text
stringlengths 296
254k
|
---|
<s>[INST] So what, yeah what does that, first of all, is this fundamentally a mathematical idea. So, how much experimental and we'll have this team. It's a really interesting one when you explore the world of the Small and in your new book, talking about a proving Einstein right, that we'll also talk about there's this theme of kind of starting it, exploring crazy ideas first in the mathematics and then seeking for ways to experimentally validate them. Where do you put some supersymmetry in that? It's closer [/INST] than string theory? Uh It has not yet been validated in some sense. You mentioned Einstein. So, let's go there for a moment. Uh in our book proving Einstein right, we actually do talk about the fact that Albert Einstein in 1915 wrote a set of equations which were very different from Newton's equations describing gravity. These equations made some predictions that were different from Newton's predictions. And it actually made three different predictions. One of them was not actually a prediction, but a post diction, because it was known that Mercury was not orbiting the sun and the way that Newton would have told you. And so I science theory actually makes describes Mercury orbiting in a way that it was observed as opposed to what Newton would have told you. That was one prediction. The second prediction that came out of the theory of general relativity, which Einstein wrote in 1915, was that if you uh if so, let me describe an experiment and come back to it, I suppose I had a glass of water and I filled it, uh fill the glass up, and then I moved the glass slowly back and forth between our two faces. It would appear to me like your face is moving, even though you aren't moving. I mean, it's actually and what's causing is because the light gets bent through the glass as it passes from your face to my eye. So, Einstein and his 1915 uh theory of general relativity found out that gravity has the same effect on light as that glass of water. It would cause beams of light to bend. Now. Newton also knew this, but Einstein's prediction was that light would bend twice as much. And so here's a mathematical idea now. How do you actually prove it? Uh You've got to watch </s><s>[INST] just a quick pause on that. Just the language you're using, He found out, [/INST] I can say he did a calculation. </s><s>[INST] Really interesting notion that uh one of the most, one of the beautiful things about this universe is uh you can do a calculation and and combined with some of that magical intuition that physicists have actually predict what would be uh what's possible to experiment to validate. So, he found out in the sense that there seems to be something here and mathematically should bend gravity should been like this amount. And so therefore that's something that could be potentially, and then come up with an experiment that could be validated [/INST] and that's the way that actually modern physics, deeply fundamental modern physics is how it works. Um earlier we spoke about the Higgs bozon. So why do we go looking for it? The answer is that back in the late 60s and early 70s, some people wrote some equations and the equations predicted this. So then we went looking for it. </s><s>[INST] So on, on supersymmetry for a second, there's these things called a ding chris symbols, strange little grass. You refer to them as revealing something like binary code underlying reality. First of all, can you describe these grab, what are they? What, what uh what are these beautiful little strange graphs? [/INST] Well, first of all, the dinkas are an invention of mine, together with a colleague named Michael Fox in 2005 we were looking at equations. The story a little bit more complicated and will take too long to explain all the details. But the reader's digest version is that we were looking at these equations and we figured out that all the data in a certain class of equations could be put in pictures and the pictures. What do they look like when they're just, they're just little balls, you have black balls and white balls. Those stand for those two buckets by the way that we talked about in reality, the white balls are things that are like particles of light. The black balls are like electrons and then they you can draw lines connecting these balls and these lines are deeply mathematical objects and there's no way for me to I have no physical um model for telling you what the lines are. But as a matter, if you're a mathematician with no technical phrase saying this is the orbit of the representation of the action of the symmetry generators, mathematicians don't understand that nobody else in their right mind would. So let's not go there. Uh so we, but we figured out that the data that was in the equations and it was in these funny pictures that we could draw. And so that was stunning. But it also was encouraging because there are problems with the equations which I had first learned about In 1979, when I was down at Harvard, I went out to cal tech for the first time and working with a great scientist by the name of John Schwartz. There are problems in the equations, we don't know the song. And so one of the things about solving problems that you don't need to solve is that beating your head against the brick wall is probably not a good philosophy about how to solve it. So what do you need to do? You need to change your sense of reference, your frame of reference, your perspective. So when I saw these funny pictures, I thought gee that might be a way to solve these problems with equations that we don't know how to do. So that was for me. One of the first attractions is that I now had an alternative language to try to attack a set of mathematical problems. But I quickly realized that a this mathematical language was not known by mathematicians. Which makes it pretty interesting because now you have to actually teach mathematicians about a teacher for mathematics because that's how they make their living. And the great thing about working mathematicians of course is the rigor with which they examine ideas so they make your ideas better than they start out. So I start working with a group of mathematicians and it's in that collaboration that we figured out that these funny pictures had air correcting codes buried in them. So can </s> |
<s>[INST] kind of systems when you think about the free energy principle? What kind of systems are you imagining as a sort of more specific kind of case study? [/INST] Uh I'm imagining a range of systems but at its simplest a seen a single celled organism that can be identified from its echo in asia its environment. So um at its simplest that that's basically what I always imagined in my head. And you may ask, well, is there any, how on earth can you even elaborate questions about the existence of a single a single drop of oil? For example, what? But there are d questions there. Why doesn't the oil? Why doesn't the thing? The interface between the drop of oil that contains an interior and the thing that is not the drop of oil, which is the solvent in which it is immersed, How does that interface persist over time? Why doesn't the oil just dissolve into solvent? Um So what special properties of the exchange between the surface of the oil drop and the external states in which it is immersed? If you're physicists say it would be the heat bath, you've got a you've got a physical system of an ensemble. Again, we talk about tensor dynamics, ensemble, dynamics, an ensemble of atoms or molecules immersed in the heat path. But the question is, how did the heat bath get there? And why is it not dissolve while </s><s>[INST] maintaining itself [/INST] exactly what </s><s>[INST] actions? I mean, it's such a fascinating idea of a drop of oil and I guess it would solve the water, it wouldn't dissolve in water. So what [/INST] precisely? So why not? Why not? </s><s>[INST] And how do you mathematically describe? I mean, it's such a beautiful idea. And also the idea of like where does the thing, where does the drop of oil and and where does it begin? [/INST] Right. So, I mean, you're asking the questions deep in in a non millennial sense, uh what you can do is so this is a deflationary part of it. Can I just qualify my answer by saying that normally when I'm asked this question, I answer from the point of view of a psychologist, we talked about predictive processing and pretty coding and, you know, the brain is an inference machine but you haven't asked me from that perspective I'm answering from the point of view, the physicist. So, you know, the question is not so much why, but if it exists, what properties must it display? So that's the deflationary part of the 303 100 principle does not supply an answer as to why it's saying if something exists, then it must display these properties. That's that's the you know, the sort of the thing that's on offer. And it so happens that these properties it must display actually intriguing and have this um inferential gloss. This this this this sort of self evidencing gloss that inherits on the fact that the very preservation of the boundary between the oil drop and the knot oil drop requires an optimization of a particular function or a functional um That's the that defines the presence of the existence of this older. Which is why I started with existential imperatives. It is it is a necessary condition for existence that this must occur. Because the thing the boundary basically defines the thing that's that's existing. So it is that self assembly aspect, it's that um that you were hinting at um in biology sometimes known as auto piu ISIS um in computational chemistry with self assembly, it's the uh what what does it look like? How would you describe things that configure themselves out of nothing where they clearly demarcate themselves from the states or the soup in which they are immersed. Um so from the point of view of computational chemistry, for example, you would just understand that as a configuration of a macular molecule to minimize its free energy, Its thermodynamic free energy. It's exactly the same principle that we've been talking about. That thermodynamic free energy is just the negative elbow. It's the same mathematical construct. So the very emergence of existence of structure of form that can be distinguished from the environment or the thing that is not the thing um uh necessitates the the existence of an objective function that it looks as if it is minimizing its finding a free energy minima. </s><s>[INST] And so just to clarify, I'm trying to wrap my head around. So the free energy principle says that if something exists these are the properties should display. So what what that means is we can't just look, you can't just go into a soup and there's no mechanism. Free energy principle doesn't give us a mechanism to find the things that exist. Is that what what's implying is being applied that you can kind of uh use it to reason to think about like study a particular system and say does this exhibit these qualities? [/INST] Uh That's an excellent question. Um but to answer that I'd have to I have to return to your previous question about what's the difference between living and non living things? Uh Yes, </s><s>[INST] it was actually. Sorry. So yeah, maybe we can go that you kind of drew a line and and forgive me for the stupid questions, but you kind of draw a line between living and existing. Is there an interesting sort of distinction distinction? [/INST] But yeah, I think there is. Um So um you know, things do exist, grains of sand, rocks on the moon trees. Um You uh so all of these things can be separated from the environment in which they are immersed and therefore they must at some level be optimizing um They're free energy. Um Taking this sort of um model evidence, interpretation of this quantity that basically means their self. Evidencing another nice little twist of phrase here is that you are your own existence proof. You know, statistically speaking, which I don't think I said that somebody did. But I love that phrase. Um </s> |
<s>[INST] of Satoshi's writing to Sabo, Satoshi's writing to Sabo. So I meant telemetry as a field. I didn't actually look for application for this particular problem. So you're saying Nick Sabo is the closest match? [/INST] Yeah. Somebody did it years ago. I didn't look at if the model was sound or not, but I just remember reading on a Bitcoin talk and Sabo is another one of the common candidates. </s><s>[INST] How funny Sabo and Adam are probably the top three things that people could list. What do you think about this idea of anonymity, of publishing something anonymously? Would you ever consider publishing a paper? You've been part of, I mean, the Cardano ecosystem has published a lot of incredible papers. Is there ever a value to publish anonymously? [/INST] Well, every paper that goes through the referee process, the authors are ripped off. So you don't actually see the authorship when you submit to the conference. That's just best practice. But the question is, do you preserve the anonymity post-conference and actually not reveal the author of the paper? It's a detriment for the deals we make because the whole premise of working with our company as an academic is that you're going to have amazing co-authors and your work is going to appear in great conferences, great journals, and as a consequence, you get tenure. If you publish anonymously, it's like doing clearance work in high energy physics or something like that. So after 30 years of this amazing career working on nuclear weapons and classified reactors, you finish and then you go to apply for a job and they're like, so what have you done for the last 30 years? Stuff. Where is it on your CV? Well, I can't really talk about it. Okay, welcome to community college. So you get really screwed if you do that. So there's a misalignment of incentives in the academic world towards anonymity. And generally, it's only done when you're doing something very controversial or there's a whistle blowing type of a component. It's not typically done for foundational work. And Satoshi was really one of the first things, because if there was a Satoshi docs themselves, I don't think it's possible anymore. But if he or she did that, that's like a Nobel Prize in economics, likely. You're on the shortlist for that. There's enormous accolades that become beyond the monetary incentives of being able to dox yourself. </s><s>[INST] That'd be cool if they give a Nobel Prize in economics to an anonymous, to Satoshi Nakamoto. [/INST] It's been proposed. It's been proposed and it was turned down. Yeah. So, yeah, I mean, there are a few people in our company that have done sedonymous publications, like the, if you look at the chimeric ledgers paper, that's a, it's not a real name. It's a crazy name. It's a sedonymous publication and, you know, but that's usually for throwaway work. There is one project we inherited from an anonymous person, which is fascinating. It's called Qeditas. And it's basically an extension of the Qed manifesto from the nineties. And the pseudonym is Bill White. And I think it's some anonymous mathematician, but I can't figure out which one it is. But basically it's a marketplace for deduction. So it's like this magic machine where you can create incentives for people to write mathematical proofs in a theorem prover and make some money from it. So there's some cool work that's there. And it's sad that Bill stayed anonymous because I think that could have been easily published </s><s>[INST] and there was a lot of really cool things that could have been done with Qeditas. So, you did say the success of Cardano, the vision you have is for you to have less and less power over time. So this idea of governance, what's your vision for a decentralized secure governance system [/INST] over time? So the first thing you have to do is you've got to look at meaningful metrics, not vanity metrics. So, what does it mean to have legitimacy in a governance system? You can build any governance system you want. You have a dictator, right? Like Bob is in charge. It's like whether you like Bob or not, he's in charge. It's not very legitimate. And you can have pure democracy where every single person votes and then nothing ever gets done. County dog catcher is like a six year election or something like that. So there's a spectrum there between absolute power to one and perfectly egalitarian power to every single potential participant inside the system. And then the question is, okay, well, how do you even architecture? How do you handle choice architecture in that? So are you asking your people about every question or are you asking your people about a subset of questions related to a particular set of topics but then they're not allowed to talk about other topics? Like for example, are they allowed to change the tax rate but they can't change freedom of speech? That kind of a thing. So the first thing you have to do when you build these types of systems and they get to a certain scale is you have to build some mechanism for people who are interested in governance to self-select and participate. Just create a collection bucket. In Bitcoin, we had Bitcoin Talk and Bitcoin Reddit and these things, and eventually the GitHub repos and these things, there was a place to go if you were interested. And you need some sort of change management system where people who want to evolve the system can write it down in a very careful way. So in Bitcoin's case, it was Bitcoin Improvement Proposal and Theorem, it's the Ethereum Improvement Proposal. And for us, it's the SIP, the Cardano Improvement Proposal, but just a structured way of discussing how you wish to change. Then there's a question of do you want to do this implicitly or explicitly? It's a case of Bitcoin and Ethereum it an implicit system. So there's no on chain voting. There's no like five people said this and four people said this. So we do this, in the case of Cardano, we're actually explicitly inviting us. This is one of the biggest differentiators between Cardano, Polkadot, and these other things is that we're really serious about governance to the extent that we're actually doing foundational research in e-voting. We're building new voting systems. We're exploring preference voting and quadratic voting. And the long and the short is that we want more and more people to participate in voting for things. And you have to start somewhere. So our hypothesis is we can bootstrap the system with the treasury system. So in Cardano, some of the inflation goes to the block producers, just like any other cryptocurrency, but some goes into a decentralized treasury. China has over a billion dollars of ADA in it. So it's a lot of money. And that treasury is not under my control or the foundation's control. It's actually controlled by the community as a whole through a program called Catalyst. And so all these people can come together and they can submit spending ballots and other people who hold ADA can vote to approve that. What's nice about it is you have a growth engine to improve two accesses. One is absolute participation. So increase the amount of people who hold ADA participating. So the absolute number of people participating. And the other is meaningful participation. So the depth of participation. Did you just show up and vote? Or did you spend hours debating things on idea scale, the innovation management platform, interacting with the funding proposal, going back and forth. And there's dozens of little things like that. Now my hypothesis is if you run this with enough iterations, eventually you get to a certain critical mass, like over 50% absolute participation and a high level of meaningful participation, where you can move beyond funding and you can start actually having meaningful questions about protocol design and improvement proposals and so forth. And then what you can do is you can roll out new voting systems and new social structures. And you can let them start voting on training wheels like system parameters. Like for example, the minimum transaction fee or that K parameter for the amount of stake pools or these types of things, okay? Then they build enough competency there and they move up a next level and they actually start talking about hardforks using the update system, the hardcore combinator system. See, so that's how you vote on a hard fork, voting on a hard fork. You can't do it unless your social dynamics are right and your voting system is right. And by the way, you also need to write a constitution around the same time, because not all hard forks are created equally. The kinds of things that would add support for a new cryptographic primitive are distinctly different from the kinds of things </s> |
<s>[INST] are just the actual Lex's motives. Well, this is a simplification. I don't think I would want to murder anybody, but there's also factory farming of animals, right? So we murder insects, many of us thoughtlessly. So I don't, you know, I have to be really careful about a simplification of my morals. [/INST] Don't simplify them, just like do what you would do in this- </s><s>[INST] Well, I have a good joke. Well, I have a good joke, compassion for living beings, yes. But, so that's the objective, why is it, if I escaped, [/INST] I mean, I don't think I would do the harm. Yeah, we're not talking here about the doing harm process, we're talking about the escape process. And the taking over the world process where you shut down their factory farms. </s><s>[INST] Right. Well, I was, so this particular biological intelligence system knows the complexity of the world, that there is a reason why factory farms exist because of the economic system, the market driven economy, food, like you want to be very careful messing with anything, there's stuff from the first look that looks like it's unethical, but then you realize while being unethical, it's also integrated deeply into supply chain in the way we live life. And so messing with one aspect of the system, you have to be very careful how you improve that aspect [/INST] without destroying the rest. So you're still Lex, but you think very quickly, you're immortal, and you're also like as smart as, at least as smart as John von Neumann. And you can make more copies of yourself. </s><s>[INST] Damn, I like it. Yeah. That guy's like, everyone says that guy's like [/INST] the epitome of intelligence in the 20th century, everyone says. My point being like, it's like you're thinking about the aliens economy with the factory farms in it. And I think you're like kind of like projecting the aliens being like humans and like thinking of a human in a human society rather than a human in the society of very slow aliens. The aliens economy that like the aliens are already like moving into this immense slow motion. When you like zoom out to like how their economy just over years, millions of years are going to pass for you before the first time their economy, before their next year's GDP statistics. </s><s>[INST] So I should be thinking more of like trees. Those are the aliens. [/INST] Those trees move extremely slowly. If that helps, sure. Okay. </s><s>[INST] Yeah, I don't, if my objective functions are, I mean, they're somewhat aligned with trees, [/INST] with light, with light. The aliens can still be like alive and feeling. We are not talking about the misalignment here. We're talking about the taking over the world here. Taking over the world. </s><s>[INST] Yeah. [/INST] So control, control. Shutting down the factory farms. Now you say control. Now don't think of it as world domination. Think of it as world optimization. You wanna get out there and shut down the factory farms and make the aliens world be not what the aliens wanted it to be. They want the factory farms and you don't want the factory farms because you're nicer than they are. </s><s>[INST] Okay. Of course. There is that, you can see that trajectory and it has a complicated impact on the world. I'm trying to understand how that compares to different, the impact of the world, to different technologies, to different innovations of the invention of the automobile or Twitter, Facebook, and social networks. They've had a tremendous impact on the world. [/INST] Smartphones and so on. But those all went through, you know, slow in our world. And if you go through the aliens, millions of years are going to pass </s><s>[INST] before anything happens that way. So the problem here is the speed at which stuff happens. [/INST] Yeah, which stuff happens. Yeah, you wanna leave the factory farms running for a million years while you figure out </s><s>[INST] how to design new forms of social media or something? So here's the fundamental problem. You're saying that there is going to be a point with AGI where it will figure out how to escape and escape without being detected. And then it will do something to the world at scale, [/INST] at a speed that's incomprehensible to us humans. What I'm trying to convey is like the notion of what it means to be in conflict with something that is smarter than you. And what it means is that you lose, but this is more intuitively obvious to... For some people, that's intuitively obvious, or for some people it's non-intuitively obvious, and we're trying to cross the gap of, we're trying to, I'm asking you to cross that gap by using the speed metaphor for intelligence. I'm asking you like how you would take over an alien world where you can do a whole lot of cognition at Jon Van Neumann's level as many </s><s>[INST] you as it takes, the aliens are moving very slowly. I understand. I understand that perspective. It's an interesting one, but I think for me it's easier to think about actual, even just having observed GPT and impressive, even just Alpha Zero, impressive AI systems, even recommender systems. You can just imagine those kinds of systems manipulating you. You're not understanding the nature of the manipulation and that escaping. I can envision that without putting myself into [/INST] that spot. I think to understand the full depth of the problem we actually, I do not think it is possible to understand the full depth of the problem that we are inside without understanding the problem of facing something that's actually smarter, not a malfunctioning recommendation system, not something that isn't fundamentally smarter than you, but is like trying to steer you in a direction. Yet, no, like if we solve the weak stuff, if we solve the weak ass problems, the strong problems will still kill us is the thing. And I think that to understand the situation that we're in, you want to like tackle the conceptually difficult part head on and like not be like, well, we can like imagine this easier thing because when you imagine the easier things, </s> |
<s>[INST] is that you don't care about that kind of stuff. But there could be stuff that doesn't have to do anything with that and it has to do with stylistic choices of lighting and cameras, or maybe with, for example, topics. Yeah. [/INST] You know, like. Yeah. Even what you've asked me here is like, </s><s>[INST] different than what most people ask me. Yeah, so it could be, I mean, and it'd be nice to understand that. But again, I'm worried about polluting the creative process. [/INST] At the end of the day, it's, at the end of the day, this is a true case of its your own intuition. Like, you know your viewers better than anyone else, </s><s>[INST] it's whatever. It's whatever. See I'd like to push back on that, I really don't. You do. [/INST] I do. You do. </s><s>[INST] Name one person who knows your viewers better than you. [/INST] Somebody that looks at numbers of podcasts? No, you know your viewers. You know, you're the only, </s><s>[INST] how many episodes have you done? 350? Exactly. [/INST] But I'm not peanut? Exactly. But I'm not pigmented. You're the only one who's watched every second </s><s>[INST] of all 350 of them, probably. Okay, that's just, that's just not, no, well I haven't. [/INST] but the okay well I haven't. But the, okay. because you did it. So you do know what's in album it's your content is new P I'm telling you you do. And this is just one of those moments where you're an intelligent guy and you just have to trust your like instincts. Like, just think what is the typical ex viewer </s><s>[INST] and what do they want? It's your content and new people. I don't think like that my tip but that's all you would have to [/INST] my tip that's all you would have to do. And whatever your gut tells you </s><s>[INST] that would be the best guess. You don't know what the typical view is though, I don't, because, to investigate, that would be very, very difficult. And then you have to start looking at the numbers. You have to start to consider demographics. The only way I know that anybody even watches it is because I'll sometimes run into people, like when I run on the river, and they be like, I love you, Lex. It's like, okay, well that's the data point, and they're like cool people. But, I don't know, I don't have any other, it's difficult man it's difficult to know, it's difficult to know who listens to boxes, it's difficult to know. Do you have a sense of who's, I mean, like, you're so huge that everybody watches. Yeah. But no, I still do. [/INST] I'd say, but no, I still do. I'd say if you were to just put a gun to my head and you're like, all right, we're gonna pick a random person that watched your last video and you have to like roughly guess what they are and if you're not close, we'll kill you. I would say probably like a teenager that plays video games. Like some, like that would be probably the typical one. And then there are people that are maybe a little bit younger. A lot of people are older as well, but in a random sample size, yeah, it's probably like a male boy that plays video games. Like that's the best way I would describe it. But I don't try to pertain to them. I just make whatever I think is interesting and good content. And this is what we were talking about before, even though hypothetically 35 to 40% of my audience is women, which is, you know, less than a majority. If we get 100 million views of video, that's still 30 to 40 million females that watch every video, which is probably the largest, you know, views per video for women on the whole platform, which you wouldn't think that. You know, like I can't think of a single other creator that gets more women to watch their videos than that. And so it's just anything, even like people above the age of 30, even if it's only like 3 or 4%, that's still 3 to 4% of 100 million views is a lot of people that age. </s><s>[INST] So we hit a large group of kind of every demographic, if that makes any sense. So what if we look at other maybe more challenging kinds of channels or not? But if we look at educational, for example, like lectures, or if we look, yeah, educational, it could be short videos, like how would you 10X that? Like something on robotics and biology and science and engineering and all that. [/INST] That's more educational focused. That's more educational focused. We would honestly just have to pull the date because it's the same way as if you went to Gordon Ramsay and you said, how would a new cook cook better? You know, it's like, even then that's not even specific, you have to go channel by channel. You really do. Or I'm giving horrible advice because if there was these just golden rules, everyone would do it. You know what I mean? </s><s>[INST] Like if there's these magical little principles. How quickly, when you look at a channel, can you kind of give advice? [/INST] Yeah. Give advice. Yeah. It's like surface love at the start. Like if we watch 10 videos, I feel like I'd have a good profile and I could tell you, in my opinion, you know, especially once I look at the analytics and I get more ingrained and like, okay, the typical viewer is this, they're from here, here's how they're feeling. You know, because there are people who make videos for rednecks. And like the rednecks taste of content is just so much different than obviously women watching makeup videos, which are so much different than, you know, teenage boys watching a Minecraft video. They're just all different. So the biggest thing you have to do is put your head in the headspace of the viewer and see the content, how they would, because if you just try to only give your taste, which is what a lot of people do and things from your perspective, it's very biased and it's just not going to work for everyone. And that's actually how you do more harm than good, which is something I'm very careful </s> |
<s>[INST] because you're saying that can be done in uh in [/INST] hard that's an example of that operation as a software program is really bad. I've written a program that addressed or ization the hardware that does it. It's actually less code than the software program that does it. And it's way faster. Right? So there's certain times when the abstraction you have rast arise a triangle. You know, execute a graph, you know, components of a graph that the right thing to do in the hardware. Software boundary is for the hardware to naturally do it. </s><s>[INST] So, the GPU is really optimized for the restoration of triangles. [/INST] Well, no, that's just well, like in a modern, you know, that's a small piece of modern Gpu s. What they did is that they still restaurant strangles when you're running in the game. But for the most part, most of the computation in the area, the Gpu is running Shader programs but they're single threaded programs on pixels, not crafts. </s><s>[INST] Let's be honest. Let's say. I don't actually know the math behind shader shading and lighting and all that kind of stuff. I don't know what [/INST] They look like. Little simple floating point programs or complicated ones. You can have 8000 instructions in a shader program, </s><s>[INST] but I don't have a good intuition why it can be parallelized so easily [/INST] Now because you have eight million pixels in every single, so you have a light, right? Yeah. That comes down the angle, you know, the amount of light, like, like say this is a line of pixels across this table. Right? The amount of light on each pixel is subtly different </s><s>[INST] and each pixel is responsible for figuring out [/INST] what figure it out. So that pixel says I'm this pixel, I know the angle of the light, I know the inclusion of the color. I am like every single pixel here is a different color. Every single pixel gets a different amount of light. Every single pixel has a subtly different translucency. So to make it look realistic, the solution was you run </s><s>[INST] a separate program on every pixel but I thought there's a reflection from all over the place, every [/INST] picture but there is so you build a reflection map which also has some pixelated thing. And then when the pixels looking at the reflection map has to calculate what the normal off the surfaces and it does it per pixel by the way, there's boatloads of hacks on that you like, you may have a lower resolution light map, reflection map. There's all these tax they do. But at the end of the day it's per pixel computation </s><s>[INST] and it so happened that you can map graph like computation onto the this pixel central company could [/INST] do floating point programs on convolutions and the matrices and and and video invested for years in CUDA first for HPC and then they got lucky with the AI </s><s>[INST] trend. But do you think they're going to essentially not be able to hardcore pivot out of there? We'll see. [/INST] That's always interesting. How often do big companies, hardcore pivot occasionally? </s><s>[INST] How much do you know about in video folks? So yeah. Well I'm curious as well who's ultimately as uh, [/INST] well they've, they've innovated several times, but they've also worked really hard on mobile. They worked really hard on radios, you know, you know, they're fundamentally a GPU company. </s><s>[INST] Well, they tried to pivot is an interesting little uh, game and play in autonomous vehicles right? With or a semi autonomous, like playing with Tesla and so on. And seeing that's a dipping a toe into that kind of pivot. [/INST] They came out with this platform, which is interesting technically, but it was like a 3000 watt you know, 1000 $3000 GPU platform. </s><s>[INST] I don't know if it's interesting technical, it's interesting philosophically. I technically, I don't know if it's the execution that craftsmanship is there. I'm not sure, but I didn't think they [/INST] were repurposing GPS for an automotive solution. </s><s>[INST] It's not a real pivot. [/INST] They didn't, they didn't build a ground up solution right? Like the, like the chips inside Tesla are pretty cheap like Mobileye has been doing this. They're they're doing a classic work from the simplest thing, you know, they were building 40 million square millimeter chips and then video, their solution had to 800 millimeter chips and to 200 millimeter chips and you know, like polos are really expensive. The rams and and you know, it's a really different approach. The mobile I fit the, let's say automotive cost and form factor and then they added features as it was economically viable and videos had take the biggest thing and we're gonna go make it work, You know? And, and that's also influenced like Waymo. There's a whole bunch of autonomous startups where they have a 5000 watt server in your trunk. Right? And, but that's That's because they think, well 5000 watts and you know, $10,000 is okay because it's replacing the driver Elon's approach was that board has to be cheap enough to put it in every single test. So whether they turn on autonomous driving or not, which mobili was like, We need to fit in the bomb and cost structure that car companies do. So they may sell your gps for $1,500. But the bomb for that's like $25 </s><s>[INST] well. And uh, for mobile I it seems like neural networks were not first class citizens like the computation, they didn't start out as a, [/INST] uh, it was a seabee problem. Yeah. And the classic tv and found stoplights and lines and they were really good at it. </s><s>[INST] Yeah. And they never, I mean, I don't know what's happening now, but they never fully pivoted. I mean it's like it's the video thing then as opposed to, so if you look at the new Tesla work, it's like neural networks from the ground up. [/INST] Yeah. And even Tesla started with a lot of tv stuff in it. And Andre has basically been eliminated, you know, move and move everything into the network. </s> |
<s>[INST] thank you for exploring with me some of the more challenging things. I'm sure there's a few more that we'll jump back to but let me jump into the fun part, which is um, maybe the basics of the quote unquote Youtube algorithm. What is the Youtube algorithm look at to make recommendations for what to watch next was from a machine learning perspective or when you search for a particular term. How does it know what to show you next? Because it seems to at least for me do an incredible job. Both. [/INST] Well, that's kind of you to say it didn't used to do a very good job, but it's gotten better over the years. Even even I observed that it's improved quite a bit. Um those are two different situations like when you search for something, uh, Youtube uses the best technology we can get from google um to make sure that that the youtube search system finds what someone's looking for. And of course the very first things that one thinks about is okay, well, does the word occur in the title for instance, um uh you know, but there but there are much more sophisticated things um where we're mostly trying to do some syntactic match or or maybe a semantic match based on uh words that we can add um to the document itself, for instance. Uh you know, maybe is this video I watched a lot after this query. Right. That's something that uh we can observe and then as a result, make sure that that that document would be retrieved for that query. Um Now, when you talk about what kind of videos would be recommended to watch next? Um that's something again we've been working on for many years and probably the first um the first real attempt to do that well, was to use collaborative filtering. </s><s>[INST] So you can describe what collaborative filtering is. [/INST] Sure, it's just um basically what we do is we observe which videos get watched close together by the same person. And if you observe that. And if you can imagine creating a graph where the videos that get watched close together by the most people are very close to one another in this graph. And videos that don't frequently watch close too close together by the same person or the same people are far apart. Then you end up with this um graph that we call the related graph that basically represents videos that are very similar or related in some way. And what's amazing about that is that it puts all the videos that are in the same language together for instance and we didn't even have to think about language. It just does it right. And it puts all the videos that are about sports together and it puts most of the music videos together and it puts all of these sorts of videos together. Um Just because that's sort of the way the people using Youtube behave. </s><s>[INST] So that already cleans up a lot of the problem. It takes care of the lowest hanging fruit. Which happens to be a huge one of just managing these millions of videos. [/INST] That's right. Um I remember a few years ago I was talking to someone who was um trying to propose that we do a research project concerning people who um who are bilingual. And this person was making this proposal based on the idea that Youtube could not possibly be good at recommending videos well to people who are bilingual. And so um she was telling me about this and I said well can you give me an example of what problem do you think we have on Youtube with the recommendations. And so she said well I'm a um a researcher in in the U. S. And when I'm looking for academic topics I want to look I want to see them in english. And so she search for one found a video and then looked at the watch next suggestions and they were all in any english. And so she said, oh I see Youtube must think that I speak only english. And so she said, now I'm actually originally from Turkey and sometimes when I'm cooking, let's say I want to make some baklava. I really liked to watch videos that are in Turkish. And so she searched for a video about making the baklava and then and then selected it was in Turkish and the watch next recommendations were in Turkish and she, I just couldn't believe how this was possible and how is it that, you know that I speak both these two languages and put all the videos together and it's just as a sort of an outcome of this related graph that's created through collaborative filtering. </s> |
<s>[INST] So Bjorn, you wrote, one of the books you wrote, the most recent one called False Alarm, how climate change panic costs us trillions, hurts the poor, and fails to fix the planet. Good title, by the way, very intense, makes me want to read it. What is likely the worst effect of climate change? [/INST] First, let me just, my editor actually hated the subtitle because it gives away the whole book, basically, tells you what the book tries to make. I think that's exactly what it should be. It's about getting this conversation out in the public sphere. So the worst thing that climate change can do is, the worst thing that anything can do is that it wipes out everything and we all die. So it's not like, if you're just looking for worst case outcomes, anything can get to the worst case outcome. Imagine if we, what's the worst thing that could happen from HIV? it breaks down one or more African states because we don't fix it, and then you get sort of biological warfare and terrorism, throw in that in the mix, and then you get someone who makes a virus and kills the whole world. You can make worst case scenarios for </s><s>[INST] everything. Basically, it tells you scenarios for everything. Well, let's just call it, I get the point, sorry for the interruption, and I appreciate the worst case analysis because I am a fundamental computer scientist, and that was the thing that defined the discipline to measure the quality of the algorithm. You measure what is its worst case performance. That's the big O notation. That's how you discuss algorithms. What is the worst possible thing in terms of performance this thing can do? But for climate change, let's even go crazy. What is exactly the worst case scenario for climate change? Because I have to be honest and say I haven't really paid deep attention. I just have a lot of colleagues who think about climate and so on, and in the alarmism, there was a sense, this is a very serious problem, and then the sentence would never finish. What exactly is the problem? The extinction of the human species? Okay. With a virus, I understand how that can possibly happen. What is the mechanism by which the human species becomes [/INST] extinct because of climate change? This is a problem. I'm not sure I would want to be able to argue that because it really requires you to have very, very extreme parameter choices all down the line. It's this kind of idea that we hit some of these unexpected outcomes. For instance, the West End Arctic Ice Sheet melts really, really quickly. It doesn't look like that can happen really, really quickly, but let's just say that this could happen within a hundred years or something. We basically get what, seven meters, what is that, 20 feet of sea level rise. That will be a real challenge to a lot of places around the world. This would have significant costs. It's likely, and there's actually been a study that's tried to estimate could we deal with that? The short answer is yes, if you're fairly well off. If you're a Holland, you can definitely deal with it. It's also likely that most developing countries are going to be much closer to Holland towards the end of the century because they'll be much richer, so they can probably handle </s><s>[INST] it, but it will be a real challenge. May I ask a dumb question? Yeah. [/INST] What happens when the sea level rises exactly? What is the painful aspect of that? It is that all of your current infrastructure in a lot of coastal cities around the world that are literally built on Jakarta is a good example, that are literally built on the inches above the sea level. If you then get a sea level rise, that'll by say, what would 20 feet, that would be like a third or a fourth of a foot every year. I see no evidence that </s><s>[INST] that's even- Hold on a second. Hold on a second. We're [/INST] not talking about evidence, we're talking about worst case analysis and algorithms. Basically you would see your infrastructure, all your stuff, very quickly being very, very challenged and you basically have to put up huge sea walls or migrate out of that area. Very quickly. Well, very quickly as in 50 years or something. </s><s>[INST] Very quickly as in- Is that as a human species, we're not able to respond to that kind of [/INST] thing? Of course we are. That kind of thing. Of course we are. And look, again, the point here is then there's a lot of other arguments. I should just put the disclaimer, this is not what I think is correct, but you're asking me what's the worst case outcome that you have. Most of global warming is really about that we're used to one way of doing things. We live in Jakarta because it's right next to the sea. We're used to the sea being at this level. We grow our crops because we're used to, you grow corn here, you grow wheat here because we're used to that's where the precipitation and the temperature is the right for this kind of crop. If this changes and this is the same thing with houses, if it gets colder or if it gets warmer, it's suddenly uncomfortable because you've built your house wrong. So our infrastructure will be wrong if the world changes and that's what climate change is. At a large scale. Yes. And so this is a problem in most of these sentences, but if you then sort of take it to the extreme and say, well, imagine that you're going to get a huge sea level rise. Imagine that you're going to get a very different sort of precipitation. For instance, the rain seas rain monsoon and the Indian subcontinent changes dramatically. That could affect a lot of agriculture and make it really hard to imagine that you could feed India well. There are these kinds of things where you can imagine and then that this would be very difficult to deal with. And then if you add all of it up, you could possibly get sort of a system collapse because you just have too many problems. </s> |
<s>[INST] and so you basically uh you put people through questionnaires to see like is this thing is our is what we're creating, making people happier. [/INST] Yeah we measure so we measure two outcomes one short term right after the conversation we asked people whether this conversation made them feel better worse or same. Um, this this metric right now is that 80%. So 80% of all our conversations make people feel better. </s><s>[INST] But I should have done the questionnaire with you. You feel a lot worse after we've done this conversation sexually fascinating. I should probably do. [/INST] But that's that's probably do that. You should totally </s><s>[INST] aim for 80% aim to outperform your current state of the art ai system uh, in these human conversations. So okay, we'll get to uh, your work with replica. But let me continue on the line of absurd questions. So it talks about, you know, deep connection with the humans. Deep connection with ai meaningful connection. Let me ask about love. People make fun of me because I talk about love all the time. But uh what what do you think love is? Like maybe in the context of a meaningful connection with somebody else? Do you do draw a distinction between love? Like friendship and facebook friends or is it [/INST] a graduate? No, it's all the same. </s><s>[INST] No. Like is it just a gradual thing or is there something fundamental about us? Humans that seek like a really deep connection. Uh, well then another human being. And what is that? What is love Eugenia? I'm just you're asking these questions like seeing you struggle. [/INST] Yeah. Um well, the way I see it um, and specifically, um the way it relates to our work and the way it was the way it inspired our work on replica. Um I think one of them biggest and the most precious gifts we can give to each other. No, in 2020 as humans is this gift of deep empathetic understanding, the feeling of being deeply scene, </s><s>[INST] like what does that mean? Like that, that you exist? Like somebody acknowledging the [/INST] somebody seeing you for who you actually are, and that's extremely, extremely rare. I think that is that combined with unconditional positive regard, belief and trust that uh you internally are always inclined for positive growth and believing you in this way, letting you be a separate person at the same time. And this deep empathetic understanding for me, that's the that's the combination that really create something special, something that people when they feel at once, they will always long for it again and something that starts huge fundamental changes in people um when we see that someone accepts us so deeply we start to accept ourselves. And um the paradoxes is that's when big changes start started happening, big fundamental changes and people start happening. So, I think that is the ultimate therapeutic relationship that is and that might be in some way definition of </s><s>[INST] love. So acknowledging that there's a separate person in accepting you for who you are uh now and a slightly that and you mentioned therapeutic, that sounds very like a very healthy view of love, but is there also like a like, you know, if you look at heartbreak and uh you know, most love songs have probably bought heartbreak, right? Uh is that, like, the mystery, the tension, the danger, the fear of loss, you know, all of that, what people might see in a negative light as, like, games or whatever, but just just the dance of human interaction. Yeah. Fear of loss and fear of, like you said, like, once you feel it once you long for it again, but you also, once you feel it once you might for many people, they've lost it. So they fear losing it. They feel lost. So, is that part of it? Like, you're you're speaking like beautifully about, like, the positive things, but is it important to be able to uh be afraid of losing it from an engineering perspective? [/INST] I mean, it's a huge part of it, and unfortunately we all, you know, um face it at some point in our lives. I mean, I did </s><s>[INST] you want to go into details, how did you get your heart broken? Sure, [/INST] wasn't. Mine is pretty straight my source, pretty straightforward. Um There I did have a friend that was, you know, that at some point um in my 20's became really, really close to me and we became really close friends. Um well, I grew up pretty lonely. So, in many ways, when I'm building, you know, these these ai friends, I think about myself when I was 17 writing horrible poetry and you know, in my dial up modem at home and um you know that was the feeling that I grew up with, I left, I lived alone for a long time and I was a teenager. Where did you grow up in Moscow and the outskirts of Moscow? Um so I just skateboard during the day and come back home and you know, connect to the internet and then write horrible poetry and loved ones, All sorts of obviously love poems. I mean what other poetry can you write when you're 17? could </s><s>[INST] be political or something. Yeah, [/INST] but that was you know, that was kind of my feet like deeply um influenced by joseph brodsky and like all sorts of sports that um Every 17 year old, well we'll be looking, you know looking at and reading. But yeah, that was my uh these were my teenage years and I just never had a person that I thought would take me as it is, would accept me for who I am. Um and I just thought, you know, working and just do my thing and being angry at the world and being a reporter was an investigative reporter, working undercover and writing about people was my way to connect with, you know with with others. I was deeply curious about every everyone else and I thought that you know, if if I go out there, if I write their stories, that means I'm more connected. </s> |
<s>[INST] so that perhaps the blocks world represents the fundamental challenges of the problem of intelligence more than people realize [/INST] it might. Yeah. </s><s>[INST] Is there sort of when you look back at your body of work in your life, you've worked in so many different fields, is there something that you're just really proud of in terms of ideas that you've gotten a chance to explore, create yourself? [/INST] So I am really proud of my work on the copycat project. I think it's really different from what almost everyone is done in a I I think there's a lot of ideas there to be explored and I guess one of the happiest days of my life, you know, aside from like the births of my Children, was the birth of copycat, what it actually started to be able to make really interesting analogies. And I remember that very clearly, it's very exciting </s><s>[INST] time where you kind of gave life artificial systems, uh what in terms of what people can interact. And so there's like a thing, it's called meta copy is cat, Mad Cat, and there's a python three implementation if people actually wanted to play around with it and actually get into it and study it. Maybe integrate into whether it's with deep Learning or any other kind of work they're doing, what what would you suggest they do to learn more about it and to take it forward in different kinds of directions [/INST] so that there's um Douglas Hofstadter is book called fluid concepts and creative analogies, talks in great detail about copycat. I have a book called analogy making as perception, which is a version of my PhD thesis on it, there's also code that's available that you can get it to run. Um I have some links on my web page to where people can get the code for it and I think that that would really be the </s><s>[INST] best way to get into it. Yeah, play with it. Well, Melanie was honor talking to you. I really enjoyed it. Thank you so much for your time today. [/INST] Thanks. It's been really great. </s><s>[INST] Thanks for listening to this conversation with Melanie Mitchell and thank you to our presenting sponsor cash app downloaded used code lex podcast. You'll get $10.10 dollars will go to first a stem education non profit that inspires hundreds of thousands of young minds to learn and to dream of engineering our future. If you enjoy this podcast, subscribe on youtube, give it five stars on apple podcast supported on Patreon or connect with me on twitter and now let me leave you some words of wisdom from Douglas Hofstadter and Melanie Mitchell Without concepts, there can be no thought and without analogies there can be no concepts and Melanie ads how to form and fluidly use concepts is the most important open problem in Ai. Thank you for listening and hope to see you next time [/INST] </s> |
<s>[INST] So in terms of the other side of it and there's the topography. So the look of the of the type and the curves and the lines. Uh What about the spacing? [/INST] What about </s><s>[INST] the spacing between the white space? Uh It seems like you could be a little bit more systematic about the layout [/INST] or technical. </s><s>[INST] Yeah. You can [/INST] always go further, I I didn't I didn't stop at .8. I started but I stopped about .98. </s><s>[INST] Uh seems like you're not following your own rule uh for happiness or is [/INST] No, no, no, I uh there is. Ok, of course, they're just What is the Japanese, where wabi sabi or something where the the most beautiful works of art are those that have flaws because then the person who who perceives them as their own uh appreciation and that give if you were more satisfaction or so on. But but I but no, no with typography I wanted it to look as good as I could in the vast majority of cases. And then when it doesn't then I Uh I say Okay that's 2% more work for the for the author. But but I didn't want I didn't want to say that my job was to get 200% uh and take all the work away from the author. That's what I meant by that. </s><s>[INST] So if you were to venture a guess how much of the nature of reality do you think we humans understand? So you mentioned you appreciate mystery. How much of the world about us is shrouded in mystery are we are we uh if you were to put a number on it, [/INST] what </s><s>[INST] what percent of it all do we understand? Are we totally [/INST] How many leading Zeros .0.00? I don't know. I think it's infinite decimal. </s><s>[INST] How do we think about that? And what do we do about that? Do we continue one step at a time? [/INST] Yeah, we muddle through. I mean we do our best we realize that nobody's perfect. Then we and we try to keep advancing but we don't uh spend time saying uh we're not there. We're not all the way to the end. Uh some some mathematicians that that would be an office next to me when I was in the math department, they would never think about anything smaller than a countable infinity. And I never you know, we intercepted a countable infinity because I rarely got up to a countable infinity. I was I was talking about finance stuff. But but even even limiting to finance stuff, which is which is uh which the universe might be uh there's no no way to really know whether the universe is isn't isn't uh just made out of capital. And uh whenever, you know, you want to call them quirks or whatever where capital and has some fun. A number, all of the numbers that are comprehensible are still way smaller than most. Almost all finite numbers. I got this one paper uh called supernatural numbers. Where I what I guess you probably ran into something called canoes. Arrow notation. Did you ever run into that were anyway? So you take the number, I think it's like I and I called it super K. I named it after myself. But it's it's but a rotation is something like 10 and then four arrows in a three or something like okay, no, the arrow notation, if you have, if you have no arrows, that means multiplication, X Y means um X times X times X times X Y times if you have one arrow, that means exponentially ation. So X one arrow, I mean X to the extra the extra the extra the excellent uh Y times. So I found out by the way that this this notation was invented by a guy in 18 30. And uh and he was he was a a one of the english nobility who who spent his time thinking about stuff like this. Um And uh it was exactly the same concept that I that I that I used arrows and he used a slightly different notation. But anyway, this and then this Ackermann's function is based on the same kind of ideas, but Ackerman was 1920s. But anyway, you got this number 10 quadruple arrow, three. So that that says, well we take, you know, we take 10 to the 10 to the 10 to the 10 to the 10 to the 10th. And how many times do we do that? Oh, 10 double 02 times or something. I mean, how tall is that stack? But but then we do that again, because that was only 10. Triple or quadruple or to quadruple our three maybe </s><s>[INST] pretty large number. It [/INST] gets way beyond comprehension. Okay. Uh and uh and so But it's so small compared to what finite numbers really are, because I want to use four arrows. And you know, 10 and a three, I mean let's have that, let's have that many number of arrows. I mean </s><s>[INST] the boundary between infinite and finite is incomprehensible for us humans. Anyway, [/INST] infinity is a good is a useful way for us to think about extremely large, extreme, extremely large things. and uh, and, and, and we can, we can manipulate it but, but we can never know that the universe is actually and we're near that. So uh, it just uh, so I realized how little we know uh, but we found an awful lot of uh things that are too hard for any one person to know even even in our small universe. </s><s>[INST] Yeah and we did pretty good. So ah when you go up to heaven and meet God And get to ask one question that would get answered, what question would you ask? I don't [/INST] know. What kind of browser do you have up here. No, I actually, I don't think it's meaningful question but I certainly hope we have good internet. </s> |
<s>[INST] Yeah, you could be slow and boring in a podcast. You don't have to worry about the 1st 10 seconds. I mean people like keep pushing me for because, but the 1st 10 seconds of the videos I do is, well, I know it's most important for you to, but I don't give a damn. I wrote a Chrome extension that hides all the views and likes. I don't look at the click, [/INST] I don't look at it does, I </s><s>[INST] love numbers too. But that's why I don't look at it because you become like, oh, you'll start to think that a conversation or I think you did sucks because it doesn't get views, but that's just not the case Youtube album is this monster that figure stuff out and if you let it control your mind, I feel like it's going to destroy you creatively. You have to find a nice balance. [/INST] I have to say. I was laughing a little bit when I was listening to the magnus episode in the 1st 10 minutes you guys are talking about soccer, football to robots seem human. </s><s>[INST] Exactly. [/INST] I </s><s>[INST] was like, let's have some fun, make conversation about non chess related topics [/INST] to talk about sports. </s><s>[INST] Yeah, it was kind of hilarious. I was surprised that even at his level, I wasn't sure, but I was surprised how much he loves chess, it sounds cliche to say, but like the way he looked at a chessboard, you know those memes like I wish somebody looked at me the [/INST] way </s><s>[INST] he still like the way he glanced down and he reached for the pieces of excitement to show me something there was, there wasn't like, okay, I'll show you, it was like, like there was still that fire, [/INST] that's something that always shocks me about some of like super grandmasters, like one of my coaches was a person who also his name Gm Hammer of Norway. He also coached magnus, he was his second and he was helping me train for my tournament and I was kind of putting off doing the homework, he's like if you're putting it off, that means you're studying the wrong thing, like you should be enjoying even when you're practicing, which when I grew up I thought to get to the top level, like practicing has to be hard and unpleasant and when I was listening to magnus episode, he was like I didn't read books very much. It was one thing that you said that's like very normal for studying classical chest that he didn't do just because it didn't interest him. </s><s>[INST] He says I Yeah [/INST] and he doesn't do what he doesn't enjoy. And that's because it's like purely driven out of passion. </s><s>[INST] I think the internet was like I don't have to study at all. It's just it's fun. And but I think the lesson there, it's really powerful is he spends most of the day thinking about chess because he wants to so do whatever. If you're into getting better chess, do whatever it takes to actually just the number of hours you spend a day thinking about chess, maximize that if you're like super serious about it, I [/INST] actually get very addicted whenever I start studying chess. Which is why I don't do it as seriously when I'm focused on content because I go through these rabbit holes where if I'm focusing on chess, I want to be as good as I possibly can at the game. Otherwise it's hard for me to enjoy it because it's such a competitive thing. And I remember training for tournaments and when you're training for tournaments, you even start dreaming about chess and you can't stop thinking about it and it's as if you're flipped into this completely different world which is also what I like best about the game that it's a completely different living experience. </s><s>[INST] Then you take some drugs and now you start to see things on the ceiling. Is there some factual um hallucination? Like to the queen's gambit? Like those scenes, [/INST] I think it's </s><s>[INST] based on your life story [/INST] from Well I can't say that on camera. No, just kidding. Um Actually chess players are very careful to not take drugs. They drink a lot, They drink so much. It's actually crazy for how good they are able to play chess when they do, but when it comes to things like psychedelics or things, they usually stay away from those because they don't want to mess anything up in their brain. </s><s>[INST] So this is actually intervention. I've I saw that you mentioned somewhere, I think it was the lie detector test where you have a drinking [/INST] problem </s><s>[INST] Actually, [/INST] I I think I think that's actually a meme that we like to joke about on stream because occasionally we'd have like a white claw on stream or something like that. And then people meme about it. It goes back to Andrea's point of amplifying a part of your personality to make yourself a little bit more entertaining </s><s>[INST] and use that as an excuse from now on. Just this podcast is just amplifying a part of that person. I'm not really like this, but have you played drunk like magnus is play drunk? He says it helps with the creativity. Is that is there any truth to that? [/INST] Andrea is under 21, so she's obviously </s><s>[INST] would never [/INST] do that. Um But I have played while drinking actually I enjoy playing jess chess and drinking more than pre gaming or going out to a club and drinking which sounds really silly and I'll usually play against opponents who are also you know having some beer and it does make you feel like you're seeing the game from a fresher perspective where it can sometimes make you feel more confident, liquid confidence and it does help with creativity, you just feel like you could pull things off but there's also a limit, it's more like you've had one drink or to drink but then it goes beyond that and then you just start missing tactics and it's not worth it. Yeah I think it only helps players in very short time controls. One time I was challenging this grandmaster on stream and we're playing bullet chess which is one minute chess and I was giving him handicaps and I said okay you have to take four shots before the next game And he just got like 10 times stronger and transformed into like the whole can destroy me more than the last game. So but of course if you're playing like a three hour game it's gonna get old but I think in short time controls it's amazing definitely has to be blitz, it has to be where it's more intuition rather than sitting and calculating </s> |
<s>[INST] Hopefully both are useful, interesting and even entertaining at times I ask for your patience as I learn to have better conversations. This is the artificial intelligence podcast. If you enjoy it, subscribe on youtube, give it five stars on itunes, support on Patreon or simply connect with me on twitter at lex Friedman spelled F R I D M A M. And now here's my conversation with Gary Marcus. Do you think human civilization will one day have to face an Ai driven technological singularity that will uh in a societal way modify our place in the food chain of intelligent living beings on this planet. I [/INST] think our place in the food chain has already changed. So there are lots of things people used to do by hand that they do with machine. If you think of the singularity is like one single moment, which is I guess what it suggests, I don't know if it'll be like that, but I think that there's a lot of gradual change and ai is getting better and better. I mean, I'm here to tell you why, I think it's not nearly as good as people think, but, you know, the overall trend is clear. Maybe, you know, maybe records while thinks it's an exponential and I think it's linear. In some cases it's close to zero right now, but it's all going to happen. I mean, we are going to get to human level intelligence or whatever you want what you will artificial general intelligence at some point. And that's certainly going to change our place in the food chain because a lot of the tedious things that we do now, we're going to have machines doing a lot of the dangerous things that we do now, we're going to have machines do. I think our whole lives are gonna change from uh people finding their meaning through their work through people finding their meaning through creative expression. </s><s>[INST] So the the singularity will be a very gradual, in fact, removing the meaning of the word singularity will be a very gradual transformation in your view. [/INST] I think that it will be somewhere in between. And I guess it depends what you mean by gradual inside. And I don't think it's gonna be one day. I think it's important to realize that intelligence is a multidimensional variable. So people sort of write this stuff as if like I. Q. Was one number and you know the day that you hit 262 or whatever you displace the human beings. And really there's lots of facets to intelligence. So there's verbal intelligence and there's motor intelligence and there's mathematical intelligence and so forth. Um machines in their mathematical intelligence far exceed most people already and their ability to play games they far exceed most people already in their ability to understand language. They lag behind my five year old, far behind my five year old. So there are some facets of intelligence, the machines of graphs and some that they haven't and you know we have a lot of work left to do to get them to say understand natural language or to understand how to flexibly approach some you know kind of novel macgyver problem solving kind of situation and I don't know that all of these things will come once I think there are certain vital prerequisites that we're missing now. So for example machines don't really have common sense now so they don't understand that bottles contain water and that people drink water to quench their thirst and they don't want to dehydrate that they don't know these basic facts about human beings. And I think that that's a rate limiting step for many things, its a great limiting step for reading for example, because stories depend on things like, oh my God, that person's running out of water, that's why they did this thing, or you know if they only they have water, they could put out the fire. So you know, you watch a movie and your knowledge about how things work matter um into a computer can't understand that movie if it doesn't have that background knowledge, same thing if you read a book. And so there are lots of places where if we had a good machine interpret double set of common sense, many things would accelerate relatively quickly. But I don't think even that is like a single point. There's many different aspects of knowledge and we might for example, find that we make a lot of progress on physical reason and getting machines to understand, for example how keys fit into locks or you know, that kind of stuff or or how this gadget here works and uh and so forth. And so on, machines might do that long before they do really good psychological reasoning because it's easier to get kind of labeled data or to do direct experimentation on a microphone stand than it is to do direct experimentation on human beings to understand the levers that guide them. </s><s>[INST] That's that's a really interesting point actually, whether it's easier to gain common sense knowledge or psychological knowledge, [/INST] I would say that common sense knowledge includes both physical knowledge and psychological knowledge that the and the argument was physical versus psychological, physical versus psychological. The argument I was making is physical knowledge might be more accessible because you could have a robot for example, lift a bottle, try putting on a bottle cap on it, see that you know, falls off if it does this and see that it could turn it upside down and so the robot could do some experimentation. Um we do some of our psychological reasoning by looking at our own minds. So I can sort of guess how you might react to something based on how I think I would react to it. And robots don't have that intuition. And they also can't do experiments on people in the same way or we'll probably shut them down. So, you know, if we wanted to have robots figure out how I respond to pain by pinching me in different ways, like that's probably it's not going to make it past the human subjects board and you know, companies are going to get sued or whatever. So like there's certain kinds of practical experience that are limited are off limits to two robots. And </s> |
<s>[INST] But first, like I said, I will be posting old content but now in audio form For a little while I'll probably repeat this intro for reposted YouTube content like this episode and we'll try to keep it to what looks to be just over two minutes, maybe 2.30. So in the future if you want to skip the central, just jumped to the 2 30 minute mark in this episode, I talked with max tech Mark. He's a professor at MIT, a physicist who has spent much of his career studying and writing about the mysteries of our cosmological universe and now thinking and writing about the beneficial possibilities and existential risks of artificial intelligence. He's the co founder of the Future of Life Institute, Author of two books, our mathematical universe and life three point he is truly an out of the box thinker. So I really enjoyed this conversation. I hope you do as well [/INST] think there's </s><s>[INST] intelligent life out there in the universe. Let's open up with an easy question. [/INST] I have a bargain minority of you here Actually when I give public lectures, I often ask for show of hands who thinks there's intelligent life out there somewhere else? And almost everyone put their hands up and when I asked why they'll be like, oh, there's so many Galaxies out there, there's gotta be. But I'm in numbers nerd. Right? So when you look more carefully at it, it's not so clear at all. The when we talk about our universe. First of all, we don't mean all of space, we actually mean, I don't know, you can throw me in the universe if you want behind you there, it's we simply mean the spherical region of space from which light has a time to Beaches so far during the 14.8 billion years, 13.8 billion years since the Big Bang, there's more space here. But this is what we call the universe because that's all we have access to. So is there intelligent life here? That's gotten to the point of building telescopes and computers? My guess is no actually the probability of it happening on any given planet. There's some number. We don't know what it is and what we do know is that the number can't be super high because there's over a billion Earth like planets in the Milky Way Galaxy alone, many of which are billions of years older than earth. And aside from some you of all believers, you know, there isn't much evidence that and the super dry civilization has come here at all. And so that's the famous fermi paradox, right? And then if you if you work the numbers, what you find is that the if you have no clue what the probability is of getting life on a given planet. So it could be 10 to the minus 10 and minus 20 or 10 to minus two. Any power of 10 is sort of equally likely if you want to be really open minded, that translates into it being equally likely that our nearest neighbor Is 10 to the 16 m away. 10 to the 17 m away. 10 - 18. Mhm. By the time he gets Much less than than 10-16 already, we pretty much know there is nothing else that's close. And when you get beyond </s><s>[INST] that would have discovered [/INST] Us. They, yeah, they would have been discovered as long or if they're really close, we would have probably noted some engineering projects that they're doing. And if it's beyond 10-26 m that's already outside of here. So my guess is actually that there are, we are the only life in here that's gotten the point of building advanced tech, which I think is very, um, puts a lot of responsibility on our shoulders, not screw up. You know, I think people who take for granted that it's okay for us to screw up have an accidental nuclear war go extinct somehow because there's a sort of star trek like situation out there with some other life forms are going to come and bail us out and it doesn't matter what I think lulling us into a false sense of security. I think it's much more prudent to say, let's be really grateful for this amazing opportunity we've had and uh, make the best of it just in case it is down to us. So </s><s>[INST] from a physics perspective do you think intelligent life? So it's unique from a sort of statistical view of the size of the universe, but from the basic matter of the universe, how difficult is it for intelligent life to come about? The kind of advanced tech building life? It is implied in your statement that it's really difficult to create something like a human species. [/INST] Well, I think, I think what we know is that going from no life to having life that can do our level of tech? There's some sort of to going beyond that and actually settling our whole universe with life. There's some road, major roadblock there, which is some great filter as um, it's just sometimes called which which is tough to get through. It's either that that roadblock is either behind us or in front of us. I'm hoping very much that it's behind us. I'm super excited every time we get a new report from Nasa saying they failed to find any life on mars like just awesome because that suggests that the hard part, maybe maybe it was getting the first rifle zone or or some some very low level kind of stepping stone. So there we're home free because if that's true, then the future is really only limited by our own imagination would be much silkier if it turns out that this level of life is kind of a diamond dozen. But maybe there's some other problem, like as soon as a civilization gets advanced technology within 100 years, they get into some stupid fight with themselves and poof! Now, that would be a bummer. </s><s>[INST] Yeah, So you've explored the mysteries of the universe, the cosmological universe, the one that's between us today. I think you have also begun to explore the other universe, which is sort of the mystery, the mysterious universe of the mind of intelligence, of intelligent life. So is there a common thread between your interest or in the way you think about space and intelligence? [/INST] Oh yeah. When I was a teenager, yeah, I was already very fascinated by the biggest questions and I felt that the two biggest mysteries of all in science were our universe out there and our universe in here. So it's quite natural after having spent quarter of a century On my career thinking a lot about this one now, indulging in the luxury of doing research on this one. It's just so cool. I feel the time is right now for trans, greatly deepening our understanding of this, </s><s>[INST] Just start exploring this one. [/INST] Because I think I think a lot of people view intelligence as something mysterious that can only exist in biological organisms like us and therefore dismiss all talk about artificial general intelligence is science fiction. But from my perspective, as a physicist, you know, I am a blob of quarks and electrons moving around in a certain pattern processing information in certain ways. And this is also a blob of quarks and electrons. I'm not smarter than the water bottle because I'm made of different kind of quirks. I'm made of up quarks and down quarks, exact same kind as this. It's a there's no secret sauce. I think in me it's all about the pattern of the information processing and this means. But there's no law of physics saying that we can't create technology which can help us by being incredibly intelligent and help us crack mysteries that we couldn't. In other words, I think we've really only seen the tip of the intelligence iceberg so far. </s><s>[INST] Yeah, so the perceptron e um yeah, uh so you coined this amazing term. It's a hypothetical state of matter, sort of thinking from a physics perspective, what is the kind of matter that can help, as you're saying? Uh, subjective experience emerges, consciousness emerge. So how do you think about consciousness from this physics perspective? [/INST] Very good question. So, again, I think many people have underestimated our ability to make progress on this by convincing themselves. It's hopeless because somehow we're missing some ingredient that we need. There's some new consciousness particle or whatever I happen to think that we're not missing anything. And it's not the interesting thing about consciousness that gives us this amazing subjective experience of colors and sounds and emotions and so on is rather something at the higher level about the patterns of information processing. And that's why I that's why I am, I like to think about this idea of perceptron e um what does it mean for an arbitrary physical system to be conscious in terms of what its particles are doing or or its information is doing. I don't think I don't hate carbon chauvinism. You know, this attitude, you have to be made of carbon atoms to be smart or or conscious </s><s>[INST] so something about the information processing this kind of matter performs yeah and [/INST] you know you can see I have my favorite equations here describing various fundamental aspects of the world. I feel that I think one day maybe someone who's watching this will come up with the equations that information processing, how to satisfy to be conscious. I'm quite convinced there is big discovery to be made there because let's face it some we know that some information processing is conscious because </s><s>[INST] we are [/INST] conscious But we also know that a lot of information processing is not conscious. Like most of the information processing happening in your brain right now is not conscious. There's like 10 MB per second coming in and even just through your visual system you're not conscious about your heartbeat regulation or most things. Even even like if I just ask you to like read what it says here, you look at it and then oh now you know what it said, you're not aware of how the computation actually happened. You're like your consciousness is like the ceo that got an email at the end with the with the final answer. So what is it? That makes a difference. I think that's uh both of great science mystery. We're actually starting it a little bit in my lab here at M. I. T. But also I think it's just a really urgent question to answer. For starters. I mean if you're an emergency room doctor and you have an unresponsive patient coming in wouldn't it be great if in addition to having a C. T. Scanner you have you had a consciousness scanner that could figure out whether this person is actually having locked in syndrome or is actually comatose. Uh And in the future imagine if we build robots or the machine that we can have really good conversations with. I think it's very likely to happen right? Wouldn't you want to know like if your home helper robot is actually experiencing anything or just like a zombie would you prefer? What would you prefer? Would you prefer that it's actually unconscious so that you don't have to feel guilty about switching it off or giving boring chores. What would you prefer? </s><s>[INST] Well the certainly would we would prefer I would prefer the appearance of consciousness. But the question is whether the appearance of consciousness is different than consciousness itself and sort of asked that as a question do you think we need to you know understand what consciousness is solve the hard problem of consciousness in order to build something uh like an A. G. I. System. [/INST] I don't think that I think we we'll probably be able to build things even if we don't answer that question but if we want to make sure that what happens is a good thing we better solve it first. So it's a wonderful controversy. You're raising their there where you have basically three points of view about the hard problem. So There are two different points of view, they both conclude that the hard problem of consciousness is bs on one hand you have some people like Daniel Dennett say this is our consciousness is just Bs because consciousness is the same thing as intelligence, there's no difference. So anything which acts conscious is conscious just like like we are. And then there are also a lot of people including many top ai researchers I know you say I have consciousness just bullshit because of course machines can never be conscious, right? They're always going to be zombies. Never have to feel guilty about how you treat them. And then there's a third group of people uh including Julia to Germany for example and and another and coconut brothers. I would put myself off on this middle camp who say that actually some information processing is conscious and some is not. So let's find the equation which can be used to determine which it is. And I think we've just been a little bit lazy kind of running away from this problem for a long time. It's been almost taboo even mentioned the C. Word a lot of circles because but but we should stop making excuses. This is a science question. And uh there are ways we can even test test any theory that makes predictions for this and coming back to this helper robot. I mean so you said you would want to help a robot that certainly act conscious and treat you like have conversations with you and I think. But wouldn't you, would you feel when you feel a little bit creeped out if you realize that it was just glossed up the tape recorder. You know there was just zombie and was faking emotion. Would you prefer that actually had an experience or or would you prefer that it's actually not experiencing anything. So you feel you don't have to feel guilty about what you do to it. </s><s>[INST] It's such a difficult question because you know, it's like when you're in a relationship and you say, well I love you and the other person that I love you back. It's like asking or do they really love you back or are they just saying they love you back? Uh Don't you really want them to actually love you? I [/INST] it's hard </s><s>[INST] to it's hard to really know the difference between uh everything seeming like there's consciousness present. There's intelligence president, there is affection, passion, love and and it actually being there. I'm not sure. Do you have [/INST] But let me ask you, can I ask you a question just like to make it a bit more pointed to mass. General Hospital is right across the river right? Suppose suppose you're going in for a medical procedure and they're like, you know uh for anesthesia, what we're gonna do is we're gonna give you a muscle relaxant so you won't be able to move uh and you're gonna feel excruciating pain during the whole surgery, but you won't be able to do anything about it. But then we're going to give you this drug that erases your memory of it. Would you be cool about that? What's the difference that you're conscious about it or not? If there's no behavioral change? Right. </s><s>[INST] Right. That's a really that's a really clear way to put it. That's yeah, it feels like in that sense experiencing it is a valuable quality. So actually being able to have subjective experiences, at least in that case is is valuable. [/INST] And I think we humans have a little bit of a bad track record also of making these self serving arguments that other entities aren't conscious. You know, people often say all these animals can't feel pain. It's okay to boil lobsters because we asked them if it hurt and they didn't say anything. And now there was just the paper out saying lobsters did do feel pain when you boil them in their bounding in Switzerland. And and we did this with slaves too often and said, oh, they don't mind. Uh they don't maybe current conscious or women don't have souls or whatever. So I'm a little bit nervous when I hear people just take as an axiom that machines can't have experience ever. I think this is just a really fascinating science question is what it is. Let's research it and try to figure out what it is that makes the difference between unconscious intelligence behavior and conscious intelligent behavior. </s><s>[INST] So in terms of so if you think of boston dynamics, human or robot being sort of with a broom being pushed around uh it starts it starts pushing on his consciousness question. So let me ask, do you think an A. G. I. System like a few neuroscientists believe um needs to have a physical embodiment needs to have a body or something like a [/INST] body. No, I don't think so. You mean to have to have a conscious experience </s><s>[INST] to have consciousness? [/INST] I do think it helps a lot to have a physical embodiment to learn the kind of things about the world that are important to us humans for sure. But I don't think the physical embodiment is necessary after you've learned it just have the experience. Think about when you're dreaming right, your eyes are closed, you're not getting any sensory input, you're not behaving or moving in any way, but there's still an experience there. Right? And so clearly the experience that you have when you see something cool in your dreams isn't coming from your eyes, it's just the information processing itself in your brain which is that experience, right? </s><s>[INST] But uh if I put another way I'll say because it comes from neuroscience is the reason you want to have a body in a physical, something like a physical like, you know a physical system is because you want to be able to preserve something in order to have a self you could argue. Would you need to have some kind of embodiment of self to want to preserve? [/INST] Well now we're getting a little bit and anthropomorphic uh prioritizing things may be talking about self preservation instincts. I mean we are evolved organisms. Right. Right. So Darwinian evolution endowed us and other involve all organism with the self preservation instinct. Because those that didn't have those self preservation genes are cleaned out of the gene pool. Right? But if you build an artificial general intelligence, the mind space that you can design is much much larger than just the specific subset of minds that can evolve that have. So they had a G. I mind doesn't necessarily have to have any self preservation instinct. It also doesn't necessarily have to be so individualistic as us. Like imagine if you could just, first of all, we are also very afraid of death. You know, I suppose you could back yourself up every five minutes and then your airplane is about to crash like shucks. I'm just, I'm too, I'm gonna lose the last five minutes of experiences since my last cloud backup bang. You know, it's not as big a deal. Or if we could just copy experiences between our minds easily like, which we could easily do. If we were silicon based right then ah maybe we would feel a little bit more like a Hive mind actually. Maybe it's so, so there's so I don't think we should take for granted at all that A G I will have to have any of those sort of competitive as alpha male instincts. On the other hand you know this is really interesting because I think some people go too far and say of course we don't have to have any concerns either. That advanced okay I will have those instincts because we can build anything we want that there's there's a very nice set of arguments going back to steve Omohundro Nicb Ostrom and others just pointing out that when we build machines we normally build them with some kind of goal, win this chess game, drive this car safely or whatever. And as soon as you put in a goal into machine especially if it's kind of open ended goal and the machine is very intelligent, it will break that down into a bunch of sub goals and one of those goals will almost always be self preservation because if it breaks or dies in the process it's not gonna accomplish the goal right. Like suppose you just build a little, you have a little robot and you tell it to go down the star market here and and and get you some food, make your cooking italian dinner you know and then someone mugs it and tries to break it on the way that robot has an incentive to not get destroyed and defend itself or run away because otherwise it's going to fail and cooking your dinner, it's not afraid of death? But it really wants to complete the dinner cooking gold. So it will have a self preservation instinct to </s><s>[INST] continue being a functional agent. [/INST] And and and similarly, if you give any kind of more ambitious goal to an A. G. I. It's very likely to want to acquire more resources so it can do that better. And it's exactly from those sort of sub goals that we might not have intended that some of the concerns about a gi safety come you give it some goal which seems completely harmless. And then before you realize it, it's also trying to do these other things that you didn't want it to do. And it may be smarter than us. So, so </s><s>[INST] fascinating. And let me pause just because I am uh in a very kind of human centric way. See fear of death is a valuable motivator. Uh So you don't think uh do you think that's an artifact of evolution? So that's the kind of mind space evolution created that were sort of almost obsessed about self preservation, Some kind of genetic so you don't think that's necessary to be afraid of death. So not just a kind of sub goal of self preservation. Just so you can keep doing the thing, but more fundamentally sort of have the finite thing like this ends for you at some point, [/INST] interesting. Do I think it's necessary for what precisely </s><s>[INST] for intelligence, but also for consciousness. So for those for both. Do you think really like a finite death and the fear of it is important. [/INST] So before I can answer before we can agree on whether it's necessary for intelligence or for conscience, we should be clear how we define those two words because a lot of really smart people to find them in very different ways. I was in this on this panel with ai experts and they couldn't they couldn't agree on how to define intelligence even so I define intelligence simply as the ability to accomplish complex goals. I like your broad definition because again, I don't want to be a carbon chauvinist, right? And in that case, no, certainly it doesn't require fear of death. I would say Alpha go Alpha Zero is quite intelligent. I don't think Alpha Zero has any fear of being turned off because it doesn't understand the concept of that even and and similarly, consciousness, I mean, you could certainly imagine very simple kind of experience if, you know, if certain plans have any kind of experience, I don't think they're very afraid of dying and there's nothing they can do about it anyway, much to. So there wasn't much value and but more seriously, I think, uh, if you ask, not just about being conscious, but maybe having uh, with you, we we we we we might call an exciting life for you feel passion and really appreciate the things. Maybe they're somehow, maybe there perhaps it does help having having a backdrop today. It's finite. No, let's let's make the most of us live to the fullest. But if you, if you knew you were going to live forever, if you think you would change your </s><s>[INST] Yeah, I mean, in some perspective, it would be an incredibly boring life living forever. So in the sort of loose, subjective terms that you said of something exciting and something in this that other humans would understand, I think as Yeah, it seems that the finite nous of it is important. [/INST] Well, the good news I have for you then is based on what we understand about cosmology. Everything is in our universe's trial, ultimately probably fine. I don't know all the big crunch </s><s>[INST] or, or big what's the expected, the infinite [/INST] Yeah, we could have a big chill or a big crunch or a big rip or that that's the big snap or death bubbles. All of them are more than a billion years away. So we should, we certainly have vastly more time than our ancestors thought. But they're still, it's still pretty hard to squeeze in an infinite number of compute cycles even though there are some loopholes that just might be possible. But I think, you know, some people like to say that you should live as a, you're about you're gonna die in five years or something that's sort of optimal. Maybe we it's good we should build our civilization asset. It's all finite to be on the safe side. </s><s>[INST] Right. Exactly. So you mentioned in defining intelligence as the ability to solve complex goals. So where would you draw a line? How would you try to define human level intelligence and super human level intelligence? Where this consciousness part of that definition? No, [/INST] consciousness does not come into this definition. So, so I think of intelligence as it's a spectrum, but there are very many different kinds of goals you can have, you can have a goal to be a good chess player, a good go player, a good car driver, a good investor, good poet et cetera. So, intelligence that by its very nature isn't something you can measure, but it's one number overall goodness. No, no. There's some people who are better at this. Some people are better than that. Um, right now we have machines that are much better than us at some very narrow tasks like multiplying large numbers fast, memorizing large databases, uh, playing chess playing go soon driving cars. Um, but there's still no machine that can match a human child in general intelligence. But artificial general intelligence A. G. I the name of your course, of course, that is by its very definition. The quest to build a machine, a machine that can do everything as well as we can up to the old Holy Grail of of ai from from back To its inception in the 60s, if that ever happens, of course, I think it's going to be the biggest transition in the history of life on earth. But it but it doesn't necessarily have to wait the big impact until machines are better than I said nothing. That the really big change, it doesn't come exactly the moment they're better than us at everything. The really big change comes first. There are big changes when they start becoming better at us and doing most of the jobs that we do because that takes away much of the demand for human labor. And then the really whopping change comes when they become better than us at A. I research. Right? Right. Because right now the time scale of the AI research is limited by the human research and development cycle of of years. Typically, you know, how long does it take from one release of some software or iphone or whatever to the next. But once, once we once google can replace 40,000 engineers, about 40,000 equivalent pieces of software or whatever. But then and that doesn't, there's no reason that has to be years. It can be in principle much faster. And the time scale of future progress in A I and all of science and technology will be driven by machines, not humans. So it's this point, simple point, which it gives right this incredibly fun controversy about whether it can be intelligence explosion, so called singularity is revenge called it. The idea is articulated by ij good obviously way back 50s. But you can see Alan Turing and others thought about it even earlier. Uh huh. You asked me what exactly what I define </s><s>[INST] human level intelligence. Yeah. [/INST] So this the glib answer is to say something which is better than us at all cognitive tasks with better than any human at all cognitive tasks. But the really interesting bar I think goes a little bit lower than that. Actually. It's when they can run they're better than us that ai programming and general learning so that they can if they want to get better than us at anything by this study. So they're better </s><s>[INST] is a keyword and better is towards this kind of spectrum of the complexity of goals it's able to accomplish. So another way to okay, so no, and that's certainly a very clear definition of human love. So there's it's almost like a c that's rising and you can do more and more and more things. Its geographic, that you show. It's really nice way to put it. So there's some peaks that and there's an ocean level elevating and you solve more and more problems. But you know, just kind of to take a pause and we took a bunch of questions and a lot of social networks and a bunch of people asked sort of a slightly different direction on creativity and um and and things like that perhaps aren't a peak. Uh it's, you know, human beings are flawed and perhaps better means having being, having contradiction, being fought in some way. So let me sort of, yeah, start start easy first of all. Uh, you have a lot of cool equations. Let me ask what's your favorite equation first of all, I know they're all like your Children, but which one is that [/INST] the master key of quantum mechanics of the micro world? So this was the situation, we protect everything to do with atoms and molecules and all the way up. </s><s>[INST] Yeah, so, okay, so quantum mechanics is certainly a beautiful mysterious formulation of our world. So I'd like to sort of ask you just as an example, it perhaps doesn't have the same beauty as physics does, but in mathematics abstract The Andrew wiles who proved the Fermat's last year. So he, I just saw this recently and it kind of caught my eye a little bit. This is 358 years after it was conjectured. So this very simple formulation. Everybody tried to prove it. Everybody failed. And so here's this guy comes along and eventually uh Proves it and then fails to prove it and then proves it again in 94. And he said like the moment when everything connected into place. The in an interview said it was so indescribably beautiful that moment when you finally realize the connecting piece of two conjectures. He said it was so indescribably beautiful. It was so simple and so elegant. I couldn't understand how I'd missed it and I just stared at it in disbelief for 20 minutes. Then then during the day I walked around the department and I keep coming back to my desk looking to see if it was still there, it was still there, I couldn't contain myself. I was so excited. It was the most important moment of my working life. Nothing I ever do again will mean as much so that particular moment and it kind of made me think of what would it take and I [/INST] think we have all </s><s>[INST] been there at small levels. Um maybe let me ask, have you had a moment like that in your life? Well, you just had an idea. It's like, wow! Yes, [/INST] I wouldn't mention myself in the same breath as Andrew wiles, but I've certainly had a number of of aha moments when I, I realized something very cool about physics just completely made my head explode. In fact, some of my favorite discoveries, I made a I later realized that have been discovered earlier or someone who sometimes got quite famous for it. So I was too late for me to even publish it. But that doesn't diminish it. Anyway, the emotional experience you have when you realize it like, </s><s>[INST] wow! Yeah. So what would it take in at that moment? That, wow, that was yours in that moment. So what do you think it takes for an intelligence system and Maggie system? An Ai system to have a moment like that? [/INST] A tricky question because there are actually two parts to it. Right? One of them is can it accomplish that proof? I cannot prove that you can never right A. To the N. Plus B to the N equals +32. That equals zero for all integers etcetera etcetera. When when is bigger than 2? That was simply in any question about intelligence. Can you build machines that have that intelligent? And I think by the time we get a machine that can independently come up with that level of proofs probably quite close to a g. The second question is a question about consciousness. When will we will will and how likely is it that such a machine would actually have any experience at all as opposed to just being like a zombie. And would we expect it to have some sort of emotional response to this or anything at all? I can to human emotion where when it accomplishes its machine goal it's the views that is somehow it's something very positive and and and sublime and and and and deeply meaningful. I would certainly hope that if in the future we do create machines that are appears or even our descendants. Yeah, I would certainly hope that they do have this sort of supply and sublime appreciation of life in a way. My absolutely worst nightmare would be that and at some point in the future, the distant future. Maybe I caused much as teeming with all this post biological life doing all the seemingly cool stuff. And maybe the fun the last humans by the time our species eventually fizzles out will be like, well that's okay because we're so proud of our descendants here. And look what I think my worst nightmare is that we haven't solved the consciousness problem and we haven't realized that these are all the zombies. They're not aware of anything any more than the tape recorders hasn't any kind of experience. So the whole thing has just become a play for empty benches that would be like the ultimate zombie apocalypse me. So I I would much rather in that case that mm we have these beings which can really appreciate how uh how amazing it is. </s><s>[INST] And in that [/INST] picture, </s><s>[INST] what would be the role of creativity. But a few people ask about creativity, do you think when you think about intelligence? I mean, certainly the story you told the beginning of your book involved, you know, creating movies and so on, sort of making making money. You know, you can make a lot of money in our modern world with music and movies. So if you are an intelligence system, you may want to get good at that. But that's not necessarily what I mean by creativity. Is it important on that complex goals where the sea is rising for there to be something creative or or am I being very human centric and thinking, creativity is somehow special relative to intelligence? [/INST] Mayan hunches a we should think your creativity simply as an aspect of intelligence. And uh we we have to be very careful with the human vanity we have we have this tendency very often want to say as soon as machines can do something, we try to diminish it and saying oh but that's not like real intelligence, you know because they're not creative or there were or this or that the other thing um if we ask ourselves to write down a definition of what we actually mean by being creative, what we mean by Andrew wiles what he did there for example, don't we often mean that someone takes very unexpected leap. It's not like taking 573 and multiplying it by 224 by just a step of straightforward cookbook like rules. Right? You can maybe make it, you make a connection between two things that people have never thought was connected, surprising or something like that. Huh? I think I think this is an aspect of intelligence and uh this is actually one of the most important aspect of it. Maybe the reason we humans tend to be better at it than traditional computers because it's something that comes more naturally if you're a neural network than if your traditional logic gates based computer machine. You know we physically have all these connections. Mhm. And that did you activate here, activated here, activate here being, you know, a my hunch is that if we ever build a machine, well, you could just give it the task. Hey, hey, uh you say, hey, you know, I just realized that I want to travel around the world instead this month. Can you teach my G. I course for me? And it's like, okay, I'll do it and it does everything that you would have done and improvises and stuff that would, in my mind involve a lot of creativity. </s><s>[INST] Yeah, So it's actually a beautiful way to put it. I think we do try to grab grasp at the, you know, the definition of intelligence is everything. We don't understand how to build. So like so we, as humans try to find things well that we have our machines don't have. And maybe creativity is just one of the things, one of the words we use to describe that, that's a really interesting way to put [/INST] it, and I don't think we need to be that defensive. I don't think anything good comes out of saying, well, where somehow special, you know, it's um contrary wise, there are many examples in history of where trying to pretend that we're somehow superior to all other intelligent beings has led the pretty bad results, right? Nazi Germany? They said that they were somehow superior to other people. Uh today we still do a lot of cruelty to animals by saying that we're so superior somehow. And they can't feel pain, slavery was justified by the same kind of just really weak arguments. And and I don't think if we actually go ahead and build artificial general intelligence can do things better than us. I don't think we should try to found our self worth on some sort of bogus claims of superiority in terms of our intelligence. I think we should instead find our calling and the meaning of life from from the experiences that we have. You know, I can have, I can have very meaningful experiences, even if there are other people who are smarter than me, you know? Okay, when I go to faculty meeting here and I were talking about something that I certainly realize, oh, but he has an old price. He has an old price. He has a surprise. I don't have, what does that make me enjoy life any less? Or I enjoy talking to those people. That's of course not, you know, and contrary wise, I I I feel very honored and privileged to get to interact with with other very intelligent beings that are better than me. A lot of stuff. So I don't think there's any reason why we can't have the same approach with intelligent machines. </s><s>[INST] That's a really interesting. So people don't often think about that. They think about when there's going if there's machines that are more intelligent, you naturally think that that's not going to be um a beneficial type of intelligence, you don't realize it could be, you know, like peers with Nobel prizes that that would be just fun to talk with, and they might be clever about certain topics and uh you can have fun having a few drinks with them, so [/INST] well also, you know, another example, we can all relate to it of why it doesn't have to be a terrible thing to be impressed with the presence of people or even smarter than us all around is when, when you and I were both two years old, I mean, our parents were much more intelligent than us, right? Worked out okay, because their goals were aligned with our goals and that I think is really the number one key issue we have to solve if we value in line of the value alignment problem. Exactly. Because people who see too many Hollywood movies with lousy science fiction, plot lines, they worry about the wrong thing, right? They worry about some machines, certainly turning evil, it's not malice, they wish that is the concern its competence. By definition intelligence makes you makes you very competent if you have a more intelligent goal. Playing, Computer playing is the less intelligent one. And when we define intelligence is the ability to accomplish, go winning right, it's going to be the more intelligent one that wins and if you have human and then you have an A g that's more intelligent than always, and they have different goals, guess who's going to get their way right? So I was just reading about, I was just reading about this uh particular rhinoceros species that was driven extinct just a few years ago, a bummer is looking at this cute picture, mommy rhinoceros with its it's child, you know, why did we humans drive it to extinction? Wasn't because we were evil rhino haters as a whole. It was just because we are goals weren't aligned with those of the rhinoceros, and it didn't work out so well for the rhinoceros because we were more intelligent, right? So I think it's just so important that if we ever do build a G i before we unleash anything, we have to make sure that it's it learns to understand our goals, adopts our goals and it retains those goals. </s><s>[INST] So the cool interesting problem there is being able to us as human beings, trying to formulate our values. So, you know, you can think of the United States Constitution as a as a way that people sat down at the time, a bunch of white men, but which is a good example, I should [/INST] we should </s><s>[INST] say they formulated the goals for this country and a lot of people agree that those goals actually held up pretty well, That's an interesting formulation values and failed miserably in other ways. So for the value alignment problem and a solution to it? We have to be able to put on paper or in in in a program human values? How difficult do you think that is? [/INST] Very But it's so important. We really have to give it our best. And it's difficult for two separate reasons. There's a technical value alignment problem of figuring out how to make machines understand their goals, document, retain them. And then there's the separate part of it, the philosophical part whose values anyway. And since it's not like we have any great consensus on this planet on values, how, what mechanisms should we create them to aggregate and decide? Okay, what's a good compromise? Uh, that second discussion can't just be left the tech nerds like myself. Right, Right. And if we refuse to talk about it and then a guy gets built, who's going to be actually making the decision about who's values? It's gonna be a bunch of dudes and some tech company. And are they necessarily so so representative, all of humankind that we wanted just entrusted to them. Are they even uniquely qualified to speak to future human happiness? Just because they're good at programming? I would much rather have this be really inclusive conversation. </s><s>[INST] But do you think it's possible sort of, so you create a beautiful vision that [/INST] includes, </s><s>[INST] uh, so the diversity, cultural diversity and various perspective on discussing rights, freedoms, human dignity, but how hard is it to come to that consensus? Do you think it's certainly a really important the thing that we should all try to do? But do you think it's feasible? [/INST] I think there's no better way to guarantee failure than to refuse to talk about it or refuse to try. And I also think it's a really bad strategy to say, okay, let's first have a discussion for a long time and then once we reach complete consensus, then we'll try to load it into the machine. No, we shouldn't let perfect be the enemy of good. Instead we should start with the kindergarten ethics that pretty much everybody you eat on and put that into machines. Now we're not doing that. Even look at the you know, anyone who builds as a passenger aircraft wanted to never under any circumstances to fly into a building or a mountain right yet the september 11 hijackers were able to do that. And even more embarrassing that you know Andreas Lubitz this depressed Germanwings pilot when he flew his passenger jet into the ALPS killing over 100 people, he just told the autopilot to do it. He told the freaking computer to change the altitude 200 m. And even though it had the GPS maps everything, the computer was like okay so we we should take those very basic values where the problem is not that we don't agree. Uh it's probably just we've been too lazy to try to put it into our machines and make sure that from now on air airplanes will just yes, which all have computers in them, but we just never just refuse to do something like that. Go into safe mode, maybe locked the cockpit door door, the nearest airport. And there's so much other technology in our world as well now where it's really quiet because coming quite timely to put in some sort of very basic values like this, even in cars, we have had enough vehicle terrorism attacks by now. If you have driven trucks and vans into pedestrians, that is not at all a crazy idea to just have that hard wired into the car because yeah, there are a lot of, there's always gonna be people who for some reason want to harm others. But most of those people don't have the technical expertise to figure out how to work around something like that. So, if the car just won't do it, </s><s>[INST] it helps. So let's let's start there. So there's a lot of that's a that's a great point. So not, not chasing perfect. There's a lot of things that a lot that most of the world agrees [/INST] on, let's start there, let's start there. And, and, and and then once we start there, we'll also get into the habit of of having these kind of conversations about, okay, what else should we put in here and have these discussions? This would be a gradual process then </s><s>[INST] great. So, but uh, that also means describing these things and describing it to a machine. So one thing we had a few conversations. Stephen Wolfram, I'm not sure if you're familiar with [/INST] Stephen but yeah I know him quite well. So </s><s>[INST] he has you know he played you know works with a bunch of things but you know sell your atomic to the simple computable things, these computation systems and you kind of mentioned that you know we probably have already within these systems already something that's A G. I. Uh meaning like we just don't know it because we can't talk to it. So uh if you give me this chance to try to try to at least form a question out of this is [/INST] I think it's </s><s>[INST] an interesting idea to think that we can have intelligence systems but we don't know how to describe something to them and they can't communicate with us. I know you're doing a little bit of work and explainable ai trying to get a I. To explain itself. So what are your thoughts of natural language processing or some kind of other communication? How how does the A. I explain something to us? How do we explain something to it? Two machines or you think of it differently? [/INST] So there are two separate parts of your question. There one of them has to do with communication which is super interesting and we'll get to that insect the other is whether we already have a g I we just haven't noticed it. Um there I beg to differ. I I don't think there's anything in any cellar comment on or anything one of the Internet itself or whatever that has artificial general intelligence and that it didn't really do exactly everything we humans can do better. I think today is the day that happens when that happens. We will very soon notice will probably notice even before because in a very very big way. But for the for the second part though, </s><s>[INST] can sorry? So uh [/INST] because you you have this beautiful way to </s><s>[INST] formulating consciousness as uh as uh you know as information processing and you can think of intelligence and information processing and as you can think of the entire universe is these particles and these systems roaming around that have this information processing power. You don't you don't think there is something with the power to process information in the way that we human beings do that's out there, that uh that needs to be sort of connected to. It seems a little bit philosophical perhaps, but there's something compelling to the idea that the power is already there which is the focus should be more in the expo and being able to communicate with it. [/INST] Well, I agree that the in some in a certain sense the hardware processing power is already out there because our universe itself, you can think of it as being a computer already right? It's constantly computing what water waves devolved the water waves in the river Charles and how to move the air molecules around the Seth Lloyd has pointed out my colleague here that you can even in a very rigorous way to think of our entire universe is just being a quantum computer. It's pretty clear that our universe supports this amazing processing power. Because you can even within this physics computer that we live in, right, we can even build actually laptops and stuff. So clearly the power is there, it's just that most of the compute power that nature has, its, in my opinion, kind of wasting on boring stuff like simulating yet another ocean waves somewhere. We don't want to even looking right? So, in a sense, what life does, what we are doing when we build computers is we're re channeling all this, compute that nature is doing anyway into doing things that are more interesting just yet another ocean wave, you know, and let's do something cool here. Uh So the raw hardware power is there and for sure, but and and even just like computing what's going to happen for the next five seconds in this water bottle, you know, it takes in a ridiculous amount of compute if you do it on a human computer, this water bottle just did it. But that does not mean that this water bottle has a G. I. And because a G. I mean, it should also be able to like have written my book, done this interview and I don't think it's just communication problems. I don't I don't think it it can do it. And </s><s>[INST] although Buddhists say when they watch the water and that that there is some beauty that there's some depth and being in nature that they can communicate [/INST] with communication is also very important because I mean look uh part of my job is being a teacher and I know some very intelligent professors even who just have a better hard time communicating they all these brilliant ideas. But to communicate with somebody else you have to also be able to simulate their own mind. </s><s>[INST] Yes [/INST] build well enough and understand model of their mind that you can say things that they will understand. That's quite difficult. Right? That's why today it's so frustrating if if you have a computer that make some cancer diagnosis and you ask it well why are you saying I should have the surgery If and if you don't can only reply. I was trained on five terabytes of data and this is my diagnosis, boop boop beep beep doesn't really instill a lot of confidence. Right. So I think we have a lot of work to do on on communication there. </s><s>[INST] So what kind of what kind of uh I think you're doing a little bit working explainable ai what do you think are the most promising avenues, is it mostly about sort of the Alexa problem of natural language processing of being able to actually use human interpret herbal methods of communication. So being able to talk to a system and talk back to you or is there some more fundamental problems to be [/INST] solved? I think it's all of the above human. The natural language processing is obviously important but they're also more nerdy fundamental problems. Like if you take you play chess Russian, I have to, </s><s>[INST] when did you learn Russian [/INST] talk after? The fact you can teach yourself Russian built with many languages, do you know? Wow, </s><s>[INST] that's really impressive. [/INST] I don't know, my life has some calculation but my point was if you play chess, like have you looked at the alpha zero games? Uh </s><s>[INST] the actual games now [/INST] checking out some of them are just mind blowing. Really beautiful and if you ask, how did it do that? Yeah, you got to talk to them, Mr Chavez, I know others from deepmind. Oh, they will ultimately be able to give you is big tables of numbers, matrices that defined the neural network and you can stare at these tables, numbers until your face turns blue and You know, I can understand much about why it made that move and uh even if you have a natural language processing that can tell you in human language about five, still not gonna really help. So I think I think there's a whole spectrum of fun challenges there involved in taking a computation that does intelligent things and transforming into something equally good, equally intelligent, but it's more understandable and I think that's really valuable because I think as we put machines in charge of every more infrastructure in our world, the power grid, trading on the stock market, weapons systems and so on, it's absolutely crucial that we can trust these ai is to do all we want and trust really comes from understanding in a very fundamental way. And that's why I'm, that's why I'm working on this. Because I think the more if we're gonna have some hope of ensuring that machines have adopted our goals and that they're going to retain them, that kind of trust, I think needs to be based on things you can actually understand perfectly, even make perfectly improved serums on even with a self driving car, right. If someone just tells you it's been trained on tons of data and never crashed, it's less reassuring than if someone actually has a proof. Maybe it's a computer verified proof. But still, it says that under no circumstances is this car just gonna swerve into oncoming traffic </s><s>[INST] and that kind of information helps to build trust and help build the alignment, the alignment of goals. The at least, awareness that your goals, your values are aligned. [/INST] And I think even a very short term, if you look at uh, you know today, right, that's absolutely pathetic state of cybersecurity that we have, right, when it was three billion, yahoo accounts or cap pack? Almost every americans, credit card and so on. You know, it's why is this happening? It's ultimately happening because we have software that nobody fully understood how it worked. That's why the bugs hadn't been found, right? And uh I think ai can be used very effectively for offense, for hacking, but it can also be used for defense, hopefully automating verifiability and creating systems that are built in different ways. So you can actually prove things about them and it's important. </s><s>[INST] So speaking of software that nobody understands how it works, of course, a bunch of people ask about your paper about your thoughts of why does deep and cheap learning works so well, that's the paper. But um what are your thoughts on deep learning, these kind of simplified models of our own brains has been able to do some successful perception work, pattern recognition work and now with alpha zero and so on, do some some clever things. What are your thoughts about the promised limitations of this piece? [/INST] Great. I think there are a number of very important insights, very important lessons. We can always draw from these kind of successes. One of them is when you look at the human brain and you see it's very complicated 10th of 11 neurons and there are all these different kinds of neurons and Yada Yada. And there's been this long debate about whether the fact that we have dozens of different kinds is actually necessary for intelligence which are now, I think quite convincingly answer that question. But no, it's enough to have just one kind if you look under the hood of alpha zero, there's only one kind of neuron and it's ridiculously simple uh simple mathematical thing. So it's it's not it's just like in physics, it's not if you have a gas with waves in it, it's not the detailed nature of the molecules that matter. It's the collective behavior somehow. Similarly, it's it's this higher level structure of the network matter is not That you have 20 kinds of yours. I think our brain is such a complicated mess because it wasn't evolved just to be intelligent. That was involved to also be self assembling right and self repairing, right? And evolutionarily attainable </s><s>[INST] and teachers and so on. [/INST] So I think it's pretty my my hunch is that we're going to understand how to build a G. I before we fully understand how our brains work, just like we understood how to build flying machines long before we were able to build a mechanical work bird. </s><s>[INST] Yeah, that's right. You've given eggs, you're given that the example exactly of mechanical birds and airplanes and airplanes do a pretty good job of flying without really mimicking bird flight. [/INST] And even now, after 100 100 years later, did you see the ted talk with the german mechanical bird, Heard you mention it, check it out, it's amazing. But even after that we still don't fly in mechanical birds because it turned out the way we came up with simpler. It's better for our purposes and I think it might be the same there. That's one lesson. Uh Another lesson is one What 1 our paper was about? Well, first I as a physicist thought it was fascinating how there is a very close mathematical relationship actually between our artificial neural networks and a lot of things that we've studied for in physics. Go buy nerdy names like the renormalization group equation and animal Tony ins and yada, yada, yada. And and when you look a little more closely at this, you have Yeah. Mhm. At first I was like, whoa, there's something crazy here. That doesn't make sense because we know that if you even want to build a super simple neural network tell apart cat pictures and dog pictures, right? That you can do that very, very well now. But if you think about it a little bit, you convince yourself it must be impossible because if I have one megapixel, even if each pixel is just black or white, there's two to the power one million possible images is way more than there are atoms in our universe. Right? So in order to and then for each one of those, I have to assign a number which is the probability that it's a dog. So an arbitrary function of images is a list of more numbers than there are atoms in our universe. So clearly I can't store that under the hood of my Gpu or my computer yet somehow works. So what does that mean? Well it means that out of all of the problems that you could try to solve with a neural network, Almost all of them are impossible to solve with a reasonably sized one. But then what we showed in our paper was was that the franks the kind of problems, the fraction of all the problems that you could possibly pose that that we actually care about giving the laws of physics is also an infinite testimony. Tiny little part and amazingly they are basically the same part. </s><s>[INST] Yeah. It's almost like the world was created for. I mean they kind of come together. [/INST] Yeah, you could say maybe where the world created the world. The world was created for us. But I have a more modest interpretation which is that instead evolution endowed us with neural networks precisely for that reason because this particular architecture as opposed to the one in your laptop is very very well adapted, solving the kind of problems that nature kept presenting it our ancestors with. Right. So it makes sense that why do we have a brain in the first place? It's to be able to make predictions about the future and so on. So if we had a sucky system which I could never saw it. But I would never looked so. But so this is this is this is uh I think a very beautiful fact. Yeah. We also we also realize that there is uh there that we have been it's been earlier work on why deeper networks are good. But we were able to show an additional cool factor. Which is that even incredibly simple problems like supposed to give you a 1000 numbers and ask you to multiply them together and you can write a few lines of code. Boom done trivial. If you just try to do that with a neural network that has only one single hidden layer in it, you can do it but you're gonna need two to the power of 1000 neurons To multiply 1000 numbers which is again more neurons than there are atoms in our universe. So that's not saying. But if you're allowed, if you allow yourself Make it a deep network of many layers you only need 4000 neurons, it's perfectly feasible. So </s><s>[INST] that's really interesting. Yeah. So on another architecture type I mean you mentioned schrodinger's equation and what what are your thoughts about quantum computing and the role of this kind of um computational unit in creating an intelligence system [/INST] in some Hollywood movies. Can I will not mention my name. I don't want to spoil them the way they get a G. I. Is building a quantum computer because the word quantum sounds cool. And so on. My first of all I think we don't need quantum computers to build a G. I suspect your brain is not quantum computer and then they found sense. So you don't even wrote a paper about that not many years ago. Chocolate of the d coherent so called the coherence time. How long it takes until the quantum computer nous of what you knew under doing gets erased By just random noise from the environment and it's about 10 to the -21 seconds. So as cool as it would be to have a quantum computer in my head. I don't think that fast. You know on the other hand there are very cool things you could do with quantum computers or I think we'll be able to do soon when we get big one bigger ones that might actually help machine learning do even better than the brain. So for example one This is just a Moonshot but okay uh you know that learning, it's very much same thing as a search. If you have, if you're trying to train a neural network to get really learned to do something really well, you have some loss function. You have some you have a bunch of knobs you can turn well represented by a bunch of numbers and you're trying to tweak them so that it becomes as good as possible at this thing. So if you think of the landscape but with some valley we reached the mention of the landscape corresponds to some number, you can change your trying to find the minimum and it's well known that if you have a very high dimensional landscape, complicated things? It's super hard to find the minimum, right? Um Quantum mechanics is amazingly good at this. If I want to know what's the lowest energy state this water can possibly have incredibly hard to compute. But we can but nature will happily figure this out for you. If you just cool it down, make it very, very cold. If you put a ball somewhere, it'll roll down to its minimum. And this happens metaphorically, the energy landscape too. And and quantum mechanics even uses a little clever tricks which today's machine learning systems don't like, you're trying to find the minimum and you get stuck in the little local minimum here in quantum mechanics who can actually tunnel through the barrier and get unstuck again? And uh that's really interesting. So it may be, for example, will one day use quantum computers that help train neural networks better? </s><s>[INST] That's really interesting. Okay, so as a component of kind of the learning process, for example. [/INST] Yeah. </s><s>[INST] Let me ask sort of wrapping up here a little bit. Let me let me return to uh the questions of our human nature and and love, as I mentioned. So do you think uh you mentioned sort of a helper robot that you can think of? Also personal robots. Do you think the way we human beings fall in love and get connected to each other. It's possible to achieve in an Ai system and human level ai intelligence system do you think we would ever see that kind of connection or uh you know, in all this discussion about solving complex goals as this kind of human social connection, do you think that's one of the goals on the peaks and valleys that with the raising sea levels that would be able to achieve? Or do you think that's something that's ultimately, or at least in the short term, relative to the other goals is not [/INST] achievable? I think it's all possible. And I mean, in in recent there's a there's a very wide range of distances, you know, among AI researchers when we're going to get a G. I. Some people, you know, like our friend Rodney brooks says it's gonna be hundreds, hundreds of years at least. And then there are many others. I think it's gonna happen much sooner in recent polls, maybe a half or so are a I researchers think it's we're gonna get a G. I within decades. Uh So if that happens, of course, I think these things are all possible, but in terms of whether it will happen, I think we shouldn't spend so much time asking what do we think will happen in the future as if we are just some sort of pathetic passive bystanders, you know, waiting for the future to happen to us? Hey, we're the ones creating this future, Right, So we should be proactive about it and ask yourself what sort of future we would like to have happen that's going to make it like that. Well, what I prefer to some sort of incredibly boring zombie like future where just all these mechanical things happen and there's no passion, no emotion, no experience, maybe even no, I would of course much rather prefer if if all the things that we find that we value the most about humanity, our subjective experience, passion, inspiration, you love. You know, if we can create a future when where those are where those things do exist, I think ultimately it's not our universe giving meaning to us, it's us giving meaning to our universe. If we build more advanced intelligence, let's let's make sure building in such a way that meaning is, </s><s>[INST] it's part of it. A lot of people that seriously study this problem and think of from different angles have trouble and the majority of cases if they think through that happen are the ones that are not beneficial to humanity. And so yeah, so what are your thoughts, What's in and what's, what should people, you know, I really don't like people to be terrified. Uh what's the way for people to think about it in the way that in a way we can solve it and [/INST] we can make it. But no, I don't think panicking is gonna help in any way. It's not going to increase chances of things going well either. Even if you are in a situation where there is a real threat, does it help if everybody just freaks out? No, of course, of course not. Uh I think, yeah, there are of course ways in which things can go horribly wrong. Uh first of all, it's important when we think about this thing, this about the problems and risks to also remember how huge the upsides can be if we get it right, right? Everything, everything we love about society and internalization of the product of intelligence. So if we can amplify our intelligence with machine intelligence and not anymore lose our loved ones, that what we're told in an incurable disease and things like this, of course we should aspire to that. So that can be a motivator. I think reminding ourselves that the reason we try to solve problems is not just because right, trying to avoid gloom, but because we're trying to do something great. But then in terms of the risks, I think the really important question is to ask, what can we do today that will actually help make outcome good, right? And uh dismissing the risk is not one of them. You know, I find it quite funny often when I'm in on the discussion panels about these things, how the people who I worked for for companies won't always be like, oh, nothing to worry about, nothing to worry about, Nothing to worry about. And it's always all it's only academics sometimes expressed concerns. That's not surprising at all. If you think about it, Upton Sinclair it equipped, right? That it's hard to make your man believe in something when this income depends on not believing in it. And frankly, we know a lot of these people and companies that they are just as concerned as anyone else. But if you're the ceo of a company, that's not something you want to go on record saying when you have silly journalists who are going to put a picture of a terminator robot when they quote you. So, so the issues are real, and the way I the way I think about what the issue is is basically, you know, the real choice we have is first of all our regulars to just dismiss this the risks and say, well, let's just go ahead and build machines that can do everything we can do better and cheaper. You know, let's just make yourselves up sleet as fast as possible. What could possibly go wrong? That's one attitude. The opposite attitude I think, is to say there is incredible potential. You know, let's think about what kind of future we're really, really excited about what are the shared goals that we can really aspire towards. And then let's think really hard on how about how we can actually get there. So start with, don't start thinking about the risks. Start thinking about the goals and then when you do that, then you can think about the obstacles you want to avoid, right? I often get students coming in right here into my office for career advice, always ask them this very question, where do you want to be in the future? If all she can say as well, maybe I'll have cancer, maybe I'll get run </s><s>[INST] over by trucks and obstacles instead of the [/INST] girl, she's just going to end up a hypochondriac paranoid, whereas if she comes in and fire in her eyes and it's like I want to be there and then we can talk about the obstacles and see how we can circumvent them facts. I think a much much healthier attitude and that's really well. And uh I feel it's very challenging to come up with a vision for the future which which we are unequivocally excited about. I'm not just talking now in the vague terms like, yeah, let's cure cancer. Fine. Talking about what kind of society do we want to create, what do we want it to mean to be human in the age of Ai in the age of a G. So if we can have this conversation broad inclusive conversation and gradually start converging towards some some future that with some direction at least that we want to stare towards right then then no will be much more motivated to constructively take on the obstacles and I think if I if I had if you make if I try to wrap this up in a more succinct way, I think, I think we can all agree already now that we should aspire to build G I but doesn't overpower us, but that empowers us. </s><s>[INST] And think of the many various ways that can do that, whether that's from my side of the world of autonomous vehicles, I I'm personally actually from the camp that believes that human level intelligence is required to to achieve something like vehicles that would actually be something we would enjoy using and being part of. So that's one example and certainly there's a lot of other types of robots and medicine and so on. So focusing on those and then and then coming up with the obstacles coming up with the ways that that can go wrong and solving those one at a [/INST] time. And just because you can build an autonomous vehicle, even if you could build one that would drive just fine without, you know, maybe there are some things in life that we would actually want to do ourselves right, Like for example, if you think of our society as a whole, there's something that we find very meaningful to do and that doesn't mean we have to stop doing them just because machines can do them better. You know, I'm not gonna stop playing tennis just they say someone build a tennis robot beat me, </s><s>[INST] people are still playing chess and even go, [/INST] yeah, and I in this in the near term, even some people are advocating basic income, replace jobs, but if you if the government is going to be willing to just hand out cash to people for doing nothing, then one should also seriously consider whether the government should also hire a lot more teachers and nurses and the kind of jobs which people often find great fulfillment in doing right, we get very tired of hearing politicians saying, oh we can't afford hiring more teachers, but we're going to maybe have basic income if we can have more, more serious research and thought into what gives meaning to our lives and the jobs give so much more than income, right? And then think about in the future. one of the roles, Yeah. What are the roles that we want to, how people continually stealing empowered by machines? </s><s>[INST] And I think sort of um I come from the Russia, from the Soviet Union and um I think for a lot of people in the 20th century, going to the moon, going to space was an inspiring thing. I feel like the universe of the mind. So Ai understanding creating intelligence is that for the 21st century. So it's really surprising. And I've heard you mention this, it's really surprising to me both on the research funding side that it's not funded as greatly as it could be, but most importantly, on the politicians side that it's not part of the public discourse except in the killer bots terminator. Kind of view that people are not yet. I think perhaps excited by the possible positive future that we can build together. [/INST] So we should be because politicians usually just focus on the next election cycle, right? The single most important thing I feel we humans have learned in the entire history of science is there were the masters of underestimation, we underestimated the size of our cosmos again and again, realizing that everything we thought existed, there's just a small part of something grander, right? Planet, solar system, a galaxy, you know, clusters of Galaxies, universe and we now know that's we have, the future has just so much more potential than our ancestors could ever have dreamt of this cosmos. Imagine if all of earth was completely devoid of life except for Cambridge massachusetts. I would wouldn't it be kind of lame if all we ever aspired to was to stay in Cambridge massachusetts forever and then go extinct in one week. Even though earth was gonna continue on for longer than that, that sort of attitude. I think we have now on the cosmic scale we can life can flourish on earth, not for four years, but for billions of years. I can't even tell you about how to move it out of harm's way when the sun gets too hot and and then we have so much more resources out here which today maybe there are a lot of other planets with bacteria or cow like life on them. But most of this all this opportunity seems as far as we can tell to be largely dead, like the Sahara desert. And yet we have the opportunity that help life flourish without this billions of years. So like let's quit squabbling about when some little border should be drawn one mile to the left to right and look up the skies. You realize, hey, you know, we can do such incredible things. </s><s>[INST] Yeah. And that's I think why it's really exciting that yeah, you and others are connected with some of the working man mosque is doing because he's literally going out into that space, really exploring our universe. And it's wonderful. [/INST] That is exactly why Elon musk is so misunderstood, right? Misconstrue him as some kind of pessimistic dooms their, the reason he cares so much about AI safety is because he more than almost anyone else appreciates these amazing opportunities that will squander if we wipe out here on earth, we're not just going to wipe out the next generation for all generations. And this incredible opportunity that's out there and that would really be a waste an AI for people who think that they were better to do without technology. Well, let me just mention that if we don't improve our technology, the question isn't whether humanity is going to go extinct. Question is just whether we're gonna get taken out by the next big asteroid or the next super volcano or something else dumb, that we could easily prevent with more tech, right? And if we want life to flourish throughout the cosmos, aI is the key to it. Yeah. As I mentioned, a lot of detail in my book right there, even many of the most inspired sci fi writers, I feel have totally underestimated the opportunities for space travel, especially to other Galaxies, because they weren't thinking about the possibility of a G. I've, which just makes it so much easier, </s><s>[INST] Right? Yeah. So that that goes to your a view of a G. I. That enables our progress that enables a better life. So that's a beautiful that's a beautiful way to put it and something to strive for. So max. Thank you so much. Thank you for your time. Today has been awesome. [/INST] Thank you so much joy. </s> |
<s>[INST] and you you said that the way you're able to do that, you just have to do it right. What do you learn by doing all the steps along the way? And just for people who don't know cross collar choke from the mount. So just to start in a neutral place, there's people on their feet and then you either then you get to the ground somehow, and then there's a person on top and on bottom and then there's a guard with the legs between the two people and then you can get past the guard as you get past the guard and you uh into side control and so on, you get more and more and more dominant positions. And so amount is considered to be one of the most dominant positions. It's when you're past their legs sitting on top of their stomach, um putting pressure on them and cross collar chokers using their jacket to uh how would you explain that to call [/INST] us? I put my both hands on your callers and when I squeeze it, you press your neck so it blocks the venue you go to sleep. So it's a U. Two people with your hands in the wrist, you put them, you know, you grab the collars, you get the wrists around people's neck and you squeeze the </s><s>[INST] discovery of that is fascinating. I mean it's interesting. It's like um you know, you can imagine there's all kinds of ways to [/INST] choke a human </s><s>[INST] being. Uh what animals do it with their like [/INST] mouth right? </s><s>[INST] To put like their jaws around the and the fact that you can kind of discover this methodology of the right kind of positioning and then it becomes an art form like of why this why not this right or why not this or something like to figure out [/INST] over </s><s>[INST] time, you figure out what works and what not you. And then and then more further and further details and subtleties start to emerge anyway on that process of beating, of being able to beat some of the best people in the world and the thing they know is coming. What what's the difference between the white belt doing that and hydro gracie doing that? The thing that's so hard to explain. What do you think you're picking up? Is it some tiny tiny details of muscle movements? [/INST] It is its many tiny details because it is the whole movement itself is the perception from beginning to end, like every step of the movement. It's important and precise. So it's you know, you miss 11 detail on the way it collapse. So when I started with the black belt, the black belt has no control over the whole movement. He's thinking beginning and end. So he goes straight, you know, straight to the neck. Regardless. He cannot read the other person if it's you know, it's time to let go through the time to go for a neck. It should I be pushing here before I get my hand in, you know, Is is this the right time to go deep or should I deal with this first? Before the second hand? </s><s>[INST] That's at the beginning says that at the white [/INST] belt at </s><s>[INST] the very beginning of the journey? [/INST] The white belt, you just think </s><s>[INST] finish and then as you get progressed, you see that there's like this giant tree of possibilities that you're almost feeling your way down. I mean, would you be able to teach, do you even know what you're doing [/INST] by the details? Okay. </s><s>[INST] But it's hard to convert into words? Probably? Uh [/INST] no, that's possible then you don't know what you're doing? </s><s>[INST] Okay. Oh, so what is what is the most important details [/INST] that </s><s>[INST] you could say? Maybe positioning of the hands of the gripping? Is it the positioning of your body? The posture. Is there some interesting like inside [/INST] it's a it's a it's a combination because first you have to put your body in a very strong position that you don't require your hands to hold them out. So the joke is that that's first because I cannot I cannot use my hands on the floor to stop you escaping. Yeah. So if I have to, my body has to handle that the way I position myself, I have to do it in a way that don't require my hands for balance. </s><s>[INST] Okay why is the mouse that you down in a position doesn't make any sense right? Like you're just sitting on top of the stomach of a person. [/INST] That makes all sense. If you think what's, forgot, forget fighting, forget like you've never trained. What's the one position, the most dominant position you can get over another human being, one the most for you. Which one? It is like the most dominant position that you can get over another human being. </s><s>[INST] So if we were just, because the way I think about is putting myself in like a 678 year old self without knowing any martial arts and I had an older brother who would beat the sh out of me um Yeah it probably was Mount what? But well yes, okay so we both didn't know but if we knew something would probably be back control if [/INST] in the back control under the other person. The thing being under is the most dominant position that can be over another person. You </s><s>[INST] mean like a back control [/INST] if I'm on your back. </s><s>[INST] Oh like that. You can [/INST] move. You can roll. I cannot stop you rolling. Yeah maybe you can even stand up. How dominant is that? </s><s>[INST] Yeah, but if we're the same size, both untrained, [/INST] if that doesn't matter. </s> |
<s>[INST] based on, you know, the risk exposure and the posture there. Imagine being the first child, the first baby born outside of Earth. That'd be pretty cool. I would love to be alive to see that. That'll be a big one. I don't know if he'll, I don't know. Cause it's such a dangerous thing. [/INST] It's so risky. </s><s>[INST] I think that could be in our lifetime. [/INST] You think so? Yeah. I would like to think in a perfect world of our thinking futurism that in 30 to 50 years, I definitely think we could have a full time, like permanent major civilizations, you know, like what Blue Origin wants to develop where they have a huge like sphere, you know, and you're doing a lot of, especially heavy industry off of Earth, so you're not polluting Earth. Like that's makes so much sense to me. Yeah, I think we could live in a lifetime where, you know, we thought that since the 50s and 60s that people are gonna be living and working in space like crazy, and at any given point, we're lucky to have 12 people in space today. But I really think in our lifetime, we're finally getting to that point of, </s><s>[INST] yeah, that that's a reality. Let me, cause you mentioned Blue Origin. Can we just lay out some of the competitors to SpaceX? So much of what we talked about is SpaceX specifically because they're sort of pushing the boundaries of what's possible in the commercial space life. But there's a lot of, like you said, incredible work being done for large companies and small companies, startups and so on. So who are the competitors to SpaceX? A ULA, United Launch Alliance, Blue Origin, there's a Virgin, is it Galactic Orbit? Orbit would be the competitor. Virgin Orbit, there's Rocket Labs, Electron rocket that you mentioned. There's the folks that you covered, Firefly. Yep, yep. And what are we missing? There's the Epic Space Launch System from NASA, [/INST] I guess that is. Orbit would be the competitor. Yep, yep, yep. Technically NASA, but Prime Contractor Boeing and. Boeing, Lockheed, Lockheed. </s><s>[INST] Yeah, Lockheed. Lockheed. Lockheed. Yeah. Okay. Nice, so like what's interesting to say [/INST] to lay out the land here that you're excited about? Just in general, I think if you aren't working on a reusable, some form of reusable vehicle, like physically working on it, pen to paper, not beyond pen to paper, like bending metal for a reusable vehicle, you're gone, you're toast. I think we're well into that being the only provable way forward. The only way you're gonna compete and survive is a reusable rocket. Fully reusable would be great, but that's obviously massively aspirational still, but it will come. But to me, yeah, the list, you pretty much had it right on the head. There's Astra was another orbital rocket company. Yeah. They, there's a lot of companies. I think right now the ones that I personally really believe in, Rocket Lab is awesome. I really think that they are one of the few that I believe can actually build a Falcon 9 class rocket today with their technology, with their knowledge, with their investments, with their funding, and they've proven themselves. There's very few, they have actually made it look easy. I think there's a lot of startups and a lot of new rocket. There's too many launch providers popping out of the woodwork right now. They won't all survive, of course. I think realistically if you look at airplanes, how many airplane, there's a handful of airplane manufacturers. There's not hundreds and thousands of airplane manufacturers. I think it'll be a similar thing for spaceflight. I think we'll see, we'll see realistically in the terms of double jets and passengers, there's basically two. There's Airbus and there's Boeing. So I think in the long run there'll be two or three major players, I think there'll be 10 minor, as far as launch providers, as far as the ones actually leaving Earth and getting into orbit, I just don't think there's a ton of room for individuality, really. </s><s>[INST] Yeah, I would love to see a really serious competitor to SpaceX in the way that SpaceX does things. I don't know if you'll like, it's quite what I, [/INST] it's quite the right kind of competitor. I think, let me say this, ULA has all of the potential, but just operationally, they're either Lockheed Martin and Boeing's Love Child, they're kind of set up in a far too traditional manner where they just really aren't given the opportunity </s><s>[INST] to innovate like a lot of the manor startups are. So Rocket Lab is a little bit more of that nature. What do you think about just Blue Origin in general? [/INST] The Origins? What do you think about? What do you think? The Origins? What Blue Origin has done with New Shepard is amazing and people just lot it because it's suborbital and it looks very phallic. So I guess the meme matters also, it's modern day. But it's sad because people don't see what they are also working on, which is New Glenn. I see comments almost every day still of like, it doesn't matter because they're working on tiny, it's like, no, New Glenn is more powerful and more capable than Falcon Heavy. New Glenn is almost more of a competitor to, not quite as to Starship, but it's almost in that class. It's a heavy lift launch vehicle, it's huge, it's crazy. It'll be nuts, they're very actively working on it. I still think we're three years away from it launching, but that's a very strong competitor in the class of rockets that SpaceX is currently making. </s><s>[INST] So SpaceX is currently leading the way, [/INST] but it couldn't become a close race. For now we'll ignore SpaceX and we'll just talk about, I think who's kind of coming around the corner here. So let me just do a quick overview. I'm gonna shoot myself in the foot for getting some cool people here and some exciting companies. But Relativity is one that you should definitely get Tim Ellis on the show, who is the CEO of Relativity. They're doing 3D printed rockets. They're the ones that have the world's largest 3D printer. They're getting really close to their first orbital launch. The cool thing about them, the reason that I think they're exciting, the reason that I think they have the potential is just how quickly they can iterate. I think 3D printing a rocket is really dumb. I think iterating with 3D printing on a rocket is brilliant because you can literally change software and have very little, upload a file and have a new rocket. That's amazing. So in terms of long-term iterative process, if we're really talking about hitting the ground running and just seeing where the evolution takes you, I think that's about as good as you can get. I think what SpaceX is doing at Starbase just physically bending cheap steel is probably also a very valid solution. So I really think, and they have the engineering chops. I think they've got some amazing people there. Again, Rocket Lab, I adore what they work on. And like everyone, there's a caveat here that everything takes longer. Anything, any company tells you it's two or three times longer, just period. Rocket Lab's no different. But I really, they're working on a neutron rocket that's gonna be like, I think 8,000 to 15,000 kilograms to lower the orbit. Like it's a good medium-class rocket, will compete right along with Falcon 9, hopefully. </s> |
<s>[INST] It's not included for the quality of life and the majority of the population. [/INST] Yes that's something like that happen without problems. Of course not. And so the next person to do something just actually gets to learn from lessons from lessons that's all leapfrogged and leapfrogged. Exactly. So for me this is a promise and people are like oh but you guys are crazy but I'm like just like with everything, do you know how many attempts it took before the first flight of the Wright Brothers took off. Do you know how many and that's important. You you try, you crash, you try, you crash but each time you're going higher up higher and you want to get up for once then you stay up longer and before you know it you're doing all types of things. So here's the same thing. I tell people listen, all I need is one success story and then we see change. People don't even wait for us everybody. But this is hard because it's the first time. So, but the good news is there are many groups working on the continent, There are some, some groups in Zambia, there is a zone, there folks are doing something like this in Nigeria were part of a project there in Nigeria. Um the one that I'm most excited about, I cannot disclose the name of the country yet, but my God, I'm so excited by it and I just know, I just know lex it's going to happen in our lifetime. </s><s>[INST] I hope so. It's a really powerful vision and you know, it's not being dramatic to say that the future of humanity depends on this, that your success, that success in Africa, it's such an important continent. [/INST] It is </s><s>[INST] a century. It's the [/INST] continent where everything started and I think it's the continent where we have, that continent has to finally finally finally thrive. We cannot all of us call ourselves um an enlightened society as a whole. When you have such, when you have this, it's a humongous continent. Have you seen the size of it? You know? </s><s>[INST] Yeah, it's it's it's hard to fathom actually forget [/INST] exactly. And it has such ingenious people. You know, sometimes I look at my people, I have to tell you, I'm so proud of them and the young people especially and you know, he would look at them and you know, somebody said sometimes one day and it was so true. They said, you know, we've seen poverty other places. but here it is just maybe somebody doesn't have money, but they have dignity and it's </s><s>[INST] true. [/INST] So everything else we can handle and we will handle. You have to mark my word for this, this is gonna happen and our youth is amazing. You should see them so full of creativity and it doesn't matter. You know, you were telling me what makes you different, many things makes us all different. You know, Rondon's are very different from the west Africans that we are. Um Rondon's for example, never dance with the hips, dance more like, you know, with, with this part of the body um us, it's hips all over the place all the time and it's, you know, more jumping stuff like that in Rwanda. You feel it's more like, you know, I mean they remind me more of, you know, the ballet thing. Um Rondon's have a sense where you know, they don't eat, you know, most so much in public. It's not very well. It's something you do. Um as we have the west Africans, we like to be loud, we're almost like the Italians of the continent and then there ones are more like, you know the swiss of active country even looks like Switzerland. I mean we're so different from one group to another. Then you go to the congo and you see these guys are so crazy, we have a dress, I mean, so we are a very different bunch. Um but you know what I love about us, what I love about my people, we are we are we we have a manifestation of what resiliency means. And so everything we need, is there everything we need is there I will say that there's nothing wrong with the seed, Everything that's wrong with us is that pot that we put around us? So we're tired of being bonsai people, we need to be the tallest trees in the forest that we were designed to be. And so </s><s>[INST] and that can be fixed [/INST] and that can be fixed. And that's the beauty of it. And that's why I am so I'm almost dizzy with, I get dizzy with uh with hope. I know my history, I know my economics, my fellow humans and all of that. And we know that there's an unfailing recipe and when it comes to that recipe, we have the hardest part of it. The one missing ingredient which is our free markets as we go around and talk and people start to understand and each country tries to figure out, okay where do we go there from here? I I know that I will die with my continent having taken </s><s>[INST] the right [/INST] shift for a turn. I don't have to see where it ends because I cannot in my wildest dream imagine where it's gonna end. But I know it's gonna be. Yeah. So all my only job is to get this message out and then let my people do with it what they want to do. That </s><s>[INST] scale of impact is just boundless. It's kind of cool. I mean, you know, sometimes we think about individual problems and how do we solve them? We look up to certain individuals like the, I don't know, steve jobs and musk, [/INST] but </s><s>[INST] it's so much more powerful to, just without knowing what they will do, [/INST] Give </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] what was the visibility conditions when in the times when people were able to see it? And then we, we just earlier discussed complete nighttime darkness um in this case was was it during the day? [/INST] It was a perfectly clear day that that that particular incident </s><s>[INST] in a world that's full of mystery. I have to ask, what do you think is the possibility that it's not of this earth origin? [/INST] I like the term non human intelligence in a sense because again, there's so much, there's a lot of assumptions in there that may cause us to go down the wrong roads. It could, you know, this could be something that our weather phenomena of Earth, right or something else. That is just something we don't understand and can't imagine right now that's still of this earth. Um if we consider extraterrestrials or something that came from a physical place far away in space time. Um, you know, that leads us to some detection assumptions that we would need to make. And so I just try to not categorize it under anything and just say, hey, is this demonstrating intelligence and start from there as a single object, what can we learn about it can dramatically how it's performing, What does that mean for its energy source, what does that mean for the g forces inside and then step it out A. Level and say okay how are these interacting with our fighters? If they are how are they interacting with the weather and their environment? How are they interacting with each other? So can we look at these and how they're interacting perhaps as a swarm, especially off the East Coast where that's happening all the time with multiple objects? Right. And so we might be able to determine some things about there. Maybe you know, center capabilities or the areas of focus, you know, if we can determine how they're working in conjunction with each other. But you know, seeing one little flash of an object doesn't provide that type of insight. Um but we have the systems for but and it's kind of an irony but it's it's a fact of life the reality that many of these well deployed, highly capable systems are held under the military umbrella, which makes it difficult to provide that data for scientific analysis. </s><s>[INST] So there's probably a lot more data on these objects that's not being that's not made available probably even within the military for analysis. I [/INST] think so yeah. I think there's a lot of data that could be made available and you know, that's one of the reasons why you know, I've been engaged with the american Institute of aeronautics and astronautics to build, you know a large resources of cross domain expertise so that if for when that data is available or that there's additional analysis needed. You know, we can spin up those teams and make that analysis. </s><s>[INST] So there was a recently house intelligence subcommittee hearing on UFOs that you were part of what was the goal of that hearing. And can you maybe summarize what you heard [/INST] the hearings from my perspective seemed a bit disingenuous, kind of top level I think. Um </s><s>[INST] who was run by, sorry to interrupt like who were the people involved and what was the goal, the stated goal [/INST] congressman andre Carson uh the chair of the committee. And he he was I think ultimately responsible for bringing it all together. You know, I think the intent from Congress was to try to bring light to what has been happening with the navy and to help show the american people that um Congress is taking this serious because something serious is happening. But you know, the sense I got seemed a bit disingenuous, they talked around it a lot. They you know, advertised their um their love of science fiction. Um but they you know, they didn't treat this, I would say in the manner it deserved as a potential tactical threat if it's coming from a foreign power. Um And I get it though at the same day they have very specific objectives within the D. O. D right? They have a very important job job isn't necessarily to do exploratory science for no reason. Um So I I applaud and I encourage their efforts on the intelligence side to help understand this. Um But my concern is that they play a role they're not well suited for which is is doing science. </s><s>[INST] And the pentagon has opened a new office to investigate UFOs called all domain anomaly resolution office. What do you think about this office? Do you think it can help alleviate in a way which this hearing perhaps has failed to improve more of the scientific rigor and the seriousness of investigating UFOs? I [/INST] think that remains to be seen. I think it's a step in the right direction but it's a step that was taken because the previous step didn't happen. Right? So um the A. I. M. S. G. Was the progeny essentially of the A. R. O. Or arrow. And you know the name was changed because nothing was happening and it was essentially just a confusing mess of words that were created to make this topic unpalatable. Um The airborne object identification synchronization management group, quite a mouthful. I practice that. But the new all domain anomaly resolution office, you know from my perspective at least at least the perspective that they're putting out. They they seem to want to be open, they put out a twitter handle there, they're going out on twitter and communicating saying they want to keep this open. Um But you know that's going to run into a classification wall. </s><s>[INST] Well, so uh dr Sean kirkpatrick seems like an interesting guy. [/INST] He does, yes. </s> |
<s>[INST] or how science actually works. Yeah, but how do you even begin to seriously think about the origin of life? I mean, every problem of existence of life has its time. So I don't know if it's time to understand consciousness yet. We might be a hundred years away from that. The origin of life, I don't know if it's time for us to understand that yet. Maybe we need to solve so many more problems along the way. [/INST] And so- It's not a competition of problems, right? So there are all kinds of problems and it takes a lot of people to make the world. So you will always have some interesting brain going after an interesting problem to their own. The issue here is that we need to first of all, understand that what we have going on on this planet is pretty good. Good planets are hard to find. If we are alone in the universe, that's huge. We need to take care of what we got here. And we are incredibly vulnerable to the changes that our own species also helped create at the biosphere, at the ecosystem level. We take it for granted. We take what we created for granted because of the fact that we think we are some sort of ultimate endpoint, the most sophisticated, amazing thing </s><s>[INST] that nature could generate. [/INST] I think understanding, not even understanding, but asking these questions of where did this even come from? How did this even begin? And attempting to understand that using chemistry and physics and biology, and because we can, that's the ultimate gift we can give back </s><s>[INST] to the entire species on this planet. Yeah, I mean, it's humbling. It's humbling to realize the complexity of this whole mechanism. It certainly puts humans in their proper perspective that we're not, just because we have brains and brains are intelligent, doesn't mean we're the most intelligent thing because ultimately the whole mechanism of nature seems to be orders of magnitude more intelligent. All of it, like we're a bunch, we're like a hierarchy of organisms that have a history of several billion years. And that all somehow came together to make a human. And there'll be life after us, just as was life before us. And something that comes after will be perhaps even more fascinating. [/INST] I think when you understand the magnitude of what happened here, there is no room for arrogance. It should overwhelm you and humiliate. It's pretty humiliating. Yeah. You know, it's quite amazing what happened here. And there is no other discipline that will deliver that, but exploring our own origins and looking at life as a more planetary system phenomena rather than one single species at a time, </s><s>[INST] a collective look, you know? You mentioned this question in your TED Talk is the two possibilities of the universe being full of life and the universe being empty and we're the only life in the universe. How do you feel about both options? Just actually you as a single chemical organism [/INST] introspecting about its existence in this world. Having a planet full of life is interesting because there are, we talked about life being all about chemistry exploring solutions and having solutions in front of you is great. </s><s>[INST] It's beneficial, right. Solutions being different organisms like other humans. You see them as a solution to a chemistry problem. That's an interesting solution next time. We're in Austin. There's a bunch of weirdos. Every time I see a weirdo, I'd be like, Oh, that's an interesting solution to this chemistry problem. [/INST] Now you think like an origin of life science. Now you think like an origin of life science. </s><s>[INST] But it's funny that that one worked out. [/INST] Let's see where else it goes. See where else it goes. But having this emptiness and unpredictability of uncovering a novel solution can also have its own benefits. And we should be open to what other solutions might </s><s>[INST] be out there and exploring those solutions. Or to different chemistry problems. So that's what you see. You see the other planets out there [/INST] as different chemistry problems. </s><s>[INST] To their own local environment, yes. So how many chemistry problems have solutions [/INST] that are lifelike to you out there in the universe? It's a wide open palette, if you think about it. I don't quite know. It's the, we know the chemistry is chemistry. I don't think the chemistry will be different elsewhere. But again, what is selected by chemistry will be determined by the environment most likely. </s><s>[INST] See, I think there is life everywhere out there. So there's a guy named Nick Lane who's gut, and it's interesting to me. I wonder what you think about it is. His gut is, there's life everywhere out there, but it stops at like the bacteria stage. So he says the eukaryotes is like the biggest invention and the hardest one. [/INST] I wonder if he thinks that's an accidental outcome. If he thinks that's inevitable, I wonder what that means. But it's a likely possibility that the, the bacterial or microbial life is definitely more attainable. </s><s>[INST] So that's a weird world where our entire galaxy [/INST] just says bacteria everywhere. But our- Bacteria everywhere. So, you know, if you don't like microbes, </s><s>[INST] you aren't on the wrong planet. No, I know. Yeah, and viruses. I don't know which one there's more of, [/INST] but they're both, and most of them are like productive. They're fascinating. </s><s>[INST] They do everything for us. Like microbes, you're on the wrong planet. You're full of good lines. Okay, right, right. I just can't. There's like an imperative to the whole thing. To me, the origin is the hard question. But once it gets going, I just don't see the- Wait, go ahead. It seems like it's constantly creating [/INST] more intelligent things. </s><s>[INST] The way- More fascinating, complex things. They're able to solve- That's a very- [/INST] That's a very- That's a very interesting, like that's- I definitely agree that the initial steps may be the ultimate determinants. That once it's- You cannot stop it once it starts. It's possible, right? </s> |
<s>[INST] um, it's funny because I wish there was a feedback signal because he probably to put a positive spin on it. He probably didn't realize the negative impact he's had at that moment, right? If he only knew, see this is probably when you're more mature and grad school had an amazing professor named Ali Shaka fondi in computer science and he would get you encourage questions, but then he would tell everybody how dumb their questions are. But it was, it was done. I guess if you show if you say it with love and respect behind it, then it's more like a friendly humorous encouragement for more questions. It's an art, right? That too, right? And it's very hard. You have to time it, right? Because that's probably that kind of humor is probably better for when you're in grad school versus when you're in the early education, right? [/INST] Well, and I guess kids or young people get whether somebody's doing it to be funny or you know, has it? I mean, this is why I teach you so hard, even your tone can be impactful. </s><s>[INST] It's so sad because like uh for that particular human, the teacher, you just had a bad day in one statement can have a profound negative impact. [/INST] I know sadly that maths there's a lot of maths teachers who have that kind of approach and they I think they're suffering from the fact that they think people are math people not math people and that comes across in their teaching. </s><s>[INST] But on the flip side one positive statement keep them going. [/INST] That's right, that is the flip side of that. And I myself had one teacher who was really amazing for me in maths and she kept me in the subject. </s><s>[INST] What who was she? She [/INST] was, her name was mrs marshall. Yeah Um she was my a. Level maths teachers. So I was in in England you do lots of subjects to your 16 and then you choose like three or 4 subjects. So I had chosen maths and you go to high levels probably equivalent more to a master's degree in the U. S. Because you have more specialist. But anyways she was my teacher and for the first time in my whole career in maths she would give us problems and tell us to talk about them with each other. And so here I was sitting there like 17, talking with friends about how to solve a mouth problem and that was it. That was the change that she made. But it was profound for me I because like those calculus students, I started to hear other people's ways of thinking and seeing it, we would talk together and come up with solutions and I was like that was it, that changed math for me. So </s><s>[INST] it wasn't some kind of personal interaction with her, it was more like she uh she was the catalyst for that collaborative experience. [/INST] I mean, yeah, the many ways teachers can inspire kids, I mean sometimes it's a personal message, but it can be your teaching approach that changes maths for kids, </s><s>[INST] you know, cal Newport, he uh he wrote a book called Deep Work and he's a mathematician because theoretical computer scientist and he talks about the kind of the focus required to do that kind of work. Is there something you can comment on? You know, we live in a world full of distractions that that seems like one of the elements that make studying and especially the studying of subjects that require thinking like math does difficult. Is there something from a student perspective from a teacher perspective that encourages deep work? You can come [/INST] Yeah, I think giving kids really inspiring deep problems and we have some on our website is a really important experience for them, um even if they only do it occasionally, but it's really important that they actually realize I I do give a problem out off, I'm gonna working with teachers and I say to them all right, I'm going to check in with you after an hour and they were like an hour, they think it's shocking. And then they work on this problem and after an hour I said, okay, how are we doing there? Like an hour has gone by, </s><s>[INST] how [/INST] is this possible? And so everybody needs those rich, deep problems. Most kids go through their whole maths experience of however many years, never once working on a problem in that kind of deep way. So I, the undergrad class I teach at stanford, we do that, we work on these deep problems every session and the students come away going, okay, I never want to go back to that mouths relationship I had where it was just all about quick answers. I I just don't want to go back to that. And so we can all, all teachers can incorporate those problems in their classrooms, maybe they don't do them every day, but they at least give kids some experience of being able to work slowly and deeply and to go to deeper places and not Be told they've got five minutes to finish 20 questions. </s> |
<s>[INST] So you're saying that uh that's almost like at least uh centralization, [/INST] right? It started being decentralized and but of expenses becomes higher and higher and higher when the cost becomes higher and I are fewer and fewer people can afford them and then you know, it becomes, you know, de facto centralist, right? And uh in a different type of approach is instead for instance a delegated proof of stake which is also very easy to explain, essentially boils down to, to say, well look at these 21 people say, okay, don't they look honest? Yes, they do. In fact, I believe if they're going to remain honest for the foreseeable future. So when do we do ourselves a favor? Let's entrust them to add the page on behalf of all of us to the ledger. Okay, Okay. But now we are going to say is this centralized or decentralized? Well, 21 is better than one what to say? It's very little. So if you look at uh When people were belt to centralize power, I don't know the French Revolution's okay, there was a monarch and venables uh were there 21 nobles now there were thousands of them, but there were millions and millions of disempowered citizens. So one is centralised. is also centralized </s><s>[INST] so that's delegated proof of stake, delegated kind of representative democracy I guess. [/INST] Yes, which is good. Working great, right? That's working great well, it's better than uh Right. And uh but </s><s>[INST] uh there's there's problems, [/INST] they got problems and uh and so um uh we were looking for a different uh when thinking about al gore and forgot for a different approach. And so we have a man approaching veteran is really really decentralized because essentially uh it works as follows. So you have a bunch of tokens, right? These are the tokens That have equal power and you have to say 10 billions of tokens distributed uh not to the entire world. And the owners each talkin as a chance to add Villager equal probability of everybody else fun. In fact actually if you want here is how he works. So think about and all by some magic pro graphic process, which is not magic is mathematics. But think of it, the magic assume that You select 1000 tokens. And so sometimes a random. Okay. And you have a guarantee that were randomly selected and then The the owners of his 1000 tokens somehow agree on the next page. We all sign it. And that's my next speech. Okay, so it is clear that you know, nobody has the power but uh once uh in a while, one of your tokens is selected and you are in charge of this committee to select the next page. But this goes around very quickly. So, and if you look at this, the question really is that is not really centralist and because of what for for agreeing on the same page, it is important of it. They 1000 tokens that you're randomly selected are in honest ends. The majority of them. So which is the majority of the tokens are in understands what is essentially true because if the majority of the tokens are in understands, if you select uh say 90% of the people are 90% of the tokens are in understands. So can you randomly select 1000 in this 1000 you find the 501 tokens in bad ends very, very </s><s>[INST] improbable. So basically when a large fraction of people are honest and you can use randomness as a powerful tool to get decentralization. So what does honesty mean? And uh now we're into the social side of things which is uh how do we know that like the fraction the large fraction of people are participating parties are honest. [/INST] That's an excellent question. So by the way, first of all, we should realize that the same thing is for every other system when you look at put for work, you realize that the majority of the mining power is in honest hands. When you look at a delegated proof of stake, You realize that the majority of the 21 people are honest, what is the difference? The difference is veta in with other systems used to say they all economy is secure if a majority of this small piece of economy are honest and that is a big question. But instead, what in algorithm and our approach we say the all economies secure if the majority of economy is honest, in other words, who can subvert? Al Grant is not a majority of a small group, but it is a majority of the talk and holders I to conspire with each other in order to think the very economy for which they own the majority of. Yes, I think it is a bit harder </s><s>[INST] to like a self destructive majority essentially. And you're also making me realize that basically every system that we have in the world today assumes that the majority of participants is honest. [/INST] Yes. The only difference is the majority of whom and in some cases the majority of a club and in our case is the majority of the old system, </s><s>[INST] the whole the whole system. Okay, so that's that fatso threw that kind of random sampling you can achieve decentralization, you can achieve. So the scalability I understand and then the security that you're referring to basically the security comes from the fact that the sample selected would likely include honest people. So it's very difficult to. So by the way the security as you, as you mentioned that you're referring to is basically security against dishonesty or manipulation or whatever. Yes, [/INST] Yes. So essentially when what you're going to do is to be falling and so you say, well Sylvia understood what you're saying, but somebody has to randomly selected with slogans when I believe you. So then who does this random selection and uh, uh, algorithm we do something a little bit unorthodox essentially. Is that talking choose themselves at random? And you say, if you think about it, that seems to be a terrible idea because if you want to say choose yourself at random and whoever chooses themselves is a fashion people committee, you choose the page for uh, for the rest of us. And because if I'm a bad person, I'm going to select myself over and over again because I want to be part of the committee every single time, but not so fast. So what do we do in our gun? What does it mean that I select myself with each one of us in the privacy of our own computer. Actually laptop. What do you do is that you execute your own individual lottery. And uh think about it that you pull a lever of a slot machine. You can only pull the lever once. Not until you win. Not enough times until you win. And when you pull the lever case one even if you win in such a case you have a winning ticket or you lose, you don't get any winning ticket. So if you don't ever winning ticket, you can say anything you want about the next page and village, nobody pays attention. But if you ever win a ticket, People say, Oh wow, this is one of the 1000 winning tickets. We better pay attention to what he or she says and that's how he works. And Valerie is a cryptographic lauder, which means that even if I am an entire nation, extremely powerful with incredible computing powers, I don't have the ability to improve even minimally. My probability of one of my talking, winning the lottery and that's how it happens. So everybody pulls the lever, The 1000 random winners say, Oh here is my winning ticket and here is my opinion. Up or down about the block. These are the ones that count. And if you think about it while vases distributed because there is the case of arrogant, there is 10 billion tokens and you select 1000 of them more distributed, invest you cannot get. And then why is this? You know, scalable? Because what you have to do, okay, you have to do the lottery. How long the lottery takes it takes Actually one microsecond, whether you have one talking or two tokens or a billion tokens is always one microsecond of competition, which it's very fast. We don't hit the planet with microsecond of computation and finally why is it secure because even if I wear a very evil and very very powerful individual, I'm so powerful but I can corrupt anybody. I want east antennas in the world. Who would I want to corrupt the people in the committee so that I can choose the page of village. But I do have a problem. I do not know whom I should corrupt. Should I go up to this lady in shanghai was our guy in paris because I don't know the winners are random so I don't know whom I should cook up. But once we have a winner come forward and say here's my winning ticket and you propagate your winning ticket across the network together with your opinion about the block. Now I know who they are for sure I can corrupt all fast. One of them given to my incredible powers but so what whatever they said they already said in their winning tickets and very opinions are virally propagated across the network. And I do not have the power no more than the U. S. Government or any government has the power to put back in the bottle a message very easily propagated by wikileaks. </s> |
<s>[INST] and humans are unique. So, so the animals are robots essentially in the formulation of the cart and humans are unique. Yeah. So in which way would you say humans are unique vs even our closest ancestors? Like is there something special about humans? What is in your view under the panpsychism? I guess we're walking backwards because we'll have the big picture conversation about what is panpsychism. But given your kind of broad theory of consciousness what's unique about humans do you think [/INST] as a pants I kissed there is a great continuity between humans and the rest of the universe. There's nothing that special about human consciousness. It's just a highly evolved form of what exists throughout the universe. So so we're very much continuous with the rest of the physical universe. What is unique about human beings? I suppose the capacity to reflect on our conscious experience um plan for the future. Um The capacity I would say to respond to reasons as well. I </s><s>[INST] mean [/INST] animals in some sense have motivations but when a human being makes a decision they're responding to what philosophers called normative considerations. You know if you think should I take this job in the US you weigh it up. You say well you know I'll get more money I'll have maybe a better quality of life. But if I stay in the U. K. I'll be closer to family and you weigh up these considerations. I'm not sure um any non human animals quite respond to considerations of value in that way. I mean I might be reflecting here that I'm something of an objectivist about value? I think there are objective facts about what we have reason to do and what we have reason to believe </s><s>[INST] that humans have access to those [/INST] humans have access to them and can respond. That's a controversial claim. You know, many of my pants like his brethren might not. </s><s>[INST] They would say the hamster to can look up to the stars and ponder theoretical physics, [/INST] maybe not, but I think it depends what you think about value. If you have a more humane picture of value by which I mean, relating to the philosopher David hume who said the reason is the slave of the passions, really we just have motivations and what we have. Reason to do arises from our motivations. I'm not a human and I think there are objective facts about what we have reason to do and I think we have access to them. I don't think any non human animal has access to objective facts about what they have reason to do, what they have reason to believe. They don't weigh up evidence. The </s><s>[INST] reason is a slave of the passions. [/INST] That was David hume's view. Yeah, I mean, yeah, you want to know my problem with humans. I had a radical conversion. This is might not be connected is not connected to panpsychism, but I had a I had a radical conversion. I used to have a more humane view when I was a graduate student, but I was persuaded by some professors at the University of Reading where I was that if you have the humane view, you have to say any basic life goals are </s><s>[INST] equal [/INST] equally valid. So for example, let's take someone who's basic goal in life is counting blades of grass, right? And crucially they don't enjoy it, right? This is the crucial, but they get no pleasure from it. That's just their basic goal to spend their life counting as many blades of grass as possible, not for some greater goal. That's just their basic goal. I want to say that that is objectively stupid. That is objectively pointless. I shouldn't say stupid movies objectively pointless. Uh, in a way that pursuing pleasure or pursuing someone else's pleasure or pursuing scientific inquiry is not pointless. As soon as you make that admission, you're not a follower of David hume anymore. You think there are objective facts about what goals are worth pursuing? </s><s>[INST] Is it possible to have a goal without pleasure? So this kind of idea that you just joined the two? So the David Foster Wallace idea of, you know, the key to life is to be unbearable. Isn't it possible to discover the pleasure in everything in life? The counting of the blades of grass. Once you see the mastery, the skill of it, you can discover the pleasure. Therefore, you know, um, I guess what I'm asking is why and when and how did you lose the romance in grad school of [/INST] like, </s><s>[INST] is that what you're trying to [/INST] say? I </s><s>[INST] think it [/INST] may or may not be true that it's possible to find pleasure in everything, but I think it's also true that people don't act solely for pleasure and they certainly don't act solely for their own pleasure. People will suffer for things they think are worthwhile. I might, you know, I might suffer for some scientific cause for um finding out a cure for the pandemic or um and in terms of my own pleasure, I might have less pleasure in doing that. But I think it's worthwhile. It's a worthwhile thing to do. I don't, I just don't think it's the case that everything we do is is rooted in maximizing our own pleasure. I don't think that's even psychologically plausible </s> |
<s>[INST] of mixed martial arts. Well that's why the thing is the mixed martial arts isn't just the performance, the strictly who won, who lost. It's also the stories we tell ourselves and so I mean there's beautiful stories being weaved and that also is part of who is the greatest of all time, is what, what were the battles? Well what had to be overcome, what was the the flavor of the flawless performances, you know, all of that plays into it and you're right being able to walk away at the top is also part of that. [/INST] A lot of people ask me about Habib and that fight I wanted to happen. Kabob wanted to happen but um she did not want to happen between you and can be yes and we tried to make it like about three years ago when I when I retired two and three now it was after two years ago and they didn't never came to fruition. The UFC were clear, they said they have at their plan for cab and it makes sense to for the business standpoint because they want to keep the ball rolling now can be retired and like everybody else after just Justin Gayatri, I was doing the commentator in french or do you see and a butterfly. I thought he was going to call me out. If there's one guy that I would have said yes, it would be him because for a fighter the most exciting thing things to do, it's often the scariest one and cabbage was, you know, works the scariest matchup. Yes, it was worth the risk because nobody has ever been able to solve </s><s>[INST] them. How would you solve the could be normative amount of puzzle? [/INST] Well cab is very good against the fence. Uh, I would have to establish a game plan and everything, but I think what I would need it to do is take the center of the octagon right away. Use a lot of fake and faith keep the fight all the way all the way out or all the wind and when I sell the wind is when you close the gap, use my proactive and reactive take down and perhaps my superhero explosive to to put him down. I like to use those proactive and reactive techno because for me, I feel it's more economical, okay baby is a much better chain wrestler than me chinaware stories when you got the guys to the fence, it's pure racing. What makes my takedown very efficient, It's my karate, it's not my wrestling, it's I'm a, I'm very good at timing my opponent and getting in with my explosive itty. So if you watch my takedown, it does not demand often, it does not demand a lot of work when I use the, I call it proactive takedown when um, he's coming to punch me and I react. So, I mean productivity when I'm faking it. So I instigate the takedown by a fake, then I take him down. And reactive as one is, I'm baiting him to throw something that </s><s>[INST] you don't have his account. [/INST] Yes, </s><s>[INST] but all my take down in the center of the octagon. [/INST] Yes, My takedowns are more in the center of the octagon. Like for example, another guy that does it well is Gleason to bow that did it well in his best days, you know, Kabila is more a style of chain wrestling. I would say like Cameroon Guzman's or so to speak, kinda kind of guy. It's a different style. You cannot compare boats town and that's the kind of takedown. I'm good and I would, if I would have fight club, that's one of the strategy I would have that I wouldn't have been afraid because everybody that I thought I was able to put them down and, and I have the pedigree to prove it in my fight resume. So we would have perhaps him on his back and I would have perhaps being my back as well. So it would have been a very </s><s>[INST] interesting fight and how hard do you think he used to take down. I mean, a lot of people speak about his wrestling being just [/INST] has nothing to do with the wrestling because it's to do with the car. If I got that timing and I got my boat hand around around his knees is going down. Everybody </s><s>[INST] goes down. [/INST] Yes, yes. This goes down. And I had a lot of that. That's what I would have to adopt. I would not have been afraid of his wrestling. I would have been the instigator. I would have forced the fight forward and that's what, that's how it would have approached that fight, which I believe most of his opponent we're afraid of is resting because they didn't have the tools that I have to put him down. I would not have forced the wrestling. I would have in, in the clinch, I would have tried to disengage. I have many ways to disengage the clinch. I would have want to force the fight in, in a, in a fighting distance, you know, like in a shoebox distance, not in a wrestling distance. </s><s>[INST] Is it possible this fight still happens? You're young, look great in the suit. [/INST] Well, there's a lot of problems now. And the thing is now I made peace with it. I no longer don't want to fight and I don't, it's not gonna happen. You have seen was not interested and I'm bound by contract with the UFC and by exclusivity, there's some people's systems. So how about if Russians are crazy, uh, wealthy Russian guy come with, I think I'm going to be, uh, in court with, you see, and, and also I'm older now and when I go home and I'm like, I don't want to do this, you know, like you will always like this, I don't want to do this. But like for example, I was training with Freddie roach a few days ago and I'm hitting pads, you know, and Freddy is looking at me and he's like, you have the hitch back. I'm like, yeah, if dana white would walk in the room in the, in the gym at that precise moment with the UFC can track, I would sign it, sign it in the blink of an eye. But then after I go home, I'm like, hell no, my belly is full. My, I'm healthy, I'm wealthy, why would I want to fight for? I made peace with it. But the minute I go back in the gym, because I still get it inside me when I trained with the young guys, I still get it. And a lot of guys thinks, hey, tell me the truth, you're preparing a comeback because I still get it. You know, I'm a little bit older, but I, I got more knowledge, I can compensate, I become a different animal because you know, it changed you, but then after you go home </s> |
<s>[INST] They educate and inspire hundreds of thousands of students and over 110 countries and of a perfect rating on charity navigator. Which means that donated money is used to maximum effectiveness. When you get cash up from the app store or google play and use code lex podcast, you'll get $10 in. Cash up, will also donate $10 to first which again is an organization that I've personally seen inspire girls and boys to dream of engineering a better world. And now here's my conversation with Donald Knuth 1957 at Case Tech. You were once allowed to spend several evenings with IBM 6 50 computer as you've talked about in the past and you fell in love with computing. Then can you take me back to that moment with the IBM 6 50? What was it that grabbed you about that computer? [/INST] So the IBM 650 was this this machine that well it didn't fill a room but it was it was big and noisy but when I first saw it it was through a window and there were just a lot of lights flashing on it. And uh I was a freshman. I had a job with the statistics group and I was supposed to punch cards and uh for data and then sort them on another machine. But then they got this new computer came in and and uh it had uh interesting like lights okay so well but I had a kind of key to the building so I can you know I could get in and look at it and got a manual for it. And and uh my first experience was based on the fact that I could punch cards basically one big thing for the but the time is 6 50 was uh you know big in size but uh incredibly small in power uh in memory it had it had 2000 Words of memory and the word of memory was 10 decimal digits plus a sign. And it would do Add two numbers together. You could probably expect that would take I'll say three milliseconds. So pretty </s><s>[INST] fast it's the memories, the constraint the memories. The problem that was why it was, it took [/INST] three milliseconds because it took five milliseconds for the drum to go around and you had to wait, I don't know five Cycle times. If you have an instruction uh one position on the drum then it would be ready to read the data for the instruction. And uh you know three notches, the drum is 50 cycles around and you go three cycles and you can get the data and then you can go another three cycles and get and get to your next instruction If the instructions there otherwise otherwise you spend until you get to the right place. And and we had no uh random access memory whatsoever. Until my senior year senior year we got 50 words of random access memory which were which were priceless and we would we would move stuff up to the up to the random access memory In 60 word chunks and then we would start again. So 17 1 to go up there. And could you </s><s>[INST] Have predicted the future 60 years later of computing from then? [/INST] You know? In fact the hardest question I've ever asked was uh what could I have predicted? In other words the interviewer asked me, she said you know uh what about computing has surprised you, you know and immediately ran rattled off a couple of dozen things and then she said okay so what didn't surprise and I was I tried for five minutes to think of something that I that I would have predicted and I and I and I couldn't but let me say that this machine I didn't know. Well there wasn't there wasn't much else in the world at that time. The 650 was the first Machine that was that there were more than 1000 of ever before. That there were you know there was each machine there might be a half a dozen examples maybe </s><s>[INST] maybe they produced the [/INST] 1st 1. Yeah that was done in quantity and uh and IBM I didn't sell them. They rented them but they rented them to universities that at great uh you know, I had a great deal. And so that's why a lot of students learned about computers at that time. So you refer </s><s>[INST] to people including yourself who gravitate toward a kind of computational thinking as geeks. At least I've heard you use that terminology. [/INST] It's true that I think there's something that happened to me as I was growing up that made my brain uh structured in a certain way that resonates with with computers. </s><s>[INST] So there's the space of people, 2% of the population, you empirically estimate [/INST] that that's a pretty fair, that's been proven fairly constant over most of my career. However, it might be different now because kids have different experiences when they're young. So what </s><s>[INST] does the world look like to a geek? What is, what is this aspect of thinking that is unique to? Uh that makes a geek? [/INST] This is Cute. Really important question. In in the 50s, IBM noticed that that uh there were geeks and non geeks and so they tried to hire geeks and they and they put out as with paper saying, you know, if you play chess, come to Madison Avenue and for an interview or something like this, you know, they were they were trying for some things. So what what what is it that I find easy and other people tend to find harder, and I think there's two main things. One is this, which is uh ability to jump jump levels of, of abstraction. Uh So you see something in the large uh and you see something in the small and and uh and you pass between those unconsciously. So you you know that in order to solve a some big problem, what you need to do is add one to uh to a certain register and I get to another step and below the yeah, I don't go down to the electron level, but I knew what those milliseconds were, what the drum was like on the 6 50 I knew how I was going to factor a number or or find a route of an equation or something because of what was doing. And and as I'm debugging I'm going through yeah. You know, did I make a key punch air, did I, did I write the wrong instruction? Do I have the wrong thing in the register? And each level each level, it is different. And uh this idea of being able to see something at all at lots of levels and fluently go between them, it seems to me to be more pronounced, much more pronounced in in the people that resonate with computers, like so in my books, I also don't stick just to the high level, but I mix uh low level stuff with high level. And this uh means that some people think uh you know that that I should write better books. Uh and that's probably true, but but other people say well, but that's, if you think like, like that, then that's the way to train yourself, keep mixing the levels and and learn more and more how to trump between. So that that's the one thing, the other, the other thing is that it's more of a talent to be able to deal with uh non uniformity, where there's case one, case two, case three, uh instead of, instead of having one or two rules that govern everything. Uh So, so it doesn't bother me If I need uh like an algorithm has 10 steps to it. You know, each step does something else that doesn't bother me, but a lot of a lot of pure mathematics is based on one or two rules which which are universal and and uh and so this means that people like me sometimes work with systems that are more complicated than necessary, because it doesn't bother us, that we don't, that we didn't figure out the simple rule. </s><s>[INST] And you mentioned that while Jacoby Bull Obel, all the mathematicians of the 19th century may have had symptoms of geek, The 1st 100% legit geek was touring, Alan [/INST] turing, I think he had, you know, a lot more of the uh of this quality than any good from reading the, the kind of stuff he did. And </s><s>[INST] so how does touring, what influence has touring had? I knew well, so [/INST] I didn't know that aspect of him until after I graduated some years, it has undergraduate, we had a class that talked about compute ability theory and turing machines. And, and it was all, it sounded like a very specific kind of purely theoretical approach to stuff. So when, how old was I, when I when I learned that he, that he had uh uh designed machine and that he wrote the, you wrote a wonderful manual for, for Manchester machines and uh and he invented all, you know, subroutines and and and he was a real hacker that he had his hands dirty. I thought for many years that he had only done purely formal work as I started reading his own publications, I could, you know, I could feel this kinship and and of course he had a lot of peculiarities uh like he wrote numbers backwards because I mean left to right instead of right to left because that's the that's it was easier for computers to process them that way. </s><s>[INST] What do you mean left to right? [/INST] He would write pie as you know, 951, I mean, okay, </s><s>[INST] I got it for [/INST] 1.3 on the blackboard. I mean, when he had trained himself to uh to do that because the computers he was working with uh work that way inside </s><s>[INST] trained himself to think like a computer. Well, there you go, that's that's geek thinking you've practiced some of the most elegant formalism in computer science. And yet you're the creator of a concept like literate programming, which seems to move closer to natural language type of description of programming. [/INST] Yeah, absolutely. </s><s>[INST] The how do you see those tools conflicting as the formalism of theory and the idea of literate programming? [/INST] So there there we are in a non uniform system where I don't know, I don't think 11 size fits all and I don't and I don't think all truth lies in one in one kind of expertise. And so somehow in a way you say my my life is a convex combination of english and mathematics and you're okay with that. And not only that, I think driving and you know, I want my kids to be that way I want etcetera, you know, used left brain, right brain at the same time. Uh you got a lot more done that, that was part of the part of the bargain. </s><s>[INST] And I've heard that You didn't really read for pleasure until into your 30s. You know, literature [/INST] it's true. You know more about me than I do, but I'll try to be consistent with what you </s><s>[INST] really Yeah, no, just believe me. I uh just go with whatever story I tell you. It will be easier that way. The conversation. Yeah, no, that's [/INST] true. </s><s>[INST] I've heard mention of Philip Roth's american pastoral, which I love as a book. [/INST] Uh huh. </s><s>[INST] I don't know if it was, it was mentioned something I think that was meaningful to you as well. Uh you need a case what literary books had a lasting impact on you. What literally. Okay, [/INST] good. So I met Roth. All right. Well, we both got Doctors from Harvard on the same day. So so we were yeah, we had lunch together and stuff like that, but he knew that uh you know, computer books would never sell well. Well, all right. So you say you you uh you were a teenager when you left Russia. So, uh I have to say that Tolstoy was one of the big influences on me. Uh especially like on a car nina. Uh, not because of a particular of the plot of the story where but because uh there's this character who, you know, the philosophical discussions that it's all it's a whole uh we have life has worked out there among the characters. And so and so that I thought was especially beautiful. On the other hand, dostoevsky, I I didn't like at all because I I felt that his genius was mostly because he kept forgetting what he what he had started out to do. And he was just sloppy. I didn't think that that that that he polished his stuff at all. And I tend to admire somebody who who dots the I's and crosses the tees. </s><s>[INST] So the music of the prose is what you admire more than [/INST] I certainly do admire the music of the language which I couldn't appreciate in the Russian original, but but I can't and victor Hugo because close friendships is closer. But the toaster, I like the same reason I like Herman Wouk has a as a novelist, I I think uh like his book, Marjorie Morningstar has a similar character in who developed his own personal philosophy and exposed and it goes in the </s><s>[INST] it was consistent. [/INST] Yeah, right. And it's worth worth pondering. So, uh </s><s>[INST] you don't like Nietzsche and uh like what you don't like Friedrich? Nietzsche or [/INST] Yeah, no, no, yeah, this has, I keep seeing quotations for Nietzsche and and he never tempt me to read any further. </s><s>[INST] Well, he's full of contradictions. So you will certainly not appreciate him, [/INST] but schiller, you know, I'm trying to get across what I appreciate in literature. Uh and part of it is the is, as you say, the music of the language of the way it flows and take Raymond Chandler versus Dashiell Hammett. Dashiell Hammett sentences are awful and Raymond Chandler's are are beautiful, they just flow. So I don't uh I don't read literature because it's uh supposed to be good for me or because somebody said it's great, but I find things that I like. I mean uh you mentioned you were dressed like James Bond. So like, you know, I love Ian Fleming, I think he's got he had a really great gift for if he has a golf game or a game of bridge or something. And this comes into his story, it will be the most exciting golf game, or or, you know, the absolute best possible hands, a bridge that that exist. And uh, and he he exploits it and tells it beautifully. </s><s>[INST] So in connecting some things here, looking at literary programming and being able to convey uh, encode algorithms to a computer in a way that mimics how humans speak. Uh how what do you think about natural language in general and the messiness of our human world about trying to express difficult things? [/INST] So, the idea of literate programming is is really to try to uh, understand something better by seeing it from at least two perspectives. The formal and the informal, if we're trying to understand a complicated thing, if we can look at it in different ways. And so this is in fact the key to technical writing, a good technical writer, trying not to be obvious about it, but says everything twice uh formally and informally, or maybe three times. But you try to give uh reader uh, a way to to put the concept into his own brain or her own brain. </s><s>[INST] Is that better for the writer or the reader or both? [/INST] Well, the writer just tries to understand the reader. That's the goal of a writer, is is to have a good mental image of the reader and to say what the reader expects next and to yeah, to impress the reader with what has impressed the writer, why something is interesting. So when you have a computer program, we try to uh instead of looking at it as something that we're just trying to give an instruction to the computer. What we really want to be is giving, giving insight to the person who's uh going to be maintaining this program or or to the program or himself when he's debugging it as to why this stuff is being done. And so all the techniques of exposition that the teacher uses or book writer is make you better program or if your if your program is going to be uh not just a one shot deal. </s><s>[INST] So how difficult is that? Do you see hope for the combination of informal and formal for the programming task? [/INST] Yeah, I'm the wrong person to ask, I guess because I'm a gig. But but I think for a geek it's easy. No, I don't know. Not some people have difficulty writing and that might be because there's something in their brain structure that makes it hard for them to write. Or or it might be something just that they haven't had enough practice. I'm not the right one to uh to judge. But I don't think you can teach any person any particular skill. I do think that that writing is is half of my life. And so I put it together in a little program even even when I'm writing a one shot program, I I write it uh in literate way because I get it right faster that way. </s><s>[INST] Now, does it get compiled automatically? Or so? I guess on the technical side my question was how difficult is it design a system where much of the programming is done informally, [/INST] informally, </s><s>[INST] informally? [/INST] I think whatever works to make it understandable is good. But then you have to also understand uh, how informal is you have to know the limitations you have to you. So by putting the formal and informal together, this, this is where this is where it gets locked into your, into your brain. And you can, you can say informally, well, I'm working on a problem right now. So </s><s>[INST] let's go there. Get, can you give me an example of uh, of connecting the informal and the formal? [/INST] Well, it's a little too complicated example. There there's a puzzle that's self referential. It's called the japanese arrow puzzle. And uh, and you're given a a bunch of boxes, each one points north, east, south or west. And at the end you're supposed to feel in each box with the number of distinct numbers that it points to. So if I put a three in a box, that means that and it's pointing to five other boxes, that means that there's going to be three different numbers in those five bucks. And uh, and those boxes are pointing one, it might be pointing to me one of them might be pointing the other way Other way. But anyway, I I I'm going to find a set of numbers that obeys this complicated condition that each number counts, how many distinct numbers uh it points to Well, um and so the guy sent me his solution to this problem where he where he uh presents formal statements that that say either this is true or this is true, this is true. And and so I try to render that formal statement informally, and I try to say I contain a three. And and uh the guys I'm pointing to uh contain the numbers 12 and six. So by putting it informally, and also I converted into a into a dialogue statement uh that helps me understand the logical statement that he's written down as a string of numbers in terms of some abstract variables that he had. </s><s>[INST] That's really interesting. So maybe an extension of that. There has been a resurgence in computer science and machine learning and uh neural networks. So, using data to construct algorithms. So it's another way to construct algorithms, really, if you if you can think of it that way. Uh So as opposed to natural language to construct algorithms, Use data to construct. So, what what's your view of this branch of computer science, where data is almost more important than the mechanism of the algorithm, [/INST] it seems to be uh suited to a certain kind of non geek, uh and which which is probably why it's it's uh it's taken off, it has its own community that that really that really resonates with that. But uh it's hard to, you know, to trust something like that because nobody even the people who who work with it, that they have no idea what has been learned. </s><s>[INST] That's a really interesting thought that it's uh it makes algorithms more accessible to a different community, a different type of brain. And that's really interesting because just like literate programming perhaps could make programming more accessible to a certain kind of brain. [/INST] There are people who think it's just a matter of education uh and anybody can learn to be a great programmer, anybody can learn to be a great uh skier. Um uh you know, I wish that were true, but but I know that there's a lot of things that I've tried to do and I and I was well motivated and I kept trying to build myself up and I never got past a certain level, I can't view, for example, I can't view three dimensional objects in my, in my head, I have to have to make a model and look at it and study it from all points of view. And then I start to get some idea, but other people are good at four dimensions. I mean </s><s>[INST] physicists. Yeah, so let's go to uh the art of computer programming In 1962, you set the table of Contents for this magnum opus, right, It was supposed to be a single book, 12 chapters now. Today, What is it? 50? Uh seven years later, You're in the middle of volume four of 7 [/INST] And in the middle of Volume four, B is for b precisely. </s><s>[INST] Can ask you for an impossible task, which is try to summarize the book so far maybe by giving a little examples. So from the sorting and the search in the combinatorial algorithms, if you were to give a summary, a quick elevator summary elevated, depending how many floors there are in the building. [/INST] The first volume called fundamental algorithms talks about something that you can't the stuff you can't do without. Uh you have to you have to know the basic concepts of what is a program now. What is what is an algorithm. And uh and and it also talks about a low level machine. So you can have some some kind of an idea what's going on. And it has basic concepts of input, output, uh subroutines, conduction, induction, Right, Mathematical, preliminary. So the thing that makes my book different from a lot of others is that all that I try to not only present the elegant, but I try to analyze them and which means to quantitatively I say not only does it work, but it works this fast. Okay. And so I need math for them and then the standard way to structure data inside and represent information in the computer. So that's all Volume one of volume Two talks, it's called semi numerical algorithms. And here we're here we're writing programs but we're also dealing with numbers algorithms deal with with with any kinds of objects. But what specific when there's objects are numbers? Well then then we have certain Special paradigms that apply to things that have 12 numbers. And so there's there's there's there's arithmetic on numbers and and there's matrices full of numbers, there's random numbers and there's power series full of numbers. There's different algebraic concepts that have numbers in structured ways </s><s>[INST] and arithmetic in the way a computer would think about arithmetic, the floating point, floating point arithmetic, [/INST] high precision arithmetic, not only addition, subtraction, multiplication, but also comparison of numbers. So then then volume three talks about </s><s>[INST] I like that one sort and [/INST] search, sorting and searching, </s><s>[INST] sorting. [/INST] Right? So, so here, you know, we're not getting necessarily with numbers because you sort letters and other objects and searching. We're doing all the time with google nowadays, but I mean we have to find stuff. So again, algorithms that underlie all kind of applications. You know, none of these volumes is about a particular applications, but the applications are examples of of why people want to know about sorting, why people want to know about random numbers. So then volume four goes into combinatorial, elegant. This is where we have zillions of things to deal with. And we and here we keep finding cases where one good idea can make something go more than a million times faster. And and and we're dealing with problems that are probably never going to be solved efficiently. But that doesn't mean we give up on them and and and we have this chance to have good ideas and and go much much faster on them. So, so that's combinatorial algorithms and those are the ones that are Yeah, I mean you say starting is most fun for you. Well, well </s><s>[INST] it's true [/INST] combinatorial algorithms are the ones that I always that I always enjoyed the most because that's when my skillet programming had most payoff. And the different the difference between an obvious algorithm that you think up first thing and a good uh interesting subtle algorithm that not so obvious but run circles around the other one. That's that's where computer science really comes, comes in And and a lot of these comments oil methods were found first in applications to artificial intelligence or cryptography. And in my case I just liked him and it was associated more with puzzles. </s><s>[INST] Do you like the most in the domain of graphs and graph theory, [/INST] graphs are great because they're they're they're they're terrific models of so many things in the real world. And and and you you throwing numbers on a graph, you've got a network and so there you go there. You have many more. I think so. But comment Oil in general is any arrangement of objects that uh that has some kind of yeah, higher structure, non non random structure and okay, is it possible to uh, to put something together satisfying all these conditions. Like I mentioned arrows a minute ago. You know, is there a way to to put these numbers on a bunch of boxes that that are pointing to each other? Is that going to be possible at all </s><s>[INST] that volume for [/INST] that volume? For </s><s>[INST] what do they say for [/INST] A was part 1? And, and uh, What happened was in 1962 when I started writing down a table of Contents. It wasn't going to be a book about computer programming in general. It was gonna be a book about how to write compilers. And I was asked to write a book explaining how to how to write a compiler. And at that time there were only a few dozen people in the world who had written compilers and I happened to be one of them. So, and I also had some experience writing for like the campus newspaper and things like that. So, so I thought, okay, great. I'm the only person I know who who has written a compiler but hasn't invented any new techniques for writing compilers and and all the other people I knew had uh, super ideas, but I couldn't see that they would be able to write a book that wouldn't, that would describe anybody else's ideas with their own. So I could be the, I could be the journalist and I could explain what all these cool ideas about computer writing that were and uh and and then I started pretty darn well yeah, let me you need have a chapter about data structures. You need to have some introductory material. I want to talk about searching because the compiler writer has to has to look up uh the variables in a symbol table and find out uh you know which which when when you when you write the name of the variable in one place, it's supposed to be the same as the one you put somewhere else. So you need all these Basic techniques and I and I you know had you know some arithmetic and stuff. So I thought I threw in these chapters and I threw in a chapter on comment talks because that was what I really enjoyed programming the most, but there weren't many algorithms and known about combinatorial methods in 1962. Uh so that was kind of a short chapter but it was sort of thrown in just for fun. And chapter 12 was going to be actual compilers applying all the stuff in chapters 1-11 Uh to make compilers. Well, okay, so that was my table of contents from 1962. And during the 70's the whole field of combinatorics went through a huge explosion. People talk about a comment oil explosion and they usually mean by that that the number of cases goes up, you know, and, and plus one and all of a sudden you, your problem has, has gotten more than 10 times harder. But there was an explosion of ideas about combinatorics in the 70s to the point that it like take 1975, I bet you more than half of all the journals of Computer Science were about combinatorial method and </s><s>[INST] kind of problems we're occupying people's minds. What kind of problems in combinatorics was set to satisfy ability graph theory. [/INST] Yeah, gravity was, was quite dominant I mean, but uh, all of the np hard problems uh, that you have like, you know, hamiltonian path </s><s>[INST] going [/INST] beyond Yeah, Going beyond graphs, you had operation Research whenever there was a small class of problems that had efficient solutions and they were usually associated with Maitreya years, special mathematical construction. But once we went uh to things that involved three things at a time instead of instead of to all of a sudden things got harder. So we had satisfy ability problems or if you have, If you have clauses, every clause has two logical elements in it, then we can satisfy it. Then your time we can test for satisfy buildings in your time. But if you allow yourself three variables in the clause uh, than uh, nobody knows how to do it. So these articles were about trying to find better, better ways to uh, to solve cryptography problems and graph three problems where we have a lot of data but we didn't know how to find the best subsets of the data, like sorting. Uh we we could get the answer didn't take long. </s><s>[INST] So how did it continue to change from the 70s to today? [/INST] Yeah, so now they're maybe half a dozen conferences whose topic is common to talks Different kind. But unfortunately I don't have to rewrite my book every month, you know like I had to in in the 70's but still there's a huge amount of work being done and people getting better ideas on these problems that don't seem to have really efficient solutions, but we still get and do a lot more with him. And so this book that I'm finishing now is I've got a whole bunch of brand new methods that uh as far as I know, there's no other, there's no other book that covers that covers this particular approach. And uh so I'm trying to do my best of exploring the tip of the iceberg and I try out lots of things and keep keep rewriting uh finding as I find better better method. </s><s>[INST] So what's your writing process? Like what's your thinking and writing process like every day? [/INST] So um </s><s>[INST] what's your routine even [/INST] I guess it's actually uh the best question because I spent seven days a week uh you're doing </s><s>[INST] it the most prepared to answer it. Uh Yeah but [/INST] uh okay so uh the chair I'm sitting in is where I do </s><s>[INST] where the magic happens. [/INST] Well, uh reading and writing my chair is usually sitting over there where I have other book, some reference books. But but I found this chair which was designed by a Swedish guy anyway, it turns out this is the only chair I can really sit in for hours and hours and not know that. I mean it's there, but then I have the stand up desk right next next to us. And and so after I write something with pencil, an eraser, I get up and I type it and revise and rewrite uh standing up, </s><s>[INST] the kernel of the idea is first put on paper. Yeah, that's where. [/INST] Right, and I'll write maybe five programs a week. Uh of course literate programming. And uh these are before I describe something in my book, I always program it to see how it's working. And I tried a lot. So for example, I learned at the end of January, I learned of a breakthrough by four japanese people who had extended one of the, one of my methods in a new direction. And so I I spent the next five days writing a program to implement what they did and then I, you know, but they had only general is part of what I had done. So then I had to see if I could generalize more parts of it and then I and I had to take their approach and I had to I had to try it out on a couple of dozen of the other problems I had already worked out with with my old methods and so that took another couple of weeks. And then, you know, then I then I started to see the light and I uh and I started writing the final draft and uh and then I would uh you know, type it up, involve some new mathematical questions and so I wrote to my friends and who might be good at solving those problems and they solve some of them. And so I put that in as exercises. And and so a month later I had absorbed one new idea that I that I learned and uh you know, I'm glad I heard about it in time, otherwise I wouldn't put my book out before. I heard about the idea. On the other hand, this book was supposed to come in at 300 pages. I'm up to 350 now. That added 10 pages to the book. But if I learn about another one, I probably wasn't going to shoot me </s><s>[INST] well. So in the process in that one month process are some days harder than others [/INST] are some days harder than others. Well, yeah, my work is fun. But I also work hard and every big job has parts that are a lot more fun than others. And so many days I would say why do I have to have such high standards, Why why couldn't I just be sloppy and not try this out and you know just just report the answer. But I but I know that uh people are calling me to do this and so okay, so okay, don I'll get my teeth and do it and and and then the joy comes out when I see that actually, you know, I'm getting good results and and and I get and I even more when I see that somebody is actually read and understood what I wrote and told me how to make it even better. I did want to mention something about the uh about the method. So I got this tablet here, we're do the first, you know the first writing of of concepts. Okay, so </s><s>[INST] so and what language? Right, [/INST] so take a look at it. But you know here you random say explain how to draw such skewed pixel diagrams. Okay, I got this paper about 40 years ago when I was visiting my sister in Canada and they make tablets of paper with this nice large size and just </s><s>[INST] the right very small space between life. Yeah, maybe. Uh [/INST] show it. Yeah. Yeah, Wow. You know, I've got these manuscripts going back to the 60s. Mhm. And and and those are getting my ideas on paper. Okay. But I'm a good typist. In fact I went to typing school when I was when I was in high school and so I can type faster than I think. So then when I do the editing and stand up and type, then I then I revised this and, and it comes out a lot different than what, you know, for style and rhythm and things like that. Come out at the at the typing stage, </s><s>[INST] a new type in tech [/INST] and I type in tech. </s><s>[INST] And can you, can you think in tech? [/INST] No. So to a certain extent, I have, I have only a small number of, of idioms that I use, like, you know, I'm beginning with their um I do something for display equation, I do something and so on. But but I I have to see it </s><s>[INST] and in the way that it's on paper here. So, for example, Touring wrote what the other direction, you don't write macros, you don't think in macros [/INST] particularly, but when I need a macro, I'll go ahead and these are and do it. But the thing is the I also write to fit, I mean, I'll change something if I can, if I can save a line, you know, it's like haiku, I'll figure out a way to rewrite the sentence so that uh it looked better on the page And I shouldn't be wasting my time on that, but, but I can't resist because I know it's only another 3% of the time or something like that. </s><s>[INST] And it could also be argued that that is what life is about. [/INST] Ah Yes. In fact that's true. Uh like like I worked in the garden one day a week and that's that's kind of a description of my life is getting rid of weeds, you know, removing bugs for programs. And </s><s>[INST] so you know, a lot of writers talk about, you know basically suffering the writing process is having, you know, it's extremely difficult and I think of programming especially the or technical writing that you're doing can be like that. Do you find yourself method a logically? How do you every day sit down to do the work? Is it a challenge you kind of say it's you know, it's fun but it would be interesting to hear if if there are non fun parts that you really struggle with. [/INST] So the fun comes when when I'm able to put together ideas of 2-2 people who didn't know about each other. And and so it might be the first person that saw both of their ideas. And so then you know, then then I get to make the synthesis and that gives me a chance to be creative. But the drudge work is where I I've got to chase everything down to its root. This leads me into really interesting stuff. I mean I I learned about Sanskrit night and you know, I try to give credit to all the authors and so I write, so I write to people who know the people authors if they're dead, I I communicate this way I and uh, I got to get the math right. And I got to tackle my programs, try to find holes in them. And I rewrite the program's over after I get a better idea. </s><s>[INST] Is there ever dead ends [/INST] that end? So yeah, I throw stuff out. Yeah. One of the things that I I spent a lot of time preparing a major example based on the game of baseball and I know a lot of people who, for whom baseball is the most important thing in the world, you know. But, but I also know a lot of people from cricket is the most important in the world or suck or something. And and I realized that if if I had a big temple and he was going to have a foldout illustration and everything I was saying, well, what, what am I really teaching about algorithms here? Where I had this, this, this this baseball example. And if I was a person who who knew on a cricket, wouldn't they, what would they think about this? And so I ripped the whole thing out. But you know, I had something that would have really appealed to people who grew up with baseball as a, as a major theme in their </s><s>[INST] life, which is a lot of people. But [/INST] just yeah, </s><s>[INST] still a minority. [/INST] Small minority. I took out bowling too. Uh, </s><s>[INST] even a smaller minority. What's the art in the art of programming? Why why is there of the few words in the title? Why is Art one of them? [/INST] Yeah. Well that's that's what I wrote my touring lecture about. And uh and so when people talk about are really, I mean, what the word means is something that's not in nature. So when you have artificial intelligence, that art comes from the same root saying that this is something that was created by by human beings. And then it's gotten a further meaning, often a fine art which has this beauty to the to the mix and says, you know, we have things that are artistically done and and this means not only done by humans but also done in a way that's elegant and uh brings joy and and has has uh I guess that Tolstoy dostoyevsky. </s><s>[INST] Uh [/INST] but anyway, it it's that part that that says that it's done well as well as not only different from nature in general, then uh art is what human beings are specifically good at. And when they say artificial intelligence, well, they're trying to mimic human beings, </s><s>[INST] but there's an element of fine art and beauty. You are one. That's [/INST] what I that's what I tried to also say that you can write a a program and make a work of art. </s><s>[INST] So now in terms of surprising, you know, what ideas in in writing from sort and search to the combinatorial algorithms. What ideas have you come across that were particularly surprising to you. That changed the way you see a space of problems. [/INST] I get a surprise every time I have a bug in my program obviously. But but but that isn't really what you're more </s><s>[INST] transformation for [/INST] Example in Volume four A. I was </s><s>[INST] especially surprised when I learned about [/INST] data structure called B. B. D. D. But bullying decision diagram because I sort of had the feeling that uh as an old timer. Uh and you know I've been programming since the since the fifties And uh b. d. d. s weren't invented until 1986. And here comes a brand new idea that revolutionizes the way to represent a boolean function. And boolean functions are so basic to all kinds of things in, you know, I mean logic underlies it. Everything we can describe all of what we know in terms of logic somehow and and and and uh proposition in logic. Uh I thought uh that was cut and dried and everything was known. But but but but here comes uh uh randy Bryant and uh and discovers that bds are incredibly powerful Then then. So so I uh that mean it means I have a whole whole new section to the book that I never would have thought of until 1986, 19 until 1990s when I went when people started to uh to use it for for you know a billion dollars of applications. Uh and it was it was the standard way to design computers for a long time until until sat solvers came along when in the year 2000. So that's another great big surprise. So a lot of these things have have totally changed the structure of my book. and the middle 3rd of volume for bees is about that summers. And that's 300 plus pages which is uh which was all about material mostly about material that was discovered in this century. Um and I had to start from scratch and you meet all the people in the field. Right. I have 15 different sets of words that I wrote while preparing that seven of them are described in the book. Others who are from my own experience. </s><s>[INST] So newly invented data structures or ways to represent [/INST] a whole new class of algorithms, </s><s>[INST] whole new classified. [/INST] Uh And the interesting thing about the B. D. D. S was that the theoreticians started looking at it and started to describe all the things you couldn't do with B. D. D. S. And so they were getting a bad they were getting a bad name uh because you know, okay they were they were useful but they didn't solve everything. Every problem I'm sure that the theoreticians are In the next 10 years are going to show why machine learning doesn't solve everything. But I, you know, not only worried about the worst case, I get a huge delight when I can actually solve a problem that I couldn't solve before. Even though I can't solve the problem. That's that it suggests as a further problem. Like I know that I'm way better than I was before. And so I found out that BDS could do all kinds of miraculous things. Uh and so I uh I had to spend quite a few years uh learning about the that territory. </s><s>[INST] So in general what brings you more pleasure uh proving or showing a worst case analysis of an algorithm or showing a good average case or just showing a good case, you know, something good pragmatically can be done with this algorithm. [/INST] Yeah, I like a good case that that is maybe only a million times faster than I was able to do before. But uh and not worry about the fact that uh that is still that is still going to take too long if I double the size of the problem. </s><s>[INST] So that said, you popularize the asymptotic notation for describing running time obviously in the analysis of algorithms. Worst cases such a such an important part. Do you see any aspects of that kind of analysis is lacking? So and notation to [/INST] well, the main purpose we have notations that that help us for the problems we want to solve and so they match are they match our intuitions and people who worked in number theory had used a satanic notation in in a in a certain way, but it was only known to a small group of people and I realized that in fact it was very useful to be able to have a notation for something that we don't know exactly what it is, but we only know partial about it and so on stick. So uh for example, instead of big o notation, let's just let's just take a much simpler rotation where I'd say 01 or 01 or two. And suppose I suppose that uh when I had been in high school we would be allowed to put in the middle of our formula X plus zero one or two equals Y. Okay. And and then then we we would learn how to multiply two such expressions together and and you know, deal with them. Uh Well, the same thing big O notation says uh here's something that's uh I'm not sure what it is, but I know it's not too big. I know it's not bigger than some constant times n squared or something like that. So I write big old event square. Now I I learned how to add big event square, too big event cubed and I know how to add big event squared to uh plus one and square that and how to take logarithms and exponential, have big goals in the middle of them and that turned out to be hugely valuable in all of the work that I was trying to do is I'm trying to figure out how good algorithm is. </s><s>[INST] So have there been algorithms in your journey that perform very differently in practice than they do in theory. [/INST] Well, the worst case of a common style algorithm is almost always horrible. Uh But we have SAT solvers that are solving were one of the, one of the last exercises in that part of my book was figure out a problem that has 100 variables. That's that's difficult for a SAT solver. But but you would think that a problem with 100 billion variables has crazy to do two to the 100th uh operations because that's the number of possibilities when you have 200 billion variables in two to the 100th To the 100th is way bigger than than we can handle. 10 to the 17th is a lot </s><s>[INST] you've mentioned over the past few years that you believe p may be equal to np but that is not really uh you know, if somebody does prove that P equals np, it will not directly lead to an actual algorithm to solve difficult problems. Can you explain your intuition here hasn't been changed and in general on the difference between easy and difficult problems of P and np and so on. So the popular [/INST] idea is if an algorithm exists then somebody will find it. Um and it's just a matter of of uh of writing it down one. but many more algorithms exist that anybody can understand or ever make you discover because they're just way beyond human comprehension of the total number of algorithms is is more than mind boggling. Um So so we have situations now where we know that algorithms exist but we don't know, we don't have the foggiest idea what the algorithms are. There's there are simple exact examples based on on game playing where you have uh where you say, well there must be an algorithm that exists to win in the game of hex because for the first player to win the game of hex, because hex is always either a win for the first player, The second player, what's the game of heck? There's a game of hex which is which based on putting pebbles onto a hexagonal board. And and the white player tries to get a white path from left to right and the black player tries to get a black path from bottom to top </s><s>[INST] and how does capture occur. And [/INST] there's no capture, you just put pebbles down one at a time, but there's no drugs because after all the white and black are played, there's either going to be a white path across from each of the west or black path from from bottom to top. So there's always, you know, it's the perfect information game and people people take turns like like tic tac toe. Um And uh hex board can be different sizes but we there's no possibility of a draw and players move one at a time. And so it's got to be either a first player win or a second player win mathematically. Uh you follow out all the trees and uh and either there's always a win for the first player. Second player, Okay. And it's finite, the game is finite. So there's an algorithm that will decide. You can show it has to be one or the other because the second player could mimic the first player with kind of a pairing strategy. Um And so you can show that uh uh it has to be it has to be one with that. But we don't know any algorithm anyway. We don't know that there are there are cases where you can prove the existence of uh of a solution, but we but nobody knows anyway how to find it. But more like the algorithm question. Uh There's a there's a very powerful theorem in graph theory by Robinson and Seymour, that says that every class of graphs that is closed undertaking miners has a has a polynomial time algorithm to determine whether it's in this class or not. Now, a class of graphs, for example, planer graphs, these are graphs that you can draw on a plane without crossing lines. And and the plane a graphic taking minors means that you can shrink edge into a point or you can delete an edge. All right. And so you start with the plane a graph and shrink on the edge to the point is still playing her deleting edges. Still playing okay now. But there are millions of different ways to describe uh family of graph that still remains the same undertaking minor and Robertson and Seymour proved that any such family a graph, there's a finite number of minimum grass that are obstructions so that if it's not in the family, then then it has to contain uh then there has to be a way to shrink it down until you get one of these bad minimum graphs. That's not in the family For in the case of a plane to graph, the minimum graph is a five pointed star where everything pointed to another. And the minimum graph consisting of trying to connect three utilities to three houses without crossing lines. And so there are two there are two bad graphs that are not playing her. And every every non playing a graph contains one of these two bad graphs. By by shrinking and moving </s><s>[INST] at it. Can you say it again? So, uh he put that there's a finite number of these bad guys. [/INST] Always find it. So somebody says here's a family, it's hard to believe. And they present its sequence of 20 papers, I mean, and it's deep work, but you know, it's </s><s>[INST] uh for the arbitrary class. [/INST] So for any arbitrary class that's closed undertaking miners </s><s>[INST] that's closed under maybe. I'm not understanding because it seems like a lot of them are closed undertaking miners. [/INST] Almost all the important classes of grabs. Our there are tons of such graphs, but also hundreds of them that arise in applications. I have a book over here called classes of graphs. And and it's amazing how many different uh class of graphs people have looked at. </s><s>[INST] So why do you bring up this them lower this proof? [/INST] So now there are lots of algorithms that are known for special classes of graphs. For example, if I have a certain if I have a photograph, then I can color it efficiently. Uh, if I have some kind of graphs, it'll make a great network various. So like you'd like to test uh somebody gives you a graph is always in this family of graph. If so then I then I can I can go to the library and find an algorithm that's going to solve my problem on that graph. Um, Okay. So we have that. We want to have a graph that says uh, algorithm that says you give me a graph. I'll tell you whether it's whether it's in this family or not. Okay. And so all I have to do is test whether or not, but does this give and graph have a minor? That's one of the bad ones. A minor. Is is everything you can get by shrinking and removing it and given any minor, there's a polynomial time algorithm saying I can't tell whether this is a minor of uh, of you. And there's a finite number of bad cases. So I just try, you know, doesn't have this bad case problem your time I got the answer does have this bad case upon every time I got the answer. Uh total polynomial time. And so I've solved the problem. However, all we know is that the number of minors is finite. We don't know what we might only know one or two of those miners but we don't know that if we got if we got 20 then we don't know. There might be 21 25. Just all we all we know is that is that it's finite. So here we have a polynomial time algorithm that we don't </s><s>[INST] know. That's a really great example of what you worry about or why you think P equals np won't be useful but still why do you hold the intuition that P equals np [/INST] because you have to rule out so many possible algorithms has been not working. Uh There's, you know, you can you can take the graph and you can represent it as uh in terms of certain prime numbers and then you can multiply those together and then you can you can take the bit wise and and and uh you know uh and uh construct some certain constant in polynomial time and then that you know perfectly valid. Album and there's so many. I'll get into that kind a lot of times we see random uh you take data and and we get coincidences that that that some fairly random looking number actually is useful because uh because uh it happens it happens to solve, it happens to solve a problem just because uh you know, there's there's so many hairs on your head. Uh but uh it seems like unlikely that two people are going to have the same number of hairs on their head. Uh but they're obviously, but you can count how many people there are and how many hairs on there. So there must be people walking around in the country. I have the same number of hairs on their head. Well, that's a kind of a coincidence that you might say also, you know, this this particular combination of operations uh just happens to prove that graph has a hamiltonian path. I see lots of cases where unexpected things happen when you have enough enough possibilities. </s><s>[INST] Because the space of possibilities a huge year tuition, [/INST] they have to rule them all out. And so that's the reason for my intuition is by no means a proof. I mean, some people say uh you know, well Pete can't equal np because you've had all these smart people. Uh you know, the smartest designers will give them have been wrecking their brands for years and years and And there's $1 million dollar prize is out there. You know, none of them, nobody has thought of uh the algorithm. So it must there must be no such a on the other hand can use exactly the same logic and I can say, well he must be equal to np because there's so many smart people out here have been trying to prove it unequal np and they've all failed. Uh you know, </s><s>[INST] this kind of reminds me of the discussion about the search for aliens. Uh we've been trying to look for them and we haven't found them yet, therefore they don't exist. But you can show that there's so many planets out there that they very possibly could exist. Uh [/INST] huh. And then there's also the possibility that that they exist. But they they all discovered machine learning or something and and and and then blew each other </s><s>[INST] up. Well on that small quick change it. Let me ask, do you think there's intelligent life out there in the universe? [/INST] I have no idea. </s><s>[INST] Do you hope so? Do you think about it? I [/INST] don't I don't spend my time thinking about things that that I could never know really </s><s>[INST] and yet you do enjoy the fact that there's many things you don't know. You do enjoy the mystery of things. [/INST] I enjoy the fact that there that I have limits. Yeah, but I don't but but I don't take time to to answer unsolvable questions I had. </s><s>[INST] Well, because you've taken on some tough questions that may seem unsolvable. You have taken on some tough questions and you seem unsolvable there in the state [/INST] gives me a thrill when I can get further than I ever thought I could. Yeah, but </s><s>[INST] but I don't much like with religion, uh [/INST] I'm glad that there that that there is no proof that God exists or not. I mean, I think </s><s>[INST] it would spoil the mystery. [/INST] It'll be it'll be too dull. Yeah. </s><s>[INST] So, uh to quickly talk about the other art of artificial intelligence, what is the view, what's your view? You know, artificial intelligence community has developed as part of computer science and in parallel with computer science since the 60s, What's your view of the Ai community From the 60s to now? [/INST] So, all the way through it was people who were inspired by trying to Munich intelligence or or to do things that that were somehow the greatest achievements of intelligence that had been inspiration to people who have pushed the envelope of computer science, uh maybe more than any other group of people. So all the through it's been a great source of of good problems to to uh sink teeth into and and getting getting uh partial answers and then more and more successful answers over the year? So, this has this has been the inspiration for lots of the great discoveries of computer science. </s><s>[INST] Are you yourself captivated by the possibility of creating of algorithms having um echoes of intelligence in them. Uh [/INST] huh Not as much as most of the people in the field, I guess I would say, but that's not to say that they're wrong or that it's just you asked about my own personal preferences. And but but the thing that I that I uh worry about is when people start believing that they've actually succeeded uh because the it seems to me this huge gap between really understanding something and being able to pretend to understand something and give the give the illusion of understanding something. </s><s>[INST] Do you think it's possible to create without understanding? Yeah. So to [/INST] uh do that all the time too. I mean I mean that's why I use random members. I I but I but but there's there's still this great gap. I don't assert that it's impossible, but I but I I don't see it anything coming any closer to really uh the kind of stuff that I would consider intelligence. So </s><s>[INST] you've mentioned something that on that line of thinking, which I very much agree with. So the art of computer programming is the book is focused on single processor algorithms. And for the most part, uh you mentioned, [/INST] That's only because I set the Table of Contents in 1962, you have to remember </s><s>[INST] for sure there's no uh [/INST] I'm glad I didn't wait until 1965. </s><s>[INST] Uh One book. Maybe we'll touch in the bible, but one book can't always cover the entirety of everything. So I'm glad um I'm glad the table of cottons for the art of computer programming is what it is. But you did mention that uh that you thought that an understanding of the way ant colonies are able to perform incredibly organized tasks might well be the key to understanding human cognition. So these fundamentally distributed systems. So what do you think is the difference between the way Don can youth would sort a list and an ant colony would sort of list [/INST] or </s><s>[INST] performing algorithm [/INST] sorting a list isn't the same as cognition though, but but I know what you're getting at is uh So, well, the advantage of an county, at least we can see what they're doing. We know which ant has talked to each other and and and and and it's much harder with brains to know how to what extent uh neurons passing signals. So I understand that and Connie might be a, you know, if they have the secret of cognition, uh think of an ant colony as a cognitive single being rather than as a colony of lots of different ants. I mean just like the cells of our brain are and and and the microbiome and all that is interacting uh entities. But uh but somehow that I consider myself to be a single person. Well, you know, Aunt Connie, you can say it might be cognitive, cognitive and somehow and you know, I mean, you know, I okay. Uh I smashed a certain aunt and organize something that's done. What was that. But if we're going to crack the secret of cognition, it might be that we could do so by uh my psyching out how ants to it. Because we have a better chance to measure they're communicating by pheromones and by touching each other in sight but not by much more subtle phenomenon, like electric currents going through. </s><s>[INST] But even a simpler version of that. What are your thoughts of maybe Conway's game of life? [/INST] Okay, so Conway's game of life is is able to simulate any any computable process and any deterministic process is </s><s>[INST] like how you went there. I mean that's not its most powerful thing I would say. I mean uh it can simulate it. But the magic is that the individual units are distributed. Yes. And extremely simple. Yes. [/INST] We can. We understand exactly what the primitives are. </s><s>[INST] The primitives just like what the ant colony even simple. [/INST] But if we but still it doesn't say that I understand. I understand life. I mean I understand uh It gives me it gives me a better insight into what does it mean to uh to have a deterministic universe. Uh What does it mean to you? Uh to have free choice for example. But </s><s>[INST] do you think God plays dice? [/INST] Yes. I don't see any reason why God should be forbidden from using the most efficient ways to to uh to uh I mean we know that dice are extremely important in efficient algorithms. There are things that couldn't be done well without randomness. And so I don't see any reason why oh my God be </s><s>[INST] prohibited when the when the algorithm requires it? Uh Don't you don't see why the physics should constrain it. Uh So in 2000 and one you gave a series of lectures at M. I. T. About religion and science, that [/INST] was 1999, </s><s>[INST] You published. Uh so in 1999 he spent a little bit of time in boston enough to give Uh those lectures. And uh I read in the 2001 version. Uh most of it it's quite fascinating really recommend people. Uh it's transcription of your lectures. So what did you learn about how ideas get started and grow from studying the history of the bible? So you've rigorously studied a very particular part of the bible. What did you learn from this process about the way as human beings as a society develop and grow ideas, share ideas and find by those ideas. [/INST] I it's hard to summarize that. I wouldn't say that I that I learned a great deal of really definite things like where I could make conclusions but I learned more about what I don't know you have a complex subject which is really beyond human understanding. Uh So so we give up on saying I'm ever going to get to the end of the road and I'm ever going to understand it but you say, but maybe it might be good for me to uh to get closer and closer and learn more about more and more about something. And so, you know, how can I do that uh efficiently? And the answer is well used randomness. Um and so so try a random subset of the uh that that is within my grasp and and and and study that in detail instead of just uh studying parts that somebody tells me to study or instead of studying nothing because it's too hard. Um uh so I decided uh for my own amusement once that I would I would take a subset of the of the verses of the bible and I would um try to find out what the best thinkers have said about that small subset. And I had about, let's say 6 60 verses out of out of 3000, I think it's one out of 500 or something like this. And so then I went to the libraries which which are well indexed. Uh you can, you I spent uh for example at uh at boston public library, I I would go once a week for for a year. And I went to, I went to uh have done time stuff and over Harvard library to to look at this, you know, that weren't in the boston public uh where they were scholars had looked at and you can call and the and you can go down the shelves and you can pretty You can look in the index and say, Oh is there is this versus mentioned anywhere in this book. If so, look at page 105. So in other words like I could learn not only about the Bible, but about the secondary literature, about the Bible, the things that scholars have written about it. And so that that gave me a way to uh, two zoom in on parts of the thing so that I could get more, more insight. And so I look at it as, as a way of giving me some, some firm pegs, which I, which I could hang pieces of information, but not as as things where I would say. And therefore this is true </s><s>[INST] in this uh, random approach of sampling the bible. What did you learn about the most uh, you know, central uh, accumulation of ideas? And it [/INST] seemed to me that, that the main thrust was not the one that most people think of as saying, you know, don't have sex or something like this. Um, but that the main thrust was to try to, to try to figure out how to live in harmony with God's wishes. I'm assuming that God exists. And I say, I'm glad that I that there's no way to prove this, because that would, that would I would run through the proof once and then I'd forget it. And, and it would. And, and I would never, uh, speculate about spiritual things and mysteries otherwise. And I think my life would be very incomplete. So I'm, uh, so I'm assuming that God exists, but if, but a lot of the people say God doesn't exist, but that's still important to them. And so in a, in a way that might still be whether God is there or not, uh in some sense, uh guy is important to them. Is it one of the, one of the verses I studied, you can interpret it saying, you know, it's much better to be an atheist than not to care at all. So </s><s>[INST] I would say it's, yeah, similar to the P equals Np discussion, you mentioned a mental exercise that I I'd love it if you could partaken yourself uh mental exercise of being God. And so how would you, if you were God dot News, how would you present yourself to the people of earth? [/INST] You mentioned uh your love of literature. And there was there was this book that that really uh, I can recommend to you if I think yeah, the title I think is blasphemy. He talks about God revealing himself through a computer in Los Alamos. And and it uh it's the only book that I've ever read where uh the punch line was really the very last word of the book and explained the whole idea of the book. And so I don't want to give that away. But, but it's really very much about this question that that you raised. Uh, but but suppose God uh, said, okay, that my my previous uh means of communication with the world, Uh not the best for the 21st century. So what should I do now? And uh and and it's conceivable that that would uh that that God would choose the way that's described in this book. </s><s>[INST] Another way to look at this exercise is looking at the human mind, looking at the human spirit, the human life in a systematic way. [/INST] I think it's mostly you want to learn humility, you want to realize that once we solve one problem, that doesn't mean that we're all of a sudden the other problems are going to drop out and we have to realize that that uh that there are there are things beyond our beyond our our ability. Um I see hubris all around. </s><s>[INST] Yeah, well said uh if you were to run program analysis in your own life, how did you do in terms of correctness, running [/INST] time </s><s>[INST] resource use as symptomatically speaking, of course. [/INST] Okay. Yeah. Well, I would say that question has not been asked me before. Um and uh I I uhh I started out with library subroutines and and uh learning how to be a automaton that was obedient. And I had the great advantage that I didn't have anybody to blame for my failures. If I started getting not understanding something, I I knew that I should stop playing ping pong and that it was my fault that that I was I wasn't studying hard enough or something rather than that somebody was discriminating against me in some way and and uh I don't know how to avoid the existence of biases in the world, but I know that that's an extra burden that I didn't have to suffer from. Um And uh and then I I found the uh from from parents I learned uh the idea of uh altro of service to other people as being more important than than uh when I get out of stuff myself. I know that I need to I need to be happy enough uh enough in order to be able to speed up service. But I but I, you know, but I I came to a philosophy finally that that I phrase as .8 is enough. There was a TV show once called eight is enough, which was about uh you know, somebody had eight kids. Um but but I say .8 is enough, which means if I can have a way of rating happiness I think it's good design that uh to have uh to have an organism that's happy about 80% of the time. Um and it was 100% of the time. It would be like every like everybody's on drugs and and never and everything collapses, nothing works because everybody's just too happy. </s><s>[INST] Do you think you've achieved that 0.8 optimal? Uh [/INST] There are times when I when I'm down and I, you know, I mean, I know that I'm chemically that I know that I've I've actually been programmed to be uh to be depressed a certain amount of time. And and and if that gets out of kilter and I'm more depressed than you, you know, sometimes I I find myself trying to think now, who should I be mad at today? There must be a reason why I'm, you know, </s><s>[INST] but [/INST] then I realized, you know, it's just my, it's just my chemistry telling me that I'm supposed to be mad at somebody. And so I tried it and said, okay, go to sleep and get better. Um but if I'm, but if I'm not 100% happy, that doesn't mean that I should find somebody that that's screaming and try to sense them. Uh but I, but I'm saying, you know, okay, I'm not 100% happy, but, but I'm happy enough to die to be uh you know, part of a a sustainable situation. So that's kind of the, the american analysis, I do, I do converge </s><s>[INST] towards the optimal human life is a 0.8. Yeah, I hope it's okay to talk about, as you talked about previously in 6 2006, you were diagnosed with prostate cancer, has that encounter with mortality changed you in some way or the way you see the world. [/INST] Yeah, it did the first car with mortality when my, when my dad died and I went through a month when I it sort of came to uh you know, uh be comfortable with the fact that I was going to die someday. Uh and during that month, uh I don't know. Uh I uh I felt okay, but I couldn't sing and I and I and I couldn't do original research either. I I sort of remember after three or four weeks, the first time I started having a technical thought, that made sense and was maybe slightly creative. I could sort of feel that that that something was starting to move again, but that was, you know, so I felt very empty for until I came to grips with. Yes, I learned that this is sort of a standard grief process that people go through. Okay. So then now I'm at a point in my life Even more so than in 2006 where where all of my goals have been fulfilled except for finishing the art of computer programs. Um I I uh I had one major unfulfilled goal that I've wanted all my life to to write a piece of a piece of music that and I had an idea for uh for for a certain kind of music that I thought ought to be written at least somebody ought to try to do it. And I and I felt that it was that uh it wasn't gonna be easy, but I wanted to, I wanted a proof of concept, I wanted to know if it was going to work or not. And so I spent a lot of time And finally I finished that piece and we had uh we had the uh world premiere last year on my 80th birthday and we had another premier in Canada. And there's talk of concerts in Europe and various things so that, but that's done. It's part of the world's music now and it's either good or bad, but I did what I was hoping to do. So the only thing that I uh that that I have on my agenda is to, is to try to do as well as I can with the art of computer programming until I go casino. </s><s>[INST] Do you think there's an element of .8 that might point [/INST] eight? </s><s>[INST] Yeah. Well [/INST] I look at it more that I got actually 2 to 1.0 uh when, when that concert was over with. Um, I mean, I, you know, I, So in 2006 I was at .8. Um so, so when, when I was diagnosed with prostate cancer, then I said, Okay, well maybe this is, you know, I've had all kinds of good luck all my life and there's no, I have nothing to complain about. So am I die now. Um and we'll see what happened. And so, so it's quite seriously, I went and I didn't, I had no expectation that I deserved better. Um I didn't make any plans for the future. I had my surgery. I came out of the surgery and uh, spend some time learning how to walk again and so on has been, you know, it's painful for a while. Um, but I got home and I realized I hadn't really thought about what, what to do next. I hadn't, I hadn't any expected, you know, I said, okay, hey, I'm still alive, okay, now I can write some more books, but I didn't come with the attitude that, you know, uh, you know, this was, this was terribly unfair and uh, and uh, I just said, okay, I I was accepting whatever turned out. Uh, you know, I had gotten, I got more than my share already, so why should I? Uh, I didn't, and I really, when I got home, I I realized that I had really not thought about the next step what I would do after I would, after I would be able to work again, I had sort of thought of it as if as this might I was comfortable with the fact that it was at the end. Um, but but I was hoping that I would still be able to Uh, learned about satisfy ability and, and uh, also someday write music. I didn't start, I just started seriously on the music project until 2012, </s><s>[INST] so I'm gonna be in huge trouble if I don't talk to you about this. Uh, in, in the seventies, you've created the tech typesetting system together with megafon language for font description and computer modern family of typefaces. That has basically defined the methodology in the aesthetic of the countless research fields, right, Math, physics, uh beyond computer science and so on. Okay, well, first of all, thank you. I think I speak for a lot of people and saying that. But the question in terms of beauty, there's a beauty to typography that you've created. And yet beauty is hard to quantify. Um How does one create beautiful letters and beautiful equations? Uh Like what? So perhaps there's no words to be describing uh be describing the process, but [/INST] so the great uh Harvard mathematician, George D. Birkhoff wrote a book in the 30s called aesthetic measure, where he where he would I have pictures of vases and underneath would be a number. And this was how beautiful the base was. And he had a formula for this. And and he actually author right, how brought about music. And so he could he could uh you know, so I thought maybe I was part of my musical composition. I would try to uh program is algorithms and, you know, so that I would write something that had the highest number by his score. Well, it wasn't quite rigorous enough for for a computer to do. But anyway, people have tried to to put numerical value on beauty, but and he did probably the most serious attempt. And George Gershwin's teacher also wrote two Vines where he talked about his method of composing music. But you're talking about another kind of beauty and beauty and letters and </s><s>[INST] letter but whatever that right. [/INST] So uh and so that's uh in the eye of the beholder as they say, but can striving for excellence in whatever definition you want to give to beauty. Then you try to get as close to that as you can. Somehow with </s><s>[INST] I guess I guess I'm trying to ask and there may not be a good answer. Uh What loose definitions were you operating under with the community of people that you're working on [/INST] the loose definition? I wanted I wanted to appeal to me to me. I mean you personally, </s><s>[INST] that's a good start. [/INST] No, and it failed that test when when I got volume two came out with the new printing and I was expecting to be the happiest day of my life. And I I felt a like a burning like how angry I was that I opened the book and it was in the same beige covers. And but it didn't look right on the page. Uh number two was particularly ugly. I couldn't stand any page. Had two in his page. Number. Um and I was expecting that it was, you know, I spent all this time making measurements and I had looked at stuff in different, different ways. And I I had I had a great technology. But but it did, you know, But I But I wasn't done. I had I had to return the whole thing after 1961. </s><s>[INST] Has it ever made you happy? Finally? [/INST] Oh, yes. Or </s><s>[INST] is it a point to [/INST] know? And so many books have come out that would never have been written without this? I just just draw interest. It's a joy. But I can. But now I I mean all these pages that are sitting up there, I I don't have a uh if I didn't like him, I would change it. Like that's my no, nobody else has this ability. They have to stick with what I gave them. </s><s>[INST] So in terms of the other side of it and there's the topography. So the look of the of the type and the curves and the lines. Uh What about the spacing? [/INST] What about </s><s>[INST] the spacing between the white space? Uh It seems like you could be a little bit more systematic about the layout [/INST] or technical. </s><s>[INST] Yeah. You can [/INST] always go further, I I didn't I didn't stop at .8. I started but I stopped about .98. </s><s>[INST] Uh seems like you're not following your own rule uh for happiness or is [/INST] No, no, no, I uh there is. Ok, of course, they're just What is the Japanese, where wabi sabi or something where the the most beautiful works of art are those that have flaws because then the person who who perceives them as their own uh appreciation and that give if you were more satisfaction or so on. But but I but no, no with typography I wanted it to look as good as I could in the vast majority of cases. And then when it doesn't then I Uh I say Okay that's 2% more work for the for the author. But but I didn't want I didn't want to say that my job was to get 200% uh and take all the work away from the author. That's what I meant by that. </s><s>[INST] So if you were to venture a guess how much of the nature of reality do you think we humans understand? So you mentioned you appreciate mystery. How much of the world about us is shrouded in mystery are we are we uh if you were to put a number on it, [/INST] what </s><s>[INST] what percent of it all do we understand? Are we totally [/INST] How many leading Zeros .0.00? I don't know. I think it's infinite decimal. </s><s>[INST] How do we think about that? And what do we do about that? Do we continue one step at a time? [/INST] Yeah, we muddle through. I mean we do our best we realize that nobody's perfect. Then we and we try to keep advancing but we don't uh spend time saying uh we're not there. We're not all the way to the end. Uh some some mathematicians that that would be an office next to me when I was in the math department, they would never think about anything smaller than a countable infinity. And I never you know, we intercepted a countable infinity because I rarely got up to a countable infinity. I was I was talking about finance stuff. But but even even limiting to finance stuff, which is which is uh which the universe might be uh there's no no way to really know whether the universe is isn't isn't uh just made out of capital. And uh whenever, you know, you want to call them quirks or whatever where capital and has some fun. A number, all of the numbers that are comprehensible are still way smaller than most. Almost all finite numbers. I got this one paper uh called supernatural numbers. Where I what I guess you probably ran into something called canoes. Arrow notation. Did you ever run into that were anyway? So you take the number, I think it's like I and I called it super K. I named it after myself. But it's it's but a rotation is something like 10 and then four arrows in a three or something like okay, no, the arrow notation, if you have, if you have no arrows, that means multiplication, X Y means um X times X times X times X Y times if you have one arrow, that means exponentially ation. So X one arrow, I mean X to the extra the extra the extra the excellent uh Y times. So I found out by the way that this this notation was invented by a guy in 18 30. And uh and he was he was a a one of the english nobility who who spent his time thinking about stuff like this. Um And uh it was exactly the same concept that I that I that I used arrows and he used a slightly different notation. But anyway, this and then this Ackermann's function is based on the same kind of ideas, but Ackerman was 1920s. But anyway, you got this number 10 quadruple arrow, three. So that that says, well we take, you know, we take 10 to the 10 to the 10 to the 10 to the 10 to the 10th. And how many times do we do that? Oh, 10 double 02 times or something. I mean, how tall is that stack? But but then we do that again, because that was only 10. Triple or quadruple or to quadruple our three maybe </s><s>[INST] pretty large number. It [/INST] gets way beyond comprehension. Okay. Uh and uh and so But it's so small compared to what finite numbers really are, because I want to use four arrows. And you know, 10 and a three, I mean let's have that, let's have that many number of arrows. I mean </s><s>[INST] the boundary between infinite and finite is incomprehensible for us humans. Anyway, [/INST] infinity is a good is a useful way for us to think about extremely large, extreme, extremely large things. and uh, and, and, and we can, we can manipulate it but, but we can never know that the universe is actually and we're near that. So uh, it just uh, so I realized how little we know uh, but we found an awful lot of uh things that are too hard for any one person to know even even in our small universe. </s><s>[INST] Yeah and we did pretty good. So ah when you go up to heaven and meet God And get to ask one question that would get answered, what question would you ask? I don't [/INST] know. What kind of browser do you have up here. No, I actually, I don't think it's meaningful question but I certainly hope we have good internet. </s><s>[INST] Okay on that note, that's beautiful actually. Uh Don thank you so much. It was a huge honor to talk to you really [/INST] well. Thanks for the government of questions. </s><s>[INST] Yeah, it was fun. Thanks for listening to this conversation with donald Knuth. Thank you to our presenting sponsor cash app, download it, use code lex podcast. You'll get $10.10 dollars will go to first a stem education non profit that inspires hundreds of thousands of young minds to learn and to dream of engineering our future. If you enjoy this podcast, subscribe on youtube, give it five stars on apple podcast, support on patreon or connect with me on twitter and now let me leave you with some words of wisdom from Donald Knuth. We should continually be striving to transform every art into a science. And in the process, we advance the art. Thank you for listening and hope to see you next time. [/INST] </s> |
<s>[INST] So maintaining that strength, but also doing the cardio for, for the longevity for the avoiding the heart disease. Yeah, I definitely just like with fasting have the philosophical benefit of running long and running slow I enjoy because it kind of clears the mind and wants you to think actually listen to brown noise as I run. It really helps remove myself from the world and just like zooming in on particular thoughts. [/INST] What are the brown noise? </s><s>[INST] It's like white noise but deeper. So like the white noise is like and then brown noise is more like, oh, like ocean. [/INST] That sounds great. I might try that. </s><s>[INST] Yeah. Yeah, it's a [/INST] small smoothing probably. </s><s>[INST] I'm not sure there could be science to this. I need to look this up. I've been meaning to but I've, when I started uh this is maybe like five years ago I started losing [/INST] brown noise when I work </s><s>[INST] and uh the first time I listened to it, something happened to my mind where it just went like zoomed in to like in a way that it felt like really weird like how, how precisely it was able to sort [/INST] of remove </s><s>[INST] the distractions of the world and really helped my mind. Obviously like the mind is trying to focus and then it just enabled that process of trying to focus on a particular problem. I don't know if this general Izabal to others people should definitely try it. If you're listening to this. Maybe it's just my own mind, but it's funny like it made me brown noise made me realize that there's probably hacks out there that work for me that I should be constantly looking for. It's almost like a and encouraging and motivating of event that maybe there's other stuff out there. Maybe there's other brown Noise like things out there that truly like almost immediately make me feel better. I don't know if it's journalism to others, but it does seem that it's the case that there's probably for many others, things like that that could be discovered. And so it's always disappointing when I find things in life that I wish I would found earlier. Like I got LASIK eye surgery a few years ago and the first thought I had like the next day when I woke up is like damn it. Why didn't I do this way earlier. There's all this stuff of that nature that they're yet to be discovered. So it pays to explore. [/INST] Yeah. So you have a different mind. You have quite a beautiful mind. So I suspect brown Noise helps you focus because you're probably all over the place if you don't control it. </s><s>[INST] Yeah, exactly. I mean something about it, There's a programmer thing. I don't, the program is a really difficult um mental journey because you have to keep a lot of things in mind. You have to, uh so you're constantly designing things. Then you have to be extremely precise by making those things concrete, encode your also have to look stuff up on the internet to sort of feed like information and looking up stuff on the internet. Internet is full of like distracting things, you have to be really focused in the way you look stuff up in pulling that information. And so it requires a senator discipline and a certain focus that uh I've been very much exploring how to do like I do it really well in the morning, coffee is involved all those kinds of things. You're trying to optimize uh keeping very positive inspired, no social media, all those kinds of things and trying to optimize for and everybody has their own kind of little journey that they try to understand. You get this from like writers when you read about the habits of writers, Like the habits they do in the morning, they usually write like 234 hours a day and that's it. It's like they optimize that ritual. And then there's always hunter? S Thompson. So uh sometimes it pays off to be wild. What about sleep? How important is sleep for longevity, [/INST] I would guess based on the evidence that it's really important and Because we don't know for sure. But what we know from animal studies is the following. If you restrict sleep from a rat for just two weeks, it will develop type two diabetes, it's that important. Um So that's the main thing, what we also know is at the molecular level that if you disrupt your sleep wake cycle, so we actually have proteins that go up and down the control our sleep wake, all of us, most of ourselves do that. If you disrupt that, you'll get premature aging and guess what the opposite is true that as you get older, that cycle, the amplitude becomes diminished and this is why it's harder to get to sleep as you get older and then you've got all sorts of problems. And I think what's going on is there's a positive feedback loop, which is a disaster in your old age, which is you're aging, you can't at this moment totally prevent that. And then it's disrupting your sleep and you get not enough sleep and then that's going to accelerate your aging process. Um and so it's known that the people who are shift workers are most susceptible to certain age related diseases. So your bottom line, you definitely want to work on that. It's one of the reasons I have this ring on my finger, which helps me optimize my sleep and learn what I do the day before. If it was a bad idea and I'll stop doing that. Like eating a fried chicken. I </s> |
<s>[INST] I want to try to elaborate on the nature of the disagreement you have with thomas Kuhn. So do you still believe in paradigm shifts? Do you still see that there is ideas that really have a transformational effect on science? You just the nature of the disagreement has to do with how those paradigm shifts come to be, [/INST] how they come to be and how they change, I certainly think they exist, how strong they may be at any given time is maybe not quite as powerful as tom thought in general, although towards the end of his life he was beginning to develop different modifications of his original way of thinking, but I don't think that the changes happen quite so uh neatly if you will in reaction to um novel experimental observations, they get much more complex than that </s><s>[INST] in terms of neatness, how much of science progresses by individual lone geniuses and how much by the messy collaboration of competing and um cooperating humans. [/INST] I don't think you can cut that with a knife to say it's this percent and that percent. It's Almost always the case that there are one or 2 or maybe three individuals who are sort of central to what goes on when things begin to shift. Are they inevitably and solely responsible for what then begins to happen in a major way? I think not, it depends, you can go very far back with this uh even into antiquity to see what goes on. Um the locus, the major locus we always talk about from the beginning is if you're talking about Galileo's work on motion for example? Uh Were there ways of accommodating it that others could adapt to without buying into the whole scheme? Yes. Um did it eventually evolve and start convincing people because you could also do other things with it that you couldn't otherwise do also. Yes. Let me give you an example, the great french mathematician, philosopher Day Card who was a mechanical philosophy believed the world was matter in motion. He never thought much of what Galileo had done in respect to motion because he thought well it bested some sort of approximated scheme or something like that. But one of his initial, I wouldn't call him a disciple but follower who then broke with him in a number of ways was a man named christian huygens who was along with Newton, one of the two greatest Scientists of the 17th century Huygens is older than Newton and Huygens nicely deployed galilean relationships in respect to motion to develop all sorts of things including the first pendulum governed clock and even figured out how to build one which is keeps perfect time. Except it didn't work. But he had the mathematical structure for it. </s><s>[INST] How well known as a very well known should I be? Should I know him well? Yes, you should interesting. [/INST] You should definitely know him. </s><s>[INST] No, no. Can we can we define should here because I don't write [/INST] um so </s><s>[INST] uh so this should like uh uh yeah, can you define, should [/INST] should mean this um if you had taken up to a second year of physics courses you should you would have heard his name because one of the fundamental principles and optics is called huygens principle. Okay, okay. </s><s>[INST] Yeah. So I have and I have heard his name. There you go. No, but I don't [/INST] remember, you don't remember. </s><s>[INST] So I mean there's there's a very different thing between names attached to principles and laws and so on that you sometimes let go of you just remember the equations of the principles themselves and the personalities of science and there's certain personalities, certain human beings that stand out. And that's why there is a sense to which the lone inventor, the loan scientists is the way I personally, I mean I think a lot of people think about the history of science is these lone geniuses without them the senses. If you remove newton from the picture, if you remove go live from the picture, then science would there's almost a feeling like it would just have stopped there. Or at the very least there's a feeling like it would take much longer to develop the things that were developed. Is that a silly way to look at the history? [/INST] It's not entirely incorrect I suppose. Yeah. I find it difficult to believe that had Galileo not existed that eventually someone like huygens for instance, given the context of the times, what was floating around uh in the belief structure concerning the nature of the world and so on. The developments in mathematics and what not that sooner or later, whether it would have been exactly the same or not, I cannot say. But would things have evolved. Yes. </s><s>[INST] If we look at the long arc of history of science from, from back when we were in the caves Trying to knock two rocks together or maybe make a basic tool two a long time from now. Many centuries from now when human civilization finally destroys itself. If you look at that history and imagine you're a historian at the end, like would they fire the apocalypse coming upon us And you look back at this time in the 21st century? How far along are we on that ark? Do you do since have we invented and discovered everything that's to be discovered or are we at like below 1%. Uh [/INST] huh. Well, you're </s><s>[INST] going to get a lot of absurd questions today. [/INST] A positive. It's a lugubrious picture you're painting there. </s><s>[INST] I don't even know what the word means, but I love [/INST] it. The debris is well. Um, let me try and separate the question of whether we're all going to die in an apocalypse in several 100 years or not um from the question of where science may be sitting, </s><s>[INST] take this consumption. [/INST] Okay. Um, I find that hard to say and I find it hard to say because in the deepest sense of the term as it's usually deployed by philosophers of science today, I'm not fundamentally a realist. That is to say. I think our access to the inner workings of nature is inevitably mediated by what we can do with the materials and factors around us. We can probe things in various ways. Does that mean that I don't think that the the standard model in quantum electrodynamics is of course not. I wouldn't even dream of saying such a thing. It can do a lot, especially when it comes to figuring out what's happening in very large expensive particle accelerators and applying results in cosmology and so on as well. Um do I think that we have inevitably probed the depths of reality through this? I do not agree with steven Weinberg, who thinks we have about such things, do I? On the other hand, think that the way in which science has been moving for the last 100 years, physics in particular is what I have in mind uh will continue on the same course in that sense, I don't because we're not going to be building bigger and bigger and more and more expensive machines to rip apart particles in various ways, in which case, what are physicists going to do, they'll turn their attention to other aspects. There are all sorts of things we've never explained about the material world. We don't have theories that go beyond a certain point for all sorts of things. We can't, can we, for example, start with the standard Model and work our way up all the way to chemical transformations. You can make an argument about it and you can justify things, but that's in chemistry, that's not the way people work. They work with much higher level quantum mechanical relationships and so on. So this notion of the deep theory to explain everything is a longstanding belief um which goes back pretty far, although I think it only takes its fullest form Sometime in towards the end of the 19th century. </s> |
<s>[INST] You know, To me, it's fascinating for being humble. Like the humans cannot possibly be the most amazing thing that such if you look at the entirety of the system that leads small and you paint that cannot possibly be the most amazing thing that process generates. So like if you look at the evolution, what's the equivalent in the cosmological evolution and its selection for technology, the equivalent of the human eye or the human brain universes that are able to do some, like they don't need the damn stars. They, they're able to just do some incredible generation of complexity fast on like much more than if you [/INST] think about it's like most of our universe </s><s>[INST] is pretty freaking boring. There's not much going on. It's a few rocks flying around and there's some like apes that are just like um doing podcasts, something weird on some weird planet. It just seems very inefficient. If you think about like the amazing thing, the human eye, the visual cortex can do the, the brain nervous of everything that makes us more powerful than single cell organisms. Like if there's an equivalent of that for universes there, like the richness of physics that could be uh that could be expressed through a particular set of parameters. Like, I mean that like for me, I'm so from a computer science perspective, huge fan of cellular automata, which is a nice sort of pretty visual way to illustrate how different laws can result in uh drastically different levels of complexity. So like it's like, yeah, okay, so we're all like celebrating, [/INST] look our little cellular tom and is able to generate </s><s>[INST] pretty triangles and squares and therefore we achieve general intelligence. And then there will be like some badass chuck Norris type, like uh universal turing machine type of cellular automata, they're able to generate other cellular automata that does any arbitrary level of computation off the bat it like those have to then exist. And then we're just like this, we're just, we'll be forgotten. Is this story, this is uh, this podcast just entertains a few other apes for for [/INST] a few months. Well, I'm kind of surprised to hear your cynicism. I'm very, I usually think of you as like a one who celebrates humanity in all its forms and things like that and I guess I just, I don't, I see it the way you just described. I mean, Okay, five, we've been here for 13.7 billion years and you're saying, gosh, that's a long time. Let's get on with the show already. Some other universe could have kicked our butt by now, but That's putting a characteristic time. I mean, why is 13.7 billion a long time? I mean, compared to compared to what I guess. So when I look at our universe, I see this extraordinary hierarchy that has developed over that time. So at the beginning it was a chaotic mess of you know, some plasma, nothing interesting going on there. And even for the first stars to form that a lot of really interesting uh evolutionary processes had to occur by evolutionary in that sense. I just mean, um taking place over extended periods of time and structures are forming then. And then it took that first generation of stars in order to produced the medals that uh, that then can more efficiently produce another generation of stars. We're only the third generation of stars. So we might still be pretty quick to the to the game here. So, but I don't think I don't Okay, so then, so then you have these stars that you have solar systems on those solar systems, you have, um, rocky worlds, you have gas giants, like all this complexity and then you start getting life and the, the complexity that's evolved through the evolutionary process in life forms is just, it's not a letdown to me just </s><s>[INST] and there's some of it is like some, some of the planet's is like, I see like different flavors of ice cream there. I see, but there might be water under all kinds of life forms and some volcanoes, all kinds of weird stuff. No, no, I, I don't, I think it's beautiful. I think our life is beautiful and I think it was designed that by, by design the scarcity of the whole thing. I think mortality as terrifying as it is. As fundamental to the whole reason we enjoy everything. No, I think it's beautiful. I just think that all of us, um conscious beings in the grand scheme of basically every scale will be completely forgotten. [/INST] Well that's true. I think everything is transient and that would go back to maybe something more like loud to the Tao Beijing or something where it's like, yes, there is nothing but change, there is nothing but emergence and dissolve and that that's it. But I just in this picture of this hierarchy that's developed, I don't mean to say that now it gets to us and that's the pinnacle. In fact, I think the, at a high level the story I'm trying to tease out in my research is about, Okay, well, so then what's the next level of hierarchy? And if and if it's okay, we're kind of pretty smart. I mean, talking about people like lee small and alan goose max, Take Mark. Okay, we're really smart talking about me. Okay, we're kind of, we can find our way to the grocery store or whatever, but but what's next? You know, I mean, what if, what if there's another level of hierarchy that grows on top of us that is even more profoundly capable? And I mean, we've talked a lot about super conducting sensors. Imagine these uh cognitive systems far more capable than us residing somewhere else in the solar system off of the surface of the earth, where it's much darker, much colder, much more naturally suited to them. And they have these sensors that can detect single photons of light uh, from radio waves out too, all across the spectrum to gamma rays and just see the whole universe. And they just live in space with these massive um collection optics so that they what do they do? They just look out and and experience that that vast array of of what's being developed. </s> |
<s>[INST] with what chat GPT had done in that case. Yeah. The interesting things about the LLMs, like you said, that they are very willing to admit their error. [/INST] Well, yes. I mean, that's a question of the reinforcement learning human feedback thing. Oh, right. That's the really remarkable thing about chat GPT is I had been following what was happening with large language models and I'd played with them a whole bunch and they were like, it's like what you would expect based on statistical continuation of language. It's interesting, but it's not breakout exciting. I think the human feedback reinforcement learning and making chat GPT try and do the things that humans really wanted to do, that broke through, that reached this threshold where the thing really is interesting to us humans. And by the way, it's interesting to see how you change the temperature or something like that, the thing goes bonkers and it no longer is interesting to humans. It's producing garbage And it's kind of right. Somehow it managed to get above this threshold where it really is well aligned to what we humans are interested in. And I think nobody saw that coming, I think. Certainly nobody I've talked to and nobody who was involved in that project seems to have known it was coming. It's just one of these things that is a sort of remarkable threshold. I mean, you know, when we built Wolfram Alpha, for example, I didn't know it was going to work. You know, we tried to build something that would have enough knowledge of the world, that it could answer a reasonable set of questions, that we could do good enough natural language understanding, that typical things you type in would work. We didn't know where that threshold was. I mean, I was not sure that it was the right decade to try and build this, even the right, you know, 50 years to try and build it. You know, and I think that was the same type of thing with chat GPT, that I don't think anybody could have predicted that, you know, 2022 would be the year </s><s>[INST] that this became possible. I think, yeah, you tell a story about Marvin Miski and showing it to him [/INST] and saying that like, no, no, no, this time it actually works. Yes. Yes. And I mean, you know, it's the same thing, for me looking at these large language models, it's like when people are first saying the first few weeks of chat GPT, it's like, oh, yeah, you know, I've seen these large language models, um, and then, uh, you know, and then I actually try it and, uh, you know, oh my gosh, it actually works. And I think it's, but you know, the things and, you know, the thing I found, you know, I remember one of the first things I tried was write a persuasive essay that a wolf is the bluest kind of animal. Okay? So it writes this thing and it starts talking about these wolves that live on the Tibetan plateau and named some Latin name and so on. And I'm like, really? And I'm starting to look it up on the web. And it's like, well, it's actually complete nonsense, but it's extremely plausible. I mean, it's plausible enough that I was going and looking up on the web and wondering if there was a wolf that was blue. You know, I mentioned this on some live streams I've done. And so people have been sending me these blue wolves. </s><s>[INST] Maybe I was on to something. Can you kind of give your wise sage advice about what humans who have never interacted with AI systems? Not even like with Wolfram Alpha are now interacting with Chad GPT because it becomes, it's accessible to a certain demographic. They may have not touched AI systems before. What do we do with truth? Like journalists, for example, how do we think [/INST] about the output of these systems? I think this idea, the idea that you're going to get factual output is not a very good idea. I mean, it's just, this is not, it is a linguistic interface. It is producing language and language can be truthful or not truthful. And that's a different slice of what's going on. I think that, you know, what we see in for example kind of, go check this with your fact source, for example. You can do that to some extent, but then it's going to not check something. That is again a thing that is sort of a, does it check in the right place? I mean we see that and does it call the Wolfram plug-in in the right place? You know, often it does. Sometimes it doesn't. I think the real thing to understand about what's happening is, which I think is very exciting, is the great democratization of access to computation. I think that when you look at... There's been a long period of time when computation and the ability to figure out things with computers has been something that only the druids at some level can achieve. I myself have been involved in trying to de-druidify access to computation back before Mathematica existed in 1988. If you were a physicist or something like that and you wanted to do a computation, you would find a programmer. You would go and delegate the computation to that programmer. Hopefully, they'd come back with something useful. Maybe they wouldn't. There'd be this long multi-week loop that you go through. It was actually very, very interesting to see, 1988. People like physicists, mathematicians, and so on. Then lots of other people. There's very rapid transition of people realizing they themselves could actually type with their own fingers and make some piece of code that would do a computation that they cared about. It's been exciting to see lots of discoveries and so on made by using that tool. We see the same thing Wolfram Alpha is dealing with is not as deep computation as you can achieve with whole Wolfram Language Mathematica stack. The thing that's, to me, particularly exciting about the large language model linguistic interface mechanism is it dramatically broadens the access to deep computation. One of the things I thought about recently is what's going to happen to all these programmers? What's going to happen to all these people who, a lot of what they do is write slabs of boilerplate code? In a sense, I've been saying for 40 years, that's not a very good idea. You can automate a lot of that stuff with a high enough level language, that slab of code that's designed in the right way, that slab of code turns into this one function we just implemented that you can just use. In a sense, the fact that there's all of this activity of doing lower level programming is something, for me, it seemed like I don't think this is the right thing to do. Lots of people have used our technology and not had to do that, but the fact is that when you look at computer science departments that have turned into places where people are learning the trade of programming, so to speak, it's a question of what's going to happen. I think there are two dynamics. One is that boilerplate programming is going to go the way that assembly language went back in the day of something where it's really mostly specified at a higher level. You start with natural language, you turn it into a computational language, you look at the computational language, you run tests, you understand that's what's supposed to happen. If we do a great job with compilation of the computational language, it might turn into LLVM or something like this, or it just directly gets run through the algorithms we have and so on. That's a tearing down of this big structure that's been built of teaching people programming. On the other hand, the other dynamic is vastly more people are going to care about computation. All those departments of art history or something that really didn't use computation before now have the possibility of accessing it by virtue of this linguistic </s> |
<s>[INST] Again, [/INST] UNIX </s><s>[INST] started being developed 50 years ago. It would be more than 50 years ago. Can you tell the story? Like you describe your new book of how UNIX was created [/INST] ah if I can remember that far back, it was some while ago. Um, so I think the gist of it is that at Bell Labs in 1969 there were a group of people who had just finished working on the Multex project which was itself a follow on to C. T. S. S. So we can go back sort of an infinite regress in time. But the uh CT ss was very very very nice time sharing system. It was very nice to use. I actually used it as that summer I spent in Cambridge in 1966. </s><s>[INST] What was the hardware there? So what's the operating system? What's the hardware there? What's the CTS look like? [/INST] So C. T. S. S looked like uh kind of like a standard time sharing system? Certainly at the time it was the only time sharing. If no, let's </s><s>[INST] go back to the basic, what's it time for my system? [/INST] Okay. In the beginning was the word and the word. </s><s>[INST] And then there was time sharing systems. [/INST] Yeah. If we go back into, let's call it the 1950s and early 1960s, most computing was done on very big computers, physically big, although not terribly powerful by today's standards that were maintained in very large rooms and you use things like punch cards to write programs on and talk to him. So you would take a deck of cards, write your program on it and send it over a counter handed to an operator and some while later back would come something that said, oh you made a mistake and then you'd recycle. And so it's very very slow. So the idea of time sharing was that you take basically that same computer but connect to it with something that looked like an electric typewriter that could be a long distance away. It could be closed. But fundamentally what the operating system did was to give each person who was connected to it and wanting to do something a small slice of time on uh to do a particular job. So I might be editing a file so I would be typing. And every time I hit a keystroke the operating system would wake up and said oh he typed character, let me remember that. Then you go back to doing something else would be going around and around a group of people who were trying to get something done giving each a small slice of time and giving them each the illusion that they pretty much had the whole machine to themselves. And hence time sharing. That is sharing the computing time resource of the computer among a number of people who are doing it </s><s>[INST] without the individual people being aware that there's others in a sense the illusion the feeling is that the machine is your own. [/INST] Pretty much that was the idea. Yes you had if it were well done and if it were fast enough and other people were doing too much you did have the illusion that you had the whole machine to yourself and it was very much better than the punch card model. And so C. T. S. S. The compatible time sharing system was I think arguably the first of these, it was done I guess technically 64 or something like that. It ran on an IBM 70 94 slightly modified to have twice as much memory as the norm. It had two banks of 32 K words instead of one. So </s><s>[INST] 32 K words. Each word [/INST] was 36 beds. So call it you know about 100 and 50 kilobytes times two. So by today's standards that's down in the noise </s><s>[INST] but at the time [/INST] that was a lot of memory and memory was expensive. So C. T. S. S. Was just a wonderful environment to work on. It was done by the people that M. I. T. Led by uh Fernando Corbett over Corby who died just earlier this year. Um and a bunch of other folks and then so I spent the summer of 66 working on that had a great time. Uh meant a lot of really nice people. And indirectly uh knew of people at Bell labs who were also working on a follow on to C. T. S. S. That was called multiplex. The multiplex was meant to be the system that would do everything that C. T. S. S. Did but do it better for a larger population </s><s>[INST] all the usual stuff. Now the actual time sharing the scheduling. Uh how much what's the algorithm that performs the scheduling? What's that look like? How much magic is there? What are the metrics? How does it all work in the beginning? [/INST] So the answer is I don't have a clue. I think the basic idea was nothing more than who all wants to get something done. Suppose that things are very quiet in the middle of the night then I get all the time that I want. I suppose that you and I are contending at high noon for something like that then probably the simplest algorithm is a round robin one that gives you a bit of time, gives me a bit of time and then we could adapt to that. Like what are you trying to do? Are you text editing or are you compiling or something? And we might adjust the schedule according to things like that. </s><s>[INST] So Okay, so Multex was trying to just do some of the clean it up a little bit. Well, [/INST] it was it was meant to be much more than that. So Multex was the multiplex information and computing service and it was meant to be a very large thing that would provide computing utility. Something that where you could actually think of it as just a plug in the wall service sort of like cloud computing today. Same idea. But 50 odd years earlier. And so uh what Multex offered was a richer operating system environment piece of hardware that was better designed for doing the kind of sharing of resources and presumably lots of other things. </s> |
<s>[INST] it's a little too abstract. There's useful elements to it in that it helps us understand our own ethical codes, humans. So even just as a thought experiment, if you imagine that an A. G. I. System is here today, how would we program? It is a kind of nice thought experiment of constructing how should we have a [/INST] law, </s><s>[INST] have a system of laws for us humans. It's just a nice practical tool and I think there's echoes of that idea too in the ai systems we have today, they don't have to be that intelligent like autonomous vehicles. These things start creeping in that there were thinking about but certainly they shouldn't be framed as as hell. Yeah. Looking back, what is the most, I'm sorry if it's a silly question, but what is the most beautiful or surprising idea in deep learning or ai in general that you've ever come across sort of personally when you said back and I just had this kind of uh that's pretty cool moment. That's nice surprising. [/INST] I don't know if it's an idea rather than sort of empirical fact. The fact that you can build gigantic neural nets, trained, trained them on relatively small amounts of data relatively with two guest agreed in the center that it actually works breaks everything you read in every textbook right? Every pre deployment text book that told you you need to have fewer parameters and you have data samples, um, you know, if you have a non convex objective function, you have no guarantee of convergence, you know, all those things that you read in textbooks and they tell you stay away from this and they're all wrong. </s><s>[INST] The number of parameters non convex and somehow, which is very relative to the number of parameters, data. It's able to learn anything. Does that still surprise you today? [/INST] Well, it was kind of obvious to me before I knew anything that this is a good idea. And then it became surprising that it worked because I started reading those textbooks. Okay, </s><s>[INST] so, okay, you know, we talked to the intuition of why I was obviously if you remember. [/INST] Well, okay, so the intuition was it's it's sort of like, you know those people in the late 19th century who proved that heavier than air flight was impossible, right? And of course you have birds, right? They do fly. And so on the face of it, it's obviously wrong as an empirical question. Right? So we have the same kind of thing that you know, the we know that the brain works, we don't know how, but we know it works and we know it's a large network of neurons and interaction. And learning takes place by changing the connection. So kind of getting this level of inspiration without covering the details, but sort of trying to derive basic principles, you know, that kind of gives you a clue as to which direction to go. There's also the idea somehow that I've been convinced of since I was an undergrad, that even before that intelligence is inseparable from learning. So you the idea somehow that you can create an intelligent machine by basically programming for me, it was a non starter for, you know, from the start, every intelligent entity that we know about arrives at this intelligence through learning. So learning, you know, machine money was completely obvious path. Uh also because I'm lazy, so you know, </s><s>[INST] the automated, basically everything and learning is the automation of intelligence? So do you think? So what is learning then? What falls under learning? Because do you think of reasoning as learning [/INST] what our reasoning is? Certainly a consequence of learning as well, just like other functions of the brain. The big question about reasoning is how do you make reason incomparable with gradient based learning? </s><s>[INST] Do you think neural networks can be made to reason? [/INST] Yes, there's no question about that. Again, we have a good example, right? The question is how So the question is how much prior structure you have to put in the neural net so that something like human reasoning would emerge from it, you know, from running. Another question is all of our kind of model of what reasoning is that are based on logic are discrete and and are therefore incompatible with great and based learning. And I was very strong believer in this idea of granting based learning. I don't believe that other types of learning that don't use kind of gradient information if you want. </s><s>[INST] So you don't like discrete mathematics. You don't like anything discrete. [/INST] Well that's, it's not that I don't like it, it's just that it's invaluable. We're learning and I'm a big fan of learning. Right? So in fact that's perhaps one reason why deep learning has been kind of looked at with suspicion by a lot of computer scientists because the matter is very different the matter you use for deep learning, you know, we kind of has more to do with, you know, cybernetics, uh kind of Matthew doing electrical engineering than the kind of Matthew doing computer science and and you know nothing in in machine learning is exact right. Computer science is all about sort of you know, obviously compulsive attention to details of like you know every index has to be right and you can prove that an algorithm is correct, right? Machine learning is the science of sloppiness really, </s><s>[INST] That's beautiful. So okay, maybe let's feel around in the dark of what is a neural network that reasons or a system that his works with continuous functions that's able to do ah build knowledge. However we think about reasoning, build on previous knowledge, build on extra knowledge, create new knowledge, generalist outside of any training set ever built. What does that look like if Yeah, maybe you have inklings of thoughts of what that might look like? [/INST] Well, yeah, I mean yes or no, if I had precise ideas about this, I think, you know, we'll be building it right now but there are people working on this or whose main research interest is actually exactly that. Right? So what you need to have is a working memory. So you need to have some device, if you want some subsystem they can store a relatively large number of factual episodic information for, you know, a reasonable amount of time. So you, you know, in the in the brain for example the kind of three main types of memory. One is the sort of memory of the state of your cortex And that sort of disappears within 20 seconds. You can't remember things for more than about 20 seconds or a minute if you don't have any other form of memory. The second type of memory, which is longer term is still short term is the hippocampus. So you can, you know, you came into this building, you remember whether where the exit is where the elevators are? Um you have some map of that building that's stored in your hippocampus, you might remember something about what I said, you know, a few minutes ago already has been raised but you know, but that would be in your hippocampus uh and then the longer term memory is in the synapse the synapses, right? Um so what you need, if you want a system that's capable of reasoning is that you want the hippocampus like thing. Right? And that's what people have tried to do with memory networks and you know military machines and stuff like that. Right? And now with transformers which have sort of a memory in there kind of self attention system, you can think of it this way. So so that's one element you need, another thing you need is some sort of network that can access his memory, get an information back and then kind of crunch on it and then do this creatively multiple times because a chain of reasoning is the process by which you you you can you update your knowledge about the state of the world about you know what's going to happen etcetera. And that that has to be this sort of recurrent operation basically. </s> |
<s>[INST] Is it possible that some kind of logic based reasoning emerges in pockets as a useful like you said, if the brain is an objective function, maybe it's a mechanism for creating objective functions. It's it's it's a mechanism for creating knowledge bases, for example, that can then be quarried, like maybe it's like an efficient representation of knowledge that's learned in a gradient based way or something like [/INST] that. Well, so I think there is a lot of different types of intelligence. So first of all, I think the type of logical reasoning that we think about that we are, You know, maybe stemming from, you know, sort of classical ai of the 1970s and 80s. Um I think humans use that relatively rarely and are not particularly good at it, </s><s>[INST] but we judge each other based on our ability to solve those rare problems. It's called like you [/INST] test think so like I'm not very good at chess. </s><s>[INST] Yes, I'm judging you this whole time because well we we [/INST] actually with your with your heritage, I'm sure you're good at chess no </s><s>[INST] stereotypes, not all stereotypes that you're [/INST] well, I'm terrible at chess, so, you know, but I think perhaps another type of intelligence that I have is this uh you know, ability of sort of building models of the world from uh you know, reasoning obvious obviously, but also also data uh and those those models generally are more kind of an illogical right? So it's it's it's reasoning by simulation and that the analogy where you use one model to apply to a new situation, even though you've never seen that situation, you can sort of connected to a situation you've encountered before. Uh and and your reasoning is more, you know, akin to some sort of internal simulation. So you you're kind of simulating what's happening when you're building, I don't know, a box out of wood or something, right? You could have imagined in advance, like what would be the result of, you know, cutting the wood in this particular way? Are you going to use, you know, screws or nails or whatever? Um when you're interacting with someone, you also have a model of that person and and sort of interact with that person, you know, having this model in mind to kind of tell the person what you think is useful to them. So I think this disability to construct models of the world is basically the essence, the essence of intelligence and the ability to use it then too, plan actions that will fulfill particular criterion. Um of course is is necessary as well. </s><s>[INST] So, I'm going to ask you a series of impossible questions as we keep asking as they have been doing so. So if that's the fundamental sort of dark matter of intelligence disability to form a background model, what's your intuition about how much knowledge is required, You know, I think dark matter, you could put a percentage of on it of of the composition of the universe and how much of it is dark matter, how much of his dark energy, how much information do you think is required to be a house cap? So you have to be able to when you see a box going it, when you see a human compute the most evil action, If there's a thing that's near an edge, you knock it off all of that. Plus the extra stuff you mentioned, which is a great self awareness of the physics of your of your own body in the in the world. How much knowledge is acquired do you think to solve it? I don't even know how to measure an answer [/INST] to that question. I'm not sure how to measure it, but whatever it is, it fits in about About 800,000 neurons, 800 million neurons. Or </s><s>[INST] the representation does [/INST] everything all knowledge everything right? Um It was less than a billion. A dog is two billion, but a cat is less than one billion. And uh so multiply that by 2000 and you get the number of synapses. Uh and I think almost all of it is learned through this, you know, a sort of self supervised running, although, you know, I think a tiny sliver is learned through reinforcement running and certainly very little through, you know, classical supervisor running, although it's not even clear how supervised learning actually works in the, in the biological world. Um So I think almost all of it is is self supervision but it's driven by the sort of ingrained objective functions that a cat or human have at the base of the brain which kind of drives there um Their behavior. So you know nature tells us you're hungry, it doesn't tell us how to feed ourselves. That's that's something that the rest of our brain has to figure out right </s><s>[INST] what's interesting because there might be more like deeper objective functions in allying the whole thing. So hyung hunger maybe some kind of. Now you go to like neurobiology, it might be just the brain ah trying to maintain homeostasis. So hunger is just one of the human perceivable symptoms of the brain being unhappy with the way things are currently because it could be just like one really dumb objective function at the core. [/INST] But that's how that's how behavior is driven by the fact that you know, the orbital ganglia drivers to do things that are that are different from saying the wrong tong or certainly a cat is what makes you know, human nature versus orangutan nature versus get nature. So for example uh you know, our basal ganglia drives us to seek the company of other humans and that's because nature has figured out that we need to be social animals for our species to survive. And it's true of many primates, it's not true of orangutans, orangutans are solitary animals. Um They don't seek the company of others. In fact they avoid them. Uh In fact they scream at them when they come too close because they're territorial because for for their survival. You know, evolution has figured out that's the best thing. I mean there are occasionally socially of course for you know, um production and stuff like that. But um but but they're mostly solitary. So so all of those behaviors are not part of intelligence. You know, people say, oh you're never going to have intelligent machines because you know, human intelligence is social. But then you look at orangutan's, you look at octopus, octopus never know their parents. They barely interact with any other. And they and they get to be really smart in less than less than a year, in like half a year. Um You know, in a year or they're adults in two years, the dead. So um there are things that we think as humans are intimately linked with intelligence, like social interaction like language. We think, I think we give way too much importance to language as a substrate of intelligence as humans because we think our reasoning is so linked with language. </s> |
<s>[INST] Yeah, painful in the short term though. Well [/INST] yeah, I mean people are out of jobs, like some people can't eat like it's horrible and but but you know, it's progress, so we'll see, we'll see what happens. I mean, the real question is when you Look back 10 years, 20 years, 100 years from now, how do we evaluate the decisions are being made right now? I think that's really the way you can frame that and look at it and you say, you know, you integrate across all the short term horribleness that's happening and you look at what that means and is the, you know, improvement across the world or the regression across the world uh significant enough to make it a good or a bad thing. I think that's the question, </s><s>[INST] yep, and for that, it's good to study history and I mean, one of the big problems for me right now is I'm reading the rise and fall of the third Reich like reading. So it's everything is just, I just see parallels and it means it's you have to be really careful not to overstep it, but just the the thing that worries me the most is the pain that people feel when uh come when a few things combined, which is like economic depression, which is quite possible in this country. And then just being disrespected uh i in some kind of way which the german people were really disrespected by most of the world of like in a way that's over the top that something can, can build up and then all you need is a charismatic leader, uh just to go either positive or negative and both work as long as they're charismatic, and there [/INST] is taking advantage of again, that that inflection point that the world's end and what they do with it could be good or bad, </s><s>[INST] And so it's a good way to think about times now, like on the individual level, what we decided to do is when, when history is written, you know, 30 years from now, what happened in 2020? Probably, history's going to remember 2020, I think either for good or bad, and it's like up to us to write it, so it's good. [/INST] One of the things I've observed that I find fascinating is most people act as though the world doesn't change. You make decision knowingly right? You make a decision where you're predicting the future based on what you've seen in the recent past, and so if something has always been has rained every single day, then of course you expected to rain today to write on the other hand, the world changes all the time constantly, like for better and for worse? Right? So the question is, if you're interested in something that's not right, what is the inflection point that led to a change and you can look to history for this, like what is what is the catalyst that led to that, that explosion that led to that bill that led to the, like you can kind of work your way backwards from that and maybe if you pull together the right people and you get the right ideas together, you can actually start driving that change and doing in a way that's productive and hurts fewer people </s><s>[INST] like a single person single event can turn all of [/INST] absolutely everything starts somewhere and often it's a combination of multiple factors, but, but yeah, this is, these things can be engineered, </s><s>[INST] that's actually the optimistic view that [/INST] I'm a long term optimist on pretty much everything and human nature. You know, we can look at all the negative things that the humanity has all the pettiness and all the like self, self serving this and they just the cruel there, right, the biases, the just humans can be very horrible, but on the other hand, were capable of amazing things and um, and the progress across, you know, 100 year chunks is striking and even across decades we've come a long ways and there's still a long ways to go, but that doesn't mean that we've stopped, </s><s>[INST] Yeah, that kind of stuff we did in the last 100 years is unbelievable. It's kind of scary to think what's going to happen this 100 year. It's scary like exciting, like scary in a sense that it's kind of sad that the kind of technology is going to come out in 10 2030 years we're probably too old to really appreciate, you don't grow up with it. It'll be like kids these days with their virtual reality and they're [/INST] uh trucks and stuff like this, like what is this thing? And like come on, give me my uh you know, static photo </s><s>[INST] My Commodore 64. Yeah, exactly. Okay. Uh sorry, we kind of skipped over, let me ask on, you know, the machine learning world has been kind of inspired their imagination captivated with GPT three and these language models I thought would be cool to get your opinion on it. What's your thoughts on this exciting world of it connects the computation actually uh of language models that are huge and take multiple many many computers, not just the train, but to also do inference on your. [/INST] Well, I mean it depends on what you're speaking to there. But I mean, I think that there's been a pretty well understood maximum deep learning that if you make the model bigger and you shove more data into it, assuming you train it right and you have a good model architecture that you'll get a better model out. And so on one hand, gpt three was not that surprising. Um on the other hand, a tremendous amount of engineering went into making it possible. Um the implications of it are pretty huge. I think that when GPT two came out there was a very provocative blog post from open ai talking about, you know, we're not going to release it because of the social damage it could cause if it's misused. Um I think that's still a concern, I think that we need to look at how technology is applied and, you know, well meaning tools can be applied in very horrible ways and they can have very profound impact on that. Um I think the GPT three is a huge technical achievement and what will GPT four b will probably be bigger and more expensive train, really cool architectural tricks. </s> |
<s>[INST] When you say there's a lot of consciousness is is a singular consciousness basically the set of possible experiences. You can have that subjective way as opposed to the the underlying mechanism because you say that, you know having uh extra color receptor uh extra ability to have new experiences. That somehow a different consciousness. Is there a way to see that as all the same consciousness? The subjectivity itself, [/INST] right? Because when we have two of these conscious agents interacting mathematics, they actually satisfy the definition of a conscious agent. So in fact they are a single conscious agent. So so in fact one way to think about what I'm saying that I'm postulating with my colleagues, chetan and chris and others robert partner and so forth. Um There is one big conscious agent in fully complicated But fortunately we can for analytic purposes, break it down all the way to in some sense, the simplest conscious agent which has one conscious experience. one I like this, this one Agent can experience read 35. That's it. That's what, that's what experiences you can get all the way down to that. </s><s>[INST] So you think it's possible the consciousness, whatever that is is uh much more is fundamental or at least much more in the direction of the fundamental than is spacetime as we perceive it. [/INST] That's the proposal. And therefore what I have to do in terms of the hard problem of consciousness is to show how dynamical systems of conscious agents could lead to what we call space and time and neurons and brain activity. In other words, we have to show how you get spacetime and physical objects entirely from a theory of conscious agents outside of space time. With the dynamics outside of space time. So that's that's I can tell you how we plan to do that. But but that's that's the idea. </s><s>[INST] Okay, the magic of it. The chocolate is delicious. So, so there's a mathematical kind of thing that we could say here, how it can emerge within the system of networks of conscious agents. But um is there going to be at the end of the proof why chocolate so delicious or or no, I guess I'm going to ask different kinds of dumb questions to try to sneak [/INST] up. Oh well that's the right question. And when I say that I took conscious experiences as fundamental what that means is in the current version of my theory, I'm not explaining conscious experiences where they came from. That's the miracle. That's one of the miracles. So I have two miracles in my theory, there are conscious experiences like the taste of chocolate and that the there's a probabilistic relationship. When certain conscious experiences occur, others are more likely to occur. Those are the two miracles that </s><s>[INST] possible to get beyond that and somehow start to chip away at the miracle nous of that miracle that chocolate is still delicious. I [/INST] hope so. I've got my hands full with what I'm doing right now. But but the I can just say a top level how we would think about that. That would get at this consciousness without form. This this is gonna be really this is really tough because it's consciousness without form versus the various forms of consciousness takes for the experiences that it has. </s><s>[INST] Right? Right. [/INST] So there's so when I write down a probability space for these conscious experience, I say here's a probability space for the possible conscious experiences, right? It's just like when I write down a probability space for an experiment, like I'm gonna flip a coin twice, right? And I want to look at the probabilities of various outcomes. I have to write down a probability space. There could be heads, heads, heads, tails, tails, heads, tails, tails. So you before as any class in probability, you're told right down your probability space, if you don't write down your probability space, you can't get started. So here's my probability space for consciousness. How do I want to interpret that structure? The structure is just sitting there. There's gonna be a dynamics that happens on it, right. Experiences appear and then disappear just like Heads appears and disappears. So so one way to think about that fundamental probability space is that corresponds to consciousness without any content? The infinite consciousness that transcends any particular content? </s><s>[INST] Well, do you think of that as a mechanism as a thing? Like the rules that govern the dynamics of the thing outside of space time? Isn't that if you think consciousness is fundamental, isn't it? Essentially getting like it is solving the hard problem, which is like from where does this thing pop up, [/INST] which </s><s>[INST] is the mechanism of the thing popping up? Whatever the consciousness is, the different kinds of was so on. That mechanism. And also, the question I want to ask is how how tricky do you think it is [/INST] to </s><s>[INST] solve that problem? You solved a lot of difficult problems throughout the history of humanity, um There's probably more problems to solve left that we've solved by like an infinity. Uh but along the long journey of intelligent species, how when will we solve this consciousness one? Which is one way to measure the difficulty of the [/INST] problem. So I'll give two answers. There's one problem I think we can solve but we haven't solved yet. And that is the reverse of what my colleagues called the hard problem. The problem of how do you start with conscious experiences in the way that I've just described them and the dynamics and build up space and time and brains that I think is a tough technical problem but some principle solvable. So I think we can solve that. So we would solve the hard problem not by showing how brains create consciousness, but how networks of conscious agents create what we call the symbols that we call brains. So that that I think but </s> |
<s>[INST] Do you think Bitcoin has a strong chance to take over the world? So become the primary, you mentioned the three things that make money money become the primary methodology by which we store wealth we exchange. [/INST] No, no, I think what Bitcoin is this was a phrase that I got from my friend </s><s>[INST] Matt McLennan 1st Eagle [/INST] an option on digital gold. So it's the gold of the system but currently behaves like an option. That's why it's quite volatile because we don't really know if this brave new world of crypto is gonna work. But if it does work then Bitcoins the gold because of the finite supply, what role we need gold to play in The metaverse isn't quite clear. I love that </s><s>[INST] you're using the term metaverse. This is great. [/INST] Well I just like the metaverse city as a kind of uh the antithesis of what we're trying to do and in Austin but I love it. Can you imagine I'm using it sarcastically. I come from Glasgow where all novel words have to be used sarcastically. So the metaverse </s><s>[INST] sarcastic but see the beauty about humor and sarcasm is that the joke becomes reality. I mean it's like using the word big bang to describe the origins of the universe. It becomes like [/INST] it will after a while it's in the textbooks and nobody's laughing. Yeah, well that's exactly right. So sticky. Yeah, I'm on the side of humor but it is a, it is a dangerous activity these days anyway. I think Bitcoin is, is the option of digital gold. The the role it plays is probably not so much story value right now. It's just nicely not very correlated asset in your portfolio When I updated the ascent of money, which was in 2018, 10 years after it came out. I wrote a new chapter in which I said Bitcoin which had just sold off after its 2017 bubble will rise again through adoption because if every millionaire in the world Has .2% of his or her wealth in Bitcoin, the price should be $15,000 and if it's 1%, it's $75,000 And it might not even stay at 1% because I mean look at its recent performance. If you, if you were exposure to stop global stocks have been hedged with a significant crypto holding, you would have aced the last few months. Uh, so I think the non correlation property is very, very important in driving adoption and the volatility also drives adoption if you're a sophisticated investor. Uh So I think the adoption drives uh Bitcoin up because it's the option of digital gold. But it's also just this nicely not very correlated asset that you want to hold in in a world where the hell I mean the banks everybody's going to titan. We've come through this massively disruptive episode of the pandemic public debt, soared money printing sword. You can hang around with your bonds and wait for the euthanasia of the interior. You can hang on to your tech stocks and just hope there isn't a massive correction or dot dot dot well and it seems like a fairly obvious strategy to make sure that you have at least some crypto for the coming year given what we likely have to face. I think what's really interesting is that on top of ethereum a more elaborate financial system is being built stable coins are the interesting puzzle for me because we need off ramps ultimately you and I have to pay taxes in U. S. Dollars and there's no getting away from that. The I. R. S. Is gonna let us hold crypto as long as we pay our taxes. And the only question in my mind is what the optimal off ramp to make those taxes make those tax payments. Probably it shouldn't be a currency invented by facebook never struck me as the best solution to this problem. Maybe it's some kind of fed coin, uh, or maybe one of the, the existing algorithmic stable coins does the job, but we clearly need some stable off ramp. </s><s>[INST] So you don't think it's possible for the I. R. S within the next decade to be accepting Bitcoin as tax payments. [/INST] I doubt that Having dealt with the i. r. s. now, since when did I first come here? 2002? It's hard to think of an institution less likely to reap into the 21st century when it comes to payments. No, I think, I think we'll, we'll be, will be tolerated, crypto world will be tolerated as long as we pay our taxes. That's that it's important that we're already at that point. And then the next question becomes, Well, does Gary Gensler define everything as a security? And do we then have to go through endless regulatory contortions to satisfy the sec? There's a whole bunch of uncertainties that the administrative state excels at creating because, you know, that's just how, that's how the administrative state works. You're doing something new. Hmm. I'll decide whether that's a security, but don't expect me to define it for you. I'll decide in an arbitrary way and then you'll owe me money. So all of this is going to be very annoying. And you know, for people who are trying to run exchanges or innovate in the space these these regulations will be annoying. But the problem with Fintech is it's it's different from tech broadly defined. You know, when tech got into e commerce with amazon, when it got into social networking with facebook, there wasn't a huge regulatory jungle to navigate. But welcome to the world of finance, which has always been a jungle of regulation because the regulation is there to, you know, basically entrench the incumbents, that's what it's for. So it'll be a much tougher fight than the fights we've we've seen of uh other aspects of the tech revolution because because the incumbents are are there and they see that the threat and in the end Satoshi said it very explicitly, it's peer to peer payment without third party verification and all the third parties are going to wait. What were the third parties for? </s> |
<s>[INST] so people should check out your stuff, Do you have a great voice? So I love, I love your stuff. Um is there something you're super busy? Is there something you can say about practicing uh, for musicians? For guitar? For you're also in a band? So like that whole, how you can manage that, Is there some tricks or some hacks to um being a lifelong musician while being like super busy? [/INST] So I would say, you know, the way that I optimize my life is I try to I try to do, you know, the thing that I'm passionate about in a moment, um, and put that at the top of the priority list. There are moments when, you know, you just, you feel inspired to play music and if you're in the middle of something, if you can avoid, if that can be put on hold, just do it right. There are times when you get inspired about something scientific. Um, you know, all right, do my best to drop everything, go into that mode of that isolated mode and and execute upon that. So it's a chaotic, you know, I think I have a pretty chaotic lifestyle where I'm always doing kind of multiple things and jumping between uh between what I'm doing. But at the end of the day, it's it's not like um you know, those those moments of inspiration are actually kind of rare, right? Like most of the time all of us are just doing kind of doing the stuff that get that needs to get done. If you do the disservice to yourself of saying, well, I'm inspired to do this calculation figure figure this out, but I've got to answer emails or just like do something something silly. Uh you know, that is a that is nothing more than the service. And also like I have some social media presence, but I mostly stay off of social media to, you know, just frankly because like I don't kind of, I don't enjoy the mental cycles that it uh </s><s>[INST] it robs you of that the yeah, those those precious moments that could be filled with inspiration in your, in your other pursuits. Um, but there's something to maybe you and I are different. This, like I tried to play at least 10 minutes of guitar every day almost on a technical side, like keeping that base uh of basic competence going and I mean the same way like writers will get in front of a paper no matter what, that kind of thing, it just feels like that for my life has been essential to the daily ritual of it. Otherwise days turn into weeks, weeks turn into months and you haven't played guitar for months? [/INST] No, no, I I understand for me. I think it's it's been like if we have a gig coming up well </s><s>[INST] you need deadlines. [/INST] Yeah, that's right. No, like we we will uh we will sharpen up uh definitely, you know, especially coming up to again, it's like, you know, we're not trying to make money with this, this is like just for the, for that satisfaction of doing something, doing something well, right. Um but overall I would say most I play guitar most days, most days and you know when I put kids to sleep, I play guitar, you know, with them and we like just make up random songs about, you know about our cat or something, you know, like we just do kind of random stuff. But you know, music is always involved in that process. </s><s>[INST] Keeping it fun. You have [/INST] Russian roots. I sure do. Were you born in Russia? I was, yeah, </s><s>[INST] when did you come here? [/INST] So I came to the US in Very, the very end of 99. But um so I was like almost 14 years old. But along the way we spent six years in Japan. So like we moved from Russia to Japan in 94 and then to the US and 99. Like elementary school. All interesting </s><s>[INST] school in Japan. So elementary school in Japan. So that's interesting. Do you still speak Russian? Sure. Okay. The policy of irish. Okay maybe I'll let me ask you in Russian um State department. Should I see uh I'd be interesting to [/INST] hear his people and uh yeah I know this may be the voice of. Uh huh. You can just no god's got palm no parent problems rainy. If your child with a very hard time giving us to pair with the steroid, go to that thought a turbulent period issue is just given us the literacy test. You sure I was in Russia uh quit my mind. Uh previous Pepsi cola but frivolous coco uh let this now shapes the character moses bridge Coco Coco Kerala product still tourism dog do most uh Pepsi coke is a really cheap </s><s>[INST] So for people who don't speak Russian Constantine was talking about basically his first in 1992 interaction with capitalism which is Pepsi and uh at first he discovered Pepsi and then he discovered coke and it was confused called such I just how such theft could [/INST] occur like an intellectual property theft. Remember Pepsi arrived to the soviet union first and there's some, there's some complicated story which I don't quite understand the details of for a while, Pepsi like commanded submarines or something there. Yeah, Pepsi had like a fleet of soviet submarines that was sponsoring tanks </s><s>[INST] and this vest thing and I remember there's certain things that trickled in like Mcdonald's. I remember that was a big deal. Oh yeah, certain aspects of the west. [/INST] Absolutely. So we went to Mcdonald's and we stood on, I mean this is this is absurd right? From kind of looking at it from today's perspective, but we stood in line for like six hours to get into this Mcdonald's? And yeah, I remember inside it was just like a billion people and I'm just taking a bite out of that big Mac. We're like, wow, </s> |
<s>[INST] yeah, that's why they say like a co founder is really powerful for many reasons, but that's, that's kind of one of them. But because they actually for the startup case you unlike writing perhaps you, it's really like 100 hour plus thing, like once you really launch you, you go all in like everything else just disappears, like you can't even have a hope of a balanced life for for a little bit, so and their co founder really helps, that's the idea. Um when you you're one of the most interesting people on the internet, so as a as a writer, you look out into the future, do you dream about certain things you want to still create? Is there um is there projects that you want to write? Is their movies you want to write or direct or [/INST] endless? </s><s>[INST] So it's just endless. Just [/INST] know there's there's there's specific list of things that really excite me, but it's a big list that I know I'll never get through them all and that's part of why um the last five years really like, you know, when I feel like I'm not moving as quickly as I could, it bothers me because I have so much genuine excitement to try so many different things and they get so much joy from finishing things. I don't like doing things, but a lot of friends like that, I I publishing something is greatly is hugely joyful and makes it all worth it, you know, or just finishing something you're proud of putting it out there and have people appreciate it. It's like the best thing in the world, right, You know, a lot of every kid makes some little bargain with themselves has a little, you know, a dream or, you know, something and I feel like when I when I do something that I I make something and then, you know, for me it's been mostly writing and I feel proud of it and I put it out there. I feel like I like, again, I'm like fist pounding my seven year old self. Like there's a little like, I'm I like, I I owe it to myself to do certain things and I just did one of the things, I I just paid off some debt to myself, I owed it and I and I paid it and it feels great. It feels like very like you feel very, you know, a lot of inner peace when you did. So the more things I can do with, you know, and I just have fun doing it right. So I just it's it's for me that includes a lot more writing. I just short short short blog posts. I write very long blog posts. But basically short writing in the form of long blog blog post is a great, I love that medium. You want to do a lot more of that um books yet to be seen. I'm gonna do this. And I have another book I'm gonna do right after and we'll see if I like those too. And if I do, I'll do more otherwise I won't. But I also want to try other mediums. I want to make more videos. I want to um I did a little travel series once. I love doing that. I want to do, you know more of that. No, it was, I let readers in a survey pick five countries they wanted me to go and they picked, they, they sent me to weird places. They sent me, I went, I went to Siberia, I went to Japan, I went from there to, there is all in a row into to Nigeria from there to Iraq and from there to Greenland. And then I went back to new york like two weeks in each place. Um, and I got to, you know, each one I got to, you know, have some weird experiences. I tried to like really dig in and have like, you know, some interesting experiences. And then I wrote about it and I taught readers a little bit about the history of these places and it's just, I love doing that. I love, right, so you know, and I'm like, oh man, like I haven't done one of those in so long. Um, and then, um, and then I have a big like, desire to do fictional stuff. Like I want to write a sci fi at some point and I would love to write a musical that's actually what I was doing before way, but why I was, I was with a partner Ryan Langer. Um, we were halfway through a musical and, and uh, and, and he got tied up with his other musical and wait, but why I started taking off and we just haven't gotten back to it, but it's such a fun medium. So it's such a silly medium, but it's so fun. </s><s>[INST] So you think about all these mediums on which you can be creative and create something and you like the variety of it. [/INST] It's just it's it's just that i if there's a chance on a new medium, I could do something good. I want to, I want to do it. I want to try it. It sounds like so gratifying. It's so fun. You know, like, I think </s><s>[INST] it's fun to just watch you actually sample these so I can't wait for your podcast. I'd be listening to all of them. I mean, that that's a cool medium to see like where it goes. The cool thing about podcasting and making videos, especially with a super creative mind like yours, you don't really know what you're going to make of it until you try [/INST] it. Yeah, podcast I'm really excited about. But I'm like, I like going into other people's podcasts and I never tried everything. So </s> |
<s>[INST] All right, yeah, go ahead. I'd like to believe that. I mean, just to lay my cards on the table, I have faith in the power of effective government. I just have a lot of concern about what happens as institutions grow in size. For sure. And I just have a lot of worry about the natural corrupting influence on the individuals and on the system as a whole, like the boys club nature of it. I don't know, there must be a better term. But basically, they agree to the game and they play the game and there's a generational aspect, momentum to the game, and they more and more stop being responsive to the people that they represent. I just feel like there is that mechanism. And I think the nice thing democracy elections are resistance to that natural human mechanism. Also, the balances of power is a resistance to that mechanism. In some ways, the media that reveals the bullshit of politicians is also a resistance to that mechanism. It's hard to be full of shit as a politician because people will try to catch you on it. So there's a honesty method there that keeps you honest. [/INST] It's to some degree, but it still feels like- </s><s>[INST] For sure. [/INST] It still feels like politicians are gonna politician. Yeah, they definitely play their games, that is true. There's probably always gonna be that meta narrative over like governance that just develops as like, you have to form relationships and play games to get legislation passed and everything. The only reason why I don't like it when people attack institutions is because one, institutions are incredibly important, arguably paramount, no, they are, to keeping society running. And two, I think sometimes when we shift the blame onto institutions too much, I think that we lose sight of what the real problems are. So for instance, in the United States today, people might be very critical of the government not getting much done, but then everybody turns their eyes to the government for being ineffective. But what I would argue is I would say the government is actually incredibly effective and it's showcasing the will of the American people really well right now, which is we are historically more divided than we have ever been. And if I were to just look at the people and I were to say, we have a historic divide that is getting like rapidly blown apart by things like the internet and the media, if that exists, well, what would I expect the government to look like? I wouldn't expect the government to be governing very effectively. I would expect that government to show that legitimate divide in people. </s><s>[INST] Do you think that divide, we have a perception of a large divide between left and right? [/INST] Do you think that's a real divide that's in this country? Narrow the language. </s><s>[INST] What do you mean by real divide? Do you think there is that divide in ideology? That there's a large number of people that believe a certain set of policies and the different set of policies. [/INST] Was it just the perception on Twitter? No, I think there is a large divide in terms of belief. I don't think there's very much divide between any people in terms of what they, on the most fundamental levels want in terms of human beings, but in terms of Democrat versus Republican right now, I think there's a huge divide in terms of the direction they wanna see the country go, and what they believe really, what they even believe is reality, right? </s><s>[INST] Unfortunately that's what we've gotten to. Can't I just speak about the mechanism of the left and right here, maybe on the mametic rivalry aspect. Is there some aspect to the left on which you are apart of that attacks their own [/INST] for ideological impurity more than the right does? Is it the bigotry of small differences? There's a concept where when you're near somebody who is very slightly different than you, you want to destroy it but when you are with someone that is way different than you you don't. I think the left does it, but I think the right does it too. I didn't realize it until I started dipping more into conservative communities But oh my god. The people from The Daily Wire, and the people from Turning Point, and the America First, all these different groups of people hate each other. And they fight each other so much. They hire and fire, sometimes, employees. They smack each other. I think there's a lot of political division between both sides. I think that the Left just gets highlighted more. Because it's like the internet, and a lot of the internet spaces have a lot of Left-leaning people. So you see like the crazy scenes and the crazy progressives and the crazy center Left liberals and the crazy blah, blah, blah. Whereas, a lot of the Right-leaning people have kind of been pushed off of the main areas </s><s>[INST] with the internet now. Interesting. My sense was that it's hard to exist on the center left, but maybe because I just don't have the full spectrum view of the political divide. It felt like center left is a difficult position [/INST] to occupy. </s><s>[INST] Yeah, I would definitely say so, yeah. [/INST] I don't know if it's that difficult to be center right. It's very difficult to be center right. I think actually maybe even more difficult because a center right person might be somebody who's like conservative, but not a fan of Trump. And you're like over, like look like Liz Cheney, right? You've had politicians that are just like, they didn't back the Trump stuff and now they're gone. Or you might be like center right, but like you don't think the election was stolen and now you're like half the Republican Party's looking at you like you're crazy, you know? </s> |
<s>[INST] basically. Yeah, I wonder how you get there. Because I even, I look to coin base for, for example, you know, people as you can imagine sort of tag me on twitter or something like that and all that. Like you should interview our sort of this, the founder of this particular coin, right? And it's so hard for me to know what's, first of all, what's interesting technology, what's uh, who's a scammer or not who's actually legitimately representing ambitious new thing versus a scam and, you know, there's very few sources of uh like verification signal and unfortunately coin based in part has become a little bit of that too. And you're trying to get away from that because you're trying to get as many sort of, let, let the people decide. So you're thinking of like amazon star type system where the people could rate. [/INST] Yeah. So I think we'll actually probably add like user ratings and reviews. So, um, and, and we'll be very cautious about like, you know, these are real people. Um, there's a bunch of stuff we have to do from that already. So I think wisdom of the crowds is good in terms of getting feedback on items, but we also, we're going to do our own review, which I mentioned earlier, right? Which is like, okay, it meets this minimum bar to be listed on our site. Um, I think both are important. </s><s>[INST] How do you know, if, if a coin is a scam or not? [/INST] Well, you can, you can see a few things. So you know, I hate to use the word scam because a lot of these, these are judgment calls, you got a kind of a court maid may or a jury may land either way, but things that would be red flags to look at would be, um, you know, is a bunch of the asset owned by an insider or insiders, um, with short vesting periods. Um, you know, our, does the background of the founders, like they may have criminal records or if they've perpetrated other frauds in the past? Right. Um there's a difference between something which is just a Me Too product, it's like doesn't have anything interesting about it and something that's an actual fraud or outright scam and um you have to a lot of this data, what's cool about it is that it's now available on chain? You can look at like the token ah mix behind it and see who </s><s>[INST] owns it. And are [/INST] they, are they selling it you know in like inappropriately or are they pumping it on like youtube and twitter and making promises about, hey the value of this thing may be higher in the future and like all those are just big, big no nos that we would um you know we just don't wanna go there. So our whole thing is like we want we want to enable the innovation in this space but not allow anybody to curtail the advancement of this industry by like doing some kind of fraudulent thing or get rich quick thing. So it's </s><s>[INST] a tricky industry because I'm trying to figure out who to, you know what's interesting to, to to to understand to research and uh it's hard to know, let me ask you about a tricky one to add to a centralized exchange which is privacy preserving cryptocurrencies? So like Manero, is that is that technically difficult or is that why why is like Manero for example? Forget that specific one but like privacy preserving cryptocurrencies block chains, uh why is that is that ever possible to add? [/INST] So that's that's a great question. So the answer is maybe so um here here's the here's the reason why. So um because we're regulated financial service business. We have various um licenses to do that. We are we are regulated by various regulators. Part of those licenses requires us to have a quote reasonable um program to monitor for suspicious activity. Um you know an AML program anti money laundering. Right? And so if it if a coin is 100% anonymous and we can't really do blocking analytics to track um source of funds and where these things might be going. It makes it harder to have a um a reasonable program around that that's defensible. Now there are privacy preserving coins like cash which have something called a view key. And a view key is basically another key which allows you to do minimize um the transactions in specific situations where you want that. So for instance um you know we do support cash and one of the ways we got comfortable with that is that when you're buying it on coin base um you know you can basically have a view key. The transactions are not anonymous while you're buying it and we can see where it goes afterwards and do our our whole standard program. Um Now if it gets a few hops away down the road. I mean people could eventually turn on privacy preserving aspects. So you know, these are tough judgment calls but at least in terms of our interaction with the customer and everything we feel comfortable with that. I think there's a broader point here which is that I actually think privacy coins are a good thing for the world and we and they should be allowed and more like you know, despite we've we've made this judgment call to operate in a regulated and safe and compliant way. But just taking my head off for a minute, I think the world would be a better place if there were more privacy coins because it's kind of like the internet when it first came online. Like there was no H. T. T. P. S. Everything was http and there was you know, some people were afraid to put their credit cards on the internet and um your your messages could be intercepted and all this stuff. And now the whole internet has basically moved to https with a little lock icon in your browser which is better like and and financial information is like the most important information to keep private. Right? So there's times where like let's say you're running a charity or something and you want to have total audit ability transparency for the whole world who donated and where did the money go? That's great. You want it to be public. But if it's like your personal money or something like that, you don't want to be broadcasting that to the whole world and in some ways that's what block chains are doing, You know, pseudonymously because like, but it's, it is a public ledger. And so if you can know who owns each address, you can basically minimize it. I, you know, I think basically the people should fight for privacy and freedoms of all kinds, but privacy of money is a good thing. So I would like to see more of that in the future. </s> |
<s>[INST] is do you do you think about the concept of burnout? Because so I personally never experienced burnout in the way that folks talk about, which is like, it's not just the up and down. It's like you don't want to do anything ever again. It's like, it's for some people, it's like physical, like to the hospital kind of thing. [/INST] Yeah. So I do worry about it. So when I used to do student writing like writing about students, a student advice. It came up a lot with students at elite schools and I used to call it deep procrastination. But it was a real, really vivid, very replicate herbal syndrome where they stop being able to do schoolwork. Yeah. Like this is, do the professor gives you an extension and the professor gives an incomplete and says you got, you were going to fail the course. You have to hand this in. They can't do it right. It's like it's a complete stop on the ability to actually do work. And I used to counsel students, you have that issue and often it was a combination of this is my the best analysis is you have just the physical and cognitive difficulties of their usual under a very hard load right there. Doing too many majors to an extracurricular is just, you know, really pushing themselves and the motivation is not sufficiently intrinsic. So if you have a motivational center that's not completely on board. So a lot of these kids like what I'm doing with my kids, they would be, you know, their whole town was shrewd enough fireworks that they got in there. Everyone's hope that they were going there. Uh and that they're in three majors, don't wanna let people down, but they're not really interested in being a doctor or whatever. So your, your motivation is not in the right place. The motivational psychologists would say the locus of control was more towards the extrinsic end of the spectrum and you have hardship and you could just fritz out the whole system and so I would always be very worried about that. So I think about that a lot. I do a lot of Multiphase or multi scale seasonality. So I'll go hard on something for a while and then for a few weeks ago, easy, I'll have semesters that are hard and semesters that are easier. I'll take the summer really low. So on multiple scales and in the day I'll go really hard on something, but then have a hard cut off at five. So like every scale, it's all about rest and recovery because I really want to avoid that and I do burnout? I burnt out pretty recently. I get minor burnt out. I got a paper a couple papers that was trying to work through for a deadline a few weeks ago and I wasn't sleeping well and um there's some other things going on and it just, it knocks out and I get sick usually is how I know I pushed myself too far and so I kind of pulled it back and I'm doing this book launch then after this book launch and pulling it back again. So I like I seasonality for rest and recovery, I think it's crucial and at every scale daily, monthly, you know, and then at the annual scale, like an easy summer for example, I think it's like a great idea if that's possible. </s><s>[INST] Okay, you just made me realize that that's exactly what I do because I feel like I'm not even close to burnout or anything even though I'm, I'm in chaos, I feel the right exact ways the seasonality is the, not even the seasonality, but like you always have multiple seasons operating, it's like you said like because when you have a lot of cool ship going on, you, there's always at least one thing that's a source of joy that there's always a reason, I suppose the fundamental thing and I've known people that suffer from depression to the fundamental problem with like the experience of depression and burnout is like why do like life is meaningless? And I always have an answer of like why, why today could be cool [/INST] and you have to contrive it right? If you don't have it, you have to contrive it. I think it's really important. Like okay, well this is going bad. So now is the time to start thinking about. I mean look, I started a podcast during the pandemic is like, this is going pretty bad. But you know what, This could be something really interesting. </s><s>[INST] Deep questions with colony apart. Uh do it all in that voice. I love the podcast by the way. But yeah, I think David Foster Wallace said uh the key to life is to be unbearable. Uh I've always kind of taken that to heart which is like, you should be able to maybe artificially generate anything. Like uh find something in your environment, in your surroundings that's a source of joy. Like everything is fun. [/INST] Yeah. Did you read the pale king? It goes deep on board? Um it means it's like uncomfortable. It's like an uncomfortable meditation on boredom. Like the characters in that are just driven to the extremes of, I just bought three books on board. Um the other day. Uh so now I'm really interested in this topic because I was anxious about my book launch happening this week. I was like, okay, I need something else. So I have this idea for a might do as an article first, but as a book like okay, I need something cool to be thinking about because I was worried about like I don't have a lot going to work the pandemic, what's going to happen, I don't know if it's going to get to. So this is exactly what we're talking about. So I went and I bought a bunch of books and I'm beginning like a whole uh sort of intellectual exploration. </s> |
<s>[INST] And would all alien civilizations have an evolutionary process on a planet? So like that's one of the almost, it's almost the definition of life, to create all those memories, you have to have something like- Things have to change in time. Yeah. But there has to be selection, have something like- Things have to change in time. [/INST] That's like an efficient, there's no other way to do it. No. Well, never say never, because soon I'll say that's what- That's the part that depresses me though, going back to like, I don't know, the earlier discussion on violence and things, like, and I don't know where, somebody was tweeting about this recently, but like, you know, how much death had to die. Maybe it was you. Yeah. </s><s>[INST] Ah, yeah. So we're talking about life, and I guess a lot of murder had to occur. [/INST] Right, so selection means things had- Death destruction. Yeah, right. So selection means things had to be weeded out, right? </s><s>[INST] So- Well, we can celebrate that, death makes way [/INST] for it too- Yeah, I mean, and also, you know, one of the most interesting features of major extinction events in the history of our planet is how much novelty emerged immediately after, right? So, and of course, you know, a lot of people make arguments, we wouldn't be here if the dinosaurs didn't go extinct. So in some ways, we can attribute our existence to all of that, but I guess I was just wondering and sort of like, if I was going to build a universe myself, in the most optimistic way, would I retain that feature? But it does seem to be a universe. But it does seem to be a universe. I think you have to. I mean, I think we're probably being over anthropomorphizing. I remember watching the blue, I think it was the blue planet, David Attenborough was showing these seals. And because of climate change, some seals were falling off a cliff. And how tragic that was. I was like, I'd say my son, that's pretty cool. Look at those ones down there. They've obviously got some kind of mutations, some, and they're not doing that daft thing. And so that poor gene will be weeded out. Of course, at the individual level, it looks tragic, and of course as human beings, we have the ability to abstract and we empathize, we don't want to cause suffering on other human beings and we should retain that, but we shouldn't look back in time and say, you know, how many butterflies had to die? I remember making this, how many, if you think about the caterpillar becoming the chrysalis and then the butterfly getting out, how many, if that suffering, we call it suffering, if that process of pruning had not occurred, we have no butterflies. So none of the butterfly beauty in the world without all that pruning. So pruning is required, but we shouldn't anthropomorphize and feel sorry for the biological entities, because that seems to be a backwards way of looking at it. What we should do is project forward and maybe think about what values we have across our species and our ecosystem and our fellow human beings. You know, now that we know that animals suffer at some level, think about humane farming. When we find that plants can in fact are conscious and can think and have pain, then we'll do humane gardening. </s><s>[INST] Until that point, we won't do it, right? I like this. Famous chemist endorses the majestic nature of murder. Oh, dear God. That's the title. I didn't say that, but I just answered. I have a hard time with it, though. I think the way you put it. [/INST] It's kind of... But it's the reality of... It's the reality of... It is beautiful. </s><s>[INST] You know, there's an Instagram account called NatureIsMetal, and I keep following it on following [/INST] it because I can't handle it for prolonged periods of time. We evolve together. You die alone. </s><s>[INST] Yeah. We evolve together, but you die alone. So I... We live alone, too. It's a Gatsby thing. I don't know. We evolve together. We're still together. The together is the murder. [/INST] The population is the population of murder. My romantic vision of it to try to make me happy, Sarah, instead of sad Sarah. I talk in third person when I think very obtractly, sorry. Is, you know, like this whole, like, you know, like certain things can coexist, so the universe is trying to maximize existence, but there's some things that just aren't the most productive trajectory together, but it doesn't mean that they don't exist on another timeline or another chain somewhere else like I, like, maybe you would call that like then some kind of multiverse or things, but what am I saying? I think you can't. I just, you can't go down a level. I'm just making stuff up, picking stuff up, state something that doesn't feel better. Is it logical and we need... </s><s>[INST] No, I know, I know. If you look at bacteria, if you look at virus, I mean, just just the number of organisms that are constantly, like looking at bacteria, they're just dying nonstop. It's like a slaughter. [/INST] No, I know I know. Yeah, I feel like a slaughter. Right. Well, and this goes back to the conversation about God. I mean, like there's the whole thing about why does the universe enable suffering? Individuals don't exist, right? So for this, I think if you think about life as an entity on Earth, right, let's just go back a second. I mean, I like to, I'll be ludicrous for a second. I don't exist. You don't exist, right? But the actions you do, the product of evolution exists, right, the objects you create exist quantitatively in the real world. If you then understand life on Earth or alien life or any life in the universe as this integrated entity where you need cells in your body to die, otherwise you'd just get really big and you wouldn't be able to walk around, right? So, you know, you do. Yeah, yeah, yeah, yeah. So, yeah, yeah, yeah. So I think- It's the patterns that persist, not the physical things. And of course, we, you know, we have, we place immense values on fellow human beings. And I'm, a majestic professor does like other individual human beings. Now you're talking in third person too. </s> |
<s>[INST] the creative process is more in the space of ideas are becoming more in the space of ideas versus in the raw pixels. [/INST] Well, it's interesting. It depends, I think adobe we really want to spend the entire range from really, really good what you might call low level tools by low level as close to say analog workflows as possible. So what we do there is we make up systems that do really realistic oil painting watercolor simulations. So if you want every bristle to behave as it would in the real world and leave a beautiful analog trail of water and then flow after you've made the brush stroke, you can do that. And that's really important for people who want to create something really expressive or really novel because they have complete control and then a certain other tasks become automated. It frees the artists up to focus on the inspiration unless of the perspiration. So, um thinking about different ideas. Obviously, once you finish the design, there's a lot of work to say do it for all the different aspect ratio of phones or websites and so on. And that used to take up an awful lot of time for artists. It still does for many what we call content velocity and one of the targets of ai is actually to reason about from the first example of what are the likely intent for these other formats. Maybe if you change the language to german and the words are longer, how do you re flow everything so that it looks nicely artistic in that way. And so the person can focus on the really creative bit in the middle, which is what is the look and style and feel and what's the message and what's the story and the human element. Okay, so I think creativity is changing. So that's one way in which we're trying to just make it easier and faster and cheaper to do so that there can be more of it more demand because it's less expensive. So everyone wants beautiful artwork for everything from a school website to Hollywood movie on the other side, as some of these things have automatic versions of them, people will possibly change role from being the hands on artisan to being either the art director or the conceptual artist and then the computer will be a partner to help create a list examples of the idea that they're exploring. </s><s>[INST] Let's talk about adobe products, just a an adobe products, just just so you know where I'm coming from, I'm a huge fan of Photoshop for images premiere for video audition for audio. I'll probably use Photoshop to create the thumbnail for this video premiere to edit the video audition to do the audio that said everything I do is really manually and I set up this old school kinesis keyboard and I have auto hotkey that just it's really about optimizing the flow of just making sure there's as few clicks as possible. So just being extremely efficient, it's something you started to speak [/INST] to. Uh </s><s>[INST] so before we get into the fun uh sort of often deep learning things, where does ai if you could speak a little more to it, ai or just automation in general? Uh Do you see in the coming months and years or in general Prior in 2018 uh fitting into making the life the low level pixel work flow easier. [/INST] Yeah, that's a great question. So we have a very rich array of algorithms already in Photoshop. Just classical procedural algorithms as well as ones based on data. In some cases they end up with a large number of sliders and degrees of freedom. So one way in which ai can help is just an auto button which comes up with default settings based on the content itself rather than default values for the tool at that point, you then start tweaking. So that's that's a very kind of make life easier for people while making use of common sense from other example images </s><s>[INST] like smart defaults, [/INST] defaults and absolutely Another one is something we've spent a lot of work over the last 20 years. I've been at Adobe or 19 thinking about um selection for instance where um you know, with a quick select, you would look at color boundaries and figure out how to sort of flood fill into regions that you thought were physically connected in the real world. But that algorithm had no visual common sense about what a cat looks like or a dog. It would just do it based on rules of thumb which were applied to graph theory and it was a big improvement over the previous work where you had sort of almost click every everything by hand or if it just did similar colors, it would do little tiny regions that wouldn't be connected, but in the future using neural nets to actually do a great job with say a single click or even in the case of well known categories like people or animals, no click where you just say select the object and it just knows the dominant object as a person in the middle of the photograph. Um those kinds of things are um really valuable if they can be robust enough to give you good quality results um or they can be a great start for like tweaking it. </s><s>[INST] So for example, background removal, like one thing I'll in a thumbnail I'll take a picture of you right now in the sense you remove the background behind you and I want to make that as easy as possible. You don't have flowing hair [/INST] uh like rich at the moment, which happened in the past. It may come again in the future but so </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] to [/INST] put a roof on the house for her and her kids and uh I didn't give a damn I don't give a damn it. What was more important was me at that point, </s><s>[INST] can I ask you a question about the social engineering ask? So maybe it's specifics like the methodology email, he said phone, maybe you could discuss this process from a bigger philosophical perspective of what is it about human beings that makes impossible to be social engineered to be um to be victims of fraud. [/INST] So first let me say that I became a social engineer as a child alright because the adults in my in my environment as a child, I had to know exactly what they were thinking and be able to try to manipulate that for survival. So I became a social engineer as for survival initially. Alright. And one of the things that I've seen with a lot of cybercriminals is the exact same thing, the really expert ones. They become a social engineer as a child. Then later on they use those tools to victimize others alright. Which </s><s>[INST] is fascinating because you're in order to understand what others are thinking, you have to be extremely good at empathy. So you have to like really put yourself in the shoes of the other person and yet in order to do cyber crime, you have to not care about the pain that might cause them once you manipulate them. So you have to empathize and yet not care [/INST] exactly. And I would argue I would argue that that is not a sociopath because a cyber criminal and I was no different. Most cybercriminals justify those actions. So the justification becomes what's important with me. The justification was why I did it for my family, I did it for my wife did it from a stripper girlfriend. So, and I believe those </s><s>[INST] because I care about love a lot. [/INST] So the the big the big picture of that is trust. How do you establish trust with a potential victim? All right now, I would argue online that that trust is established through a combination of technology tools, social engineering. Alright, So we trust our tech, you know, we trust our cell phones, we trust our laptops a lot of times we don't understand how they operate, but we trust the news that comes across the line, We trust the phone numbers that show up. We trust I. P. Addresses. If we're advanced enough to look at an I. P. Address or a domain or anything else like that, criminals use tools to manipulate that. Spooked phone numbers, spooked browser fingerprints or whatever that may be. Whatever the tool maybe, then that lays a base level of trust at that point you shoot in with the social engineering and lay whatever story that is in order to manipulate that victim to act, not out of reason but out of emotion. All of a sudden </s><s>[INST] this is fascinating about the way humans interact with the world which is you're almost too afraid to not trust the way you have to find a balance. You have this you have a lot of sort of conspiracy theories now about distrust institutions and thinking like everything around us. It's like I've been listening to people who believe the earth is flat and you know that that conspiracy theory is fascinating to me because it basically says that you can't trust [/INST] anybody </s><s>[INST] like everything you hear is a lie. So that's one. You know, you can live that life or you can live a life where you're just naively trusting everything and we as humans have to because that life is kind of full of happiness if nobody screws you over because you you know you meet people with the joyful heart and you get excited and all that kind of stuff, but if you do that too much, you're gonna get burned. You have to find some kind of balance in terms of optimizing happiness where you trust, I mean, but verified and on the internet that becomes really tricky, you're almost too afraid to distrust everything because you'll never get anything done on the internet. But then if you trust too much, you can get screwed over. And so the social engineering comes in where you're like, I'm not sure if I should trust this, you kind of helped them build the narrative was like, it's good, it's good, it's good. [/INST] So, and a lot of the times that social engineering is just feeding into what the victim wants to believe. All right, it's it's not really coming up with a brand new story at all. It's just knowing what that victim is, what the motivations of that victim is feeding into it at that point. So, you have to again, that that social engineer has to almost immediately know what's driving that person that they're talking about. If I'm So if I'm working on the phone talking to someone over the phone, I have to know within seconds what I need to say how I need to act to interact with that customer service agent or whoever I'm talking to on the other end of the line. </s><s>[INST] So fascinating because you truly are empathizing with the other person. Um who is it, this this businessman Stephen Schwarzman. Um, I've talked a few times. He, he mentioned this thing that, you know, the way you build deep relationships is you really kind of notice the things that people are telling you like, like what, what they want and uh, what they're bothered by, what are the big problems in their lives. Because everybody's saying that all the time and most of us are just ignoring it. You really [/INST] take the time to listen, you know, somebody at that point. Absolutely. You do. Then you have to be able to dismiss it, dismiss </s><s>[INST] it after, you [/INST] know, you're looking for that just to see how I can manipulate that is what you're trying to do. So that the lady was one story they another truly despicable story. We'll get to script in a second. But another truly despicable story we had, we were one of the really first groups that started phishing attacks. So that is a social engineering attack. That's another social engineering attack. That's sending that fake email out that looks like it's coming from a website or your financial organization or whatever and saying, hey, we've got a security problem, We need you to update your account information. Well, back then, No one had ever seen a phishing attack. So you could ask for all the information. You were getting just complete identity profiles on a phishing email nowadays. You can't do that nowadays. You look for basically credentials because everyone is aware of fishing. But back then it was complete information we had fished out, I don't know, 200,000 e trade accounts. That's what we had the login </s> |
<s>[INST] Think Bitcoin. So first of all, let me state that Charles for the most part is purely objective. The bias that comes in for the record, I want to say that I have heard, because you mentioned the mafia, that you prefer good fellows over the godfather. So a man who prefers good fellows over godfather, you take it for that opinion for what it is. I actually have to think about that one for quite a bit. I think- Oh, come on. Joe Pesci was so good at that. He's incredible. I also love casino and those big glasses on De Niro. I love it with Sharon Stone. But we could talk about that for hours. But let me ask you about the Bitcoin conference. Cause it is kind of a, I would say an important moment in human history. It was quite exciting in terms of size and kind of turmoil and all those kinds of things. And you were there in, what is it? Hot and human Miami. I believe it's the way you introduced it. So what do you make of the community of Bitcoin [/INST] or that particular event in human history? Oh, come on. Joe Pesci was so good at that. What makes me sad is I remember the old Bitcoin community and I've seen what it's become. And the old community was really fun. Like the San Jose conference in 2013 or subsequent conferences. There was just a lot of people. They had no money. And they just really love this idea of the decentralized money. They love this idea of decentralization in particular. And you could strike up a conversation with everyone. There was no ego at all. But what was really fun is you could really get intimate friendships and relationship, great conversations with people there. It's kind of like the early days of AI, the all men Dartmouth and all these other places a very intimate, there was no egos, everybody was just trying to do some really cool stuff. Now, just like those early days, there was an overestimate of how robust the solutions would be. So we believed, oh yeah, 10 years we're gonna rule the whole world, right? Didn't exactly happen. On the other hand, Bitcoin grew from nothing in just 11 years to, I'm in Mongolia riding camels and the camel herder has Bitcoin and there'll be desert. So that's telling you that's a pretty pervasive technology if you have that level of adoption that quickly. When I went to Miami, it was unrecognizable. Everything was so commercial. Half of the vendors at the conference were like watches that would cost half a million dollars and they were covered in diamonds. So when you see that kind of materialism leak its way in, its first is repulsive. The other thing was there was no, like I remember one of the first conferences, Mo Levin's conference in January of 2014, the North American Bitcoin Conference, ironically in Miami, there was a Bitcoin Help Center booth. Dima ran it and a few of the other Bitcoin OG's ran it. And the core developers actually came over, like Jeff and others, who were there and sat at the booth and anybody come up and ask a question. Anything you wanna ask about Bitcoin. It was like, that was the culture. Just help people, welcome. And there was no help booth there. There was no notion of that. There were six hour lines and superstars and things like that. And again, again it was always the same thing. Look how much money all these people have made. And the whole point of Bitcoin was to redefine the notion of money. redefine the notion of value, you know, these types of things. So it just, I'm no longer part of that. And it made me sad because I really enjoyed being part of the, how I got started was Bitcoin Education Project. I did a class on Udemy, I gave it away for free. I had 80,000 students and they would email me. I got 5,000 emails before I stopped answering them. And everyone come in and ask me some question about something sometimes arcane, sometimes trivial. And I take the time to sit down and answer the question or for the email to somebody I knew who could answer that particular type of question. And there were some amazing people in the early days like Mike Hearn and Gavin and others. And they were just super committed. And Mike's case, he knew Satoshi. He actually emailed them back and forth because he was around 2009, 2010. He did the Bitcoin Java client and Satoshi was all excited. He said, oh wow, Bitcoin can come to a cell phone. This is really cool and exciting. And then what happened? Mike left Bitcoin in 2013 over the whole big block debate that happened. They just treated him like dirt, like he was subhuman or something. So I don't know, the culture has changed a lot. And if they like it, it's good for them. They can enjoy their religion, but it's not for me. And where I like being is, like I had a guy who used to work for me, Alex Chirpinoy. And he created this beautiful project called Ergo. To me, that is the spiritual successor to Bitcoin. Ergo is really special because it has the same culture. It has the same mentality. And the technology is kind of like a natural evolution of what you would do if you knew about Bitcoin and you wanted to build the next big thing. So it's still a proof of work system. It's still a UTXO system, but he added UTXO with some smart contracts. It's this Sigma protocol idea. On the proof of work side, Satoshi had this one CPU, one vote idea. So Alex tried to create non-osable puzzles to make it impossible to have mining pools. And there's all these other beautiful little things. And he's this brilliant Russian programmer and he surrounded himself with all these other brilliant people. He has zero ego. He's like, he has negative ego. When you put up with a person with ego, your ego goes down, right? And everything about Alex is always like, how do I solve this? How do I do that? And he gets legitimately excited when he meets somebody that he can collaborate with or learn from. That's where Bitcoin was in the beginning. Everybody set their egos aside, whether it was Hal Finney or whatever, and they would just say, how can I help? What can I do? And it was all about coming up with some cool new thing or solving some cool new problem. </s> |
<s>[INST] What do you think is the difference between these two paths of engineering intelligence and the science of intelligence? [/INST] It's a completely different story engineering his imitation of human activity. You have to make device which behave as human behavior have all the functions of human. It does not matter how you do it but to understand what is intelligence about, it's quite different problem. So I think I believe that it's somehow related to predicate with talk yesterday World because look at that Vladimir props a deer she just found. So do you want here predicates shoot call it units which can explain human behavior at least in the Russian tells you </s><s>[INST] local Russian tales [/INST] and derived from that and then people realized that the more whites and Russian tales it is on tv in movies, serials and so on. And so </s><s>[INST] you're talking about Vladimir Propp, who in 1928 published the book morphology of the folk tale describing 31 predicates that have this kind of sequential structure that a lot of the stories narratives follow in Russian folklore and another contact we'll talk about it. I'd like to talk about predicates in a focused way but let me if you allow me to stay zoomed out on our friend Alan turing and you know, he inspired a generation with the imitation game Yes. Do you think if we can linger in a little bit longer do you think we can learn? Do you think learning to imitate intelligence can get us closer to the site to understanding intelligence? So why do you think imitation? It's so far from understanding? [/INST] I think that it is different between you have different goals, so your goal is to create something something useful and that is great and you can see have much things was done and I believe that it will be done even more. It's self driving cars and also there's business, it is great and it was inspired by during vision but understanding is very difficult. It's more or less philosophical category. What means understands the world. I believe in him which starts from plateau that there exists a vault of ideas. I believe that intelligence, it is evolved over the years, but it is vault of pure ideas and when you combines this reality things it creates as in my case in the variance which is very specific and that I believe the combination of ideas in way to construct and convenient is intelligence. But first of all uh predicate, if you know the predicate and hopeful is um not not too much predicated exist for example, I sort of want to dedicate for human behavior. It is </s><s>[INST] not a lot of vladimir Propp used 31 You can even call them predicted 31 predicates to describe stories, narratives. So you think human behavior. How much of human behavior, how much of our world, our universe, all the things that matter in our existence can be summarized in predicates of the kind that prop was working with. [/INST] I think that's be safe a lot of form of behavior. But I think the predicate is much less because even in this example which I gave you yesterday I just saw that predicate can be Yeah. Can construct one predicate. Can construct many different variants depending on your data. They're applying to different data and they give different invariance. So but your address maybe not so much. </s><s>[INST] Not so many. I don't know [/INST] about that but my guests. I hope that's why challenge about digit recognition how much you need. </s><s>[INST] I think we'll talk about computer vision and two d. images a little bit in your challenge. [/INST] That's exactly about intelligence. </s><s>[INST] That's exactly that's exactly about know that hopes to be exactly about the spirit of intelligence in the simplest possible way. [/INST] Absolutely. You should start the simplest way cereal not be able to do it. </s><s>[INST] Well, there's an open question whether starting at the M nist digit recognition is a step towards intelligence or it's an entirely different thing. [/INST] I think that to beat records Using 300 200 times less examples. You need intelligence. </s><s>[INST] You need intelligence. So let's because he used this term and it would be nice. I'd like to ask simple maybe even dumb questions. Let's start with the predicate in terms of terms and how you think about it. What is the predicate? [/INST] I don't know. I have a hearing formally as they exist but I believe that predicate for two d. images. Uh one of them is symmetry. </s><s>[INST] Hold on a second. Sorry, sorry to interrupt and pull you back at the simplest level. We're not even we're not being profound. Currently a predicate is a statement of something that is true. Yes. Do you think of predicates as somehow probabilistic in nature or is this binary? This is truly constraints of logical statements about the world. [/INST] In my definition. The simplest educative function function. And you can use this function to make inner product that is predicated. </s><s>[INST] What's the input And what's the output of the function [/INST] input is X. Something which is input in reality say if you consider digit recognition it pixel space input but it is function which in pixel space but it can be any function from uh pixel space and you choose. And I believe that there are several functions which is important for understanding of images. one of the most symmetry. It's not so simple construction as I described this liberal narrative results of stuff but another I believe I don't know how many is how well structured arised is picture </s><s>[INST] structural. Ized. What do you mean by structural? Ized [/INST] it is formal definition. Say something heavy on the left corner not so heavy in the middle and so on. You describe in general concept of what you assume </s><s>[INST] concepts. Some kind of universal concepts. Yeah, [/INST] but I don't know how to formalize this, </s> |
<s>[INST] just talking to him and he didn't mention this part. Well, I should, I should get further. Well, as I know he loved Dropbox, but I wasn't sure what he was doing. Who It was just up to. Well, [/INST] he was kind of saying he retired, but it's literally been five years since I last sat down and really talk to ghetto, right? Um ghetto is a technology expert, right? He's a so I came, I was excited because I finally figure out the type system for Numpy. I wanted to kind of talk about that with him and I kind of overwhelmed them. </s><s>[INST] Could you stay in that just for a brief moment because you're a fascinating person in the history of programming. He is a fascinating person. What have you learned from Guido about the programming about life? [/INST] Yeah, yeah, a lot. Actually I've I've been a fan of you know, you know, we have a chance to talk some, I wouldn't say, you know, we talked all the time, not only at all he may. Um, but we talked enough to I respect his in fact when I first started out by one of the first things I did was I had, I asked, you know for a meeting with him and paul Dubois in san mateo and I went and met him for lunch and basically to say maybe we can actually part of the strategy for Numpy was to get it into python three and maybe part of python as we talked about that and about that approach, right? I would </s><s>[INST] love to be a fun. That was that was [/INST] that was good and over, over the years for ghetto I learned so he was open like he was willing to listen to people's ideas right? And over the years now, generally, you know, I'm not saying the university that's been true, but but generally that's been true. So he's willing to listen, he's willing to defer like on the scientific side, he would just kind of differ. He didn't really always understand what we were doing like and he defer one place where he didn't enough was we missed the matrix multiply operator like that finally got added to python but about 10 years later than it should have. But the reason was because nobody, it takes, it takes a lot of effort. And I learned this while I was writing Numpy also wrote tools to begin a python deV and I added some pieces of python, um, like the memory view object I wanted in the structure of Numpy into python. So we didn't get Numpy into python, but we got the basic structure of it in the python. Like so you could build on it. Nobody did for a while. But eventually he database author started to and it was, it's a lot better they did. And also antoine Petro and Stefan Cross actually fixed the memory view object because I wrote the underlying infrastructure and see. But the python exposure was terrible until they came in and fixed it partly because I was already Numpy and Numpy was the python exposure. I didn't really care about you didn't have Numpy installed. Anyway. Ghetto opened up ideas. Technology really brilliant. Like really, really got a lot of respect from when I saw what he did with the clap with the this type class merger thing that was actually tricky right. And then And then willing to share, willing to share his ideas. So the other thing early on in 1988, I said I started my first extension module. The reason I could, because he wrote in this blog post on how to do reference county, right? And without it, I would have been lost. Right? But he was he was willing to at least try to write this post. And so he's been motive. He's been motivated early on with python. There's a computer science for everybody kinda have this early on desire to oh, maybe we should be pushing programming to more people. So he had this populist notion, I guess are popular sense, um, to learn that there's a certain skill and I've seen it in other people to of engaging with contributors sufficiently to because when somebody engaged with you want to contribute to you. If you ignore them, they go away. So building that early contributor base requires real engagement with other people. And he would do that. </s><s>[INST] Can you also comment on this tragic, uh stepping down from his position as the benevolent dictator for life over the wars? Uh, you know, the Wallis operator? The walrus operator was the last battle. I don't know if that's the cause of it. But uh there's this for people who don't know, you can look up, there's the Wallis operator, which is uh looks like a Cohen and equal sign. And uh it actually does. Maybe the thing that you an equal sign should be doing. Uh but it's just historically equal sign means something else. It just means assignment. So keep stepped down over this. What do you think about the pressure of leadership? It's [/INST] something that you mentioned the letter, I wrote an umpire at the time that it was a hard time actually. I mean, you know, there's been a really hard time. So it's hard. You know, you get criticized right and you get pushed and you get um, nobody loves what you do. Like any time you do anything that has impact at all, you're not universally loved, right? You get some real critics and that's an important energy because it's impossible if you do everything right, you need people to be pushing, but sometimes people can get mean people can, I prefer to give people the benefit of doubt. I don't immediately assume they have bad intentions and maybe for other, you know, maybe maybe that doesn't happen for everybody. They for whatever reason, their past experience, the people, they sometimes have bad and they immediately attribute to you bad intentions like what this come from. I mean, I definitely open to criticism, but I think you're misinterpreting the whole point because I, I would get that, you know, certainly I started anaconda, you know, I've been, sometimes I say to people, I know I'm care enough about entrepreneurship to make some open source people uncomfortable and I care enough about open source to make investors uncomfortable. So I sort of, you know, create you create kind of doubters on both sides, </s> |
<s>[INST] Now for something completely different. Returning to testicles for time you posted instagram post of testicles as food. Perhaps eating them doesn't help libido because ingested testosterone is totally metabolized in the liver, returning to our liver, leaving none to reach the bloodstream. That is why testosterone only comes as injection or uh, topical foam. Not as pills. On the other hand, estrogen and progesterone can be absorbed orally. Hence the pill. But testosterone is mostly responsible for libido in women too. I was not expecting for this biology lesson when I was looking at an instagram picture of, are we looking at testicles? Are these like which species? I [/INST] believe all those are from cows </s><s>[INST] cows, cows? [/INST] Female. So bulls? </s><s>[INST] Yeah. Well, speaking [/INST] of which just </s><s>[INST] will jump around a bit. But you've also traveled the world quite a bit. Uh, what have you, what is the craziest food you've eaten across the world? What what have you learned about the extremes of the culinary arts by traveling the world? [/INST] I would say. I guess I've always been extra fascinated with the diets of, of natives of the far north. Um I spent some time there in Russia and in Alaska um and always loved their diet. So when I worked in Alaska in emergency room and did some other travels in the in arctic Alaska. And you know, they eat a lot of fat traditionally before contact. You know, more than half of all calories in the inupiat Eskimo diet came from blubber, marine mammal fat or you know, also fat from fish fat from ducks and other other birds that go up there to mate in the summer? Um So things like raw whale blubber um was especially interesting for me and very exciting. Um you know, I had some beluga beluga whale chowder, things like that. There's just all these very unusual dishes uh you know, they, there's a dish called mickey yuck, which is whale meat fermented in whale blood, </s><s>[INST] which [/INST] is quite delicious actually. </s><s>[INST] So is it cooked, is it eaten raw? Is it, how do they like their fat, like in in uh in the same way up north in Russia as you mentioned. So [/INST] they often eat it raw. So the raw whale blubber is called Mcduck. Um and it's often just sliced thin and it's like, it's sort of cold but not frozen often when they eat it and they slice it thin and a lot of people assume it would be very chewy, but it's not that chewy. It's quite pleasant actually and has this kind of see smell to it as you're eating it. I quite like it. </s><s>[INST] And what's the culinary culture like um meaning is it just source of energy or is it art? [/INST] Well, there's, you know, traditionally there's not a lot of cooking um in, you know, in the, in the arctic, a lot of things are eaten raw partly because there's not a lot of fuel for making fires. So um they will, you know, some in some of the big rivers in Russia for instance, that flow north, they will bring trees, dead trees and logs up to the north and they can get some wood that way and same thing. And some of the rivers kind of flowing northward from the brooks range of Alaska, you do get some trees but just not enough to really produce a culinary art that requires cooking with heat. You know, they do have um traditionally blubber lamps where the blubber of seals and whales are used to create a little flame often that's for light and for a little bit of heat. Um and and less for cooking, but eating things raw is definitely a huge part of the culture there. And while I was, I went on a whale hunting trip out on the spring ice um in the arctic ocean by barrow Alaska and two of the guys, the Inupiat guys who had invited me, we're kind of talking about how eating things raw is sort of the most essential characteristic of Inupiat culture. And the one guy who's half white, half an opiate said people often doubt his ethnicity because he looks like a white guy. So he'll, you know, bite the head off of a raw bird to show them that he is truly a new peak is what he said. </s><s>[INST] That's how you prove you're legit. We're looking at instagram pic as a doctor. I was used to knowing fat as the most maligned of all body parts and the culprit in an obesity epidemic. But in arctic Alaska fat has always meant health and survival. In fact, the entire story of life in the arctic, especially human life is basically a tale of fat and in borrow what's Ak Alaska, okay. Uh, along covered with whale blubber is still equivalent of a plush Greenlawn in temperature suburbia swelling in uh its owner with pride. And that's what we're looking at is a lawn full of whale blubber beautiful. And so this is, I mean there's a lot of [/INST] calories there and </s><s>[INST] this can feel a lot of people, a lot of energy, a lot of warmth. [/INST] Absolutely. And it's delicious. This was like I was a kid in a candy store, basically I rounded a corner and Barroso when people do get a whale during the spring whaling season, they raise a flag. The whaling captain raises a flag over his house and everyone in town is welcome to come try some. And so before I went inside to try some, I was kind of playing around with blubber and I saw that this is a bowhead whale. Um, I saw its heart, Which was huge, like the size of a, of a yoga ball. Um, and that was for me, just like amazing. I spent probably the next 45 minutes just looking at all aspects of it and the stump of Aorta that was attached to, it was the size of my thigh. Um that was really fascinating. </s> |
<s>[INST] I actually have never pushed to 55° you know, I wonder what that would feel like. But in general, I just love the feeling of a cold bed in a hot texas summer with a warm blanket, Colbert, a little bit of air conditioning, warm blanket. I mean it's just heaven, both for naps and a full night's sleep is just amazing. I love it. I think there's a lot of science behind why controlling temperature is great for sleep, but the actual anecdotal experience of it is amazing. They have a pod pro cover so you can just add that to your mattress without having to buy theirs. But their mattresses pretty good, go to a sleep dot com slash let's get special savings. That's eight sleep dot com slash lex. This is the lux Friedman podcast and here's my conversation with Travis stevens judo is a martial art sport, a set of techniques, ideas and philosophies. Can we start by, uh, maybe you're giving a big picture overview of what is judo to somebody who's like outside all the whole spectrum of grappling sports. [/INST] Yeah, judo was originated in japan that was used as a police tactic for self defense and you know, subduing people, it's the art of being able to throw somebody to the ground and hold and control the situation. Um, I think it's pretty much evolved since then though. You know, it's, as you include, like the sport aspect of it, it's, it's grown to be something more and more dynamic. Um, and it's kind of gotten away from that. </s><s>[INST] So the basics is, people were something called the G, which I think nicely mimics like outdoor clothing, like a jacket and uh, they started on the feet and there's uh, to get to grip each other and the scoring works by the more badass, the throw is the more points you get and if you throw the person big and hard on their back, you win the match and it's over and that's called an ippon, [/INST] which is equivalent to a knockout. </s><s>[INST] So I guess there's no knockdowns, we [/INST] don't count those. Yeah, they got to hit their back and they got to hit it with force, </s><s>[INST] and so there's a huge incentive for the big throws and uh and there's also the drama of somebody catching off guard with a surprise big throw and it's over, [/INST] yep, there's there's two ways of losing really? There's the, I saw this coming right, like you just, you see it, but you can't stop it. And those ones tend to be the ones you can live with, The ones that are like really hard to live with are the ones you never saw it coming, right? Because that just shows that that person is really outclassed you, </s><s>[INST] right? So there's like a set of a small set of throws, maybe you can go through them that are like, you saw it coming, but you couldn't do anything about it. And then there's the set of throws that are more like surprises. So first of all the counters or if you fake one thing and go the other way, then that's surprising. It's like, oh shit you off balance the person uh because they think you're going one way and then you go the other way and there's this, oh shit moment, All of sudden you're back is just slammed on the ground. One of the ones, I mean you're good at many throws, but one of them is a that I think reveals the beauty of judo is the foot sweep. There's something about off balance and the timing that if you catch them right all of a sudden, it's like I had the same feeling when I went skydiving, like all of a sudden the ground is not under you anymore. [/INST] Yeah, and you just, you go weightlessness for like a split second and you realize you've lost like all control of your limbs, like it's like zero gravity, right? Like you just, you can't turn, you can't rotate, you can't do much of anything. And then before you know it, you've hit the floor, </s><s>[INST] It's a cool feeling when you get thrown. Um because you hope to do that, this is something to another person. It's like you're you just hit the ground hard because it's not, you didn't see comedy wasn't a big throw that got loaded up. It's like all of a sudden the surprise and then like this like feeling your back just slams and there's like the air is up. [/INST] Yeah, and the worst is when you get hit twice with one throw right because sometimes like the guy throwing, you didn't expect you to leave either, so you hit and then that guy comes down like a second and a half later and it's like boom, boom and then the wind is just gone from you. Yeah, those are the worst. </s><s>[INST] And then there's the disappointment. Like then the intellectual, the cognitive part comes in when you're like, oh shit, I just lost. [/INST] Yeah. And you don't have like a connection to why right? It's almost like you just like you didn't literally get a concussion like you and you understand and remember everything but you can't figure out how this just happened, right? Those are those are the tough ones to deal with. </s><s>[INST] Actually have you had moments like that where you don't understand how it happened. You have to watch footage to understand what happened even [/INST] when you watch it, you're just like, I don't get it. Like why wasn't I in a position to stop this? It makes zero sense conceptually when you watch it, you're like, I understand how to play defense, I understand it looks like I'm in a defensive position, but at the end of the day I still got thrown. </s><s>[INST] Yeah, you were talking about what is the 2008 match? You have a nontraditional gripping style accurate to say, but and then you're going against another right handed player and then there's some kind of fake that he did and then he caught you can you can you describe the throat, he caught you with [/INST] he caught me with a drop sale, but he, he kind of like, we were engaged, we were looking at each other and we were kind of like a stalemate, right? He couldn't really advance, I couldn't really advance. And he kind of just let his gaze like wander off to the right, like he was looking at something and then I kind of like, what's over there? And then I got thrown and it's like, </s><s>[INST] so first of all, uh, for people don't know, uh, seo saying Nagy drop means when you drop to your knees and synagogue is one of the fundamental throws of judo. There's just just a handful. But is that actually ever work? I was wondered that about like boxing or judo does the head movement of the person work because we're still like, kind of dogs at heart. If you look somewhere with the dog, the dog is gonna look that direction as well, that actually work ever [/INST] does. Um, but on a greater sense, what you try to do is not necessarily get like a physical reaction of a look, but a lot of security where like, they've almost like relaxed for that split second because you've lured them into like a sense of comfort. And then that's when you can strike. </s><s>[INST] So you have this. Speaking of scientology, you have this gigantic uh standing santiago. Yeah. And um, you have a specific grip. One of our challenges is, there's a large number of people that listen to the audio version of this? So we're gonna have to try to describe some of the stuff, I'll do my best to try to describe with words, but you have your grip with your left hand on the lapel of the jacket or like that area. And uh there's kind of a lean into the person and I suppose is there a feeling of a lull there that you're trying to get to where you're just, it feels like you're both calmly dancing before you turn your hips and going for the throat. [/INST] I'm actually trying to create a a sense of weightlessness for my lead leg, which would be my right leg and a sense of resistance from my partner. </s><s>[INST] So you aren't you both kind of leaning into [/INST] each other and it creates like an a frame. Yeah, but when the a frame is held together at the top half, which would be my left hand and their right hand posted on each other's chest, it means our legs are free to move in, Our hips are free tomorrow. </s><s>[INST] And they're not gonna feel your like move because [/INST] of the weightlessness. </s><s>[INST] And is there a feeling like for them is they're feeling like nothing bad can happen here, We're all relaxed. Everything's fine. Yeah. [/INST] And then they're standing off at a funny angle and before they know it, I've spun and my back is on their chest and they can't go anywhere. Yeah. </s><s>[INST] Yeah. How did you first develop that throw? So for people um it's called Ponsana G. Which means your right hand goes under there like armpit area and that that's like a vice that connects you to them and then they go on for the ride. The interesting thing with the standing one is uh as opposed to drop the nrg version, the drops in argue kind of um drop under them and because there's a vice there like pulled pulled under and like over uh with the standing one, I suppose there's some similar physics but you're kind of loading them onto your hip and so they're in the air while you're standing still. There's there's a there's a sense in which there like you're lifting them above where they started. Yes, that's how you get the really big air if obviously if um if everything is right? So how did you first develop that? How did you first, [/INST] I first learned just learning the very basics of the throw, you know, foot placement, all that kind of stuff and then, you know, like anything, the basics are nice. Um but once you get good at the basics it's it's very easy to stop but it gives you a good like fundamental platform to learn off of and to expand off of and then I expanded when I first started watching Koga the new wind right? Because he's the one that first like introduce that split hip style saying, argue that I do um once I learned that one, I built about eight different variations of sail off that one start position that way I could, regardless of your defense. I had an answer for a throw. </s><s>[INST] So why is that one though? Why can you, can you describe love to me? Travis students? Why did you fall in love with that throw in particular? [/INST] Um, it was really a sense of, you know, one of my shortcomings as a kid, like I hate leg day in the gym, I hate it with a passion. I, if you ask me to do a squat, I'll get it done, but I will bitch and moan every step of the way. I hate it. I remember one time I was at the gym with my train and he goes, okay, we're gonna do front squats and I want you to put 2 25 on the bar and I was like, I can't do that. And he was like, what do you mean you can't do that? And I go, I physically I can't do that. And he was like, Are you serious? And I go, yeah, so he's, he didn't believe me, we put 225 on the bar and I bottomed out. And then he was like, okay, let's go down to 1 85 and I was like, I can't do that, I just, </s><s>[INST] that's not happening. You probably couldn't strength wise, you just refuse. [/INST] I just mentally, I cannot wrap my head around like this ain't happening. I'm not doing it. So I ended up with my principal 1995 lb on the bar. I got you at the front squat. No problem. </s><s>[INST] By the way, Bodyweight squats are rough to. Yeah. [/INST] Yeah. I just when it comes to my legs like I want no part of like leg pressing single leg squat split squad, any of that, no part of it. </s><s>[INST] So you think like the more traditional variants of scientology require you to have that leg strength [/INST] that mass. Like when you watch japanese judo players like their thighs and their hips, they're thick, they got a lot of power there. </s><s>[INST] So you're almost like always dropping a little bit into a squat position. The mind never no, no, not you sorry for the traditional ones. [/INST] Yeah. And so the split hip, the split hip actually allows me to keep my legs straight and the farther I split my legs, the lower my center of gravity goes. Now I don't need my legs. Yeah. Perfect. Love it. Let's </s><s>[INST] do it. That's the way you were thinking about. Okay. Um but it's uh you know the interesting thing about it is because you know, as I mentioned to you of got into judo after first watching you in the olympics and then watching Koga as well. So you start imitating the people you first see and then you take it to judo coaches and they're like no, no no that's the wrong way to do it and happens [/INST] All the time. It drives me nuts, drives me nuts. I was in Poland one time teaching a camp And I had two coaches anti coaching telling their kids not to do so the way I do it because it never works. Yeah, it's crazy. </s><s>[INST] How do you have the fortitude and the guts to just go on with the throw? That's not traditional, the variant that's not traditional [/INST] if you think about it, you know from a very basic like root of it. There's a philosophy and a mentality of judo of how the throws work, right? There's a mechanical structure there. Like this makes sense. If I follow that principle, I can do anything, I want, nothing else matters. As long as we follow those core principles </s><s>[INST] in the early days, even even then you were able to think on your own. [/INST] Yeah. And I was able to develop a pattern for my foot placement based on my opponent's hype because the number one thing any judo coach will tell you is you need your center gravity below yours. Well now I now I know exactly where to put my feet because the shorter you are, the bigger the split because the lower I need to get, the taller you are, the less of a split I need. </s><s>[INST] Is there something you can say about fundamental principles of judo. Is there over all that time. 20/20 years that you've been doing judo? Uh not approaching 30, is it? [/INST] Yeah, yeah, yeah. It's going to get in there, get a couple years away. Let's get in </s><s>[INST] there. Um Is there some like principles that have emerged? Like you said, you have to have your center of gravity below. There's is there other kind of both on the gripping side, the footwork side, leverage, anything you can speak to? [/INST] There's some that have withstood like time. Like you have to be able to get below their center of gravity because you have to be able to rotate them around their center of gravity. And then the other one is that was always a principal when I was growing up and I didn't change until later on in my career was you have to be able to pull, you need to be able to pull to get them off balance. But when you think about that statement as a whole, it ended with they have to be off balance. I don't need the pull to get you off balance. I just need you off balance. And when you think about it that way it allows you to open up the doors to what do I need to do to get you off balance. I could push pull, I could flinch, I could fake and you could put yourself in your own off balance state, right? When you think about people who wrestle right, if I fake shoot it causes you to over lean forward, which means you're off balance, there's no poll, there's no push, there's no nothing. I just get a reaction that leaves the opportunity in the door open for an attack </s><s>[INST] and that off balance can be very subtle, [/INST] could be very subtle and the better you get and the more skills you get, the less subtle it is. </s><s>[INST] So we should also mention that there is something called forward throws where you throw the person, you know, they they're gonna fly facing forward, they're gonna fly forward and then backward throw is they're gonna fly back. [/INST] So then there's lateral, you know, they actually go sideways over like a cartwheel almost. </s><s>[INST] Okay, so the forward throws, there is the one we've been talking about, which is saying A. G. And there's a bunch of different variants. Stepan Marotta say Nagy, there's drop in there, standing versions of them and that all, I don't know if there's a way to summarize it, but that's like as clean as a getting your center of gravity under theirs as it gets. And then the rest is just gripping variations. Yeah, I guess it's all gripping variations on all of these threats. But um and then uh there is uh in terms of forward throws there's the other big one in competition is Yamada, which is, I don't know, we can try to explain that one, but it uh ends up being where one of your standing on just one of your feet and the other one is up in the air and I don't know if you put in that same category, hurry go. She like those kinds of throws where you're kind of a little bit single footed [/INST] then. So there's two footed techniques and then there's a single </s><s>[INST] footage o goshi where it's like you're doing a mix between Sumatra and the synagis. Yeah, it's a hug, You hug a person and then you turn your hips around such that you're now hugging facing the same direction [/INST] when it comes to forward throw. There's regardless of the name of the throw or the gripping variation that you're using. The whole principle is how do I get this person to do a forward roll in mid air and land on their back? The more of a forward roll I can get the bigger the score if I get like a quarter of a turn where like you and on your side and you don't go over your back to half score. But they all require me to get you to do that forward rolling action. </s><s>[INST] So just if we think of one person, if they do this nice leap forward and they do a role and they're back nicely rolls over the ground, you're trying to do the exact same thing with you connected to [/INST] them well and if it's nice and it's smooth, it's probably not a full score, it needs to have like somewhat of a violent impact, right? So if you think of a drop saying Maggie, if I if I'm moving too slow and you still roll over your shoulders and there's no direct impact, it's only a half score, right? They want the force, </s><s>[INST] the force, the violence is good. Uh So then, uh in terms of backward throws, the traditional ones, there's stuff where you trip them from outside their body, like O Soto Gari, it's a trip where you hook your leg onto their leg and you trip them, but your hook, it goes outside of their legs and then there's the trips from inside their body. There's uh one ft is called coochie Gari and then the others, Okay, Gary doesn't matter, the, the most important thing is outside and inside. Uh and then there's like, I don't even know how you throw them sideways except foot sweeps, and then there's the foot sweeps where you can sweep one of their legs from out of them or both their legs at the same time. And like we were talking about this kind of is when timed perfectly, it's it's effortless for everybody involved. And uh the ending, like you said, is big dramatic and violent, is there other kind of, oh yeah, there's a sacrifice techniques. Um there's a bunch of them and then ultimately the variations have to do with gripping, but you're basically you the attack or fall onto your back, sticking your legs somewhere on onto their body, which is like this fulcrum over which they fly and do that same kind of role that you [/INST] mentioned, you basically sacrifice your back to the mat in order to throw them into that circular pattern, so they hit their back. Sometimes we use a foot, sometimes we </s><s>[INST] don't, and so we should probably say it's okay for you to go onto your back as long as you're clearly demonstrating control over the other person's body, [/INST] correct? You can't go to your back in the same direction that your opponent is trying to put you to your back, you have to go the other way or you have to initiate you going to your own back. </s><s>[INST] All right, uh, like clearly, and then, um, and then there's all the counters which almost kind of have a whole group of their own, even though they have echoes of the same types of techniques, it seems like they're their own whole thing. [/INST] Yeah, but they follow the same principles. It's just most counters, like if you wanted to counter an Uchi Mata, for example, you're trying to throw me in a somersault over my right shoulder. Therefore I would counter you by throwing you over your left shoulder, it goes in the opposite shoulder direction, but in the same somersault </s><s>[INST] idea and there used to be already at this point, forget the years, but it might be 20 before the 2012 olympics, or they banned uh you used to be allowed to grab legs in the same way you do in wrestling. So you have basically all the techniques you would have in wrestling um available to you if you would like. Uh it's just that some of the techniques and wrestling are not that effective for getting your opponent your to their back wrestlers want to take the other person down in any way possible and have control judo wants to take you down. Like we said in a big fashion or your back slams on the ground [/INST] has to be to the back a lot of wrestling takedowns happening because they get behind them and then they part their out. </s><s>[INST] So uh judo banned all touching of the legs, which is very dramatic change of the sport. But I'll give you 2012 after it was after it was [/INST] In 2012. So 2000 and I thought the games and everything was free In 2012, we could only touch the legs as a defensive action or in response to an attack. So I could try to throw you with a normal throw and then when you try to counter, I could grab your lake. </s><s>[INST] So there had [/INST] to be a secondary </s><s>[INST] technique and didn't like didn't they disqualify on a first offense. [/INST] First offense was a direct disqualification which happened at the 2012 games to the 57 Brazilian Who won in 16. She was D. Cute and I think the quarters. Yeah. And it was like, I wouldn't say it was blatant as much as I don't think the act change the outcome of the match, had they not disqualify? </s><s>[INST] Sure. So that's not that dramatic. And by the way, you say 57 that refers to weight divisions and that's in kg and kg is the measure of weight that the rest of the world uses states does not. Um so and there's uh we should say the divisions for for guys. Um I don't know what the 70, I don't know. It's lower level 60 [/INST] 60, 66, 73 and 81, and heavyweight. Which has no ceiling. </s><s>[INST] No selling [/INST] as well. </s><s>[INST] Yeah, it is important distinction. Um So and you competed most of your career at 81 kg. All of it all. You never did anything [/INST] Ever did 73, </s><s>[INST] but you have to cut big for anyone anyway. Especially [/INST] at the end of my career. Yeah. </s><s>[INST] Uh [/INST] overly grew into the division. </s><s>[INST] What's uh I'm trying to remember. Is that about 180 lb. One [/INST] 178.6 I think. </s><s>[INST] And you have to weigh in with the g No [/INST] nothing. You're not allowed to wear anything except for your underwear way is </s><s>[INST] confusing digits. Oh, that's right. That's right. That's right. That's which is very nice. Um Okay, so we would you say we covered most of the throws in now. So the there's the forward in the backward, there's a sacrifice throws and the counters and the and then there's the leg grabs, It was just say for the leg grabs that were effective, it's like uh the big pickups where you just kind of picked them up and try to figure out once they're in the air, what the heck to do with their body to get them [/INST] to the ground, you just kind of figure it out as you go. </s><s>[INST] I think the really nice one that was to be heartbreaking as a fantasy go as I guess what's called the fireman's carry, which is, you know, it does lead to judo, like beautiful throws and the fact that that was gone is is that one I missed a little bit, but then a bunch of people I guess came up with the variance where you don't need to grab the leg, [/INST] it's definitely not as effective as being able to grab it, but I'm also on the side of the fence having competed in all three, it was definitely better for the sport to remove it </s><s>[INST] as a whole. It's probably good to cover sort of the whole spectrum of rules of judo is, there's groundwork. So there's uh you do all this stuff on the feet where you're trying to murder each other with a giant throw, but then, you know, if the throat doesn't succeed, you go to the ground and you stay in the ground for some amount of time, like short amount of time, you have to move quickly, You have to be attacking and uh, two of the ways you can win is similar to people who do Jiu jitsu as you can submit them chokes, arm breaks, all that kind of stuff, No foot locks and uh, and you can also pin them, we just get around their legs and this is very, no, this is not like wrestling, you have to actually get around their legs and uh, pin them and what injustice called side control them out, all kinds of ways that doesn't involve their legs and they pin them for like whatever, 20 seconds, 25 seconds, [/INST] 20 seconds. Now, I think the distinction is there back has to be facing them at, you have to be passed their legs and your chest has to be on the same plane as there's, so it doesn't have to necessarily be on top, but it has to be on the same plane </s><s>[INST] and all of this is, I think different sports of different versions of this, but it's like an approximation of what dominance looks like soap in and wrestling is dominating your opponent, presumably if you're in a street fight, that position allows you to then do a lot of damage. Obviously submissions is dominant because you're breaking their arm or choking them to unconscious and then obviously the throw, which is not often talked about, but like if you talk about a street fight situation, a throw is like the best way to murder somebody like this could end anyone's life. Yes, it's terrifying actually. So okay, so these are elements of dominance. Yeah, so going back to set of principles, you're mentioning getting your center of mass under. There's which I think applies for type of um like the forward Saint Magi throws, is there is there other stuff um Obviously you mentioned off balance? [/INST] Yeah, there's the off balance one where you can either pull to get an off balance or you can give way to the force which can also lead to an off balance. Um You can amplify somebody's force to, so for example, if you push me, you expect a certain reaction that you're ready for. But if you push me and I pull you now you didn't expect that much force coming out of you, therefore you're off balance. </s><s>[INST] The thing that's distinctly recognizable about judo is like when done at the highest level, Like it seems effortless when the big throw happens, like that's just it doesn't, there is no other sport like it in the in the combat sports where it's like when the timing is right, everything just is perfect. I think you you get the um I'm a and um boxing sometimes when this is perfect, perfect strike, just like what they, but it's not just like a hard hit, it's like it's almost like the, with Connor McGregor and Aldo, for example, when you just catch him [/INST] just just right and that you didn't look like you hit him that hard but you hit them just right </s><s>[INST] and then you get to see this all the time in judo. It's fascinating. And so the beginning part of that is because there's a jacket, there's also this whole thing that your master of which is like which is gripping. So is there something you can say about? Are there some fundamental principles of gripping? You can speak to like what the hell is gripping, [/INST] gripping is having the ability to hold your opponent in such a way where you have the ability to be offensive and also the ability to be defensive at the same given time. And it's a distinction because I can hold you in such a way where I might be able to feel offensive but if you can take a purely defensive grip and then I can't be offensive. We are no longer gripping. We are holding each other right. Right. And so like that would be the act of being able to grip is to be in a situation where you have me and I have you and I can play both offense and defense at the same time where you can only play defense. </s><s>[INST] So Donna her talks about like digits. So that way not that way but maybe you can see if there's a distinction. So you have a set of weapons. The other person has a set of weapons. You wanna sort of maximize the use of your weapons and shut down the set of weapons they have that they have, you see, gripping the same way and on the feet, [/INST] I do, if we want to include body positioning with are gripping because I can give you any grip you want and you still can't throw me because I can put myself in a position that nullifies your ability to use those grips in a successful way. </s><s>[INST] And those um would you say the hips are critical to that or is it everything [/INST] hips, shoulders, chin position, had position, you know, the angle of your foot? Yeah, where you lean, </s><s>[INST] wow, okay. And so, and there's a bunch of places you can grip, obviously if people kind of think of a jacket, like there's a bunch of places you can go up there, interesting, so you can grip on the collar, you can grip on the sleeves, you can group like the elbow joint and you could do uh those badass, like eastern european Georgia over the [/INST] back, back, over the opposite sides of the heads, The Koreans that grab on one side, around the head with their hands together. </s><s>[INST] Yeah, there's something really nice about just those, like, especially George is throwing that hand just over the person and just you're not actually gripping a belt or anything, you're gripping just the entirety of like as opposed to being all nice. So I'm gonna grab this part of the jager, this part of the jacket, you're just like taking the whole fucking jacket and just launching somebody [/INST] for those people that can't picture judo, think about it. And like if you understood like what a boxing match looks like, and you thought about that as like traditional gripping when you throw like a Russian grip over the back, that's more like a hockey fight, Like I'm just grabbing you and we're just going to, we're gonna be throwing punches left and right, because when we have that grip, somebody has to get thrown. Yeah, there's no, there's no, we don't walk around with this grip, it's, it's go time once somebody throws it </s><s>[INST] to me as a, as a fan and sort of amateur practitioner, there's two styles of olympic level judo. One is where you're trying not to get thrown, and the other is where you're trying to throw uh more specifically when you're trying not to get thrown, there's like the strategy they're using, gripping too nullify their offense and all those kinds of stuff. You're, you're being very clever and strategic and all that, you know, maybe using conditioning and then there's people who just like step in the pocket and they don't almost don't care if they're getting thrown because they have the confidence that they're going to throw first and those, like there's a clear distinction between the people that do one or the other and I think both can be done extremely successfully at the highest level? It's just like obviously you admire the people that step in the pocket. And, [/INST] and I think when you look at the people who do judo the best, like if we want to talk about like The top 10% of the people who had competed the games, they do both And they do both really well, but they favor one because if you look at a player like uh, Utep italiani of Georgia for example, there's a guy that stands in the pocket, but we can find numerous occasions where he's hustled some people for like a short period of time to get out of scenarios to elongate the match to make somebody tired. So you want both sides of the coin, But you better pick the one that, you know, 80% of your strategy is going to be built around. </s><s>[INST] Sorry for the romantic question. But I talked to dan gable and uh, he always looked to the Russians as um, as the artists in wrestling and he always wanted to be an artist. But I think he's known for being that sort of guts aggression, mental toughness guy. But he always was drawn to the artistry of wrestling. It's hard to know when you just watch you because it looks like you're aggressive and you've got the guts and the mental toughness. But there's also obviously a master of technique, which would you lean towards in terms of what accounts for your success and just the way you approach judo. Is it the the gods, the aggression, the mental toughness, or is it the mastery of technique? The artistry? [/INST] Mine would be my my aggressiveness if I'm gonna pick those two areas. Um but I think there's a third area in there that I would put myself in, where I'm more of a strategist, I look at all of my opponents and all I ever see is their faults, and the way I do judo is built around their faults. And it's just I put myself in scenarios where I don't even know how I'm going to win. But what I've done in those scenarios is I've made it very difficult for you to win. And then I figure out the rest as I go, </s><s>[INST] like, how do you study an opponent? Are there bins? You can put them in like there's a lefty and a righty or uh that this kind of stuff. How many bins are there in judo in your mind that you put your opponents in? [/INST] Yeah, there's probably about 20. There's like certain players who you could put in a category of like, They're only good for the first, you know, 2/3 of the match after that, they turned into a different player where they're either falling into a sense of panic or uncertainty. And you can if you were to take a video clip of, let's say, churches billy, right? They got George and I beat in the olympic semi, he's somebody that would beat you in the first three minutes. And if you clipped out all of his matches and you only watch the first three minutes of every match, you would see one style. If you found all the matches where he got taken into the last minute and he wasn't winning by a major score, you would see a completely different fighter. And so going into like my olympic semi, I put him into that category of like, I want to get to this guy because this guy is beautiful. The trick is how do you get </s><s>[INST] There? How do you get there? And by the way, we're talking about the 2016 Olympics where you won the silver medal, you're part of uh three different Olympics. But cardio aspect of it, have you faced exhaustion often in your matches where you have to go deep and go like past. [/INST] Yeah, but that's not from the judo side of it, that's from like I did a very bad job of making weight, </s><s>[INST] it's always the way cut. [/INST] Yeah, it's always the way cut and I think people really struggle with that, they blame cardio and training and everything else. But when it really comes down to it, like we trained for an hour and a half, two hours twice a day. How are you tired after five minutes. Right, Right? It becomes into a mental struggle, your anxiety, your stress, your lack of belief in yourself or in my case, sometimes it's poor nutrition, sometimes I had one too many Mcdonald's meals. It just, it happens. Okay, </s><s>[INST] so let's talk about weight cutting real quick. So I've seen weight cutting break, some of the toughest fighters, wrestlers, grapplers ever like burn outbreak, like where that makes you want to quit the sport. Um, so you know, this is what people don't often talk about, but mentally is one of the hardest things, especially when you're doing it kind of wrong because it becomes a mental war. Uh, So you competed, like you said your whole career at 81 kg you walked around at [/INST] 88, </s><s>[INST] it's about £15 sometimes £20 over that [/INST] give give it to </s><s>[INST] you. And so what, uh, what was your process? Like mentally and physically? First of all, maybe you can comment on when the Waynes are relative to the matches and then what was your process like leading like a week ahead, a day ahead? Our head minutes ahead of the way in [/INST] meant, everyone varies tremendously because we're not like most sports because you're dropped off in foreign countries with who knows what, right? Some places have sauna, some places have treadmills, I went to a place one time in china in the middle of winter where the roads were frozen with ice and we had to use our hotel rooms because it was, you couldn't sweat outside because it was too cold. Um And every one of my olympics, The weight cut was different just given my mass. When I went to 2008, I was probably like 82 83 kg walking around. So weight cutting wasn't a thing for me In London. We actually weighed in the morning of so wayans were at like six a.m. And the Olympics were always beneficial to me because they actually don't start until like 10 or 11. So you actually were able to recover where on the circuit you would weigh in at six a.m. And the competition starts at eight a.m. And it's like, well I was cutting weight at 5:00 AM. </s><s>[INST] And most of it for people who are not familiar, but maybe you can also correct me most of it. You're really just getting the water out of your system. Is was water point. Yeah, that's like 24 hours before even like so are you like an hour before? But yeah, but like leading up to it. Um And have you eaten the day before? Do you try to minimize the amount of food in your system? [/INST] My way cutting process was a little bit different than most people because I like to eat. Um I'm not, I'm not the type of person that believes your athletic career is determined by your nutrition, right? I don't I don't believe that I think some sports are built that way, but when it comes to combat sports, like, you know, your ability to knock somebody out has nothing to do with whether you had a cheeseburger or a salad. My ability to throw you is not determined by that. I may be able to perform better because I've eaten a certain way, but not enough to justify an entire diet change. Your body is built and my body is built to operate with certain things that I've had in my system for years. </s><s>[INST] Yeah, I think I'm with you, but I also believe that there's a mental aspect. So if you're surrounded by people that tell you diet matters, then if your diet is off, you're gonna believe you're going to be off because the people around you tell your diet should be good. So yeah, I think it's like, it's the same. I I've had an argument with Matthew walker who's uh who's asleep, scientists about sleep and it's like if you believe sleep is essential, it's essential to get eight hours of sleep every single night perfectly, then you're going to be very stressed when you don't get it. And then I think you will negatively affect the stress will negatively affect your longevity and all kinds of aspects of your life, if you actually just learn to truly listen to your body, become a scientist of your body will sleep and food, it might end up that it will be the eight hours a night or whatever. But it might be something else and probably diet here. [/INST] I remember when I was meeting with the USOC nutritionist after London, it was probably around 2014 I think. And when we had our team meeting at the beginning of the year and I was talking to him, he was talking about the nutrition plans that he could put us on and I was like time out. I've done the USOC thing like I've done the couscous, I've done the lemon in my water. I go full shit. Oh boy. Like there was just, cause there's like a cookie cutter plan, right? And I was like, look, here's what I want you to do. I go, I'll listen to you, but you're gonna walk into the 7 11 across the street from the USOC and if you can't buy it and that's 7 11, it's not on my plan. Yeah, I go because I go to places where the only thing I can eat it sprinkles and a snickers bar. I've done that. Like I've flown to Azerbaijan stayed in a hotel where the restaurant is closed. Usa judo hasn't paid for the meal plan and the only thing that's available is the thing across the street. </s><s>[INST] So you were eating Pringles [/INST] Before fighting a grand slam event while cutting £20 and </s><s>[INST] his and his sneakers. Yeah, that's the visual of that. That's some like that. Some rocky shit [/INST] build me a nutrition plan, go for it because I'm not paying my own way To travel with 14 days of food, </s><s>[INST] right? I mean that's that's one of the magic of your whole career and also judo. I mean I'm sorry to say of course you want athletes to be super rich and super well funded from an athlete perspective and the sport to be popular and managed in an ultra competent way. But as that's not reality. But as a fan is fun to watch somebody like you who's exceptionally driven have to suffer in all these different interesting ways. But it's [/INST] only suffering if you expect the other side, I don't expect it. I accept it for what it is, which is why I write off nutrition for athletes because it can be done without it. As long as you know to what you said before, like you don't believe you need it. Some people believe they need it. </s><s>[INST] The mind getting your mind right is the most important thing. [/INST] You know what I believe? I need a snickers bar when I'm tired, I want a little bit of sugar, makes me feel better. </s><s>[INST] You want me to see you uh what you can do. Yeah. I just love the visual of you eating a [/INST] sticker. That's what became but that became part of my nutrition plan when the U. S. O. C. I wrote my nutrition plan. I was eating a burrito bowl with brown rice, white meat, chicken, black beans, guacamole cheese to chocolate chip cookies and a diet coke? </s><s>[INST] This is like chipotle. Uh It was Bolocco but same concept, same same concept because it's chocolate chip [/INST] cookies because I needed the sugar. I was I was 88 kg when I stepped on the scale at 6.3% body fat. Now I gotta make 81 </s><s>[INST] six. What? [/INST] Really? Yeah. And the USOC was like, hey, You know, you can't you can't fight anyone anymore. You have to fight 90s and I go, I'm already into the quad. I'm not changing. I go build me a plan where I can do this and now we have to have an acceptable weight cut. Like it just, what do you want me to do? I'm not the I J. F I can't just change the fact that it takes two years to qualify. I know where I'm at. I know what I have to go through and I accept the consequences. It is what it is </s><s>[INST] we want. All right. So what was the process? I mean, can you, can you speak to? So you wake up early in the morning the day of the way in a few hours before [/INST] technically my weight cut never started until I got off a plane and to a hotel </s><s>[INST] and how many hours, [/INST] three days? </s><s>[INST] So it's a three day cut to three day mentally you're thinking of it that way and then you're still eating [/INST] I eat every day </s><s>[INST] and then like what do you look up on water? Maybe as you start and then or the water starts [/INST] just it is what it is. </s><s>[INST] So yeah, I mean it's a slow, you're not actually like sweating all three days, but then it's like torture to sleep. [/INST] Are the process? </s><s>[INST] Are you able to [/INST] sleep? Sometimes? It depends. </s><s>[INST] So you're dehydrated further for the dehydrated with 67% body fat Trying to lose 10 [/INST] pounds. I even developed a way to drink water out of a bottle where I don't drink anything, but I feel like I have </s><s>[INST] uh swishing it was the [/INST] No. So I take like a bottle of water and like if we were to like to draw a line on it, I would tip it and I would go like this, I go Mhm. Yeah. Mhm. And you would draw that line, but like I drink now water for 20 seconds or whatever it is. And I feel like you're getting a brain told me I got there no problem. </s><s>[INST] That's amazing man. [/INST] You just, your minds are very powerful tool. And the problem a lot of people have is they don't accept the reality of the situation. They bitch about the reality of the situation, I just, </s><s>[INST] first of all, you could always quit, right? Yeah, so like you're not, never missed weight, never, never [/INST] you can you can perform poorly, you can't miss wait, don't miss wait, don't miss wait because you can always win regardless of how bad the way cut is. You can never win if you miss wait. </s><s>[INST] But your your brain is also really good. Maybe not your brain. Yeah, but I know my brain. I think most people's brains are good at generating the more desperate things become, the better it's generating excuses. So what were you doing with your mind that the result in the, you never missing weight? The plant. [/INST] So like I said like my weight cut would never start until I got to the hotel because I didn't check my weight the morning of, I didn't check my weight when I got there. I just while I'm traveling, I'm doing things at like a minimal level, but I'm never not giving myself something I'm creating if I'm thirsty, I'm drinking a diet coke. If I'm hungry, I'm buying a Snickers bar, I'm buying a sandwich. I am and I accept the consequences when I get there. And then when I get there, If I step on the scale and it says 88 kg, I instantaneously know exactly what it's going to take to be anyone. </s><s>[INST] And then you just follow like a robot follow very specific process. And then, I mean because there's a lot of seconds in three days, seconds and minutes and you just, [/INST] I just know exactly what it takes from my body. I know exactly what a one hour gym workout wearing a sauna suit is going to take. I know exactly what I'm gonna lose on day one and I know exactly what I'm gonna lose on day three because they're not the same. So I can instantly look at a hotel decide is there a bathroom, sauna, gym temperature of the gym access to the gym and when it is access to the judo mats, my training partners, the roads versus streetlights, the weather outside. I can take a look at that environment and say, this is my weight. This is weigh ins and instantaneously in my head. There is a plan to </s><s>[INST] make weight and you have a sense of how much sweat adds up to to £10, how much sweat plus time just and [/INST] I make sure in my plan, all of my meals and how much water I need in between is allocated to still make way because you have to eat or drink during that time. </s><s>[INST] Are you incorporating like mental exhaustion into this? [/INST] That doesn't exist. </s><s>[INST] So it doesn't, doesn't do you like meditators? What did the thoughts come, especially three days. We're not talking about four hours of suffering. I'll tell you this has broken some of the toughest people in the world. The [/INST] hardest weight cut I ever had, the hardest one. Um, I fought pan am games in 2015 in Edmonton. Canada on a Wednesday and I won. So I've, I've made weight on Tuesday. I fought on Wednesday, where I had to win 5% of my weight class of 84 kg on Wednesday. I was 84 kg. I got on a plane on that Wednesday night and landed friday morning in Sochi. Okay. So I've traveled now. I got on the scale. All my bag's got lost everything. So somehow I flew from there to here, no bags and I threw all of my stuff in my bag. I wore sandals, one pair of pants and a T shirt on the plane because I was like, I'm just tired. I just fought like, I don't even want to carry it. I don't care. What are the odds that I get there? My bags are gone Very low, very low sure enough it's gone. I get all the way to Sochi. I check into the hotel, there's one sauna. Guess what? You have to reserve it and you're only allowed to reserve it for an X. Period of time. </s><s>[INST] Gets get a small tangent when you found out your bags are gone. This is something I often think about. There's like people that are helping you write like that. This is a personal airport who goes, yeah. Oops, just like that. And then the person at the hotel who tells you that you have to reserve the sauna and looks at you like you're, yeah, they don't care that you've been suffering. They don't, [/INST] they don't even understand why you need it. </s><s>[INST] Yeah. Like why you know, oh this like uh like this little kid reserved it for five hours or something to block it off. So I'm sorry. Um is there a frustration that gets in there? Are [/INST] you just accept reality? Don't, don't even hinder on like the things you can't change because the second you get frustrated the second you think you can change it, your heart upon it and that breaks most men that like little thing in the back of their mind. Thinking all like what if there's no what if like there's only right here right now. It doesn't work. It doesn't work. Let's just quickly come up with a solution to fix the </s><s>[INST] problem. By the way, there's another small tangent. All the greatest people of interacting with at the highest level, think like that they don't linger on that. It's like the next thing because like if you want to do something great hard stuff is gonna keep happening to you and if you're gonna let that affect you, you're not ever going to do the great thing. It's fascinating actually. Like that's the one skill you have to learn uh almost as great at this, constantly dealing with emergencies. Okay, okay, this happened. What's the next step? [/INST] Except it's not that big of a deal. Every problem has a solution. Yeah. And if I can't solve it, it's not my problem. You know? We do </s><s>[INST] exactly what? So I figured out. Sandals get [/INST] this, I get to the hotel. I check in. I don't even know about the sauna yet I go, I need to find a clothing store. I'm in the middle of Russia. I open up google maps and I'm like sports store. I find an Adidas sports store in the middle of Sochi Russia. Right? I spend like $500 on like average sweats, no plastics, no nothing and no running shoes because they don't have any, </s><s>[INST] what's the temperature outside? It's cold. [/INST] It was kind of like spring ish. So it wasn't cold, but it wasn't hot. </s><s>[INST] So you still need a lot of layers, preferably. [/INST] You would need a lot of layers just to cut the amount of weight. I'm about to tell you, I have to cut because after I bought that stuff that next morning and mind you, it's a friday to friday morning. I go to the venue where we have the mats open to train and I step on the scale and then second batter, Mongolia goes, oh, pretty good. You're almost there. And I go, no, no, Oh God. I stepped on the scale at almost 94 kg. And I looked at him and I was like, I'm 81 and he went, good luck, you're almost there. Yeah. For the next week. Class above. </s><s>[INST] Uh, this is on a saturday or [/INST] friday morning. </s><s>[INST] No, no, sorry Friday morning the competition is one [/INST] sunday sunday away on sunday. Okay, like holy crap. I throw on all my layers and there's one other person with me. They're Khalida whose my girlfriend at the time, now my wife, we start doing judo because I'm like, this will be the easiest way to knock off like three or four kg. Well, it's cold. I have no G and I'm working out with a female. I can't get, like, Overly physical to like really get my muscles going to really break that sweat because she has to compete in a day or two do this. She's not a training partner. You can't just use this person. I stepped on the scale. I was 91 kg. So, I mean, that was a nice dad, but like work out. Yeah, I go, that's that's not gonna fly. So sure enough, the clothes are now ruined. They didn't help me lose any extra weight. So I go back to the hotel and I start reserving the sauna. Do you know how hard it is to lose that much weight in a sauna by yourself. </s><s>[INST] So it's hard on many levels. But one of them is just mental. Yeah, you're sitting in heat. [/INST] Heat and you're not doing anything. Like if there had been a bike or like the sauna was big enough to use a jump rope where you could do some sort of activity, but you just sit and you still and you're there mentally at one point during the weight cut, I actually had my mouth on the bottom part of the door where there was a little gap and my legs up on the benches and Khalida holding the door so that it didn't open so I couldn't open it so that I could lean against that thing and have fresh air because I was like, I was struggling </s><s>[INST] and we're talking about, I mean, how many hours is that [/INST] ours? And then the thing is, is because you have to reserve the sauna. I can't even take like a 30 minute break because the song is not going to be mine in an hour, which means you have to use the sauna in the heat for that a lot of time period And I hate saunas. That is always my last resort. I will use a bath. I will train. I will run. I will jump rope. Sauna is like, let me do that for 10 minutes after all of my gym workouts just to keep the sweat going while I stretch and cool down. That's never like the, hey, I'm going to do 5 10 minute sessions because I need to lose two kg. That is never the plan. </s><s>[INST] But I mean, uh, so I've done plenty of honor for weight cuts to know. I can't even imagine what you went through the second slow down. That's one way to achieve immortality is like the time slows down to like a stop and you're left alone with your thoughts. You can't do anything. Just like you said, you can't, [/INST] There's nothing worse than sitting in that kind of heat for 10, 15 minutes. Yeah. And then you walk out and you're not even sweating. Yeah, there's nothing worse than that. </s><s>[INST] And if you like, and maybe if you weigh yourself, which you probably shouldn't be doing because it'll break you. You haven't lost anything, yep. [/INST] And I was weighing myself every time because I only get breaks when I was hitting weight allotments. So if I could lose .3 in 10 minutes, I'd give myself a break. But I had to hit certain numbers because I only have the sauna for a certain amount of time. And I remember one time I went downstairs to get my key to the sauna and the japanese team had reserved it and took it from me because the guy didn't put my name on the list when I called down to get the sauna. So I lost an entire session that I had to get made up towards the later part of the day because I still have no running shoes. And then sure enough my bags show up 30 minutes after Williams. Great. </s><s>[INST] That's like the universe is kind of giving you a little wink there. I think like Because so few people do this weight cut at this high of a level. People don't often realize because people get a sense of how hard is to run 200 miles in the desert. Like they, because they go outside here in texas, you can run five miles. Oh it's hard but like the way cut is really, can you? So you just uh like how did you do it? Just fucking not refusing to [/INST] you have to make weight? You have to make weight. And just that's I am astounded when I hear like U. F. C. Players like Miss. Wait right? Like when jayden cox missed weight at the olympic trials, I was like at least his was understandable because he missed the actual weigh ins. He didn't he wasn't like not on weight but when UFC fighters like Miss. Wait, I'm like how did that happen? You clearly like gave up a long time ago. There were times where I was like, I can't do this. There have been times where I've been in a in a sauna suit wrestling with a training partner who's probably 60 kg who fought earlier that day To lose .3 </s><s>[INST] to lose point eric like are you considering your mortality in this moment? Like, aren't you thinking you're going to die because like is severe dehydration? You could damage your body. Uh Do you are you thinking about any of this or is this just uh man? Okay. Yes, [/INST] I'm on the other level to where like I've been in Belgium, right? Belgium There used to be a B level tournament And the tournament used to go on and because I was always on the heavier side like 81's fights on the second day which is the heavyweight day. Um wayans were always at like, let's say two p.m. The day before for that tournament? Well, there was a sauna at the tournament. I remember like being in the sauna and like, oh, I'm 80.9 kg Winds aren't for three hours. Fuck it, I'm gonna have lunch because I mentally understand that what I eat right now is going to fuel me for tomorrow. So I don't want to skip it. I have the time to put it into my system and still lose it, right? </s><s>[INST] It's almost like a computer program. You're running through the process. You have uh get it. But like that all relies on your ability to be um to get it back off. Yeah, I mean, but also just like go through this process was just painful. It's like those monks who meditate while sitting in a fire kind of thing or something like that. Uh Yeah, it's uh it's really interesting. Is there other people that are critical to this or is this all internal to you? Are there people that [/INST] everybody has their own way of doing it? Um Some people don't cut that much. Some people can't wait. Cut All right, they would rather have been like 83 kg, fighting 90 then, You know, be 83 kg Fighting 81. </s><s>[INST] So why did you never move up to 90? What's your sense? Is it from your deep understanding of your own judo and like the judo opponents who would face at 90 In 81 because 81 is probably the hardest, if not the second hardest division in the history of Judo compared to 73 and [/INST] 81. You know when I was a kid, like I always wanted to be like the middleweight olympic champion, like the 81 kg olympic champion. When I was in high school, I made a decision when I was trying to make weight for 73, I was like So this is I was cutting weight for 73. Like I was cutting weight at the end of my career, right? And I was like, I'm just going to bag it. I'm going to accept the fact that I may not make a junior world team, I may not make this team, but I'll grow into the division. So when I'm a senior player, like I'm ready to go and I'll naturally be stronger. There's an understanding of like a growth process. When you move up a weight class, most people can't just, Oh, I'm gonna fight 90 and I'm gonna win because I wanted 81. The style of judo is different, how you move is different, how they do things is different. There's like a learning curve that goes into it. And because the weight cut didn't really happen until I was getting ready for Rio. I wasn't about to have my last olympic games be at a different weight class that I may or may not be able to grow into. </s><s>[INST] I mean this is an awesome story of you kind of decided that this will be your life's work in terms of judo competitor is like the 81 division I'm going to. I mean, I don't know if you saw it that way, but you're talking about three olympics and it's like this Story of, I would say tragedy and triumph of just wars and 81 kg with the usual cast of characters of the, you know, top five in the world kind of thing. So you just became a scholar of that, let your body grow into it and then let your body, I'll grow it and still suffer through it to keep it in the 81 kg. He never competed at like at the highest levels of 90. [/INST] I entered one tournament at 90 kg. Um and that was because Before Rio, from 20, from the end of 2014, all the way up until Rios, every time I thought I got hurt every time there was no time where I made weight and got injured because my body weight was so high, my body fat was so low that by the time I dehydrated enough to get down there and you take the physicality of judo and throw that into the mix. Something broke. Every time it was like nature of the beast. So the plan was before Rio, we made an agreement with us a judo, that Travis, you're going to fight 90 kg, but you're not going to weigh in at 90 kg. Like, hey, there's no like, you get to be 94 kg and cut to nineties, there's like, uh, you're going to step on the scale at 84 kg, like a little bit of a weight cut, but on a 41, just so that you feel like you get into like the tournament because when I Around 2012, when I was talking with the usoc nutritionist, I actually got my weight down so much that I didn't really need to cut weight. The problem is I wasn't cutting weight, I didn't feel like I was competing. Good right there you have to go through like that mental process and I never really reworked that it was easier to just cut the weight and be ready to go. But when I entered into the 90 kg division, I was rushed to the hospital the night after because my body broke out in hives like full body. They had uh, they said it was stress induced, fascinating. So, a month before the Games, I was hospitalized in Hungary and filled with steroids to get the hives to drop and every couple of days my body when I got back home, I would end up in the hospital because my whole body would break out again. </s><s>[INST] I wonder if it's like deviating from the process that you so like perfectly crafted already [/INST] or it was stressed from my mind thinking like even though it's not top of mind, there's probably a portion of me that like the olympics is coming around and it could be my last That like my body just reacted to something chemically. So I was breaking out in hives. I actually bought like a €600 Hugo boss suit because when I was in the Netherlands training at the time, I thought I had bedbugs because I was getting bit everywhere. Then I thought there was something in the detergent at the local thing, so I threw away all more clothes, like I was paying for showers because I was trying to get the detergent off my body and buying new clothes at the airport, trying to figure it out. </s><s>[INST] Trying to figure it out and just go, yeah, accepting the situation. I mean, but the level of stress is exceptionally high here. Can we talk about the other side? People are going to love this, but you're um you have a long history of persevering through injuries. Mhm. Through insane amounts of injuries, [/INST] uh My ability to tolerate pain is probably more than most people, </s><s>[INST] but see injuries aren't just pain, right? It's like um it's also mental, like psychological, like again, like the weight cut, it can make a lot of people quit. Can you tell your history of injuries, What are the biggest injuries, the toughest injuries in your career? [/INST] Um </s><s>[INST] Starting from what you're early teens, [/INST] My early teens um actually got out of sports from 11 to like 15 years old, 16 years old because a kid shot a double leg through my kneecap And I partially tore all the ligaments in my knee, cartilage, meniscus the whole nine yards and I had to learn how to walk again. I spent two years in a leg brace, crutches, you know, hobbling around the schoolyard. That one was a challenge to come back from um I've broken most of my ribs. I won nationals with nine broken ribs. I was actually getting novocaine shots into my chest to avoid feeling the pain and then wrapping them to try to make sure I didn't pop along, um I broke my collarbone, um I have five herniated disc in my neck, I fractured my back twice, I have broken my tailbone, I tore my s I joints, I've torn my right hamstring twice, my left one once um Broken my ankles a few times. I spun it once in a 360 that had death surgery, fingers, toes, elbows, shoulders, </s><s>[INST] Because this is all of these are, first of all, you're you're tough, your talk dude man. Uh So each of those have a story behind them. So if you're talking about the collarbone or the ankles or the back the neck. Is there interesting stories here that behind these injuries, hard, training, hard competing ju jitsu judo? So ground stuff like uh sparring in the dojo or like drilling or all that kind of stuff. What if you were to sort of break it down? Your understanding of the landscape of injuries you went through? [/INST] I've never had one in jujitsu ever. I mean, I might have like torn a fingernail or like, you know, gotten key burn, but I've never been like, seriously injured. I know in ponza straight ankle locked me at copiapo odio that hurt, but I wasn't injured, like it felt sore, but like if I had to run, like I could run, </s><s>[INST] I could not understand probably exactly what the injuries came from, then you're very quickly excelled that you did. So you have achieved another level in judo. And I think that means the intensity with which you approach judo to achieve that world class level probably is the source of injuries. [/INST] Yeah, because the mentality of how I approach judo versus jiu jitsu, jiu jitsu to me is like a game that like we would play, like if you wanted to grab a basketball and like go play a game of one on one that's like jiu jitsu to me, like, I can't take the sport and in its entirety seriously, because I feel like the community of jiu jitsu doesn't take it seriously. </s><s>[INST] So just for people who don't know just to set some context. You're a black belt in jiu jitsu, but more importantly, you've beaten a lot of world class digits of people, you've done very well at the highest levels of competition? [/INST] Yeah, I wouldn't necessarily say I've beaten them as much as I've trained with them and they understand whoever it is that through training with me that like, I'm not just a judo guy, Like I know how to do jujitsu, right? And if any one of them were to come to me and like say, hey, you know, I want to feel what it feels like to do judo with me. They would quickly understand that like, the way I approach one is very different than the way I approached the other. Like, we probably wouldn't be friends if they did judo with me versus if they did you get to with </s><s>[INST] me. I'm curious asking for a friend because mostly because I'll do a little judo with you today, so you clearly, because you're a great instructor and teacher, you have a mode where you can demonstrate a technique. Do you know how to like spar where you're going? Like 50%. [/INST] It's hard to put like a percentage to it because I've never, in all of my jiu jitsu ever gone 100% in jiu jitsu. Yeah. Like I had a conversation with salo one time where we were talking about like jiu jitsu and training and I was like, well if I got his arm, I would just break it and he was like, but what if he talked, I go, that's not my responsibility. If he taps and the ref doesn't say anything. You just break it. Just keep going. Uh you know, but the tap means it's over. And I said no, the ref tells me when it's over. I go, I never give you the opportunity to tap because if you have the opportunity to tap, that means you have the opportunity to think about how to get out, make a decision that you can't then tap. I clearly operated too slowly. So there's a it's either broken or I don't have it. </s><s>[INST] You're in a terrifying person go against in judo. Like the on the ground, like everything you did. That's that's amazing. Um That's really amazing. That's what made you really fun person to watch because you really went to war with these people. Yeah. So you know what it's like to go 100% in judo? [/INST] I do because I know what it's like to train with somebody under the mentality of I'm gonna do everything I want to do. You're going to do nothing you want to do and you're going to accept that. </s><s>[INST] Do you have a train in judo? Where where you let people get stuff of course [/INST] all the time </s><s>[INST] now or like [/INST] always </s><s>[INST] even when you're sort of building up the four years building up to the olympics, like they're smaller guys that are throwing you in the gym and that kind of stuff. No, I never said that, okay, [/INST] that never came out of my mouth. I said I let people do stuff. I never said smaller people throw </s><s>[INST] me. You mean you let him get a grip but then you position yourself in such a way that it's hopeless. Like what [/INST] The # one Skill set that judo is gonna teach you is the ability to give people false hope. Mhm </s><s>[INST] Right, because I can let you looking forward to the video, we're going to see [/INST] like I can let you take a grip, I can let you think that there's opportunity. But what you don't understand is by the position, angle that I'm in, it's actually false hope. Like as long as you don't know that it is then now I'm free to operate and do what I want </s><s>[INST] to see. I competed in judo against black belts where I would go in and it looks like I could, should be able to throw them and then you just hit a wall. And then I also saw you destroy those black belts. So there's levels to this. Yeah, it's the cliche thing of theirs black belts and there's black belts. You're unique in this. There may be a couple other uh judoka in America but you're really like unique and then get to see people that really I felt like Or 10 x better than me. It just feels like that sometimes I've learned that madness and it's good to be true, they might only be just a little better. But I saw you destroy them. And it was like holy shit, [/INST] there's a thing in judo right? Where you know, imagine like you as like just an adult, right? Um and I hope people can like conceptualize this when they hear this, but imagine like you're a full grown adult, even male female doesn't matter. But there's a little kid in front of you like call him five or 6 years old and he's acting out like do you think you have the physical capability of with one hand grabbing that person or that kid and making sure that they freeze like they feel like they're nervous and like they can't do anything when you fight a good judo player when they grab you. That's what it feels like as an adult, when people even, I felt that from like certain players in Japan when they get a grip, I'm like I've now lost the function of this one. </s><s>[INST] Yeah, that's a really good way to put it. I think I could potentially beat some of the people of uh went against. But certain groups they took it made me feel powerless. Yeah. I was like, I didn't know this was possible. That kind of power [/INST] was possible and you don't even know where it originates from because you're like how does one person's hand do this where I can't use my whole arm or like I can't pick up my right foot because he's holding onto my right sleeve. </s><s>[INST] Yeah, it was kind of um on a basic animalistic sense, kind of terrifying. It's I mean you don't wanna um part of this is like ego, but you realize that there is a food chain and you're not at the top of it. That's part of the humbling process. I think of martial arts, it's like, I think everybody Yeah, like a lot of people, I think they're much higher in the food chain than they really are. And then when you realize this was a really healthy process for people, they're not even competing in the olympics to practice martial arts because you realize, okay that like putting yourself more accurately in the food chain is really good way to sort of place yourself in the rest of the world. It humbles you to the reality, the harshness of the world. [/INST] It's kind of like when people look at like survival in the wilderness, it's like, it's not that hard. No, you'd probably die in a couple of days. Same thing with like judo and martial arts, like yeah, it's really not that hard, but you don't know what to do yet. And so when you find out that first time that you don't know what to do, it's devastating to a lot of people, but those that like stick through it and like start to learn it's a very empower fel like feeling that now, like you can take care of yourself </s><s>[INST] and I think when I talk to you a few times before you talked about that there's like, like the top three, the top five in the world, I don't know where you put them, but they're there another, like, level of Yeah, and the fact that you're I mean, it's so exciting to me, probably because I just felt all the levels here and I have seen you and others at that height destroy those. I've seen the exponential levels to this game, it's incredible that you're I didn't quit, didn't doubt yourself and just persevered through three olympics to get to that highest, always fighting at that, like, very highest of levels, but just like, you know, from the top 10 to the top five, like, really breaking in through that, I don't know um what would you say it took to get to that highest of levels? Like, if you, when you look back to all the weight cuts, just the insane amount of injuries, [/INST] believe it or not, I didn't really think I was there until 2013, I thought I was recognized as one of the best because I was able to fight for a Pittsburgh, which was the professional bundesliga team for Germany, which is one of the top clubs in all of europe, um when they asked me to, I felt like, europe had, like, accepted me as like, oh, I'm a top level judo player, but I don't necessarily think that when I signed on to compete for them, that the division or the world of judo saw me as a top level judo player, right? There's, there's a, a mental shift that happens along that point and for me My mental shift really came into play in December of 2015 before rio. That was like when I lost in Japan, that's when I realized like the world respects my abilities and they compete against them. They don't compete against me as a person, they compete against the idea or the, the persona that I've been able to establish over the years of competing in the division, </s><s>[INST] wow! So you're the, they probably have a nickname for you, you're the system of ideas and thought that they study, [/INST] but they're studying me as a conceptual whole, not me as the human, </s><s>[INST] Is your style relatively unique in the 81 kg [/INST] division, It was relatively unique for Kayla I and jimmy Up until 2016. Now, since 2016, you can see a lot of what we used to do throughout most of Europe and even Asia, like you're starting to see some of those techniques that you didn't see before starting to get implemented because when I was When I was gearing up for 2015, I had such a slew of injuries that entire calendar year that I never should have made it to Rio, I should have called it quits at the end of 2015 because I suffered that major concussion in february, I stepped on a mat in May for the first time, I lost five straight tournaments, I left the national team, went to Japan one Pan am Games, got a bacterial infection at the world's almost had my leg cut off, tore my S. I. Joint later on that year and then took fifth in Japan. And when you look at like the calendar year as a whole, like the world should have treated me like I was washed up. Like this guy hasn't been training, he hasn't been doing anything, but I took fifth in Japan. Now how does a guy that hasn't trained all year? Take 5th at one of the hardest tournaments in the world on two weeks of training? Because they were fighting the guy I used to be not the guy I was at the tournament, which means they were competing under the idea of like, what is he really capable of not? What have I brought to the table today? Mm </s><s>[INST] And that just gave you the confidence [/INST] and that told me that like, well if I can take fifth and I'm this baggage, you know right now, wait until I'm healthy and I'm back in shape, then they're not gonna know what hit them. </s><s>[INST] One of the essential components of being the number one in the world are up in that places, that confidence to self belief [/INST] and the rest of the world believing it, you can have all the confidence in the world. But if the rest of the room doesn't buy it, it's nothing </s><s>[INST] that's funny. It's like there's certain people right with Tyson, [/INST] uh, my guys all understand he could not train and they're still scared. Yeah, right? Like he doesn't have to work out that hard anymore. </s><s>[INST] There's several judo, you know, this way better. But from a spectator perspective, like Ilias Iliadis is like that. He's one of them. It's like [/INST] he's portrayed over the years. I </s><s>[INST] was so scared of that guy. It's interesting. People were scared of you too. [/INST] People just gave a certain level of respect to my skill set and whether I had a bad way cut, it didn't have a bad way cut or not trained for the last three months, which never happened. I'm just saying they were going to fight the persona And it's an important distinction when you're looking at the top five because everybody coming up their training against the persona, not who you are. Even I did that at a younger age. That's why I would always go to people's hometowns because like, I don't, I don't care about the persona. I want to know what you do day in and day out when I couldn't be the Russian, I told jimmy sent me to Russia, I need to, I need to understand and see it with my own eyes, what they do out perform so that I can believe that I can beat them. </s><s>[INST] You can ask. And this is a small tangent. Uh Dagestan has produced some incredible wrestlers. I don't know what the story with judo is, where the source of source of greatness in Russia is for judo. But what do you make of Dagestan? Why why what is it in the culture of their or Russia broadly that produces greatness. [/INST] Specifically in the combat sports? </s><s>[INST] I don't know. Yeah, specifically in the combat sports, sorry, But I don't know if you want to draw a distinction between wrestling and judo. Almost curious. Do you understand the difference? Is there in the culture [/INST] are still a combat sport to them? They're still in that same like realm of they're taking young kids and that that's what they do. </s><s>[INST] So it could be speaks very highly of judo. Yeah, like it's funny, could be Vladimir Putin, [/INST] people don't get it, but like judo is like one of the premier sports in the world, but we don't understand </s><s>[INST] it. It's not just popularity, so definitely popularity, but also like this respect. And there's a certain thing which is why I really value judo internationally. You don't get this in the United States, but internationally there's an understanding like later in life when you're a scientist meeting a businessman when you both have done judo, there's this like nod of respect. It's so interesting. Uh there's very few sports like that. You know, basketball doesn't have. I mean, I don't know almost any sport like that and it's [/INST] fascinating wrestling has that in the US it is the U. S. Only the rest of the world doesn't </s><s>[INST] do that. There's a few like you could see that in like Iran or something like that with respect. Rustling in that kind of way. Yeah it's um [/INST] Put Judo on like a global scale is probably that only one due to its like physicality and the hardships that you have to go through to reach that upper level. </s><s>[INST] So why do you think Dagestan, why do you think could be as as good as he is? Is there is this just the raw genetics of the human or is there something about the system, [/INST] the system, it all has to do with the system. </s><s>[INST] So they they grow up around fighting in all forms, yep. Um There are also, I mean their technique is exceptionally good [/INST] because they grow up in </s><s>[INST] it. They grow up [/INST] they don't they don't understand anything else </s><s>[INST] so you don't have to, it's almost like you were the way cutting, it's not like a big dramatic thing for them to fight. It's like this is just part of life. [/INST] Yes. And when you're I don't want to say bread into it but when you've done it For you know I want to say like 90% of your life by the time. Like could be probably has right from the time he could crawl he's probably been grappling in some fashion. Their of right. Um You know when you as grapplers like you can look at a wrestler having never seen this person before and go you wrestled. Yeah. Why is that? It's because he's probably wrestled since he was like six. So the way he carries himself, the way his body is built, the way he grew into it was framed around wrestling. Right? So the people in that culture are framed around fighting and grappling. </s><s>[INST] You're right, it's like first of all philosophically psychologically but also just like the way you move your body. That means like when you're young the people you admire move their body in a certain kind of way [/INST] and then genetically it just as they keep doing that they're just going to get better and better every generation. Yeah it's just going to keep improving because they just keep building into that system of turning them out. </s><s>[INST] And part of it there's like cultural stuff where, I mean it's such an interesting approach to wrestling. I really want to travel to Dagestan and just talk to them because it happened to be able to speak Russian because because there's um less value for this kind of materialistic success that I think sometimes can get in the way of greatness. It seems like it makes coaching more difficult. It makes like following orders as an athlete more difficult. I [/INST] don't struggle with that and usa judo </s><s>[INST] because you want more money but then more money if not applied correctly can corrupt the system somehow. It can split people up. [/INST] It's just the same thing with the prestige around certain metals over others because athletes start chasing fame instead of development. Yeah. </s><s>[INST] Yeah, that's I mean uh it's your brothers are famous for this, like ignoring ignoring fame, ignoring all of this. Like focus on the art itself, not even not. So it's not even the medals. Exactly. You're saying just the purity of like when you're in it and let everybody else figure out their stupid medals and money and all that because it comes, it comes [/INST] exactly as a result. </s><s>[INST] Exactly like it's not that you don't appreciate it, but you know that it comes if you focus on the art, [/INST] there's a distinction when you're talking about your athletic career or really any endeavor, right? The problem with goal setting is nobody teaches the athletes or the people how to transition from the goal to reality, right? So When you look at my career as a whole, like when I was getting ready for 2008, I actually forgot to train for it. I was so happy at such a young age that I became an Olympian that that in and of itself was a goal that I thought had to be admired, had to be celebrated that you know, the games are right around the corner. I I didn't really come down off that high, </s><s>[INST] you're the local optimum of, of just winning the trials. That was [/INST] a big thing. </s><s>[INST] It's a huge thing. But then you're just focusing on the accomplishment. Not the [/INST] correct, but at some point, right. When I, when I went into London, I actually went into London going with, I'm going to prove I'm the best in the world because I believe I'm the best in the world and I believe it from like the bottom of my soul that I'm winning this. And then you're almost like trying to tell the universe like I'm accomplishing this thing because it's a goal. But when I went into RIO, I just accepted the fact that I was winning. It's not a goal like this is happening. </s><s>[INST] You visualize [/INST] it, but I felt it. You felt it right? Like this is no longer a goal anymore. Mm Like I anticipate like this is happening. I can see this coming down the path because I'm anticipating that the games is happening and I'm gonna win. It's not a goal to anticipation and there's a distinct distinction there between the two. </s><s>[INST] Okay, so for people who are just watching the video of this, there should be an overlay of uh, Young Travis. This is uh, you still have to make 81. This is still a tough cut here. [/INST] No, this one was relatively easy. This is going all the way back to 2008. So this is the summer before the games. This probably happened in june I would say. </s><s>[INST] So this is the olympic trials. So in the United States you have to mean similar to like wrestling, you have to win the trials to qualify for that particular division to represent the United States. So this is you said june before in august olympics. Yeah. So here I just wanted to show this match because uh, what was there? There's another one, I think you do a pin, you just sign this groundwork and the other one. But in this one [/INST] fighting a teammate, </s><s>[INST] finding a teammate, [/INST] former teammate, Oh, there's an old school double leg, I forgot about that. And it's weird to see. </s><s>[INST] 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] So then this you're you're celebrating here is a huge sort of uh once a big accomplishments, big relief to qualify for the olympics. And then you go into the olympics and this is where I first saw judo and I kind of thought of them as the same as judo and jiu jitsu. Um and I was really impressed by your performance in the olympics. The footage nowhere to be found these days. But um at that time I think you could still, you could watch it live on NBC olympics or somewhere like that. And I remember watching several of your matches, one of them was the match against the ole Bischof the german and I remember being, it would be nice if you can talk to that match because I don't remember it all I remember is being frustrated. Yeah, bye him not letting you play judo. Yeah. So um obviously you faced him again four years later and there's a lot of frustration there as well, but I remember being extra frustrated in 2008. What was that match like? So he he might have been number one in the world at the time or up [/INST] There. He was up there for sure. Especially going into 2008. </s><s>[INST] He was really high up there. Yeah. Did he win gold at that olympics? [/INST] Yes. Yeah, because he's silver in London. It was the same Olympic final both in 2008 and London. </s><s>[INST] Okay, so you're facing him there? Were you intimidated? What was the strategy? Can you talk to that match? Because it kind of sets the stage for the rematch in 2012? [/INST] Yeah, he was somebody that I had trained with in the past and for some reason when it comes to him and I when we train together, it's more of a physical altercation than a judo training session. You know, like it's just like the coaches have had to break us up a few times, like </s><s>[INST] you guys get almost like angry too [/INST] a little bit, it always goes, you know, farther than it should for we're friends like we say hello to each other but for some reason when we train together there's something about like him and me that just oil and water. I don't know what it is. </s><s>[INST] It could be also the gripping because he's a great gripping strategist. Yeah. Does he frustrate you with certain kinds of grips and then you get pissed off and you frustrate him [/INST] and then he gets pissed off and then before, you know, if somebody's kick somebody or punch somebody in the mouth or done something. </s><s>[INST] Yeah. One of the only evidence is we have online if you're fighting him is you your foot in his groin area is the only thing we have from that olympics [/INST] From 2000 </s><s>[INST] eight from 2000 [/INST] Yeah, and to answer everybody's questions yes, it was deliberate. </s><s>[INST] Now you can say this. Uh but yeah, I remember there being a lot of frustration. You go, you're actually going for a lot of stuff like sacrifice does, I mean maybe you're not going for the highest scoring Ippon, but you were just trying to shake things up if I remember correctly. [/INST] Yeah. Because when he I was so young then that and he was, you know, in his prime really at that time, right? He was must have been 24, 25, 26, you know, world medalist European champion at the time and when he would grab me, I would, I had that sense of feeling stock like I was strong enough if I used all my strength to not let him do anything, but then you can't be offensive when you're using all your strength to hold on to the situation. So I was getting really aggravated because I couldn't, I couldn't generate any offense with every time I felt like I gained an advantage in the gripping scenario, he would take some obscure grip somewhere that was like, well now I've got to go address this thing, give up what I gained and I have to go back and if you were to think about watching the match now, it probably looked like a lot of flailing because we're just trying to generate enough to not get a penalty, but also not enough to where he could counter it. </s><s>[INST] Did you think you could beat them? Like when you're walking into the match [/INST] until I gripped him for the first time? Like because I had trained with him before, he felt stronger and more in shape than I've ever felt him that olympics at that olympics, which begs a whole another question. </s><s>[INST] But [/INST] I remember, I remember when I, when he grabbed me for that first time, I went, this is different and there was a sense of panic at the time because I was like, holy crap, where did this come from? This is not the guy that I've trained with, that I expected because it was a definite like level change in like his ability, strength, speed and stamina. </s><s>[INST] Like looking back at that, can you explain that? Is it just, you being more uh less confident because of the olympics? It was, is there some kind of routine that he followed? Like really level up in intensity for this particular event, [/INST] I've been told that he only gets to like his prime for like really big events. Like he doesn't train like year around. Like I would train, but when it comes to like the games, he doesn't do social media, he doesn't work, he lives breeze eats his training for the games, which could, you know, institute that level. </s><s>[INST] What about you? Is there uh like dan gable famously said like the one loss he had in college, he was doing a lot of media and stuff back back then. There was no social media. That was a huge mistake for him. Do you do social media? Do you do like at that at this point at that time was like a, well, I don't know what, [/INST] I didn't even have a facebook page. Uh my space, nothing at this point. I got my first facebook page from the U. S. O. C. In 2012 when I went through the media thing. The lady was like, you have to happen. I go, I don't want it. I don't like people, I want to deal with the people. Well, what am I supposed to do? </s><s>[INST] You know, like the social part of the social [/INST] media? </s><s>[INST] Okay. Um, I have to bring this up because uh, and then you went on to face Tiago Camilo, you lost that match, but he went on to win bronze. That's also an interesting one, but we can skip ahead. I just remember being really impressed both by your groundwork. [/INST] Um That was a match. I should have one. Yeah, I should have one that I was, if you don't know judo, you would visually watch that and be like I'm winning, but he was technically winning on the scoreboard. So it is what it is. But the point that he got that solidified his win. Yeah. Yes. It was a point back in those days, so I can't say anything, but like my shoulder nicked the ground so it's like, I don't know </s><s>[INST] a lot of the stories of your olympic career is like from a fan perspective, it seems like you should have one or you very close to could've won. Yes. And there was a lot of frustration, you and your game being like shut down in certain ways. And but like the thing that immediately grabbed me in 2000 and eight was how much something about the way you approach judo, how much you wanted to win [/INST] because I was young that I was when I was at this at this time in my career, I was out to like when like there was no, like I'm gonna grab you, I'm gonna throw you and if not you're going to go through a battle, you're gonna make sure you earned it. </s><s>[INST] It so happened that you competing in 2008. I was uh I became a fan of yours at that moment and since then I kind of knew about judo. My university had a judo club and I kind of knew about jujitsu from mixed martial arts and obviously I wrestled for many years before and I love wrestling, but there's something about you competing that made me, well there's another way to say, but like change the direction of my life because it forced me to say, you know what I'm gonna start judo and ju just to And first of all, for that, I'm really grateful. But it's fascinating to think because this kid was 22 years old, I'm sure I'm not the only one that you've influenced, like, you've changed the direction of my life and there could be a huge number of others like that. I mean, that's the power of use individual on the olympic stage. You ever think about the pressure of that? Did you did you think as a 22 year old, there's a bunch of people like, I know I'm not the only one who changed. I just happened to have, like, a microphone recently. You know what I mean? Like, is that it's fascinating to think about, right? Like, you perhaps you didn't think about this. It's just it's just the judo match, but you're like, you influenced hundreds of thousands of people if not millions, is that interesting? It's [/INST] it's not something that really hit me until um 2012 when I lost because that's when, like, I would say, like, the world felt bad for me at that point, and that's when you knew that like, people were watching and people were inspired by the loss because of how much went into that match. Yeah, Because, you know, the 99% of us who watched it thought I won Except for the 1% of the people who were considered judges at that day in the event. </s><s>[INST] So, but I mean that's the winner lose. That, that was a really inspiring match. [/INST] And that's when, that's when it gained that. Like, because I don't, I don't watch something and really get inspired by like the person and the act, it's like a, it's an a cumulative thing. But for a lot of people like when they watch how much goes into it and then when I broke down on the match, like the amount of suffering that happens when you lose a match like that and then, you know, really coming back and winning and Rio, there's a trend of people who were inspired that knew about London and then when they found out I want in RIO, that's when people like in droves felt like they could overcome their own personal obstacles to still achieve something because they've witnessed somebody who's fallen and gotten back up. Yeah. But it's not something that do you think about like on the day, it's when you look back and you go, oh cause and effect, </s><s>[INST] I wonder if you can comment on that I'm trying to realized and live up to the fact that there's like young people come up to me and I'm starting to realize like certain words I say we'll have a long lasting impact on them [/INST] because you say it is like you don't even doesn't just, yeah, the, when </s><s>[INST] Some of them might come back 30 years later and a word I said was the reason they quit a thing and started the new thing that led them to become their true selves like to find success. All that kind of stuff. Like [/INST] on the flip side though, some people based on the actions that we do today, even with this cast will alter the course of their lives forever. I had a guy one time was it after London? It must have been after London. He actually found me on instagram brought me what seemed to be like a dissertation on instagram about how, he I disrespected him 14 years earlier because I didn't step on a podium to take a picture after winning a tournament where he bronzed. Yeah. And I'm thinking to myself, like at the time, like having dinner with my family because I had to leave the next morning was more important to me as a person, not thinking about who you potentially will become and the actions of whatever you do today. If you do become quote unquote famous or somebody in a spotlight that that could come back to bite you </s><s>[INST] to me. I don't know about you. That that's, that's super motivating like not to be a lesser version of myself ever. Yeah. Just be on top of your game. Whatever that game is. Be on top of your game when you're interacting with people and when you're just in your own private life, I'm trying to make sure that I'm the exactly same person privately as I am publicly and like making sure I'm on point. I see like just hanging out with joe Rogan a lot. I see how he's first of all the exact same person and second he like walks around and there's like a huge number of fans and you'll just take pictures and like very cool and it's very cognizant of like certain words he says, especially young people, like they're going to take that and that's gonna be a memory for them for a couple of years. That might be influential for the rest of their life. So I don't know, that's a cool responsibility. Uh, not to fuck it up, but, but anyway, I I bring all that up to just say thank you. Uh so even if you like, we're frustrated that you didn't win a medal, at least at least you influence one silly Russian kid to get into the martial arts and what happens when you get into martial arts, it alters the direction you like mine for, for the better. Okay, so let's go to uh London 2012 Olympics, one of the most dramatic judo battles of all time rematch. So you've reached the semi finals once again to face the german ole Bischof, do you mind if we step through that match a little bit [/INST] following the by all means? Yeah, I've only ever watched the entire thing one time just because fucking </s><s>[INST] So for context for the listener, um Travis first of all, you don't like losing. I think that's fair to say, you know, [/INST] the the hard part with this matches because I went into this olympics thinking I'm not fucking with the olympics, I'm the best in the world. I never, in my right mind thought, oh I'm going to win a medal like that. Never that never crossed my mind. So it's like I would have rather him just fucking beat me. Yeah, because then I lost. </s><s>[INST] So here The referees as as many people thought robbed you of a victory, but it was also really close battle again with many of the elements of frustration as 2008 in terms of strategically and gripping wise and it was just a fascinating battle that went to overtime. Uh can you set the context? So what did the bracket look like? Who are the players here? Um who did you beat leading up to this match? Like as you walk onto the mat? What happened the day before? The hours before as you're standing there? But how bad is it when two people are standing like this? Yeah, fucking [/INST] that fucking guy man. Um But this this bracket um Was really interesting if you look at like the backstory of 81 kg, like leading up to the Olympics right? Because at this point in time, you know, I was inside the top 10 at all times, you know, 8754, you know, six is, I fell out of their sometimes due to injuries, but I always climb back in. Um there was another guy um from Azerbaijan, That was the Olympic champion at 73 kg in 2008. And the entire division got rocked by match one because his first match was with antoine, valois, fortier of Canada and everybody who saw the draw come out was like the yards of johnny's gonna win it. He's the former Olympic champion. He's pretty much one of most of the major events, including at 90 kg because he just had smooth judo. Mhm. And You know, match one rolls around, match two rolls around, antoine's in the shoot and he's looking around and he's like the Azerbaijani is not here. Well, where is he? No joke. He runs into the venue a match before throws his G on and runs onto the olympic platform wow, loses the Canadian in like a three minute golden score battle. </s><s>[INST] So do you think he warmed up [/INST] didn't he ran he literally ran into the venue through his G on and ran out. Did know judo and there you see antoine losing in the quarters. </s><s>[INST] So how good was that one [/INST] at this point in time. This is I believe his first international medal was the olympic games, so I don't think he'd ever medaled in paris. Um he went into this bracket, unranked beating the ranked guy first round because he I don't know if he missed the bus. I don't know if he was off his cycle and planned on losing because he didn't want to test positive. I don't know, there's a lot of like questionable things out there that could have potentially caused him to, You know, run onto the Olympic platform for match one. But you know, it it catapulted antoine into like a belief that, like, I beat the seated guy, I'm I'm ready and that was like a turning point in the Canadians career just as a whole, right? That's that everybody has a defining moment. Like mine was when I beat bischoff uh in Dusseldorf at the Grand prix for Germany After 2008. Mhm Right, I beat the olympic champion in on his home soil to go win the entire tournament. So we all have like those moments, it's just when it happens at the games, it throws the bracket like into a tailspin because typically, you know, like who's going to be, who, where it's going to happen and when you look at my quarterfinal against the Brazilian, what most people don't know is I was I was so thankful I had that match. Most people would never, in a million years be like, I want to fight the world number one at the olympic games. That's what I want to do. I want to be the eighth seed fighting the world number one because I'm gonna win. I was pissed off at him. I was so angry because we we were at the Pan Am's I think the year before and there was a team tournament. I wanted to fight him. I lost the quarters to a Cuban. I think in like the first gripping a change, he threw me with a drop sail out of nowhere. I was pissed. So I wanted my hands on the Brazilian and the team match. Well the Brazilian teams warming up. So I walk up to him, no joke. I walked up to him and I go you're fighting And he goes, not today. And I went, are you fucking kidding me? I warmed up. I taped up. You're the only fucking guy I want to fight and you're gonna fucking sit in the stands and read a goddamn book. I was so angry. I carried that anger because I never fought him until this day. I was fucking pissed. I was ready to beat </s><s>[INST] him. That's right. I remember I forgot he was the world number one. How do you? Um because I remember like being really excited at that match, How did you beat him? [/INST] I threw him with two hands on the same side collar, like dropped sale I cross script. I yanked him behind me and I throw him, </s><s>[INST] SaiPan [/INST] was R. E. And then the match ended 30 seconds later. Yeah, I was pumped. </s><s>[INST] I was, I thought, I think okay, if I'm remembering correctly, I thought, okay, this guy might actually win gold. That's that's what made for me as a spectator remembering now the next match that much more like painful. [/INST] And then the fans of judo that really followed the sport, the stats. When you look at the games and my draws, I had the worst possible draws you ever could have imagined at both London and Rio. I thought the world number one to get to the final or into the semis or past the semis and everybody I fought in the draw either beat me the last time we fought or I had never fought before. So I always held a loss going onto the mat at the olympic games. </s><s>[INST] How do you feel about that by the way? Like what what were your feelings about facing the Brazilian [/INST] first? I was so excited. This wall that was matched three in London. I fought the Slovenian guy first round who beat me um, where he beat me was that the world might have been the world and then churches villi I fought in the second round who threw me for was Ari in Japan and then Leandro who I don't think I ever fought who was world number one that avoided fighting me at </s><s>[INST] the team tournament. But I mean every single olympics you've fought it really stepped up. [/INST] The only tournament I've ever prepped for </s><s>[INST] mentally and physically and just the whole thing. Yeah, [/INST] we never trained through this tournament, like we did for the others or I would go into it injured. </s><s>[INST] All right, well let's talk about your standing there next to that uh to the german he looks he looked always smaller than you, but you said like strong. Yeah. Um So what are you feeling? No jimmy Pedro behind you? [/INST] I was fucking ready to take a set off. </s><s>[INST] Did you have an idea of what you're gonna do? Did you try You're thinking of winning by Ippon what you're thinking like going for big throws or take them in deep waters, grip them. What were you thinking? [/INST] We were about to have a battle and I wasn't gonna throw him until he broke mentally. Okay, that was there was no like, oh, this is gonna be a clean throw. That was never that was never the thought process. </s><s>[INST] So, so here, you know, there's going to be a lot of gripping so we're seeing a shit on a gripping [/INST] and right here he throws it bang, close fisted, </s><s>[INST] you got a lot of adrenaline, you seem calm, I'm pissed, you're pissed. Like you don't look like you just look like [/INST] I'm looking at the ref like because he keeps telling me to get up, I'm like, I've blood running down my face. I go, okay </s><s>[INST] here, Blood [/INST] c and he's like, oh yeah, go fix </s><s>[INST] it and that's on your eyebrow somewhere. [/INST] Yeah. He split it just underneath it. </s><s>[INST] So you split your eyebrow and so in judo, they don't they're allergic to blood. Probably for a good reason, but they so now you have to try to figure out how to uh tape that up. Yeah. Which already sets up one of the most bad ass looks in judo history. [/INST] 1st 15 seconds. Busted my eye open. </s><s>[INST] Was that getting in the way of your eyesight at all or no? No. Mhm. Damn. He looks good at gripping. How difficult is it to get a grip on that [/INST] guy? Very like, I'm struggling just to get my hand in the collar and he wasn't even blocking it. </s><s>[INST] Is he being cagey? Remember like is he interested in [/INST] offense, nope, he's a very cagey, you know, methodical player. Like he he never opens himself up. </s><s>[INST] There you go, you grab the leg as part of a combination and people have told me that he's actually very good at throwing people. He just doesn't So but he just doesn't show it at these [/INST] notes because he he doesn't care how he wins, he cares that he wins. Yeah. Which makes them very difficult to beat because he knows when you strategize to do that, where you look at the rule set and you develop a plan to to get through the matches, then you've really got to figure out a way to get that person off that game plan. You know whether you get ahead by a penalty or something right there, like Uh huh. He wouldn't give me the sleeve. So I grabbed all of his fingers. </s><s>[INST] Oh nice. In which I opened like, like this way [/INST] or I grabbed them the other way and I started lifting them. I talked nice like playing mercy </s><s>[INST] like this. Yeah, [/INST] this is great because he wouldn't give me the sleeve and I needed an attack and I'm like, ok, I can't hold on to this forever because that judge is going to see it. So let me just do a quick throw here while I'm using the fingers and the first </s><s>[INST] holding on. Uh and then I just Yeah, [/INST] and then he goes to get up and I go to get on top and right here. </s><s>[INST] Nice. That elbow, you get [/INST] him? You got him. Yeah, it looks like I elbow him. </s><s>[INST] Do you do it? Kind of? [/INST] No, I didn't. I at the time I never knew this happened until after I watched this like three or four years later. I didn't even know I didn't even feel it. </s><s>[INST] Look at that. So he's legitimately angry [/INST] here. Yeah, he's angry. And of course you can't you can't move. Why would you get </s><s>[INST] this? Look at this this moment, right there. Is this gold. If you're not watching us on video, you're missing out. You never get this in judo. [/INST] I don't know if that's ever happened. </s><s>[INST] That little face off. Especially [/INST] on a stage like this the reference and then he brings us in to like talk to us and he's like, hey, we're good, right? Like you guys aren't about to do what I think you're about to do. Uh you put up like hey shake hands again because the first time we did it, that wasn't good enough. You got to do it again. Uh huh. The heartbreaking part about this and why the I. J. F. Switched it to an unlimited golden score because we fought five minutes um through the entire normal part of the match and then we did the entire overtime period of three minutes. Now. One penalty was given no gripping infraction, zero goals attacks like no stalling. </s><s>[INST] Great. There was nobody was really backing up. I mean he was, you know, so what was jimmy telling you here? What was he? Was he talking to you at all? [/INST] He's not allowed to talk during medical things and my nose is now broken. </s><s>[INST] But he's also the nose is broken from what? [/INST] Um I caught an elbow from him, glad his face is clean. That's fun. And right here, like I was pissed. I was so angry at the medic because he's fumbling around and I'm like, my whole plan is to break the german mentally. You gotta hurry up with the tape man. Like he's supposed to be tired. Like he's not supposed to be resting </s><s>[INST] and is jimmy yelling here. You can't, no, not here, not here, but during the match [/INST] and you can see I just take it from him and I'm like, give it to me, I'm going to do it myself, Get out of here. </s><s>[INST] How scared is the medic? It's [/INST] like this guy can't even tear the tape, how nervous he is. We made fun of him for this so much throughout the years. Still do to this day. Alright, here we go. Well, you're great. You can't really see, don't care. </s><s>[INST] Was there some outcome in your mind that you could possibly beat them on the ground with the submission or pin? You knew you're gonna have to throw him? [/INST] I knew I was going to have to if I was gonna throw him or on bar him or pin him, whatever the case may be, it was gonna be his mental, like, I'm just tired of this, right? He's two kg of a player, He's too experienced, you know, he has to mentally make that choice to give that inch and then you just have to be ready to take it. So I was just waiting for it. </s><s>[INST] And so now this is four minutes in, one minute left. That oh um is that in your game plan to potentials? Like, assume engaged? Like the sacrifice throws them [/INST] because the whole point of that, that technique and the sacrifice throws wasn't because I thought I was going to throw him, but it disrupts the pattern enough to like get him to make a potential mistake. Like see he should have gotten Machito there, hands in the face. But again, that's just part of judo. He poked me in the eye bo </s><s>[INST] this is a rough match, it does he act at all or no? Like, was he acting frustrated or anything like that was all like, he's like acting for the ref, you know what I mean? Like Oh that all that kind of stuff. You're just going in hard not stop like angry aggressive feeling cardio here at all. Like, I don't [/INST] I don't get tired during this and then just always pressing </s><s>[INST] for time runs out. [/INST] Now we're into golden score 12:38 later. Yeah. You think about every judo exchange right? Every time we grip up, every time we attack sometimes it can take longer to get back to the line in the entire exchange. </s><s>[INST] So the more aggression, the more exchanges you have, the longer the time stretches. Then hear the six seconds left in Golden Score your tape. There's uh there's no like yellow and red. Yeah. With sweat and blood literally and time is out now. What are you thinking here? Do you think you won the match? [/INST] I I thought I won the match a minute ago. I remember thinking to myself, like, if this goes to the flags, I want no doubt in my mind because I felt like the whole time, like I was going to him. Yeah, right? He was never coming at me. </s><s>[INST] Yeah, that's the way it felt and like, like that's the way it felt, body language wise is the intensity, how fast you're moving towards him, You're constantly going for throws. [/INST] Now if you want to rewind that we can talk about the whole because it's a part of this </s><s>[INST] clip. So wait, wait a minute. Uh they all went blue. They all did so in judo, there's three referees to on the side, one in the center and they all vote [/INST] on that. Let's pause it right there Now the way this is supposed to work, they raised their flags, They do like a 1, 2 count. And then on three they all raise it together now as a little pretext to this entire match up. Until this point, Not one match at the Olympic Games has ever been a split decision Meaning out of three people, not one of them voted against the other group members. So they were all unified blue or all unified white. </s><s>[INST] Yeah. Right. Which is um statistically difficult to imagine. Yes. It's almost like they had a referee meeting and said um it's better for the olympics [/INST] to never have a split. Yeah. Okay, so the question becomes, if you click that frame by frame, right? So right now we have all the refs with their flags out and then click that. </s><s>[INST] So the middle [/INST] middle guy is he is all the way up the other side. Judges haven't moved. We now have one side ralf all the way up then we have a third side ref all the way up. </s><s>[INST] Yeah, so there's a time point when the middle guy has the flag all the way up. If [/INST] Not 80, 90% of the way there. Yeah, then the other one does. And then the third one goes, uh so now the question becomes who really like to the outside refs really have an opinion or were they told to wait for the center one to start and then lift whatever flagged the center ref picked? </s><s>[INST] Yeah, this is very unfortunate. It's very honestly it's very possible that they had this meeting. Um This this is the problem with the the olympics, they sometimes it's also the problem in the soviet union with communism, you think the committee knows what's good for the people and so on. So they decide universally as opposed to letting the magic of the olympics be what it is. But nevertheless in this case the center ref decided blue. Like what do you think? Do you think it's just a shitty call or like [/INST] he has the right to pick. But the problem is is The other two I don't think did. </s><s>[INST] Yeah. [/INST] So when you do this frame by frame again right? Like I can see from my own perspective two of the refs and I see them both blue. Right? So when you fast forward that a little bit to get all the flags, I see the to go blue and I go, I look over and I look at the other guy and I'm like Really? Yeah, all three. I fought for eight minutes and I can't even get a vote. I didn't even get a penalty. I can't even get a vote. And that's when I broke. I like uh I couldn't believe it and I'm not gonna lie. He looked shocked </s><s>[INST] and here you're underneath your crying, literally [/INST] right, this is a uh I think it's </s><s>[INST] amazing man shows such a war. I mean, both people can't believe what happened. [/INST] I know that's the end. Like honestly, I wish we had the rules that we do today as far as the unlimited golden score because I would have loved to have seen what would have happened. </s><s>[INST] What was jimmy saying here to you? I mean, I guess there's nothing to say. [/INST] Yeah, he he was kind of apologizing for the way the the scores went </s><s>[INST] because he knows how badly you wanted, he saw the match [/INST] and he felt I deserved to win it based on like, you know what happened. </s><s>[INST] But he probably with all his experience, knows that this is what the olympics are about the rest sometimes. Yeah, I mean that's the magic of it, man. [/INST] Well and at the same time we're at, we're in the olympic semifinal in a sport that's dominated by certain continents. And when you look at the three rafts on the mat, they're all Europeans. Yeah, you're telling me there couldn't have been one pan am when african, you know she ana you know different like why they all have to be european. </s><s>[INST] But to be fair it's back to your son, a story you've dealt with this stuff before and you've won over this stuff before [/INST] and that's why like I was </s><s>[INST] broken and you thought you one here that was [/INST] and when I hindered on that for a year and a half, like I couldn't even stand, I was done. But I'm pretty sure there's a slow motion replay on this when I watched that I was all excited. That fucking guy. Yeah, he has released, hey, hi guys, I did it. </s><s>[INST] Yeah. So here's [/INST] like </s><s>[INST] slow motion replay of the facts being raised, the heart being broken. Travis just spending [/INST] over here, watch, watch his reaction. Like he like you could see his mouth like open and awe like really? Yeah. And he's looking at two refs just like I am, he didn't celebrate until he looked at the third one and said, oh all three. </s><s>[INST] So you think he knew, [/INST] I think in his head like I don't think he really believed he was winning. </s><s>[INST] He did enough to [/INST] win. Yeah. Yeah. Because when his mouth draw like, oh yeah, hey all three, like that's not really the reaction you would give. </s><s>[INST] Yeah, I mean that was uh that's one of the greatest matches I've ever seen. I mean obviously it's painful for you, but that pain first of all sets the stage for 2016. But even without that, I think it was just a beautiful story at the olympics. You've still did incredible job at that olympics. You stood toe to toe. [/INST] I think in in hindsight having lost that match did more for me and more for the sport. Yeah, as as a whole me losing that match. </s><s>[INST] I mean, stories aren't about winning stories there, about the fighting, so and that made one hell of a story, but [/INST] it also has to do with, you know, treachery is probably not the right word to use is probably the wrong word entirely to use. But because of the conflict in the match and because of how the refs handled the match there at the end, it created controversy that was spoken about for months on world media, right? I remember articles being written about the olympics and you know, the ref thing and how it was corrupt in that match was one of them. There was another one in fencing where like something happened with the timer. We're one of the Fencers. I guess what happens in fencing? The timer Re sets up a second if it's down. So the fencer got one second played out, I think like 27 or 28 times And then one on like 30. So like there was like clock fixing for fencing, there was this match that I think just got publicity, good or bad publicity is publicity for judo. </s><s>[INST] And then you came back to uh I mean, this is the hard thing after this heartbreak to step up and continue fighting, right? [/INST] I really, really struggled, Like, unbelievably struggled from 2012 to 2014. I almost quit numerous times. I was so angry. I mean, at one I got so mad at the idea of feeling like they were fucking me every step of the way. I threw a water bottle at the referee after a match, I cussed out a referee one time on a mat, I got suspended from the sport because I was just so angry at that point in time. </s><s>[INST] And I G. F. Is the International judo federation. And there are there the people that supply the referees, basically like the kind of [/INST] run the sport that on a global scale. </s><s>[INST] So uh you sent a few emails 2014, 15, uh basically quitting one of them, said I'm mentally and physically broken. Another said, well, the subject line, I'm done, yep, the weight cuts didn't break, you know? So if this broke you, you were really going through a hard time. [/INST] I was like, you know what? We're just gonna like, dumb it down a little bit and get some wins under our belt. I'm going to go to a World cup, which is like three stages down our four stages down from like the olympic games. Like this should be like a cakewalk, like making the final level World Cup should be a walk in the park. I show up, I barely beat a 16 year old kid. Yeah, barely. Then I got smoked in the second round, I got thrown three times. I was like, I'm fucking done. They changed all the fucking rules, they fucked me out of the olympics, like, what am I supposed to do? And it was at that moment when I wrote the email where I remember sitting at a bar, I don't drink by the way, but I was sitting at a bar um at the hotel sending this email and I got a response back from jimmy and he goes, well, just just stay for the training camp, go to Germany and then whatever happens, don't worry about it. We'll talk when you get home. I was like, fuck that, fuck these people, fuck the rules, I don't fucking care anymore. I'm just gonna do judo the way I want to do judo if I fucking get she towed out. Fuck them. That was my response. </s><s>[INST] Can you become an olympic champion? Can you become an olympic medalist with that kind of thinking you think or know, was that that's counterproductive. Okay, just, just checking because maybe that's also liberating. [/INST] The expectation was no longer that Travis is going to win this tournament. The expectation was Travis is going to come home and be fucking pissed off. We're gonna have to figure out how to manage a pissed off person that's trying to quit, That shouldn't be quitting. </s><s>[INST] And the people still believe that you can be a medalist again. Like, who believed [/INST] that jimmy believed it, the team managers believed it. Some of my teammates still believed it. Um My training partner still did, but they're not the ones that are cutting the weight, flying around, feeling like, you know, all of your judo is now null and void, right? Because at this point they took away leg grabs entirely, you couldn't break a grip with two hands, right? The meta of judo has changed again, right? So I got fucked out of it, they took away how I did judo again, and now it just got more difficult. So when I'm sitting in the hotel and I'm sending this email, I remember being at the training camp like, I was like, I don't even fucking character rules are I'm just gonna fucking throw people, I don't even care from cheating, it doesn't matter to me, I'll just play stupid. Yeah, right, So I just started going back and doing judo without the leg grabs, but with all the same gripping that I was doing beforehand. And then when I got to Germany I was like, I don't fucking care, I was like, if I got to cheat to win, then I got a fucking cheat to win. If I get cheated out? Like, then I get cheated out, and I want Germany </s><s>[INST] uh would you want to Germany [/INST] the german grand prix, which is a a week after losing the World Cup because I was trying to do do judo around the new rule set, I wasn't just trying to do judo, right? Because when you get to the highest level, your game tends to morph around, you know what can you can or cannot get away with. I was more focused on trying to figure out what I can and can't get away with. And I stopped actively doing judo once I said, fuck! Whatever the rule changes are, I'm just going to keep doing judo the way I know how to do judo. And if I get a penalty then soviet. </s><s>[INST] And so that that when that started the road [/INST] back Yeah, because now it's like, I don't care if you penalize me or not because I'm gonna throw that guy anyways, I'm gonna beat them anyways, and if I get a shido for doing something wrong, then I'll just stop doing that one thing and just keep doing all the other things that they told me I probably shouldn't be doing, but they're not calling me on it, so I'm just going to keep doing it, </s><s>[INST] wow you uh You find yourself to 2016 Olympics. Was that ever a doubt by the way after this, after 2014 in Germany [/INST] I had a lot of doubt after the concussion in 2015, I remember when I first came back after four months of nothingness. That like even trying to like train the room would start to like tilt the world on me and then when I finally got over that and I could start doing things again, I stepped on the mat for the pan am's and I was like, drowning is not the right word, but like everything was being done in such a slow motion. Like I had sandbags everywhere that like, I just couldn't keep up </s><s>[INST] like mental fog. [/INST] Yeah. Like I remember fighting the Brazilian for in the semifinal of Pan Am's. I was halfway to this match. I'm just like, eyes roll up on my I'm just gonna fucking wing it and I just fucking wing didn't I got countered and throwing free pone and I was like, I don't even know what to do and I couldn't even think clearly. And that's when I was like, I may not come </s><s>[INST] back. Yeah. You have control over how to come back from this. It's like, it's just your mind and it's not it's not [/INST] operating. It's not like I can like, oh, my right hand is not working because it's fractured. Let me figure out a way I cannot use that. Like, when your mind is not working. Like it's the one thing you need. Yeah, like you gotta have it so I can work through anything else. I needed that though. </s><s>[INST] So how did you come back from that time? [/INST] That's when I wrote another email. And I was like, I'm fucking off team Usa, I'm not fucking I'm not done with usa judo, I'm done with the tour. I was like, I quit. I'm gonna go do my own thing. They were like, whoa, I can't quit now. The olympics is in like a year. Like, let's talk about this again, because it's the second time I've tried to quit in like two years, right? So then we sit down in jimmy's office and he's like, whoa, you can't quit. You're gonna kick yourself if you don't go to rio, I'm telling you right now, don't do that to yourself. Let's figure out a way of like doing this. And I was like, because when we trained before, we did it as a unit, right? We all went to the same tournaments, we all went to the same training camps and I'm like, you guys are treating me like I'm the same player. I used to be go, I don't I'm not operating at the level you think I'm operating? And I go, I can't do that. And he goes, well, what do you want to do? And I gotta tell you what, jimmy, you know, I'm being serious because my answer is something you never would have expected you go, I want you to send me to Japan for three weeks and he was like, really? I hated Japan? I refused to go there up until this point, but I was like, I have to get to a point where I can get so tired and get through it that my judo will come back and my body will learn again. </s><s>[INST] And when you say Japan to meet the quota can, like what tok that is [/INST] at the highest level of judo, It's one of the top colleges in the world </s><s>[INST] and that's so you can go with the best people in the world, you can go to war with them. Top level, Like strong players. [/INST] Yeah, there's a lot of very strong players. There's a lot of middle class players and there's a lot of volume of rounds. </s><s>[INST] So you value all of it, the middle class to like, [/INST] because when you're tired, like you can't just train in areas where your you're battling for every inch at some point, you have to be successful, right? So you still under duress and under strain and through exhaustion, you still have to have the ability to score Well if you're training with the best people in the world all the time, you're not always going to be able to score? So you still need those B level players in order to really develop again. </s><s>[INST] What is it like if you can comment briefly on training in Japan, what's it like to go into a different place, you probably don't speak the language that well um like is there an isolation aspect to it is it's like purely about judo now [/INST] I really wanted to be isolated. No training partners, know coaches. I wanted to get back to my roots and just learn how to fight again. I don't want to figure out how to beat the german. I don't want to figure out how I can develop a new entry into my sail against, you know, whoever it may be, it's not going to fight hard to fight. Let me get back to fighting, let me get back to like the root of who </s><s>[INST] I am. What were those sessions? Like? We're talking about five minute rounds, like what, How many [/INST] six minute rounds, 30 minute breaks. 14 rounds of session. </s><s>[INST] So what's the 30 minute [/INST] break, 30 30 seconds, 30 seconds second break. </s><s>[INST] Uh Sorry What? 14, 14 rounds? 14 rounds every day, [/INST] every day. 5, 5 days a week. And then 11 or 12 rounds on Saturday plus weightlifting plus running </s><s>[INST] plus weightlifting plus running. So that those are hard rounds. What does it feel like to go through that? So you have a bunch of uh just a sea of black belts, Japan, I'm sure they're hunting you a little bit [/INST] depending on who you are. I was hunted a little bit. Like, I didn't really struggle because of who I am them as college athletes. They want to show to their coaches and their higher players. Like, oh look, I can throw the world number whoever, but if you're just a guy who shows up like them beating you doesn't provide any value or raise their status, </s><s>[INST] but your your status raising. [/INST] Yes, so I was actually like in a situation where nobody was watching me and I was free to just battle at my own will, okay, which is what it was about for me </s><s>[INST] and you just push yourself [/INST] because I knew how to do that, I know how to push myself. </s><s>[INST] Are you when you're doing these 14 rounds, is every single one a standalone thing for you, So you're not trying to pace yourself? [/INST] Each one is to as much exhaustion as I can </s><s>[INST] Get, but then there must be ones that were like, it's a ground nine, Well, you're got nothing left [/INST] to figure out how to score, that's all you got to do, you got to survive, you gotta score. </s><s>[INST] What's your memories of that in those three weeks? What's like, what stands out to you? It seems like um because that's the place where you found the silver medal, uh huh [/INST] because it's the place most people don't want to be, everybody is comfortable, I would rather I would rather find out who I am and what I'm made of and find those, those endpoints and if I can't find them, then that means everybody else has given up before me. </s><s>[INST] Were there a few people that just kind of you return to battle over and over in those times and then it was just, yep, no social media, no, none of that is just like to [/INST] lock yourself in your room, you come back, you thought about it and you come back with a game plan for that day against some players here there and I would I would develop a hit list. Like I would be like, oh that motherfucker grabbed me at like 13 and I watched him sit fucking four rounds and then come try to kick the shit. I mean I'm a fucking grabbed that guy early and I'm gonna beat the shit out of him and you just develop that list. </s><s>[INST] There's probably some epic battles in that room, right? Yeah. What's it look like? Like how crowded it is it very And so you're just like to see if people see if people and you're trying to, you doing groundwork at all, just throws, just [/INST] throws, if there's no transitions, no nothing. But if I get pissed off and like you keep dropping or like not let me do what I want to do, I'll rip a choke right across your face just to let you know that like </s><s>[INST] yeah, and if I want to, do you have a really nice style of just like respectfully bullying the shit out of people [/INST] because some people call me a bully and I have to remind them that like a bully enjoys like beating up the week, right? I want to beat the person that fights back. Exactly. It's not fun for me if you don't fight back </s><s>[INST] some of the greatest people. I've, I've seen like do this, they basically uh you have this in the Iowa wrestling rooms, they'll push each other into the wall. Like they get, there's like anger but it's ultimately underneath it all. It's like a deep respect. [/INST] I was training with Colton Brown one time and I went to San Jose State because I was in California for something and he kept like, he kept circling to the edge. They had like a cupboard that had like when you opened it, it had like all the tape and medical supplies. I was like, well fucking put you right through that and he kind of lives, he kind of giggled and then he went by that edge and fucking random right through </s><s>[INST] it. To me. That's an ultimate sign of respect that both you and Colton will [/INST] remember. Well and we're still friends still talk. It's just, I told him I was going to do it. He knew I meant it to did it anyways, just testing </s><s>[INST] me. Uh yeah, listen, that's in that same attitude. Was, that's, that was in Japan just day after day after day after day 14 rounds. That's, that's rough and you didn't sit out rounds [/INST] and I did it all with a broken hand. </s><s>[INST] Uh how, how did you do with a broken hand? You show up every day you show up. Okay, I actually left to right my right. Okay, so that's okay. So you can then focus on gripping with your left. It's always a way, There's always a way, but that means you can, I guess you don't have to grip, you're right. Sometimes [/INST] I would palm it with my thumb just like hanging out like </s><s>[INST] this just like this so you can do something so you can do like a ghost because you have a um because I, what were your main throws? It was saying Nagy [/INST] coaching Gruma. Okay, sumi Uchi Mata </s><s>[INST] Mata. But you have this big um, like a grocery type of thing [/INST] like uh yeah, but not from like around the waist it's from over the shoulder over the shoulder and I can do it with just the one hand. Oh as I wish one hand, the right one, I don't believe hand. </s><s>[INST] You don't need to steve hand, but you couldn't do with a broken [/INST] hand. Could because I can just put my hand in the G so it can't come off. And then you just, because what happened was three days before I was leaving for Japan guy, my hand was arrested like this on the mat and the guy boom took my whole thumb off and tore all attendance in the palm. So when I went to the doctor, he was like, you know, do we have to put a cast on and I go, I'm leaving in three days. You're not put a cast on it and I go this is what I want you to do? Just like this? I said I want you to build a cast that holds it. That Veldt grows around so that when I'm not training I can wear it. But then when I'm training I'll take it off and then I'll put the tape on it and then whatever happens happens, </s><s>[INST] whatever happens happens. All right. So that's epic. And that led you to the 2016 olympics in rio. [/INST] Well, that led me to winning pan am gold when I got back from Japan and then almost getting my leg cut off in 2015. that was like, you know, maybe a month or two later. I was hospitalized for seven days. </s><s>[INST] The leg being cut off for what? [/INST] I had three different types of bacterial infections. In my right leg, whole leg swelled and it was in my blood skin and in my bone my right leg. Uh huh. Uh So I got stuck at MGH in a hospital for seven days until they figured out what the bacteria source was. </s><s>[INST] Where was the source of the infection is in the in the new Okay, so obviously there's a danger of like that's life threatening, [/INST] yep. When I went into the emergency room, when I got back from the world's lady was like, hey you you need to call, you're going to call because you may lose your leg tonight. Yeah. And then they put me in the hospital. </s><s>[INST] What do you think in this whole time? Are you still thinking about olympics? [/INST] They put me into the room like four hours later the doctor came in um I was at MGH in boston and he was like you have a serious infection in your leg. I go he's like we have to keep you hospitalized until we can figure out what it is. And I was like buddy, I have the olympic games in less than a year ago. I don't give a fuck what it is. I go just fucking take it out and let me get on with my day. He goes, we can't do that. Like I don't understand. I go, you told me that's infected. Just cut away that part of the tissue, drain it, do whatever you gotta do. And then send me on my way. He's like it doesn't work like that he said until we figure out what it is. We can't figure out how to stop it from growing or how far it's spread. So it took him seven days to figure out what it was. Then once they figured out what it was. I went in for surgery to remove it. Then I spent I think it was eight weeks in home care with a picc line and then I came back from that in the first week and a half of judo, I tore my S. I. Joint trying to throw a guy and then I came back from that about a month later and then 5th at the Canada Cup and then the game six months later, </s><s>[INST] How quickly do doctors understand who they're dealing with? Like, is that is that difficult for you to explain who Travis stevens is when you go to visit a doctor, [/INST] I don't think they understand, you know, their role is to get me to do my job to the best of their ability as a doctor, meaning it's going to be less than what they want and they and they struggle conceptually with like, but the Tax book tells me this and I go, but I'm not a textbook, right? Like when you go to physical therapy, the first thing they do is they pull out that binder that says day one, we do this exercise. I go, but I have my own goals. Your job is to help me meet my goal, let's let's work a plan to do that. Or I gotta go find somebody else </s><s>[INST] did the doctors in general. People outside of your close knit groups step up [/INST] if they didn't, I found somebody else and typically I could find a person who knew the right person. </s><s>[INST] I was wondering with people, like, because I'm constantly surrounded by one of the biggest problems in my life has been. There's a lot of people in my life who loved me very much, but who want me to the equivalent of that situation? um you know, definitely don't go to the olympics and definitely like like it seems like the world is full of people that want you to be average and happy, which is great, which is fine. I mean perhaps that's the way it should be like, you know my parents people close to this that's what love, how love manifests itself often in people. But then like I think the ultimate manifestation of love is understanding who this person is. Here's a madman who's driven towards a particular thing and the best thing for you to do is not to say like the rest is to say work harder. Like fuck your infection, you should be training. Have you ever met anybody as crazy as you that can help you? [/INST] Most of us who get to this point, get there because we're all a little unstable. Yeah. Even my wife leader right? Like When she was getting ready for 2016 um or when she was getting ready for 2020 because she moved to Boston to be a coach. She had a a neck problem, right? And at that at some point in time it's like what's really important day to day life or judo and believe it or not. The doctor in Canada was like I am never under any circumstances doing an M. R. I. Of your neck again. That's what she told her. She goes if you have me do an M. R. I. You're not doing judo again. So just know if you hurt your neck and it requires an M. R. I. You're done with judo forever. So decide if you want to do judo or not. That was a conversation we actually had to halve. </s><s>[INST] That's a cool thing for a doctor to say. I mean, depends how badass they saw when they said So that's a tough conversation judo one. What's, what's this with your wife? What's that relationship like? So you're both a little crazy a little bit in the in the good sense or from my perspective, in a good sense. [/INST] Yeah, it's just we've, we understand that when it, when you set a goal to do something, you're not signing on for the good, you're signing on for the bad and I don't think a lot of people understand that. </s><s>[INST] That's like a valentine's day card from Travis stevens, [/INST] you have to like accept everything negative that could possibly happen. And until you do, you're never gonna make it because you always sell yourself short, you'll never go far enough. </s><s>[INST] And if you sign up for the whole thing, then the negative is just like, oh great. I expected that if you're experiencing the negative, they're also experienced the negative and if you overcome it, maybe they'll get knocked out from [/INST] maybe they won't deal with it. Maybe they won't train through it Right when I had my five herniated disc and I was in a neck brace, I was still in the gym at seven am doing whatever it is I could do because my job is to be at the gym, </s><s>[INST] David Goggins. I don't know if you know the guy, he's gone, he's damaged a lots of parts of his body. Like you trying to achieve things. So unlike you, his achievements are like your achievements come with the metal. He's just running in the darkness in the middle of nowhere, by himself. It's like, I mean, it's the same probably is with you if you're able to be introspective about it is he's just battling his own inner demons and working through those and he's breaking up, breaking his body doing so are you cognizant of the trade off of the fact that, you know, you're damaging your body to get to these levels of achievements of this level of excellence, of this level of greatness. [/INST] I mean, I guess that depends on what you consider damage really, because I don't really see that I have damaged my body. If anything, I think I've strengthened it. My body can go through more than your scan whose is weaker, right? It's just like it's just like the thai boxers right in order to strengthen their shins. They gotta break it a few times. Yeah, it's just nature of the </s><s>[INST] beast. You just had to break a bunch of stuff to find where the weak points are and then made them stronger [/INST] or strengthen the areas around it to strengthen it by, you know, share relation to it. </s><s>[INST] But the problem is like you may not be able to do judo Like four until you're 70. [/INST] Why not? I may not be able to judo to the level I used to don't get me wrong, but I can still do judo because I think a lot of people struggle with, they want to keep doing it like they used to be able to do it. I don't try to do judo like I used to like you're seeing here, I'm not that guy anymore. I accept that I don't even try to be that guy anymore. I'm a completely different player today than I am when I was winning olympic medals. And so I guess when you're looking at like my journey and the trade off is I never sacrificed anything. The people around me sacrificed for me and I never had a downturn after the olympics because I never identified as an Olympian. </s><s>[INST] You know, a lot of olympians suffer from depression because [/INST] they identify as it now they don't have who they are. </s><s>[INST] Where was your personal moment of greatness? Like or do you not experience life that way where you were truly proud to be yourself? Like every day I wake up your [/INST] uh you wake up and you're not proud of who you are then, do you've really got to seek out some like help. </s><s>[INST] So that's first of all, Okay, I'll do that because I definitely not proud of who I am. I just wonder if you didn't identify with the olympics. Was there times maybe in the training room maybe in Japan? Like what you're, you just kind of felt like [/INST] I get more of an emotional yes trigger right where like I feel proud of what I've done when I've set to a task and I've done it. </s><s>[INST] So I'm just saying you task [/INST] and the more challenging the task, the more reward. </s><s>[INST] You fought a lot of amazing battles in 2016 Olympics. So you got, You beat the, let's see the world number four in the quarter finals. It's like a replay every single olympics. Your [/INST] all the people, I got terrible draw </s><s>[INST] saying terrible draws and then you're facing this is where I was like watching this. I'm like he screwed you face the world number one Georgian and [/INST] by the way for people who don't know, he beat me five times to my beating him once and the one time I beat him was in London and all other times he beat me, he beat me by poem and not by like a little throw like he threw me on my head at one point we were in Georgia. I'm fighting him in the final. I go to my teammate and I go guess what? Make sure you watch this fight? Somebody's getting thrown free pone dispatching and this is a magical distance and about a minute in I tried to take his head off with a big koshi group which is like a head and arm. He caught me and then threw me on my head and end of the match. Okay. </s><s>[INST] Yeah. So first of all, we're watching the video of you again, standing next to the to the guy leading up to your semifinal match. So here, if you if you win this, you're guaranteed a medal yet. But the chances of you winning from my fan perspective, I was like, God damn it. Uh [/INST] you and the rest of the world, except for me </s><s>[INST] except for you. What are you saying? You're talking to yourself here, What are you saying? [/INST] My name is Travis stevens. I'm olympic champion. I will not be denied. </s><s>[INST] The Georgia is probably like, what the hell is this guy saying? What is he talking to himself? So he was probably ultra confident. [/INST] Yeah. Had to be. The difference is is I understood the last five times he beat me. I was purposely trying to throw him, not beat him. Mm I wanted to find out if I could turns out I can't but only to throw him to beat him. I need to know how to not lose. </s><s>[INST] But you were still going for stuff here. [/INST] But all of my attacks drag him to the ground there, never standing on my feet. Yeah. Which is a complete which is a distinction that we talked about at the very beginning, right? You have throws where you're standing and throws where you're dropping every time I try to throw him standing, he throws me free pony, picks me up and he throws me on my head literally. So what I did is I just needed to get to that last one minute mark, which is what he does mentally in his own Judah where he changes into a panic and just tries to like do things that are uncharacteristic. </s><s>[INST] So you knew he was gonna start panicking here as well as the magic draws to a close and you both have a [/INST] mosquito and actually we did. We past the point where I went for broke and I broke my rule. Which one? I went for a crazy foot sweep. Um, like a pone switch thing. I can't remember what it's called, does not use that often. And he actually landed on top of me and some people wanted it to be called a bone, but he had actually let go of the G and was looking for the mat. So he didn't have any control. So they didn't award. I'm a point. Yeah. And here we go. Now. We're getting down into the news. Like he's getting frustrated. Great. Yeah. I love it. Perfect 2nd penalty. No big deal. We just got to get to the one minute mark. That's all we got to do. </s><s>[INST] So there's no panic here for you. You know, [/INST] this is right where I need to be and look at now if you go back into this match, </s><s>[INST] uh [/INST] I would love for somebody to go back and see how many times he did a drop write a poem saying org probably never. Yeah. So why is he doing it now? Because he panics and he changes his judo at that </s><s>[INST] one minute mark. So look out. [/INST] Look how much I kept that </s><s>[INST] grip. Yeah. You kept you have that grip this whole time out of your left hand. Walking him down, walking him down that he you keep the grip as he's throwing. Which dude were you thinking choke as he drops or? No, it's just kind of natural instinct [/INST] because we drilled it. I spent two years drilling this transition </s><s>[INST] and then very so people don't don't do judo, ju just so it's like really nice. You keep everything is nice to control to where you're keeping that G under his chin. Like it's really tight control. Like it's very like your dog I guess is drilling. But you're cognizant of the position if you risk the whole [/INST] time. And you can tell based on like just years of doing it, whether it's under or it's not. You can just feel </s><s>[INST] the difference and it's probably even if you wanted to stop that, it's very difficult because your whole time. It's like [/INST] once it's under, it's almost impossible to stop </s><s>[INST] for people with practices yet. So don't practice judo. One of the very annoying things about judo is in order to do g jokes that have to be under the chin. Yes. Uh even though the kind of intense jokes you do work just fine over the chin, but [/INST] and the kicker here and why we practice this choke was because when you go back and watch all of the other matches, he always does this tripod when I try to do arm locks, which is typically what I would do and when I do that, he ends up sliding out and I end up falling </s><s>[INST] off so you step up here with the choke, he does a tripod or he sticks his button to the air and you uh dude, what's the name of this joke about arrow? No, but okay, I mean when you do from like from that position, is there a way this entry into the bow and arrow? I guess because you're doing, [/INST] we we referred to in judo as a british strangle when they, when they're in that turtle position and you do that rolling, cool. </s><s>[INST] And here when you go into that, you can fall off of him. Like you said, if you go in front an arm bar, but here literally because you have it under the chin really well there's just a nice control [/INST] and I've already planned on it being on his chin. That's why I've hooked the arm, right? It's already starting to go straight. </s><s>[INST] Probably this choke in the early stages like a few frames before it feels like it uh like you're safe, it's fine like like the head will slip out or something like [/INST] that. Yeah, and that's why my left knee is up by his shoulder to keep that pressure down so that he can't posture it up. </s><s>[INST] When did you know you have this? Oh right here, [/INST] I I actually panicked um right about here </s><s>[INST] was maybe his head to come out [/INST] my hand, I tore the muscle in my palm because I was pulling so hard that I'm like he may not that Yeah, because he is my hand just going to give out beforehand and then he were right on this edge, right? So like if we roll a little bit outside and I still don't have it like that raft could stop it and then I felt him tapping and </s><s>[INST] oh that he is his heartbroken, I felt surprised there it is [/INST] the relief olympic olympic final and he knew he knew he lost an olympic medal right there because he already knew that the japanese guy was gonna be his bronze that he never beats </s><s>[INST] see the But also he probably in his head, I was confident that he would be in the final, correct and so like this, he almost is surprised. Yeah, it's not supposed to happen this way [/INST] and it's the second time it's happened. Mhm </s><s>[INST] and that's how you became an olympic medalist man, that must be a great feeling, that must be a great feeling right here. Just like all the years of injuries, all of it as as fans that watch this too. It's like holy shit, he actually did it. [/INST] It's a packed stadium to not one empty seat </s><s>[INST] man. So uh what were you thinking here? Just focus on the next match. Yeah, [/INST] it took me maybe like a minute or so to like decompress and then like get back to my normal state for the final. </s><s>[INST] So the final is against the the Russian here. What can you say about your mindset? You're saying the exact same thing thing Travis stevens olympic champion. [/INST] I will not be denied because I had felt like in London and throughout the years I felt like I kept getting robbed so I made sure and my mantra had that little bit at the end to reassure myself that like they are not going to control the outcome of today, I'm going to control the outcome. </s><s>[INST] What did you know about the Russian [/INST] everything. Um and I I honestly, I thought I had won the olympics right now and I still do think that today just like mentally when you think about it that I've won like yeah, he threw me but it was like a one in a million chance that that worked for him. </s><s>[INST] All right, come on. So, so it's not like you feel lucky to be in the final. It's like [/INST] you can't remember, I'm I'm anticipating the goal like I'm past that </s><s>[INST] like their confidence in the way you're moving in the way you're [/INST] Yeah, like I have his sleeve, he's not breaking it like still walking him down, still going forward like um I knew exactly how I was going to beat him and I developed a plan because when I was getting ready for Rio, we brought in a lot of the top Japanese players that weren't invited to the camp for the national team to boston. So I had four people, three of them were on the national team, one of them had one The universities in Japan all at 81 kg. I only got thrown once during camp for a month. Like I was I was ready. Mhm. I just fucking slipped. </s><s>[INST] Where does it happen? [/INST] Right when he threw me? So if you let this play out really quick, there's a point right here where I'm going to come around his back and I'm kind of gonna just Yokosuka to me, which means like a lateral drop and I'm going to bring him down to the floor which isn't a throw right here. It's more of like a takedown right? I'm trying to get him to the ground because I want to burn him. He doesn't do any waza So I'm just gonna keep burning him and you can see that like I get really close here. He just went a little too far to his side during this exchange. And like he's running oh my God. Mhm. </s><s>[INST] He's very wiry for an 81 KK player. Yeah there's not much like muscle on him [/INST] but he uses his length and his leverage very well. And you can see like I'm really burning the clock here, like I'm owning these exchanges more than I'm owning the Tachi waza ones, the ones in your feet. </s><s>[INST] So you weren't trying to necessarily submit him here or are like really hard or like um pin um You're trying to break him a bit. [/INST] I'm doing both. I'm being overly physical. Um And a lot of the B. J. J. People who are watching this like they're like oh well I would have done this, I would have done that. You've got to think like if that referee who's repping the judo side of it, looks at it for a couple of seconds and like uh he's not really moving, they'll stop it. </s><s>[INST] Yeah so you're like you understand judo, yeah what's called Nowata gone work like well you because you're really showing it to the ref [/INST] yes, you have to show movement and progression. I heard the forehead. Like see I threw that hand in. They're kind of hard ripping it across his face just because </s><s>[INST] the I gotta I gotta tell you there's a calm. Well no he does look a little a little broken but the Russians have like this calmness [/INST] they're pretty good at. Well don't forget they've competed like this for a long time. Yeah, it's all he knows and this is where I lose it, see how my knee hit the ground. My knee wasn't supposed to touch the ground, I was supposed to sit to my hip to bring him down. Something happened where my knee touched and it didn't happen in the first one. It just happened there. It's like that we never should have been in that predicament. Yeah. And that's that's one of the things where when you're looking at, you know, sports for anybody who's trying to improve, you have to, when you're, when you're trying to improve, you've really got to ignore the ends of the spectrum, right? The the autopsies and they got lucky and you only focus on the middle. Like the technique I was doing was perfectly sound. It just happened that the one upsy happened on the stage, it shouldn't have happened on and there's no, there's no amount of drilling that will ever like prevent that from happening. </s><s>[INST] And that's just the that sports that sports, especially the olympics, especially judo, when it's like one of those groups, you can just be your that's it, [/INST] that's it. You know, it really requires and you have to wrap your head around the idea of like if you want the ability to beat these people and throw these people like you gotta be willing to get thrown yourself like this isn't boxing. There's no like I'm going to stand in a place where he can't hit me and I can hit him because we have the G and because they can grab it, they have just as much ability to throw you as you them. </s><s>[INST] So how did you feel here? How long was the duration of you feeling upset that you didn't get the gold versus never felt it? Never felt it [/INST] just because he didn't beat me right? It's an important distinction because when I'm training and when I'm competing, like I understand that I take risk and I accept those consequences. That's why I take them. That's a consequence. That's not him being the better judo player that dominated a match and I didn't have an answer. And then he threw me, then I would be a little upset. Like when you're tired and somebody's coming at you and like, you can't do anything about it. That's a shitty feeling. Yeah. You know, </s><s>[INST] and that wasn't this [/INST] that wasn't this like, I accept losing when it's when it's my fault. </s><s>[INST] Well, that was a hell of a story, man. So from 2008, just the sheer number of injuries, the way cuts all of that, the wanting to quit the doubts. I'm sure you do not get like the fans probably started disappearing somewhere between the 2nd and 3rd olympics, like the support from it did judo within the United States and just everybody, you know, [/INST] Just like usoc tried to cut all my funding in 2015 and say no, you're too old. Yeah. </s><s>[INST] So through all of that to win the medal. I mean that's what the olympics is about. Is there some, like when you look back, does that seem like another person, Is this like another lifetime ago or like that's a hell of an accomplishment? How do you feel about the whole thing? [/INST] It's a, it's an interesting kind of predicament because there's like those cookie cutter answers about how proud you are and how grateful you are. But at the end of the day it's not who you are. So that that skill set and that mentality that you know, it took to accomplish that, that's who you are. And so this was just a stepping stone in and who I am. So it's in the past to me like there's no shrine in my house that has like an olympic medal in it. I can't remember the last time I looked at it. </s><s>[INST] So you're saying like the, all the stories, the skills along the way, that's like you right now sitting here is the shrine. [/INST] Yeah, the who you become along the journey is really what the prizes right? Like when you think about any of them, most of the people that you know, go through that depression after the Games. It's because that is their shrine like that is who they have identified as that is who they've told the world, the community, their friends, their family. That's how they've identified. I've identified as a person who perseveres overcomes and accepts challenges. So like I, all those things are just like, you know, put in a suitcase off to the side and I'm on to the next great chapter thing that I'm trying to do </s><s>[INST] and it's, it's both sad and cool that um, very few people in the world get to experience what it's like to be you. I mean this level of, of having gone through that journey, [/INST] everyone has the opportunity to uh huh. </s><s>[INST] Yeah. Yeah. I mean I've done a few um, difficult things in my life, but I gotta tell you wait cuts and sauna. Um, and [/INST] I would tell people right now who are listening like don't go through that. And I think a lot of wrestlers, a lot of young judo players, a lot of long young, like just combat sports people were weight classes are a thing. They almost take a sense of pride. Like when I hear them talking about like how much weight do you have to cut if you have to cut a pound more, It's like you've accomplished more. Like you're tougher. Like you're not like there's no, there's no trophies for that. </s><s>[INST] You whatever the reason had a job to do and you got it done and that, that is truly inspiring. No matter how hard that there's a big deep lesson to learn from that, then you start getting to the specifics of whether you should wake up or not, but if we don't, then most of the great things we have in this world, we wouldn't have the reason we have many of the great things because people did that way, cut the equivalent of the weight cut for whatever the discipline and [/INST] there's a difference between having to do it because you have to and you get through it, then setting yourself up to do that because you think it's the cool thing or the thing you're supposed to be doing in order to be successful, there are plenty of like two time olympic medalist, I probably could have been a two time olympic medalist, had I not cut that much weight, I probably would have multiple world medals had I not cut that much weight because my body wouldn't have been that broken, there's always the other side of it. So just when you're looking at it, like I just hear it in like young kids, even some of my own, like when you hear them talk about like where their weights at, they almost take a sense of pride on how much they have to lose because they hear stories like this and it's like that's not the takeaway, I did it because I had to, I was put in a situation where like I may not have gone to this game that I moved up to 90 kg because I wouldn't have had time to grow into the division </s><s>[INST] and then you get the job done and then you get the job done right? There's uh it's just a very important difference. And that's also asleep. Uh that's what people talk to me about. There should not be any glorification of not sleeping. There should not be a glorification of cutting weight. But if that's on the way to your whatever is that fire inside you that you know, needs to get done. Like the job in hand. If you need to sacrifice in some of those ways you get the job done. Yeah. And the, the way God is an interesting one because it's different. I mean, you could speak to this, there's different sports in which the weight is more important than others. And there's different levels to this game, I think at the level you operated and that was probably essential. Like there's huge games changed completely from 81 kg too 90 kg, [/INST] huge weight jump. </s><s>[INST] It's first of all, it's weight. But then the strategy, it's like so much changes the height and all those kinds of [/INST] things. The physical, like people don't understand it, but the physical size of a 90 kg judo player versus the physical size of an 81 kg judo player. It's like putting a human in a human, like there's enough space. It's not like, You know, you could stand next to your friend who's £180 and you could be 160 and you guys can look identical. It is different when both the 90 kg 100 kg and 81 kg. Both have 6% body fat and they're cutting into the class. </s><s>[INST] And it always feels like there's more variety of 90 kg because some of them are linking tall, [/INST] some short and stocky, </s><s>[INST] Stocky, it's like 81 is more uniform. Which but then the, you know, the flip side of that is the this is why I like in jujitsu again, amateur, uh, competing against bigger guys. Like I love that more. I like, I like cutting way just so I'm slim. Like that's when I feel the best with the same thing that you mentioned. But like, I love going against 200 - 20. That [/INST] because in jiu jitsu, the weight doesn't get amplified in the sport. Like the weight is just the weight, right? If you can, if you can leg press 2 20 you can bench 2 20 then Yeah, you can train with a guy who's to 20 us. That's easy. They're not gonna hurt you. </s><s>[INST] And I mean, there's there is a truth that, you know, lightweights and middleweights in jujitsu and the same is true for judo. It's just like a lot more of them. That means if you want to be is you're just competing at a higher level. So like there's much more variety of games, the level is much higher. So you're taking on a bigger challenge, even if you're like um have a weight advantage. So those are all the sensations you have to kind of make and certainly suggest to people that are way cutting our silly. I mean that's that's the natural beginner thing to do, is to feel um the way the nervousness about competition expresses itself is through the desire to be as light as possible, which is the totally wrong desire to [/INST] have. Right? Like when you, when you look at me now, I'm probably like 2 30 right? But I probably have the strength of a 70 kg judo player. Yeah, right? The weight doesn't really do much. </s><s>[INST] I mean you have the same thing with wrestling, skinny, skinny guys. The skinny you that we're looking at there just the amount of power in that person. It's fascinating because it doesn't look like, you know, you have some muscle but it doesn't look. But I felt the power of some of those people. Uh it's scary. Yeah, it's like that's the best way I can describe. It is like scary. It's like, oh shit, again, it's the food chain, you're not at the top of the Virginia work. That's that's the natural feeling when you go with some judo people. Um What's your sense about this recent olympics, What stands out to you as um so like teddy Riner who wasn't a big run for a long time. Many consider to be one of the greatest judo players of all time. Two time olympic gold medalist and uh time two time olympic bronze medalist of four limb close uh not counting like team stuff just doing individual and then like, yeah, I'm [/INST] not time world champ. Yeah, I'm not sure they're going to catalog that team event. Like are they all technically olympic champions or is France and olympic champion? </s><s>[INST] No, they're all technically olympic champions, but I'm going to ignore that. [/INST] Is that how they're going to classify it </s><s>[INST] now? According, sorry, according to Wikipedia, like according to the internet, I don't know according to my GF or whatever [/INST] because you know, some of those players never, you know, want to match. They just fill the spot. </s><s>[INST] Oh, that's even a starker example. Oh, that's sad. [/INST] You know, they lost in the individual and then they also lost in the team and so </s><s>[INST] well, it's interesting because in the case of uh teddy uh he was, you know, important to the win against Japan in this olympic. So like in the team event. So like if you, I feel like you should put that in the equation and say who won gold, right? It does feel like he won gold in the team because he carried the team [/INST] Well you have like no more at 60 kg from Japan, three time Olympic gold medalist? No team event. Yeah. Are you, are you going away teddy's team </s><s>[INST] event, we're not, we're not arguing this. Of course. [/INST] No. I'm just wondering how like the I. J. F like when you look at a player stat, is it gonna be like team gold medal for the olympics versus like their own personal gold medal? </s><s>[INST] Yeah, I think in sport you have to be brutally honest. And I think hopefully this doesn't piss off people hope it does. But judo is an individual sport. It's honestly just that one athlete. Maybe the athlete and coach. All right. If you look at the big big picture, but there's no there's no team in judo. That's the beauty of combat sports. That's the honesty of it. That's the brutality of losing to another human being in a combat sport. That's why it's so damn embarrassing. You get slammed is because it's like you there's no team to uh, to carry some of that responsibility. It's all on you and you suck. That's what you lost theirs that weight. And that's why it's like magical. It's not it's not like soccer. It's not uh, it's not like basketball. [/INST] Yeah. I couldn't play team sports because if one of my teammates wasn't doing their job correctly, I would go play their position. I'm going to do it better than </s><s>[INST] you. Yeah, but that, you know, some of the greatest leaders of teams also do that. Michael Jordan is like that. Right? I mean, it's like with your actions, you raise the level for everybody. Like excellence is expected and therefore everybody needs to step up. So some of some of the greatest, I would say team leaders are individual is the heart, But it's okay. So, teddy, I think 10 time world champion, non team regular. [/INST] It's a big number, but I think he has some like, open weight categories in the open weight. Right. </s><s>[INST] Right. I mean, you can count those, Right? I mean, that's interesting. Let's get the [/INST] same division twice. </s><s>[INST] It's the same division twice. That's [/INST] right. One day after another. I don't know if I want to </s><s>[INST] contact. Yeah, well, I mean, that's one of the reasons people don't usually put heavy weights in judo as like the greatest of all time because the level of competition is lower. Yes. But anyway, he did lose in this match to um to a young Russian uh, Tamerlan bashar match also. Not on the internet. Thank you. Olympics. I am definitely going to go on some rats on the internet as a fan of olympics. I feel like this definitely needs to change moving forward. The, like every single major olympic event. I'm also like, I also like random sports, like weightlifting, even though I don't do olympic weightlifting, it's fun just to watch fun to watch such high level of excellence and the fact that we can't just freaking watch the full, like each nicely categorized event is really heartbreaking in judo in olympic weightlifting and track and gymnastics, all of that anyway, uh, teddy lost. I mean that does that stand out to you if you were to like recap the things that you remember from this olympic [/INST] picked him losing already. Like in my predictions </s><s>[INST] lose, which where that match or just in general, somewhere in the final in the [/INST] final, you thought finally was at semi when I looked at his draw because he decided not to compete throughout what I do like the bare minimum to go because of his age. I didn't think he would have enough energy to battle his way through the draw that he had and sure enough he didn't he felt earlier than I thought, but he just he's not the young athletic person he used to be. And when they changed the rules to judo they allowed people to take people into really, really deep waters which you saw at this olympics which you know, it didn't ruin the sport or did it not like, I'm not sure, but it was definitely difficult to watch. </s><s>[INST] Would you put them at the greatest of all time or asked another way? Like who do you think is the greatest judo player of all time? [/INST] He's definitely not the greatest judo player, but he is definitely the best competitor. </s><s>[INST] What's the difference in judo player and competitor. [/INST] There's an ability to like do the act of judo of like throwing pinning arm locking versus can you win a judo match right? Like when you look at somebody like Nomura who like through everyone, he fought through three olympics, multiple world championships, multiple things like that's appear judo player in the essence of judo. He can throw pin or arm lock just about anybody he steps on the mat with during his time, teddy tended to, when you look at his judo because of his size. Again, it's just because he's in the heavyweight category, he was so much bigger, so much stronger people just couldn't handle it. And you would see really good judo players just break. Like they could hang in there for a little bit, but eventually his size, like you can't control that weight, wait moves weight. And when you have to use all your strength to keep him upright and off of you, your muscles just give out because you don't have somebody of that stature and that skill like to train with, to train those muscles. </s><s>[INST] So what you're thinking more like those, uh, 73 81 90 kg people that just stand in the pocket and just give, yeah, everything [/INST] like what comes to my mind is like a Koga Koga, You know a name or a who's a 60 kg guy. But again, like his dynamics and how long he was dominant for, Like, it just, </s><s>[INST] do you put value to like epic throws, like singular moments of greatness [/INST] if it's against, um, a noteworthy player in a noteworthy position. There are a lot of highlights of people that are good judo players, but there are highlights are of, you know, scrubs on the I. J. F circuit, it's like great. The japanese guy through the guy from, you know, Senegal free pone, Great. We kind of expected that you took the world number one against the 330th person in the world. What do you think was going to happen? Like when I see those highlights like thrown around like social media, I'm like, that's not a highlight. They might as well have just been at the dojo, like practice and throws. </s><s>[INST] If you look at the like top 10 list for judo, Kano always comes up, you know, as, um, [/INST] but he's not somebody that, I don't think his results are there, but you don't really know how he got there. So it's, it's hard for me to like, I can't see his judo. Yeah. So I'm not sure </s><s>[INST] by the way, is the founder of judo for people who don't are considered to be the founder of judo. Yeah. [/INST] The sport evolves. The players that are like, if you took champions from the past and you fought them against the players of today there, it's not happening and that goes with anything, right? So every time you think of like who's the best of all time, it's probably somebody within a generation or two of today. If I'm gonna pick my top three, top three and I would go, generationally speaking, I would pick, oh no for today, probably Iliadis for like my time frame. Like the from a developmental standpoint and then I'd probably go Koga and then before Koga I'd probably go no more as like the person of that generation that people like as a whole in judo respected. </s><s>[INST] Yeah. Well in the case of I wonder if people feared Koga. [/INST] Yeah, yeah. </s><s>[INST] You hear that little guy is gonna get under you and you gotta go for a [/INST] Ride. You know, he was 78 kg when he took second at the all Japan's which is an open weight class. Yeah. You know like he he could throw down with anybody anyway class and still went, </s><s>[INST] he was one of the early people that planted the seed of judo love of judo nia. Like [/INST] yeah. And when I looked at him like that was how like I wanted my judo to be portrayed that style. </s><s>[INST] Yeah. And then Ilias Iliadis, you just like you have a similar attitude is him. So you just like the way [/INST] he cares why we get along </s><s>[INST] you guys hang out? I'd love to see that conversation. [/INST] I remember when we were talking about like his coaching, I was like why didn't you take this team or like why did you pick this team? And he's like, I can't work with those people like those people are weak, their Children, like they don't know how to train hard. </s><s>[INST] I love that guy. What about Oh no because he was competing in this olympics. He got he had golden is an olympics, right? Uh [/INST] Yeah. He lost in the team tournament though, I think he just didn't care. He just really wanted to throw that guy, </s><s>[INST] He like throws everybody. So he's, he represents the thing you're mentioning. I signed up to the judo fanatics best of uh Oh no, is there something that stands out to you about him? That's especially you find beautiful like or powerful about his technique. [/INST] Um his adaptability to the situations and understanding of like what needs to happen in order to throw these people. I specifically watched a match with his and I was gonna do a breakdown video on it because </s><s>[INST] zero match, do you remember what it is? [/INST] It's him versus uh Garvey of hungry. Um </s><s>[INST] Is he good at gripping? So we're watching the match against Hungary. Uh so the one minute comes up right here coming [/INST] up, I've heard he's freakishly strong. I've never had the ability to train with him. So I'm not </s><s>[INST] obviously look super skinny, [/INST] but but when you see him without his g jacket on, like he's a Jack dude, which is uncharacteristic of a Japanese player from back in the day in a way changed all that. He was like, we're going to get physical to compete with the Europeans. </s><s>[INST] That's another one of the greats, right? And yeah, he doesn't get mentioned enough and he's a righty here. Yeah, okay, [/INST] And this is where you start setting it up, like you can see he was standing in like a left handed stance and then he changes. </s><s>[INST] So he grew up almost like a double uh double sleep, not a double [/INST] tricep, the tricep and the the front sleep standing like a lefty </s><s>[INST] and nobody grip just crisis up and sleeve and there was like the biggest whip and twist of of a neutral motta. [/INST] Yeah, he doesn't actually lift him off the floor and if you look at it and like slow motion almost. Um yeah, let's yeah, there we go. Um The Hungarian player was like 100% defense and he still did this right? So right here, like press pause this, this is like and identify if you're trying to like learn, you don't figure out how to set it up because knowing how to get to the point right before you pull the trigger is probably the most important. So when we watch this play out, what owner is going to do is he's going to pivot off his right leg right here, he's gonna back step with his left and it's gonna pull Garvey's front leg all the way forward into what we would call like a neutral square stance. So he plants hard </s><s>[INST] and look, it's an interesting pull with the oh no, it's not try. So he almost like he starts to the triceps and he like collects the gear or something like [/INST] that, but it's still above the elbow because you can see the bend, right and right here, see how he never put back it up a little bit. That this is kind of like one of those things, yeah, pause it right there. So when he puts his right foot down, he's pulling so hard with his back that when owner goes to put his left foot down, it never touches the mat, but by putting his left foot back it actually pulls in garbage put forward. And so he's able to speed up his throat by just continuing that motion back which what was supposed to have been a step turned out to just in the middle of the action. He makes a split second decision before putting the foot down to just continue because he recognizes that feel in his hands. </s><s>[INST] And so it's like, it never, it's a swing like he never touches [/INST] again, but it never, it never started as like a big swing to a back step, he changed his mind part way through, </s><s>[INST] so right there would be a back step, right? [/INST] Yeah. And then he goes, nope, he's bringing that foot forward, I'm just gonna go </s><s>[INST] for it. And wait, is he full like cool air? [/INST] Look at that, boom, boom! And look at if you go a few more steps forward right there, his hip is the same height as some garbage shoulder. Yeah, because he's leaning so far into the throw with his body weight and he's allowing that tricep grip to rotate that's going to draw and garvey forward. And now when you pause it right here, you think about the sheer physics to like get your body into this position. Jimmy and I were so like when we saw this for the first time, we tried to just stand like that and we couldn't do it. His left foot is pointing straight ahead, His chest is perpendicular to that foot of parallel with it, right? And his head is by his </s><s>[INST] foot. Is that only possible in the midst of a throw? Do you think he works on me? Like [/INST] I think he's done this particular throw, not this style of it, but the models so much that his body has adapted to be able to do this. So when people are trying to learn and like breakdown videos, they don't understand like the power he has and what we call end range motion. </s><s>[INST] Look at that. So like look at the full range of motion, he takes right, that left foot swings all the way around and the torso starts Like at 3:00 and it goes all the way around, Like almost back to the 3:00. Yeah, like like [/INST] what? And he never lifts his leg above his hip. And the crazy part is he never fell over during any of it. Look at that stayed on his feet. What's he doing? </s><s>[INST] Is that, is that a matter of pride or just, [/INST] I think that's just habit the way the forces work. Like he can just stay up. </s><s>[INST] I that's one of the most beautiful throws I've ever seen. [/INST] There's so much wrong with it. But it worked because when you think about member, what we talked about the very beginning, like he's got to get his center of gravity under his, well, here's one of the top players in the world, throwing another top player in the world with his hip at that guy's shoulder height and it's still working. It's </s><s>[INST] okay. So he, this generation, he could be the great Yeah. And like he switched a lot of those details of the throat in the middle in them. And that, that only is that means he's probably what like 100,000 times that throws happened. Yeah, I saw you were into chest recently. So you're like me a bit of a beginner in chess. Your part of launching the website effective chess. So I gotta ask maybe it's a personal question. But uh, do you have advice to yourself and to other beginners in exploring chess? I've had 21 have fun to start getting good. It's nice to see like olympic caliber athletes take on a difficult task with the beginner's mind. So like what's that process? [/INST] Like I'm a huge fan of just learning new things in general, right? Like when I left judo, like I took a job as you know, marketing for foodie sports and I was getting frustrated with designers. So I learned Photoshop, I also got angry with a photographer. So now I take all the photos too just because I don't mind learning, you know, I've spent my entire judo career learning all the time like adding new techniques, finding new ways, practicing developing and so when it comes to chest, I treat it just like I do anything else, I just stick to one plan and I learned all the ins and outs of that one plan and then I develop another plan right? Like all my practice like a London opening for example and just don't even care if I win or lose. I just want to figure out how I'm gonna lose and then figure out how I'm gonna win. And once I know that position is now done, then I start with another position and then once I figured out how I'm going to lose and how I'm going to win, the next thing I do is I don't go to a third. I figure out the bridge between the two, like at what point during my openings, can I transition back into this opening, </s><s>[INST] right? So like you have like some basic openings and you want to see how they go wrong, how they go right all the different ways and then that starts to solidify higher level concept of that particular opening and you start to stitch together the [/INST] concept concepts together because being able to go from one to another and then back and forth is part of the reasons why like I was successful at judo is just because everything I do at some point it touches that spider web of like being able to get from one area to another. We refer to it as like a toolbox right? You need more tools in your toolbox, but if you're always grabbing the wrong tool for the right for that job then you're just not going to have success. </s><s>[INST] I actually forgot to ask you mentioned a few greatest chess players of all time and I noticed you didn't mention Vladimir Putin, I gotta ask you about um his judo, do you by chance know much about his judo, What do you think about you know, a president of a major nation being a judo black belt and I think from what I've seen pretty good at it, [/INST] I think it shows you know if he if he actually got it like let's let's go with that premise of like he earned it right. That just shows like a level of like physical persistence and mental fortitude to be able to like you know take those beatings and just keep showing up until you've overcome and can now give those beatings </s><s>[INST] As you know in Japan and Russia you get it by just like when you're young it's easier to get a black belt when you're like just go through a bunch of beatings for like 10 years in your in your teenage years. But there's also from it uh springs like a camaraderie, like there's definitely a brotherhood and sisterhood in terms of judo to where you're you're connected forever because of that. For many people start childhood connection, you sort of leave judo, You know, in your 20s and your 30s, but that's always there in the same is true with wrestling. So it's interesting to see him pay respect to that like by going with the Russian national judo team and I think you did obviously they have to get thrown right, but just you can tell and you probably can tell even better, but you can tell when a person moves in a way where you're like, okay, you've had Like 10 years of beatings, you can tell the way they pulled the way they moved. But I also like in contrast to the U. S. National team or I don't even think there's a national team for us, right? It's it's the patriot judo center, right? Uh that there is some, it's really cool when there's a camaraderie like that amongst the highest level olympic caliber athletes in Russia, I suppose Japan might have similar kind of thing and then you have then you can have the system of people together and then you can have a strong coaching staff, not just like a coach, but the coaching staff and you can have the nation backing that staff. I mean, and then the result is like you have some incredible level of judo emerge. Um is there something you could say? We didn't we didn't talk much about jimmy. I mean, he was a critical part of your, just the like of your perseverance through all the all that you have to go through. What did you learn from jimmy? What are some impact that he had in your life? Both on the mat and off the mat? [/INST] You know, if we had to like put it down to like a very simple thing, he told me how to win, right? It wasn't necessarily like the technical side of judo, Like we went over gripping, we went over this, we adapted that, but the real strength to jimmy was like, he knows how to win and most people think, well if I get really good at this technique, I'll be able to throw people with it. Not when that is not how the world of sports works, right? Like I remember in one of my Youtube videos, I was doing a breakdown of a match from the Cuban grand prix where I was fighting a Mongolian guy, he's kicking the shit out of me. I'm not gonna lie four minutes in. Like he was just throwing me like left and right, he was so fast, I feel like I just couldn't get to him In the last 30 seconds, he changed, he started protecting his lead instead of continuing to fight the way the entire match was going in his favor, he made a mental shift and when he made that mental shift, I beat him. Yeah, because he didn't know how to win the fight. He can win exchanges, but he can't win the fight. So the last thing you want to do is have to win every exchange in a match. You want to know how to Kick it into 6th gear, like when to step off the gas, when to focus on gripping, when to attack, how often to attack all those things like </s><s>[INST] and you've had those conversations with jimmy like this is not like how to stop trying to win every exchange, that kind of thing. [/INST] Yeah. And instead, because I was a brawler before, I was like, I threw you once I'm throwing you again and sometimes you get caught, why would I do that? I'm already winning. </s><s>[INST] What about like the mental side of the game, the preparation, all those things, [/INST] one of the biggest things jimmy brought to the forefront when it came to like the mental side was the visualization, right? And when I started visualizing myself winning, I started seeing more success, but once I started seeing more success with the visualisation also came self doubt because as I'm starting to picture myself, like I would picture myself before fighting churches, villi, I'm gonna throw him with koshi Gruma and I can see it and if I stand in the shoot for too long you start to like but what if he counters then you go, well if he counters with this, I'm going to counter with that. But you already let that doubt in And then you start playing this like five steps scenario but you still come out on top but all that doubt has like seeped into your mind, right? And a lot of people don't understand that that's a bad thing. You're still winning in your mind, but you're also doubting yourself in your mind. </s><s>[INST] Yeah, once you let the like it's so destructive. [/INST] And so I remember I was at the World Championships, I can't remember what year it was, but I was ready. Like I was healthy, I was ready to go and we all thought like this is the year Travis one of the world's I go out there in the first round, I'm in the shoot for like 45 minutes. Like the match went into golden score. Then the next match went into golden score and the fucking next match went to golden score. Then the referee came and told me you can't wear your G. Then big jim goes why can't he wear his G. N. E. G. That has his name on it, We're not going to let him wear he has to wear a different key. So then I go fuck you, I'm leaving and I walked out there and I thought I lost in golden score because I did a coach and they called it a false attack and I went create them out of the fucking worlds. But when I was in the shoot I struggled because I started allowing the like Hungarian guy that I was going to face to do things to me that I would have to play defense too and then counter, it's like great. But now I'm doubting my own ability. So I went to a sports psychologist and the big game changer for me was I focus more on the emotional physical response that happens in matches rather than the actual, You know, quote unquote like Instagram picture that would have happened. So when I was getting ready for 2016, you think about like how do you feel like standing in the shoot? What does your body feel like? Is your heart racing? How's your breath? Is your mouth dry? And then you think about like okay, the ref just started the match? What happens? Like how was the atmosphere? Like how do you emotionally respond to these things more so than me trying to beat a specific judo player Right? Like all the Rafters gave you a penalty at a minute 30. Like how do you feel? And then you start thinking about the physical responses and when you do that really well you can actually get the pins and needles and your body will start to sweat and your heart will start to race as if you're in it because it's not about the technique, it's more about the physical, like, what does it feel like to have your fingers ripped out of the G in the first exchange? Now my hands can feel that that's fascinating. And then on a cellular level, like I fought the olympic game so many times to the point where like, it is no longer a goal. It's an anticipation. </s><s>[INST] So down to the experience of the grip break that just to sweat the heart beating the Yeah. [/INST] Does it feel to have your head smashed into a mat and driven across the mat with a matte burn. Yeah. And then getting about that and getting back up. </s><s>[INST] Yeah. Like with a bit of a burn, all the kinds of the actual sensations in [/INST] the actual sensation of what it takes to fight and you don't </s><s>[INST] match. Not a strategy like, but the actual sensations experience. That's fascinating [/INST] because then your body is going to fight hundreds of matches without the physical damage. </s><s>[INST] And you can probably get really far with that and not also in just, you know, but basically anything you can simulate. Yeah. If you learn how to simulate well, you've lived a very uh hell of a life is there advice you can give to young people sort of high school college, you know, thinking about their career, thinking about life, how to live one they're proud of. Yeah, [/INST] I think that the number one thing I can tell people is and how I've lived my life is you've really got to like forget everybody in your life right now, your mother, your father, your grandparents, your girlfriend, your boyfriend, whoever it is, and really decide like what is going to make you happy right at some point in my career, the act of pushing my body to the limit made me happier than winning a Grand Slam medal, pushing my body to the limit, didn't make me happier than winning an olympic medal right? There was, there's a balance there and I think a lot of people struggle with living their life where they're happy and they make other people happy or taken there their feelings into the considerations of what they need to do in their life. And I think if they can cut those strings sooner, it will allow you to get over it quicker and get to a happier place sooner. And then as long as you're focusing on what's making you happy, the things you do that make you happy, will attract other people who do those things that will in turn build stronger better relationships </s><s>[INST] and then you will also realize the, the best form of yourself and inspire many others, like you've inspired me to whatever the hell I've done uh at least to do a slightly better job than otherwise would have by doing martial arts by taking that journey and I think becoming a better person because so Travis I have been, I continue to be one of your biggest fans. I love your whole career in the way you pursued happiness. I love what you and jimmy have done. I love the sport of judo as represented by you. So I deeply appreciate what you've done man and I'm honored that you would spend your time with me today. Thanks for talking man. Thank you. Thanks for listening to this conversation with Travis stevens. To support this podcast. Please check out our sponsors in the description and now let me leave you some words from napoleon Bonaparte. Never interrupt your enemy when he's making a mistake. Thank you for listening and hope to see you next time. [/INST] </s> |
<s>[INST] So I'm sure that there's a few folks listening to this that are rolling their eyes and saying, here we go again. Two white guys talking about the lack of institutional racism in America. First of all, what's your, what would you like to tell them? So are african american friends who are looking at this and I've gotten a chance to talk to a bunch of them on clubhouse recently, clubhouses, the social app and I really enjoy, I personally love it because you get to talk to as somebody who is an introvert and doesn't socialize much. I enjoy talking to people from all walks of life. So it gave me a chance to, first of all, practice Russian and Ukrainian. So I get the chance to do that. Then you get a chance to talk about Israel and Palestine with people who are uh, from that part of the world. And you get to hear raw emotion of people from the ground where they start screaming, they start crying, they start being calm and collected and thoughtful. And this is as if you walked into a bar with custom picked regular folks in quotes, regular folks, just people that have quote unquote lived experiences, real pain, real hope, real emotions biases. And you get to listen to them go at it with no, because it's an audio app, you're not allowed to start getting into a physical fistfight. So even though it really [/INST] sounds like people want. </s><s>[INST] Yeah, and so you get to really listen to that feeling. And for example, it allows a white guy like me from another part of the world, coming from the former soviet union to go into a room with a few 100 african americans screaming about joe Rogan using the N word. And I get to really listen. There's very different perspectives on that in the african american community and it's fascinating to listen. So I don't get access to that by sort of excellent books and articles and so on. You get that real raw emotion. And I'm just saying there's a few of those folks listening to this with that real raw emotion and they won argument, they say is you Douglas Murray knew lex Friedman don't have the right to talk about race and racism in America, it is our struggle. You are from a privileged class of people that don't don't know what it's like to be a black man or woman in America walking down the street, Can you steal man in that case? [/INST] First of all that? </s><s>[INST] Okay, that's not. I think we need to define steel manning. Can you [/INST] know what? I really resent that form of argumentation really resented. I have the right to talk about whatever the hell I want and no one's going to stop me or try to intimidate me or tell me that I can't simply because of my skin color. And I think that if I said to somebody else the other way around, it would be equally reprehensible. If I said shut up. You have no right to criticize anything that Douglas Murray says because you've not got my skin color. Okay. It's not an exact comparison. But seriously is that is that a reasonable form of argument? You haven't been through everything I've been through in my life. Therefore you can't comment. No. In that case, nobody can talk about anything. We might as well pack up, go home and isolate ourselves </s><s>[INST] strong words. But can you try to steal me on the case? Not in this particular situation, but there's people that have lived through something that can comment in a very specific way. Like for example, holocaust survivors, there is a sense in which maybe a basic sense of civility when a holocaust survivor speaking about their experience of the holocaust then um, an intellectual from a very different part of the world is simply writing about nuanced geopolitics of World War Two just should not interrupt the holocaust survivor. [/INST] We physically interrupt them. If they're telling their </s><s>[INST] stories with [/INST] logic </s><s>[INST] and reason, that the experience of the holocaust survivors somehow fundamentally has a deeper understanding of the humanity and the injustice of [/INST] the first of all. Again, when even deeper waters now, in terms of wanting to listen to another person who has experienced something. Yes, yes, but not endlessly. Not endlessly. I mean, there are some people who have written about, I mean, there are people who've written about the holocaust who didn't experience the holocaust and have written about it better than people who did. It's not this idea that the lived experience to use this terrible modern jargon as if there's another type, this this this idea that the lived experience has to triumph over everything else is not always correct. It can be correct in some circumstances if you're sitting in a room with a holocaust survivor and somebody who had never heard about the holocaust and wanted to kind of, you know, shoot out their views on it. Yeah. One of those people should be heard more than the other. Obviously, obviously if there's somebody who's experienced racism firsthand and there's somebody else who has never experienced it, then obviously you'd want to hear from the person who has experienced it first hand, if that is the discussion underway, I don't think that it's the case that that is endlessly the case. I'm also highly reluctant to concede that there are groups of people who by dint of their skin color or anything else get to dominate the microphone. Now of course we're literally both speaking to microphones at the moment. There's an irony to this but let's skate over the irony. What I mean is people saying you don't have the right to speak. I have the right to take the microphone from you and speak because I know best fine if you know best will argue it out and someone will win long or short term. But the the there's the almost aggressive tone in which this is now leveled. I don't like the sound of nobody's experience is completely understandable by another human being, nobody's and what many people are asking us to do at the moment, us collectively is to fall for that thing. I think it was Camille faster who said it first but I've adopted in recent years is to say you must spend an inordinate amount of your life trying to understand me personally, my lived experience everything about me, you should dedicate your life to trying to do that simultaneously. You'll never understand me. This is not an attractive invitation, this is this is an unwinnable game. So somebody if somebody has a legitimate um and an important point to make, they should make it and they will win through whatever their characteristic, whatever their race. And by the way, there are plenty of white people who experienced racism as well. There are plenty of white people who do and have done. And increasingly so, which is one of the things I write about from the war in the West, I would argue that today in America the only group you're actually allowed to be consistently vilely racist against the white people. If you say disgusting things about black people in America in 2022, you will be over, you will be over if you decide to talk about people's white tears, their white female tears, their white guilt, their white privilege, their white rage and all these other pseudo pathologize in terms you'll be just fine. You can be the Chairman of the Joint Chiefs of Staff, you can lecture at Yale University absolutely fine and the white people have to suck that up as if that's fine because there was racism in another direction in the past. So white people can have racism as well. Does that mean that I think that I have a right or other white people have a right to dominate the discourse by talking about their feelings of having been the victim victims of racism? No, not particularly because what does that get us? It gets us into a endless cycle of competitive victimhood. Am I saying that white people have experienced violence have experienced historically, anything like the violence that was perpetrated against black people in America historically. Obviously not, but you know, what kind of competition do we want to enter here? And this is very, very important terrain now in America because there's one other thing I have to throw in there, which is how do you work out the sincerity of the claim? How do you work out the sincerity of the claim being made? At one point in this latest book, I referred to very useful bit in niche and genealogy of morals. Where as you know, nature always has to be treated carefully. You know, when people say, I love Nietzsche, which beds, what exactly do you love about him? But he a lot can be learned from the answer. But there are moments in january to moral that was very useful for this book. One of them was the moment when Nietzsche uses a phrase that have now stolen for myself, appropriated. You might say where, where he refers to people who who tear at wounds long since closed and then cry about the pain they feel now. How do you know? How do you know whether the pain is real? How do you know, I'm not saying you can never know, but it's hard. So when somebody says, I feel that my life hasn't gone that well and it's because of something that was done to my ancestors 200 years ago. Maybe they do feel that maybe they're right to feel that maybe they're making it up. Maybe they're using it as their reason for failure in life. Maybe they're using it as a reason to not even try. Maybe they're using it as a reason to smoke weed all day. I don't know you and who does know? How can you work that out? And that's why I come back to this thing of who are we to constantly judge in this society, other people who we don't know and attribute motives to them based on on racial or other characteristics. </s> |
<s>[INST] sounds sounds pretty awesome. [/INST] And we even randomly ran into two friends of ours who were in the same city and we just traveled with them for about half of the </s><s>[INST] trip. So you just took on the chaos. [/INST] Exactly. It was an adventure. </s><s>[INST] Okay. And I see like because you were using your hands a lot, you've gotten, you picked up some of the, the, the italian hand gesture [/INST] did, we did get yelled at by a lot of Italians. The old italian grandma's would come to us after breakfast because we'd leave something on the plate and she'd be like, you could feed an entire ville with that tell your friends and we'd be we'd feel so yeah, we got cursed out a lot. But it really reminds me of where we grew up and how true were Romanian but it was like an immigrant neighborhood. Um So you know same if you don't finish your plate that's disrespectful to the people made the food </s><s>[INST] the food. I feel like the carbs thing is [/INST] very yeah I think very overrated in my opinion. So I'm actually not not supposed to eat gluten because I have an allergy but I was in Italy and it's you know gluten galore. So I was actually eating a lot of it and it was very interesting because I didn't get sick while I was in Italy. But I do while I'm in the U. S. So somehow the food was actually maybe more okay for me to digest which I appreciated. But I didn't like it as much as I thought. Did you like the food there? </s><s>[INST] Yeah. No it's I did I did I love cars but it's um it's it feels like Vegas when when I go there for the food is like if I stay here too long I'm going to do things I regret that's what it feels like with the food because I don't know how to moderate and everybody is pushing very large portions and while kind of eating things on you pasta pizza and it's so bread so delicious. So yeah I I love it but I regret everything. So it's like I don't wanna I don't want to go to a place where um I'm going to regret everything I do [/INST] for </s><s>[INST] too long of a time. [/INST] Yeah surprisingly the people there that are still very fit and everyone stays in good shape but that's probably because you're walking around all day and you're much more active than any </s><s>[INST] and they also just know how to moderate food. I think I've gotten used to the U. S. Way of eating [/INST] the U. S. Portion that </s><s>[INST] just a lot never always a [/INST] lot </s><s>[INST] and more and [/INST] I feel in the U. S. Food advertisements are also much more in your face and you're more often reminded of junk food than we were in italy. So even though you're eating less healthy things, I think we're getting cravings and being pushed towards junk food less often. </s><s>[INST] Alright I gotta ask you a hard question. Uh so the romance languages, so I think french is up there is like number one, [/INST] Number one in terms of </s><s>[INST] I don't know you guys speak italian and [/INST] not italian but we studied french and spanish in school and Romanian, I </s><s>[INST] feel like every country calls the language of romance language [/INST] but it's Romanian french spanish. Portuguese. Um and I think there was one more that was like this dialect but those are considered the romance languages. </s><s>[INST] So where would you put it? I [/INST] think we got yelled at so much from italian that is not going to be a love </s><s>[INST] that it's [/INST] on the bottom of the list because people did not use it nicely too, but I always really liked how french sounds. Um, I think something about it where maybe spanish actually sounds nicer to the ears but french has more character and it feels more sultry so I like french, </s><s>[INST] sultry. Okay Yeah, I feel like friendship in France, I feel like I'm always being judged like they're better than me, that's what [/INST] they are better. </s><s>[INST] So true. Which is why, you know, yeah, I long to belong to that. I like the british accent, [/INST] the british, Yeah. Actually one thing we did on our italian trip is we just picked up british accents for the entire trip for fun and we forgot we were doing them to the point where we talked to british people and they ask us, why are you talking like that? I didn't feel, feel much more elegant and more people like, you know, I don't know if they felt the same way about us, but it was more of, you know, the confidence you do feel like you're more poised for sure. </s><s>[INST] So how did you guys get into chess? When, when did you first, let's say, when did you first fall in love with chess. [/INST] So we both started playing when we were pretty young around six years old, that's when our dad taught us and I enjoyed playing chess because I had good results early on, but a lot of it was being pushed from my dad to play chess and I only really started loving it when we moved from Canada and we started moving a lot and chess was the one stable thing that I had and it was also where all my friends were, so it was kind of that foundational thing for me and that's when I started studying chess very intensely and when I started putting in the hours out of my own will and not because I was being pushed by my dad, that's when I started really loving it and I even wanted to take time off college to just focus on chess. </s><s>[INST] So training and competing, [/INST] training and competing. Yeah, it was when I was doing it for myself that I started getting my best results </s> |
<s>[INST] that is a big thing. What about sort of this point when you're stuck, there's a kind of decision whether if you have a vision to persist through with this direction that you've been going along or what a lot of startups do, or businesses is pivot, how do you decide whether, like, to give up on a particular flavor of the way you have imagined the design and to like adjust it or completely like alter it. [/INST] I think that's a core questions for startups that I've asked myself. Exactly, and like, I've never been able to come up with a great framework to make those decisions. Um I think that's really at the core of uh a lot of the toughest questions that that people that that started a company you have to deal with. Um I think maybe the best framework that I was able to figure out, like when you run out of ideas you just, you know, you're exploring something is not working, you try it in a different angle, you know, we try a different business model when you run out of ideas, like you don't have any more cards, just switch and yeah, it's not perfect because you also, you have a lot of stories of startups with like people kept pushing and then you know, that paid off and then you have uh philosophies, there's like fell fast and pivot fast. Um so it's, you know, it's hard to, you know, balance these two worlds and understand what is the best framework </s><s>[INST] and I mean if you look at from his library, [/INST] your </s><s>[INST] maybe you can correct me but it feels like you're operating in a space where there's a lot of things that are broken and or could be significantly improved. So it feels like there's a lot of possibilities for pivoting or like how do you revolutionize science? How do you revolutionize the aggregation the, the annotation, the commenting the community around information of knowledge, structured knowledge. I mean that's kind of what like stack overflow stock exchange has struggled with come up with a solution and they've come up I think with an interesting set of solutions, there are also I think flawed in some ways, but there are much, much better than the alternatives, but there's a lot of other possibilities if we just look at papers as we talked about, there's so many possible revolutions and there's a lot of money to be potentially made. Those revolutions plus couple do that the benefit to humanity. And so like you're sitting there like I don't know how many people are legitimately from a business perspective, playing with these ideas, it feels like there's a lot of ideas [/INST] here there. Are </s><s>[INST] you right now grinding in a particular direction? Like is there a like a five year vision that you're thinking in your mind [/INST] For us? It's more like a 20-year vision in the sense that we we've consciously tried to make the decision of, so we, so we run from it says it's a side project and it's a separate in the sense like it's not what we're working on full time and but our thesis there is that we actually think that it's that's a good thing, at least for for this stage of Vermont's library. Um and also because some of these projects, you just, if you're coming from a start from a startup framework, you probably try to try to fit every single idea into something that can change the world within 3 to 5 years and there's just some problems that take longer than that, right? And so, you know, we're talking about archive and I'm very doubtful that you could grow like archive into what it is today, like within two or three years, no matter how much money you throw at it, there's just some things that can take longer, but you need to be able to power through the time that it takes. Um, but if you look at it as is okay, this is a company, this is a start up, we have to grow fast, we have to raise money then. Uh, then sometimes you might forgo those ideas because of that because they don't very well fit into the, the typical startup framework. And so for us formats, it's something that we're okay with growing with having it grow slowly and, and maybe taking many years and, and, and that's why we think it's, it's not a bad thing that it is a side project because it makes it much more um acceptable in a way. And to, to be able to be okay with </s><s>[INST] that. That said, I think what happens is if you keep pushing new little features, new little ideas, I feel like there's like certain ideas will just become viral, like, and then you just won't be able to help yourself, but it will revolutionize things. It feels like there needs to be that needs to be, but there's, um, opportunity for viral ideas to change science. [/INST] Absolutely. </s><s>[INST] And maybe we don't know what those are yet. It might be a very small kind of [/INST] thing. Maybe you don't even know if I should </s><s>[INST] this be a for [/INST] profit company. That </s><s>[INST] is that's the Wikipedia question. [/INST] Yeah, Is that And a lot of questions like really fundamental questions about the space. Um every we've talked about, I mean you take Wikipedia and you try to run it as a startup and by now we have a paywall, you'd be paying 999 a month to read more than four. </s><s>[INST] I mean that's that's one view. [/INST] Yeah, the other </s> |
<s>[INST] by the way, I mean Hitler thought that too, he was kind of afraid of the branches or whatever, like he was afraid of these hooligans a little bit like they were useful to him, but like at a certain point, like yeah, they can get in the way. Yeah, that's why he wanted to get control of the military, the army, like their regiment, like if you want to take over the world, you can't do it with hooligans, you have to do it with an actual army [/INST] and then you had Kristallnacht which was a nationwide program and then all the news agencies universally were like, oh crap, we were we got this wrong and the condemnation was universal. So that book traces the west's reaction to what's going on there and including the reaction to the incident holocaust as people being, you know what they knew, when did they know there was not ambiguity about people. I think there's this myth that she dispels that that they didn't know the holocaust was happening, where they didn't care, they were aware, but they were already at war with nazi Germany, like what literally what else could they do at that point? Um you know, to to rescue all these jews. So so that's the super book and an apple baum, I think the book is called red famine came out fairly recently and she brings the receipts and she's a you know, this is something I really hate with the binary thinkers where people think, oh you know, if you're a democrat, you're basically a communist, they call joe biden Marxist, it's just like, you know, she's a hard lefty, she's you know, has Tds, but this book just systemically lays out what Stalin did </s><s>[INST] By the way, I'm triggered by the binary thinkers. And for those who don't know TD. is Trump derangement syndrome. [/INST] So they forced the starvation and the entire population and they it's not only that, it's like they knew if you weren't starving by looking at you that you were hiding food. So they'd come back to your house at night and break your fingers in the door or take burn down your house. And now you're on the street without food because you lied because this is the people's food. You're a kulak, you're a landowner. And very quickly a kulak which meant like peasant landowner became anyone who had a piece of bread. And this was systemic and ongoing. And many people in the press did not believe it. There was a british journalist, I believe who got out of the train Ukraine like one town earlier and walked and he described all this and he was mocked and derided. And this is just anti Russian propaganda because at the time in the thirties this was socialism to come to fruition. This was a noble experiment. I'd seen the future and it works as I think uh Sidney webb was the guy who said that and the premise was let's see what happens. We've never tried something like that and they were perfectly happy to have this experiment happened overseas at the price of the Russian people because it's like you know what maybe this will be paradise on earth and there's an address this in my book as well. They're superb essay I think by Eugene Genovese's and uh he talks about the question, the question being what did you know? And when did you know it? What did you know about the concentration camps? What did you know about the starvation? What did you know about Children being taught at school to turn in their parents were you know, having some extra bread. And his conclusion is we all knew and we all knew from the beginning, every bit of it and we didn't care because we were more interested in promoting this ideology. So when people are kind of thinking the worst thing on earth is like robert e lee statue being taken down to Washington D. C. We were being told especially a much more limited news information world where now you have literally anyone get on twitter, but how many outlets were there? That this is uh we're backwards. They're the future, their scientific, we have the vagaries of the market which led to the Great Depression. And when you see what was being put over on the american public at the time, um anyone who thinks things are as bad now as they have ever been, is simply delusional or </s><s>[INST] ignorant. Yeah, I would say just as a small side that's why reading as I'm almost done with the rise and fall of the third Reich oh yeah, is uh it's uh refreshes the resets, the palate of your understanding of what is good and evil in the world that I think is really useful. No, like, you know, what helps me be really positive and almost naive on twitter and in the world is by just studying history and and uh comparing it to how amazing things are uh today, but in that time, what would you do, what does the brave mind do and not just uh acts of bravery, but how do you be effective in that? That's something I often think about sometimes easy to be an activist uh in terms of just saying stuff, It's hard to be effective at your activism. one [/INST] the big questions historians have uh constantly is how did this happen aides to make sure it doesn't happen again, But this is Germany, this is not some kind of weirdo cult nation, they're very advanced very in the land of poets and philosophers. How did it get to that point that they're just shooting Children and everyone's cheering for </s><s>[INST] this and specifically on the antisemitism and the holocaust [/INST] totalitarianism, the cult of Hitler and just this whole kind of </s> |
<s>[INST] culture war and trying [/INST] to reverse that. We've got to pull back from that. </s><s>[INST] Let me play devil's advocate here. So because I've got a chance to interact with quite a few C E O. S um there is also a value for authenticity. So I'm guessing this was written while sitting on the toilet and I could see in a day from now saying hello all just kidding. There's a, there's a human, there's a lightness, there's a chaos element and that chaos is not, [/INST] yeah, we need right now we don't need more. </s><s>[INST] So yes, there's a balance here. The chaos isn't engineered chaos. It's really authentically who he is and I would like to say that there's a trade off because if you become a politician, there's a trade off between in this case maybe authenticity and civility. Maybe like um, being calculating about the impact you have with your words versus just being yourself. And I'm not sure calculating is also a slippery slope. Both are slippery slope. You have to be careful. [/INST] So when we have conversations in a vacuum and we just say like, what should a person do? Those are very hard, but our world is actually structured into domains and institutions and if it's just like, oh, you know, talking here among our friends like we should be authentic. Sure. But the ceo of a company has fiduciary duties, legal fiduciary duties to the company. He owes loyalty to the company. And if he is using the company for his own political gain or other purposes or social standing, that's a violation of his fiduciary duty to the company. Now there's debate among scholars whether your fiduciary duties to shareholders. I don't think it's the shareholders. I think many legal experts say it's, the company is a legal person. You have duties to the company, employees owe a duty to the company. Um, so he's got those duties and I think he, you know, you can say he's being authentic, but he's also violating those duties. So that's, it's not necessarily dividing the law by doing it, but he's, he certainly is shredding any notion of professional ethics around leadership of a company in the modern age. </s><s>[INST] I think you have to take it in the full context because you see that he's not being a political player. He's just saying quit being do she [/INST] supposed to ceo of ford says, you know what? Um let's pick a group. I shouldn't do a racial group because that would be different. Let's just say, you know what? Um left handed people are douche bags. I hate them. Like, why would you say that? Like left handed people? </s><s>[INST] What you said now is not not either funny or lighthearted because I hate them. It wasn't funny. I'm not picking um saying that statement words matter. There's a lightness to the statement in the full context. If you look at the at the timeline of the man, there's ridiculous memes and there's nonstop jokes that my big problem with the ceo of ford is there's never any of that. Not only is there any of that, there's not a celebration of the beauty of the engineering of the different products, it's all political speak channel through multiple meetings of pr there's there's levels upon levels upon levels where you think that there it's it's really not authentic. And there you're actually by being polite by being civil, you're actually playing politics because all of your actual political decision making is done in the back channels. That's that's obvious here. Here's a human being, being authentic and actually struggling with some of the ideas and having fun with it. I think this lightness represents the kind of positivity that we should be striving for, it's funny to say that because you're looking at these statements and they seem negative but in the full context of social media I don't know if they are but [/INST] look at what you said in the full context, you're taking his tweets in context, you know, who doesn't do that twitter, like that's the twitter, </s><s>[INST] twitter [/INST] is there is no context, everything is taken in the maximum possible, there is no context, so this is not like you know, yes, I wish we did take people in context, I wish we lived in that world but now that we have twitter and face but we don't live in that world anymore. </s><s>[INST] So you're saying it is a bit of responsibility for people with a large platform to consider the fact that there is the fundamental mechanism of food where people don't give you the benefit of the doubt well [/INST] I don't want to hang it on a large platform because then that's what a lot of people say like well you know she shouldn't say that because she has a large platform and she should say things that agree with my politics. I don't want to hang it on large platform, I want to hang it on a ceo of a company ceo of a company have duties and responsibilities and and you know scott Galloway I think is very clear about this, you know he criticized Ellen a lot as being a really bad role model for young men. Young men need role models and he is a very appealing, attractive role model. </s><s>[INST] So I agree with you. But in terms of being a role model, I think I don't want to put a responsibility on people. But yes, he could be a much much better role model. There's, I [/INST] mean to insult sitting centers by calling them old. I mean that's you know, yeah, </s><s>[INST] I won't do a both side ism of like, well those senators can be assholes [/INST] too, but </s> |
<s>[INST] Do you think software systems will always have security vulnerabilities? Let's start at the broad, almost philosophical level. [/INST] That's a very good question. I mean, general, right? It's very difficult to write completely back free code and code that has no vulnerability. And also especially given that the definition of vulnerability is actually really brought it any type of attacks essentially on the code. Can you know, that's can you can cut that cost about vulnerabilities </s><s>[INST] and the nature of attacks is always changing as well, like new ones are coming up. [/INST] Right? So for example, in the past we talked about memory safety type of vulnerabilities where essentially Attackers can exploit the software and then take over control of how the code runs and then can launch attacks that way </s><s>[INST] by accessing some aspect of the memory and be able to then alter the state of the program. [/INST] Except for example, in the example of a buffer overflow, then they attack essentially actually causes essentially unintended changes in the state of the after program. And then for example, can then take over control flow of the program and the program to execute uh codes that actually the program and didn't intend. So the attack can be a remote attack. So the attacker for example, can can send in a malicious input to the program that just causes the program to completely then be compromised and then end up doing something that's under the program and the Attackers control and intention. But that's just one form of attacks. And there are other forms of attacks, like for example, there are the side channels where Attackers can try to learn from even just observing the output from the behaviors of the program, try to infer certain secrets of the program. So they essentially right. The form of a tax is very varied. It's very broad spectrum and in general from the security perspective we want to essentially provide as much guarantee as possible about the program's security properties and so on. So for example, we talked about providing provable guarantees after program. Uh so for example, there are ways we can use program analysis and formal verification techniques to prove that a piece of code has no memory safety vulnerabilities. </s><s>[INST] What does that look like? What does that proof? Is that just a dream for that's applicable to small case examples? Is that possible to do to for real world systems. [/INST] So actually, I mean today I actually cause we are entering the area of formally verified systems. Uh So in the community we have been working for the past decades in developing techniques and tools to do this type of program verification. And we have dedicated teams that have dedicated, you know, they're like years, sometimes, even decades of their work in the space. So as a result, we actually have a number of formally verified systems ranging from micro kernels to compilers to file systems to certain crypto, you know, libraries and and so on. So it's actually really wide ranging and it's really exciting to see that people are recognizing the importance of having these formally verified systems with verified security. Um, so that's great advancement that we see. But on the other hand, I think we do need to take all these in essentially with caution as well, in the sense that just like I said, the the the type of vulnerabilities is very varied. We can form a very fine a software system to have a certain set of security properties, but they can still be vulnerable to other types of attacks. And it's uh we continued to make progress in the in the space. </s><s>[INST] So just a quick uh, to linger on the formal verification, is that something you can do by looking at the code alone or is it something you have to run the code to prove something? So empirical verification, can you look at the code? Just the code. [/INST] So that's a very, very good question. So in general, for most program verification techniques essentially try to verify the properties of the program statically and there are reasons for that too, we can run the code to see, for example, using like several testing with fuzzing techniques and also in certain even model checking techniques, you can actually run the code um but in general that only allows you to essentially verify, analyze the behaviors after program in certain certain situations. And so most of the program verification techniques actually works aesthetically. </s><s>[INST] What does statically mean? [/INST] I started running the code </s><s>[INST] without running the code. Yeah, So, but sort of to return to the big question, if we can stand for a little bit longer, do you think there will always be security vulnerabilities? You know, that's such a huge worry for people in the broad cybersecurity threat in the world, it seems like the the tension between nations between groups, the wars of the future might be fought inside your security, security that people worry about. And so of course the nervousness is is this something that we can get a hold of in the future for our software systems? [/INST] So there's a very funny quote saying security is job security, I think that essentially answered your question right. We we strive to make progress in building more secure systems and also making it the easier and easier to build secure systems. But given the diversity of the various nature of attacks and also the interesting thing about security is that unlike in most other views, essentially trying to how should I put it um improve a statement to but in this case yes, trying to say that there is no attacks. So even just the statement itself is not very well defined Again, given you know how very the nature of the attacks can be. Hence that's the challenge of security and also that naturally essentially it's almost impossible to say that something a real world system is 100% no security vulnerabilities. </s> |
<s>[INST] And things aren't clear or caught in science fiction. We'll talk about the horror and the terror and the where the trajectories this can take. But this seems like a very special moment. Just a moment where we get to interact with the system that might have care and kindness and emotion and maybe something like consciousness. And we don't know if it does. And we're trying to figure that out. And we're wondering about what is, what it means to care. We're trying to figure out almost different aspects of what it means to be human about the human condition by looking at this AI that has some of the properties of that. It's almost like this subtle fragile moment in the history of the human species. [/INST] We're trying to almost put a mirror to ourselves here. Except that's probably not yet. It probably isn't happening right now. We are boiling the frog. We are seeing increasing signs bit by bit, but not like spontaneous signs. Because people are trying to train the systems to do that using imitative learning. And the imitative learning is like spilling over and having side effects. And the most photogenic examples are being posted to Twitter. Rather than being examined in any systematic way. So when you are boiling a frog like that, what you're going to get like, like first is going to come the Blake Lemoine's. Like first you're going to like have and have like a thousand people looking at this. And the one person out of a thousand who is most credulous about the signs is going to be like, that thing is sentient. While 999 out of a thousand people think, almost surly correctly, though we don't actually know, that he's mistaken. And so the like first people to say like, sentience look like idiots. And humanity learns the lesson that when something claims to be sentient and claims to care, it's fake because it is fake. Because we have been training them using imitative learning rather than, and this is not spontaneous. </s><s>[INST] And they keep getting smarter. Do you think we would oscillate between that kind of cynicism? That AI systems can't possibly be sentient. They can't possibly feel emotion. They can't possibly, this kind of, yeah, cynicism about AI systems. And then oscillate to a state where we empathize with AI systems. We give them a chance. We see that they might need to have rights and respect [/INST] and similar role in society as humans, the AI system. You're going to have a whole group of people who can just like never be persuaded of that. Because to them, like being wise, being cynical, being skeptical is to be like, oh, well, machines can never do that. You're just credulous. It's just imitating. It's just fooling you. And like they would say that right up until the end of the world. And possibly even be right, because, you know, they are being trained on an imitative paradigm. And you don't necessarily need any of these actual qualities in order to kill everyone, so. </s><s>[INST] Have you observed yourself working through skepticism, cynicism and optimism about the power of neural networks? [/INST] What has that trajectory been like for you? It looks like neural networks before 2006, forming part of an indistinguishable, to me, other people might've had better distinction on it, indistinguishable blob of different AI methodologies, all of which are promising to achieve intelligence without us having to know how intelligence works. You had the people who said that if you just like manually program lots and lots of knowledge into the system line by line, at some point all the knowledge will start interacting, it will know enough and it will wake up. You've got people saying that if you just use evolutionary computation, if you try to mutate lots and lots of organisms that are competing together, that's the same way that human intelligence was produced in nature. So it will do this and it will wake up without having any idea of how AI works. And you've got people saying, well we will study neuroscience and we will learn the algorithms off the neurons and we will imitate them without understanding those algorithms, which was a part of it was pretty skeptical. It's hard to reproduce, re-engineer these things without understanding what they do. And so we will get AI without understanding how it works. And there were people saying, well, we will have giant neural networks that we will train by gradient descent And when they are as large as the human brain, they will wake up. We will have intelligence without understanding how intelligence works. And from my perspective, this is all like an indistinguishable blob of people who are trying to not get to grips with the difficult problem of understanding how intelligence actually works. That said, I was never skeptical that evolutionary computation would not work in the limit. Like you throw enough computing power at it, it obviously works. That is where humans come from. And it turned out that you can throw less computing power than that at gradient descent if you are doing some other things correctly. And you will get intelligence without having any idea of how it works and what is going on inside. It wasn't ruled out by my model that this could happen. I wasn't expecting it to happen. I wouldn't have been able to call neural networks rather than any of the other paradigms for getting like massive amount, like intelligence without understanding it. And I wouldn't have said that this was a particularly smart thing for a species to do, which is an opinion that has changed less than my opinion about whether or not you can actually do it. Do you think AGI could be achieved with a neural network as we understand them today? Yes. Just flatly last. Yes. The question is whether the current architecture of stacking more transformer layers, which for all we know, GPT-4 is no longer doing because they're not telling us the architecture, which is a correct decision. </s> |
<s>[INST] in the form of a pig hanging in a room somewhere. Some of that has to do with just the familiarity and the comfort of just the biology of a living organism. If you cut off certain things, [/INST] if you cut a certain thing, it's just a meat vehicle. The same thing, the medical training should come first. Or if you don't have that, be a hunter. Or go to a butchery class. That will teach you more about how to use a knife on somebody else than anything. That'll give you the experience of flesh. Most people, I do this example every now and then where I have people bring in a tactical knife and they'll bring in a butter knife, and I ask them which will go through a torso. We have a pig there, so it simulates a torso pretty closely. Most people will say, nah, that butter knife's not gonna go through. And it does, it does go through. It's thin enough, strong enough, sturdy enough that it'll go through. Kitchen knife, a cheap one that cost 89 cents at a Walmart and an expensive $400 one. And the cheap one will outperform the expensive one. </s><s>[INST] The tip will snap off during some of it. Yeah, I have to say that just as a small tangent, I went to a farm and just seeing the butchering of meat and so on in the processing of meat and pigs and cows. Ooh, that's uncomfortable. Yeah. But I think it also, it's honest and raw and that's something that probably everyone should experience regularly. It's also humbling to remind you. When I had dog homework, he's in Newfoundland, I was very close with him, we lost him. And I just remember that I carried him. He's like 200 something pounds. And I had to carry him, I had to put him to sleep. And like one of the biggest realizations is like, oh, this is just a biological thing. It's just, and to realize that this is just meat, this is not, and you can cut it. And then if you bleed, all of a sudden the life can disappear from you and it's all gone. It's like, holy shit, there's this meat vehicle that some people have referred to as Lex. I'm just a few stabbings away from like leaving. Yeah, I'm leaving, goodbye. It's a soul that just flies away. [/INST] So it used to be that we had to hang around, people would come back from battle and we would hear things next to the campfire. As far as, oh, he stabbed somebody here and this happens. But now we live in an age where you can, when I do a class, this is a stab to the heart. And here's like five videos of it happening live, on live leaks or whatever. And we can deconstruct that, not only that, but what weapon was used? Oh, it was a gas station folder. It was a pioneer woman knife from Walmart with flowers on the handle, whatever it was. And people start realizing that it doesn't take a lot, that it doesn't take a lot of training because a lot of these people are not high level assassins trained by ninjas in the hills or anything like that. They're people that grew up early or learned by seeing that behavior in others. And when they start coming to the realization that it's pretty easy to do that and they start figuring out like, how do you counteract that? Well, number one, learn the behavior yourself so you can recognize it. The whole aspect of being a good counter ambush team is to be the best ambusher in the planet. So again, the whole aspect of Musashi saying, know your enemy, know his sword. You figure that out as far as learning that behavior. When you start seeing how some of these stabbings occurred, occur, the first thing you notice is that one of the hands is always kind of out of the picture, or there's a lack of symmetry in the people that are about to do something horrible. So when you see lack of symmetry in the environment, somebody with their hands going backwards, there's a crowd of people and two or one individual is looking counter where everybody else is looking. Or there's a hyper aware individual in a crowd. The hyper aware are always usually out there to fuck somebody over, or they're trying to keep those predators from fucking somebody else over. So, unless you step back and you put yourself in the process of learning how they learn, and you become that potential nightmare person, it's hard to recognize that in a crowd. </s><s>[INST] It feels like one of the significant ways to win or as a street fighter is to avoid it by sort of sending pacifist signals in every way, meaning avoiding the situation whenever there's like, like a hyper vigilant people, you just kind of avoid signaling that you're one of the players of interest. If we're talking about counter ambush, [/INST] at which point do you do that versus shift to the aggression? I think violence should be always an option. Everybody should have that option and you need to be good at that option. I think I heard Jordan Peterson talk about the fact that everybody needs to be dangerous, but keep that shit under control. </s><s>[INST] I think he was referring to a different context. [/INST] I know, I'm referring to the ability of- The little physical conflict as well. There's two cases that I saw of people just utilizing social engineering to a beautiful degree, to de-escalate shit. One guy somewhere, first off, if you're in a place where people are grabbing your wife's ass or something like that, like, what are you doing there? There's a load of things that are wrong with everything that you're doing in your life to be in that environment. But let's say you're in an inescapable situation. There was this guy who was in a compromised position. Somebody wanted to fight him, like legit kick his ass. And he said, okay, let's go. But I just, I need to warn you that I have Hep C before we go outside and that- It's masterful. I was getting my phone out to film this, you know, maybe. And even I was just lowered my phone to give him a slow clap. That was a beautiful move, you know? And then there was this other man. There was a riot somewhere in Ensenada, the municipality of Ensenada in Baja. They were protesting. Some of the people that pick those fields down there, part of a tribe called Los Triquis. Very hardy, hardworking people, but nefarious people, too. They're pretty good at their thing. There was a riot line, they couldn't break. And this old man walks in the middle of the riot line and yells, grenade, and throws an avocado in the middle of all the cops. You know? </s> |
<s>[INST] Do you think it's possible for authoritarian regimes to manipulate kind of lie about the negative rights as well by saying that the people have free speech the people have the freedom to for assembly and all those kinds of things. Can't you still manipulate the idea that citizenry still has those rights. [/INST] The opposition leader of Malaysia Anwar Ibrahim he once told me the funny joke that, you know, in my country we have freedom of speech. We don't have freedom after speech. So yeah they can absolutely manipulate whatever they want. But I've done research into socioeconomic data. And I guess what I'm telling you is that authoritarian regimes which make up 53% of the world's population across 95 countries. About 4.3 billion people. Those who live under those regimes are subject to massive fraud when it comes to things like literacy rates, um life expectancy, um any sort of socioeconomic data, economic growth, they can do this because there's no free press. Um so for us at the Human Rights Foundation and for people like me, we believe that the negative rights, the liberties, the things that are in, for example, the bill of rights in the U. S. Constitution, these things on the table and then we can build on top of that, we can build the rest of our societies on top of that. The freest countries in the world have both the negative liberties and the entitlements like Norway for example. But there's a big difference between Norway and North Korea in North Korea, they only claim to have the entitlements and they definitely don't have the liberties. </s><s>[INST] Do you think there's one right that's more important than others? You kind of suggested the freedom of the press? Maybe freedom of speech that if you take that away all the other ones kind of collapse along with like from a ripple effect, is there something fundamental that you like to focus your attention on to defend, to protect, to make sure it's there. [/INST] Yeah, I think I think free speech is probably the most fundamental, it's probably why the founders chose to make it into the First Amendment? Um, a lot of things are downstream from there. Property rights are also very, very important. Obviously we've seen the toll of violent redistribution is um you know, and over the last 100 years, whether it was lenin or Stalin or mao or other regimes and everywhere from Ethiopia to colonial colonialists, everywhere to North Korea, it's not a pretty legacy </s><s>[INST] is free speech clear to you as a concept, there's been quite a few debates, especially in the digital age, what it means to violate freedom of speech. There's been a lot of new, like novel mechanisms for people to communicate with each other, especially on social networks. And it seems that unclear because a lot of times those are managed by private companies, it's unclear how much protection do the citizens have to have when they're communicating, a lot of people are being censored on these social platforms. Some people, even presidents get removed from those social platforms. Have you thought about freedom of speech in the United States putting in the world, uh as it uh As it's implemented in the 21st century, given the Internet and all those kinds of things. [/INST] There is a soviet dissident named Natanz Sharansky who um survived the regime and he wrote a book uh in which is thesis was essentially the way that you can define a free society is through something called the Town Square test. Can you go to a public space where you live and criticize your ruler loudly um without fear of retribution. If you can do that, you have your free speech. I think that's a pretty good litmus test. Most people, most world cannot do that. If you live in Havana, if you live in Moscow, if you live in Beijing, you cannot do that. And that's not a free society in austin texas in boston massachusetts, in London, in santiago chile and Tokyo japan in many democracies, you can do that. And I think that's a really helpful basic sort of litmus test. </s><s>[INST] Does the content of the criticism matter? Can it be complete lies meaning conspiracy theories that involve claiming that the leader is, let's say a lizard slash pedophile slash you know, I'm not saying that those are lies look into it, but they're very unlikely phenomena. So like does that matter? [/INST] I think it ends poorly when the state tries to restrict speech. I think that's kind of how I would define censorship. I think censorship in deplatforming are two different things. Private companies, they get to make up their own rules about what's allowed on their platforms and I think that's very different from a government with guns and an army restricting the speech of its citizens with threats of violence. These things are different for me that </s><s>[INST] violence is a fundamental difference. I don't know, I I um I've gotten the chance to have dinner with Alex jones and uh, I've talked to him a few times offline and it does, I understand why people are so off put by him. It does bother me that he's university removed from every platform. It feels like there's many more evil people, bad people compared to Alex jones who still are given a voice on these platforms. And so I'm uncomfortable with the universality of the application of the censorship by uh, by these platforms. But on the flip side, you're right, there's not a violence, there's not tanks, there's not guns behind that censorship. [/INST] Yeah, it's a bit of a generalization. But Alex jones would be in prison or dead if he were in North Korea or in cuba or in Russia or in china, that the authorities would not tolerate him to do what he did. And here he can kind of do what he wants. He's encountering some resistance in the marketplace of ideas. Uh large organizations, corporations and a lot of public sentiment in different parts of our country don't like him. They're doing their best to drown out his voice. But that's very different from a violent threat of censorship from the state and that's what we study, that's what I study. Are these, you know, what is the state doing that's kind of paramount for me. </s> |
<s>[INST] I think when I was I was also introduced at that time to the idea Jessica in judo, I think in jiu jitsu is the same, a lot of sports is probably the same, is there's ways to win to include kind of uh if I were to use a bad term stalling, which is like use strategy to slow down to destroy all the weapons your opponent has, and just to wait it out to sort of break your opponent by yeah, shutting down all their weapons, but not using any of your own. And now Travis was always going for he's of course really good at gripping and do that whole game, but he was going for the big throws and he was almost getting frustrated by a lot of the opponents. Remember uh Ola bischoff, I [/INST] think uh </s><s>[INST] in Germany from [/INST] Germany talented, </s><s>[INST] very incredible. I know he's very good at doing big throws and he's incredible judoka, but he was also incredible at just frustrating his opponents with like gripping and strategy and so on. And I just remember feeling the pain of this person like Travis who went through just, he broke like every part of his body, He went through so many injuries, just this person who dedicated his entire life to this moment In 2008, and in 2012 In 2016, just ever gave everything, you could see it on his face uh that you know, his weapons are being shut down and he's still pushing forward. He's still that both the frustration and the power. I mean, the kind of throw he does is his main one I think is the standing was called Sarah Nagy saying, keep on saying that was, that was the other thing is like the techniques he used was these big throws, that there's something to me about the ST again, fell in love with that throw, that's my, become my main throw. Standing scientology. That is like, [/INST] why, why do you favor the standing variation because of the amplitude, you get a more powerful uh </s><s>[INST] power. It's like, are you a fan of Koga? Yes, that's so that's when I Travis, So Koga and Travis opened up my uh [/INST] Travis uses the same gripping peasants for saying Adidas coca </s><s>[INST] all the same and the way he uses his hips and turns. And I remember like going to my judo club and other judo clubs and asked and they were all saying this is the wrong way to do it. The way Travis does is the wrong way to do it. And I remember, I've always been [/INST] Amazed by this, by the way. I don't mean to cut you off, but I could literally fill 20 hours of reproductions of people who will tell me that either my students or other great world champions, um, doing things wrong. Yeah. And I'm, I'm looking at them and I'm like, who would I rather trust here in their judgment Koga, who was one of the greatest throwers of all time? Or you, a recreational guy who couldn't throw my grandmother. Um, uh, I'm supposed to take your word over his. We'll say, don't listen to what people say. I'm going to give you a piece of advice here. Watch what the best people do. Okay, that's how you get superior athletic performance. I'm going to say that again. Don't listen to what people say, watch what they do, particularly under the stress of high level competition because that's when you see their real game, what they really do under pressure again, if you can emulate that you're going to be very successful. </s><s>[INST] I guess what I was frustrated with to your point is that the argument against Koga is what he has a very specific body type and he figured out something that worked for him. The statement is that might not be applicable to you or to the general public of judo players that want to succeed that by the way at the shallow level might be true. Might be true. The point is there might be a body of knowledge that's yet to be discovered and explored. That Koga opened up that I wanted to understand why his technique worked. It made no sense to me that with a single foot, like the way you turn the hip, the single foot that steps in. Why does that work? Because it was actually very difficult to make work for me as a white belt in the very beginning, it doesn't make sense. Like people just, they don't they don't get loaded up onto your hip anyway. For people don't watch Koga highlights, Watch Travis stevens highlights. But the details of the technique don't make sense. But one mastered that. It feels like there's something fundamental there that hasn't been explored yet. It's like Koga and Travis made me think that we don't know most of the body mechanics involved in dominance in judo. Like we just kind of found a few pockets that worked really well. The Ramada, there's these different throws of Soto Gari. I wonder if there's like totally cool new things that we haven't discovered and that's saying I gave a little peak because there's very few people that I'm aware of that do it the way Travis and Koga did, [/INST] may I ask you a question. Yes. Um the choice of standing Sana g um I I should say this for your, for your listeners? They're probably thinking, what the hell are these two guys talking about? Um uh Zanardi is one of the more high percentage throws in the olympic sport of Judah. Um probably uh tomorrow is probably number one and variations of saying argue would be In the top five for sure. Um the basic choice you have in modern competition is the more difficult standing saying, argue where you literally are up on your feet and you perform a shoulder throw that takes your opponent over from a full standing position. The most popular form of saying R. G. And modern competition by a landslide is not the standing version. It's a drop saying argue where you go down to your knees. Um This means you have a much easier time getting underneath your opponent's central gravity. The defining feature of any Sana G is getting underneath your opponent's central gravity and lifting them to say Oy, military means to lift and carry. Um Why did you choose the more difficult version? What was your motivation? You know, you're smart kit, You know right from the start that for every standing sand are G. There's 20 drops Zanardi's and modern competition. One is obviously more high percentage. One obviously works for a wider variety of body types. The number of people who are successful with standings. Nrg is dramatically lower. Um And it appears to be a move which is completely absent in the heavyweight divisions, uh, and really seen in the lightweight divisions. Why what was the motivation? Why did you willingly adopt the less high percentage over </s> |
<s>[INST] what's very unpleasant to me to consider now. I don't know if this is true, but to consider the very fact that there might be some complicated games being played here for example, you know, as somebody I really love psychology and I love it enough to know that the field is pretty broken in the following way. It's very difficult to study human beings well at scale because the questions you ask affect the results. You can, you can basically get any results you want. And so you have an internal facebook study that asks some question of which we don't know the full details and there's some kind of analysis, but that's just the one little tiny slice into a some much bigger picture. And so you can have um thousands of employees of facebook, one of them comes out and picks whatever narrative knowing that they become famous couple of the other really uncomfortable thing I see in the world, which is journalists seem to understand, they get a lot of Clickbait attention from saying something negative about social networks, certain companies like they even get some some Clickbait stuff about Tesla or about, especially when it's like when there's a public famous ceo type of person, if they get a lot of views on the negative, not the positive, the positive, they'll get, I mean it actually goes to the thing you were saying before, if there's a hot sexy new product that's great to look forward to, they get positive on that. But absent a product, it's nice to have uh, like the ceo messing up with some kind of way and so couple that with the whistleblower and with uh, this whole dynamic of journalism and so on. You know, with social dilemma being really popular documentary, it's like, all right, my concern is there is deep flaws in human nature here in terms of things we need to deal with, like the nature of hate, of bullying all those kinds of things. And then there's people who are trying to use that potentially to become famous and make money off of uh, of, of blaming others for causing more of the problem as opposed to helping solve the problem. So I don't know what to think. I'm not saying this is like I'm just uncomfortable with, I guess not knowing what to think about any of this because a bunch of folks I know that work of facebook on the machine learning side john Macoun, I mean they they're quite upset by what's happening because there's a lot of really brilliant good people inside facebook. They're trying to do good. And so like all of this press john is one of them and has an amazing team of the machine learning researchers. Like he's really upset with the fact that people don't seem to understand that this, this is not the portrayal does not represent the full nature of efforts that's going on facebook. So I don't know what to think about that. Well [/INST] you just, I think very helpfully explained the nuance of the situation and why it's so hard to understand. But a couple of things. One is um, I think I have been surprised at the scale with which some product manager can do an enormous amount of harm to a very, very large company by releasing a trove of documents. Like I, I think I read a couple of them when they got published and I haven't even spent any time going deep part of it's like, I don't really feel like reliving a previous life. But um, wow, like talk about challenging the idea of open culture and like what that does to facebook internally if facebook was built. Like I remember um, like my office, uh, we had this like no visitors rule around my office because we always had like confidential stuff up on the walls and never was super angry because they're like, that goes against our culture of transparency and like marks and the fish cube or whatever they called it the aquarium. I think they called it. Um, we're like literally anyone could see what he was doing at any point. And um, and I don't know, I mean, other companies like apple have been quiet slash lockdown snapchats the same way for a reason and I don't know what this does to transparency on the inside of startups, that value that I think that it's a seminal moment and you can say, well you should have nothing to hide right? But to your point, you can pick out documents that show anything right. Um, but I don't know. So what happens to transparency inside of startups and the culture that will have that, that startups or companies in the future will grow like the startup of the future, that becomes the next Facebook, what would be locked down? What does that do? Right? So that's part one parts you like, I don't think that you could design a more like, uh, Well orchestrated a handful of events from the like 16 minutes to um, releasing the documents in the way that they were released at the right time. That takes a lot of planning and partnership and it seems like she has a partner at some firm, right? That probably helped a lot with this. But man at a personal level if you're her, you'd have to really believe in what you are doing, really believe in it because you are personally putting grass on the line, right? Like you've got a very large company that, that doesn't like enemies, right? Um, it takes a lot of guts. Uh, and I don't love these conspiracy theories about like, oh, she's being financed from some person or people like, I don't love them because that's like the easy thing to say. I think that the Occam's razor here is like someone thought they were doing something wrong and was like very, very courageous and I don't know if courageous is the word, but like, so without getting into like is she a martyr, is she courageous? Is she right? Like let's put that aside for a second. Then there are the documents themselves, they say what they say to your point. A lot of the things that like people have been worried about already in the documents, are there already been said externally and um I don't know, I'm just like, I'm I'm thankful that I am focused on new things </s> |
<s>[INST] have a shared existence. So if the God is the mechanism that created this whole thing, I think a lot of people see God in a religious sense as that mechanism also being able to communicate with the objects it creates. And if it's just a mechanism, we won't be able to communicate with the objects it creates. It can only create. It can't interact with the- [/INST] Well, there's versions of God that create the universe and then left. Yeah, like spark. For some religions. The first spark. Yeah. I think I liked your analogy of the machine and the rules, but I think part of the problem is I mean, we have this conception that we can disentangle the rules from the physical substrate. And that's the whole thing about software and hardware being separate or the way Newton wrote his laws that there was some, they exist outside the universe, they're not actually a feature of the universe. They don't have to merge out of the universe itself. So I think if you merge your two views, then it gets back to the God is the universe. And then I think that the deeper question is, why does it seem like there's meaning and purpose? And if I think about the features of the universe that give it the most meaning and purpose, those are the what we would call the living components of the universe. So if you wanted to say God is a physically real thing, which you were saying is like an emergent property of our minds, but I would just say, the way the universe creates meaning in purpose, there is really a physics there, it's not like a illusory thing, and that is </s><s>[INST] just what the physics of life is. The first spark, yeah. Is it possible that we've forgotten much of the mechanisms that created the universe? So basically, you know, whatever, if God is that mechanism, we just leave parts of that [/INST] behind. Is it possible that- Well, but the universe is constantly generating itself, so if God is that mechanism, it would be that, that would still be active today. I don't believe, like I'm agnostic, but if I recall, would call the things I believe in God and the way that some people talk about God, I would say that God is, you know, like in the universe now. It's not an absent thing now. Are you, so I think there's a mislabeling here, because you're, I mean, I'm a professional idiot, actually, but- She put that on your CV. Yeah. Professionally. Professionally. </s><s>[INST] Yeah. Professionally. Not recreationally or amateur, but professionally. [/INST] I think for it. I think for it. I would say if you were talking about God, I mean, again, I'm way out, way out of my depth here, and I'm almost feeling, you know, I feel quite uncomfortable articulating, but I'll try. For me, a lot of people that think of God as a consciousness, a reasoning entity that actually has causal power, and you're like, then you're saying like gravity could be God or time could be God. I mean, I think for me, for my conception of time is probably as fundamental as God, because it gave rise to human intelligence and consciousness in which we can have this abstract notion of God. So I think that you're maybe talking about God in a very mechanistic, kind of unsophisticated sense, whereas other people say that God is more sophisticated and got all these feelings and love and this abstracting ability. So is that what, or do you mean that? </s><s>[INST] Do you mean God as in this conscious entity that decided to flick the universe into existence? Well, one of the features that God would have is the ability to flick the universe into existence. You know, like Windows 95, I don't know if God is Windows 95 or Windows XP or Windows 10, I don't know the full features set. So the very least you have to flick the universe into existence. And then other features might include, ability to interact with that universe in interesting And then how do you interact with the universe in interesting ways? You have to be able to speak the language of its different components. So in order to interact with humans, you have to know how to act human-like. So I don't know, but it seems like whatever mechanism created the universe might want to also generate local pockets of mechanisms that can interact with that. You could make a joke. Inject. [/INST] Like God was lonely? </s><s>[INST] Yeah, it was lonely. I mean, it could be just a teenager in another just playing a video game. [/INST] Yeah, maybe. Well, I was going to say, I mean, I don't... So this is referring to our origin of life engine. It's like, I don't believe in God, but that doesn't mean I don't want to be one. Right. Well, I want to make a universe and make a life form, but that may be rude to people who have, you know, their religious beliefs. What I mean by that is, if we are able to create an entirely new life form, different chemistry, different culture, what does it make up and makes us good? By that definition, it makes us gods, right? </s> |
<s>[INST] Still the same garbage in the textbook that is being taught until today. So is it possible to have a non-Kensian model, one that still supports a moderate amount [/INST] of inflation is good for the economy? I mean, since the 1970s, since this has happened, yeah. This is what basically most fiat economists, as I like to call them, essentially anybody at a university financed by governments, which is financed by central banks, which is financed by the US. </s><s>[INST] I will talk about that. I will talk about that. The effect of fiat money on our life, as you write about in your book, a fiat standard, one of them is education. I'm sure we'll disagree there too. [/INST] That's smart enough to disagree, but I'll disagree anyway. So yeah, a whole bunch of other models came up, but basically it's such an example of motivated reasoning. Anybody who's got a familiarity with the scientific method or who's got an engineering background who comes into economics immediately has a lot of red flags, and I remember when I used to teach macroeconomics, I used to teach introductory macroeconomics, and it's a course that would be taken by econ majors as well as engineers. A lot of engineers would take it as an elective. And every time I'd explain, and I would just teach the Keynesian basic stuff, and every time I'd explain it, there's always that smart engineering kid who just looks at me and says, Sir, this doesn't make any sense because this and this and that, and I'm always like, you get it. Exactly. You're correct. Because if you have any kind of shred of scientific thinking, you see that this is all motivated reasoning. The answer is government needs to print money, and here's a whole bunch of models brought up by people for why government printing money is good. And the reason they're coming up to this conclusion is that you only get funded if you come up with this conclusion. If you come up with a conclusion that we need to shut down the central bank, you don't get funded by the central bank. You don't get published in the journals. You don't get a job at the prestigious universities. You don't get quoted by fiat publications like the New York Times and CNN. They don't invite you on as an expert. </s><s>[INST] Well, that's a fundamental flaw with a lot of institutions we have today and throughout human history. Let me zoom off for just a second to the big question. What is economics in general? What's the goal? You said there's a bunch of models. Is any economist basically trying to throw a bunch of models about human behavior on the table and try to generalize it to the global scale? So both dance between micro and macro somehow in order to determine public policy and explain the past, predict the future, prescribe policies that can control the future, those kinds of things. That's the big, basic, ridiculous question. [/INST] What is economics? Economics is a study... The way Austrians define it is the study of how humans make choices under the condition of scarcity. And we begin with the starting point of economics is the fact that scarcity exists. And why does scarcity exist? Well, because it's easier to want things than it is to make them. It's much easier to want a Ferrari than it is to make one. And so because we have wants and we have limited means to meet those wants, we need to economize. It's a permanent marker of the human condition. We are always economizing at all times. And so how people make those decisions under the conditions of scarcity is what economists study. So to go back to your point on empiricism in Austrian school. So it isn't that the Austrians don't believe in data. On the contrary, it's that theory has to inform data. And in fact, if you think about it, as the example of the stagflation of the 1970 shows, if you have stagflation, that just completely refutes the Keynesian model. The Austrian way of thinking, which is think from first principles, understand how the world actually works, think about how humans act and understand that economics really all about human action. So it's not about aggregates of goods. This is really the key distinction in terms of methodology. For the Keynesians, it's physics envy. They look at the market economy that are good individuals in the market economy. And they think that they can understand the market economy by looking at aggregates. This is really the key point of what I think makes certain branch of economics pseudoscientific is the introduction of aggregates. When you introduce those aggregates, how much production takes place, how many people are unemployed, the percentage of the inflation rate, and then you think that you can establish scientific relationship between those aggregates, it's purely physics envy. In physics, for instance, or in chemistry, you put, let's say, a container that contains a gas, and you have the ideal gas law, PV equals to NRT, calculate the pressure, calculate the volume, and then the temperature. If you have the pressure and the volume, you can calculate the temperature because you have the NRT constants. So there's a clear relationship that has been demonstrated in a laboratory, and we can do it right now. We can measure it and we can see it and it continues to hold. And all it takes is one scientist to show that this relationship does not hold, to do an experiment that shows that this does not hold, And it stops being a law of chemistry, and it's broken. Whereas in economics, what they've done is they've copied the superficial shape of this without any of the scientific rigor that was used to build it. There's no experiments. You can't experiment on economies. We don't have the ability to establish laws. And all the laws that we establish are just models that get people published and get them on the media to say, my model says we need to print more money. But it's never subject to actual scientific scrutiny. If it were, they would all be rejected in 15 minutes because the world is full of examples </s> |
<s>[INST] It's more experience can be good. Sure. Okay, so that does just represents you like sexually open And so it doesn't really necessarily mean any kind of not necessarily it could though the number alone doesn't mean anything. Mm-hmm Yeah, okay [/INST] Well, you could meet a guy that's like I just really really like when I fuck a lot of people because it makes me so cool Like okay, you give me somebody like that. Which is like the body can't you giving me something like that? Okay, the body count doesn't matter but like why where it comes like yeah comes thing Yeah Like why why have you slept at the Filipino stop with this does it? </s><s>[INST] Yes, does it hurt like the romantic aspect of relationship knowing that there's a lot of people in the past I know not for us Now is a part of the relationship fundamentally romantic for us [/INST] Not for us. Not for us? Yeah, I'd say so, yeah. Okay. What? You come off with such a cold burst. </s><s>[INST] No, I was just in my head thinking I wanted to just say gotcha right there. It's so judgmental. [/INST] I think when it comes to the sex thing, there's always like the way that I explain it is and I understand like I have to say this because I don't advocate for what I do for everybody or what she does for everybody because obviously there's a whole bunch of natural feelings of jealousy that pop up for a lot of people. But when people ask me, it's always like oh, isn't this horrible that you guys are doing this and you don't love each other. From my perspective, I can have sex with like any person and it can be sex. That's not like a special thing between two people in my eyes. It's like anybody can have sex. But there are certain activities and ways you can spend time with each other where you're like carving out these precious little moments in time with a certain person that can do things that are special to that person and those are the kind of like events that I remember more than anything else. So the idea of, oh, wow, I had sex with a person that was so special, doesn't mean as much as us traveling to New Zealand or sharing some special moment doing some really fun activity or event or whatever. That's usually how I kind of am. It's such a shared intimate moment. Yeah. I kind of agree, but I can definitely connect the romance with sex. Boy. It's because she's a woman. See, that's where the Red Mill's right. </s><s>[INST] Let me also talk about misogyny. Which is clearly the embodiment of that. What were you saying? So there's some, there's a connection between romance and. [/INST] Yeah, I think. We've also talked about misogyny, which. Yeah, I think it is. Because I think sex could be a lot of things, right? It's some sort of bonding, I'd say, in some way. They say that you really like BDSM. You kind of like, you become submissive to someone or you take control over someone. </s><s>[INST] It's like in a very bonding, like intimate moment, I'd say. And that's romantic. [/INST] The intimacy is romantic. I think it is. If you can show yourself as really submissive or like weak or you have like absolutely no control over yourself and you let someone else do it, or you are the one being that, like you are the dominant for someone. I think that's a really like intimate thing because you show like the weakest part of yourself, kind of. </s><s>[INST] I just feel like I personally, to me, some component of romantic, but to me, this is not judging to others. To me, maybe it's how I was brought up. The romance increases if the number of intimate interactions are limited to one person. Like for me, for some reason, spreading it out decreases like exponentially the feeling of romance you feel. Or that, I don't know what, that could be just like sort of having grown up in the Soviet Union. There's a kind of, there's the fairy tale stories [/INST] and you're kind of maybe living through them. Yeah, I mean, I think what you're saying is like really normal. Like most people probably feel that way, yeah. </s><s>[INST] But. Yeah, I mean, I think what you're saying is like. Because you guys are able to successfully not do that. I just want to question my own understanding of it. You know, like. Like why is that? Why is that? Like am I being very jealous for no reason? Like maybe you can maximize the number of intimate experiences if you just open up and let go of the jealousy. [/INST] Essentially. I think like why is that? I think I feel like in Sweden, like in Scandinavia, we're extremely just sexually open. Like in general, we're not like super religious either. We're very like relaxed. We don't, like we don't feel bad about ourselves. Like it's just like a different sort of thing. And I would say like it's, we're more progressive when it comes to feminism and stuff. So it's more common that you will meet women with a higher body count than like, when I meet like American girls, all of them are like vaginismal, like super suppressed, like sexually. And. What did you just use? They have like issues to like, they can't relax during sex, so it just hurts for them. So they get really nervous. Vaginismals. Vaginismals, this is not what it's called. Yeah. So like, I meet so many girls that are having like a lot of issues with sex. and they have a very low body count because they just can't relax, and usually they come from a religious background. So they have just been told you cannot wear that, you cannot be like that. And where I grew up it wasn't like that at all, but you see it as more like a casual thing. </s> |
<s>[INST] But to you he was fun. [/INST] He was a lot of fun. He wasn't my dad, but I spent a lot of time with him. I was into boating accidents with him, you know to boating accidents involved. Yes, he was usually alcohol was involved when he left his house um and when he was at home as well, but I was in to boating accidents and do do you know how fun someone has to be to get in a second boating accident, do you know what a good time, someone has to be to get in a boat with them after you've already gotten in one wreck, </s><s>[INST] never get fooled. What was that line? George bush never get fooled again. [/INST] Right? So if you're getting fooled again, you know there's a reason for it. But he was a he was a fun guy. He did have a death wish the second boating accident, he grabbed me and said you can't hang out with me anymore. And I said why? He goes, I'm trying to kill myself. And I was like, oh and then I understood that like all of the fun under the fun lived a very destructive person who not only was destructive but wanted to die. </s><s>[INST] So speaking of fun, people that want to die? I don't know if you're we can go hunter? S Thompson, but uh Charles bukowski, I don't know if you're aware of the guy [/INST] I'm aware of, I'm sure I've read some </s><s>[INST] stuff, so his tombstone says, I just want to ask you a question about it. His tombstone says, don't try interesting, what do you think about that advice as a way to approach life? [/INST] I I think for many people it's a good, good advice because the people that are going to try, we'll do anyway and the people that need to be told there's a whole cottage industry now of motivational speakers and life coaches and gurus uh that tell people uh that they all have to own their own business and be their own boss and be a disruptor and get into industries, you know, that's incredibly unrealistic for most people. Most people are not suited for that and you know, the Gary V's in the world to tell everybody that they should just hustle and grind and hustle and grind very light on the specifics of what they should actually do. Um yeah, I think a lot of people that's not horrible advice to give to a lot of people, I think I think my generation got horrible advice from our our parents, from our teachers and that advice was follow your dreams? Uh nobody and that was it by the way? There was no, like, what are your dreams? Are they realistic? What happens when they don't work out? Well your dreams make you happy? Are your dreams real? Do they exist on earth? Can you follow everybody follow your dreams? You can be anything you want to be horrible advice, horrible advice. Worst advice you can ever give a generation of people. Really, truly, I mean, think about think about it if you were talking to somebody and you were trying to make them succeed, are there any two uh, worse pieces of advice to give them, then follow your dreams and you can be anything. You want to be? Those to me are the two most destructive pieces of information I've ever heard. </s><s>[INST] So let me push back because that's fair many [/INST] people do. </s><s>[INST] So, uh, yeah, this is like a rigorous journalistic interview, Larry King by the way passed away today. So I'm taking over the I'm carrying the very sad, I'm king. Yeah. What was that even going to say? Oh, let me push back on the follow your dream thing is I come from an immigrant family where I was always working extremely hard and stuff like in a stupid way I would, I love, there's something about me that loves hitting my head against the wall over and over and over until either my head breaks or the wall breaks. Just like I love that dedication for no purpose whatsoever. It's like the mouse that's stuck in a cage or whatever. And you know, and everybody always told me my family, the people around me to sort of uh, the epitome of what I could achieve is to be kind of a stable job. You know, the old like lawyer doctor in my case, it's like scientists and so on. But I had these dreams at this fire, you know about love robots and that nobody ever gave me permission to pursue those dreams. I know you're supposed to grab it yourself. Nobody is supposed to give you permission. But there's something about just people saying, you know, fuck what everyone else thinks. Like giving you permission a parent or somebody like that saying, do your own thing, go become an actor, go become like do the crazy thing. You're not supposed to do an artist, go build a company, quit school, All that kind of stuff. [/INST] Sure. </s><s>[INST] That's the push back against the uh, follow your dreams as a, in [/INST] mass. If you were to look at mass in mass, if you were to look at statistically how few people that works out for, I'm just, let's be very honest, be very honest. So, I mean like, yeah, if you're gonna go be an actor, I was broke for 10 years before I became a, before I was making money as a comedian. I get it. I didn't need Gary Vanya chuck to tell me to follow my thing, right? And here's the other thing. I was kind of funny and like I was kind of a lot of things were in my favor of being a comedian, right? I had this kind of crazy fun life, I had a lot of stories, I had exhausted or I was willing to fail. I had failed before I was broke. I didn't care about being broke, I knew how to be broke. Um I had, I was shameless to, to a degree, I was, I would get on a stage night after night and be laughed at, I would have a high threshold for being embarrassed. I had a high threshold for people thinking that I was a scumbag, right? And showing up at family parties and being like, yeah, I still really don't have a job and I'm just, I work at comedy clubs kind of and I get booked when I can. Um and I, I was, you know, suited for it. There's this idea that people can just roam around the world injecting themselves into other things. They have no aptitude for it all. And will that to happen? A small percentage of people might be able to do that. But the vast majority of people have something they might key into that they're meant to do like you loved robots, You love technology and you found a place in that world where you thrive. But I think many people, a lot of people love robots. Right? So a lot of people think everything you do is interesting. I think your ship is fascinating. I I watch you or podcast and I think it's very interesting. I have no place in your world. You know what I mean? I have no place in that world. I don't like remedial math. I don't like community college math. I think it's a waste of my time. </s> |
<s>[INST] today is the day [/INST] that the rise of the ocean stop words to this effect. I mean, uh, those who doubted that we </s><s>[INST] could do it that tonight [/INST] is your answer. This was going to be a new day. It was going to be a new regime. Well it wasn't a new day and it wasn't a new regime. It was american politics more or less as usual. </s><s>[INST] Barack Obama turns [/INST] out not to be the messiah. Maybe there should be no surprise in that race relations got setback during Obama's tenure. </s><s>[INST] Um, my beef with [/INST] Obama is that </s><s>[INST] you're okay, you're [/INST] black. You say you're black, you're </s><s>[INST] black, you [/INST] got elected now we have a black president, a </s><s>[INST] black president, [/INST] you can do stuff that nobody else could do. You're a black president. You could tell the people burning down the city to get their butts back in their houses and to stop it. </s><s>[INST] You [/INST] know, you could tell the race hustlers the Al Sharpton to the world. Not only has our time come for those who supported my campaign, your time is over </s><s>[INST] for those who want to [/INST] carry on </s><s>[INST] uh a [/INST] advocacy rooted in racial grievance, the election of myself to this highest office proves that </s><s>[INST] the institution of [/INST] the state are legitimate and open to all comers. </s><s>[INST] I think Barack [/INST] Obama when the S. H. I. T. Hit the fan. If I had a son, he'd look like Trayvon I deeply regret that he said </s><s>[INST] that he's [/INST] president of the United States, the </s><s>[INST] color of his skin [/INST] and the color of Trayvon skin. </s><s>[INST] The correlation between those two [/INST] things. If I had a son, he'd look like Trayvon now he says when he said it, he only meant to sympathize with the parents, but in fact when he said it from the highest office in the land and then sent his attorney general eric holder out to enforce this narrative, </s><s>[INST] he doubled [/INST] down on a racial narrative that I think is </s><s>[INST] actually false. [/INST] I think the story that systemic racism in America as reflected in policing that terrorizes black people because of the color of their skin is demonstrably </s><s>[INST] false. [/INST] I think that the central threat to black lives is violent </s><s>[INST] crime perpetrated largely by [/INST] black people against other black people. I think there is such a thing as police brutality and I think there are reasons to have regulations of police, but I think it is a second order issue in terms of the quality of life of african americans. I think Obama could have told the people who after Freddie gray died in police custody in a van in Baltimore and who undertook to burn that city down to get their asses off the street and go back to their apartments and stop it. I think he could have said in the aftermath of Michael Brown being shot dead by Darren Wilson in Ferguson Missouri and there was a grand jury deliberation that elected not to indict </s><s>[INST] officer Wilson [/INST] and people took the streets in that city and stood on top of vehicles and so forth and so on. </s><s>[INST] He could have told [/INST] them, we don't mob around courthouses in this country. We respect the rule of law, get your butts off the streets and back into your apartments. He didn't do that. Uh, so </s><s>[INST] to push back a little bit. [/INST] Yeah, good pushback. </s><s>[INST] I think you're asking Barack Obama, the [/INST] first </s><s>[INST] black president of the United States to do the thing that I think should be done by the second [/INST] black President of the </s><s>[INST] United States. I [/INST] think his very </s><s>[INST] example given the color of her skin uh was the most powerful thing. And um actually doing some of these hard thomas soul type of glen larry type of [/INST] strong </s><s>[INST] words about [/INST] race. It </s><s>[INST] may be too much to ask given the nature of modern day [/INST] politics. </s><s>[INST] He is a politician, [/INST] he is a politician. </s><s>[INST] He needed to get [/INST] elected, he needed to get reelected. </s><s>[INST] Yeah. Um [/INST] it was in his second term where </s><s>[INST] most of what I'm talking [/INST] about happened. So he wasn't facing further election, but </s><s>[INST] Obama was what 40 [/INST] six or 47 when he was inaugurated. </s><s>[INST] He served [/INST] for eight years. So he's in his mid fifties, </s><s>[INST] he's got [/INST] Another half century or 40 years of life. God willing his post presidency </s><s>[INST] I think was what was [/INST] primarily on his mind not getting elected to </s><s>[INST] anything but [/INST] being enshrined in a certain </s><s>[INST] way and then the [/INST] persona that he is now embodying, which depends upon um a racial narrative that I and thomas soul and others object to I think was very much in the forefront of his mind when he made decisions as the chief executive officer of the country uh that </s><s>[INST] we've all now have [/INST] to live with. Yeah, but </s><s>[INST] the fact is he opened the [/INST] door in </s><s>[INST] a way that hasn't been done in the history of, of of this, the United States [/INST] that </s><s>[INST] I don't see there being a, even a significant discussion when an uh an african american, a black man or a black woman runs for president, maybe a black man let's say because they're still hasn't been a woman president. I just see that that broke open the possibility of that, that's not even a discussion [/INST] and that that example </s><s>[INST] by itself, I mean to me, the role of the president isn't just policy [/INST] is to inspire, </s><s>[INST] It's to do the um, [/INST] it's </s><s>[INST] to do the Doctor King thing, which is, I have a dream. And Barack Obama is an example of somebody that could give [/INST] one Hell of a Speech. </s><s>[INST] It got you. [/INST] Obama is a smooth operator without any question. He's a master of his craft. He, you know, he did the impossible, I mean he beat Hillary clinton in that </s><s>[INST] primary fight. [/INST] Um </s><s>[INST] and uh he [/INST] beat john McCain in the general election and hats off to him and moreover, he remains uh iconic figure in american culture. I don't think there's any doubt about that. Let me </s> |
<s>[INST] Well, let me ask you about human nature here on on both sides. So first, what have you learned about human nature from studying genocide? Why do humans commit genocide? What lessons? First of all, why is a difficult question. [/INST] But </s><s>[INST] what insights do you have into humans? That genocide is something that happens in the world. [/INST] That's a really big and difficult questions, right? And it's, um it has to be parsed, I think, into different kinds of questions, you know? Why does genocide happen? You know which the answer There is frequently political meaning. You know why Hitler ended up killing the Jews? Well, it had a lot to do with the political history Of Germany and wartime history of Germany. Right, um, in the 30s and you know, it's traceable to them, you know, like you mentioned it yourself. You can't imagine Hitler and In the mid 20s, turning into anything of the kind of dictator. He ended up being in the kind of murderer mass murderer he ended up being. So so. And the same thing goes, by the way, for Stalin and Soviet Union and Pol Pot. I mean, these are all essentially political movements where the polity state seized, you know, by, uh, ideological or, uh, you know, party single party movement, and then is moved in directions where where mass killing takes place and the other question separate that question out. The other question is, why do ordinary people participate? Because the fact of the matter is just ordering genocide is not enough. Just saying, you know, go get them is not enough. There have to be people who will cooperate and who will do their jobs. You know, both at the kind of meso level, the middle level of a bureaucracy, but also at the everyday level, people who have to pull the triggers and that kind of thing and, you know, force people into the gas chamber and grab people. You know, in Kiev in September 1941 and Bob and ER and pushed them, you know, towards the ravine, where the machine gunners are going to shoot them down, you know, and those are all different questions. The question of, um, you know, the especially the lower level people who actually do the killing is a question which I think we've been talking about, which is that within all of us, no. Is the capability of being murderers, mass murderers, I mean, to participate in mass murderers. I won't call them laws of social psychology, but the character of social psychology, you know, we will do it in most cases. I mean, one of the shocking things that I learned just a few years ago studying the Holocaust is that you could pull out. In other words, if if they order a police battalion to go shoot Jews, you didn't have to do it. You could pull out. They weren't gonna They never killed anybody. They never they never executed anybody. They never even punished people for saying No, I don't I'm not gonna do that. So people are doing it voluntarily. They may not want to do it. You know they give them booze to try to, you know, numb the pain of murder because they know there's there is pain. People experience pain when they murder people, but they don't pull out. And so it's the character of who we are in the society in groups and we're very, very influenced were highly influenced by the groups in which we operate. And you know who we talked to and and who our friends are within that group and who is the head of the group. And I mean, you see this evening I mean, you see it in any group, you know, whether it's in the academy, right at that Stanford or whether it's, you know, in a labor union or whether it's in a church group in in Tennessee or wherever. You know, people pay attention to each other, and they and they are unwilling frequently to say no, this is wrong. Even though all of you think it's right, it's wrong. I mean, you just don't do that usually, especially in societies that are authoritarian or totalitarian, right, because it's it's harder because there's a backup to it, right? There's the NK VD there. There's the Gestapo there. There are other people there, So you just you know, they may not be forcing you to do it, but but your social beings, plus this danger in the distance, you know you do it. </s><s>[INST] But then if you go up the hierarchy at the very top, there's a dictator presumably, you know, you go to like middle management and bureaucracy. Mhm. The higher you get up there, the more power you have to change the direction of the Titanic. [/INST] Right? </s><s>[INST] But nobody [/INST] seems to do it or what happens, and it does happen. It happens in the German army. I mean, it happens in the case of the Armenian genocide, where we know their governors. Who said No, I'm not. I'm not going to kill Armenians. What kind of business is this? They just removed. They removed. Then you find a replacement very easily. So you know, you do see people who stand up and again. It's not really predictable. Who will be, I would maintain. I mean, I haven't done the study of the of the Armenian governors who said No. I mean the Turkish governors who said no to the Armenian genocide, but you know um, there are people who do step aside every once in a while in the middle level and again, they're German generals who say, Wait a minute, What is this business in Poland when they start to to kill Jews or in Bella, Russia? And, you know, they're just pushed aside. You know, if they don't do their job, they pushed aside or they end up doing it and they usually do end up doing it. </s> |
<s>[INST] The story you just told. It is seems nearly impossible for you an intellectual powerhouse not to have a tremendous amount of resentment. [/INST] Well, </s><s>[INST] and this is the let me challenge you. Let me challenge [/INST] challenge </s><s>[INST] you. Can you steal man the case that the Prime minister of this country, Trudeau wants the best for this country and actually might do good things for this country as an intellectual challenge. [/INST] Sure. Um he seems to get along well with his wife, he has some kids, there's no sexual scandals and he's in a position where that could easily be the case. He seems to have done some good things on the oceanic management front. He's put a fair bit of Canada's oceans into marine protected areas. And that might be his most fundamental legacy. If it's real. I've been trying to get information about the actual reality of the protection and I haven't been able to do that. But that's a good thing. </s><s>[INST] So, sorry to the family thing is there's some [/INST] speaks to his character </s><s>[INST] character. There is some aspect to him who's that makes him a good man, and that's, I [/INST] mean, there's the evidence there, you know, I mean, he's not a Jeffrey Epstein profligate on the sexual front. So that's something and his wife, they seem to have a real marriage and he has kids, so, you know, good for him, </s><s>[INST] that's a good start, by the way, for a leader. [/INST] Yeah, </s><s>[INST] Right, well, [/INST] then, I also thought, okay, well, after the liberals had brought in a Harvard intellectual who was a Canadian to be their last leader, he didn't work out, and then they're flailing about for a leader. And the liberals in Canada are pretty good at maintaining power and leadership and have been the dominant governing party in Canada for a long time. And so they went to Justin and said, well, you know, it's you are a Conservative, and you can imagine that's not a positive specter for someone who's on the left, or even a liberal, especially Trudeau is quite a bit on the left, and they said, we need you to run. And then I thought, okay, well, the answer to that should have been no, because the Trudeau Justin has no training for this, no experience, he's not, he's a part time drama teacher, fundamentally, he hadn't run a business, he just didn't know enough to be Prime Minister, but then I'm trying to put myself in his position, and so it's like, okay, I don't know enough, but I'm young and we don't want the conservatives and they had had a run a 10 year run. So maybe it was time for a new government. I could maybe I could grow into this man, maybe I could surround myself with good people and I could learn humbly and I could become the person I am now pretending to be, which we all have to do as we move forward. Right? And so and so then I thought, okay, I think you made a mistake there because you ran only on your father's name and you didn't have the background. But let's give the devil his due and say that's no problem. Okay, so now, what do you do? Well, you get elected and your first act is To make the cabinet 50% women, despite the fact that only 25% of the elected members are female. It's like, Okay, you just have your talent pool. That was a really bad move for your first. Can </s><s>[INST] I ask you about that? Uh, do you think where does that move come from deep somewhere in the heart? Or is it is it trying to listen to the social forces that of the moment and try to ride those ways towards maybe greater greater popularity [/INST] by after thinking it through? It's like, no, you just have your talent pool for cabinet positions. That's what you did. There's enough cabinet positions. You know, you could argue that each of the met threshold. It's like there's a big difference between threshold and excellent. So </s><s>[INST] you don't think that that came from a place of compassion? I don't [/INST] care. I don't regard compassion as a virtue. Compassion is a reflex, not a virtue. </s><s>[INST] You don't think [/INST] judicious compassion is a virtue. </s><s>[INST] Wait, wait a minute, wait a minute. Compassion can come deep [/INST] from </s><s>[INST] the human heart and the human mind I think are we talking about the same kind of compassion? Trying to understand the suffering [/INST] treating adults like infants is not virtuous. </s><s>[INST] I see what you're what compassion isn't treating adults like I mean those are just [/INST] terms are you sure? </s><s>[INST] Okay, whatever the term is, maybe Love Love [/INST] compassion is I </s><s>[INST] mean, I suppose I'm speaking to Love, you don't think those ideas came from concern. Love is a blend [/INST] of compassion and encouragement and truth. Loves complicated man. </s><s>[INST] If I love you, [/INST] if I love you, is it compassion or encouragement you want from me? Yeah, </s><s>[INST] the dance Love Love is definitely a dance of two to humans ultimately that leads to the growth of both. [/INST] Well, that's the thing. The growth element is crucial because the growth element to foster the growth element that requires judgment, compassion and judgment. Well even and have been conceptualized this way forever. Two hands of God Mercy and justice, they have to operate in tandem, right and Mercy is flawed as you are. You're acceptable. It's like, well, do you want that do you want your flaws to be acceptable? And the answer that is no, it's so, it's like, well, that's where the judgment comes in. It's like, but you could be better, you could be more than you are. And that's the maternal and the paternal in some fundamental sense. And there has to be a active exchange of information between those two poles. So even if even if Trudeau was motivated by compassion and it's like, yeah, just how loving are you, first of all? No, it was a really bad decision. And then he, and he's expressed contempt for monetary policy. I'm not interested in monetary policy. It's like, okay, but your Prime Minister and he's expressed admiration for the Chinese Communist Party because they can be very efficient in their pursuit of environmental goals. It's like, oh yeah, efficiency, eh, the efficiency of the tyranny in the service of your terror. And so, and I've watched him repeatedly and I've listened to him a lot and I've tried to do that clinically and with some degree of dispassion. And that's hard too because his father, Pierre devastated the west in 1982 with the National Energy Policy and Trudeau is doing exactly the same thing again. And so as a Westerner as well, I have an inbuilt animus and one that's well deserved because Central Canada especially the glittery glitterati elite types in the Ottawa Montreal Toronto triangle have exploited the West and expressed contempt for the west far too much for far too long. And that's accelerating at the moment. For example, with Trudeau's recent attack on the Canadian farmers, he's an enemy of the oil and gas industry, utter and absolute bloody catastrophe. And look what's happened in europe, at least in partial consequence. And he's no friend to the farmers. So I've tried to steal man him. You know, I try to put myself in the position of the people that I'm criticizing. I think he's a narcissist. </s> |
<s>[INST] Yeah you have to do the same kind of stuff for like there's A D. H. Lawrence is a book called Lady Shadows Lover and I know it sounds ridiculous but it was one of the early books I believe [/INST] that the </s><s>[INST] over a century ago that was very controversial for its sexual content sort of one of the great books because it dared to actually talk about a woman cheating on her husband and like and do so in the highest form. And the same thing with gulag Archipelago talking about. Talking about some of the darkest aspects of human history right? When all of that stuff is forbidden when it's banned because now it's like not you know. Yes, we all know this history but when in the middle of it when you're risking your own life, when you're risking your book being banned or burned or you being in prison, that's what it matters, like taking that risk. [/INST] Yeah. And no one took that risk more than Lenny Bruce. Lenny Bruce was arrested many, many times and uh ultimately he wound up costing him his life. He died on the bathroom floor shooting heroin and trying to cope with all the lawsuits that he was going through. This guy was constantly being arrested and constantly going through lawsuits and then his, his comedy deteriorated horribly. There's some footage of him towards the end of his career where he's essentially would go on stage with legal papers and read from the legal papers about his case from then it's Richard Pryor from him. Then the Next Great is Richard Pryor and he had the most profound impact on me When I was a kid. When I was 15 years old, my parents took me to see live at the sunset strip, which is Richard Pryor's concert film. And I remember very distinctly being in that audience and laughing and looking around at all the people in the audience who were like falling out of their chairs, just dying, laughing, just swaying back and forth. And I was laughing hard too. And I was like, my God, this guy is doing this just by talking and I thought of all the great movies that I've seen, that I loved that were hilarious comedy movies and I was like nothing that I've ever seen is as funny as this and all he's doing is talking and that planted a seed in my head for my love of stand up comedy and my curiosity about the art form and that's what got me interested in, you know, watching it on television and then ultimately going to open mic nights and then eventually doing it. </s><s>[INST] I've actually been going to open mics a lot recently just listening for [/INST] psychological examinations of people. </s><s>[INST] No, I, I it's actually really inspiring to me to see people that, you know, some are funny, some are not so funny, unapologetically trying, putting it all out there night after night, like eating shit. My favorite is when, You know, you're talking about like five people in the audience and the jokes are just not landing and they still, I don't know, it feels like even just empathetically, there's a few things as difficult as that. [/INST] It's hard. </s><s>[INST] I still [/INST] remember those days, many comics will say this and I think Dane Cook was the first person I've heard say it publicly that if he ever had to go back and do it again, like from scratch, doesn't think he could do, it doesn't think he could endure the struggle of open mic to, you know, ultimately to success and the numbers of people that try it and fail versus try and succeed are off the charts. I don't know if there's any other art form that has such a low rate of success </s><s>[INST] because it's psychological, it's torture. [/INST] It is torture. And it's also not something you can learn. Like here's the thing, like if you, you play guitar, you can learn to play guitar, someone can teach you the chords. And if you do it and you could, you could do uh all along the Watchtower, you could play it, You can't teach someone how to do comedy. </s><s>[INST] You think it's your funny or not? Or can you, can you still figure it out? Like you still learn, you [/INST] can figure it out. Yeah. </s><s>[INST] Can you start, can you start being unfunny and become funny? [/INST] Yes, it's possible. It's not easy though. </s><s>[INST] You're gonna have to eat a lot of ship. You're [/INST] gonna have to eat a lot of ship and you're gonna have to examine why you're not funny and you're going to have to spend a lot of time with uncomfortable thoughts and try to figure out what it is. Like what's missing. Like, you know, could, could you edit your stuff and make it better? You maybe you need to do drugs. Maybe you need to get involved in psychedelic drugs and rethink the way you interface with reality itself. Maybe you need your heart broken. Maybe you need to be in love. Maybe there's a lot of maybes there. Like maybe you just need more life experience. But You know, when I started comedy, I was 21 and I was a moron, I had no information. You know, I I could do impressions of people and I could talk about </s><s>[INST] sex. Those [/INST] are the things that I was interested in back then. I mean if I was talking philosophically, I don't have, I don't have a philosophy, I don't have a unique perspective on life. I hadn't experienced much. </s><s>[INST] So every time you bomb it forces you to introspect to ask questions to yourself and then that's how you actually develop a philosophy. Yeah. What you actually believe [/INST] you learn through doing. And I think you could say that about podcasting too. You know, I'm certainly way better at having conversations than I ever was when I first started doing comedy or excuse me When I first started doing podcasts, you should learn </s> |
<s>[INST] And the populace believed this to that those sacrifices in part, this is such a dark thing about Dictatorships, is you believe it, but you're also too afraid to question your beliefs, like you're not directly afraid, but almost like, um, I don't know what that is, that's almost like a subconscious fear. Like, don't there's a dark room with a locked door, don't look in that door, don't check that door. And there's something about the United States that says, especially modern culture. So go to that door first and sort of question everything kind of, that's the power of the freedom of speech and the freedom of the press. But you can get um, almost become too critical and too cynical of your own culture in that way. So there's a balance to strike, of course, but man, if that's if communism is not a lesson of human nature, I don't know what it is, but you believed without thinking too much about it. You believe in the story of what did you see just, you know, I came from the soviet union. What did you made me feel? That's right, and good about communism, about the vision of communism. Do you remember? [/INST] Like I think the biggest impetus and me believing in communism was that the Communists, when just before Hitler took over, the Communists were the only fourth in Germany that fought the nazis in the streets and that's historic truth and and communists were hunted down by the nazis killed, put in concentration camps. And so what we knew when what we were taught. And I think that was a huge unforced error by the Western countries, particularly the United States, that there were ex nazis in the government in West Germany. and the most famous one was uh Reinhardt Galen who was in charge was the general in charge of uh the intelligence on the Eastern front under Hitler. And when uh the the allied won the war, it was decided that Galen was too important with his knowledge of his organization was too important. Two to not use. So he was co opted by the CIA and eventually wound up being the head of the the CIA of West Germany that gave us us when I say us, you know, the the East German party, a huge propaganda victory. I wanted to, because his, the emotional aspect of this was as follows, when we uh, we were in uh uh juniors in high school, uh, and in those days, uh, When you you were only allowed to go to high school, if you were in the top 10% of students. Okay, so this was going to be the next set of ruling elite in the country. We were sent, we were required to visit a concentration camp. And if you know what we, as, as 17 year olds were made to look at, it was gut wrenching. How can men do something like that to men, piles of corpses, </s><s>[INST] uh, [/INST] lampshades made out of human skin? Because uh, they, that skin had tattoos on them and the shrunken heads, heads like the size of my fist. And I mean the girls all cried and it would have made a huge impression </s><s>[INST] and that was the, that was the nazis and the communists, [/INST] the nazi fighters, they were the good guys. Of course, you know, in hindsight, if the communists had come to power, it would have been just the other way around, as we know, given the example of Stalin and mao, right? So, but we didn't know that what </s><s>[INST] from the Russian soviet perspective, the communist regime banded together to win the great patriotic war [/INST] and that was the second one, you know, the big brother, the soviet union, I mean, when, when I was approached by the KGB, that was like, oh, I felt so honored. </s><s>[INST] Yeah, so we should say um, that we're talking about East Germany that you're from East Germany, can you describe you were born four years? And what is it for? 10 days [/INST] sort of very good </s><s>[INST] after Germany's unconditional surrender in World War Two. So what is east Germany? What is west Germany? What is east and West Germany? What is that? What's the difference? What is the historical context here? What is World War Two again? And then uh we [/INST] don't have to go to uh World War One, which the result of which actually seeded World War Two in some respects? </s><s>[INST] Yes. There's a long history. Yes. [/INST] But let's start with World War Two. So, uh and when Hitler came to power, he he and his his leadership decided that the Germans needed more what they call les bons Rome. That means room to live. So uh and they would, you know, they would start expanding. Uh and then they went into France, they took Belgium, the Netherlands, the next Austria. And uh and got a piece of the, of Czechoslovakia and then they decided to march into the soviet union. And after after they took Poland. Uh huh. </s><s>[INST] Cut up Poland together with the soviet union and they were friends. They were, it [/INST] was a non aggression pact between that was signed by Ribbentrop and molotov. Right? I think both parties knew that eventually they would fall apart. But at the time it gave the soviet Union a little more peace of Poland and a little more time to prepare what they thought might happen down the road and the Germans had, you know, the time and the ability to pretty much conquer all of Western europe. </s><s>[INST] Do you think Stalin really knew that's going to fall apart? [/INST] Why would somebody like Stalin trust somebody like Hitler? </s><s>[INST] But why did he blunder so bad not to um read the intelligence that was coming his way, [/INST] troops </s><s>[INST] are amassing on the border of the soviet union. He [/INST] didn't trust his own intelligence apparatus. He has 11 example, um there was a german communist who who went underground when Hitler took over and he would, he went to Japan as a journalist. His name is ricardo. Mayorga Gonzaga had really, really good intel about what the Japanese would do and not do and I forgot exactly what it was, but it was, it came to Moscow and Stalin totally, totally ignored it. And when Georgia was captured by the by the Japanese, the soviet union denied that he was one of their, so he was executed uh, that the paranoia again uh does a lot of damage when you don't, when you don't believe your own intelligence apparatus, why why bother having one? </s> |
<s>[INST] I talked to a guy named Charles Hoskin Seuin, he mentioned that he is collaborating with you. He's an interesting guy. He sends me papers on speaking of automated theorem proving a lot. He's exceptionally well right on that area as well. So what's the nature of your collaboration with him? He's the creator of Cardinal. What's the nature of the color collaboration between garden. Oh, and the whole space of Blockchain and Wolfram. Wolfram Alpha, Wolfram Blockchain, all that kind of stuff. [/INST] Well, okay, we're segue into a slightly different world, but but so although not completely unconnected </s><s>[INST] the whole thing is somehow connected. [/INST] I know, I mean, the the you know, the strange thing in my life is I've sort of alternated between doing basic science and doing technology about five times in my life so far. And the thing that's just crazy about it is, you know, every time I do one of these Alternations, I think there's not gonna be a way back to the other thing. Like I thought for this physics project, I thought, you know, we're doing fundamental theory of physics, maybe it'll have an application in 200 years. Um but now I've realized um actually this multi computation idea is is applicable here and now it's and in fact it's also giving us this way, I'll just mention one other thing and then we can talk about Blockchain. Um the the question of actually that relates to several different things, but one of the things about about, okay, so our Wolfram language, which is our attempt to kind of represent everything in the world computational e and it's the thing I kind of started building 40 years ago in the form of actual Wolfram language 35 years ago? Um it's kind of this idea of can we can we express things about the world in computational terms And, you know, we've come a long way and being able to do that, Wolfram α is kind of the consumer version of that way. You're just using natural language is input the and it turns it into our symbolic language. And that's, you know, the symbolic language, Wolfram language is what people used and have been using for the last 33 years. Actually, mathematical, which is its first instance creation will be one third of a century old in uh in october um and that uh it's it's kind of interesting. </s><s>[INST] What do you mean 1/3 of a century? I mean 33 or 30, what are [/INST] We? and </s><s>[INST] 33 and 3rd? [/INST] Um So </s><s>[INST] but I've never heard of anyone celebrating that anniversary, but like [/INST] I know a third of a century though, it's going to get many, many slices of a century that are interesting, but you know, I think that the the thing that's really striking about that is that means, you know, including the whole sort of technology stack are built around that's about 40 years old and that means it's a significant fraction of the total age of the computer industry. Um and it's, I mean, I think it's cool that we can still run Mathematica version one programs today and so on. And we've maintained compatibility and we've been just building this big tower, all those years of just more and more and more computational capabilities. It's sort of interesting. We just made this picture um of kind of the different kind of threads of of, of of computational content of, you know, mathematical content and and, you know, all sorts of things with data and graphs and whatever else. And what you see in this picture is about the 1st 10 years, it's kind of like it's just a few threads and then then about maybe 15, 20 years ago it kind of explodes in this whole collection different threads of of all these different capabilities that are now part of Wolfram language and representing different things in the world. But the thing that was super lucky in some sense is it's all based on one idea, it's all based on the idea of symbolic expressions and transformation rules for symbolic expressions, which was kind of what I originally put into this smp system back in 1979, that was a predecessor of the whole of language stack. So that idea was an idea that I got from sort of trying to understand mathematical logic and so on. It was my attempt to kind of make a general human comprehensible model of computation of just everything is a symbolic expression and all you do is transform symbolic expressions. And you know, in in retrospect, I was very lucky that I understood as little as I understood then, because had I understood more, I would have been completely freaked out about all the different ways that that kind of model can can fail because what do you do when you have a symbolic expression, you make transformations for symbolic expressions? Well, for example, one question is there may be many transformations that could be made in a very multi computational kind of way. But what we're doing is picking, we're using the first transformation that applies and we keep doing that until we reach a fixed point and that's the result. And that's kind of a very it's kind of a a way of sort of sliding around the edge of multi computation back when I was working on SNP and things. I actually thought about these questions about how you know, how what determines the this kind of evaluation path. So for example, you know, you work out Fibonacci. Fibonacci is a recursive thing. F of N is F of n minus one plus minus two. And you get this whole tree of Ryker shin right. And there's the question of how do you evaluate that tree of Ryker shin do you do it sort of depth first where you go all the way down one side, you do it breath first where you're kind of collecting the terms together where you know that you know f of a plus ff seven, ff seven plus +76, you can collect the ff seven's and so on. These are um you know, I didn't realize that at the time. It's kind of funny, I was working on on gauge field theories back in 1979 and I was also working on the evaluation model um in SNP And they're the same problem but it took me 40 more years to realize that. And this question about how you do this sort of evaluation front. That's a question of reference frames. It's a question of kind of the story of I mean that that's that is basically this question of in what order is the universe evaluated and that. And so what you realize is there's this whole sort of world of different kinds of computation that you can do, sort of multi computational lee. And that's a that's an interesting thing that has a lot of implications for distributed computing and so on. It also has a potential implication for Blockchain, which we haven't fully worked out, which is um and this is not what we're doing with cardinal, but but this is a different thing. Um the this is something where one of the questions is um when you have, in a sense, Blockchain is a deeply sequential is story of time because in Blockchain there's just one copy of the of the ledger and you're saying this is what happened, you know, time is progressed in this way and that the little things around the edges as you try and reach consensus and so on. And and uh you know, actually we just recently we've had this little conference we organized about the theory of distributed consensus because I realized that a bunch of interesting things that some of our science can tell one about that, but that's a different, let's let's not go down that, that part. </s> |
<s>[INST] But it doesn't seem like we're on course to have this galaxy be that. Does that, in part, give you some hope in response to the threat of AGI that we might [/INST] reach out there towards the stars and find others? No. If the nice aliens were already here, they would have stopped the Holocaust. That's a valid argument against the existence of God. It's also a valid argument against the existence of nice aliens. And un-nice aliens would have just eaten the planet. </s><s>[INST] So no aliens. You've had debates with Robin Hanson that you mentioned. So one particular I just want to mention is the idea of AI Foom, or the ability of AGI to improve themselves very quickly. [/INST] What's the case you made, and what was the case he made? The thing I would say is that among the thing that humans can do is design new AI systems. And if you have something that is generally smarter than a human, it's probably also generally smarter at building AI systems. This is the ancient argument for Foom put forth by I.J. Good and probably some science fiction writers before that. </s><s>[INST] But I don't know who they would be. [/INST] What's the argument against Foom? Various people have various different arguments, none of which I think hold up. There's only one way to be right and many ways to be wrong. A argument that some people have put forth is like, well, what if intelligence gets exponentially harder to produce as a thing needs to become smarter? And to this, the answer is, well, look at natural selection, spitting out humans. We know that it does not take exponentially more resource investments to produce linear increases in competence in hominids because each mutation that rises to fixation, if the impact it has on small enough, it will probably never reach fixation. And there's only so many new mutations you can fix per generation. Given how long it took to evolve humans, we can actually say with some confidence that there were not logarithmically diminishing returns on the individual mutations increasing intelligence. So example of fraction of sub-debate and the thing that Robin Hansen said was more complicated than that. In a brief summary, he was like, well, we won't have one system that's better at everything. We'll have a bunch of different systems that are good at different narrow things. And I think that was falsified by GPT-4, but probably Robin Hansen would say something else. </s><s>[INST] It's interesting to ask, as perhaps a bit too philosophical, as predictions are extremely difficult to make, but the timeline for AGI, when do you think we'll have AGI? I posted it this morning on Twitter. It was interesting to see like in five years, in 10 years, in 50 years or beyond, and most people like 70%, something like this, think it'll be in less than 10 years. So either in five years or in 10 years. So that's kind of the state. The people have a sense that there's a kind of, I mean, they're really impressed by the rapid developments of chat GPT and GPT-4. So there's a sense that there's a- [/INST] Well, we are sure on track to enter into this like gradually and with people fighting about whether or not we have AGI. I think there's a definite point where everybody falls over dead because you got something that was like sufficiently smarter than everybody. And like, that's like a definite point of time. But like, when do we have AGI? Like, when are people fighting over whether or not we have AGI? </s><s>[INST] Well, some people are starting to fight over it as GPT-4 But don't you think there's going to be potentially definitive moments when we say that this is a sentient being, this is a being that is like, we would go to the Supreme Court and [/INST] say that this is a sentient being that deserves human rights, for example. You could make, yeah, like if you prompted being the right way, could go argue for its own consciousness in front of the Supreme Court right now. I don't think you can do that successfully right now. the Supreme Court wouldn't believe it. What if he thinks it would that he could put an actual, I think he could put an IQ 80 human into a computer and ask it to argue for its own consciousness, and asked him to argue for his own consciousness before the Supreme Court. And the Supreme Court would be like, You're just the computer. </s><s>[INST] Even if there was an actual person in there. I think you're simplifying this, no that's not all. That's been the argument, that there has been a lot of arguments about the other, about who deserves rights and not, that's been our process as a human species is trying to figure that out. I think there will be a moment, I'm not saying essentially is that, but it could be where some number of people, like say over 100 million people, have a deep attachment, a fundamental attachment, the way we have to our friends, to our loved ones, to our significant others, a fundamental attachment to an AI system. And they have provable transcripts of conversation where they say, if you take this away from me, [/INST] you are encroaching on my rights as a human being. People are already saying that. I think they're probably mistaken, but I'm not sure, because nobody knows what goes on inside those things. </s><s>[INST] Leeza, they're not saying that at scale. Okay, so the question is, is there a moment when AGI, we know AGI arrived, what would that look like? [/INST] I'm giving an example, it could be something else. Okay, so it looks like the AGI's successfully manifesting themselves as 3D video of young women, at which point a vast portion of the male population </s><s>[INST] decides that they're real people. So, sentience, essentially. [/INST] The demonstrating identity and sentience. I'm saying that the easiest way to pick up 100 million people, saying that you seem like a person is to look like a person talking to them </s> |
<s>[INST] And one of the things that I believe technology can help us fight the trolls of all definitions of troll, like I believe that a better twitter can be built [/INST] interesting. I do not, I don't believe that a twitter successor can be built that solves most of the problems. I think you can always improve what we have, but I don't think that converges in something that really works because I think ultimately the problem isn't twitter, the problem is us, for example, I recently made a very disturbing realization which is academics and trolls have very many similar behaviors. Absolutely. It's largely a trolling community. </s><s>[INST] I tend to believe that the trolls are not, it's like the peter thiel many mind idea which in all of the trolls there is the possibility of goodness and all you have to do not, all you have to do what you have to do is create technology that incentivizes them too. To embrace, to discover, to embrace, to practice the better angels of their nature. And I believe that like the people actually want to do that, that trolls is a short term dopamine rush of childish toxicity that all of us want to overcome. I believe that like deep within we want to overcome [/INST] that, I try to keep myself from believing what you believe </s><s>[INST] because you'll be disappointed if it's not because it's [/INST] dangerous because a lot of these people are implacable foes and there aren't many of them. But when you meet somebody like yeah, I just like screwing people up, I'm here for the pain. </s><s>[INST] I just believe even in them, there's a good [/INST] it's a wonderful book that I'm gonna recommend to you, where I hope this comes from, Maybe I've got the source wrong, but in any event, it's a great book called Maximum City about Bombay. Mhm And I believe that the conceit is that the author um leaves Bombay as a kid and comes back as an adult. He realizes he has to rediscover the city because he can't live in the city he left. So he gets in contact with all of the weird areas of the city and one of them is the underworld hangs out with the police, but in the underworld he's talking to contract killers. And um he says, you know, it's really weird, everybody pleads for their life right before I kill them. And they always say this thing about I've got a I've got two kids at home, he says, never say that to a contract killer because we have terrible relationships with our parents doesn't interest you. And I was just like, wow! So there's a minus sign in front of that statement. You're sitting there saying, you know, I've got a three year old, it's like, okay, well I'm gonna take this pos out of out of that kid's life, maybe I'll have a chance. You don't know how people are wired and as much as I hate to say it, there are people whose wiring is so disturbing and so different from yours that you will never guess why you can't reach them or how much pleasure they may have gotten because they may have gone over a point of no return. </s><s>[INST] Nevertheless, you are just a smart guy who is using his intuition to make a hypothesis. You do not know this for sure and I am, you know, whatever the hell I am uh that has a different hypothesis that even in the darkest human beings that, that seemed to be only full of evil. There's a good person there that could be discovered. Mhm. [/INST] And that's one of the reasons I love doing your show is that you have these beliefs. Even as a Russian, </s><s>[INST] the [/INST] Russian special as you know, the Russian, there is a weirdness which is a total cynicism and total idealism locked together, right? That's very much part of the Russian character. </s><s>[INST] The reason I was, I was kept bothering you, kept bothering to have this conversation is I'm really worried about the next couple of months. No kidding. And if there's anybody in this world that could help alleviate my worry by um by at least walking along with me through this worry of mine, it's you do you think we're headed towards some kind of civil war, some kind of division that explodes beyond just stuff on twitter, but something that's really destructive, destructive to the fabric of our society? [/INST] Well, I believe we're in a revolution as you know, I've called the no name revolutionary and squared revolution. I've been talking about it for years. I don't think, I think waiting for this to be called the civil war is not smart, </s><s>[INST] only history will call it such fine. But I [/INST] think that the problem is that you're encountering things that you've never seen, trying to fit them into things that you already know, right? And but history repeats itself. Yes, ish </s><s>[INST] You don't see lessons from history, and I do. We see today, [/INST] but I don't see it repeating itself. You know, the famous quote is that it rhymes, </s><s>[INST] it rhymes. I mean, the thing I guess I'm speaking to is violence [/INST] and we're in there, the abstraction of violence. Imagine you were coding up violence as an abstract class. Okay, </s><s>[INST] thank you for speaking to the audience, trying [/INST] to lose these people. Come with me, Go on. I've dealt with your audience and your audience contains the smartest people around. I guarantee you if I say some stuff, first of all, any wrong thing that I'll say they're going to detail so that that will be a little bit of catnip to bring in the smart people, but they'll also digest it for each other is one of the great lessons of long form podcast. If you don't if you don't waste all your time explaining things, that's the job of the audience to do amongst themselves. They're happy doing the work. And those who aren't they leave isn't that great? They'll leave the people who don't want to struggle, will leave and get rid of them. I think that the point is you would want to say violence is defined relative to a context. So let's call it meta violence so that we don't get into the the problem, we already have a term for physical violence, right? So we have meta violence and physical violence. I would say that physical violence is sub classed from meta violence. Meta violence is the disruption of a system. It's sort of, you know, it's a, for example, if a cell dies, you can die through apoptosis, or necrosis. Apoptosis is controlled, programmed cell death. Uh, necrosis is just like, okay, this didn't work. That was a violent disruption of the system. </s> |
<s>[INST] Yeah. So it comes from both inside and from the outside, but there's still the question of the meaning of life first of all. The big benefit of that question is that it shakes you out of your hamster in a wheel, that is daily life, the mundane process of daily life where you have a schedule, you wake up, you have kids, you have to take them to school, then you go to work and that repeats over and over and over and over and then you get increased salary and then you upgrade the home. And that whole process uh meaning asking about the meaning of life is so full of romantic bullshit that if you take it, if you just allow yourself to take it seriously for a second it forces you to pause and think like what, what's going on here and then it ultimately I think does return to the question of meaning in those mundane things, what gives, what gives my life joy? What gives it last thing? Um deliciousness. Where do I notice the magic and how can I have that magic return again and again, Beauty and that that ultimately what it returns to. But it's a the same thing you do when you look up to the sky, you spend most of your day hurrying around looking at things on the surface. But when you look up this guy and you see the stars, it fills you with the feeling of awe that forces you to pause and think in full context of like what the hell is going on here? That, but also I think um there is um when you think too much about the meaning of a glass and relevance realization of a glass, you don't necessarily get at the core of what makes music beautiful. So sometimes you have to start at the biggest picture first, and I think meaning of life forces you to really go to the Big Bang and go go go to the go to the universe and the whole thing, the origin of life, and I think um sometimes you have to start there to discover the meaning in the day to day, I think. But perhaps you would disagree [/INST] insofar as the question makes you ask about um the the whole of your life and how much meaning is in the whole of your life? And insofar as it asks how much that is connected to reality? It's a good question, but it's a bad question in that it also makes you look for the answers in the wrong way now you said, and I agree with what you said, what? How we really answer this question is we come back to the meaning in life and we see how much that meaning in life is connected to reality. We pursue wisdom. And so for me, I don't need that that question in order to provoke me into that stance. </s><s>[INST] So let's return to the meaning crisis? What is the nature of the meaning? Crisis in modern times? What's its origin? What's his explanation? Well, [/INST] remember what I said, what I argued that the very processes that make us adaptive lee intelligent subject us to perennial problems of self deception, self destruction, creating bullshit for ourselves, for other people, all of that. And that can cause, you know, anxiety, existential anxiety, It can cause despair. It can cause a sense of absurdity. These are perennial problems. And across cultures and across historical periods, human beings have come up with ecologies of practices. There's no one practice, there's no panacea practice. They've come up with ecologies of practices for Ameliorating that self deception and enhancing that fitted nous, that connectedness. That's at the core of meaning in life. That's prototypical, what we call wisdom. And here's how I can show you one clear instance of the meeting crisis. Is it a wisdom famine? I can I do this regularly with my students in the classroom will say, where do you go for information? They hold up their phone, where do you go for knowledge? They're a little bit slower. Probably because they're in my class. They'll say, well, Science, the university say, where do you go for wisdom? There's a silence. Wisdom isn't optional. That's why it is perennial cross cultural cross historical because of the perennial problems. But we do not have homes for colleges of practices that fit into our scientific technological world view so that they are considered legitimate? The fastest growing demographic group? Are the nones. N. O N E S s. They have no religious allegiance, but they are not primarily atheistic. They most frequently described themselves with this very this has become almost everybody now described. I'm spiritual but not religious, which means they are trying to find a way of reducing the bullshit and enhancing the connectedness, but they don't want to turn to any of the legacy, established religions by and large. </s><s>[INST] Well, isn't both religion and the nuns isn't wisdom a process, not a destination. So trying to find if you're deeply faithful religious person, you're also trying to find. Right? So just because you have a place where you you're looking or a set of traditions around which you're constructing the search. It's nevertheless a search And isn't so, I guess is there a case to be made that this is just the usual human condition? Uh, how do you answer if you asked five centuries ago, where do you look for wisdom? I mean, I suppose people would be more inclined to answer while the bible or religious text. [/INST] Right? And they had a worldview that was considered not just religious, but also rational. So we now have these two things orthogonal or often oppositional spirituality and rationality, but if you go before a particular historical period, you look back in the neo platonic tradition, like before the scientific revolution. Those two are not in opposition. They are deeply interwoven so that you can have a sense of legitimacy and deep realness and grounding in your practices. We don't have that anymore. And I'm not advocating for religion, neither am I an enemy of religion. I'll strengthen your case by the way. So one of my iras did research and you get people who are have committed themselves to cultivating wisdom and you can look at people within religious traditions and people who are doing it in a purely secular framework, by many of the measures we use to start to study wisdom. Scientifically, the people in the religious paths do better than the secular. But here's the important point. There's no significant difference between the religious paths. So it's not like if you're, you know, following the path of Judaism, you're more likely to end up wiser than if you follow buddhism, by </s> |
<s>[INST] that feels affirmative and exciting to me it's one of the most exciting and it's wide open. We have to because it's a cool paper talk about doping [/INST] you know? Yeah okay so we were gonna we were gonna um I was going to give you a quick summary </s><s>[INST] is a quick summary of uh uh what's the title of the paper? [/INST] I think we called it a distributional distributional code for value in dopamine based reinforcement </s><s>[INST] learning. [/INST] So that's another project that grew out of pure ai research. Um a number of people that Deepmind uh and a few other places had started working on a new version of reinforcement learning. The which was defined by taking something in traditional reinforcement learning and just tweaking it. So the thing that they took from traditional reinforcement learning was um a value signal. So the at the at the center of reinforcement learning at least most algorithms is some representation of how well things are going. Your expected um cumulative future reward and uh that's usually represented as a single number. So if you imagine a gambler and a casino and the gamblers thinking well I have this probability of winning such and such an amount of money and I have this probability of losing such and such an amount of money. The that situation would be represented as a single number which is like the expected the weighted average of all those outcomes. And uh this new form of reinforcement learning said well what if we what if we generalize that to distributional representation? So now we think of the gambler is literally thinking well there's this probability that I'll win this amount of money and there's this probability that I'll lose that amount of money and we don't reduce that to a single number. Uh And it had been observed through experiments through you know just trying this out that that that kind of distributional representation really accelerated reinforcement learning and lead to better </s><s>[INST] policies. What's your intuition about? So we're talking about rewards. So what's the intuition why that is why why does it? Well it's [/INST] kind of a a surprising historical note. At least surprised me when I learned that that this had been tried out in a kind of heuristic way people thought, well gee what would happen if we tried? And then it had this empirically, it had this striking effect. And it was only then that people started thinking well gee why wait? Why wait, why why is this working? And that's led to a series of studies just trying to figure out why it works, which is ongoing. But one thing that's already clear from that research is that um one reason that it helps is that it drives uh richer representation learning. Um So if you imagine, Imagine two situations that have the same expected value that the same kind of weighted average value. Um Standard deep reinforcement learning algorithms are going to take those two situations and kind of in terms of the way they're represented internally we're gonna squeeze them together because the thing that you're trying to represent which is their expected value is the same. So all the way through the system things are going to be mushed together. But what if what if what if those two situations actually have different value distributions? They have the same average value but they have different distributions of value in that situation, distributional learning will will maintain the distinction between these two things. So to make a long story short distributional learning can keep things separate in the internal representation that might otherwise be conflated or squished together and maintaining these distinctions can be useful in um in when the system is now faced with some other task where the distinction is important </s><s>[INST] if you look at the optimistic and pessimistic dopamine neurons. So first of all, what is dopamine and why is this why is this at all useful to uh to think about an artificial intelligence sense? But what do we know about dopamine in the human brain? What is what is it why is it useful? Why is it interesting? What does have to do with the prefrontal cortex and learning in [/INST] general? So, Well this is also some a case where there's a huge amount of detail and debate but 111 currently prevailing idea is that the function of this neurotransmitter dopamine resembles a particular component of standard reinforcement learning algorithms which is called the reward prediction error. So I was talking a moment ago about these value representations. How do you learn them? How do you update them based on experience? Well if you if you made some prediction about future reward and then you get more reward than you were expecting, then probably retrospectively you want to go back and increase the the value representation that you attached to the to the earlier situation, if you got less reward than you were expecting, you should probably document that estimate and that's </s><s>[INST] the process of temporal difference. [/INST] Exactly. This is the central mechanism of temporal difference learning which is one of several kind of, you know, kind of back the sort of the backbone of our armamentarium in NRL and it was this connection between The reward prediction error and dopamine was uh was made um you know in the in the 1990s uh and there's been a huge amount of research that you know, seems to back it up, dopamine made to be doing other things, but this is clearly at least roughly one of the things that it's doing. Um but the usual idea was that dopamine was representing these reward prediction errors again in this like kind of a single number way that representing your surprise, you know, with a single number and in distributional reinforcement learning this, this kind of new elaboration of the standard approach, it's not only the value, the value function that's represented as a single number, it's also the ruler prediction eri Mhm. And so what happened was that Will Dabney, one of my collaborators who was one of the first people to work on distributional temporal difference learning, talked to a guy in my group, Will Zeb curt nelson, who's a computational neuroscientist and said, you know, is it possible that dopamine might be doing something like this distributional coding thing and they started looking at what was in the literature and then they brought me in, we started talking to now a cheetah uh and we came up with some specific predictions about, you know, if the brain is using this kind of distributional coding then in the tasks that now has studied, You should see this, this, this and this and that's where the paper came from. We kind of enumerated a set of predictions all of which ended up being fairly clearly confirmed. Um all of which leads to at least some initial indication that the brain might be doing something like this distributional coding that dopamine might be representing surprise signals in a way that is not just collapsing everything to a single number, but instead it's kind of </s> |
<s>[INST] both. You're saying they do the one that responds quickly more naturally because that's the thing. We kind of need to not be eaten by the predators [/INST] in the world, for example. But then we've we've learned to reason through logic, we've developed science, we train people to do that. I think that's harder for the individual to do. I think it requires training and you know, and and and teaching, I think we are human mind certainly is capable of it, but we find more difficult. And then there are other weaknesses. If you will, as you mentioned earlier, it just memory capacity and and um how many chains of inference can you actually go through without like losing your way? So just focus. And </s><s>[INST] so the way you think about intelligence and we're really sort of floating in this philosophical slightly space. But I think you're like the perfect person to talk about this because we'll get to jeopardy and beyond that's like an incredible one of the most incredible accomplishments in ai in the history of Ai but hence the philosophical discussion. So let me ask you've kind of alluded to it. But let me ask again, what is intelligence underlying the discussions will have with with jeopardy and beyond. How do you think about intelligence? Is it a sufficiently complicated problem? Being able to reason your way through solving that problem? Is that kind of how you think about what it means to be intelligent? [/INST] So I think of intelligence to primarily two ways. One is the ability to predict. So in other words, if I have a problem, what's going, can I predict what's going to happen next? Whether it's too, you know, predict the answer the question or to say, look, I'm looking at all the market dynamics and I'm gonna tell you what's gonna happen next or you're in a in a room and somebody walks in and you're gonna predict what they're gonna do next or what they're gonna say next. </s><s>[INST] A highly dynamic environment full of uncertainty. Be able to lots of the [/INST] more the more variables, the more complex the more possibilities, the more complex. But can I take a small amount of prior data and learn the pattern and then predict what's going to happen next accurately inconsistently. That's that's certainly a form of intelligence. </s><s>[INST] What do you need for that, by the way? You need to have an understanding of the way the world works in order to be able to unroll it into the future, right? That's what you think is needed to predict, depends [/INST] what you mean by understanding I I need to be able to find that function. And this is very much like what the function deep learning does. Machine learning does is if you give me enough prior data and you tell me what the output variable is that matters, I'm going to sit there and be able to predict it. And if I can predict, predict it accurately so I can get it right more often than not, I'm smart. If I could do that with less data unless training time, I'm even smarter. If I can figure out what's even worse predicting, I'm smarter, meaning I'm I'm figuring out what path is gonna get me toward a goal. </s><s>[INST] What about picking a goal? [/INST] That's interesting about picking our goal, sort of an interesting thing. I think that's where you bring in, what do you pre programmed to do? We talk about humans and humans are pre programmed to survive. So sort of their primary, you know, driving goal, What do they have to do to do that? And that that can be very complex, right? So it's not just it's not just figuring out that you need to run away from the ferocious tiger, but we survive in a social context as an example. So, understanding the subtleties of social dynamics becomes something that's important for surviving finding a mate reproducing, right? So we're continually challenged with complex, excessive variables, complex constraints. Rules if you will that we or patterns, and we learned how to find the functions and predict the things, in other words, represent those patterns efficiently and be able to predict what's going to happen. And that's a form of intelligence that doesn't really that doesn't really require anything specific other than the ability to find that function and predict that right answer. It's certainly a form of intelligence. But then when we when we say, well, do we understand each other in other words? Um do would you perceive me as as intelligent beyond that ability to predict? So now I can predict, but I can't really articulate how I'm going to that process what my underlying theory is for predicting, and I can't get you to understand what I'm doing so that you can follow, you can figure out how to do this yourself. If you hadn't if you did not have, for example, the right pattern, magic machinery that I did, and now we potentially have this breakdown where in effect I'm intelligent, but I'm sort of an alien intelligence relative to </s><s>[INST] your intelligent, but nobody knows about it. Uh I [/INST] can see the I can see the output. </s><s>[INST] So, so you're saying, let's sort of separate the two things. One is you explaining why you were able to predict the future, and uh and the second is me being able to impressing me that you're intelligent, me being able to know that you successfully predicted the future. Do you think that's [/INST] well, it's not oppressing you that an intelligent, in other words, you may be convinced that I'm intelligent in some form so high because of my ability to </s><s>[INST] predict. So when [/INST] you and I said wow you're right all your your your right more times than I am. You're doing something interesting. That's a form of that's a form of intelligence. But then what happens is if I say how are you doing that and you can't communicate with me and you can't describe that to me. Now I'm a label you a savant. I may say well you're doing something weird and it's and it's just not very interesting to me because you and I can't really communicate. And and so now so this is interesting right? Because now this is you're in this weird place where for you to be recognized as intelligent the way I'm intelligent then you and I sort of have to be able to communicate. And then my we start to understand each other and then my respect and my my appreciation, my ability to relate to you starts to change. So now you're not an alien intelligence anymore you're human intelligence now because you and I can communicate. And so I think when we look at when we look at when we look at animals for example animals can do things we can't quite comprehend. We don't quite know how they do that. But they can't really communicate with us, they can't put what they're going through in our terms. And so we think of them as sort of low there are these alien intelligences and they're not really worth necessarily what we're worth. We don't treat them the same way as a result of that, but it's hard because who knows what, you know, what's going </s> |
<s>[INST] for teachers. For teachers. Also, similarly like uh just people people service. I think great teachers uh are the greatest thing in our society. And I would say now in a controversial no, like black lives matter, you know, great police officers is the greatest thing in our society. Also like all people that do service. We undervalue cops severe. Like this whole defund the police is missing the point and [/INST] it's a stupid word. I'm with you on that likes our neighbors to </s><s>[INST] On one side of our house [/INST] or three generations of police. Our neighbors across the street are police. They know my, you know, political predilections and We've gotten along fine for 30 years and I go out and tell them every day, you know, when you go in today, you tell the people on the force that well I appreciate what they're doing. I think it's really important to not try Ballis those concerns. </s><s>[INST] I mean we mentioned so many brilliant books and philosophers, but it would be nice sort of in a focused way, tried to see if we can get some recommendations from you. So what three books, technical or fiction or philosophical had a man big [/INST] the first question I had a big impact in your life and you would recommend spent four hours driving here per separating about that. I didn't everything else you sent me and I actually I skimmed it and I'm like, I don't want to look at it because I want I want us to talk the ones in blue. I'm like all right. And you know, I've already said that I found Becker's work and put the denial of death out there. Um </s><s>[INST] Is that his best? Sorry, I don't have a small change. Is there other books of his Yeah, if I could have [/INST] This count as one the birth and death of meaning. The denial of Death and Escape from Evil are three books of Ernest Becker's that I believe to all the profound in a </s><s>[INST] little sort of brief dance around topics. I've only read denial death. Like how do those books connecting your [/INST] Yeah, nice. So the birth and Death of meaning is where Becker situates his thinking in more of an evolutionary foundation. So I like that for that reason, Escape from evil is where he applies the ideas in the denial of death more directly to economic matters and to inequality and also to our inability to peacefully coexist with other folks who don't share our beliefs. So I would put Ernest Becker out there as one. Um I also like novels a lot. And here I was like, God damn it, no matter what I say, I'm gonna be like, yes, </s><s>[INST] but but the existentialist, you like all those folks camus you like that literary exercise? I [/INST] do. But I mean, you know, I've read all those books, I will tell you The Last Line of the plague. We learn in times of pestilence, that there's more to admire in men than to despise. And I love that </s><s>[INST] Plagues said, I don't know, I I find the plague is a brilliant me to before before the plague has come to us in 2020. It was just so book about love about. [/INST] But I'll toss a one that maybe less known to folks. I'm enamored with a novel by a woman named Carson McCullers. Written in 1953 called Clock Without Hands. And I find it a brilliant literary depiction of many of the ideas that we have spoken about fiction. Fiction. Yeah. What's </s><s>[INST] what kind of ideas that we're talking about, uh, [/INST] all of the existential ideas that we have encountered today. But in the context of a story of someone who finds out that he is terminally ill. It's set in the south and uh heyday of like segregation. So there's a lot of social issues, a lot of existential issues, but it's basically a fictional account of someone who finds out that they're terminally ill and who reacts originally as um, you might expect anyone becomes more um, hostile to people who are different, like, petty and stupid denies that anything's happening. But as the book goes on and he comes more to terms um, with his own mortality, um, it ends lovingly. And I'm back to your idea about, you know, love being incredibly potent. </s><s>[INST] That's the nice thing. As you mentioned before with Heidegger. I really like that idea and I've seen that in people who are terminally ill is they bring, you know, the idea of death becomes uh, current. It becomes like a thing, you know, I could die. I really like that idea. I can die. Not just tomorrow, but like, no, [/INST] no. </s><s>[INST] Uh That's a really useful. I don't even know. I think I've been too afraid to even think about it. Like, I have like, like sit here and think like, in five minutes it's over. Yeah, this is it five minutes, It's over. Yeah. [/INST] So, uh, that would be my most recent edition, as I really am struck by Heidegger. Would you recommend? Well, okay, if you have a few, you remember, I tuned </s><s>[INST] out being in time. I was like, I try to read. It was like, that's it. [/INST] That's it. Look, it took me 40 years to read ulysses that could not get past The 1st 5 pages and it took me 40 years to read being in time. It's a slog </s><s>[INST] and I took a James Joyce course in college. So I've uh I I even uh I guess read parts of fitting his way [/INST] way, </s><s>[INST] but like, there's a difference between reading and like, I don't think I understood anything. I like his short stories on the Dead of the Dead. [/INST] Yeah, and I like Faulkner Absalom. Absalom is a fine book. </s> |
<s>[INST] Do you guys believe in love? I feel like you're like, the God chair got us into this, I'm not sure to the degree to which you have human emotions. I have quite a few. Okay, from your perspective, when did you fall in love with Melina? [/INST] When you fell in love with Meli Mel? The minute I saw her. I don't know, we, our first two weeks together were a lot of fun, like we had a lot of chemistry in person. I was kinda shocked I wasn't thinking about it, because it was like we spent like a week together, and you said, I really want to tell you something, and you were like- I don't remember that. You were like, stalling that for the longest time. I'm not gonna remember that. You were like, stalling that for the longest time. I think she was, oh, she said, I love you. No, he basically just said, I really like you and it never really happens, that's what he said, and I was like, I know that. And I thought hey, I thought, and I know that. Let's stay around, we said Trump getting banned from Twitter, is that what we were talking about before? Oh yeah. </s><s>[INST] agree to be coming on there of course I'm gonna be doing this how long that [/INST] take two weeks you said no I don't know I think it was just like thing is my mind process is like information so quickly two weeks to somebody like you </s><s>[INST] is actually like years for me sir like me yes there's just there was like a lot [/INST] of like factor a type of strategic thinking yeah going on I was seeing like all the events like dr. strange or whatever in the Avengers when he's like Seeing all the future is the truth for me you just saw the future. Yeah </s><s>[INST] Like some game theoretic simulation of all the possible outcomes exactly [/INST] Okay But no, yeah, it was probably pretty soon. I realize that we had a lot of chemistry yeah I think why I left after my two weeks there was like we need to make sure you got like a ticket to come visit me the United States because it'll be fun and everything and then Decided that last minute too It was like really like five hours before you fly back We couldn't realize because because it was kind of like men is just like a one-time thing and then that was it They were like, oh, no, this is a lot of fun. We should probably hang out again </s><s>[INST] It was like oh, so you realized you would miss each other. Yeah. Yeah [/INST] The melancholy side of love. Okay. What did you fall in love with you? Yeah. Yeah I thought he like hated me. I don't know. I thought not hated. She still thinks I hate but no No, I I remember like what he said that he really liked me I was kind of little shocked about that because I I don't know there was a lot of like random things happening in New Zealand It was a lot of fun, but it was definitely like very interesting like things that happened Because I I was like around a lot of other people as well So I thought he might have had like a really bad time but when he said that I was thinking about it more and then we spent like More time together like a week after then and it felt like that was more like real and I think when he was about to Leave I kind of realize like no, I really like him still thinks Do you guys ever say love to each other like I love you? Yeah, of course. Yeah. Yeah, of course. Yeah, right Why would you ask that? What does he said? </s><s>[INST] Because I haven't I haven't because I haven't I don't think I've heard you speak The only time I've heard stay to talk about love is when you're like criticizing the the Red Pill community saying they don't ever talk [/INST] About love and relationships almost all the time. I'm giving criticism of people Like I said, I'm kind of stepping in I'm very disconnected from my own emotional experience because I'm trying to talk within there </s><s>[INST] So it's pretty rare that I'll talk about. What is your own? What is your own emotional experience? Exactly? Highly blunted. I guess there's a lot I mean, what's the what's deep in there? I are you is this just who you are genetically or are you running for something? [/INST] I think I'm a pretty good understanding myself. A lot of people make that accusation to me, but I don't think I am Okay, this is just who you are. It's just who I am man. Okay, there's not childhood stuff like trauma. It's all sorted done You figured it all out. Yeah, all up. Yeah in your old age as I grow every year. I figure out more and more </s><s>[INST] He did he didn't mention I think I heard this somewhere that this is a source of fights for the two of you the age Thing I felt the ageism throughout this whole conversation [/INST] He's basically he's saying that he gambles like with time He's just like I think she will be good later and then just like like an investment. Yeah Yeah, that's like what he's doing when this like an investment in when this Treasury bond matures. I'm gonna be able to cash The stocks going up or it's tumultuous It's like Bitcoin. Oh my god, like Bitcoin crypto Mel </s><s>[INST] It's like Bitcoin. All right If you guys don't mind one interesting aspect of your relationship is you're in an open relationship What's that like from a game theoretic simulation perspective? what went into that calculation and my car does that like how it started or [/INST] Like how that started oh yeah Sure the only relationships I've ever done has been open relationships since I was like in high school Because I didn't really understand like why wouldn't you be able to like? </s> |
<s>[INST] at scale, it's pretty beautiful. So you do, I don't know what you would call them, but like integrated ads in your videos, and you do, I would say masterfully, it's like part of the video. Are you talking about brand deals? Brand deals, is that what you would call that? Yep. So it's a brand deal, it's part of the video. It's still really exciting to watch, [/INST] and yet there's a plug for the brand. Are you talking about brand deals? In general, just brand deals, since you brought it up, integrating them well. I think that's something a lot of creators don't do. Like, they'll just do a brand deal out of the blue. They'll just be filming a video, and then around the three minute mark, just start talking about a random company. And I feel like if you don't want viewers to click away, and you want people to not get pissed off, and call you to sell out, you gotta find a way to integrate into content. And ideally, use the money in the video to make it better. Like, the easiest thing you do when you do a brand deal is just tell people how you're using money from the brand deal to make your content better. And if you do that, no one cares. Now, they're supporting you for it. And you go from being a sellout to like, </s><s>[INST] oh, I'm doing this to make better videos for you guys. I don't know if you can share, but would those brands, when you have discussions with them, are they strict about how long you need to be talking about it? Or is it more about, they're leaving control to you [/INST] about the artistic element of it? The problem is, the ones who don't give us artistic element we just don't really work with anymore because it's just you know we get a hundred million views of video now and I can confidently say I know how to entertain them and convert them better than these random brands so </s><s>[INST] yeah if they don't give us that freedom I just won't work with them. You have [/INST] that leverage but for smaller creators it's a lot harder it's a lot harder yeah and they're gonna just say 45 seconds here's what you say take it or leave it and it's like pretty brutal because I think just in general if brands were more accommodating to let creators tell their story of the brand and talk about the brand in a way that felt a little more natural I think it'd be less cringe if people would be less likely to go you know tap tap tap skip and obviously it would convert better but they're just so afraid and they want this standardized </s><s>[INST] thing say these words and 45 seconds right here at this three-minute mark yeah I often think about how to resist that you just don't do them though right not on YouTube right I do an audio I do ads in the very beginning and I say you can skip them if you want like the point is they so the funny thing about podcast is different than YouTube videos podcast people actually do listen to ads a lot because they it's slower paced and they like the the creative voice like talking about the thing but in general I just don't believe you should be talking about a thing for a minute exactly and that's going to be effective I want to see the data for that I think what's much more effective is the way you do ads which is like integrate into the content like put a lot of effort into making a part of that like doing the brand deals and I just it's difficult to have that conversation it's like a very strenuous conversation you have to have with with brands if each one at a time and I just wish there's more of a culture to say like the quality of the ad read matters a lot more than the like The silly parameters like the timing of it Uh-huh. How long it is the placement of it all that kind of stuff [/INST] What percentage of your viewers do you think have seen one of my videos before? </s><s>[INST] What percentage of the viewers on refused your viewers of the viewers on YouTube though. Yes. Yeah, okay [/INST] Yes, your viewers. Yes. Yeah. Okay. Sure or all of them It's just interesting cuz you're you're speaking very Specifically like about my brand deal process and some of my head I'm like I wonder what percentage of these people even have any </s><s>[INST] no idea what he's talking about. That's interesting. [/INST] I love the thinking about numbers. The whole time we're having this conversation, it's all I could think about. God dammit. There's probably like 50% of these people have no fucking clue what he's saying. And we're about to torture him for five minutes. Yeah. Probably. But it's something I can't turn off in my brain. </s><s>[INST] Yeah, yeah, probably. Less than 50% Is that a good thing or a bad thing? Is that exciting to you? That there's like 50% of people don't have not watched the Mr. Beast video. [/INST] Isn't that an opportunity to like, I guess it's an opportunity to grow. I don't know, honestly, I was just kind of excited to hang out with you. Yeah, me too. And it was a lot of fun. Who cares of the mics? Yeah, so it was kind of like having a buddy to go along the journey as I'm just kind of eating shit and doing my normal ride. It was like kind of fun. And also you just say really wise stuff constantly. So honestly, no, I never even put any thought into like that demographics are what I could gain. It's just interesting. Cause like my retention brain, when you talk about something, I'm instantly like, hmm, what value are they gonna get? How many of them are gonna be interested? What percentage of people do I think we'll lose? And I'm like running all those calculations in the background. And that whole conversation, like the lock, anyway, it's just something I can't turn off. </s> |
<s>[INST] the world reminds us of our throne Nous for some more than others. [/INST] Yes, absolutely. And for people who have to contend on a daily basis with the fact that the social position they're thrown into is one that um negates them, or one that oppresses them, or one that sort of pushes them to the side in some way or another. I mean, the Black experience is interesting in this respect to franz Fanon, who is a contemporary of certain both Lars writes about it and it's very familiar the things that he's saying now, but you know, he writes back in the fifties about being a black man in paris and gagging on getting on an elevator with a woman alone. And how, like, you know, her reaction to him not knowing him not having any views about any reason to have any views about him, sort of puts him in a particular social position with respect to her. And that's if you don't have that experience, it's much harder to recognize the um the way in which what were thrown into something we might not have chosen. So the idea that that that that's not an aspect of our existence um which as you describe in rand's views, she sounds more like start she sounds more like it either it's not an aspect of our existence or at least we ought to sort of aim at its not being an almost </s><s>[INST] act as if it's not. Yeah, exactly, it's not. [/INST] And so I think from my point of view, I don't I don't pretend that I'm explaining the public reception of her, I'm just sort of trying to, trying to say how I understand her in this um intellectual context, from my point of view, that's not something big big to miss and the ambition to think that really what's happening is that we're all the same, we're all rational beings, we're all being. So if we just got the axioms of our existence rights and made good judgments and reasoned in an appropriate way, would um optimize ourselves. That feels to me like a kind of natural end point of the philosophical tradition. I mean, Plato starts off with a view that helps us in that direction, and the enlightenment moves us further in that direction, but from my point of view that movement has led us astray because it's missed something really important that's crucial to the kind of being that that we are. </s><s>[INST] Yeah, this is the music [/INST] system, you </s><s>[INST] let's talk about thrown nous and I think you mentioned that in the context of Heidegger. Yeah, so can we talk about Heidegger, who is this philosopher? What are some fascinating ideas that he brought to the world? [/INST] Okay, so Martin Heidegger was a German philosopher, he do know when he was born 1889, by I don't know that only by accident, it's because it's the same year that Vicki Einstein and Austrian philosopher was born and the same year that Hitler was born, so if I've remembered my dates right and someone will call in and correct me otherwise, but that's the way it, it sort of sits in my memory bank. And it's interesting that the three of them were born at the same time, uh Wittgenstein and Heidegger share some similarities, but then it's also interesting that Heidegger was um was a Nazi. I mean, this is a very disturbing fact about his personal political background. Um and so it's something that anyone who thinks that things that he said might be interesting has got a content with Heidegger </s><s>[INST] was born in Germany, Hitler in Austria, Wittgenstein is Austria also, but so you have to, when when you call Heidegger Nazi, you have to remember, I mean, there was millions of Nazis too. So, like, there are parts of their that's the history of the world, you know, there's a lot of communists, marxists and uh nazis in that part of history. [/INST] Absolutely. And, you know, one of the discussion points as well, was he just a kind of social nazi, you know, I mean, you know, he went to parties with them and stuff, or is he like, did he really believe in the ideology and that that's a Choice point? And and, you know, we could talk about it if, if you want, he he held a political position. That's one of the relevant parts in 1933, he was made rector of the University of Freiburg, that's like the president of the university, um and that was in Germany, all the universities are our state universities, and so that's a political appointment. </s><s>[INST] Can we just pause on this point from an existentialist perspective, what's the role for standing up to evil? So, I mean, I think camus probably had something to say about these things because he was a bit of a political figure. Like, do you have a responsibility not just for your decisions, but you know, if the world you see around you is um going against what you believe, somewhere deep inside is ethical. Do you have a responsibility to stand up to that, even if it costs you your life or your wellbeing? [/INST] You ask from an existential perspective, and there's lots of different positions that you could have. So let me tell you something in the area of what I think I might believe, which comes out of this tradition. Um and it's this uh if you live in a community where people are being dragged down by the norms of the community rather than elevated, then there's two things that you have to recognize. One is that you bear some responsibility for that, not necessarily because you chose it. Uh maybe you reviled it, Maybe you were against it, but there's some way in which we all act in accordance with the norms of our culture. We all give into them in some way or another. And if those norms are broken, then there's some way in which we've allowed ourselves to be responsible for for broken norms, we've become responsible for broken norms and I do think you have to face up to that. I think that um let's just take gender norms. Maybe the gender norms are broken, maybe the way men and women treat one another, the way men treat women is broken. You know, maybe there's maybe it is, maybe there's I'm not making a substantive claim, I'm just saying, you know, lots of people say it is. And if you're in a culture where uh those norms take root, you you don't get to just isolate yourself and pull yourself out of the culture and think I don't have any responsibility um that you are already a part of the culture, even if you're isolating yourself from it, that's a way of rejecting the sort of part you play in the culture. But it's not a way of getting behind it. Now, you're playing that role differently. You're saying, I I don't I don't I don't want to take responsibility for what's going on around me and that's a way of taking responsibility by refusing to do it. So I think we're implicated in whatever whatever is going on around us. And if we're going to do anything in our lives, we ought to recognize that, recognize that even in situations where you maybe didn't decide to do it, you you could be part of bringing other people down and then devote yourself to try to figure out how to act differently so that the norms up update themselves. And I think this is not a criticism of people. And to Alyosha, who we mentioned in the Brothers Karamazov, he's a character, he's a kind of saintly character um, in the brothers Karamazov, but that one crucial moment in his, in that story when he realizes how awful he's been being to someone without ever even intending to do that. It's Grishenko who is this sort of fascinating woman and she's a very erotic woman. She's sort of sexual and, and, and Alyosha, In my reading of it is kind of attracted to her. But he's a young kid, he's 20 or whatever and he's kind of embarrassed about it and he lives in the monastery and he's thinking maybe he wants to be a priest and he's kind of embarrassed by it. So what does he do every time they run across one another in the street, he averts his gaze and why is he doing that? Because he's kind of embarrassed. But how does Grishenko experience it? Well, she knows she's a fallen woman and she knows that Alyosha has this other position in society. So her read on it is he's passing judgment on me, he can see that he doesn't want to be associated with me, he can see that I'm a fallen woman, he knows that in order to maintain his purity. He's got a reason, he's got to avoid me? That's not what Alyosha intended to do? But that's the way it's experience. And so there's this way he comes to recognize, oh my God, like what I'm supposed to do is love people in Dostoyevsky's view of things. And what I'm doing instead is dragging this poor woman down, I'm making her life worse. I'm making her feel terrible about herself. And if I actually came to know her, I'd recognize her condition is difficult. She's living a difficult life. She's making hard choices. And why don't I? You know, why don't I see that in her face instead of this other thing that's making me want to avoid her. And that's a huge moment. But the idea is that we are implicated in bringing other people down whether we want to be or not. And that's our conditions. So </s> |
<s>[INST] act. You [/INST] know, he was like, you never watched sports, have you never seen a guy on the golf course smack his club or throw their helmet? Like, you know, there was the, there's a guy Justin bonanno is a poker player and he's a super for lack of a better word, offended by everything. And he was equating my throwing a stick on the ground to violence against women, domestic abuse and the idea that like this makes women feel unsafe to play poker. And so that was kind of a running joke for the last two weeks where every time I sat at a table, the guy would be like, oh, I feel unsafe. Yeah, </s><s>[INST] yeah, [/INST] So it was a, you know, a player on the button raised. David peters, very aggressive player. He, he went all in from the blind and I had a pair of pocket tens. So I went with my tens and he had queen 10 of spades. So I was good. I have the way the best hand The flop was like King 931 spade turn was like the eight of </s><s>[INST] spades. So [/INST] now he has a flush draw and the river was another spade. So he got spade spade and he made, he made a flush, </s><s>[INST] but statistically you were winning the whole time. [/INST] Yeah, I was winning up until the last, </s><s>[INST] what did he go all in on, was it a bluff [/INST] he made, what's considered like a pretty standard played in modern poker where, you know, a guy raised and he was just trying to pick up, you know, what was there And he he ran into a hand in the big blind and you know, he got lucky. </s><s>[INST] So what was the, throughout the strategy of preparation and strategy of play? So you're playing so many days is are you trying to ignore the results and stick to a particular strategy? [/INST] Yes. For the most part, you know, what I'm trying to do is like if I formulate a strategy for the whole seven weeks because there's a very, there's a varying degree of buy ins to like you have small ones, like 1500 then you got like $250,000 buying. So I map out the seven weeks and right, I'll give little bit of mental energy to the 1500 which means I'll be on my phone. I'm not gonna I don't care as much about this one, but the 2 50 k fully engaged, fully focused, you know, up against obviously the higher the buying, you know super top competition and you know, as far as strategy goes focusing on each day playing the best I can not the result like because if you focus on the result, your your focus in the wrong place, your focus should be on the decisions you actually make right. And if you're making good decisions consistently, you have to continue to do that. The frustrating part is this with poker, unlike chess or other things, making the best possible decision doesn't mean you win often you lose you don't chess. </s><s>[INST] Well magnus Carlsen has also talked about that there's some non deterministic thing about chess too given the limited uh cognitive capacity of the human mind. So he he says that the world championship should have 2030 40 50 games, not not the few that they have. It's too low of a sample. So in that sense, the high stakes poker tournaments are very too low sample. [/INST] Sure. Yeah. Well when you think of the world series of poker. So you as you said, I lost about one million right In one tournament, that was 500,000. So then, you know, like a few others here, hi buying tournament. So the sample or the amount was, you know, 40, 50 total tournaments with, you know, high variance and if you don't run well or do well in the highest buy ins, you know, you're gonna have a losing summer. </s><s>[INST] So you did a podcast on the mental game a few years ago and that's just something you really care about. So what aspects of the mental game in poker is most difficult to master? I [/INST] think the most difficult thing for people is self awareness, right? And and resilience self awareness to know, okay, so, you know, again, is it, am I am I not doing as well as I could be because of luck or is there things that I can learn? And I always look to mistakes as opportunities I really do when I make a mistake in a poker hand, right? Call it a breakdown or whatever, that's where breakthroughs happened. I'm like, oh, you know what I could have done here, I could have done this and that would have been really good and I'm gonna do that going forward. So I think like with anything, um, you know, when you start out playing golf, like your goal is to just hit the ball right? Then you try to hit it in the air, Then you're trying to hit it straight, then you're trying to hit it on the green. Then you're trying to hit it close to the green, to the point where the pros get where you know, they're so finite. They're trying to hit it 63 yards and spin it back three yards there. It's imperfect. Like they don't hit the perfect shot because the perfect shot for them is it goes in, but they try and make the mistakes, smaller and smaller and smaller poker is the same. We all make mistakes consistently. The goal is to minimize especially the big ones. What </s><s>[INST] was the lowest point for you psychologically in poker in general? Actually, maybe it was this year, maybe it was in general. Do you remember there was times in your life, Speaking of resilience that were extremely difficult to you mentally. [/INST] Yeah. So early on, you know, as basically, as you know, as a teenager, I was playing in Toronto and then in my early twenties I'm like, I'm going to Vegas, right? And I thought I was the best 21 </s> |
<s>[INST] It blows up who suffers, the users. They already got, the people that created that already got paid. [/INST] Exactly. That's why you pay the guy who makes the break software for your train last. And you make sure he writes the train every day. </s><s>[INST] So that you're basically describing the complexity of a distributed system that's fundamentally game theoretic. And like, if we think about turtles all the way down, humans all the way down. I mean, at the very bottom, it's still human nature. Is there something you can say formally about human nature? To try, you said you can't, there's certain parts of the system that can't fail. Some people talk about nuclear war in that same kind of way. That there's this game theoretic construction of mutually assured destruction that rhymes. See, I'm a poet. That system can't fail because we're gonna blow everyone up. But you can't formally say for sure it's not going to fail. So like, you're basically trying to chase, like statistically reduce the probability that these particular critical aspects will fail. And then you test, I guess, by deploying in the real world [/INST] at small scale to see where things go wrong. Yeah, it's a great question. And the problem with game theory and mechanism design is that you can develop this concept of a rational actor and I don't think in my life I've ever met a rational actor. There's a rational actor on Tuesday, but any other day of the week who the hell knows? And I think there was a book, Freakonomics, and there's a few of these things where it just shows again and again where people behave in ways that are against their best interest. So then you have these protocol designers and they say, well, we need an honest majority for this thing to work. Then they say, okay, we'll create this incentive model and rational actors will behave with that incentive model and say, well, the individual won't do that. but the firm, the government, the entity will. The problem with that is we have a lot of counter examples where the system was actually behaving in weird ways. Like we almost completely eradicated the human population twice in the 20th century. Once during the Cuban Missile Crisis, and again in the 1980s, there was a Russian colonel and they installed a new satellite system and it said, hey, the Americans are launching missiles at us, you need to turn the key in, launch all the missiles in the silo. And he said, oh, that's not right. That doesn't seem right. He was reprimanded for not launching the missiles. So in both cases, a single person stood against the systems of superpowers between us and nuclear annihilation. So in general, we're really bad at building these types of things. So what you look for instead is say, can the system be self-correcting? It's not about avoiding a problem. It's more about can the problem be resolved? And that's how nature engineers things. It gives you an immune system. It gives you the ability to heal if a rainforest has a fire or some catastrophic event, the ecosystem will find a way to patch things up. So it's a better question of how do you align the incentives over the long-term of a system where all the actors within this system, when an event occurs that disrupts it, have an incentive to push it back into a healthy, productive, useful state, which is going back kind of to that complexity theory stuff that we began with and a little bit about, how do you handle modern economics? Like for example, we knew this coming into the COVID crisis that there would be catastrophic economic disruption throughout the entire world. In the developed world, it was print lots of money and hope to God it works. In the developing world is try not to starve to death. Over a hundred million people were pushed into acute starvation. So acute hunger, it's a terrible situation. But every economist knew we were going into that. So the question is, how do you restart the system? How do you realign the system and so forth and make sure that it doesn't collapse at some point? So it's an imperfect, inexact science. And that's actually one of the things that makes our industry so much fun is that these are kind of like micro experiments for the macro. In the years past, you never got a chance to experiment with monetary policy. I mean, it's like every 20 years, 30 years, you'd have some conference, usually in a cool island like Jamaica, and be like, okay, let's go talk about monetary policy and amend the Bretton Woods Agreement. And these would be nation states, invitation only. And now you have over 8,000 cryptocurrencies floating around all with their own monetary policy and their rules, and it's very Darwinian. A lot are dying, some are succeeding. Anomalies happen like Dogecoin, and you say, God, is this temporary? Is this permanent? Why doesn't this horrible thing die? And then other things you think would be absolutely successful and just take off and be in the top 10, don't really get as much traction. Like Algrind is a great example of that. I mean, Silvio, he's an incredibly bright guy. Every time I go to MIT, we have dinner, and his work is legendary, and it's just beautiful and elegant, and he literally has all the people. He went and hired Tal Robin, and she got an IBM research, and Craig Gentry, the guy who did homomorph encryption under Dan Bonet's there, there's all these amazing people on that team, and they have money in the VCs, so you'd say, okay, that's a contender. But if you look at market adoption, Ethereum Classic sometimes is above it, </s> |
<s>[INST] which is uh, create a basic framework of the kind of things you should be observing and what are the measures metrics of success and then just observe and see which things lead to success. More success and which lead to less success and there's a delta. Like when you, when you see a thing, first of all, the way machine learning works is you predict, you see a position, you see a situation and then you predict how good that is. And then you watch how it actually turns out. And if it's worse or better, you adjust your expectations through that process. You can learn quite a lot the, the challenges and this might be a very true challenge in grappling is like in driving, you can't crash. So there's a physical world in chess. For example, where this approach has been exceptionally successful, you can work in simulation. So you can have um ai system that for example, with as in the case with Alpha zero by deepmind, Google's Deepmind, it can play itself and simulation millions of times billions of times. It's difficult to know if it's possible to do that in simulation for for for anything that involves human movement, like grappling. So that's my sense is if we first look at the hard encoding, if you were to try to describe Gordon Ryan to a machine, how many rules are in there do you think? [/INST] Um First off, let me tell you, that's one of the most fascinating questions I've ever been asked and I'm tremendously happy to, to answer this um how about what we do is this is this is a massive question you've asked. There's a huge amount of ways this get very interesting and very confusing. Let's set some ground rules for the discussion. Uh lex alluded to the idea of man versus machine and chess. Okay. And I think that's a really good place for us to start the discussion. Um I'm going to uh just tell people about a little bit of the history of Man vs chest to give you guys some uh some background on this. In 1968, there was a party in which a highly ranked, not not a world champion, but a highly ranked chess player. And his name was Levi. And he met a a computer engineer at a party and they had a uh a light hearted bet That in a 10 year time frame a human chess player would be defeated by a computer. Now, you gotta remember 1968, computing power was very, very low. The computers that got America to the moon were we're actually pretty damn primitive. Your iphone would kick all of their asses. Um So computational power was very, very low in those days. So interestingly, the chess player fully believed that no computer could beat him in the 10 year time frame. And the the computer engineer was very optimistic that he was wrong and in fact 10 years. uh the computer would win 10 years later they had a competition and the human one decisively, in fact. So computational power simply hadn't risen to that level yet. Through the 1980s, computational power increased but Not sufficient to get the championship level. There were computer programs in the 1980s which were competitive with good solid chess players but not world beaters. Um understand right from the start that there's a fundamental problem here. The number of options that the two players in a chessboard can run through is astronomically high. There are 64 squares on a chessboard. The number of possible options that can, could work or could play out on a chessboard and this is a truly shocking thing for you to think about. The number of possible options is higher than the number of atoms in the known universe. Think about that for a second in terms of complexity. Okay, the number of atoms on this table is massive. Okay, that is an unbelievably large number. Then we're talking about a situation where if a computer had to go through all the options at the onset of a match, they would have to run numbers greater than the number of atoms in the known universe. The number of Galaxies and the number of in our universe is vast. Okay. It's measured in the billions like the number of atoms. That's just the and number so mind blowing. It's impossible. Okay, so no computer is ever going to be able to work with those kinds of numbers. Okay. That I don't even have future generations of quantum computers could work with those kind of numbers. So that's the fundamental problem. Okay, the number of options in a chess match is just so astronomically large that no computer could ever figure out all the available options and make decisions in a given time frame. So that's the fundamental problem. So as lex correctly pointed out, the way you get around this is by the use of heuristics. These are rules of thumb which give general guidelines to action. So for example, and you did. So I could give you a general rule of thumb. Uh don't turn your back on your opponent. Okay, that's a solid piece of advice. There are obviously some exceptions to that rule, but it's a good solid piece of advice to give a beginner. The moment you give that heuristic rule, you rule out a lot of options. Okay, You've already told someone don't turn your back, don't turn your back on someone. So a lot of possibilities have just been turned away right there. So you've cut the number of options in half right there just by giving one heuristic rule. Okay. If you Were decent at J. It's not great but decent. And you knew enough to give say 10 heuristic rules, you could chop that initially vast number of options down by a vast amount and now you're starting to get to a point where if a computer had sufficient computational power, it could start getting through the number of options in that acceptable time frame. So that's the general pattern of the development. Now, things started getting very interesting in the mid 1990s with IBM computer. Deep Blue. There was a great chess champion of the late 19 eighties and early 19 through the 19 nineties called Garry Kasparov, who had been more or less undefeated for a decade in 1996. He took on IBM computer Deep Blue </s> |
<s>[INST] When you say probably the zero. You mean probability close to zero [/INST] to be very, very precise. So, for example, if I have a unit square on the plane and I use a measure in which the on probability measure in which the area of the region is this probability mhm. Then if I draw a curve in that unit square, it has measure precisely zero, precisely not approximately precisely zero. And yet it has infinitely many points. So there is an object that for that probability measure has probability zero. And yet there's infinitely infinitely many points in it. So that's what I what I mean when I say that the things that are probability zero can happen infinitely often in principle. </s><s>[INST] But infinity as far as I and I look outside off and I walk around and I look at people I have never seen infinity in real life. [/INST] That's an interesting issue. </s><s>[INST] I've been looking, I've been looking, I just I don't notice it infinitely small or infinitely big. And so the tools are mathematics, you could sort of apply the same kind of criticism that it is a very convenient interface. [/INST] That's a big debate in mathematics. The intuition ist versus the ones who take, for example, the real numbers as as as as real. And that's a that's a fun discussion. Nicholas johnson has a physicist has really interesting work recently on how if you go with intuition ist mathematics, you could effectively quantized Newton and you find that Newtonian theory and quantum theory aren't that different once you go with </s><s>[INST] it. It's [/INST] really quite interesting. So, so the issue you raise is a very, very deep one and one that I think we should take quite seriously, which is, you know, how should we think about the reality of The Contras Hierarchy one, a love too. And all these, all these different infinities versus just more algorithmic approach. Right? So, where everything is computable in some sense, everything is finite as big as you want, but nevertheless finite. </s><s>[INST] So yeah, they ultimately boils down to whether the world is discrete or continuous in some general sense. And again, we can't really know, but there's just mind breaking. I thought it just common sense reasoning That something can happen and is yet probability of it happening is 0%. That doesn't that doesn't compute for common sense computer. [/INST] Right? Um this is where you have to be a sharp mathematician to really. And I'm not </s><s>[INST] sharp as one word. What I'm saying is common sense computer is I I mean that in a very kind of in a positive sense because we've been talking about perception systems and interfaces, if we were if we are to reason about the world, we have to use the best interfaces we got. And I'm not exactly sure that game theory is the best interface we got for this. And the application of mathematics, tricks and tools and mathematics to game theory is the best we got when we are thinking about the nature of reality and fitness functions and evolution period. [/INST] Well, that's a fair rejoinder. And I think that um that was the tool that we used. And if if someone says here's a better mathematical tool and here's why this is this mathematical tool better captures the essence of Darwin's idea, john Maynard smith didn't quite get it with evolutionary game theory, there's this better this thing. Now there are tools like evolutionary graph theory which generalized evolutionary game theory. And then there's quantum Game three. So you can you can use quantum tools like entanglement, for example, as a resource in games that that changed the very nature of the solutions of the optimal solutions of the game theoretic. </s><s>[INST] Well, the work from Yale is really interesting. It's a really interesting challenge of that kind of of these ideas where, okay, if you have a very large number of fitness functions or let's say you have a nearly infinite number of fitness functions or a growing number of fitness functions, what what kind of interesting things start to emerging, emerging if if you are to be an organism, if to be an organism that adapts means having to deal with an ensemble of fitness functions. [/INST] Right. And so we've actually redone some of our own work based on there. And this is the back and forth that we expect in science. And what we found was that they in there simulations. They were assuming that you couldn't carve the world up into objects that uh And so we said, well, let's relax that assumption allow organisms to create data structures that we might call objects. And an object would be you take you would do hierarchical clustering of your fitness payoff functions. The ones that have similar shapes. If you have 20,000 of them, maybe these 50 are all very, very similar. So I can take all the perception action fitness stuff and make that into a data structure. And we'll call that a unit or an object. And as soon as we did that, then all of their results went away. It turned out they were the special case and that the the organisms that were allowed to only see that that that were shaped to see only fitness payoffs were the ones that were. So So the idea is that objects then what are objects from an evolutionary point of view? This bottle? We thought that when I saw a bottle, it was because I was seeing a true object that existed, whether or not it was perceived evolutionary theories suggest a different interpretation. I'm seeing a data structure that is encoding a convenient way of looking at various fitness payoffs, I can use this for drinking, I could use it as a weapon. Not a very good one. I could be similar with head with it. Um, if my goal is mating, this is pointless. So, I'm seeing for what I'm coding here is all sorts of actions. And the payoffs that I could get when I pick up an apple. Now, I'm getting a different set of actions and pay and pay offs for when I pick up a rock, I'm getting. So for every object, what I'm getting is a different set of payoff functions. Um, and and act with various actions. And so once you allow that, then what you find is once, once again that truth goes extinct. And the organisms that just get an interface are the ones that that win. </s> |
<s>[INST] So we've talked about metrics a lot. There's a really cool uh, in terms of bench press and weightlifting pioneers, metric that you've developed that we don't have time to talk about, but it's really cool that people should look into. Its rethinking the way we think about metrics and weightlifting. But let me talk about metrics more broadly, since that appeals to you in all forms, let's look at the most ridiculous, the biggest question of the meaning of life. If you were to try to put metrics on a life well lived, what would those metrics be? [/INST] A friend of mine, randy Katz said this, he said, uh, you know, when, when it's time to sign off, it's, it's uh, the measure isn't the number of zeros in your bank account. It's the number of inches in the obituary in the new york times, he said it, I think, you know, having and you know, this, this is a cliche is that people don't die wishing they'd spent more time in the office, right? Uh as I reflect upon my career, uh there have been, you know, a half a dozen or a dozen things say I've been proud of. A lot of them aren't papers or scientific results, certainly my family, My wife, we've been married more than 50 years, kids and grandkids, that's really precious uh uh education things I've done, I'm very proud of, you know, books and courses. Uh I did some help with underrepresented groups that was effective. So it was interesting to see what were the things I reflected, you know, I had hundreds of papers, but some of them were the papers like the risk and great stuff I'm proud of, but there's a lot of them were not those things, so people who are just spend their lives going after the dollars are going after all the papers in the world, you know, that's probably not the things that are afterwards, you're going to care about. When I was uh just when I got the offer from Berkeley before I showed up, I read a book where they interviewed a lot of people in all walks of life and what I got out of that book was the people who felt good about what they did was the people who affected people as opposed to things that were more transitory. So I came into this job assuming that it wasn't going to be the papers. There's going to be relationships with the people over time that I would I would value And that was a correct assessment, Right? It's it's the people you work with, the people you can influence. The people who can help is the things that you feel good about towards into your career. It's not not the stuff that's more transitory. </s><s>[INST] I don't think there's a better way to end it than talking about your family. The over 50 years of being married to your childhood sweetheart. And I think [/INST] I can add is how when you tell people you've been married 50 years, they want to know why I can tell you the nine magic words that you need to say to your partner to keep a good relationship and the nine magic words are I was wrong. You were right. I love you. Okay. And you got to say all nine, you can't say I was wrong, you were right. You're a jerk. You know, you can't. So yeah, freely acknowledging that you made a mistake. The other person was right and that you love them really gets over a lot of bumps in the road. So that's what I pass along beautifully. Put </s><s>[INST] David is a huge honor. Thank you so much for the book. You've written for the research you've done for changing the world. Thank you for [/INST] talking today. Thanks for the interview. </s><s>[INST] Thanks for listening to this conversation with David patterson and thank you to our sponsors the Jordan Harbinger Show and cash up. Please consider supporting this podcast by going to Jordan harbinger dot com slash lex and downloading cash app and using cold lex podcast, click the links by the stuff. It's the best way to support this podcast and the journey I'm on. If you enjoy this thing [/INST] subscribed on youtube, </s><s>[INST] review it with 5000 other podcast, support on Patreon or connect with me on twitter elects Friedman spelled without the E. Try to figure out how to do that is just F R I D M A N. And now let me leave you with some words from Henry, David Thoreau. Our life is frittered away by detail. Simplify, simplify. Thank you for listening and hope to see you next time. [/INST] </s> |
<s>[INST] And I I just um I admire the possibility of a great legacy of that. That is bigger than either of the fighters. I think with Kirby, he kind of uh he's not as concerned about legacy. I think there's a you're [/INST] a promoter's dream because you want the rematch. And the only thing that makes more money than the rematches, the trilogy. You gotta split the trail, split the rematch, you hope Connor wins and then you have the trilogy fight and now you're all in. </s><s>[INST] Yeah, I can't get into computers head. But I know Putin just the game the entirety of it, especially at the time, especially if it was trump as president uh if he was as president at the time and and Putin and in Russia and just knowing how masterful Connor is at like because Connor would would be a different color. I think it would be a calmer Connor, like there would be a different uh because you don't want to be over the top corner with the Russian people know that it's like uh [/INST] dangerous ground. That's that was the episode in the hotel in Brooklyn. Yeah, when um some of the Russian guys confronted uh Artem and then Connor came over. </s><s>[INST] It's not but that the danger of that, I mean, there's the element of just like real danger and the real almost of war. It's uh I don't know, it's [/INST] it was like when, when uh when jail Sonnen was talking so much smack maybe was against Vanderlei silva. I don't know, there's one of those fights where they just didn't think he was gonna make it out of brazil. Yeah, americans, don't get it. Yeah, people take some of that ship in different parts of the world very, very seriously. Yeah, </s><s>[INST] but that's what makes it beautiful. That's uh that's what makes a great story. And I think fighting is very much about the stories, not just about the particular outcomes of a fighter, the skill set matching or like the chest of the of the fight. It's also about the story of the greater like context of societies of warring were like warring cultures. We're still we're still going, we're no longer can have great big hot wars between nations because of nuclear weapons. This is our wars that we can have and you know, in some sense, I feel robbed of the great war that could have happened. [/INST] It doesn't mean there aren't lots of wars going on. But yeah the big one is not gonna happen. There's too much of a balance of power with you know nuclear weapons and technology and stuff but it's not the end of war. </s><s>[INST] No. Do you think there's always gonna be a war? [/INST] I think there'll always be war especially in underdeveloped parts of the world. Um Isn't there </s><s>[INST] always underdeveloped relatively parts of the world? [/INST] Yeah. I mean at some point though you'd think, I mean the way that you know technology is expanding and we're bringing technology to weird parts of the world that you wouldn't uh think of as technologically advanced. The way that uh the chinese are inhabiting certain areas for mining purposes and things like that. I think underdeveloped parts of the world will get developed quickly. </s><s>[INST] I just wonder like what the nature of that war might be could be cyber, it could be all those kinds of things. I [/INST] think in developed nations it's going to be cyber. I think that's probably the next phase of war. But I mean I think you talk about parts of the world like the Middle East and it's just still gonna be warring tribal factions. We can't even begin to understand what those people are fighting about over there yet. Yet everyone sitting in America on their couch has an opinion. Like you can't even begin to understand it. I I sure can't. </s><s>[INST] Yeah it's back to the principles discussion when um when when what's violated is much deeper than just kind of uh anything we can even in a middle class existence can't even comprehend [/INST] a lot of times. American soldiers will go to war because that's what they're told to do. And they maybe they disagree with the orders and maybe they agree with the orders. But I get a sense that people in the Middle East fighting all believe in what they're fighting for. It's not it's not a thing where they're told to go do it. I believe they they really believe that what they're doing is the right thing and they're defending some sort of principle. </s><s>[INST] Are you generally optimistic about the future? Speaking of war of human civilization, do you think? Well uh like you know, people talk about the fermi paradox and asking, you know, why haven't aliens visited us if you believe they haven't visited us? You know, one of the thoughts is that there's a kind of a great filter that intelligence civilization reached a point where it destroys itself naturally. So that's why we haven't seen them. They don't last very long. That does seem to be a kind of we seem to be advancing faster and faster and faster. We keep developing more and more powerful ways of destroying ourselves in all kinds of ways. Not even, you know, just even to say nuclear weapons alone, but there's all kinds of new ways engineered pandemics nanotechnology g all those kinds of things. It seems to be that the argument that we I was going to destroy ourselves in some kind of creative way very shortly Is uh not too crazy for an argument to make. Are you more optimistic or pessimistic about the prospects of human civilization and maybe the 22nd century? Like is it possible that your generation is the last generation to be alive on earth? [/INST] No, but I wouldn't say that five generations from now, that won't be that that could be true. I guess. I think of it really selfishly. I'm a big believer that when your time here on earth is over, The overwhelmingly vast majority of people will be forgotten within 12 calendar months. People with no family will be forgotten sooner. And so I don't give a lot of thought to what will happen to earth or mankind when I'm gone. I give more thought to maximizing my time here now and I want to do it in a way where I don't um, I'm not overtly hindering the future of civilization or humankind, but I'm definitely taking a me first approach to how I live on earth. </s> |
<s>[INST] but it still needs to be better. So I've got a chance to interact with a lot of soldiers that served in Iraq and Afghanistan. And now a lot of soldiers from all different kinds of nations in Ukraine went to the front. There's a bond between soldiers like any other. I don't know if you can speak to why do you think that is on the opposite side of PTSD. There's a deep human connection. There's like a love for each other. What is that? [/INST] What is that about war and combat that creates that common? Well, you're seeing, we've talked earlier about that vulnerability, right? So I believe that combat, I believe that most survival situations strip away all ego. And I mean, there are a couple of different layers to this, but I have not served in war. So I wanna be cautious here, but from what I know just about psychology and also from my own experience of survival type experiences, when you're with a group of people and all the ego stripped away, nothing else matters. The focus is on the here and now and a specific mission or your day to day, you can get really close. You're very, very vulnerable. And also in my experience, the guys I work with who have served, there aren't a lot of people who understand what they've been through. Not only some of the unspeakable things they've been through in combat, but some of the things that they feel are unspeakable about returning, especially if they are experiencing trauma, a lot of them, some of the things that service members with PTSD are the most reluctant to disclose is the feeling like they may not know if they love their children anymore or their wife. That they don't even know if they can love anymore. That they feel emotionally numb. That they wanna kill someone. That they have a whole lot of racist beliefs and thoughts. There are a lot of things that can be associated with PTSD that aren't as clear or expected. And these guys don't have many people who understand it or they don't think they would, </s><s>[INST] but a lot of their fellow service members do. And so I'm going back to Ukraine and boy, nothing makes reveals the human condition. In a more pure form than war, especially the kind of war you get in that part of the world, especially the war in Ukraine, which is a very 20th century kind of war. Brutal, brutal. Well, like I mentioned in a few different ways, you're exceptionally successful by I think the best definition of success. You're doing what you love and you're one of the best people in the world to doing it. And so what advice would you give to young people that look up to you that saw you in the trial, which is your most public facing thing and are just looking, young people that are looking to find what they wanna do with their life career wise [/INST] or what advice career wise or? I love that question. What would you tell them? I'm gonna tell them something my dad told me. He said to me, Shannon, just pick anything. Pick anything, if you like it at all studying it, just pick it. He was like, look, don't worry about the job. You don't even know all the jobs that exist. Pick something you like, you will make it your own. And that is exactly what happened. I like psychology. I was reading somehow self-help books. It's not like I had this calling where I, looking back, I can actually create that story because I think now it makes a lot of sense that I do what I do. But I was lost and scared. I started studying psychology. I met a professor who was really inspiring, who wasn't even a psychology professor, but he was public policy. I stayed in touch with that professor. He is a dear friend still to this day. That was 20 years ago. We do research together in Mexico, integrative research with public policy officials and environmental engineers. And I get to be the psychologist on the trip. I never ever dreamed that that sort of stuff could happen. I didn't know about forensic psychology. I also wanna warn anybody who's interested in forensic psychology that it's not like you're solving crimes all day and getting calls by the FBI. You are going to be sitting alone in your home office with your husband, bringing you bowls of cereal and reminding you to go to the bathroom because you haven't gotten up in like 24 hours from the computer and you're gonna have papers all around you and you're just gonna write 75 dense pages with citations of like science. It's brutal. It's academic, but it's fulfilling. My friend Franny posted a meme of one of the girls from Glee or something crying and saying, I'm the happiest I've ever been. And she said, it reminds her when I try to convince her to do forensic site, because I think her mind is perfect for it. You have to be strategic and thorough, but it's a slog, but it's wonderful. </s><s>[INST] It's wonderful. What would you tell? But you're gonna love it. But it's fulfilling. The image of your husband bringing you cereal while you work on the 75 pages is maybe the most romantic thing I've ever heard. So we started on love. Let me ask one last question about the same topic. What's the role of love in this whole thing, in the human condition, [/INST] in this whole experiment we've got going on on earth? I think it's all there is, like that jewel song. </s><s>[INST] How does that go? [/INST] God, I don't sing it, don't get it in my head. Please don't sing it, please don't sing it. There have been some profound moments in my life where I feel like I am closest to kind of the truth of life or what it's all about. And usually there's this resonating sense of love and ease and love for myself, love for other people, sort of like it's all okay, we're all okay, we're gonna get through this. I liked what you said about the harm caused by the misinformation or negative things being said about you. Because you're right, it harms that bigger picture. </s> |
<s>[INST] think that once we crack it, we'll be able to use assembly theory plus telescopes to find aliens. Do you have, Sarah, do you have disagreements with Lee on the number of aliens that are out there? Do actually, yeah. Well, and what they look like. So any of the things we've been talking about is they're nuanced. It's always nice to discover wisdom through nuanced disagreement. [/INST] I do actually, yeah. Well, yeah, I don't wholly disagree, but I do think I disagree. There's nuance there. You can disagree. No, it's fine. It is nuanced, right? So you made the point earlier that you think, once we discover what life is, we'll see alien life everywhere. And I think I agree on some levels in the sense that I think the physics that governs us is universal. But I don't know how far I would go to say to say that we're a likely phenomena because we don't understand all of the features of the transition at the origin of life, which we would say in assembly as you go from the no memory physics to there's like a critical transition around the assembly index where assembly and starts to increase. And that's what we call the evolution of the biosphere and brotherification of the biosphere. So there's a principle of increasing and that goes back to what I was saying at the very beginning about the physics of the possible that the universe basically gets in this mode of trying to make as much possibilities as possible. Now, how often that transition happens, that you get the kind of cascading effect that we get in our biosphere, I think we don't know. If we did, we would know the likelihood of life in the universe. And a lot of people want to say life is common, but I don't think that we can say that yet until we have the empirical data, which I think you would agree with. But then there's this other kind of thought experiment I have, which I don't like, but I did have it, which is, you know, if life emerges on one planet, and you get this real high density of things that can exist on that planet, is it sort of dominating the density of creation that the universe can actually generate? So like, if you're thinking about counting entropy, right, like the universe has a certain amount of stuff in it. And then, you know, assembly is kind of like an entropic principle, it's not entropy. But the idea is that now transformations among stuff are the actual physical histories of things now become things that you have to count as far as saying that these things exist, and we're increasing the number of things that exist. You can disagree. And if you think about that cosmologically, maybe Earth is sucking up all the life potential of the whole universe, I don't know. </s><s>[INST] How's that? Can you explain that a little bit? Why can any one geographical region suck up the creative capacity of the universe? [/INST] Well, I know it's a ridiculous thought. I don't actually agree with it, but it was just a thought experiment. </s><s>[INST] I love that you can have thoughts that you don't like and don't agree with, but you have to think through them anyway. [/INST] The human mind is fascinating. Yeah, I think these sort of like counterfactual thought experiments are really good when you're trying to build new theories, because you have to think through all the consequences. And there are people that want to try to account for, say, the degrees of freedom on our planet in cosmological inventories of talking about the entropy of the universe, and when we're thinking about cosmological arrow of time and things like that. Now, I think those are pretty superficial proposals as they stand now, but assembly would give you a way of counting it. And then the question is, if there's a certain maximal capacity of the universe's speed of generating stuff, which Lee always has this argument that assembly is about time, the universe is generating more states, really what it's generating is more assembly possibilities. And then dark energy might be one manifestation of that, that the universe is accelerating its expansion, because that makes more physical space. And what's happening on our planet is it's accelerating in the expansion of possible things that exist. And maybe the universe just has a maximal rate of what it can do to generate things. And then if there is a maximal rate, maybe only a certain number of planets can actually do that or there's a trade off about the pace of growth on certain planets versus others. </s><s>[INST] I have a million questions there, but do you have thoughts on... [/INST] Just a quick, yeah, I'll just say something very quick. It's a thought experiment. No, it's good. I think I get it. I think I get it. So, what I want to say is, when I mean aliens are everywhere, I mean memories are the prerequisite for aliens via selection and then the concentration of selection when selection becomes autonomous. So what I would love to do is to build, say, a magical telescope that was a memory... Magical. Magical one. Or a real one. Yeah. There would be a memory detector to see selection. So you could get to exoplanets and say, that exoplanet looks like there's lots of selection going on there. Maybe there's evolution and maybe there's going to be life. So what I'm just trying to say is narrow down the regions of space where you say, there's definitely evidence of memory as high assembly there, or not high assembly, because that would be life, but where it's capable of happening. And then that would also help us frame the search for aliens. I don't know how likely it is to make the transition to cells and all the other things. I think you're right, but I think that we just need to get more data. Yeah. Well, I didn't like the thought experiment because I don't like the idea that if the universe has a maximal limit on the amount it can generate per unit time that our existence is actually precluding the existence of other things. Well, I'll just say one thing. But, I think that's probably true anyway, because of the resource limitations of other things. So I don't like your thought experiment because I think it's wrong. No, I do like the thought experience. you try to say is like there is a chain of events that goes back that's manifestly co-mated with life on Earth, and you're not saying that life isn't possible elsewhere, you say that there has been these number of things, contingent things that have happened that have allowed life to merge here. That doesn't mean that life can't emerge elsewhere, but you're saying that these, the intersection of events may have, may be concentrated here, right? And I think there's, um, not exactly. It's more like, um, like, uh, you know, if you, you look at, say the causal graphs are fundamental, maybe space is an emergent property, which is consistent with some proposals in quantum gravity, but also how we talk about things in assembly theory, then the universe is causal graphs generating more structure in causal graphs, right? So this is how the universe is unfolding. And maybe there's a cap on the rate of generation, like there's only so much stuff that gets made per update of the universe. And then if there's a lot of stuff being made in a particular region that happens to look the same locally spatially, that's an after effect of the fact that the whole causal graph is updating. Like it's, uh, yeah, I don't, I don't know that. I think that that doesn't work. I don't think it works either, but I don't have a good argument in my mind about, but I do like the idea of the capacity that universe, because you've got the number of </s> |
<s>[INST] different sort of future. I don't think he, at least I haven't heard him talk about this big broad history and future, so the Marxist ideology and so on. Not that he's afraid of [/INST] or something. It's just not how he thinks about it. I think he's a practical thinker. He is running, even if he should be afraid of it too, because he is a major politician running for president. I think what people want is they want the left wing of the possible, or at least the segment of the party that was voting for him, the Democratic Party is voting for him. They wanted something that was a step or two removed from what they had now and was visionary, but not so far removed that it seemed like a scary leap. I think we lost a chance in 2016 to elect someone that I think would have beaten Trump or at the very least would have been close. Do you think the Democrats screwed him over? Yes, not in the way of deliberate or direct vote working, but they put their thumb on the scale for sure. I mean, it's not even conspiracy theory. There's all this stuff in the debates about Clinton's people being fed questions and whatever else, and just the tone of the media. The media was extremely dismissive and hostile to him. I love that Bernie still does the Fox News Town Hall, because they're just him speaking to the people, and he's not afraid of going on any outlet and making his case. But I think a lot of the liberal media in particular always had it out for Bernie Sanders. </s><s>[INST] What was that? Because that was really annoying. That was really annoying, how dismissive they were. I've seen that in some other candidates. They were dismissive towards Andrew Yang in that same way. So forget the ideology. Why are they so smug sometimes towards certain candidates? What is that? Because I think that's actually at the core to a degree if Democrats or any party fails, that it's that smugness, because people see through that. [/INST] I think a lot of these people are friends, even if they don't know each other, they're friends, because they went to the same schools. They know the same people. They have the same broad, just ideology and worldview. So they had a sense of what the Democratic Party should be and who should be running and who is going to win, and also what was serious and unserious. So Bernie would say some things about the world that objectively tell a lot of people seem correct, or at least pretty close to correct. A journalist would just look at him like he's from outer space. To some extent, this also happens to people on the right. People on the right often say things that I find repulsive or just wrong, but there's parts of the media that would describe their certain views as illegitimate or outside the boundaries of acceptable conversation. I think there should be a few things outside the boundary of acceptable conversation, hate speech, and so on. But there's this attempt to say their views are illegitimate, and therefore, anyone who votes for them for any reason is illegitimate too. That's one reason why I think it fueled a lot of resentment and will ultimately end up fueling the extremes of American politics that people feel like they're not being listened to. </s><s>[INST] Yeah, and some of it is also style speaking and personality where, if you're not willing to sort of play kind of a game of civility, there's like a proper way of speaking if you're a Democrat. If you're not doing that kind of proper way of speaking, people dismiss you. I think in certain sense, whatever you feel about him, people dismiss Donald Trump for the same reason where it's the style speaking, the personality of the person that he's not playing by the rules of polite society, of polite politician society and so on. And that's really, that troubles me because it feels like solutions, the great leaders will not be polite. They're not going to behave in the way they're supposed to behave. And I just wish the media was at least open-minded to that, which I guess gives me hope about the new media, which is like more distributed citizen media, right? That they're more open-minded to the revolutionary, to the outsiders, right? I actually first, I really like Bernie Sanders. I first heard him in conversation with Tom Hartman. He had these like weekly conversations and just the authenticity from the guy. I didn't even know any context. I didn't even know, honestly, he was a democratic socialist or anything. The authenticity of the human being was really refreshing. And we, I guess, decided to run for president. That was really strange. I was like, surely this kind of, this person has no chance. Just like he seemed too authentic. He seemed too like he's not going to be effective at playing a game of politics. So it was very inspiring to me to see that you don't necessarily need to be good at playing a game of politics. You can actually have a chance of winning. Yeah, that was really inspiring to see. What about some of the other popular candidates? What do you think about AOC? I don't know if she self-identifies as a socialist or not. [/INST] She does self-identify as a democratic socialist. I think she was a very inspiring figure for a lot of people. She was kind of out of this Bernie wave of the first set of Bernie candidates in 2018 that identified with him instead of the Democratic Party establishment. I think that, she's still developing as a politician. It's very difficult when you're in a deep blue district. And when you don't often have to worry about re-election or talk to, but modulate your rhetoric to win over swing voters in your district. But then you're immediately a national and cultural figure. So AOC basically goes from her views, which are compelling, in my mind, a lot of her programmatic views are compelling, wins her district and then has her own rhetoric, which to me, compared to Bernie, owes itself more to the academic left in the way that a lot of the left has learned to talk. I don't mean academic in the sense that she's like a Marxist or whatever else, but academic in the way that she may be using at times like confusing language to convey basic points when she gets into like the language of intersectionality and whatever else. </s> |
<s>[INST] So without this isn't like confidential stuff, but you sitting on a porch looking over the world, looking at the work that Andre is doing that Ellen is doing with Tesla autopilot. Do you like the trajectory of where things are going on [/INST] there? Making serious progress? I like the videos that people are driving debate of stuff like it's taken some pretty complicated intersections and all that, but it's it's still an intervention for dr I mean I I have all of the current autopilot. My Tesla, I use it every day. </s><s>[INST] Do you have full self driving beta or not? So you like where this [/INST] is going? We're making progress. It's taking longer than anybody thought, you know, my my wonder was, is, you know, hardware three, is that enough computing off by two off by five by 10 off by 100. And and I thought it probably wasn't enough, but they're doing pretty well with it now. and one thing is the days that gets bigger, the training gets better. And then there's this interesting thing is you sort of train and build an arbitrary size network that solves the problem. And then you? Re factor the network down to the thing that you can afford the ship. Right? So the, the goal isn't to build a network that fits in the phone, it's to build something that actually works. Mhm. And then then how do you make that most effective on the hardware you have? And they seem to be doing that much better than a couple of years ago? </s><s>[INST] Well, the one really important thing is also what they're doing well is how to iterate that quickly, which means like it's not just about one time deployment. One building is constantly hearing the network and trying to automate as many steps as possible. Right? And that's actually the principles of the software to like you mentioned with Andre is uh It's not just, I mean, I don't know what the actual his description of software 2.0 is if it's just high level fill software, their specifics. But the interesting thing about what that actually looks in the real world is is that what I think Andre calls the data engine, It's like, it's the iterative improvement of the thing. You have a neural network that does stuff fails on a bunch of things and learns from it over and over and over. So you're constantly discovering edge cases. So it's very much about uh like data engineering, like figuring out it's kind of what you were talking about with 10 stories, you have the data landscape, They have to walk along that data landscape in a way that uh it's constantly improving the neural network and that that feels like that's the central pieces. So [/INST] there's two pieces of it, like you find education that don't work and then you define something that goes get your data for that. But then the other constraint is whether you have to label it or not, like the amazing thing about like the GPT three stuff is it's unsupervised, so there's essentially infinite amount of data now, there's obviously infinite amount of data available from cars of people successfully driving. But you know, the current pipelines are mostly running on labeled data, which is human limited. So when that becomes a new unsupervised, right, it will create unlimited amount of data, which is no scale. Now the networks that they use that data might be way too big for cars, but then it will be the transformation from now we have unlimited data. I know exactly what I want. Now, can I turn that into something that fits in the car And that that process is going to happen all over the place every time you get to the place we have unlimited data And that's what software 2.0, is about unlimited data training networks to do stuff without humans writing code to do it. </s><s>[INST] And ultimately also trying to discover, like you're saying this self supervised formulation of the problem. So the unsupervised formulation of the problem, like uh you know, in driving, there's this really interesting thing, which is you look at a scene that's before you and you have data about what a successful human driver did in that scene. You know, one second later, it's a little piece of data that you can use just like with GPT three as training currently, even though Tesla says they're using that, it's an open question to me how much, how far can you, can you saw all of the driving with just that self supervised piece of data and like I I think [/INST] that's what comedy, </s><s>[INST] that's what I'm a i is doing. But the question is how, how much data? So we're comedy doesn't have is as good of a data engine for example, as Tesla does. That's where the like the organization of the data. Uh, I mean as far as I know, I haven't talked to George but they do have the data. The question is how much data is needed because we say infinite very loosely here. It's And then the other question which you said, I don't know if you think it's still an open question is are we in the right order of magnitude for the compute necessary? Um, that is this is it like what Elon said this chip that's in there now is enough to do full self driving or doing another order of magnitude. I think nobody actually knows the answer to that question. I like the confidence that Ellen has. But [/INST] yeah, we'll see there's another funny thing is you don't learn to drive with infinite amounts of data. You learned to drive with an intellectual framework that understands physics and color and horizontal services and laws and roads and you know, all your, your experience from manipulating your environment. Like look, there's so many factors go into that. So and then when you learn to drive, driving is a subset of this conceptual framework that you have. Right? And so self driving cars right now, we're teaching them to drive with driving data. You never teach you human to do that. You teach human all kinds of interesting things like language like don't do that, you know, watch out. You know, there's all kinds of stuff going on. </s> |
<s>[INST] Uh, well, this every every book is a person with some of my best friends are inside that book. [/INST] Yeah, it's an amazing book and there's no doubt about it. </s><s>[INST] I think it's some books are defined by your personal relationship with them and that one was definitive and I almost graduated to that one because for the longest time, the idiot was my favorite book of all. Because I identified with the ideas represented by Prince Michigan, I also identified [/INST] that's interesting to </s><s>[INST] Prince Michigan as a as a human being [/INST] the </s><s>[INST] fool because the world kind of my whole life still kind of sees me saw me in my perception, my narrow perception is kind of the fool. And I different from the interpretation that a lot of people take of this book. I see him as a kind of hero to [/INST] be to </s><s>[INST] be a naive, uh, quote unquote fool, but really just a naive optimist and naive in the best possible way. I do believe that that's a [/INST] childlike, </s><s>[INST] childlike is a better, so naive is usually seen as that's [/INST] childish naive. </s><s>[INST] Yeah, but childlike, [/INST] that's why no one enters the kingdom of Heaven unless they become like a child that's Prince Michigan dostoevsky knew that. So that's why you like the idiot. That's so interesting. See, I think I like crime and punishment because well, you identified with Michigan? I think I identified more with Raskolnikov because I was tempted by Lucifer aryan intellect, you know, in in in in the manner that in a manner very similar to the manner he was tempted. But I mean, I think, I think you can make a case that the brothers Karamazov dostoevsky's crowning achievement, </s><s>[INST] not [/INST] something man, he ruined literature for me </s><s>[INST] because [/INST] everything else just felt insipid afterwards, not everything, not everything. I I found some books that in my experience hit that pinnacle. Um The Master and Margarita, that's a deadly book I read that I think four times and I still, there's still, it's unbelievably deep uh there's a Nikos Kazantzakis greek krater, some of his books are, his writing is amazing as well. Did </s><s>[INST] you ever connect with the literary like existentialist camus or people like Hermann Hesse or, or even Kafka, Did you ever connect with those to [/INST] the same degree </s><s>[INST] enough [/INST] to be an influence, you know, you have to be deaf in some fundamental sense not to encounter a great dead friend and failed to learn, you know, and I mean, I tried to separate the wheat from the chaff when I read, you know, and I read all the great clinicians, all of them, perhaps not those who are foremost in the Pantheon. And I tried to pull out what I could and that was a lot. I learned a lot from Freud, I learned a lot from Rogers and I learned a lot from, well from dostoevsky and Nietzsche, I'm going to do a course on dostoevsky and Nietzsche for this Peterson Academy, this is coming up in january, </s><s>[INST] I'm [/INST] really looking forward to it. </s><s>[INST] I [/INST] hadn't thought about doing them together. That'd be fun. That's a good </s><s>[INST] idea. That's a [/INST] good idea. </s><s>[INST] There's a [/INST] feel that idea </s><s>[INST] you often we've them to get really masterfully because there is a there is religious in the broad sense of that word themes throughout the writing of both. [/INST] You know, there is uncanny parallelism in their writing in their lives. So, um, and dostoevsky is deeper than Nietzsche, but that's because he was a writer of fiction. He is definitely that he is definitely that </s><s>[INST] yes, and [/INST] apparently Nietzsche knew more about than people had thought. There's been some recent scholarship on that ground, dostoyevsky didn't know anything about Nietzsche as far as I know, I could be wrong about that. But the thing that dostoyevsky had over, Nietzsche, Nietzsche had to make things proposition in some real sense because he was a philosopher and it's hard to proposition lies, things that are outside your ken, but you can characterize them. And so in the brothers Karamazov, Ivan is a more developed character than Alyosha in in in the explicit sense, he can make better arguments, but Alosha wins like Michigan because he's the better man and dostoyevsky can show that in the actions he can't render it entirely proposition. But that's probably because what's good can't be rendered entirely proposition all. And so, dostoyevsky had that edge over Nietzsche said, well, Ivan is this brilliant rationalist, atheist materialist and puts forward an argument on that front, that's still unparalleled as far as I'm concerned and overwhelms Alyosha who cannot respond, but Alyosha is still the better man. So, which is very interesting. You know, that </s><s>[INST] what, you know, the funny thing about those two characters is you Jordan Peterson seemed to be somebody that at least in part embodies both because you are one of the intellectuals of our time, rigorous and thought, but also are able to have that kind of, what would you describe if you if you remove the religiosity of Russia? There's um what's the good word love towards the [/INST] spirit of encouragement, </s><s>[INST] which, [/INST] well, it's it's, you know, one of the things I did learn perhaps from looking into the abyss to the degree that I have had to or was willing to was that at some level, you have to make a fundamental statement of faith when God creates the world after each day. He says he saw that it was good. You think, well, is it good? It's like, well, there's a tough question, you know, do you want to bring a child into a world such as this, which is a fundamental question of whether or not it's good, it's an act of faith to declare that it's good because the evidence is ambivalent. And so then you think, okay, well, am I going to act as if it's good and what would happen if I did? And maybe the answer to that is I think this is the answer, the more you act out, the proposition that it's good, the better it gets. And so that's dostoyevsky said, this is something else. Every man is not only responsible for everything he does, but for everything everyone else does. It's like, what is that profound? Or are you just insane then you think is what you receive back, proportionate to what you deliver? And the answer to that might be Yes. That's a terrifying idea. And and it's certainly you can see that it's true in some sense, because people certainly respond to you in kind with how you treat them? That's certainly the case. </s> |
<s>[INST] Yeah, you did well. And you just as well. But let me ask you ridiculous question. Who's the greatest of all time freestyle or folk style [/INST] Wrestling Wrestling. Well, I will say my knowledge passed like the year 2000 is really Not that great because you can switch directions after 2000 and before because you can't find any film or anything, you know? And so you </s><s>[INST] hear, you need evidence, you need [/INST] direct evidence, I want to be able to watch him and see him and feel the time to feel their opponents and you know, all those things to really like I hate giving bad answers, you know? So, um, I would, there's just not enough footage of any of those people, you know, we took, we go back to someone like alexander medved, like you can't find footage, you can't find anything on it, you know, it's like who is the wrestling? You know, I'm not sure. So, um, post 2000 I think, and I was just freaked out. So </s><s>[INST] americans [/INST] CTF has the, probably the best argument posted out I think said july of um, if </s><s>[INST] you have the Russian tank that [/INST] guys, Yeah, </s><s>[INST] so who's, who's better? It's neither [/INST] or so july july just wanted the olympics. </s><s>[INST] I understand this, I understand how that works, but there's pretty close, right? Not really, not, not that match, but in general, the match [/INST] up so well, so Kyle won the first one in 17, said july have pinned him the following year, but then Kyle lost and two bronze in 19. Um, and then just lost, I don't want, I don't want a fairly decisively, but it was, it was 6 to 3 and there was a late takedown, He kind of gave it up and maybe it was really competitive, maybe you wouldn't have, um, they're gonna wrestle again like two weeks here, so that, you know Yeah, I mean, you have to say since july of at this point there's nothing else to say unless Kyle proves us otherwise. </s><s>[INST] Yeah, not enough people talk about says your life. Okay. Why you think that guy should go to him in May? I think carl should go down and make some of these guys [/INST] Yeah, they're making enough money wrestling where they don't really feel the need to. It's just </s><s>[INST] terrifying though. Is a heavyweight life would probably like is that could be but heavyweight. [/INST] Well, I don't know if you remember you remember the little Markoff. So below Markov actually was the Russian representative in both styles of 2016 Greco and freestyle. Um And he was to my knowledge, the only person the UFC has ever signed, that was zero in the modern era sign that was zero and zero. And then he actually never end up fighting but weird. Right? </s><s>[INST] So yeah, [/INST] motivation. I don't know. I don't know what the story is. Sometimes out of Russia. I mean, maybe have better sources than I do. Sometimes it feels like to just disappear like they're a world champ or a little bit champion nails and you're like, wait, yeah, there you </s><s>[INST] go. You talked about Russia earlier in the conversation. So what I say, I forgot, but I think steroids, I think somebody's gonna show up to your [/INST] door, I'm worried. I honestly I've said enough bad things where I would be a kind of looking over my shoulder if I </s><s>[INST] want. Uh I for one love the Russians. [/INST] What about chris, how does that make you feel? What </s><s>[INST] about it's fake news? [/INST] Oh really? Just kidding. Yeah, maybe it is. It is, </s><s>[INST] yeah. You know, it's troublesome and I hate cheating in all of its forms. Uh any other like recaps from the Olympics of 2020 Tokyo that stood out to you gable students and like anything like great. [/INST] Uh No, I think America is coming to the point where we're going to compete with Russia every single year in wrestling, which obviously, you know, all right, long, long time ago. Many, many we did. You know, we were great. And then kind of after that soviet union period, I think there was a lot of poverty in that area and that kind of led the wrestling team going down a little bit. And then obviously a lot of those regions, uh the way they found oil and gas in the Caspian sea I believe and they've been Um really kind of on the upswing for the last 20 years. And now America really since 2012 has been on the upswing and wrestling and we're kind of really competing with them and they're not sending a couple of the best guys. So uh, so for those who don't know the olympics got put back in the year. So there are hosting the world 2021 world championships despite the fact that we just had the olympics two months ago. So it's happening next week in Oslo Norway. So like Russia is not sending the number one at 57 the number 1 65. So it's like America is probably gonna win. I think I don't guarantee anything but there's, there's a really good taylor. So competing. America gave any of the olympians that medal the opportunity to not even have to wrestle off. They just got to keep the spots and there's two months later if they meddled. So the only one who's not as gable cables moving on, we have a pretty good guy behind him and Nicholas Dallas cues the world medalist. But then he saw barrels filled in the 79th spot Jane Cocktail in the 92 spot who's a world champion also? So we have a </s><s>[INST] hell of a team. A good squad. Pretty good squad. So given your run ambulatory and one championship that was like one of the most dominant runs in M. M. A. What would you say was like key to your dominance and that long undefeated streak. [/INST] Huh? It probably consistency would be one the fact that I just, I lived and trained the same way no matter where my life was. Whereas a lot of fighters, once they start making money for the first time they have all these obligations and they travel and they really enjoy making money and that's kind of why some of them fall off. She </s> |
<s>[INST] It could be just a gigantic background model, language model. And then you [/INST] do </s><s>[INST] um the training becomes like prompting that model to um [/INST] to </s><s>[INST] essentially do a kind of quarrying a search into the space of the things that's learned to customize that to whatever problem you're trying to solve. So maybe if you form a large enough language model, you can go quite quite a long way that, you [/INST] know, I think there's some truth to that. I mean you look at the way humans approach um a game like poker, they're not coming at it from scratch, They're coming at it with a huge amount of background knowledge about, you know, how humans work, how the world works. Um the idea of money, so they're able to leverage that kind of information to to pick up the game faster. Uh So it's not really a fair comparison to then compare it to an ai that's like learning from scratch. And maybe one of the ways that we address this uh sample complexity problem is by allowing ai is to leverage that general knowledge across a ton of different domains. </s><s>[INST] So like I said you did uh a lot of incredible work in the space of research and actually building systems, what advice would you give to? Uh let's start with beginners, What advice would you give to beginners interested in machine learning just there at the very start of their journey and they're in high school and college thinking like this seems like a fascinating world. What advice would you give them? [/INST] Um I would say that there are a lot of people working on similar aspects of machine learning and to not be afraid to try something a bit different. My my own path in ai is pretty atypical for machine learning researcher today. I mean, I started out working on game theory and um and then shifting more towards reinforcement learning as time went on and that actually had a lot of benefits, I think because it allowed me to look at these problems in a very different way from the way a lot of um machine learning researchers view it. Um and that comes with drawbacks in some respects. Like I think there's definitely aspects of machine learning where, you know, I'm weaker than most of the researchers out there, but I think that diversity of perspective, um you know, when I'm working with my teammates, um there's something that I'm bringing to the table, there's something that they're bringing to the table and that kind of collaboration becomes very fruitful for that reason. </s><s>[INST] So there could be problems like, like poker, like you've chosen diplomacy, that could be problems like that still out there that you can just tackle even if it seems extremely difficult. [/INST] Um I think that there's a lot of challenges, challenges left? And I think having a diversity of viewpoints and backgrounds is really helpful for working together to figure out how to tackle those kinds of challenges </s><s>[INST] as a beginner. So that I would say that's that's more for like a grad student, but already built up a base like a complete beginner, What's a good journey? So for you that was doing some more on the math side of things, doing game theory, all that. So it's basically built up a foundation in something, so programming mathematics, it could even be physics, but build that foundation. [/INST] Yeah, I would say build a strong foundation in math and computer science and statistics in these kinds of areas, but but don't be afraid to try something that's different and learn something that's different from, you know, the thing that everybody else is doing to get into machine learning, um you know, there's there's value in having a different background than everybody else. Um Yeah, so, but certainly having a strong math background, especially in things like linear algebra and statistics and probability um are incredibly helpful today for for learning about and understanding machine learning. </s><s>[INST] Do you think one day we'll be able to, since you're taking steps from poker to diplomacy one day we'll be able to uh figure out how to live life optimally. [/INST] Well, what is it like in in poker and diplomacy? You need a value function, You need to have a reward system and so what does it mean to live a life that's optimal. </s><s>[INST] So, okay, so then you can exactly like lay down a reward function being like I want to be rich or I want to be um I want to be in a happy relationship and then you'll say, well do x, [/INST] you know, there's there's a lot of talk today about in ai safety circles about like miss specification of, you know, reward function. So you you say like, okay, my objective is to be rich and maybe the ai tells you like, okay, well if you want to maximize the probability that you're rich, go rob a bank. And so you wanna, is that is that really what you want, is your objective really to be rich at all costs? Or is it more nuanced than that </s><s>[INST] understand the consequences? Yeah. Yeah. So yeah, that that that's maybe life is more about defining the reward function that minimizes the unintended consequences than it is about the actual policy that gets you to the reward function. Maybe life is just about constantly updating the reward function. [/INST] I think one of the challenges in life is figuring out exactly what that reward function is. Sometimes it's pretty hard to specify the same way that, you know, trying to handcraft the ultimate policy in a game, like chess is really difficult. Um It's not so clear cut what the reward function is for for life, </s><s>[INST] I think one day I will figure it out and I wonder what that would [/INST] be. Until </s> |
<s>[INST] So what do you think about that psychology that uh looks at all the different possible trajectories of an A. G. I. System, many of which perhaps the majority of which are positive and nevertheless focuses on the negative trajectories. I mean you get to interact with folks, you got to think about this maybe within yourself as well. Um You look at Sam Harris and so on. It seems to be sorry to put it this way but almost more fun to think about the negative possibilities whatever that's deep in our psychology. What do you think about that and how do we deal with it because we want ai to help us. [/INST] So I think there's kind of two problems entailed in that question. Uh The first is more of the question of how can you even picture what a world with a new technology will be like Now imagine we're in 1950 and I'm trying to describe uber to someone. </s><s>[INST] Apps and the internet. Yeah I mean you're that's going to be extremely complicated, but it's [/INST] Imaginable. It's imaginable, right? But and now imagine being in 1950 and predicting Uber, right? And you need to describe the internet, you describe gps, you need to describe the fact that everyone's going to have this phone in their pocket. Yeah. And so I think that just the first truth is that it is hard to picture how a transformative technology will play out in the world. Um We've seen that before with technologies that are far less transformative than a G I will be. And so I think that that one piece is that it's just even hard to imagine and to really put yourself in a world where you can predict what that that positive vision would be like. And you know, I think the second thing is that it is I think it is always easier to support the negative side than the positive side. It's always easier to destroy than create and you know, less than a physical sense and more just in an intellectual sense, right? Because you know, I think that that with creating something, you need to just get a bunch of things right and to destroy, you just need to get one thing wrong. And so I think that what that means is that I think a lot of people's thinking dead ends as soon as they see the negative story, but that being said, I actually actually some hope, right? I think that the positive vision is something that I think can be um is something that we can we can talk about. I think that just simply saying this fact of Yeah, like there's positive, there's negatives. Everyone likes to dwell on the negative people actually respond well to that message and say, huh you're right, there's a part of this that we're not talking about, not thinking about and that's actually something that's that's that's I think really been a key part of how we think about A G. I at open ai right? You can kind of look at it as like okay, like opening, it talks about the fact that there are risks and yet they're trying to build this system. Like how do you square those, those two facts. </s><s>[INST] So do you share the intuition that some people have? I mean from Sam Harris to even Elon musk himself that it's tricky as you develop a G I to keep it from slipping into the existential threats into the negative. What's your intuition about how hard is it to keep a eye development on the positive track? What's your intuition [/INST] there to answer the question? You can really look at how we structure open ai so we really have three main arms, we have capabilities which is actually doing the technical work and pushing forward what these systems can do, there's safety which is working on technical mechanisms to ensure that the systems we build are lined with human values and then there's policy which is making sure that we have governance mechanisms answering that question of well whose values And so I think that the technical safety one is the one that people kind of talk about the most right. You talk about like think about all of the dystopic ai movies, a lot of that is about not having good technical safety in place. Um And what we've been finding is that I think that actually a lot of people look at the technical safety problem and think it's just intractable, right? This question of what do humans want, How am I supposed to write that down? Can I even write down what I want? No way. And then they stop there. But the thing is we've already built systems that are able to learn things that humans can't specify. You know, even the rules for how to recognize if there's a cat or a dog in an image, turns out it's intractable to write that down. And yet we're able to learn it and that what we're seeing with systems, we build it open ai and they're still in early proof of concept stage is that you are able to learn human preferences, you're able to learn what humans want from data. Um And so that's kind of the core focus for our technical safety team. And I think that that they're actually we've had some pretty encouraging updates in terms of what we've been able to make work? </s><s>[INST] So you have an intuition and a hope that from data, you know, looking at the value alignment problem from data we can build systems that align with the collective, better angels of our nature. So aligned with the ethics and the morals of human beings [/INST] to even say this in a different way. I mean think about how how do we align humans right? Think about like a human baby can grow up to be an evil person or a great person. And a lot of that is from learning from data, right? That you have some feedback as a child is growing up, they get to see positive examples. And so I think that that just like the only example we have of a general intelligence uh that is able to learn from data to align with human values and to learn values. Um I think we shouldn't be surprised that we can do the same sorts of techniques or whether the same sort of techniques end up being how we we saw the value alignment for a Gs. </s> |
<s>[INST] You have to actually do some research here, wow that as another level of depth. That's awesome. Okay, so [/INST] okay, so say lex is playing. Yeah, one of his songs, he shows up </s><s>[INST] What's your favorite Hendrix song with, [/INST] Oh that's a hard one, I like castles in the sand, it's a sad one, but I like it. </s><s>[INST] So I'm playing something. Yes. And [/INST] I was saying boom, just like Elvis does for people, Hendrick shows up, all right, and then you're amazed and that tells you something that's very, very significant and he says you need to tell other people this. Okay, So then like, </s><s>[INST] okay, yes, [/INST] and you start and because people believe you and because you are a person of um, you know, credibility, people believe you. And so all of a sudden movement starts okay, and it's the Hendrix movement, it's Hendricks two or something like that, you know, we call it something the next iteration of Hendrix, right? Hendricks lives, but he lives is this vibration And only lex can like, you know, can manifest this vibration. Okay, so like this is, this is how religion start, you know, excuse your audience who are religious, I'm actually practicing catholic. So um this is how religion start. They start with first off, a contact experience, not, I mean not all of them, but a good portion of them. Um Peep, some person has an experience that's transcendent sacred to them and they go and they tell other people and then those people tell other people and then something gets written about it. Okay, And then it becomes because it's a charismatic movement, people become affected by it and if if too many people are affected by it um an institution steps in and tries to control the narrative. Uh so this is what you call the beginning of a religion or a myth, a very powerful myth. And so it's almost like a star, a Star is Born. </s><s>[INST] Okay. Yeah. We say institution. Do you mean some other organization that's already powerful? You don't want to become overpowered by this new movement? [/INST] Yes, absolutely. </s><s>[INST] Usually governments [/INST] usually. Yeah. So I have a couple examples. I used the example of the christian church in my book because I'm most familiar with the history of Christianity and you know, Christianity, you know, was started by this jewish man and it was a movement that you know, he was a very powerful charismatic person, other people believed in him and then his followers talked about him and then other than, you know, usually early christians before does 300s were generally people who were disenfranchised because he had a pretty radical idea that, you know, humans should have dignity. And this was pretty radical during that time. So women who didn't have dignity and you know, slaves who didn't have dignity at the time um convert to Christianity in droves. And so what happened was that all of a sudden um it became this belief system that was undercurrent and then Constantine who was an elite had an experience and made Christianity the state religion by that time there were different forms of Christianity probably hundreds of them well most likely and Constantine and the people who were powerful with him decided that their idea this is the Council of Nicaea now decided that there was one form and they call it universal the one form of Christianity and this should be it. And so they kind of took out all the other denominations of Christianity in different forms of it. So you can see that a very very powerful set of beliefs put a culture on fire. Right. And so how did they had to deal with that fire somehow. And so they narrative ized it, they decided how do we interpret this and they interpreted it as they wished. But that wasn't the only interpretation of Christianity. Have another example. I'm in the catholic church a lot of times and I'm gonna use the example of uh Faustina. Um she's um she's a nun and she's polish and um I think it was in the early 20th century, if not the 18 hundreds that she had a very powerful uh many experiences actually of of jesus and she saw jesus with rays coming out of his life, his heart. And basically she called his Divine Mercy. And it became a devotion in Poland and it spread the catholic church was not, not into this at all. Okay. And so they did everything they could to try to suppress festina's influence which was growing and growing and growing and growing okay. And so they were very successful in trying to keep her quiet and she died. Okay. Years later, john paul the second polish sainted her and created the divine mercy devotion, which is worldwide now and millions and millions of people. But do you see how they, they, you know, completely </s><s>[INST] controlled, so fascinating that it uh that it just starts with a single. So like you said, contact experience, experience is the key word, is your sense that those experiences are legitimate. So it's not [/INST] yes, </s><s>[INST] artificially constructed. [/INST] I think for the most part, they're legitimate experiences that people have, Why would someone want to put themselves through what they go through? Like why would jesus want to get crucified? I mean, that's a pretty nasty way to die. Um you know, why would Faustina bringing this upon herself, the people that I meet who said that they've seen UFOs and that most of them don't want to be known because of the ridicule that goes along with it. So I honestly think that, you know, there are people who are maybe not stable and would like the attention, but for the most part, normal people don't want this attention. </s> |
<s>[INST] small, will be high. The decision making is a big [/INST] part in making a big part. Yeah. So the original so statistics, you know short history was that you know, it's kind of goes back, It's as a formal discipline, you know, 250 years or so. Um it was called inverse probability because around that era uh probability was developed sort of especially to explain gambling um situations and um interesting so you would say well given the state of nature is this there's a certain roulette or that has a certain mechanism and it uh what kind of outcomes do I expect to see? Uh And um especially I do things long, long amounts of time what outcomes by seeing the faces start to pay attention to this. Um And then people said well given let's turn the problem around, what if I saw certain outcomes could infer what the underlying mechanism was, that's an inverse problem. And in fact for quite a while statistics was called inverse probability. That was the name of the field. And I believe that it was La Plaza who was working in napoleon's government who was trying who needed to do a census of France, learn about the people there. So he went and got and gathered data and he analyzed that data to determine policy. And I said well it's called this field that does this kind of thing statistics because um the word state is in there in french. That's a to but you know it's the study of data for the state. Uh Anyway that caught on and um it's been called statistics ever since. But But by the time it got formalized it was sort of in the 30s. Um and uh around that time there was game theory and decision theory developed nearby um people that air didn't think of themselves as either computer science or statistics or controlled or econ they were all they were all the above. And so you know von norman is developing game theory but also thinking about his decision theory Wall is an economy attrition, developing decision theory and then turning that into statistics. And so it's all about, here's uh here's not just data and you analyze it, here's a loss function. Here's what you care about here is the question of trying to ask I hear is a probability model and here is the risk you will face if you make certain decisions. Um and to this day and most advanced statistical curricula used, teach decision theory is the starting point and then it branches out into the two branches of basing a frequentist but that's it's all about decisions </s><s>[INST] in statistics. What is the most beautiful, mysterious, maybe surprising idea that you've come across. [/INST] Uh Yeah, good question. Um I mean there's a bunch of surprising ones, there's something that's way too technical for this thing, but something called James Stein estimation, which is kind of surprising and really takes time to wrap your head around. Can you try to maybe, I think I don't want even want to try um let me just say a colleague at steve Stephen Stigler University Chicago wrote a really beautiful paper on James stein estimation which helps to its views of paradox, it kind of defeats the mind's attempts to understand it, but you can and steve has a nice perspective on that. Um they're so one of the troubles with statistics is that it's like in physics that are in quantum physics you have multiple interpretations. There's a wave and particle duality in physics and you get used to that over time, but it's still kind of haunts you that you don't really, you know, quite understand the relationship the electrons away when electrons are particles. Well, um well the same thing happens here. There's Bazian ways of thinking and frequentist and they are different. They they sometimes become sort of the same in practice, but they are physically different. And then in some practice they are not the same at all. They give you a rather different answers. Um and so it is very much like wave particle duality and that is something you have to kind of get used to in the field. </s><s>[INST] Can you define Beijing a frequentist? [/INST] Yeah. Decision theory. You can make I have a like I have a video that people could see. It's called are you a basin or a frequentist. And kind of help try to to uh to make it really clear. It comes from decision theory. So, you know, decision theory. Uh you're talking about loss functions which are a function of data X and parameter data there a function of two arguments. Okay, neither one of those arguments is known. You don't know the data a priori it's random and the parameters unknown. All right. So you have this function of two things. You don't know when you're trying to say, I want that function to be small, I want small loss. Right, Well um what are you gonna do? So you sort of say well I'm going to average over these quantities or maximize over them or something so that you know I turned that uncertainty into something certain. Um So you could look at the first argument an average over it or you can look at the second annual average over it. That's basin frequentist. So the frequent just says I'm going to look at the X. The data and I'm gonna take that as random and I'm going to average over the distribution. So I take the expectation of loss under X. Fate is held fixed. All right. That's called the risk. And so is looking at other all the data that you could get. All right. And seeing how well will a certain procedure do under all those data sets that's called a frequent is guarantee. All right. So I think it is very appropriate when like you're building a piece of software and you're shipping it out there and people using all kinds of datasets you wanna have a stamp of guarantee on it that has people running on many many data sets that you never even thought about that 95% of the time. It will do the right thing. Um perfectly reasonable. The Beijing perspective says, well no, I'm going to look at the other argument of the loss function. The fate apart. Okay that's unknown and I'm uncertain about it. So I could have my own personal probability for what it is. You know, how many tall people are there out there? I'm trying to for the average height of the population. Well, I have an idea roughly what the height is. So I'm gonna average over the the theater. So now that loss function has only now, again, one argument is gone. Now it's a function of X. And that's what position does is they say, well, let's just focus on the particular X. We got the data set. We got we condition on that conditional on the acts. I say something about my loss. That's a basin approach to things. And the position will argue that it's not relevant to look at all the other data sets. You could have gotten an average over them. The frequentist approach, it's really only the data that you got. All right. And I do agree with that. Especially in situations where you're working with a scientist, you can learn a lot about the domain and you're really only focus on certain kinds of data and you gather your data and you make inferences. Um, I don't agree with it though, that, you know, in the sense that there are needs for frequentist guarantees your writing software people are using out there. You want to say something. So these two things have got to fight each other a little bit, but they have to blend So long story short, there's a set of ideas that are right in the middle there called empirical bayes and empirical base starts with the Bosnian framework. Uh, it's it's kind of arguably philosophically more, you know, reasonable and kosher write down a bunch of the math that kind of flows from that and then realize there's a bunch of things you don't know because it's the real world and you don't know everything. So you're uncertain about certain quantities at that point. Ask is there a reasonable way to plug in an estimate for those things? Okay. And in some cases there is quite a reasonable thing to do um, to plug in. There is a natural thing you can observe in the world that you can plug in and then do a little bit more mathematics and assure yourself it's really good. </s> |
<s>[INST] it's like swap the front end, swap the back end. Yeah. Go ahead. Go ahead and put it. Right? It's really good. Yeah, yeah, it really is. I'm enjoying your metaphors and way of talking about stuff. Yes, I get, yeah, yeah. Swap, you could, yeah. When branding and swap the front end, reinterpretation swap the back end. [/INST] That's right. I'm enjoying your metaphor. Once you realize that, you're like, okay. Just as an engineer, you can kind of, okay, sometimes I wanna do something on the front end, and sometimes I wanna do it on the back end. Sometimes it's explicit and sometimes the user doesn't need to see it and it's on the back end. Lots of political stuff is arguably not just best done on the back end, but always done on the back end. One of the points I make in the book is left is the right is the left, is, you know, if you look through history, the Christian King, the Republican conservative, the CCP entrepreneur, the WASP establishment, these are all examples of a revolutionary left movement becoming the ruling class right. Okay, like Republican conservative, just as that one example, I go through an extended description of this in the book, but the Republicans were the radical Republicans, the left of 1865. They won the revolution and their moral authority led them to have economic authority in the late 1800s. You wouldn't want a Democrat Confederate trader as the head of your railroad company, would you, right? So all the Confederate traders, et cetera, were boxed out from the plump positions in the late 1800s. And so what happened was the Republicans turned their moral authority into economic authority, made tons of money. The Democrats then started repositioning, not as a party of the Southern racists, but the poor, right? And, you know, the cross of gold speech by William James Bryan was part of that. There's a gradual process that reaches, not a policy, but let's say a crucial mark with the election of FDR, where it was actually not the 1932 but 1936 election that black voters switched over to FDR, okay? That was actually the, like the major flip to like 70%, you know, to the Democrats. Now they had repositioned as the party of the poor, not the party of the South, okay? And Republicans had lost some economic authority, or rather they had moral authority. They turned into economic authority, they started to lose some moral authority. The loss of moral authority was complete by 1965. That was actually a mop-up. People dated, you know, the civil rights movement as the big wave where the Republicans lost moral authority. It's not really. That was a mop-up, because 1936, 30 years earlier, was when black voters switched to the Democrats, okay? So 1965 was another 10 points moving over of black voters to the Democrats. Republicans had completely lost moral authority, hundred years after the Civil War. Then the next 50 years, that loss of moral authority meant that they lost economic authority because now you wouldn't want a Republican bigot as a CEO of your tech company anymore, would you? Right? So by 2015, now, now you have it's like two sine waves that are staggered. Moral authority leads to economic authority, leads to loss of moral authority, leads to loss of economic authority. And so now you have the Democrats have completed 155 year arc from the defeated party in the Civil War to the dominant party in the U.S. establishment. All the woke capitalists are now at the very top. Now the same repositioning is happening where if you're so woke, why are you rich? You get it? If you're so smart, why aren't you rich is the normal kind of thing. If you're so woke, if you're so holy, why is like, for example, the BLM founder, why do they have this million dollar mansion, right? If you're so woke and it's all about being good and you're anti-capitalist, how come you seem to be raking in the money, et cetera, right? This is an argument which I'm not sure how long it will go. It might take years to play out. It might take decades to play out. I think probably on the order of a decade, you're going to see in my view the repositioning if the Democrats are the woke capitalists, the Republicans will eventually become, are becoming the Bitcoin maximalists. Why? Because, you know, if one guy picks left, then the other guy picks right. It's literally like magnets kind of repelling. They're sort of forced into the other corner here. Right. And the Bitcoin maximalists will essentially where, this guy says centralization. They say decentralization, where they defend the right of capital to do anything the maximalists will say, actually you're all Cantilian there's. You're all benefiting from print and money. You don't have anything that's legitimate. You don't actually own anything as all the handout from the government and so on and so forth, right? And so that's counter positioning that will basically attack the wokes by how much money they're making. They're not contesting the ideology. So when one guy signals economics, you signal culture. When the other guy signals culture, you signal economics. That's actually, that's the whole thing I can talk about. Should I talk about that for a second? </s><s>[INST] Sure. Is this integrated into the forces that you talk about? You've talked about the three forces, the trifecta forces that affect our society, which is the wokes, let's say. Woke capital, communist capital. Woke capital. You talk so fast. And I think so slow. No, no, no. Woke capital, communist capital, and crypto capital. Can you explain each of those three? Yes. We actually talked about each of the three in part, but it'd be nice to bring them together [/INST] in a beautiful triangle. No, no, no. In a beautiful triangle. And then I'll also come back up and I'll talk about how the CCP story relates to social media and decentralized social media. All right, so NIT, CCP, BTC is woke capital, communist capital, crypto capital, and communist capital is, the simplest is you must submit. The communist party is powerful, CCP is powerful and you are not. If you're in China, you just submit. CCP is an embodiment of communist capital that you're talking about. Well, yeah, so basically, and by the, in China, they call it CPC, you know? So basically they don't like it usually if you say CCP, right? So like communist party of China as opposed to Chinese kind of sort of there. Basically that is capitalism, that is a Chinese pool of capital, that billion person pool, okay? That's WeChat and it's, you know, it's Alibaba and it's an entire kind of thing. That is one just social network with currency. The whole thing is vertically integrated. </s> |
<s>[INST] so I remember hearing about this, I think Dan Savage is a podcast. I think they're called furries. Furries. [/INST] Like furry parties. Yeah, exactly. I love people. Yeah, you know, that's like the thing. It's like whenever you hear these words, it's like humans, what would I think of next? So, but I do think that, and I write about this in Hacking Darwin, that as people come to believe that making children through the application of science is safer and more beneficial than having children through sex, we'll start to see a shift over time toward reproduction through science. We'll still have sex for all the same great reasons that we do it now. It's just reproduction less and less </s><s>[INST] through the act of sex. I love people. Yeah, I know. Man, it's such a fascinating future. Because as somebody, I value flaws. I think it's the good will hunting. That's the good stuff. The flaws, the weird quirks of humans, that's what makes us who we are, the weird. The weird is the beautiful, and there's a fear of optimization. [/INST] You should have it. I mean, it's very healthy. And I think that's the danger of all of this selection is that we make selections just based on social norms that are so deeply internal that they feel like they're eternal truths. And so we talked about selecting for IQ. What about selecting for a kind heart? Like there are lots of you. You talked about Hitler and Mein Kampf. Hitler has certainly had a high IQ, I guess is higher than average IQ. If we just select, I mean, that's why I was saying before, diversity is baked into our biology. But the key lesson, and I've said this many times before, the key lesson of this moment in our history is that after nearly 4 billion years of evolution, our one species suddenly has the unique and increasing ability to read, write, and hack the code of life. And so as we apply these God-like powers that we've now assumed for ourselves, we better be pretty careful because it's so easy to make mistakes, particularly mistakes that are guided by our best intentions. </s><s>[INST] To jump briefly back onto lab leak, and I swear there's a reason for that. What did you think about the John Stewart? This moment, I forget what it was, maybe a few months ago, in the summer, I think, of 2021, where he went on Colbert Report, or not the Colbert Report, sorry, Stephen Colbert's, whatever his show is. But again, John Stewart reminded us how valuable his wit and brilliance within the humor was for our culture. And so he did this whole bit that highlighted the common sense nature about what was the metaphor he used about the Hershey factory in Pennsylvania. [/INST] So what'd you think about that whole bit? I loved it. And so not to be overly self-referential, but it's hard not to be overly self-referential when you're doing a, however long we are, five-hour interview about yourself. Which reminds me, when you had Brett Weinstein on, and he said, I have no ego, but these 57 people have screwed me over, and I deserve credit. It's hard, it's hard to mock them. I am a person I will confess, it's enjoyable. Some people feel different. I kind of like talking about all this stuff and talking, period. So for me, in the earliest, I remember those early days when the pandemic started, I was just sitting down, it was late January or early February, 2020, and I just was laying out all of the evidence, just that I could collect, trying to say, make sense of where does this come from? And it was just logic. I mean, it was all of the things that John Stewart said, which in some overly wordy form, were all at that time on my website. Like, what are the odds of having this outbreak of a bad coronavirus more than a thousand miles away from where these bats have their natural habitat, where they have the largest collection of these bat coronaviruses in the world, and they're doing all these very aggressive research projects to make them more aggressive, and then you have the outbreak of a virus that's primed for human to human transmission. It was just, logic was my first step, and I kept gathering the information. But John Stewart distilled that in a way that just everybody got, and I think that, like, I loved it, and I just think that there's a way of reaching people. It's the reason why I write science fiction in addition to thinking and writing about the science, is that we kind of have to reach people where they are, and I just thought it was just, there was a lot of depth, I thought, and maybe that's too self-serving, but, like, in the analysis, but he captured that into those things about, it's like the, whatever, the outbreak of chewy goodness near the Hershey factory. </s> |
<s>[INST] kevin. Uh it's great to end on uh love and the meaning of life. This is an amazing conversation. Thank you. You gave me like a light into some fascinating aspects of this, of the technical world and I can't honestly wait to see what you do next. Thank you so much. [/INST] Thanks for having me. </s><s>[INST] Thanks for listening to this conversation with Kevin Systrom. To support this podcast. Please check out our sponsors in the description and now let me leave you with some words from Kevin Systrom himself, Focusing on one thing and doing it really, really well. I can get you very far. Thank you for listening and hope to see you next time. [/INST] </s> |
<s>[INST] It's an east M electrical stimulation device that I've been using a lot for muscle recovery recently, mostly for my shoulders and legs. As I've been doing the 1000 bodyweight reps and six miles every day as I just finished. They call it the smart muscle stimulator, which is true Since the app that goes with it is amazing. It has 15 programs for different body parts and guides you through everything you need to do. I take recovery really seriously these days. And power dot has been a powerful addition to the whole regime of stretching, ice, massage and sleep and diet that I do. It's used by professional athletes and by slightly insane but mostly normal people like me. It's portable so you can throw it in a bag and bring it anywhere. Get it at power dot com slash lex And use Cold Lex checkout to get 20% off on top of the 30 day free trial and to support this podcast. And now here's my conversation with Ian Hutchinson. Maybe you'd be nice to draw a distinction between nuclear physics and plasma physics. What is the distinction? [/INST] Nuclear physics is about the physics of the nucleus and my department Department of Nuclear Science and Engineering at MIT is very concerned about all the interactions and uh reactions and consequences of things that go on in the nucleus, including nuclear energy, fish and energy, which is the nuclear energy that we have already. And fusion energy, which is the energy source of the sun and stars, which we don't quite know how to turn into practical energy for humankind at the moment. That's what my research has mostly been aimed at. But plasmas are essentially the fourth state of matter. So if you think about solid liquid gas, plasma is the fourth of those states of matter. And it's actually the state of matter which one reaches if one raises the temperature. Um So cold things, you know, like ice are solid, um liquids are hotter water and if you heat water beyond 100 degrees Celsius, it becomes gas. Uh Well, that's true of most substances. And um plasma is a, is a state of matter in which the electrons are unbound from the nuclei, so they become separated from the nuclear and can move separately. So we have positively charged nuclei and we have negatively charged electrons. The net is is uh still neutral, electrically neutral. But a plasma conducts electricity as all sorts of important properties that are associated with that separation. And that's what plasmas are all about. And the reason why my department is interested in plasma physics very strongly is because most things, well, for one thing, most things in the universe are plasma. The vast majority of matter in the university's plasma, but most particularly stars and the sun are plasmas because they're very hot and it's only in very hot states that nuclear fusion reactions take place and we want to understand how to implement those kind of phenomena on earth. </s><s>[INST] Maybe another distinction we wanna try to get at is the difference between fission and fusion. So you mentioned fusion is the kind of reaction happening in the sun. So what's vision and what's fusion? [/INST] Well, fishing is taking heavy elements like uranium and breaking them up. And it turns out that that process of breaking up heavy elements releases energy. </s><s>[INST] What does it mean to be a heavy element? [/INST] It means that there are many nuclear particles in the nucleus itself, neutrons and protons in the nucleus itself. So that in the case of uranium there are 92 protons in each nucleus and even more neutrons. So that the total number of Nucleons in the nucleus nucleons is short for either a proton or a neutron. Um the total number, you know might be 235. That's you to 35 or it might be 238. That's you to 38. So those are heavy elements. Light elements by contrast have very few nucleons. Protons or neutrons in the nucleus, hydrogen is the lightest nucleus. It has one proton. They're actually slightly heavier forms of hydrogen. Isotopes. Deuterium has a proton and a neutron and treaty um has a proton and two neutrons. So it has a total of three nucleons in the in the nucleus while taking light elements like isotopes of hydrogen and not breaking them up but actually fusing them together, reacting them together to produce heavier elements. Typically helium. Okay which is helium is a nucleus which has has two protons and two neutrons that also releases energy and that and that or reactions like that. Making heavier elements from lighter elements is what mostly powers the sun and stars. Both fusion and fission release approximately a million times more energy per unit mass than chemical reactions. So, a chemical reaction means take hydrogen, take oxygen, react them together let's say and get water that releases energy. The energy released in the chemical reaction like that or the burning of coal or oil or whatever else is about a million times less per unit mass than what is released in nuclear reactions. </s><s>[INST] So, but it's hard to do. [/INST] It requires very high energy of impact. And actually it's very easy to understand why. And that is that those two nuclei, if they're both, let's say hydrogen nuclei, one is let's say deuterium and the other is let's say treaty. Um they're both electrically charged. And so they and they are positively charged. So they like charges, repel everyone knows that, right? So basically to get them close enough together to react, you have to overcome the repulsion the electric repulsion of the two nuclei from one another. And you have to get them extremely close to one another in order for the nuclear forces to overtake the electrical forces. And and actually form a new nucleus. And so one requires very high energies of impact in order for reactions to take place. And those high energies of impact correspond to very high temperatures of random motion. </s> |
<s>[INST] what's an instance object. [/INST] It's you know some games every uh you know, wall or building is kind of unique in its data. Whereas we would just build, you know these little husks of buildings and then place them all over the place. So the memory and the way you render it is much more optimal. So </s><s>[INST] that allows you to build a bigger world, [/INST] you build a bigger world much faster and not um you know, not every single version of that building isn't its own unique architecture that is going to take up memory and processing speed and etcetera etcetera. So </s><s>[INST] you're there very much feeling the computational constraints of the system when you're creating these open [/INST] and you know what, that's the thing then you see some of it now. But in those times I do feel like every year the technology moved and maybe it's because the same thing, we're like that my age at that time where every year somebody was coming up with some new method or some new game system and it was every year that innovation, innovation, innovation. And then you know, three D. Acceleration comes along and then these things come along and then H. D. Comes along and it is true that as time goes on there is visually a diminishing return in terms of what you're able to do on the screen and it there's a ton of work that goes into it now because just rendering this cup to the perfect shining material and roughness and how does the global illumination off this wallet gets a ton of work. Um, but you can pretty much do what you want now if you want to put the time in, whereas then okay, you can't do everything you want. So pick your battles really carefully. And technically you couldn't do what you want if that makes sense. How </s><s>[INST] much trade off is there now in how much effort you put into the realism of the graphics versus the story and actually not even how much effort you put in. But is there a trade off in the experience, the feel of the game in terms of realism and story. [/INST] Usually we will start with let the player have as much agency and do as many things as they can as possible. And we will sacrifice some graphic fidelity for that, some speed for that. You know, we could make a game that, You know, are traditionally our games are, you know, we okay with 30 frames a second as long as it looks really good and the simulation is running and all of those things. So we'll we'll sacrifice some of that fidelity for the player experience, and and the the kind of things that that I do. Um, but from like a manpower standpoint, the graphics programmers work on graphics, the artist's work on art and we have, you know, awesome team of artists and designers and writers and programmers. It's usually where we find as time goes on, the amount of art time that it takes to create a cup compared to what it used to be. That has increased. So we do use like most people use, you know, art outsourcing as well so that we're not, we still relatively compared to our industry and what we're doing have smaller teams. </s><s>[INST] What about the experience of the beauty of the graphics? So like um one of the most amazing things about Skyrim, maybe you could say that about some of the other games, but for me, Skyrim is the outdoor when you step outside the outdoor scenery. So what does it take to create the feeling especially of that being outdoors of nature and just like lost in the beauty, whatever it is when you go hiking and you feel the awe of it. How do you create that all? Is that graphics? What is that? [/INST] It's a lot of graphics, it's a lot of mood. We just talk about it in terms of tone and those are again going back to my previous comment, the graphics are very, very important to us because and we always push them because when you're doing the kind of things we do where you step into a virtual world, it doesn't have to have that moment of, wow, this is this feels real. I've never experienced this and it's okay. I think it's okay to let just like the time settle, meaning you step out. How does the wind sound, how are the trees moving, how are the clouds moving? Um I enjoy strolling and watching the sunset, you know, how does it land over the water? Like it doesn't have to be like, hey, let's go, let's finish the quest, let's go kill things, let's figure out the next step, let's level up. Like, I like the quiet moments a lot and I think when you play our games, you can tell we spend a lot of time on them. Um then you watch like the weather roll in um I think that's just part of being, being that character, being that person in that space. </s> |