So you have to take a square root. Now, square root usually has a plus or minus sign when you take it. And when he did this, he originally didn't notice this didn't pay attention to this puzzle minus sign. But data physics pointed out two directions. Look there's also this minus sign and if you use this minus sign you get negative energy. In fact it was very, very annoying that, you know, somebody else tells you this obvious mistake you make polly famous physicist told Direct this is nonsense. You're going to get negative energy with your equation. Which negative energy without any bottom you can go all the way down to negative infinite energy. So it doesn't make any sense. Direct thought about it. And then he remembered Pauli's exclusion principle before, just before him, police said, you know, there's this principle called the exclusion principle that, you know, two or two electrons cannot be in the same orbit. And so Direct said, okay, you know what all these negative energy states our fields orbits occupied. So according to you, uh Mr probably there's no place to go. So therefore they only have to go positive. Sounded like a big cheat and then probably said, oh, you know what? We can change orbits from one over to another. What if I take one of these negative energy orbits and put it up there, then it seems to be a new particle which has opposite properties to the electron has positive energy but it has a positive charge. What is that? Uh the Iraq was a bit worried said maybe that's proton because proton has plus charged. He wasn't sure. But then he said, oh maybe it's proton. But then they said, no, no, no, it has the same mass as the electron cannot be protein because protein is heavier. The rock was stuck. He says, well then maybe another park we haven't seen by that time Direct himself was getting a little bit worried about his own equation and his own crazy interpretation. Until a few years later, Anderson and photographic cosmic in the photographic place that he had gotten from this cosmic rays, he discovered a particle which goes in the opposite direction that the electron goes when there's a magnetic field and with the same mass exactly like what the Iraq had predicted. And this was what we call now positron. And in fact beginning with the work of Iraq, we know that every particle has an anti particle. And so this idea that there's an anti particle came from this simple math. You know, there's a plus and a minus from the drugs, quote unquote mistake. So again, trying to combine ideas sometimes the math is smarter than the person who uses it to apply it and we try to resist it and then you you kind of confronted by criticism which is the way it should be. So physics comes and said, no, no, that's wrong and you corrected and so on. So that is the development of the idea. There's particle, there's anti particle and so on. So this is the beginning of development of quantum mechanics and the connection with relativity. But the thing was more challenging because we have to also describe how electric and magnetic fields worked with quantum mechanics. This is much more complicated because it's not just one point electric and magnetic fields were everywhere. So you have to talk about fluctuating and fuzziness of electrical field and magnetic fields everywhere. And the math for that was was was very difficult to deal with. And this led to a subject called quantum field theory feels like electric and magnetic fields had to be quantum have to be described also in a wavy way. Fine men in particular was one of the pioneers and along with stringers and others to try to come up with the formalism to deal with fields like electric and magnetic fields interacting with electrons in a consistent quantum fashion. And they developed this beautiful theory. Quantum electrodynamics from that. And later on that same formalism quantum field theory led to the discovery of other forces and other particles, all consistent with the idea of quantum mechanics. So that was how physics progress. And so basically we learned that all particles and all the forces are are in some sense related to particle exchanges. And so for example, the electromagnetic forces are, are mediated by particle, we call photo on and uh and so forth. And the same for other forces that they discovered strong forces and the weak force is. So so we've got the sense of what quantum field theory is, </s> |
<s>[INST] you said that there's a difference between a fighter and a martial artist. So now we were talking about fighting, you're considered by many to be one of the greatest fighters of all time. But you've said that there's a difference between a fighter and a martial artist. A fighter is training for a purpose. He has a fight. I I'm a martial artist. I don't train for a fight. I trained for myself. I'm training all the time. My goal is perfection, but I will never reach perfection. So what do you, does it mean to be a martial artist? [/INST] Martial artist is because that lifestyle that I have has been introduced to me and the seed has been planted to my mind a long, long time ago by by my father. I am I do not train because I have a fight. I will always train even now it kind of amused me that to see that a lot of people because I'm still training because I love the science of fighting. I do not like to fight, but I love the science of it and I will always do it as long as I can do it. People think I'm going to make a comeback and everything I'm I'm about to get to have 40 years old, you know, like it's have you know, like, </s><s>[INST] well I don't [/INST] Want to fight in a cage at 40 years old. I mean, some people have done it, they did it very well, but I'm not one of them. I'm I feel a little bit to me that and you never say never. I felt like to me like it's a little like a kid that he played with the strain when he's young, like, and he's five years old, six or seven years old, eight years old. And I was like, What the hell I'm doing here and I'm 12 for this. Like, it's AI I've done it, you know, and and and and I got out of it on top and, and I'm I'm healthy, which is the most important thing right now. I'm touching wood and I'm I'm wealthy, I beat the game, you know what I mean? In a way, like that's not to be cocky, but I did it and I wish more more fighters could do the same thing I wish. But it's unfortunate because a lot of them, they stay there and hang out for too long and they get badly hurt, they get beaten and broken, you know, and they finished broke as well because the lifestyle you have when you're a pro athlete, it's crazy, you know, it's it's unbelievable. However, everything that goes up and life goes down and you need to plan your future. So for for me what if some guys have the same mentality as me and they were watching us right now, I would say if you do it because you're just good at it. You like the money that they advantage, the freedom that it gives you. But you don't necessarily like to fight when you're done. You finish on top, you know, okay, go cash out and get out </s><s>[INST] of the way. It's hard to do. [/INST] However, Alexis, it's not everybody that does it for that reason, some people generally love to fight, love to compete, so they do it because I love it, you know, or they do it because of the money, but if you don't love it, if you don't like to fight because it's very stressful and you don't enjoy, you enjoy the training perhaps, but you don't like to fight, You do it because it's part of what you need to do in order to keep that lifestyle and, you know, like, you don't need the money to get out of here, man. If you're in, you're you're in your prime, get out of here because if you don't, you'll hurt your own legacy, you'll damage your health. It's it's very sad and it's a it's a it's a sad business, you know what I mean? Uh it's like a lot of, one of the place where is the most, the most, one of the most happiest place for me to go and the most saddest place for me to go. It's in the gym tri star in Montreal because it's one of the happiest place for me to go because I can go train and do what I love to do, but it's also a very sad place for me because after when I'm about to leave, there's always a bunch of young kids that comes or Guys that are around 30, years old and they come to me, Hey George you have some advice for me and I look at them and if they're my friend there, real close friend of mine, I'll tell them the truth in their faith and I've done it many times and it was not well received, but if they're not my friend, I have to, you know, you know, there's always an advice about fighting, then I answer their question is my pleasure. But the truth, if they want me to tell the truth, the big majority of them, I would tell them, I said, listen man, you're in a maybe a three, like an a on a losing streak of three fight, You're 30, 33 years old, you know, I think you should think about doing something else in your life. You know, I have other goals, you know, because you're not gonna make it and you know, I've seen that movie before and it's a very sad ending and I'm I'm sad to tell you the truth because you're not gonna make the money just choose something. But if I tell them that they're gonna be angry at me because they would be like, oh you you make it and you think I cannot make it so it's kind of you're gonna think I'm cocky, but I was lucky to make it, you know, and that's the start we're all aligned. But at one point you need to be able to to have a plan B. You know, like like some parents, they come to see me with their kids, hey, this is the future world champion and UFC and what advice would you give him? I always tell the same thing and it doesn't not make everybody happy when I said I say I go to the case a are you good at school? Say stay at school? School is very important for you. Stay educated. Yeah. Do boxing, martial arts. A great sports stay in shape, but don't put your eggs all in the same basket and the parents sometimes are angry when I'm not angry, but I can see in their eyes they're like they kind of surprise and it's not because I made it that I will tell their kids to follow the same path that I did. I went to school to. I I've studied, I I dropped out of school when I had my first world championship fight against matt Hughes, but before that I was school. So I had another, you know, another way to go if things would not have gone the same the way I wanted, but the problem and I'm saying that it's not only about boxing in M M. A. I'm talking about our key basketball, baseball, same same thing, maybe it's the one on 100,000 that make it. And I'm saying I'm saying that make it what I'm saying, I make it doesn't mean they can retire and have enough money for the rest of his life because it's a sad story, the only people only heard about the people that makes it, but a lot of fight or even in the UFC champion in boxing champion, even the football, basketball, I don't I don't I don't care the big names when they retire, they have zero, they're bankrupt my friend. And it's a very sad, sad story in a sad reality that most people are not </s> |
<s>[INST] Yeah. [/INST] What they do is because they know that when someone gets a cancer diagnosis, that their ability to comprehend information changes. When you get a cancer diagnosis, you all the tropes they happen, you're hearing it's weird, you're basically having like an anxiety attack. If I had to guess it's like a hardcore anxiety attack. And then, you know, a nurse is there with me as he's explaining it. And then her job is even though he's telling me how to get to the machine that's gonna scan my body to see if it's gotten into my brain, uh he knows I'm not gonna remember that. And so this nurse, when you're in this like fog takes you at least took me to the machine that does the scan, You're not going to get that data back for a few days. And so that's where you really live in the real world. That's the real </s><s>[INST] world. Such a fascinating moment and the days that follow. And even at that moment because that doctor you talk about the matrix where like the pills and so on. You get the blue pill and the red pill. [/INST] Yeah, this </s><s>[INST] is like the, [/INST] like </s><s>[INST] the real world introduction, the human introduction is the truth. You've now just taken the red pill. You get to see the truth of reality. And here's a busy doctor just telling you like all those dreams, you've had all those illusions, you've built up to somehow your work as a comedian and actor will make you live forever somehow. It's just the basic illusion we have that we're this is this whole project. Uh it's gonna be an infinite sequence of fun things that we're gonna get to do. It's like, holy sh it's not [/INST] that's right, it's over, that's right. And there's very sophisticated ways of doing that. And there's very dumb ways of doing that. And I had really been doing a dumb way of doing that. Like I've been playing around with this idiot notion of subjective consciousness, so like, like I've been sort of kicking around this, like, I think they call it solipsism, it's like you're like, okay, I know I'm self aware, but no one else can prove that they're self aware. Like, I don't I have no way of proving that everything around me isn't just a video game isn't just some projection isn't, you know, who knows what? So maybe everybody else dies there, nBcs, but I don't because I'm the only thing I know that has subjective consciousness now, it's not like I really believed that it's like an idea you toy around with when you're trying to evade confronting the reality of your own mortality. Just the brain will produce all kinds of ridiculous forms of ignorance. And that was one I've been playing around with it. </s><s>[INST] You mean for like a large part of your life you were playing around with that. [/INST] I'm not like really? I think it's important to really emphasize, I didn't think I was immortal. Like I knew at some level I'm probably gonna die. Everyone dies, but there's ways that you can sort of poke around with that idea. I still do it to this day. Like I still do it. Like it's a natural thing to do when you're confronted with that with annihilation. You want a way out, you want to talk your way out, figure it out. There's gotta be some way to fix it. We'll fix it. That's another thing people do. They'll fix </s><s>[INST] it. They'll [/INST] expand the human lifespan. That's what they'll do. I mean that was, that's a big argument for it is like, look, the human lifespan up until covid, which they had to recalculate like the lifespan because of the statistically all the people who died, like threw it off a little bit. But pandemics aside the idea was the human lifespan seemed to be increasing by half a year every year or something like that. We're living longer. So all you gotta do one more half a </s><s>[INST] year and [/INST] we're immortal, right? And we can, we live a year longer every year, then we live forever. And so that's another way you can get out of confronting death as you can think. Well, maybe right now we don't have the tech, but it's coming consciousness uploads or downloads or whatever, depending on how you want to look at it. Another way people try to score them out of the reality of death. There's all kinds of tricks. </s><s>[INST] Yeah. And we do all of them. And sometimes, yeah, I mean, a lot of religions provide different, even more tools in the toolkit for coming up with ideas of how you can living the illusion that we're not going to. There's not an end to this particular experience that we're having here on earth right now. And then when you get that cancer diagnosis, it's like, yeah. What was that? Like going home the car ride, you drive home alone. [/INST] Yeah, I mean, it was one of the most. </s><s>[INST] Would you listen to Bruce Springsteen [/INST] Bruce Little Girl Is your daddy? That's </s><s>[INST] Not a Good 1 to listen. [/INST] You have cancer. Is he gonna die? Yeah. </s><s>[INST] Love songs? Maybe you take you experience them more intensely. [/INST] I don't remember what I listened to and I don't remember driving home, but I do remember driving to another doctor appointment. Doctor's appointment the next day. I think it was the next day. I think the Goodyear blimp was floating in the sky and I was looking, I was a stoplight, looking around is the, is the person flying and how to cure cancer? </s><s>[INST] No, [/INST] I didn't think that what I thought was, this ship just keeps going. That's what I thought. I thought I'm gonna be gone and it's just gonna keep going. And that was a beautiful moment for me. Was this beautiful moment </s><s>[INST] of like, [/INST] Oh yeah, you know, like, that's just what you're talking about with um the Ukraine, what you're talking about. It's like, unless you've been been there, it's really hard to explain to people that even in the midst of what is generally accepted as one of the worst things that can happen to you war cancer. Somehow, </s> |
<s>[INST] and [/INST] he talks about how there's some poem that Lorcan had written that made him realize that the universe itself was aching. But the ache was okay because that's the way you embrace the sun and the </s><s>[INST] moon. [/INST] And that's what I think is. That's why I think there's this whole Witteveen in </s><s>[INST] in this [/INST] bittersweet tradition that he embodies. That's like the essence of beauty. You know, it's the way you embrace the sun in the moon, </s><s>[INST] the song Hallelujah. I returned to that often have been me to play it. Um have now a friend who wants to sing it with me. Are you [/INST] a singer? </s><s>[INST] Mm [/INST] What </s><s>[INST] what when when somebody says they're a singer, do they have to be [/INST] good because </s><s>[INST] then no, but I would say yes, I was in a band for a while. I sang for a while. I was always bad. But I I enjoy it. I enjoy it. I enjoy lyrics. I enjoy awards when sung or spoken. They capture something that could get in that moment. Tom waits is a huge favorite of mine for that reason. Um Although he often his lyrics are often not that not that simple. I'd rather have a bottle in front of me than a frontal Lobotomy. He's always playing with just like these [/INST] weird </s><s>[INST] word play. That's especially in the english language is trickier to do. I'm fortunate enough to know another language which is Russian. So I get to understand that certain languages allow for more world wordplay than others english for that reason, I don't think has a, like, like a, like a culture of, you know what, I need to push back on what I'm about to say. But there was no culture of wordplay until hip hop came along. [/INST] So </s><s>[INST] like, like distorting words in interesting ways for there to be a rhythm rhyme and at the same time you're capturing some really powerful message. Um plus humor, all of that mixed in actually hip hop does does a really good job of this. But there wasn't a tradition, if you look at poetry in the 20th century, there wasn't really a tradition of that in the United States, but there was in other parts of the world and certainly in Russia empowered, also, not just by language by the fact that you go through a world war where tens of millions of people die. Something about mass mass death of civilians that inspires great literature and music and art. [/INST] Yeah, absolutely. Because you start telling the real truth. I think </s><s>[INST] there's no more reason for small talk. Um [/INST] that's funny. I always have thought that if I could choose any other medium besides writing it would be singing. Um but </s><s>[INST] then [/INST] no, I mean, like I'm really not, I just love the idea of it. But then I also think, you know, I'm fundamentally a shy person. So I think it's much better that my medium is writing instead of singing. So like it all worked out </s><s>[INST] that said you're also an exceptionally good public speaker and you're not supposed to be mathematically speaking [/INST] mathematically speaking, </s><s>[INST] you're not supposed to be a good public speaker. [/INST] Oh, you mean because of shyness or </s><s>[INST] because of shyness? Because of introversion? Because of all those kinds of things. [/INST] Oh yeah, but lots of introverts or public speakers actually, like this is one of I I knew this from the studies, but then also when I started going out on the lecture circuit, I realized that all my fellow speakers and all these conferences I was going to, they're all introverts because, you know, there are people who like spent years figuring out some idea and now they're out there talking about it </s><s>[INST] in their head, figuring out the idea. How do you explain? How do you explain that the the public speakers, would you say the good public speakers are usually introverts? [/INST] No, I think there's just different styles of it and I think that we just have when we hear the word public speaker, we have a really limited idea of who that person would be. Um so for me, like I used to be very phobic about public speaking and part of the reason for it was because I thought that being the kind of person I was didn't equal being able to be a good public speaker because you're you're only imagining, you know, like that super kind of out </s><s>[INST] there showman. [/INST] Um but I think there's another style of public speaking that's more reflective and thoughtful and conveying ideas and people like that too, </s><s>[INST] is there advice you can give on how to overcome that? Like, if you're a shy person, how to be a public speaker, [/INST] totally give that advice because I used to before I would give speeches, you know, if I had to do it in law school, if I knew, like today was the day when I was going to get called on in a law school class, I literally one time vomited on my way to class. That's how nervous I used to be. Um and yeah, the way to do it is through desensitization, you know, it's like been figured out, it's the way to overcome any fear. You have to expose yourself to the thing you fear, but in very small doses, so you can't start by giving the ted talk, you have to start, I I started by going to this class for people with public speaking anxiety, where the first day all we had to do was stand up and say our name </s><s>[INST] and sit [/INST] down and like, that's the victory. </s><s>[INST] That's fun to watch all those people with anxiety. Just okay, that's the first step in the step, one step at a time. [/INST] Yeah, and then, like with this class, you go back the next week and and he would have us come to the front of the room and stand up with other people standing next to us so that you didn't have the feeling of being all alone in the spotlight, through others, sharing it with you. And you would answer some questions about where do you grow up? You know, where do you go to school and you declare victory and you're done? And then little by little by little, you keep ratcheting up the exercises until you get to the point </s> |
<s>[INST] all. There's a kind of morality, like a big statement that Wall Street bets made in terms of like the elites can't just push us around, they can't bully around, but at the same time, you know, they're also interested in making money, right? Is uh what's your sense, you said that some of the people in the Wall Street bets might have broken off and and short of the stocks, are they more interested? There was an emergent like morality that emerged and and said like, we're not gonna put up with the centralized elites, but is that going to continue, are they going to fight the power structures that are bad for society? Are they going to now? Like, I mean, are they ultimately going to introduce more chaos that's going to damage the economy and damage the world, or they're going to continue being the good guys and fighting the uh the, the evils that manipulate the market. What's your sense? [/INST] You know, it, it really feels like the Dark Knight series of films where like some people just want to see the world burn and I think there is a contingent of people who just literally want to see chaos, Like, you know, that contingent on some of these, you know, forums who just want to create chaos, right? Um so there's certainly that chaos contingent, but I think overall what the ark will show is a group of people getting massively educated, you see it in crypto as well, there was like a three year period where all of these failed entrepreneurs who I knew who couldn't build companies were then coming back to me after their companies have failed or after they gave up or couldn't clear market raising money with the venture capital community and they were doing I ceos and I was like, I met you before, right? And they're like, yeah, yeah, yeah, no, I'm doing an I C E O now, I'm like, okay, where is your company? And they're like, here's a white paper and I was like this white paper with spelling errors in it that says you're going to destroy Airbnb because everybody's apartment is going to be on an immutable ledger. Like, wouldn't that be better in a regular database that was private and not public? Like why does it need to be an immutable ledger can't change. I'm like not changing the database is a feature that does not seem like a good feature and they couldn't explain it. They were like, well, just people are interested in I C E O S and those that I C O mania. And what it showed was there was a global appetite for risk, People want to try new things. This is one of the great things about the human spirit is one of the great things about capitalism. And one of the things that concerns me most about where and society is the sort of socialism, communism, you know, entrepreneurship is bad, technology is bad and polarization of wealth and you know, people getting rich is a bad thing when I grew up, I'm 50 now, but when I was a gen xer growing up, we kind of maybe too much idolized Bill Gates and people who are doing interesting things in the world and we thought capitalism was a force for good. I still believe capitalism is a force for good because when a group of people build a product or service that changes the world and it, and it gets globally distributed, whether it's Tesla or SpaceX or google or Airbnb or Uber or Robin Hood, you know, everybody gets to benefit from that product or service having to compete. And if you look at the places where there's no competition, like public education or less, you know, you know, uh, you know, established, you know, college is something that less competition for accreditation degrees, like things tend to get a little weird, don't they? Um, and people tend to be protected and that's not good. You need, you need competition. Um, doesn't mean that, you know, people shouldn't have global health care, It doesn't mean that, you know, we shouldn't have a safety net, but we need to keep capitalism vibrant, especially because china has now co opted capitalism and created their own version of capitalism, which is communism with capitalism. It's like this weird operating system. Like we still want to keep communism so we can take any of your gains at any time, but we'd like you to be entrepreneurial and then you have somebody like, you know, um, you know, the founder of Alibaba, Jack Ma, who disappears for a couple of weeks, who's that Jack exactly who's Jack Ma's like, he kind of disappears for a couple of weeks and then he comes back and he's really sorry about the things he said and then he disappears again and like you know, we have to be very careful if china wins capitalism, this is going to be but existential threat for humanity. The chinese are no joke, I mean they are seriously focused um and they are picking the winners. </s><s>[INST] It's a very weird system because it is in fact, I don't know what you call it like communism, capitalism such overloaded terms, but they do encourage entrepreneurship but they and they do a good job of it, but then they're like, they're like the surveillance thing and they're controlling things in a way. It's weird because it seems to work really well for them uh in the short [/INST] term it's definitely a short term </s> |