text
stringlengths
296
254k
<s>[INST] At the risk of disagreeing with a man who did 50 lectures on the meaning crisis. Let me hard disagree, but I think would probably agree, but it's just like a dance. Like any dialogue. I think meaning of life gets at the same kind of relationship between you and the glass of water between whatever the forces of the universe that created the planets, the proteins, the multi cell organisms, the intelligent early humans, the beautiful human civilizations and the technologies that will overtake them. It's trying to understand the the relevance realization of the big bang to the feeling of love you have for another human being. It's reaching for that, even though it's hopeless to understand. It's the question, the asking of the question is the reaching Now it is in fact romantic bullshit technically speaking, but it could be that romantic bullshit is actually the essence of life and the source of his deepest meaning? Well, [/INST] I hope not. But </s><s>[INST] technically speaking romantic bullshit meaning romantic [/INST] in the philosophical sense. Yes. </s><s>[INST] So I I mean, what is poetry? What is music? What is the magic you feel when you hear a beautiful piece of music? What is that? Oh, [/INST] but that's exactly to my point, is music inside you, or is it outside you? It's both and neither. And that's precisely why you find it so meaningful. In fact, it can be so meaningful. You can regard it as sacred what you said, I don't think. And you preface that we might not be in disagreement right? What you said is, no, no, no, there is, there's a way in which reality is realizing itself. And I want my relevance realization to be in the best possible relationship that the sort of meta, optimal grip to what is most real? I totally agree. I totally think that's one of the things I said this earlier, one of our meta desires is whatever is satisfying our desires is also real. I do this with my students. I'll say, um, you know, because romantic relationships are sort of take the role of God and religion and history and culture for us right now, we we put everything on them and that's why they break, but right, strong </s><s>[INST] words, but [/INST] I'll say to them, okay, how many of you are in really satisfying romantic relationships? Put up your hands and say, okay, I'm not only talking to these people Of those people, how many of you would want to know your partner is cheating on you, even if it means the destruction of the relationship, 95% of them put up their hands and I say but why? And they and and here's my students who are usually all sort of bitten with cynicism and postmodernism and they'll just say spontaneously well because it's not real because it's not real, right? So I think what you're pointing to is actually you're pointing not to an objective or a subjective thing. So Romanticism says it's subjective, there's some sort of I guess like positivism or lucky and empiricism says its objective, but you're saying no, no, no, there's reality realization. And can I get relevance realization to be optimally gripping in the best right relationship with it? And and there's good reason you can because think about it, your relevance realization isn't just representing properties of the world, it's in stance, there's something very similar to biological evolution, which is that the guts of life, if I'm right, running your cognition is not just that you all have ideas. You actually inst ansi eight, that's what I mean by conformity, the same principles there within and without they don't belong to you subjectively, they're not just out there, they're both at the same time and they help to explain how you are actually bound to the evolutionary world. </s>
<s>[INST] And that's ultimately the physical side. How well are you using for this entire mechanism, the energy available to you? And so given all the resilience to errors and all that kind of stuff, it seems that it's close to its maximum. And this paper aside, it does seem that life, obviously, that's the constraint we have on Earth, right? Is the amount of energy. So that's one way to define life. Well, the input is energy, and the output is what? I don't know. Self-replicating. Okay, let's go there. How do you personally define life? Do you have a favorite definition that you try to sneak up on? Is it possible to define life on Earth? [/INST] I don't know. It depends on what you are defining it for. If you're defining it for finding different life forms, then it probably needs to have some quantification in it, so that you can use it in whatever the mission that you're operating. </s><s>[INST] Do you mean like it's not binary? It's like a 7 out of 10. Life-like. [/INST] I don't know. I don't think that defining is that essential. I think it's a good exercise, but I'm not sure if we need to agree a universally defined way of understanding life. Because the definition itself seems to be ever evolving anyway, right? We have the NASA's definition. It has its minuses and pluses, but it seems to be doing its job. </s><s>[INST] But what are the different, if there is a line, and it's impossible or unproductive to define that line, nevertheless, we know it when we see it as one definition that the Supreme Court likes. That's kind of an important thing to think about when we look at life on other planets. How do we try to identify if a thing is living when we go to Mars, when we go to the different moons in our solar system, or we go outside our solar system to look for life [/INST] on other planets? It's unlikely to be a smoking gun event, right? It's not going to be, hey, I found this. You don't think so? I don't think so. Unless you find an elephant on </s><s>[INST] some exoplanet, then I can say, yeah, there's life here. You don't think so? No, but isn't there a dynamic nature to the thing? It moves. It has a membrane that looks like there's [/INST] stuff inside. It doesn't need to move. It doesn't need to move, right? I mean, look at plants. I mean, they grow, but there are plants that can be also pretty dormant. And arguably, they do everything that, as one of my favorite professors once said, that the plant does everything that a giraffe does without moving. So movement is not necessarily. </s><s>[INST] But on a certain time scale, the plant does move. It just moves slower. Yes. It moves pretty quickly. [/INST] I would say that, yes. It moves pretty quickly. I would say that it's hard to quantify this or even measure it, but life is definitely chemistry finding solutions, right? So it is chemistry exploring itself and maintaining this exploration for billions of years. </s><s>[INST] So, okay. So a planet is a bunch of chemistry and then you run it and say, all right, all right, figure out what cool stuff you can come up with. That's essentially what life is. Given a chemistry, what is the cool stuff I can come up with? [/INST] If that chemistry or the solutions that it embarks upon are maintained in a form of memory, right? So you don't just need to have the exploring chemical space, but you need to also maintain a memory of some of those solutions for over long periods of time. So that's the memory component makes it more living to me because chemistry can always sample, right? So chemistry is chemistry. But are you just constantly sampling or are you building on your former solutions and then maintaining a memory of those solutions over billions of years? Or at least that's what happened here. </s><s>[INST] Chemistry can't build life if it's always living in the moment. The physicists will be very upset with you. Okay. So memory could be a fundamental requirement for life. [/INST] I mean, life is obviously the chemistry and physics leading to biology. So this is not a disciplinary problem of one discipline, triumphing other discipline. But what you need to have is definitely, chemistry is everywhere, right? I tend to think you can be a chemist, you can study chemistry, you can study physics, you can study geology anywhere in the universe, but this is the only place you can study biology. This is the only place to be a biologist. That's it. So definitely something very fundamental happened here. And you cannot take biology out of the equation. If you want to understand how the vast chemistry space, how that general sequence space got narrowed down to what is available or what is used by life, you need to understand the rules of selection and that's when evolution and biology comes into play. Yeah, so the rules of natural selection operate to you on the level of biology? Rules? I don't know if there are any rules like that. It would be fascinating to find in terms of the biology's rules. That's very interesting and it's a very fascinating area of study now and probably we will hear more about that in the decades to come. But if you want to go from the broad to specific, you need to understand the rules of selection and that is going to come </s>
<s>[INST] So I think it's really exciting what optimist art is doing in terms of it feels the most reachable, like they'll actually be here and have an impact. [/INST] That is the idea. </s><s>[INST] And if we contrast that again, we'll go back to our old friends, Waymo and Tesla. So Waymo seems to have sort of technically similar approaches as optimist ride, but a different, they're not as interested as having an impact today. Uh, is they have a longer term sort of investments, almost more of a research project still meaning they're trying to solve as far as I understand it, maybe you can, you can differentiate but they seem to want to do more unrestricted movement meaning move from A to B where A to B is all over the place versus optimist right? Is really nicely geo fence and really sort of establishment ability in a particular environment before you expand it. And then Tesla is like the complete opposite, which is, you know, the entirety of the world actually is going to be automated highway driving, urban driving every kind of driving, you know, you kind of creep up to it by incrementally improving the capabilities of the autopilot system. So when you contrast all of these and on top of that, let me throw a question and nobody likes but his uh, timeline, When do you think each of these approaches, loosely speaking, nobody can predict the future. We'll see mass deployment. So your mosque predicts the craziest approach. Is that the, I've heard figures like at the end of this year. Right? So that's probably wildly inaccurate. But how wildly inaccurate is it? [/INST] I mean, first thing to lay out like everybody else, it's really, it's really hard to guess. I mean, I don't know, I don't know where where Tesla can look at our Elon musk and look at and say, hey, you know, it's the end of this year. I mean, I don't know what you can look at. You know, even the data that, you know, I mean, if you look at the data, um, even kind of trying to extrapolate the end state without knowing what exactly is going to go, especially for like a machine learning approach. I mean it's just kind of very hard to predict. But I do think the following does happen. I think a lot of people, you know, what they do is that there's something that I called a couple times time dilation in technology prediction happens. Let me try to describe a little bit, there's a lot of things that are so far ahead. People think they're close and there's a lot of things that are actually close. People think it's far ahead. People try to kind of look at the whole landscape of technology development, admittedly it's chaos, Anything can happen in any order at any time and there's a whole bunch of things in that people take it clamp it and put it into the next three years. Um, and so then what happens is that there's some things that maybe can happen by the end of the year or next year and so on, and they push that into like a few years ahead because it's just hard to explain. And there are things that are, like, we're looking at 20 years more, maybe, you know, um, hopefully in my lifetime type of things. And because, you know, we don't know, we don't know how how hard it is. Even like, that's a problem. We don't know like if some of these problems are actually ai complete, like we have no idea what's going on and you know, we we take all of that and then we clamp it and then we say three years from now. Um, and then some of us are more optimistic. So they're shooting at the at the end of the year and some of us are more realistic. They say like five years, but you know, we all, I think it's just hard to know and I think um, trying to predict like products ahead to three years, it's hard to know in the following sense, You know, like we typically say, okay, this is a technology company, but sometimes sometimes really you're trying to build something like a technology like there's a technology gap, you know, like, and Tesla had that electric vehicles, you know, like when they first started, they would look at a chart much like a moose law type of chart and they would just kind of extrapolate that out and they say we want to be here. What's the technology to get that? We don't know, it goes like this. So it's probably just gonna keep going um, with ai that goes into the cars. We don't even have that. Like, you can't, I mean, what can you quantify? Like what kind of chart are you looking at? You know? Um, but so, but so I think when there's the technology gap, it's just kind of really hard to predict. So now I realize I talked like five minutes and avoid your question. I didn't tell you anything about that. It was very skillfully done was very, I don't think, </s><s>[INST] I think you've actually argued that it's not even any answer to provide now is not that useful. It's gonna be very [/INST] hard. There's one thing that I really believe in and, and you know, this is not my idea and it's been, you know, discussed several times. But, but this, um, this, this kind of like something like a startup or, or, or a kind of an innovative company, including definitely made very more Tesla, maybe even some of the other big companies that are kind of trying things, this kind of like Iterated learning is very important. The fact that we're over there and we're trying things and so on. I think that's um, that's important. We try to understand. And, and I think that, you know, the coding code Silicon Valley has done that with business models pretty well. And now I think we're trying to get to do it, but there's a literal technology gap. I mean before, like, you know, you're trying to build, I'm not trying to, you know, I think these companies are building great technology to, for example, enable internet search to do it so quickly and that kind of didn't didn't what wasn't there so much, But at least like it was a kind of a technology that you could predict to some degree and so on. And now we're just kind of trying to build, you know, things that it's kind of hard to quantify. What kind of a metric are we looking at. </s>
<s>[INST] that, I mean there's a lot of, a lot of questions, really exciting space, especially to me, I just find it a fascinating problem. Could, could enrich the experience in the car in so many ways, especially because like we spend still despite Covid, I mean Covid changed things. So it's in interesting ways, but I think the world is bouncing back and we spend so much time in the car and the car is such a weird little world we have for ourselves, like people do all kinds of different stuff, like listen to podcasts, they think about stuff, they get angry, they get, um, they do phone calls. So it's like a little world of its own with a kind of privacy that for many people, they don't get anywhere else. Uh, it's, and it's, it's a little box that's like a psychology experiment because it feels like the angriest many humans in this world get is inside the car. It's so interesting. So it's such an opportunity to explore how we can enrich um, how how companies can enrich that experience. And also as the cars get become more and more automated, There's more and more opportunity, the variety of activities that you can do in the car increases. So it's super interesting. So, um, I mean, in a practical sense, smart eye has been selected at least I read by 14 of the world's leading car manufacturers for 94 car models. So it's in a lot of cars. How hard is it to work with car companies? So they're all different? They all have different needs. The ones I've gotten a chance to interact with are very focused on cost. So, um, it's, and anyone who's focused on costs, it's like, alright, do you hate fun? [/INST] Let's </s><s>[INST] just have some fun. Let's figure out the most fun thing we can do and then worry about costs later. But I think because the way the car industry works, I mean, it's, it's a very then margin that you get to operate under. So you have to really, really make sure that everything you add to the car makes sense financially. So anyways, there is this new industry, especially at this scale of, of smart. I does it hold any lessons for you? [/INST] Yeah, I think it is a very tough market to, to penetrate. But once you're in, it's awesome because once you're in, you're designed into these car models for like somewhere between 5-7 years, which is awesome. And you just, once they're on the road, you just get paid a royalty fee per vehicle. So it's a high barrier to entry. But once you're in, it's amazing. I think the thing that I struggle the most with in, in this industry is the time to market so often we're asked to lock or do a code freeze two years before the car is going to be on the road? I'm like, guys, like, do you understand the pace with which technology moves? So I think car companies are really trying to make the Tesla, the Tesla transition to become more of a software driven architecture and that's hard for many. It's just a cultural change. I mean, I'm sure you've experienced that, right? </s><s>[INST] I think one of the biggest inventions or imperatives created by Tesla is like to me personally, okay, people are gonna complain about this, but I know electric vehicle, I know autopilot ai stuff. To me. The software over their software updates is like the biggest revolution in cars and um, it is extremely difficult to switch to that because it is a culture shift. It, uh, at first, especially if you're not comfortable with it, it seems dangerous. Like there's, uh, there's an approach to cars, so safety focused for so many decades. They're like, what do you mean? We dynamically change code? The whole point is you have a thing that you test [/INST] like, </s><s>[INST] and like it's not reliable because do you know how much you, cause if you have to recall this car's right? There's a, there's a, there's an understandable obsession with safety. But the downside of an obsession with safety is the same as with being obsessed with safety as a parent is like, if you do that too much, you limit the potential development and the flourishing of, in that particular aspect human being. But in this particular aspect of software, the, the artificial neural network of it. And um, but it's, it's tough to do? It's it's really tough to do culturally and technically like the deployment, the mass deployment of software is really, really difficult. But I hope that's where the industry is doing. One of the reasons I really want. Tesla succeeds exactly about that point. Not autopilot, not the electrical vehicle, but the software ization of basically everything, but cars. Especially because to me that's actually going to increase two things, increase safety because you can update much faster but also increase the effectiveness of folks like you who dream about enriching the human experience with with AI because you can just [/INST] like, there's </s><s>[INST] a feature like you want, like a new Emoji or whatever. Like the way Tiktok releases filters, you can just release that foreign car in car stuff. So, but yeah, that, that, that's definitely um, one [/INST] of the use cases we're looking into is once, you know, the sentiment of the passengers in the vehicle, you can optimize the temperature in the car. You can change the lighting, right? So if the backseat passengers are falling asleep, you can dim the lights, you can lower the music, right? You can do all sorts of things. Um, </s>
<s>[INST] and I'm not very good at it. Yeah. I do think that if you establish yourself as a person who could be trusted and is a good human being, you have a lot more freedom to then explore ideas that are different from your peer group. So like those seem like, if you separate the space of ideas versus some kind of like deeper sense of what this person is like that they're an interesting [/INST] and trustworthy and good human being. Well, like, is there somebody that you respect to, you can consider significantly smarter than you. And can you imagine believing an idea that you've heard them talk really disdainfully about? Like, how would you feel coming to me? </s><s>[INST] Like, I believe this thing that you find to be. Yeah, I do all the time. [/INST] Oh, yeah? Oh, yeah? Yeah. You make me braver than me. And to be fair, I support doing this. Like I try to do this, but I think like subconsciously I noticed that I don't do it as much. And so I'm suspicious of myself. I'm like, oh, I wonder if I'm hiding to myself like actual curiosity about things that might deviate from my peer group. Because I noticed that I'm not actually deviating with them </s><s>[INST] as much as I do with the outside world. Yeah, that's interesting. Like, because I do see most people I interact with as smarter than me, but I also have this intuitive feeling that dumb people, which I consider myself being, have wisdom. So like, in the disagreement, actually, I mostly believe in the power of conversation and in the tension of disagreement. So I think even just disagreeing from a place, from a good place, from a place of like love and respect for each other, I think I just believe in that. So it's not like individuals, you're disagreeing. You're like working towards arriving at some deeper truth together, right? Even if the other person is smarter. Maybe that's how I justify it for myself. I'm also a fan of conversations, because like I've seen just listening to conversations. It seems like a great conversation more emerges from it than the sum of its parts, right? Like somehow two people together can do like that, dance of ideas can somehow create a cool thing. By the way, I saw a video of you dancing at a bar drunk. It wasn't the bar drunk, it didn't look drunk, but just the dancing. It was like ballroom dancing type of thing. I was like, yeah. Something like that. I've been doing a bit of tango dancing. [/INST] I like it. Something like that. </s><s>[INST] Argentine? I like stuff with the body in general, like wrestling or combat. Usually when there's a tension, you have to understand the mechanics of how two bodies move [/INST] when they're in conflict and dancing is similar. You have to do rapid thinking, also. Rapid intuitive physical thinking, and that's my favorite kind of thing. A lot of exercise is really boring to me, because you can just do it while your brain's off. But something like ballroom dancing or fusion dancing, you have to constantly be figuring out, </s><s>[INST] like it's a rapid puzzle, and that's so wonderful. [/INST] What's fusion dancing? That's the video. Fusion dancing is like, if you have any sort of dance background, you can come and you just kind of mix those together. Oh, just kind of improvise. So you can have lot of people doing ballet, with people doing ballroom, with people doing blues. </s><s>[INST] Oh, it's cool. So you can have like people doing ballet. Okay, cool, and then there's an interesting dynamic because there's I don't know, maybe you can correct me, but there's, that's very meta. There's usually a lead and a follow. I guess most dancers have that. Yeah. Yeah, and so that, but both have a different, like you both have to be quite sensitive [/INST] to the other human being, but in a different way. </s><s>[INST] Yeah. [/INST] Yeah, it's interesting. So I like both that there is that definitive role </s><s>[INST] but also it's not somehow that one is better than the other. [/INST] There's an interesting tension between the two. Yeah, because it's like a basic rule set that allows for a ton of expression. I've recently started to experiment with reverse leading. It's not like back leading, it's like, I don't know. </s><s>[INST] Sometimes I was like, lead a move. So you can lead as a follow. [/INST] Oh, you can lead as a follow. When I'm typically following, </s><s>[INST] I'll occasionally throw in a little lead here and there. But don't you kind of always, oh, I see. But don't you hint at a lead when you're following? Don't you, just by the dynamics of your movement, you're not perfectly following. Because the lead is listening to your body, right? Yeah. [/INST] So you're kind of both figuring out what you do next. Yeah, that's true. I'm a very good follow though. Okay. So I'm like, I'm an invisible follow. You do move, it's like I... </s><s>[INST] Okay, oh, interesting. I'm not good at technique. I didn't know those existed like a perfect follow. [/INST] You seek it for perfect follow. I'm not good at technique. Oh yeah, I'm perfect. I didn't seek a perfect follow. I'm really ideal. I'm not great at technique and sometimes I'll follow over </s><s>[INST] but like with the following part, I'm very good at it. [/INST] Do you enjoy following? Yeah, yeah, yeah, it's really nice. It's, again, like it's a very fast physical puzzle you have to solve. It's like typing, I really like typing, </s><s>[INST] That's why I was inquiring about your keyboard earlier. [/INST] Why do you like typing? It's like the very fast, like the really rapid response was the reaction time. I like things that like have very fast reaction times, </s><s>[INST] like games like that. But typing is not a reaction. Or is it the brain generating words and then you're cost typing [/INST] a reaction? Well, okay the sensation that I get when I am typing is the kind of thing that I'm trying to point at. So maybe reaction time isn't quite, I don't know what the term is. But whatever that thing is. Like the thing where you have like look at a word and then communicate it into your fingers. Yeah. </s>
<s>[INST] Don't you think that's a good thing for the world that ai could potentially [/INST] I do. Absolutely. And furthermore, I want, you know, I'm pushing 80 now by the time I need help like that. I also wanted to roll itself in a corner and shut the funk </s><s>[INST] up. Let me let me linger on that point. Do you really [/INST] though? Yeah, I do. Here's </s><s>[INST] what you wanted to push back a little bit [/INST] a little but I have watched my friends go through the whole issue around having help in the house and some of them have been very lucky and had fabulous help and some of them have had people in the house who want to keep the television going on all day, who want to talk on their phones all day? No, </s><s>[INST] so basically [/INST] just roll yourself in the corner. </s><s>[INST] Unfortunately as humans, when we're assistance, we we care, we're still, even when we're assisting others, we care about ourselves more. And so you create more frustration and robot ai assistant can really optimize the experience for you. I was just speaking to the point, you actually bring up a very, very, very good point. But I was speaking to the fact that as humans are a little complicated, that we don't necessarily want a perfect servant. I don't maybe you disagree with that, but there's a, I think uh there's a push and pull with humans a little attention. A little mystery that of course that's really difficult for you to get right. But I do sense especially in today with social media, that people are getting more and more lonely, even young folks and sometimes especially young folks that loneliness, there's a longing for connection and a I can help alleviate some of that loneliness. Some just somebody who listens like in person, [/INST] um, that's so we </s><s>[INST] speak, so, so, so, so to speak. Yeah, so to speak. Yeah, that to me is really exciting. But so if we look at that, that level of intelligence, which is exceptionally difficult to achieve actually as the singularity or whatever. That's the human level bar that people have dreamt of that to touring dreamt of it. Uh He had a date timeline. Do you have how of your own timeline evolved on? [/INST] I don't I don't even think about it. You don't even think just this field has been so full of surprises for me. You're </s><s>[INST] just taking in and see fundamental. Yeah. [/INST] I just can't. Maybe that's because I've been around the field long enough to think, you know, don't don't go that way. Herb Simon was terrible about making these predictions of when this and that would happen. And he was a sensible guy. </s><s>[INST] His quotes are he often used right? As uh Yeah. Do you have concerns about ai the existential threats that many people like Elon musk and uh Sam Harris and others that [/INST] are thinking about that takes up a half a chapter in my book. I call it the male gaze. Well, you hear me out, The male gaze is actually a term from film criticism and I'm blocking on the woman's who dreamed this up. But she pointed out how most movies were made from the male point of view that women were objects, not subjects they didn't have any uh agency and so on and so forth. So when Elon and his pals Hawking and so on. Ok. Ai is going to eat our lunch and our dinner and our midnight snack too. I thought what? And I said to edify confound. Ah this is the first guy first. These guys have always been the smartest guy on the block and here comes something that might be smarter. Ooh let's stamp it out before it takes over. And Ed laughed. He said I didn't think about it that way. But I did, I did. And it is the male gaze, you know, okay, suppose these things do have agency. Well let's wait and see what happens. Can we imbue them with ethics? Can we imbue them with a sense of empathy or are they just going to be? I know we've had centuries of guys like </s><s>[INST] that. That's interesting that uh the the ego the male gaze is immediately threatened. So you can't think in a patient calm way of of how the tech could evolved. And he's speaking of which, You're 96 book The Future of Women I think at the time and now certainly now. I mean I'm sorry maybe at the time but I'm more cognizant of now is extremely relevant. You and Nancy Ramsey talk about four possible futures of women in science and Tech. So if we look at the decades before and after the book was released, can you tell a history, sorry, of women in science and tech and how it has evolved? How have things changed? Where do we stand? [/INST] Not enough? They have not changed enough the way that women are ground down in computing is simply unbelievable. </s><s>[INST] But What are the four possible futures for women in tech from the book? [/INST] What you're really looking at our various aspects of the present? So for each of those you could say, oh yeah, we do have backlash, look at what's happening with abortion and so on and so forth. Uh We have one step forward. One step back. The Golden Age of Equality was the hardest chapter to write. And I used something from the santa fe institute, which is the sand pile effect that you drop sand very slowly onto a pile and it grows and it grows and it grows until suddenly it just breaks apart. And in a way, me too has done that. That was the last drop of sand that broke everything apart. That was a perfect example of the sand pile effect. And that made me feel good. It didn't change all of society, but it really woke a lot of people up. </s>
<s>[INST] hard problem, a hard problem. But you haven't shied away from hard problems so well, you know. Uh So deep learning has been at the core of a lot of this technology. Are you optimistic about the current deep learning approaches to solving the hardest aspects of what we're talking about or do you think there will come a time where new ideas need to for the, you know, if you look at reasoning, so open the I. D. Mind a lot of folks are now starting to work in reasoning, trying to see how you can make your own networks, reason. Do you see that new approaches need to be invented to take the next big leap? [/INST] Absolutely. I think there has to be a lot more investment and I think in many different ways. And there are these, I would say nuggets of research farming in a good way, like learning with less data or uh like zero short learning, one short learning </s><s>[INST] and the active learning stuff you've talked about it. Yes, it's incredible. [/INST] So transfer learning is also super critical, especially when you're thinking about applying knowledge from one task to another or one language to another. Right? It's really right. So these are great pieces Deep learning has been useful to and now we're sort of marrying deep learning with uh transfer learning. Uh an active learning of course, that's more straightforward in terms of applying deep learning and an active learning setup. But but I do think in terms of uh now looking into more reasoning based approaches is going to be key for our next wave of technology. But there is a good news. The good news is that I think for keeping on to delight customers that a lot of it can be done by prediction tasks. Uh so and so we haven't exhausted back, so it's uh we don't need to give up on the deep learning approaches for that. So that's just, I wanted to uh </s><s>[INST] sort of creating a rich, fulfilling, amazing experience that makes amazon a lot of money and a lot of everybody a lot of money because it does awesome things. Deep learning is enough. The point, the point, I don't [/INST] think uh no, I mean I wouldn't say deep learning is enough, I think for the purposes of Alexa accomplished the task for customers, I'm saying there's still a lot of things we can do with prediction based approaches that do not reason, right? I'm not saying that and we haven't exhausted those, but for the kind of high utility experiences that I'm personally passionate about what Alexa needs to do, reasoning has to be solved to the uh to the same extent as you can think of natural language understanding and speech recognition to the extent of understanding intense has been, how accurate it has become. But reasoning, we have very, very early days, </s><s>[INST] let me ask you another way, how hard of a problem do you think that is [/INST] hardest of them? I would say hardest of them because again uh the hypothesis space of Israeli really large and when you go back in time, like you were saying, I wanna, I want Alexa to remember more things that once you go beyond a session of interaction, which is by session, I mean a time span which is today to worse is remembering which restaurant I like and then when I'm planning a night out to say do you want to go to the same restaurant now? You're up the stakes big time. And and this is where the reasoning dimension also goes very, very bigger. </s><s>[INST] So you think the space be elaborate on that a little bit just philosophically speaking, Do you think when you reason about trying to model what the goal of a person is in the context of interacting with Alexa, you think that space is huge? It's [/INST] huge? Absolutely. </s><s>[INST] You think so like another sort of devil's advocate would be that we human beings are really simple and we all want like just a small set of things. And there, so do you think you think it's possible cause we're not talking about fulfilling general conversation perhaps actually the Alexa prize is a little bit more about after that creating a customer, like there's so many of the interactions, it feels like are clustered in groups that are don't require general reasoning [/INST] I think yeah, you right in terms of the head of the distribution of all the possible things customers may want to accomplish. The tail is long and its diverse. Uh Right, so </s><s>[INST] from many, many long [/INST] tails from that perspective, I think you have to solve that problem otherwise uh and everyone is very different, like I mean we see this already in terms of the skills, right? I mean if you if you're an average surfer, which I am not right, but somebody is asking Alexa about surfing conditions, right? And there is a skill that is there for them to get to, right, that tells you that the tail is massive, like in terms of like what kind of skills people have created, it's humongous in terms of it and which means there are these diverse needs. And uh and when you start looking at the combinations of these, right? Even if you are pairs of skills, uh 90,000 to 2, it's still a big concern of combinations you're going. So I'm saying there's a huge to do here now uh and I think customers are, you know, wonderfully frustrated with things and they keep getting to do better things </s>
<s>[INST] Because in this— Why go to the moon in this decade and do the other things, JFK? Not because it's easy, because it's hard. Yeah, exactly. Don't ask questions. Okay, so the jumping, I mean, there's a lot of incredible stuff. If we can just rewind a little bit to the DARPA Robotics Challenge in 2015, I think, which was for people who are familiar with the DARPA Challenges, it was first with autonomous vehicles, and there's a lot of interesting challenges around that. And the DARPA Robotics Challenge was when humanoid robots were tasked to do all kinds of manipulation, walking, driving a car, all these kinds of challenges with, if I remember correctly, sort of some slight capability to communicate with humans, but the communication was very poor. [/INST] So it basically has to be almost entirely autonomous. You could have periods where the communication was entirely interrupted and the robot had to be able to proceed. But you could provide some high-level guidance to the robot, basically low-bandwidth communications </s><s>[INST] to steer it. I watched that challenge with kind of tears in my eyes eating popcorn. It was hard. But I wasn't personally losing hundreds of thousands, millions of dollars, and many years of incredible hard work by some of the most brilliant roboticists in the world. So that was why the tragic, that's why the tears came. So anyway, what have you, just looking back to that time, what have you learned from that experience? Maybe if you could describe what it was, [/INST] sort of the setup for people who haven't seen it. So there was a contest where a bunch of different robots were asked to do a series of tasks, some of those that you mentioned, drive a vehicle, get out, open a door, go identify a valve, shut a valve, use a tool to maybe cut a hole in a surface, and then crawl over some stairs and maybe some rough terrain. So it was, the idea was have a general purpose robot that could do lots of different things. Had to be mobility and manipulation, onboard perception. And there was a contest, which DARPA likes, at the time was running, sort of follow on to the grand challenge, which was let's try to push vehicle autonomy along, right? They encourage people to build autonomous cars. So they're trying to basically push an industry forward. And we were asked, our role in this was to build a humanoid at the time it was our sort of first generation Atlas robot. And we built maybe 10 of them. I don't remember the exact number. And DARPA distributed those to various teams that sort of won a contest, showed that they could program these robots, and then use them to compete against each other. And then other robots were introduced as well. Some teams built their own robots. Carnegie Mellon, for example, built their own robot. And all these robots competed to see who could sort of get through this maze of the fastest. And again, I think the purpose was to kind of push the whole industry forward. This may, we provided the robot and some baseline software, but we didn't actually compete as a participant where we were trying to drive the robot through this maze. We were just trying to support the other teams. It was humbling because it was really a hard task. And honestly, the robots, the tiers were because mostly the robots didn't do it. They fell down repeatedly. It was hard to get through this contest. Some did, and they were rewarded and won. But it was humbling because of just how hard, these tasks weren't all that hard. A person could have done it very easily, but it was really hard to get the robots to do it. </s><s>[INST] It was really, you know, you know. With the general nature of it, the variety of it. The variety. [/INST] And also, that I don't know if the tasks were of it. </s><s>[INST] The variety. Sort of the task in themselves helped us understand what is difficult and what is not. I don't know if that was obvious before the contest was designed. So you kind of try to figure that out. And I think Atlas is really a general robot platform. And it's perhaps not best suited for the specific tasks of that contest. Like for just, for example, probably the hardest task is not the driving of the car, but getting in and out of the car. And Atlas probably, you know, if you were to design a robot that can get into the car easily and get out easily, you probably would not make Atlas that particular car. [/INST] The robot was a little bit big to get in and out of that car. Right? It doesn't fit, yeah. This is the curse of a general purpose robot. That they're not perfect at any one thing. But they might be able to do a wide variety of things. And that is the goal at the end of the day. You know, I think we all want to build general purpose robots that can be used for lots of different activities. But it's hard. And the wisdom in building successful robots up until this point have been, go build a robot for a specific task and it'll do it very well. And as long as you control that environment, it'll operate perfectly. But robots need to be able to deal with uncertainty. If they're gonna be useful to us in the future, they need to be able to deal with unexpected situations. And that's sort of the goal of a general purpose or a multi-purpose robot. And that's just darn hard. And so some of the other is these curious little failures. Like I remember one of a robot, you know, the first time you start to try to push on the world with a robot, you forget that the world pushes back and will push you over if you're not ready for it. And the robot, you know, reached to grab the door handle. I think it missed the grasp of the door handle. It was expecting that its hand was on the door handle. And so when it tried to turn the knob, it just threw itself over. It didn't realize, Oh, I had missed the door handle. I didn't have, I didn't, I was expecting a force back from the door. It wasn't there. And then I lost my balance. So these little simple things that you and I would take totally for granted and deal with, the robots don't know how to deal with yet. And so you have to start to deal with all of those circumstances. </s>
<s>[INST] shopping for you. And so you would have potentially federal support of that kind of thing. So these kinds of efforts [/INST] and identify where they're vulnerable people live. It's really challenging in multigenerational homes in La County, for instance, there's a lot of, of older people living together with younger people in relatively crowded there there, there, there, it's really quite a challenge. But there again, you can use resources. So if grandma uh, is worried that grandson has come home but is potentially being exposed, grandson calls grandma says, I mean, I might have been at a party where I might either, where covid was grandma calls public health, public health and says, okay, you can have this hotel room for a couple of days until you check turned </s><s>[INST] negative in case it wasn't clear. The idea of focus protection is the people that are vulnerable, protect them and everybody else goes on with their lives. Open up the economy, just do as it was before. [/INST] And there was still fear abroad. So there still would be some restrictions people would pose on themselves. They probably would go to parties. Last grandsons probably wouldn't go so many parties, right? Um, uh, that there would be less, less participation in big gatherings. Uh, and you may even save like big gatherings in order to, to restrict community spread again, I'm not against any of that. Um but you shouldn't be closing businesses, you shouldn't be closing churches and synagogues, you shouldn't be closing, you shouldn't be forcing people to not go to school. You should, you should not be shuttering businesses, You should just let just allow society go on some disease will spread. But as we've seen the lockdown didn't stop the disease from spreading anyways. </s><s>[INST] Right? So what do you make of the criticism that this idea, like all good ideas cannot actually be implemented in a heterogeneous society where there's a lot of people inter mixing and once you open it up, people like that, the younger people will just forget that this is even existing and they'll stop caring about the older people and mess up the whole thing and the government will not want to fund and you kind of the great efforts you're talking about, about food delivery and then the food delivery services will be like, why the heck am I helping out on this anyway? Because like it's not making me much money and so therefore like all good ideas, it will collapse. [/INST] That might be true. I mean, I think it's always a risk with policy thing, but I think like think back to the moment, but we actually felt like we were in this together to some extent, right? I think I think that that um that empathy that we had that was used to like tell people to stay in and like happily not not going happily, but like stay in um to to like wear a mask or two to do all these things that we thought would help other people could have been redirected to actually helping the people who </s><s>[INST] most needed to be. Especially I do remember March. So this is even way, way before Barrington, all all that kind of stuff. March april may there was a feeling like if if we all just work together will solve this and that maybe started to, when did that start breaking down? I mean unfortunately the election is mixed into this that it became politicized but I think it lasted quite a long [/INST] time. I think into the summer. I think there was some, some, some of that sense. I don't know, obviously varied among different people but but I think that it's true. It would have been challenging. It's also true. That is heterogeneous exactly the way you said. Um But what that means is you need a local response a response. So like, like my vision of a public health officer is someone that understands their community, not not necessarily the nation at large but their community and then works within their community to figure out how to deploy the resources that they have available. Um to do, to do the kind of protection policies we're talking about. That's that's what should have happened instead. They spent a huge amount of efforts closing, making sure businesses stay closed businesses that I mean there are, you know, like hardware stores that closed. What good did it closing a hardware store do for the spread of Covid? If it has an effect on spread? Covid spread, I mean, it's going to be checking to make sure that plexiglass was put up everywhere, which now in retrospect, turns out to probably made the disease worse. You know, masking enforcement. So shaming around mask, I mean, a huge amount of effort on things that were only tangentially related to focus protection. What if we turned our energy, </s><s>[INST] that [/INST] enormous energy put into that instead into focus protection of the vulnerable. That's essentially the conversation I was calling for. And it wasn't I mean, I didn't think of it as we had every single idea. I mean, we gave some concrete proposals, but the criticism we got was that those concrete proposals weren't enough. And the answer to that I have is that's true. They weren't enough. I wasn't thinking of them as enough. I was thinking that I wanted to involve an enormous number of people in local public health to help think about how to do focus protection in their communities. </s>
<s>[INST] when they're talking about the police. So the overstepping, overreach, the lack of transparency. Of course, we see this kind of stuff in foreign policy as well, which is starting military conflicts and a lot of the supporters, at least with the Iraq and Afghanistan wars were conservatives and hawks and so on. So there's a lot of hypocrisy in terms of principles and so on. But maybe one question is, in this discussion about racism and policing, there was a lot of cops that might listen to this and feel like they're not being, their profession is not being respected. They're not being heard. Not being respected to the difficulty of the problem they're facing. [/INST] Can I just interject? Remember a few moments ago. I mean, if I were in charge of things, if I were in charge of things, I'd pay police more, in fact, much more than they receive. I do, police have a very difficult job, extraordinarily difficult job. I mean, for one thing, sort of maintaining the law. The law, that's a very complicated thing, the law. That's not an easy thing. I mean, I teach law. I spend a lot of hours with very smart people trying to understand the law, very difficult. So here we expect people to understand the law at the same time that they are grappling with people, some of whom are violent. It's very difficult. I respect police officers. And I said, we need police officers. You did not hear me say, by the way, so let's get down to brass tacks. You did not hear me say, defund the police, did you? In fact, to the contrary, I said, defund, actually I want more funds for the police. I want to hold them accountable. I understand the difficulty of their job. I respect the police. I want people to respect the police. I also want the police to respect civilians and demand that they do. I am not a police abolitionist, far from it, far from it. Again, we need good policing. </s><s>[INST] For good policing, we need good people. To what degree, almost philosophically, maybe practically, do you think police should be doing racial profiling? [/INST] Profiling in general. </s><s>[INST] Okay. It's a very difficult philosophical, moral human question. [/INST] Yeah, so first thing we need to do, and here we get back to the early part of our conversation because we focus so much on, first part, a word. Here we have another word, profiling. Question, what is racial profiling? Now, here we have, in the weeds, we have people talking past one another. I've been in conversations with police officers and debates, and we talk past one another because we are defining racial profiling very differently. If you ask, I've been in conversations with police officers and they say, oh, I'm totally against racial profiling. Then I say, well, sir, what do you mean by racial profiling? And here's what they say. Racial profiling is when police officers act against somebody wholly on the basis of race that gets rid of the issue because most police officers don't act against anyone wholly on the basis of race. You could have the most racist police officer, and that police officer is not going to act adversely against the 90-year-old black woman walking down the street with a cane, okay? So it's always, you know, if you define racial profiling that way, you're getting rid of the issue. The issue is, the proper issue is this. Should the police be able to act against someone taking race into account as a factor? So let's imagine that a black person who's 25 years old is walking down the street right next to a white person who's 25 years old. Some people would say, you know what? Under those circumstances, it's okay for the police officer to give two looks at the black person and only one look at the white person. Why? Because the statistics tell us that the black 25-year-old, there's much more risk of that person acting in an unlawful way. If you take a look at, you know, crime statistics and ask the question, with respect to, you know, homicide, with respect to robbery, with respect to various, you know, crimes, is there, is there a difference between the white 25-year-old and the black 25-year-old? With respect to certain crimes, the answer is, in certain places, the answer is, yeah, there is a difference. And there is a greater risk that the black 25-year-old has engaged in various forms of criminality. I'm not, you know, that, okay. Under those circumstances, what do I say? Should the police officer, therefore, be allowed to take action vis-a-vis the black person, as opposed, you know, as against the white person? My answer is no. I'm fully willing to concede, let's concede for the point of, you know, for the point of discussion, that there is more risk. There might be, there might be. But, for reasons of constructing the sort of society I want, we should not empower agents of the state to act towards certain people in a way that's, you know, adverse to them. Let me try to break this down in a little different way. Let's go back to, let's talk about what happens when you wanna get on an airplane. You know, wasn't so long, you know, 9-11 wasn't all that long ago. It was a while ago, but it wasn't all that long ago. And this very issue came up with the respect of the profiling of Muslims. And there were some people who said, well, geez, you know, in the aftermath of 9-11, profiling of Muslims makes sense. You know, no hard feelings, but, you know, the 11 people who, you know, were on those planes, were all Muslims. Now, there is a rationale. You could just simply say, it's not prejudice, it's not animus, it's not invidious, it's just, you know, the facts take us this way. Well, the facts never take us this way. There are facts, and then there is our choice of how we want to respond to those facts. Now, you could respond by saying, well, we perceive Muslims to be more likely to, you know, do bad things on an airliner. You could respond in that way. On the other hand, you could say, no, we want a society in which people do not have to grapple with prejudice on the basis of their religion or on the basis of their race. And to deal with that, we are gonna demand, we're gonna demand that agents of the state act towards people in the same way. And so if that means that everybody getting on the airplane, before they get on the airplane, has to, you know, open up their luggage and it slows things down, but everybody has to open up their luggage. I would prefer that over a system in which we focus on people who are Muslim. And one of the reasons, and I'm gonna bring this back to the racial thing. One of the reasons why I wanna insist upon that is because if, you know, if we all have to open up our luggage, what that means is we're all paying a tax for more security. And we're all likely to ask ourselves, hmm, do we wanna pay this tax? Whereas if we focus simply on the Muslims and allow the Muslims to be the only ones who are sort of paying the tax, we'll foist that on them. Same in the, you know, black person, white person, 25 years old, walking down the street. Do we want to impose a racial tax on the black 25 year old? Some people would say, yes. I say, that's a mistake. Black people aren't stupid. They know that they're paying this tax. It is a violation of, it seems to me, the rules that we ought to want to have to govern our society. I say, spread the costs, make the police deal with everybody the same, and don't allow a situation to develop in which a group of people can accurately say, we are paying more of a cost </s>
<s>[INST] But I think the core fascinating idea with the Tesla bought is the one that's carried by Waymo as well as when you're solving the general robotics problem of perception control where there's a very clear applications of driving. It's as you get better and better at it when you have like Waymo driver, the whole world starts to kind of start to look like a robotics problem. So it's very interesting for [/INST] now your reflection, complication, segmentation, tracking planning. Like it's scary. </s><s>[INST] Yeah, so there's no reason. I mean I'm not, I'm not speaking for Waymo here, but you know, um moving goods, there's no reason transformer, like this thing could, you know, uh take the goods up an elevator, you know like that, like uh slowly expand what it means to move goods and expand more and more of the world into a robotics problem. [/INST] Well that's right and you start to like think of it as an and then robotics problem from like loading from, you know from everything and even like the truck itself, um you know, today's generation is integrating into today's understanding of what a vehicle is, right, A Pacifica, jaguar, the freight liners from DEMAR, there's nothing that stops these us from like down the road after like starting to get to scale, to like expand these partnerships to really rethink what would the next generation of a truck look like? Um that is actually optimized for autonomy, not for today's world. Um and maybe that means a very different type of trailer, maybe that like there's a lot of things you could rethink on that front which is on its own very, very exciting. </s><s>[INST] Let me ask you, like I said, you went to the mecca of robotics which is cmu, Carnegie Mellon University, you got a PhD there, so maybe by way of advice and maybe by way of story and memories, what does it take to get a PhD in robotics at cmu and maybe you can throw in there some advice for people who are thinking about doing work in artificial intelligence and robotics and are thinking about whether to get a PhD. [/INST] I actually, when I was a senior for undergrad as well and didn't know anything about robotics coming in and was doing, you know what your computer engineering, computer science and really got more and more into kind of a I and then fell in love with autonomous driving and at that point like that was just by a big margin, like such a incredible like central spot of develop of investment in that area. And so what I would say is that like robotics, like for all the progress that's happened is still a really young field, there's a huge amount of opportunity now that opportunity shifted where something like autonomous driving has moved from being very research and academics driven to being commercial driven, where you see the investments happening um in commercial now there's other areas that are much younger um and you see like kind of grasping and manipulation, making kind of the same sort of journey that like autonomy made and there's other areas as well, what I would say is the space moves very quickly. Anything you do a PhD in like it is in most areas will be evolve and change as technology changes and constraints change in hardware changes in the world changes. Um and so the beautiful thing about robotics is a super broad, it's not a narrow space at all and it could be a million different things in a million different industries. And so uh it's a great opportunity to come in and get a broad foundation on ai machine learning, computer vision systems, hardware sensors, all these separate things, you do need to like go deep and find something that you're like really, really passionate about obviously like just like any PhD this is like a 56 year kind of endeavor and you have to love it enough to go super deep to learn all the things necessary to be super deeply functioning in that area and then contribute to it in a way that hasn't been done before. And in robotics that probably means more breath because robotics is rarely kind of like one particular kind of narrow technology and it means being able to collaborate with teams where like one of the coolest aspects of like my the the experience that I like kind of cherishing our PhD is that we actually had a pretty large A V. Project that for that time was like a pretty serious initiative where you got to like partner with a larger team and you had the experts in perception and the experts in planning and the staff and the mechanical challenge. So I was working on a project called U. P. I. Back then which was basically the off road version of the DARPA challenge. It was a DARPA funded project for basically like a large off road vehicle that you would like drop and then give it away 0.10 kilometers away and it would have to navigate a complete instruction and off road environment. Yeah, so like forest, ditches, rocks, vegetation and so it was like a really really interesting kind of a hard problem where like wheels would be up to my shoulders is like gigantic right </s><s>[INST] by the way, a V. For people stands for autonomous [/INST] vehicles, vehicles. Yeah. Sorry. Uh And so what I think is like the beauty of robotics, but also kind of like the expectation is that um there's um spaces and computer science where you can be very very narrow and deep robotics. One of the the necessity but also the beauty of it is that it forces you to be excited about that breath and that partnership across different disciplines that enable it. But that also opens up so many more doors where you can go and you can do robotics. And almost any category where robotics isn't a isn't really an industry. It's like it's like a I right, it's like the application of physical automation to uh you know, to all these other worlds. And so you can do robotic surgery, you can do vehicles, you can do factory automation, you can do health care or you can do like uh leverage the ai around the sensing to think about static sensors and seeing understanding. So um so I think that's gotta be the expectation, the excitement and uh breeds people. They're probably a little bit more collaborative and more excited about um working in teams. </s>
<s>[INST] that. But it's at a certain point at the same time, I've gotten to hang out with certain people, especially in L. A. That are like in the middle of nowhere, like a Malibu or something. And it's like that quiet, can [/INST] you hear your ears ringing? It's so quiet </s><s>[INST] basically. And it's like holy sh it is a good place. This is a good way if you want to write something or create something. This is like super quiet. So [/INST] my mom was, my mom is a science journalist, science author. He just published her first her first book actually on poop of all things. Yeah, fecal. The waste management is actually very fascinating concept and look through history and she would do that. She goes to complete solitude. And she writes, yeah, </s><s>[INST] it's beautiful. No sirens. I mean new york is the opposite of that. So, you know, it's, you've, you've brought it uh you brought on yourself, [/INST] I've lived there for 20 years. </s><s>[INST] Has it been tough? Like going on stream to put on the face of happiness through that? [/INST] Yeah. Yes. But I find my ways to </s><s>[INST] have [/INST] Moments where I can talk about it if it's on a stream, I don't get 10,000 live viewers. So it's very different. It's, if I stream late night I get a 1500-2000 viewers. I used to care a lot more about viewers on, on, on stream, but I've basically invested fully in Youtube. So that's kind of </s><s>[INST] the way. And I think, I don't know, maybe you can correct me, but I think people [/INST] appreciate </s><s>[INST] the human being behind the chess streamer. I [/INST] think so. I think so. I think a lot of people, not in the chess world, but just a lot of people they put on a persona. And just in general, social media is the highlights of your life or the low lights. Just as long as they're dramatic. But I've tried, I tried to be very open and honest when I'm tired, I'm tired, it's what makes my recaps of my tournaments. I think so. Real. </s><s>[INST] Yeah, man, you're an incredible person. I've been a fan for a long time. It's kind of funny that we connected and we got a chance to talk. Uh please please keep creating, keep teaching people for [/INST] now. I'm not going anywhere. </s><s>[INST] Well, it could end at any moment as we talked about. So yeah, thank you so much for talking today, man. Thank you for everything you do. It was an honor. It [/INST] was great. Thanks for having me on. </s><s>[INST] Thanks for listening to this conversation with Lydia Osmond. To support this podcast. Please check out our sponsors in the description and now let me leave you with some words from Irving Chair nev Every chess master was once a beginner. Thank you for listening and hope to see you next time. [/INST] </s>
<s>[INST] Like, this deeply about YouTube analytics? I think a large amount care about curiosity and exploration of interesting ideas. [/INST] So, in that sense, yeah, this would fit it. In that sense, yeah, I love it. This is funny. This isn't me like trying to make, I love you, and I actually, I loved your Magnus one and even your Hikaru one was really good, a bunch of other ones, but I think we're getting to the point now where only analytics junkies would want to keep hearing more analytics talk and the normie is probably like, they've had their dose of YouTube talk for the next </s><s>[INST] three years. I love you. [/INST] I actually, I love you too. Maybe I'm wrong. Comment if I'm wrong. I could be. I don't know your audience. </s><s>[INST] See, this is where you would tell me, shut up, I know my audience, you dumbass. And I don't at all. I actually, I just follow the thread of curiosity and I think there's just a lot of curious humans in the world. And to me, it's like, so the question about analytics is the question of basically stepping away, stepping outside of yourself and thinking, why the hell do I like TikTok so much? Why do I like Twitter so much? Why do I like YouTube so much? And getting, even if you're not a creator, getting an insight into that is really interesting. It's like, what, because all these platforms are fundamentally changing the nature of content. People are reading books less, they're probably going to be watching movies less and less, they're probably going to be watching Netflix less and less. Do you ever think about the sort of the darker side of YouTube and with shadow banning and censorship and all that kind of topics, especially if you see it in other platforms like Twitter, that Elon recently highlighted the shadow banning that was happening and in general, the censorship that was happening on those platforms. Do you think about the role of centralized control of which information is or isn't made available through search and discovery? I'll be honest, I never really think about it. [/INST] You just try to make fun videos that- Yeah, I'm more, I'm kind of more in my own lane, but it's not like that I don't just specifically think about, I just like a lot of stuff in general, I'm just kind of in my own lane thinking about my own stuff. But now that you asked, I'm curious, what are your thoughts on YouTube and that kind </s><s>[INST] of stuff? Well, I'm generally against centralized censorship or shadow banning. Shadow banning is the worst one because not that the goal of creating a healthy platform where you're having great conversations and videos that are not spreading misinformation, that sounds like an admirable goal, but that's too difficult of a job for a centralized entity. [/INST] That's too big of a- Yeah, there's the misinformation stuff and then there's also just like the videos where they do something that causes, what happened back in the day, the adpocalypse and a lot of creators revenue plummets because people are doing videos that advertisers don't deem acceptable and then now all these big advertisers are pulling and the little guys are getting hit because ad rates dropped by 30% and the person who just quit his job to go full-time consecration now can't sustain it. So it's also, it's like a lot of different variables as well. That makes it so complicated. </s><s>[INST] Well, I think the big thing is transparency, especially around shadow banning for people. [/INST] I agree, I agree. On shadow banning, you should be transparent. You should let people know it, you know, obviously there has to be some type of controls. People can't just post whatever and so if you're pulling those levers, they should at </s><s>[INST] least know. Yeah, so they know how to improve their content. They can understand it, they can, if it's a wrong shadow banning, like as a society that we should not shadow ban this kind of content, that means you should be publicly [/INST] discussing it and having that. Because if not and if it's not known, then it's just kind of like, well then who's pulling the strings and like, how do we know they're not just manipulating things to get whatever </s><s>[INST] message they want out there and silence other ones? Yeah, and there could be sort of in the background, government influence, which is where actual freedom of speech comes into play, that government should not have any control or be able to put pressure on censorship of speech, and it gets weird if none of that is being, there's no transparency around it, but to be fair, that's a huge responsibility. [/INST] The amount of content that YouTube is uploaded on YouTube that is shared by YouTube, viewed by YouTube. But even more of a reason why it would probably make sense to be transparent, because then </s><s>[INST] people can help fact check it. That's right. But that requires building a platform that makes that easy. To make fact checking easy, to make Twitter now has being able to share context and all that kind of stuff. That crowdsource it. Crowdsources the way Wikipedia crowdsources it. I mean, there's... Right. [/INST] It's right. </s><s>[INST] And then you open a random Wikipedia article. But people criticize Wikipedia because there is a political lean to the editors of Wikipedia and then they get some articles that definitely have a bias to them and all that kind of stuff. It's a difficult problem. It's a difficult problem to solve that ultimately, as much as possible, it would be nice for the viewer to have control of that versus the entity that's hosting it. So for the viewer to decide. [/INST] I'll let you just figure that stuff out. </s><s>[INST] I'm just going to make fun. Cool videos? [/INST] Yeah. Yeah. </s>
<s>[INST] is by the way fishing is how the current nuclear power plants were. [/INST] And so we have nuclear energy today because fishing reactors are relatively easy to build. You've got to have what's hard is getting the materials. Okay. And that's just as well because if everyone could get those materials there would be weapons proliferation and so forth. But it wasn't all that long after even the discovery of nuclear fission, that fission reactors were built and fission reactors of course operated before we had weapons. Um So um I think nuclear power is obviously important to meet the energy challenges of our age. It is completely intrinsically completely, Our co two emissions free. And in fact the wastes that come from nuclear power, whether it's fishing or fusion for that matter are so moderate in quantity that we shouldn't really be worried about them. I mean, yes, fish and products are highly radioactive and we need to keep them away from people. But there's so little of them that keeping them away from people is not particularly difficult. And so while people complain a lot about the drawbacks of fish and energy, um I think most of those complaints are ill informed. We can talk about the challenges and the disasters, if you like, of of of fission reactors. But I think fishing in the near term offers a terrific opportunity for environmentally friendly energy. Which which in the world as a whole is rapidly being taken advantage of china and India and places like that are rapidly building fish and plants were not rapidly building fish and plants in the U. S. Although we are actually building two at the moment um Two new ones, but we do still get 20% of our electricity from fish and energy and we could get a lot more. </s><s>[INST] So. So it's clean energy. [/INST] So it's clean energy. </s><s>[INST] Now now again, the concern is that there's a very popular HBO show on uh just came out on Chernobyl. Uh there's the Three Mile Island, there's Fukushima, that's the most recent disaster. So there's a kind of a concern of uh yeah, I mean if nuclear disasters, is that what what do you make of that kind of concern, especially if we look into the future of fish and energy based reactors? [/INST] Well, first of all, let me say one or two words about the contrast between fission and fusion and then we'll come on to the question of the disasters and so forth. Fishing does have some drawbacks and they're, and they're largely to do With 4, 4 main areas. One is, do we have enough uranium or other fissile fuels to supply our energy needs for a long time. The answer to that is that we know we have um enough uranium to support fish and energy worldwide for thousands of years, but maybe not for millions of years. Okay. Um so that's resources. Um secondly, there there are issues to do with wastes, fish and wastes are highly radioactive and some of them are volatile. And so for example, um uh in Fukushima, the problem was that some fraction of the fish and wastes were volatile ist and went out as a cloud and and polluted areas with um cesium 1 37 strontium 90 and things like that. So that's a challenge of fishing. Um there's a problem of safety beyond that and that is that inefficient. It's hard to turn the reactor off when you, when you stop the nuclear reactions, there is still a lot of heat being liberated from the fission products and that is actually what the problem was at Fukushima, the Fukushima reactors were shut down the moment that the earthquake took place and they were shut down safely. What then happened after that Fukushima was, you know, there was this enormous tidal wave many tens of meters high that came through and destroyed the electricity grid feed to the Fukushima reactors. And they are cooling was then turned off and it was the after heat of the turned off reactors that eventually caused the problems that led to release. And so that so that is, that's a safety concern. And then and then finally there's a problem of proliferation. And that is that fish and reactors need fissile fuel and the technologies for producing the enriching and so forth. The fuels can be used can be can be bye bye bad actors to generate um the materials needed for a nuclear weapon. And that's a very, very serious concerns. So those are the four problems. Fusion has major advantages in respect of all of those problems. It has more longer term um fuel resources, It has far more benign waste issues. The radio activity from fusion reactions is at least 100 times less than it is from fission reactions. It has um no, no, essentially none of this after heat problem because it doesn't produce fish and products that are highly radioactive and generating their own heat when it's turned off. In fact, the hard part of fusion is turning it on not turning it off. And and finally, you don't need the same uh fission technology to do to make fusion work. And so it there it's got terrific advantages from the point of view of proliferation control. So those are the those are four main issues which make fusion seem attractive technologically. Because they address some of the problems of fish and energy. I don't mean to say that fish and energy is overwhelmingly problematic, but clearly there have been catastrophes associated with fishing reactors. Fukushima actually is, I think in many ways are often overstated as a disaster because after all, nobody was killed by the reactors essentially zero. And that's in the context of a disaster And tsunami that killed between 15 and 20,000 people instantaneous, more or less instantaneously. So, you know, in the scale of risks, one should take the view that uh in my in my in my estimation that um fish and energy came out of that looking pretty good. Okay. Of course that's not the popular conception. Okay. </s>
<s>[INST] mentioned, one of the things you're focused on is expanding the number of people, maybe a billion people on coin base or using Cryptocurrency, where are we at now? How do we get to a billion? As [/INST] of Q4 last year we had 89 million verified accounts on Coinbase, but in any given Quarter only, you know, maybe like 10 or a little more million of those are like really active, so um and then if you look at globally, I think some of the estimates I've seen is maybe there's like 200 million people or something like that who have ever used or tried crypto so we're along, you know, we're a ways from a billion, but it's not like that far off um </s><s>[INST] Yeah, [/INST] so a few things, one is the Blockchain has got to become way more scalable. Um it's kind of like we're all running dial up modems and we need broadband and so it's just like too expensive, too slow to do all these transactions and I think if we just get L. two is working and scalability, you know, we'll see another order of magnitude kind of come out just from that. Um I think the second would be more clear regulation that would help a lot. Um I do talk to, you know pension funds and um you know various asset managers having wealth funds and stuff and a lot of them tell me we've we've got 1% of our portfolio in crypto today but we really would rather have like 20% in there. But what we're waiting for is more clear regulation um coming out and saying that clear test that I was saying these assets or commodities regulated by. So if you see these are my sec these are treasury, whatever. So that would be a big unlock </s><s>[INST] do transactions. So one of the things that you mentioned payments. Sorry? Well does that unlock a lot of users? [/INST] Yeah it does. I mean remittances like a huge thing. People sending money home to their families in other countries where the fees are super high. So yeah, if we get blocks needs to be more scalable and there's more global adoption, like I think we'll see Remittance quarters um move over to crypto a lot. There's also just um the other thing that's driving a lot of crypto adoption is basically the creation of more and more third party apps, so adapts they're sometimes called the central adapt. So a lot of startups now um you know how like you used to use in the early two thousand's they call them dot com startups but now you don't need to say dot com because everybody's using the internet and so now there's like hundreds of thousands of these crypto startups but I think in the future you won't need to call them crypto startups because they'll just be called start up because everyone is using the internet and crypto and whatever. So anyway the the use cases, the utility of crypto is is getting better and better with like all these third party apps getting funded and created and </s><s>[INST] do you think there's going to be a killer or a set of like a thing where nobody can live without? I was still waiting for that. [/INST] There's gonna be a bunch of them, it's just like, it's like the internet, like what were the killer web companies, you know like Uber and Wikipedia and every being google and like so there's gonna be some big winners but there'll be thousands of this is basically the new, it's like what happened with the dot com startups in the early two thousands is like a lot of the best entrepreneurs are building crypto startups now. So um tons of venture money flowing into the space, a lot of smart young people. So </s><s>[INST] do you think Bitcoin or some other Cryptocurrency will become the reserve currency of the world at some [/INST] point. So this is kind of a controversial idea but I actually think yes, um I do think Bitcoin could end up becoming a reserve currency of the world, There's so I've been reading Ray Dalio recently um with his new book like the Changing World order and I thought it was a really well researched book. Um He talks in there. He looks back at history, right? He looks at like empires and um you know going back to various chinese empires, the Dutch and Ottomans and everybody and how did they rise? And they were able to have the reserve currency as they as they rose And what produced that like it came from you know good education and innovation and better trade. And anyway, so the U. S. By some measures is kind of looks like it's maybe had a really good run and it's coming down a little bit and china is kind of kind of coming up, who knows how that will play out by the way? Like the world is very complicated. It could that could switch. Um But I guess if the US dollar is going to be seeing more inflation in the future, the chinese yuan is not like necessarily better. Right? I mean they have a ton of debt as well. And um you know it's not like you could really that you want could be inflated as well, right? I probably will be. And so I do think that there's this group of people today which probably most traditional. Um I don't know like the people who run big banks and like governments and stuff that they're not, this is not really on their radar today. But I think there's there's a basically a group of younger people in that kind of You know 25, year old range who are tech savvy, they're starting to think of crypto as like the primary thing in their financial life. It's like I basically hold my wealth in crypto and I use dollars or euros or whatever. If I if I happen to need something, I convert it to that last minute. Like if I if I go home, if I'm traveling I might convert some local currency in the moment. But that's not where I hold my most of my wealth. So this segment of the population is not like massive yet from a GDP point of view, but um I think it's a leading indicator of where things could be going and this is actually good for the world. It's kind of like, especially if china does continue to rise and it has a more authoritarian view, it'll be kind of this very centralized east versus a decentralized west um where people are in the west in the free world really kind of embracing um crypto and a more open, fair free global financial system, which I think will be enormously beneficial for humanity. And I do think basically Bitcoin is the reserve currency, the gold standard of the crypto economy. Um so that's pretty crazy. </s>
<s>[INST] You mentioned a lot of great autonomous vehicle companies uh, that are taking sort of the level four, level five, they jump in full autonomy with a safety driver and take that kind of approach and also through simulation and so on. There's also the approach that Tesla autopilot is doing, which is kind of incrementally taking a level two vehicle and using machine learning and learning from the driving of human beings and trying to creep up, trying to incrementally improve the system until it's able to achieve Love of four taught me so perfect autonomy in certain kind of geographical regions. What are your thoughts on these contrasting approaches? [/INST] When she first of all, I'm a very proud Tesla owner and I literally used the autopilot every day and it literally has kept me safe is a beautiful technology specifically for highway driving when I'm slightly tired because then it turns me into a much safer driver And that 100% confident that's the case in terms of the right approach. I think the biggest change I've seen since I've been away my team is it's a single deep learning. I think deep learning was not a hot topic when I when I started being more or google self driving cars, it was there. In fact we started google brain at the same time in google X. So I invested in deep learning, but people didn't talk about, it wasn't a hot topic. And nowadays there's a shift of emphasis from a more geometric perspective where you use geometric sensors, they give you a full three D view when you do geometric reasoning about all this box over here might be a car Towards a more human, like, Oh let's just learn about it. This looks like the thing I've seen 10,000 times before. So maybe it's the same thing, machine learning perspective and that has really put, I think all these approaches on steroids. Um, and Udacity, we teach a course in self driving cars. Uh in fact, I think we've graduated over 20,000 or so people on self driving car skills. So every, every self driving car team in the world now use our engineers and in this course, the very first homework assignment is to do lane finding on and images and lane finding images for laymen. What this means is you, you put a camera into your car or you open your eyes and even know where the line is, right? So so you can stay inside the lane with your car. Humans can do this super easily. You just look and you know where the line is just intuitively for machines for a long term was super hard because people would write these kind of crazy rules if there's like vinyl and Marcus and he's literally means this is not quite white enough. So it's all, it's not right or maybe the sun is shining, so when the sun shines and this is why And this is a straight line and maybe it's not quite a straight line because the vote is curved and and do we know that there's a six ft between lane markings or not or 12 ft whatever it is. Um and now what the students are doing, they would take machine learning. So instead of like writing these crazy rules for the lane marker is there to say, hey, let's take an hour driving and label it and tell the vehicle this is actually the laying by hand and then these are examples and have the machine find its own rules what lane markings are And within 24 hours now every student has never done any programming before in this space can write a perfect lane finder. As good as the best commercial land finders. And that's completely amazing to me. We've seen progress using machine learning that completely dwarfed anything that I saw 10 years ago ago. </s><s>[INST] Yeah. And just as a side note the self driving car, nano degree, the fact that you launched that Many years ago now, maybe four years [/INST] Ago, three years ago, three </s><s>[INST] years ago. It's incredible that that's a great example of system level thinking sort of just taking an entire course that teaches how to solve the entire problem, I definitely recommend people, [/INST] it's been popular, it's become actually incredibly high quality related with Mercedes and and and raise other companies in that space and we find that engineers from Tesla and Waymo are taking it today um the the inside was that two things one is existing universities will be very slow to move because the department lies and there's no department for self driving cars. So between mickey and doubly and computer science, getting these folks together into one room is really, really hard. Um and every professor listening, he ever know probably agree to that. And secondly, even if if all the great universities just did this which none so far has developed a curriculum in this field, it is just a few 1000 students they can partake because all the great universities are super selective. So how about people in India, how about people in china or in the Middle East or Indonesia or africa, why should those be excluded from the skill of building self driving cars? Are there any dumber than we are any less privileged? And the answer is we should just give everybody the skill to build a self driving car because if you do this then we have like 1000 self driving car startups and if 10% succeed it's like 100 that means 100 countries now we'll have self driving cars and be safer. </s>
<s>[INST] on, having lunch right? [/INST] I can tell you they are super smart. They don't seem to be so arrogant about their physics backgrounds that they think they can do things that nobody else can do. But the physics way of thinking I think will add will add great value to um we'll bring value to the machine learning. I believe it will and I think it already has </s><s>[INST] at what time scale do you think predicting the future becomes useless and your long experience and being surprised that new discoveries [/INST] Sometimes a day, sometimes 20 years. There are things which I thought we were very far from understanding which practically in a snap of the fingers or a blink of the eye suddenly uh became understood completely surprising to me. There are other things which I looked at and I said We're not going to understand these things for 500 years in particular quantum gravity. The scale for that was 20 years, 25 years And we understand a lot. We don't understand it completely now by any means but we I thought it was 500 years to make any progress. It turned out to be very, very far from that. It turned out to be more like 20 or 25 years from the time when I thought it was 500 years. </s><s>[INST] So if we make can we jump around quantum gravity some basic ideas in physics. Yeah. What is the dream of string theory? Mathematically. What is the hope? Where does it come from? What problem is it trying to solve? I [/INST] don't think the dream of string theory is any different than the dream of fundamental theoretical physics altogether. </s><s>[INST] Understanding unified theory of everything. [/INST] I I don't like thinking of string theory as a subject unto itself with people called string theorists who are the practitioners of this thing called string theory. I much prefer to think of them as theoretical physicists. Trying to answer deep fundamental questions about nature in particular gravity, in particular gravity and its connection with quantum mechanics. Um And who at the present time find string theory a useful tool rather than saying there's a subject called string theorist. I don't like being referred to as a string theorist </s><s>[INST] but as a tool. Is it useful to think about our nature in multiple dimensions? The strings vibrating. [/INST] I believe it is useful. I'll tell you what the main use of it has been up to now. Well it has had a number of main uses originally. String theory was invented and I know that I was there. I was right at the spot where it was being invented literally. And it was being invented to understand hydrophones, hydrophones of sub nuclear particles, protons, neutrons, mesons and Mhm. At that time, the late 60s, early 70's it was clear from experiment that these particles called Hadrian's had could vibrate, could rotate, could do all the things that a little closed string can do. And uh it was and is a valid and correct theory of these Hadrian's. It's been experimentally tested and that is a done deal. Mhm. It had a second life as a theory of gravity. The same basic mathematics except on a very very much smaller distance scale. The objects of gravitation are 19 orders of magnitude smaller than a proton. But the same mathematics turned up the same mathematics turned up What has been its value. Its value is that it's mathematically rigorous in many ways. And enabled us to find to find mathematical structures which have both quantum mechanics and gravity with rigor. We can test out ideas. We can test out ideas. We can test them in the laboratory that the 19 orders of magnitude too small or things that we're interested in. But we can test them out mathematically and analyze their internal consistency. Bye now, 40 years ago, 35 years ago and so forth. People very, very much questioned the consistency between gravity and quantum mechanics. Stephen Hawking was very famous for it rightly so now nobody questions that consistency anymore. They don't because we have mathematically precise string theories which contain both gravity and quantum mechanics in a consistent way. So it's provided that that certainty that quantum mechanics and gravity can coexist. That's not a small thing. That's a huge thing. It's a huge thing to be proud. Einstein could not be appalled. I don't know, he didn't like quantum mechanics very much, but he would certainly be struck by it. I think that maybe at this time its biggest contribution to physics in illustrating almost definitively that quantum mechanics and gravity are very closely related and not inconsistent with each other. </s><s>[INST] Is there a possibility of something deeper more profound that still is consistent with string theory but is deeper that is to be found? Well, [/INST] you could ask the same thing that quantum mechanics, Is there something Exactly? Yeah, I think string theory is just an example of a quantum mechanical system that contains both gravitation and uh and quantum mechanics. So is there something underlying quantum mechanics? </s><s>[INST] Perhaps something deterministic? Perhaps [/INST] something deterministic. My friend Faraday Tufte, whose name, you may know, he's a very famous physicist Dutch, not as famous as it should be, but but hard </s><s>[INST] to spell his name. [/INST] It's hard to say his name. You know, it's easy to spell his name. Apostrophe is the only person I know his name begins with an apostrophe and he's one of my heroes in physics. And he's a little younger than me. But it's nevertheless one of my heroes. The tuft believes that there is some sub structure to the world which is classical in character. The deterministic and character which somehow by some mechanism that he has a hard time spelling out, emerges as quantum mechanics. </s><s>[INST] I don't the way function is somehow emergent, [/INST] the wave function and not just the wave function, but the whole milk and the whole thing that goes with quantum mechanics, uncertainty, entanglement, all these things are emergent. </s>
<s>[INST] So I ever had some Wikipedia. Uh she was a master. There's apparently only one grand master. That's okay. [/INST] Anyway, is the phrase grandmaster ever uttered in the script? </s><s>[INST] I don't think so. I don't think so. But there's a story, [/INST] oh, there's, there's off, off script cannon. I'm gonna call Glen berger right now and find out if any of this is true. </s><s>[INST] All right, You're not supposed to call out my journalistic integrity. Um, but master Oogway Master Oogway, he says a couple of things I'd like to bring up with you. So one is part of a longer quote recommends that you should find a battle worth fighting. We've talked about several battles just now. What is the battle worth fighting for for eric Weinstein in the next few months in the next year [/INST] there's only one. Well, it's the moses, it's the moses thing. It's time to go. It's time to leave this place is over to get off the planet. Yeah, I freaked people out when I say that, but like look at your world, you just got introduced to the problem of the virus. Wait, wait till its fusion devices and you understand what it means to have one interconnected planet with no un correlated experiments happening anywhere else? You know? </s><s>[INST] So do you see the foray your work in physics and maybe like the echoes of it in ship. Ellen, [/INST] everybody who has a possible plan to avoid what is coming if we don't have one should work on the plan that he she thinks best. Right? So Ellen wants to do rockets people misinterpret me. I meta eric says I don't think that's a smart plan. Mhm. Regular eric says, Mhm. All people who have hope should do that thing. Yeah, at least it's mars man at least it's the moon and mars and maybe tighten and whatever and I don't think it will work and it doesn't make sense and it looks silly </s><s>[INST] but that's exactly the kind of fight. Worth fighting. But it's [/INST] The kind of fits for the same reason that I went on Brett's unity 2020 thing when I didn't think it had a hope in hell and people you know, are making fun of it. Like we got to do things that make that make us feel dumb and silly and childish, they possibly have a hope of working. Okay, so everybody should do something. My version of this I'm the most hopeful about because I wouldn't have chosen to do if I thought that daniel smoked in burgers wisdom project was a better hope I do that. It's more down to earth in a certain way. I just think that it's more probable. Look, we got from powered flight with the Wright Brothers and wind tunnels to sending back images from the surface of titan huygens cassini in less than a century. Okay, what we can do if we can change the laws of physics is something we can't even conceive of. It may be that it buys us nothing. And at least we'll, we will know why we died on this planet. </s><s>[INST] As a small aside, I think this is not the right time to take the full journey. But I feel like you will guide me like master wei did and I'm the kung fu panda. [/INST] It's something I only have one conversation. </s><s>[INST] We're on our way. We didn't [/INST] well, </s><s>[INST] we're jews and they weren't so we talked too much, but the guy doesn't have to be with words. Uh, you don't think po is jewish. It's debatable. We'll have to go back to the Wikipedia. [/INST] Yeah. </s><s>[INST] Is there, um, that you would guide me through some more intuition about the source called the source code of our universe. Can you comment on where since we last spoke, where you're thinking has been, has roamed around geometric unity around that work in physics. In this fight. I'm trying to figure out [/INST] when to release it and how I mean, I've released the video in the video quite honestly, I think it has a very bizarre reaction. I think one of the things that I've learned from the video because the video is coming up on half a million views on youtube alone to say nothing of the um, the audio. But yeah, it produced a very strange reaction. One of the things I don't think that I properly understood is that most physicists don't talk in this geometric language. I thought that more of the physics world probably had converted over into manifolds, bundles, differential forms, connections, curvature, tensors, et cetera. And I saw a lot of the comments would say things like I have a PhD in theoretical physics and I'm not even familiar with all of these concepts and I think that was probably a distortion coming from living in Cambridge massachusetts for almost 20 years. So what's the solution to that? Do you want to do it? I can make this make as much sense as anybody needs to. My problem is, you know, my calculation is that as long as the boomers are still in charge, the same people have these perverse incentives on them where they've invested in these programs that didn't work. So they're extremely hostile and kind of difficult to deal with. The fact that I'm not a physicist, um, has its own set of issues, which is that effectively, it's like the hermit kingdom. They don't get any visitors and they don't necessarily want somebody, you know, rolling up and saying, I know how to do physics. So I'm always very clear. I'm not a physicist. Um, that said, if I wait too long, I don't know that theoretical physics is really going to exist after the boomers because everyone in you, I think you had Wolfram on your program. I don't remember whether he said this to you or brian keating, but he said something like everybody got discouraged. It was too hard. We can't do that guys, we cannot do that. There's something about the renormalization revolution that innovated the physics community because it taught them just because you can see in this energy regime doesn't mean you can extrapolate somewhere else unless you understand how, you know, coupling constants run and what kind of UV fixed points exist, blah blah blah. Somehow that discouraged people from guessing from believing everything became an effective theory. The beauty of the effective theory wasn't taken to be really the beauty of the universe, just the beauty of an energy level. So, I think the renormalization was one of the most important revolutions that ever happened in science and also its interpretation by the physics community was catastrophic. Well, the story I'm telling myself is that in part I'm waiting for them to get weaker. But on the other hand, I don't know that we have any time left. And so are </s>
<s>[INST] Yeah, but distributed consensus that still has a sequential. There's like, don't tell me, you're thinking through like how to apply multi computation to? Uh [/INST] Yes. And so, so that becomes a story of, you know, instead of transactions all having to settle in one ledger, it's like a story of all these different ledgers and they all have to have some ultimate consistency, which is what causal variants would give one. But it can take a while and it can take awhile is kind of like quantum mechanics. So it's kind of what's happening is that these different paths of history that correspond to, you know, in one path of history, you got paid this amount in another part of history, you got paid this amount in the end, the universe will always become consistent. Now, another way it works is okay, it's a little bit more complicated than that. What happens is the way space is knitted together in our theory of physics is through all these events. And the the the idea is that the way that economic spaces knitted together is but is there these autonomous events that essentially knit together economic space? So they're all these threads of transactions that are happening? And the question is, can they be made consistent, are there is there something forcing them to be sort of a consistent fabric of, of economic reality? And sort of what this has led me to is trying to realize, how does economics fundamentally work. And you know, what is economics and uh you know what what are the atoms of economics, so to speak. And so what I've kind of realized is that that sort of the perhaps I don't even know if this is right yet. There's sort of events in economics, the transactions, there are states of agents that are kind of the atoms of economics and then transactions are kind of agents transact, transact in some way and that's an event. And then the question is, how do you knit together sort of economic space from that? What is there in economic space? Well, all these transactions, there's a whole complicated collection of possible transactions. But one thing that's true about economics is we tend to have the notion of a definite value for things. We could imagine that you know, you buy a cookie from somebody and they want to get a movie ticket. And there is some way that ai bots could make some path from the cookie to the movie ticket by all these different intermediate transactions. But in fact we have an approximation to that which is we say they each have a dollar value. And we have this kind of numerous rare concept of there's just a way of kind of of taking this whole complicated space of transactions and parsing it in something which is a kind of a simplified thing that is kind of like our parsing of physical space. And so my my guess is that the yet again, I mean it's crazy that all these things are so connected? This is another multi computation story. Another story of where what's happening is that the economic consciousness, the economic observer is not going to deal with all of those are different microscopic transactions, they're just going to pass the whole thing by saying there's this value, it's a number and that's that's their understanding of their summary of this economic network and there will be all kinds of things like there are all kinds of arbitrage opportunities which are kind of like the quantum effects in this whole thing. And that's you know, and places where there's where there's sort of different paths that can be followed and and so on. And there's so the question is, can one make a sort of global theory of economics? And then my test cases again, what is time dilation and economics? And I know for you know, if you if you imagine a very agricultural economics where people are growing lettuces and fields and things like this And you ask questions about, well, if you're transporting lettuces to different places, you know, what is the value of the lettuces after you have to transport them versus if you're just sitting in one place and selling them, you can kind of get a little bit of analogy there. But I think there's a there's a better and more complete analogy and that that's the question of, is there a theory like general activity that is a global theory of economics? And is it about something we care about? It could be that there is a global theory, but it's about a feature of economic reality that isn't important to us. Now, another part of the story is, can one use those ideas to make essentially a distributed Blockchain, a distributed generalization of Blockchain, kind of the quantum analog of money, so to speak, where you have, for example, you can have uncertainty relations where you're saying, you know, well, if I, if I insist on knowing my bank account right now, there'll be some uncertainty. If I'm prepared to wait a while, then it will be much more certain. Um, and so there's, you know, is there a way of using And so we, we've made a bunch of prototypes of this, um, which I'm not yet happy with. What I realized is to really understand these prototypes. I actually have to have a foundational theory of economics. And so that's kind of a, uh, you know, it may be that we could deploy one of these prototypes is a practical system, but I think it's really going to be much better if we actually have an understanding of how this plugs into kind of the economics, </s><s>[INST] that means like a fundamental theory of transactions between entities. Well, that's what you mean by economics? [/INST] Yes, I think so. But I mean, you know, how, how there emerged sort of laws of economics? I don't even know. And I've been asking friends of mine who are who are economists and things? What is economics? You know, is it an axiomatic theory? Is it a theory that is a kind of a qualitative description theory? Is that, you know, what kind of a theory is it? Is it a theory? What kind of thinking? It's like, like in in biology and evolutionary biology, for example, there's a certain there's a certain pattern of thinking that goes on in evolutionary biology where if you're a, you know, a good evolutionary biologist, somebody says that creature has a weird horn and they'll say, well, that's because this and this and this and this selection of this kind and that kind And that's the story. And it's not a mathematical story. It's a story of a different type of thinking about these things. By the way, evolution of biology is yet another place where it looks like this multi computational idea can be applied. And that's where where maybe speciation is related to things like event horizons and there's a whole whole other kind of world of that. But </s>
<s>[INST] world. So would you recommend it as a good whirlwind overview of the history of economics. [/INST] Yeah, I think that's exactly right, it kind of takes you through the different things. Um and you know, you can understand how they reached thinking some of the strengths and weaknesses. I mean probably is a little out of date now. It needs to be updated a bit. But you know, you could at least look through the first couple 100 years of economics, which is not a bad place to start more recently. I mean a book I really enjoy, it is by my friend and colleague max tag Mark called Life three point Oh, you should have on your podcast if you haven't already. </s><s>[INST] He was episode # one. [/INST] Oh my God, </s><s>[INST] he's back. He'll be back. He'll be back soon. [/INST] Yeah, no, he's terrific. I I love the way his brain works and he makes you think about profound things. He's got such a joyful approach to life. And uh so that's been a great book and you know, you learn, I learn a lot from it, I think everybody but he explains it in a way, even though you're so brilliant that you know, everyone can understand that. I can understand um you know, that's three, but let me mention maybe one or two others. I mean, I recently read more from less by my sometimes co author Andrew Mcafee. It made me optimistic about how we can continue to have rising living standards while living more lightly on the planet. In fact because of higher living standards, because of technology, because of digitization that I mentioned. Um we don't have to have this big an impact on the planet and that's a great story to tell. And he documents it very carefully. Uh you know, a personal kind of self help book that I'm not kind of useful people is is atomic habits. I think it's uh, what's his name? James? Clear. James clear. Um, he's just has a good name because he writes very clearly and you know, most of the sentences I read in that book, I was like, yeah, I know that. But it just really helps to have somebody like remind you and tell you and kind of just reinforce it and uh </s><s>[INST] build habits in your life that you, you hope to have uh, have a positive impact and don't have to make it big things. It could be just tiny [/INST] little Exactly. Atomic. It's a little bit of a pun. I think he says, you know, one atomic museum really small. You take these little things, but also like atomic power. It can have like, you know, big impact. </s><s>[INST] That's funny. Yeah. The biggest ridiculous question, especially to ask an economist, but also a human being. What's the meaning of [/INST] life? I hope you've got the answer that from somebody. I think we're all still working on that one. But um, what is it? You know, I actually learned a lot from my son Luke and he's 19 now, but he's always loved philosophy and he reads way more sophisticated philosophy than I do. I once took him to Oxford and he spent the whole time like pulling all these obscure books down and reading them. And a couple years ago we had this argument um and he was trying to convince me that Hedonism was the ultimate, you know, meaning of life, just pleasure seeking and how </s><s>[INST] old was he at the [/INST] Time, 17, but he made a really good like intellectual argument for it too. And you know, I just didn't strike me as right and I think that um you know, while I am kind of utilitarian, like, you know, I do think we should do the greatest good for the greatest number. That's just too shallow. And I think I've convinced myself that real happiness doesn't come from seeking pleasure. It's kind of a little bit ironic, like if you really focus on being happy, I think it doesn't work, you gotta be doing something bigger. It's I think the analogy sometimes use is, you know, when you look at a dim star in the sky, if you look right at it, it kind of disappears, but you have to look a little to the side and then the parts of your retina that are better at absorbing light, you can pick it up better, it's the same thing with happiness. I think you need to sort of find something other goal something some meaning in life and that ultimately makes you happier than if you go squarely at just pleasure. And so for me, you know, the kind of research I do that I think is trying to change the world, make the world a better place. And I'm not like an evolutionary psychologist, but my guess is that our brains are wired not just for pleasure, but we're social animals and we're wired to help others and ultimately, you know, that's something that's really deeply rooted in our psyche. And if we do help others, if we do or at least feel like we're helping others, you know, our reward systems kick in and we end up being more deeply satisfied than if we just do something selfish and shallow, </s><s>[INST] beautifully put. I don't think there's a better way to end eric, you're one of the people when I first showed up at M. I. T. That made me proud to be an M. It's so it's so sad that you're now at stanford. But as I'm sure you'll do wonderful things at stanford as well. I can't wait till future books and people should definitely read. [/INST] Well thank you so much and I think we're all we're all part of the Invisible College as we call it. You know, we're all part of this intellectual and human community where we all can learn from each other. It doesn't really matter physically where we are so much anymore. </s>
<s>[INST] This episode is brought to you by Element, spelled L-M-N-T. It's an electrolyte drink mix that I'm currently drinking that I drink throughout the day. I drink a huge amount of it. My favorite flavor is the watermelon salt flavor. It doesn't mean it will be your favorite flavor, but I'm pretty sure it's gonna be your favorite flavor. For fasting, for low carb diets, for all kinds of diets, really, but certainly for low carbohydrate keto carnivore, you have to get the electrolytes right. They call it the keto flu if you don't get the electrolytes right. You know for doing all kinds of crazy exercise that I do, all of that. You have to get the sodium, the potassium, magnesium, and element. Great job of balancing all of that. Makes it delicious. Makes it really easy to make sure [/INST] that you're getting just the water intake right. I enjoy this. </s><s>[INST] Element doesn't, because it basically makes water taste great and balances out the electrolytes, the hydration, everything for you. I bring it, when I travel, I bring it anywhere I go. I have to have element as part of my life. It makes me happy. It makes me feel like I got my stuff together. Anyway, get a simple pack for free with any purchase. Try it at drinkelement.com slash Lex. This show is also brought to you by NetSuite, an all-in-one cloud business management system. You can manage financials, HR, inventory, e-commerce if you do that kind of thing, and many business-related details. Running a company is really complicated. There's a lot of people involved, a lot of tasks involved, a lot of roles involved. It's not just engineering. It's not just design, idea, strategy, vision, all those kinds of things. It's all of the glue, the thing that makes the thing a cohesive, singular system that works efficiently and flawlessly. And so you have to hire the right people. You have to use the best tools for the job. NetSuite does that in the cloud to manage all kinds of messy business details and make it super easy. You can start now with no payment or interest for six months. Go to netsuite.com slash Lex to access their one-of-a-kind financing program. That's netsuite.com slash Lex. This episode is also brought to you by BetterHelp. It's spelled H-E-L-P, help. They figure out what you need and match you with a licensed professional therapist in under 48 hours. Talking to somebody through all the difficult things that are going through your mind, taking those thoughts, taking those memories, converting them into words and letting those words leave your mouth sounds somehow transforms your own understanding of what those memories, those thoughts mean. It allows you to move past them, to integrate them into a healthier, a deeper understanding of the world around you, your own emotions of your own way of being. It's kind of amazing that talk therapy, that talking, talking with a person that knows what they're doing is a powerful way to do that kind of growth. It's funny and it's amazing when simple things like therapy can have a big profound impact, results on your life. Anyway, one of the big things about BetterHelp is just how easy it is to get started. I think that's a barrier for a lot of people. So it's really important to say this, easy, discreet. It is affordable and it's available everywhere worldwide. Check them out at betterhelp.com slash Lex and save on your first month. That's betterhelp.com slash Lex. This is a Lex Friedman podcast to support it. Please check out our sponsors in the description. And now, dear friends, here's Neil Gershenfeld. You have spent your life working at the boundary between bits and atoms, so the digital and the physical. What have you learned about engineering and about nature reality from working at this divide, [/INST] trying to bridge this divide? I learned why von Neumann and Turing made fundamental mistakes. I learned the secret of life. Yeah. I learned how to solve many of the world's most important problems, which all sound presumptuous, </s><s>[INST] but all of those are things I learned at that boundary. Okay, so Turing and von Neumann, let's start there. Some of the most impactful, important humans [/INST] who have ever lived in computing, why were they wrong? Were they wrong? So I worked with Andy Gleason, who is Turing's counterpart. So just for background, if anybody doesn't know, Turing is credited with the modern architecture of computing, among many other things. Andy Gleason was his US counterpart. And you might not have heard of Andy Gleason, but you might have heard of the Hilbert problems. And Andy Gleason solved the fifth one. So he was a really notable mathematician. During the war, he was Turing's counterpart. Then von Neumann is credited with the modern architecture of computing, and one of his students was Marvin Minsky. So I could ask Marvin what Johnny was thinking, and I could ask Andy what Alan was thinking. And what came out from that, what I came to appreciate as background, I never understood the difference between computer science and physical science, but Turing's machine that's the foundation of modern computing has a simple physics mistake, which is the head is distinct from the tape. So in the Turing machine, there's a head that programmatically moves and reads and writes the tape. The head is distinct from the tape, which means persistence of information is separate from interaction with information. Then von Neumann wrote deeply and beautifully about many things but not computing. He wrote a horrible memo called the first draft of a report on the EdVAC, which is how you program a very early computer. In it, he essentially roughly took Turing's architecture and built it into a machine. So the legacy of that is the computer somebody's using to watch this is spending much of its effort moving information from storage transistors to processing transistors, even though they have the same computational complexity. So in computer science, when you learn about computing, there's a ridiculous taxonomy of about a hundred different models of computation, but they're all fictions. In physics, a patch of space occupies space, it stores state, it takes time to transit, and you can interact. That is the only model of computation that's physical. Everything else is a fiction. So I really came to appreciate that a few years back when I did a keynote for the annual meeting of the supercomputer industry and then went into the halls and spent time with the supercomputer builders and came to appreciate, oh, let's see, if you're familiar with the movie, The Metropolis, people would frolic upstairs in the gardens and down in the basement, people would move levers. And that's how computing exists today, that we pretend software is not physical, it's separate from hardware, and the whole canon of computer science is based on this fiction that bits aren't constrained by atoms, but all sorts of scaling issues in computing come from that boundary, but all sorts of opportunities come from that boundary. And so you can trace it all the way back to Turing's machine making this mistake between the head and the tape. Van Neumann, he never called it Van Neumann's architecture, he wrote about it in this dreadful memo, and then he wrote beautifully about other things we'll talk about. Now, to end a long answer, Turing and Van Neumann both knew this. So all of the canon of computer scientists credits them for what was never meant to be a computer architecture. Both Turing and Van Neumann ended their life studying exactly how software becomes hardware. So Van Neumann studied self-reproducing automata, how a machine communicates its own construction. Turing studied morphogenesis, how genes give rise to form. They ended their life studying the embodiment of computation, something that's been forgotten by the canon of computing, but developed sort of off to the sides </s>
<s>[INST] So, given that slavery in America as part as part of its history, how do we incorporate into the calculus of um policy today, social discourse, what we learned in school, we can look at slavery in America, we can look at maybe more recent things like uh in europe, the other atrocities, the holocaust? How do we incorporate that in terms of how we create policy, how we treat each other, all those kinds of things. Um what is the calculus of integrating the atrocities, the injustices of the past into the way we are today, [/INST] that's a very complex question, because it's a it's a moral question at this point, and a moral question long after the fact. Um I say at one point in the war in the west, that the argument for instance, on reparations. Now that goes on and it's not a, not a fringe argument anymore. Some people say, oh, you're pulling up this fringe argument. It really isn't. I mean every contender for the Democratic nomination for the presidency in 2020 was willing to talk about possibility of reparations. Some very eager that this country America goes through that entirely self destructive exercise. Um, I say that there's a lot of problems with this. But if I can find it out of one thing, I'd say this, it's no longer about a wealth transfer from one group of people who did something wrong to another group of people who were wrong. It would have been, it would have been, that could have been that 200 years ago today. It's not even the descendants of people who did something wrong giving money to people who were the descendants of people who were wronged. It's the wealth transfer from people who look like people who did a wrong thing in the past to another group of people who resemble people who were wrong. That's impossible to do. I'm completely clear about this. There is no way in which you could organize such a a wealth transfer. Our moral or practical reasons America is filled with people who are have the same skin color as asked, for instance, who have no connection to the slave trade and should not be made to pay money to people who have some connection. And then the country is also filled with ethnic minorities who have come after slavery, who would not be due for any reimbursement as it were. The problem. The problem with this is though, is that there are, I'm perfectly open to the possibility that there are um residual inequities that exist in american life. And that's and that the consequences of slavery could be one of the factors that resulted from this. The thing is, I don't think it's a I don't think it's a single issue answer. I think it's a multidimensional issue, something like black underachievement in America. It is obviously a multidimensional issue much of the left and others wish to say it's not, it's only about racism and they can't answer why asians who've arrived more recently, don't, for instance, get held down by white supremacy. But actually I say white supremacy and quotes obviously, but don't get held back by it, but actually flourish to the extent that asian americans have higher household earnings and higher house household mean, uh equity than home equity and so on than than white americans. Uh, so I don't think that on the merits the evidence is there that, you know, racism is the explanation for black ongoing black underachievement in some segments of the black community in America. Um it's obviously a part of it, could you say that even those things like fatherlessness and um similar family breakdown issues, our long term consequence of it possibly, but it's it's being awfully generous to people's ability to make bad decisions. For instance, how many generations after the holocaust would you allow people to claim that everything that went wrong in the jewish community was as a result of the holocaust? I mean, is there is there some kind of term limit on this? I would have thought so, and I think most people probably think that's over. I </s><s>[INST] think the details matter there and um but it's very different. [/INST] Yeah, </s><s>[INST] I enjoy swimming out in the ocean, so although I'm terrified of what's lurking underneath in the darkness. Um okay, it's really complicated calculus with the holocaust and slavery. So the argument in America is that there there's deep institutional racism against african americans that's rooted in slavery. And so however, that calculus turns out that calculation, it still persists in the culture and the institutions in the allocation of resources in the way that we communicate in in subtle ways and major ways, all that kind of stuff. Um how is it possible to win or lose that argument of how much institutional racism there? Is that's rooted in in slavery. Is it a winnable? [/INST] It's an unquantifiable argument and I I'd like to apply some shortcuts to some of this and the following, Yes, are for instance all um let's take the the the one that's most often often cited if if a white person is walking down a street in America and they see a group of young black men coming towards them and it's late at night and they cross the road. Is it because of slavery? Is it because of institutional racism? No, it's because they've made a calculus based not entirely on unfounded beliefs that given crime rates, it's possible that this group of people might be a group of people they don't want to meet late at night. That's an ugly fact. But as crime statistics in american cities after american cities bear out, Um, it's not an entirely unreasonable one. It's not reasonable every time obviously, obviously, but is it attributable to slavery? That's a stretch. If you're in a city like Chicago where the homicide rates shot up in the last two years, albeit again as, as always has to be remembered mainly black on black gun violence and knife violence. Nevertheless, if you're in a city like Chicago and you make that calculus, I just suggested the cliche and one that the street late at night, there are other factors other than a memory of slavery, the kick in and I'm afraid it's, it's something which people don't want to particularly acknowledge in America for obvious reasons because it's the ugliest damn debate in the world. But I was actually just writing in my column in new york post today about a, a very interesting case is sort of similar, which is the question of obesity in the US. As you know, America's the most overweight country in the world. America has. I think 40% of the population is obese In medical ways. And the nearest next country is a long way down. That's New Zealand at 30% of the population. So America is a long way ahead. Why? During the coronavirus era, when we know that obesity is the one clearest factor that's likely to lead to your hospitalization. If you also get the virus, why did almost no public health information. America focus on obesity. 80% of the people who ended up hospitalized in America with coronavirus were obese. We locked the schools when there was no evidence that the coronavirus was deadly for Children. We all wore cloth masks. When there was very little evidence that this was much use in stopping the spread of the virus. We had massive evidence about obesity being a problem and we never addressed it. Why is it just because we're worried about fat people? No, it's actually because about fat shaming as well. No, it's also because it's a great extent. It's a racial issue in America as well. And actually, I quoted this new publication from the university University of Chicago as it happens, which makes that claim explicit, says the reasons why people are have views that are negative about obesity is because of racism and slavery. This is what everything is drawn back to. America. Anything you want to stop. You say it's because of racism, it's because of slavery. How about it's actually because new mind the hospital is getting clogged up. You mind people dying, You mind ethnic minorities, disproportionately dying and you'd like to say something about it once again. As in everything in America, it's cut off by some poorly educated academic saying it's about slavery. So we're really not. I mean this requires a kind of form of brain surgery to perform it on a society. Probably one that's not possible without killing the patient and it's being done by people who wearing like mittens. </s>
<s>[INST] Yeah. So the yeah, we humans aren't able to answer the why either. Yeah, but I do think the question here is, well, first of all, language is finite, certainly weren't expressed to a tweet. Uh so it is also combinatorial problem. The question is how much more difficult it is than chess. And I think I think all the same ways that we see the solutions to chest is deeply surprising when it was first addressed with I B M. D. Blue and then with alpha go and Alphago zero, alpha zero. I think in that same way language can be addressed and communication can be addressed. I don't see having done this podcast many reasons why everything I'm doing, especially as a digital being on the internet can't be done by an Ai system eventually. So like I think we're being very human centric and thinking were special. I think one of the hardest things is the physical space actually operating like touch and the magic of body language and the music of all of that because it's so deeply integrated through the long evolutionary process of what it's like to be on earth, what is fundamentally different and ai has you can catch up on is the way we apply our evolutionary history on the way we act on the internet and the way we act online and as more and more of the world becomes digital, you're not operating in a space where A. I. Is behind much less. So Like we're both starting at zero. [/INST] I think that's super interesting. Do you do you know this, do you know this author brian christian, is that someone you've ever heard of? He's a guy who competed in the, what is it called? The lobster competition. Yeah, the during testing. So, and I'll just tell you this story. But I think it's directly related to the last thing you said about where we're starting in the same place. Uh he competed in this in this competition. But not he didn't enter a program that was supposed to try to pass the turing test. The turing test. You know, there's three people, there's the judge, there's the program and then there's there's a someone who's a human the way they do it. And the judge has got to figure out what by asking questions, which is the computer in which is the human so little known fact, there's two prizes in that competition. There's the most human computer prize that's the computer that wins the most and then there's the most human human rise and he competed for the most human human progress and he wanted. He kept one winning it. And and so he tried to think about what it is that um, you have to be able to do in order to convince judges that you're human instead of a computer. And that's an interesting question, I think. Um, and when he came to my take away from his version of this story, is that it is true that computers are winning these contests more and more, you know, as technology progresses. But there's two possible explanations for that. One is that the computers are becoming more human and the other is that the humans are becoming more like computers. And he says, actually, the more we live our lives in this world where in this sort of technological world where we have to moderate our behavior so that it's readable. Bye. Something that's effectively, you know, a computer, the more we become like that. And he says, it happens even when you're uh not interacting with a computer. He says, have you ever been to the, you know, on the phone with the call, you know, center? And they're going through their script and that's what they've got to do. They've got to go through their script because that's how they keep their job. And they ask you this question, you've got to answer it. And and it's as if you're no longer interacting with a person, even though it's a person because they've so given up everything that's involved normally with being able to make judgments and decisions and act in situations and take responsibility. And so I think that's that's the other side of it, it is true that technology is amazing and can solve huge ranges of problems and and do fantastic things. Was also true that we're changing ourselves in response to it. And the one thing I'm worried about is that we're changing ourselves in such a way that the norms for what we're aiming at are being changed to move in the direction of this sort of efficiently and in an optimized way, solving a problem and move away from this other kind of thing that we were calling alive, Alive Nous or significance. And and so that's the that's the other side of the story. </s><s>[INST] And that's the worry. But it's very possible that there is uh for you and I, the ancient dinosaurs, we may not see the liveliness in tick tock the Alive nous in the digital space that you see it as us being dragged into this over optimized world, but that may be uh this is in fact, it is a world that opens up opportunities to truly experience life. And there's interesting to think about all the people growing up now who their early experience of life is always mediated through a digital device. Not always, but more and more often mediated through that device and how we're both evolving. The technology is evolving. The humans are evolving to them. Maybe open a door to the whole world where the humans and the technology or ai systems are interacting as equals. [/INST] So now I'm going to agree with you, you might be surprised that I'm going to agree with you, but I think that's exactly right. I I don't want to be the person who's saying our job is to resist all of this stuff that I don't want to be a Luddite. That's not my goal. The goal is to point out that in the supreme danger lies the saving power. The point is to get in the right relation to that understanding of what we are uh that allows us to find the joy in it. And that's I think that's a hard thing to do. It's hard to understand even what we're supposed to be doing when we do it. Maybe I more than you and I'm not of the right generation to be able to do that. But I do think that's got to be the move. The move is not to resist it. It's not a nostalgic move. It's an attempt to push people to get in the relation to it. That's not the relation of it controlling you and depriving you of stuff. But if you're recognizing some great joy that can be found in it </s>
<s>[INST] As always, no ads in the middle. I try to make this interesting, but if you must skip them, please still check out our sponsors. I enjoy their stuff. Maybe you will too. This episode is brought to you by Asleep and its new Pod3 mattress. The very device, the technological smart portal into a dimension that I take every single day for many hours once and for a few minutes once or twice a day, also known as NAPs. Wherever the place that that portal takes me, this is a wonderful place. All I know, very importantly, is when I return, I return a new human being. [/INST] Whatever happens to me in the middle, </s><s>[INST] all I know are the creatures that dwell in that alternate dimension. Whatever they do to me, they reset the CPU and the memory and whatever is required. They defrag the hard drive enough to where I wake up refreshed and ready to take on the rest of the day. NAPs are just magic. Big believer, big lover of NAPs. If there's a hack to the simulation that we're all existing in, NAPs are it. Anyway, check out this magical portal into the alternate dimension and get special savings when you go to eighthsleep.com slash Lex. This episode is also brought to you by Linode, now called Akamai, and they're incredible Linux virtual machines. I've said this many times, but Linux is my favorite operating system, all of the flavors. Some people talk about their favorite flavors of ice cream. I talk about my favorite flavors of Linux, both the ice cream and the Linux that have evolved over the years. There was a time when I used to love coconut ice cream, and there was a time when I would use Gentoo, but that time is long gone. I've grown up a little bit, still young in heart, but practical enough to be using a Bantu. And my favorite flavor of Bantu is mate. Anyway, all of that doesn't matter. The point is Linux is Linux, and you can use Linux in the cloud in a way that's super easy for small personal projects and for huge systems, great customer support, lower cost than AWS. I love Linode, now called Akamai. I need to get used to saying I love Akamai. I rose by any other name will smell as sweet. Shakespeare has some wisdom on that one. Anyway, check out this beautiful, sweet-smelling rose that is Akamai at akamai.com slash Lex, or linode.com slash Lex for a free credit. This show is also brought to you by Insight Tracker, a service I use to track data that comes from my own body, and that data, when run through machine learning algorithms, is able to give me advice on what to do with my life. Well, some basic sort of lifestyle gone, and diet decisions. Unfortunately, you can't tell me what I should do in terms of career or relationships or how to navigate all the different and the beautiful complexities of life. I think using data that comes from your own body to make decisions about your life, health decisions, medical decisions, career decisions, all that kind of stuff, obviously when you look at the power of large language models, it's clear that when paired with great data, large neural networks can help do incredible predictive work. This is the future, but it starts with getting data from your body and starts by taking action based on that data. And so Insight Tracker is a pioneer that I support in this effort that I think will define a great quality of life in the 21st century. So you should check them out and get special savings at a limited time when you go to insighttracker.com slash Lex. This is a Lex Friedman podcast to support it. Please check out our sponsors in the description. And now, dear friends, here's Randall Kennedy. You wrote a book whose title is the N word spelled out with a hard R at the end. So let's start with the history of this word. [/INST] What is the history of this tree of the N word? The word you're referring to is nigger. The book that you're referring to is nigger, the strange career of a troublesome word. The word dates back to the 16th, 17th century. It's got a long lineage in other words. Basically Latin, basically Spanish, basically NIG, you know, black in various formulations. We don't know actually how the term nigger became a slur. So there were words that were close to NIGGER that were used in various ways. For instance, NIGG, UH has been, was used. NIGG, U-R is used. And sometimes it was used in a way that seemed to be just purely descriptive. We do know that by the early 19th century, it had become a slur. It had become a derogatory word about which people complained. </s><s>[INST] But exactly how that came about, not altogether clear. So it's been 20 years since you've written the book. What have you, what wisdom have you gained about this word since writing the book? And maybe having to interact with people, having to read, having to see, [/INST] having to feel the response to the book. This book has generated a lot of controversy. I thought it would, it's probably generated more controversy than I had anticipated. It has certainly generated more, more different sorts of experiences than I had anticipated. So for instance, I did not think that writing this book would prompt people to ask me to be an expert witness in cases. And over the past 20 years, I've been an expert witness in a number of different cases. I've been an expert witness in case, in a murder case, in various cases of assault. I've been an expert witness in cases involving tort cases, intentional infliction of emotional distress. I've been an expert witness in a number of employment cases. I had not anticipated that, nor had I anticipated the extent to which people would get in trouble for using my book. Every year, there are teachers who are suspended or who are fired because they will excerpt a chapter of my book. Let's imagine, and this is not, I'm not imagining things as has happened. A teacher is teaching, for instance, the Mark Twain's Huckleberry Finn. The word nigger appears in that book over 200 times. The teacher, trying to be earnest, trying to be sensible, trying to be serious, will excerpt a part of my book to acquaint students with the history of the word and maybe the history of controversy involving the use of the word in this particular novel. The teacher will give it out, hand it out to the teachers, hand it out to students, and there have been a number of teachers who've been suspended or worse because of that. Students will get upset, go home, tell their parents. Their parents will storm to the school and say that this is terrible. The teacher is, quote, using the word nigger in an offensive way, and oftentimes, administrators will basically abandon the teacher. And whenever this comes to my attention, I write, I'll write the superintendent of schools or I'll write the principal, or sometimes I'll write an opinion editorial piece for the local newspaper. But every year, there are teachers who are disciplined for using my book. </s><s>[INST] I had not anticipated that. And what is the nature of the letter or the op-ed that you write on why they shouldn't be disciplined [/INST] or if they, to the degree they should be or shouldn't be? There's not been one case, there's not been one case that has come to my attention in which it was even remotely sensible for the teacher to be disciplined. And what I say is that, number one, frankly, I go through, what I write is almost a synopsis of my book. Number one, this is an important word in American history. It is a word that is explosive, that's why people get so upset. It's a word that's volatile, it's a word that has typically been used in a terrible way. It's a word that is part of the soundtrack of racial terrorism in the United States. So people ought to know about this word. I mean, if you're interested in knowing the real history of the United States, if you're interested in knowing about lynching, if you're interested in knowing about the way in which black people have been terrorized in the United States, you need to know this word. You need to know that history. So you need to know why it is that people are upset about the word. But it doesn't end there. You have to know that. And if you know that, then that knowledge should equip you to be careful. It should equip you to know that, to know the range of context in which this word appears. But again, it doesn't just end there because especially young people, you tell that to young people, they nod, they read, they understand that. But then what? But then they turn on their radios and they turn on, they listen to Spotify. They listen to some of their favorite entertainers. They listen to Dr. Dre. They listen to the ghetto boys. They listen to Snoop. And they listen to NWA. What are they here? They listen to standup comedians. They listen to Dave Chappelle. They listen to Cat Williams. What do they hear? They hear the word nigger or nigga being used in a lot of different ways. And so they need to know about that as well. What are people doing? How does one explain the fact that Dick Gregory, Dick Gregory was a comedian, activist, friend of Martin Luther King Jr., a true activist? I mean, he had a flourishing career as an entertainer that he abandons in order to struggle for racial justice throughout the United States and including the Deep South. How does one explain the fact that he wrote several memoirs but his first memoir is called Nigger, a memoir. How does one explain that? How does one explain the way in which, how does one explain Richard Pryor? I mean Richard Pryor's best album is that niggers crazy. Well, was Richard Pryor trying to put down Black people? How does one explain that? One can only explain that by getting deeper into the word, by understanding that, yes, this is a word that has been used in a derogatory way. This is a word that has been used to put people down. This is a word that has been used to terrorize people. You gotta know that, but you also have to know that this is a word that has also been put to other uses. There are artists, there are entertainers who have used this word, like Dick Gregory used it, to put up a mirror to American society and say, look at this word and look at the terrible way in which it's been used. We don't want you to look away. No, don't look away. No euphemism, no asterisk, no n-word, no nigger. Now we want you to look at that and we wanna talk about that. James Baldwin, there was a documentary about James Baldwin a couple of years ago, highly lauded documentary. The title that was given in this documentary was, I Am Not Your Negro. That's not what James Baldwin said. Anybody can go to YouTube right now, take a look. James Baldwin said, I am not your nigger. And then he went on to talk about that. Well, James Baldwin wasn't, again, he wasn't starting to cover up anything. He wanted people to face the facts of American life. And it seems to me that if you're a teacher and you want to have your students face the facts about American life, well, you've got to grapple with the word nigger. Now, let me just quickly say, teachers have a tough job. And if we're talking about students, of course, there's a wide range of students. Am I saying that one ought to give my book to kindergartners? No, kindergartners are probably not ready for such a book. Third graders, probably no, not third grade. If we're talking however, about people in the 10th grade, do I think the 10th graders can read my book? Yeah, sure, absolutely. 11th graders, 12th graders, people in college, there are people in college, there are people in college, there are people in law schools. Teachers in law schools have been disciplined for, because the word nigger has come out of a teacher's mouth. Why? A couple of cases recently, a teacher would be reading a court opinion. The word appears in the court opinion, the teacher pronounces the word, students get up, leave in a huff, report the teacher. There's some instances in which teachers have been under those circumstances, have been disciplined. In my view, that's bad. And people ought to say it's bad. It's bad pedagogically. And frankly, in many of these instances, it's not only bad, it's stupid. And I don't mind saying that. I think that some of these instances in which teachers have been disciplined, absolutely stupid. People say, well, the teacher used the word, excuse me, used the word. It'd be one thing, it'd be one thing if a teacher looked at a student and called the student nigger. Get out of here, nigger. That'd be one, that'd be, you know, fine. Discipline, that's teacher, that's bad, but that's not what's going on. You don't have, none of these are cases in which you have an individual who is a stranger to another individual and this word just sort of comes out, no. What we have here is a class involving a person who is a teacher interacting with students, talking about subjects in which it would be perfectly understandable why this word would emerge as a subject of conversation. Now, under those circumstances, it's somehow wrong for a teacher to utter this word. In my view, the answer is no. And, you know, I said that 20 years ago, </s><s>[INST] I say it even more emphatically now. Still, it is one of the most powerful words in the English language. And there's a kind of responsibility that we as humans should have with words, with statements. That word, if not used skillfully, if not used competently, even when just read from a legal transcript, [/INST] can do more harm than good. Yeah, I agree with what you say. Yes, words are powerful. Words do matter. And so I am certainly not suggesting that people be lax. I'm not suggesting that people be irresponsible. It's precisely because words matter, however, that we need to be willing to face words and grapple with words and talk about words and talk about the history of words, precisely because words matter. And among other things, it seems to me, it's important to understand that words can mean different things in different contexts. It's not the case that a word means the same thing in every context, the word discriminating. Sometimes it's a very bad thing. That person discriminates. And when, again, intonation of voice means something. If I say that person discriminates, and I'm obviously being disapproving, implicitly what I'm saying is that person distinguishes between things on an unjustifiable basis. And that's a bad thing. On the other hand, that person has discriminating taste. Oh, that means something very different. That means that the person differentiates in a way that shows that they understand the difference between excellent, good, and not so good. And we think that that's a good thing. So words can mean different things in different contexts. It seems to me that that's something that actually we ought to recognize and talk about. </s><s>[INST] Well, some words enter this territory of being a slur. And it seems like when they cross the line into being a slur, there's the number of contexts in which it's okay to mention it exponentially decreases. Right? [/INST] Uh, no, no, I'm gonna resist that a little bit because the whole idea of slurs, slurs change. Yankee was a slur. Yankee was a slur in 18th century United States. Slur today, New York Yankees, I'm a Yankee fan. I'm a Yankee, Queer, queer, and this is in my lifetime. There was a time you queer and people would really run away from it and that was a bad thing. And then, thank goodness, I'm a queer fan. Goodness, gay liberation movement, gay liberation movement, basically, we're not gonna run away from this. We're gonna grab this quote slur and we're going to affix it to ourselves. And we are going to repurpose it. Now, the word queer is again, you know, can it be a slur? Yeah, it can be a slur, doesn't have to be. And it seems to me that it's important for people to know about how a word, a symbol, in some context can be a slur, in some context, doesn't have to be. So the whole idea of what's a slur, </s><s>[INST] that's a complicated idea in and of itself. It's very complicated. It's, if I may say, almost fascinating how language evolves. But if we were to kind of have a minute by minute evaluation of the most powerful, intensely slur-like words in the world, I think the N word with a hard R at the end, which is the title of your book, [/INST] is number one on that list. Well, I probably so. And of course, that's one of the reasons </s><s>[INST] why I wrote a little book about it. Yeah, but it hasn't, even since you wrote a little book about it, it seems like it's maintained its number one status. You mentioned queer. Mm-hmm. Maybe queer was in the top 20, I don't know, for a while, and now it's sliding into the top 1,000, [/INST] and the N word is at the top. You're absolutely right. The origins of this book, I clearly remember, I was at my office and I was thinking about lecture topics. And I get invited to give lectures from time to time. And I was thinking, well, what might make for an interesting lecture? And all of a sudden, the word nigger popped into my mind. Now, this is a word, I've grown up with this word. I mean, there's never been a time in my life when, at least in my conscious life, in which this word's been absent. I mean, in my household, for instance, in my household, my parents are black people, my parents were refugees from the Jim Crow South. I was born in the Deep South, South Carolina. In my household, I heard the word nigger used in every possible way. I heard it used as a slur. I also heard it used with respect to people who were praised, you know? My father, I clearly remember my father, whom I revere. That's the smartest nigga in the world. That's the bravest nigga in the world. That's the baddest nigga I know. He wasn't putting people down. This is the way he talked. And I grew up hearing this word in various ways. And so I was thinking to myself, God, where did this word come from? And one of the first things I did, I clearly remember just jumping up out of my seat, running up to the library, Oxford English Dictionary. When did this word first appear in English? Was the history of the word. And then what really sort of grabbed my attention is I went, I get my computer going, and I asked the computer system, give me every case, every federal court case in which this word appears, thousands of cases. And then I said, oh my goodness, this is really, and you know, this is really interesting. And then I started just cataloging all the different cases. There came a point, I'd say probably about a month into this, I compared the usage, I compared the number of times a nigger came up with other sorts of slurs. So for instance, kike, K-I-K-E, long time, derogatory word for Jews. How many times has this word come up? There was a time in which the word appeared, but nothing like the infamous N word, nothing. What about wetback? What about, and then I just, let me just take a look at all the other slurs. Nothing came close, not even remotely close to nigger. And I think it has something to do with, I think it has something to do with the uniqueness of the color line, particularly as it pertains to African Americans. I think that the fact that nigger sort of occupies such a unique status among slurs, I think that's a reflection of the unique stigma </s><s>[INST] that has been imposed on African Americans. It's hard to know the chicken or the egg, why one word is able to so distinctly and clearly encapsulate this struggle between races that is throughout American history. I mean, they didn't have to probably be so, [/INST] but it came to be that way. It became that, not only that, not only that, but of course the nigger spurred other slurs. So Arabs, sand niggers, the Irish, the niggers of Europe, </s><s>[INST] women, the niggers of the world. [/INST] John Lennon even has a song. That's right. Well, I think Yoko Ono I think had something to do with that song. So, I mean, it is a slur that has spawned other slurs. And again, that's why, as you indicated a moment ago, </s><s>[INST] this is a quite unique term. But are you conscious? Are you deliberate in you saying this word? So let me just say from a personal experience, maybe my upbringing, where I came from, in my daily life, I don't think I've ever heard that word with a hard R said as often used clearly in my life, said that I've heard it today more than I have ever heard in my entire life. And I think there's a few people who listen to this, they'll be listening to this and be very uncomfortable. I would say not in a bad way, probably in a good way. I'm uncomfortable now, and I am almost introspecting and trying to figure out why I'm uncomfortable. And I think even the title of your book is making me think that, just looking into my own mind and trying to understand, wow, words of power. And why does it have so much power? But are you deliberate in that action? And by the way, not only are the people listening to this sweating, this will be on YouTube in part. And YouTube, the people on the other side [/INST] will be sweating, what do we do with this? Yeah, well, am I deliberate? The answer is yes. And let me unpack that a little bit. First, that's right, I mean, am I deliberate? Yeah, I deliberately wrote a book called, Nigger, The Strange Career of a Troublesome Word. And was that deliberate? </s><s>[INST] Yeah, that was quite deliberate. [/INST] But the title could have been N word, versus spell. The title could have been N word, sure. The title could have been... The title could have been a book about a word that causes pain to many people. I could have named it that. There are many titles, I could have used. Did I want a title that would be provocative? Did I want a title that would grab people? The answer to that is, yes. I'm a writer, I want people to read what I write. Was I being sensationalistic? Well, I mean, if you wanna put it like that, yes. I don't, I'm not embarrassed to say that. I mean, I'm sure that when people write books, they think really hard about their titles and they try to get a title that will grab people's attention. I know people, respect people very deeply who never, it's a matter of principle, never utter this word. And I've talked with people, I've had people say, I read your book, let's talk about it, but let's be very clear, I'm not gonna use the word. I've had many conversations with people who've asked me not to use the word. I was on a, the first time this came up was a book tour. It was 20 years ago when the book first came out and I was on one of these call-in shows early in the morning. Time came to call in, seven o'clock, I call in at five or seven. Right before I go on, the host of the show says, oh, by the way, we have a strict policy here at the station. We never use this word. And I said, well, gosh, I wish you had told me this earlier. Does this mean then that you're never going to pronounce fully the title of my book? And she said, that's right. And I had to make up choice right then and there. Am I gonna go on or am I not? What'd you do? I went on and I abided by the station's rules and you know, fine, we had a perfectly fine conversation. And you know, there is a place for euphemism. The American language is a very supple language. There are lots of words that one can use. I do not get angry with people who don't, you know, they say as a matter of principle, they're not gonna use the word fine. I'm willing to, I understand where they're coming from </s><s>[INST] and often I will defer to their wishes. [/INST] What'd you do? All I say is I want people to understand where I'm coming from. I'm not just using this word willy-nilly. There's a pedagogical reason. There is a reason for why I'm saying what I'm saying. </s><s>[INST] There is a reason why I use the word. Can you make the case why using the word is a good idea? And can you make, can you steal man the case why it's a bad idea? Maybe you've heard from some critics. Yes. Who said that you saying this word out loud is actually causing a lot of harm. Not like harm because people's feelings are hurt but increasing the amount of racism and hate in the world. [/INST] Yeah. Critics. Let's start with the critics. One, again, going back to when the book was first published, I remember going to the first bookstore I went to and I talked about the book, had a very, you know, talked, asked questions. And the last comment wasn't a question but the last comment was made by an elderly black man. I called on him and he said, I've listened to what you've had to say and I appreciate what you've had to say. But he, he said, but I remain unconvinced and I remain unconvinced because when I was coming up, this word was used to put me in the back of the bus. And this word was used to prevent me from voting. And this was the word that was used to justify me never being called as a juror. So to me, this word has only one meaning. It's a terrible meaning. I'm never going to use the word. It hurts me when I hear people use the word, especially those who don't know anything about the, really about the history of it. And he went on to say, I think that your book though well-intended he's probably going to be seen by some people as giving them permission to use the word. And then he stopped. And I thought there was a lot of power behind that gentleman's comment. I think that what he said is probably correct. And so far as there are probably some people who read the book, there probably some people who are listening to our conversation right now who will think that I'm giving people permission to use the word. You know, I have said that I'm not, I want people to understand the word, I think that there is a burden that comes from whenever you utter a word like this, but that's, you know, that that's a critique and I think there's strength to that critique. I'm not gonna say that that's a ridiculous critique. I think that there is something to that. And by the way, I should say, and that's why I would say to anyone, that's right, if this word comes out of your mouth, you are taking on real responsibility. So for years, it doesn't happen so much now, but they were, I'd say for about the first five years after this book was published, I would get an email at least once a week and it would begin like this, you know, dear professor Kennedy, I read your book and I'm calling to ask you a question. And as soon as I saw that, I knew what the question was gonna be and then what the person would say is the following, I like rap. And then I knew it was coming, I like rap. I'm white and I have black friends and we listened to rap and we're driving in the car and we're listening to the song, we start humming along and singing along and my black friends sing along and when nigger or nigga comes up, they sing and I don't know what to do. Is it wrong for me to sing along? This happened so often that I'd say about the 10th time I got in such an email, I wrote a form letter because I didn't wanna just, you know, take up time writing, you know, sort of crafting letter after letter after letter. So I wrote a form letter and basically what I said was listen, number one, I'm flattered that you're asking me but number one, you should have a conversation with your friend, number two, no matter what your friend says let me put something else for you to consider. Let's suppose for the sake of discussion that your friend says, oh, doesn't bother me, I know where you're coming from, we're just enjoying the music, I don't think that this is a you know, a racist utterance, you know, coming out of your mouth. Let's suppose that your friend says that, that doesn't end matters because let's imagine the following, let's imagine that you're in a theater and you're waiting for the, you know, a film to start and you're just, you know, talking with your friends are singing with your friends or just, you know, kicking back with your friends and they're talking about nigger this or, nigger this and you say it, you the white boys say it and the next thing you feel is a fist, a big fist in your mouth that has been launched by a person that you did not see who was right behind you. All this person saw was a white person saying nigger and the next thing, that's not, you know, some sort of overheated scenario coming from some law professor's mind. That is a very plausible scenario. So you have to be worried about lots of things, including mistake. So my advice to you is be prudent. I would stay clear of the word unless, unless you're very certain and unless if you're called on it, you feel you're in a position to defend yourself, defend what you're doing. </s><s>[INST] But the prudent thing would be to stay clear. There's so many questions I wanna ask there. One is about the violence and the legal aspect of that. It's very interesting, you raised that in the book. But, you know, I do wanna bring up something I probably disagree with you on, which is you say that there's not a significant difference between the different variations of the n-word. The one the, or maybe you don't. I just listened to a bunch of your interviews. So there's the version with the er at the end, version with the ga at the end and then gro at the end. These are all different versions. And I feel like in that list of powerful words, you know, I feel like there's a distinction. I feel that the number one spot is the one with the hard R. And I don't know, maybe you can try to shed light, but I feel like the one that ends in ga is really far down the list in terms of modern culture. So this is, we talked about the evolution of the words and the word queer, for example. It feels like because maybe because of rap, because of comedians, because it's become much more, it lost so much of its power. Oh, you don't think so? [/INST] No, I think there's a difference between nigger and nigger. I mean, people make a distinction between them. And I think that, to the extent that lots of people make a distinction between them. I think, you know, just as a sociological fact, they are different. I think that people who get upset if somebody, especially white people, so, you know, if a white person says nigga, and they're, you know, and they're, you know, sort of criticized about it, and they say, well, I didn't say nigger, I said nigga, believe me. I think most people who are mad at them are gonna stay mad at them. Now you raised the word, you know, so nigger and nigga, I would put in a very different category than nigro. Educate me here. Well, yeah, sure, I'm happy to. Nigro is a, also controversial. It's also controversial. But nigro has never been viewed by a substantial number of people as a derogatory term, at least in the, with the same amount of animus, the same amount of, it's a very different kind of word than nigger or nigga. I mean, after all, I mean, you know, nigro, Martin Luther King, Jr., you know, all of his great oratory, nigro. You read the work of the great W.E.B. Du Bois, nigro. You read the work of, my boss, so for instance, I use the word nigro. I use African American, black, Afro American, but I also use the word nigro. Now there are some people who get really mad at me because of, you know, when I use the word nigro. And then, so for instance, there's students who've gotten really quite exercised and they'll say, you know, I'll be giving a lecture and a hand will go up, I'll call on somebody and I'll say, listen, are you using the word nigro in its purely because of the historical time period that you're using? So, you know, is that why you're using it or are you using it in your own voice? And often I'll say, well, I'm using it in my own voice. And I'll say, well, I'm offended. We think that this is, you know, that's old timey. It's derogatory. When this first came up, I said, let's pause for a moment and I'll take that under advisement and let me look into this. And I ended up writing an essay about it, an essay about the history of the terms that black people have used to describe themselves. And it's a long list, you know, black, colored, Afro-American, African-American, nigro, et cetera. So I go through all that and I said, now, let me just tell you, I know for certain when I started using the word nigro often in writing, I can date it, 1983, the summer of 1983 is when I started using the word nigro in my professional life as a lawyer. And I did it for a very specific reason. I did it because my boss demanded that I nigro capital N. Now, who was my boss? My boss in the summer of 1983 was Associate Justice of the United States Supreme Court Thurgood Marshall, known as Mr. Civil Rights. Now it seems to me you were telling me that this word is so out of bounds, that this word is derogatory, nobody should ever use this word. Does the fact that Thurgood Marshall demanded that I use this word, does that complicate things a little bit? And so I think that people, again, you know, ought to know more. I mean, I've encountered students who don't know very much but who want to lecture me on word usage because they know, you know, three sentences about current fashion and hold it, you know, hold it. By the way, I push it further. I sometimes use the word colored. And then, you know, some people really don't like that, really don't like that. Colored, well, you know, there's an organization still very much alive in American life and law. The National Association for the Advancement of Colored People, the N-A-A-C-P. They haven't changed their name. And as far as I'm concerned, it's a wonderful organization. There are people who have used the word colored. That's what my grandmother used. Colored, perfectly fine as far as I'm concerned. So again, there are lots of different words that one can use. You can use different formulations. Understand that people have different preferences, fine. </s><s>[INST] I have my preferences, at least know where I'm coming from. Still, words have power and they have power to hurt. And there's a lot of reasons that I could see to justify the use of the word in its full form, as you're saying, in this conversation as you're using it. One of them is perhaps fighting for the freedom to be able to use those kinds of words. So let me ask you about the freedom of speech and the censorship of the word. Should the use of the N-word be censored, for example, on social networks? So we can come up with different places. We can say university campuses, maybe in op-eds or, I don't know, but I think social networks currently is a very interesting place. There's a lot of conversations that are happening on them. There's the ability, the technical capability to sentence, to remove the ability of people to use the word. Do you think they should be allowed to use the word [/INST] on Twitter, for example? My response is it all depends on the way in which the word is being used. If the word is being used to intimidate, if the word is being used to terrorize, then no, along with lots of other words, by the way. I could use the word, I suppose, gentlemen. I mean, I'm sure that I could conjure up a way in which that word could be used in an intimidating way. So would I be happy if there was a technology that always blanked this word, N-I-G-G-E-R? I would be against that. For one thing, it would erase the name of one of my books. I think that the book actually has a lot of useful information, makes some useful points. Let's imagine a world in which there was a technology that blanked every time N-I-G-G-E-R appeared. You would have, what would that do to novels by James Baldwin, by Toni Morrison, by, what would that do to the speeches of Malcolm X, Martin Luther King, Jr.? What would that do to the comedy albums of Richard Pryor, Cat Williams, Dave Chappelle? If one sort of plays that out, would one want to have all of those blanks in important literary and political performances? No, I don't want such blanks. What I want, I would want the word to be there and for people to understand how to deal with this word. And by the way, you've used the word hurt an awful lot. So let's talk about hurt. I think we need to be more careful with the way in which we deal with hurt. Because people can be justifiably hurt, you can have justifiably hurt feelings. And if somebody has justifiably hurt feelings, I then think that we should turn to the person who has hurt those feelings and say, you have acted wrongly because this person's feelings are justifiably hurt in relationship to what you've done. On the other hand, there are people who have hurt feelings and frankly, it's unjustified. So just imagine the following. Let's imagine that I give a talk about the greatness of Martin Luther King, Jr. And then let's imagine that a Ku Klux Klansman comes up to me after my talk and says, oh, you have now hurt my feelings. What, am I supposed to be, am I supposed to apologize? Am I supposed to be regretful that my talk about the greatness of Martin Luther King, Jr. has hurt the feelings of the Klansman? No, my response is gonna be, you need to reevaluate your feelings because actually your feeling of hurt is unjustified. And no, there's no apology coming from me. </s><s>[INST] But there's a kind of line and perhaps it's a gray area. And maybe the word hurt has been overused because if you try to avoid hurting a small fraction of society that is mentally weak in a way where everything hurts them, that's the wrong way to build a society. But if we flip that upside down and say, trying to maximize the amount of love in the world and think about decisions we make in terms of language we use to try to maximize the amount of love and not just short term, but long term. And that's where freedom of speech is very powerful because it's a short term painful thing often, a long term beneficial thing, just having freedom. And so there's where the question of the N word starts to come in. How much, how do we think about its use on the internet on college campuses in a way that maximizes the amount [/INST] of love and compassion and camaraderie in the world? I think that's good. And I would associate myself with your vision, how can we maximize, how can we maximize love? No, I love that, I think that's great. So let's take that on. I doubt that the way of doing that is to erase the infamous N word. I doubt that the way of doing that is to say to people, we understand that your feelings are really hurt and we're gonna do all that we can to avoid this symbolic action, maybe this word or maybe this symbol. We're gonna really, we're gonna do all that we can to suppress it so that we can have a more loving universe. I doubt that that's the way to do it. I think a better way to do it, I think a better way to do it would be to fully educate people, including educate people such that, you see that over there? That is the uniform of the Ku Klux Klan. I want you to be educated about the uniform of the Ku Klux Klan so that you can look at the uniform of the Ku Klux Klan and know what it's about. You're not terrorized by it. You're not immediately, you don't see it and sink to your knees and start wailing and crying. You don't see it and say, huh, I'm traumatized? No, you don't do any of that. You see it, you understand it, if somebody asks you about it, you're fully prepared to talk about it. Seems to me that attitude, that poise, that strength, that knowledge would be a better way of equipping us to have a more loving world. And by the way, just so, I would say that about the swastika, I would say it about the infamous N-word, I would say it about all of the things that we're talking about. It would be better for people to be educated </s><s>[INST] so that they are not traumatized. So do you, the N-word should not be removed from Huck Finn, Adventures of Huck Finn, [/INST] or from the works of James Baldwin and Toni Morrison? Not at all. In fact, it seems to me that the bolderization of these great artists' literary work, as far as I'm concerned, highly objectionable, </s><s>[INST] highly objectionable. When is it okay for a white man to say the N-word [/INST] with a hard R? Well, you know, here we need to focus on the word say. Is it ever okay for anyone, you know, black, white, pink, yellow, I don't care, red, orange? Is it okay for anyone to use this word in a way to put down people, to terrorize people, to intimidate people? Answer, no. But, you know, and I'd say that black person, I've seen, I mean, by the way, I've seen black people use this word to try to intimidate, put down other black people, bad. So I'm against it with a black person, white person, doesn't matter. On the other hand, on the other hand, imagine a white person who is giving a lecture on the history of American racism, a lecture on the history of American racism. And in giving that lecture, quotes the, you know, white racist politicians who until fairly recently in American life, use the infamous N word. So imagine a white history professor giving a lecture about the history of American racism and says, in 1948, this is what so-and-so running for the presidency of the United States said. And then quotes a paragraph or two in which the infamous N word is featured. Is that bad? No, that's not bad. No, that's not bad. Sounds like a perfectly good lecture. And I'm glad that you put the infamous N word in there so that we can see that as recently as 1948, people running for the presidency of the United States openly used the word. That does not bother me. I'll say this too. Now, you know, somebody says, well, you know, nice job, Kennedy, but you've, you've limited it to over here. You've put it in an academic setting. What about other settings? It does not bother me. Let's imagine somebody who's a comedian, a white comedian who is satirizing word usage. Let's imagine a white comedian who is satirizing our current practice and wants to poke fun at the way in which, let's imagine you have a black rapper who invites people on stage. And let's suppose they invite a black person on stage and they're perfectly happy when the black persons flout with their lyrics. They invite a white person on stage. The white person is, you know, that doesn't really sort of mystified, but it comes on stage. And flout with what the rapper says, including the infamous N-word, and then the black rapper gets mad. Imagine the white comedian who satirizes that, pokes fun at that, and in poking fun at that, says the infamous N-word. Am I angry? No, I'm not angry. </s><s>[INST] Not angry at all. What if in the process of satirizing [/INST] that comedian is not very funny? You say that bad joke, you were not funny. I don't object to the use of the infamous N-word. I just say, you know, mm, you're not very funny, N-word? </s><s>[INST] I just say, you know, you're not very funny. But because there's a line, when the joke is not funny, it just seems like the comedy's used as a cover to actually say something hateful. It's interesting thing about comedy. I feel like the funnier you are, the more you can get away with. Probably. And that's something to do with the thing we said earlier, which is when you use words that have power, you should do so with skill and competence [/INST] and the responsibility those words carry. Again, the cases that I'm most familiar with are the cases involving teachers, professors, you know, academic, and it is said sometimes, oh, you know, why do I object? I object, sometimes people say, because, you know, I suspect that this teacher just wanted to say the word and that all of this is a cover, a pretext. Do I, you know, in my sense, my sense of it is, no, I don't think it's a pretext. If, you know, if it's pretextual, that's bad. But in my experience, I have not seen that. </s><s>[INST] I don't believe that that's what's going on. I agree with you on that, but sometimes I do see people that kind of have this fly flying towards the light, desire to say something controversial and edgy, and they don't realize that there's a responsibility there. There's a skill that you should, you shouldn't just say, I mean, actually when comedians first start out, they'll sometimes go into that territory. They'll say edgy stuff that's totally not funny. And then you realize this is not like the edgier the thing, the more skills required to really serve. Like if you're cooking as a chef, a poisonous fish, there's a responsibility on how to cook the damn thing [/INST] so you don't poison the people eating it. I would agree, but to get back to your question, let's imagine that somebody produces a new set of Lenny Bruce albums. So Lenny Bruce was white, Lenny Bruce used the term nigger in his sets. Question, would I want Lenny Bruce's albums now to be purged of the infamous n-word? </s><s>[INST] My response, absolutely not. There's another follow-on sort of question, what you think, I've seen interviews you've done about this particular book, the title of those interviews on YouTube and elsewhere, would use the full word. What do you think about that? [/INST] Should I use this word in the title? In my view, the answer would be yes. Again, there are people, I've been on interviews, I've been on stage with people who had a different conclusion reached. And I respect a different way. Again, there is a place for euphemism. Again, it all depends, I'm not offended. Let's imagine that you posted this and you had asterisks instead of spelling it out. Would I be offended? No, I wouldn't be offended. I would prefer the full spelling, but I would understand where you're coming from. Would it offend me? </s><s>[INST] No, I wouldn't offend. Well, here's the weird calculation is which version of the word in the title, as silly as that is, brings more love to the world. It's hard, and basically your answer is, I don't know. [/INST] Your answer is kind of, you have to do it and find out. I'm not sure, again, there's certain questions in which, there's certain questions you're not gonna, we're not really going to know, there's no sociologist who's gonna be able to tell us that. So what do we do then? Then we go to secondary positions. And my secondary position is, I don't know, one thing that I hold on to, however, very strongly, is the virtue of openness, the virtue of transparency, the virtue of freedom. And I feel as though, if I'm holding on to those things, if I'm trying to engage in a serious conversation in which I'm trying to make other people understand me and I'm listening carefully to other people, I feel at ease, I feel at ease. I feel this is going to eventuate in something positive. </s><s>[INST] And I feel okay. You are at Harvard. You're one of the most respected people in the history of Harvard. That said, you did write a book with the N-word in it, and you also have a lot of opinions that challenge the mainstream perspectives on race from all sides. Hopefully we'll get to talk about some of them. But what's your view on Harvard and universities in general and speech? Did you feel pressure from any direction on, first of all, the title of this book, the content of the book, [/INST] and in general, your views on race? Yeah, I am very laudatory of Harvard University I've been at Harvard since 1984. I think it is a wonderful place to work. I have, in the various positions I've taken, particularly with respect to this book or all my other books, what has Harvard University done? Harvard University has done nothing but provide support, sustenance, encouragement. I think that people get down on Harvard University. I would say to anybody, imagine the following. Imagine that the ethos of Harvard University became the governing ethos of the United States overnight. Tomorrow we would wake up in a much better United States of America. I've been supported by Harvard University. I think well of Harvard University. That's not to say that I don't have criticisms of it. But by and large, Harvard University, more than by and large, overwhelmingly it has provided me, and I think it overwhelmingly provides my colleagues with a work setting in which they can do their work without fear, and that's a good thing. Are there certain aspects of Harvard University about which I'm critical? </s><s>[INST] Yeah, sure. By the way, I think a few people, rightfully or wrongfully, would disagree with you that if the ethos of Harvard University took over the country, it'd be a better place. But there's a lot of interesting ways to break that down because, Harvard, there's not one ethos, there's a lot of things going on that are very interesting. But one of the things that's happening is the disproportionate and aggressive growth of the administration versus faculty and students. I think the power of the university should always be with the faculty and the students. That's where the beauty is. That's where the flourishing happens, and the more you have rules, and bureaucracy, and all that kind of stuff, [/INST] the less powerful the university is going on that are very interesting. I think that at my university and at many universities, that's right. There's too much bureaucracy, too much regulation, and are there dangers to freedom of expression at my university and at other universities? Answer, yeah, there are, there are. So, and this has really hit home for me. There was a period of time in which I was getting off of, I'd gotten off of all boards. I was just doing my work, forget it, I'm just gonna do my work, I'm not gonna be associated with any organizations. In the last five years, that has changed quite dramatically. I have gotten on various, I've reassociated myself with various organizations, mainly organizations involving academic freedom because of what's going on on university campuses. Again, I have been, at least thus far, thus far. </s><s>[INST] This hasn't pinched me where I live, but. [/INST] You mean in the space of ideas. In the space of ideas, in the space of speech, in the face of teaching, I haven't been pinched, but I am concerned about things. So, for instance, let's imagine that you're applying for a job, you know, you wanna be an assistant professor. Or let's suppose that you're seeking a promotion. On many university campuses, you are asked to give a DEI statement in which you say, I plan to, you know, one of the reasons why you should hire me or one of the reasons why you should promote me is because I'm going to, you know, advance the, </s><s>[INST] you know, the DEI ambitions. Diversity, equity, and inclusion for people who don't know. This is the general, the set of programs that most universities now have. [/INST] Yeah, yes, that's right. So, you know, you've gotta sort of, you know, basically what you're being asked to do, whether they say it explicitly or not. They don't say this explicitly, but this is what they're, this is what is up. What you're being asked to do is to say, I'm down with the diversity, equity, and inclusion ethos, program, policy, campaign. And here's what I've done that shows that I'm down with this program and therefore I'm okay. Well, you know, a lot of what I do would fit very comfortably within that. But let's suppose that I didn't, just suppose I didn't like this. And by the way, there's certain aspects of the DEI, you know, industry that I don't like. You mean to tell me that, you know, I'm being judged at an academic institution. Let's suppose I want to be a chemist. Let's suppose I want to be a physicist. Let's suppose I want to be, I don't care, you know, a, you know, a critic of literature. I oppose this program. I don't, you know, I'm, I, I don't think this is the way in which higher education should be going. Should I have to, on pain of relinquishing my ability to be hired? Should I have to sign on to this? Just suppose, and let's change it around. Let's not make it a DEI campaign. Let's make it a Makeup Erika Great Again campaign. What would we think then? Let's suppose it was something that said, instead of it saying DEI, let's make it, let's make it say, the advancement of American capitalism as we know it. We want you to be down with that. What have you done that shows us that you believe in the advancement of capitalism in America? Would I be happy about, no, I would say this is no. Well, no with respect to these, as far as I'm concerned with the, you know, the DEI statements, oh, here's another one. I just learned, and in fact, I mean, there's certain things that are happening, and I must say, I mean, I'm in academia, but it's news to me. I didn't know until relatively recently about positionality statements. So these are statements in which somebody writes an article. Let's suppose, you know, I write an article, and it's not enough for me just to submit my article to some law review or to some, you know, some other sort of journal. No, in addition to me submitting my article, I've got to give a positionality statement in which I say whether I am, you know, gay or straight or what have you, in which I say my race, in which I say my nationality, in which I say my stance toward this ideological position </s><s>[INST] or that ideological position. Interesting. What? [/INST] Is this becoming a kind of a standard? I don't know how widespread it is. I know there was a very good article in the New York Times a couple of days ago about these positionality statements. And in fact, that's what sort of tipped me off. Somebody had told me there was a law review at my home institution. And I had a friend who sort of mentioned this offhandedly and who said, well, I submitted an article to this journal and I was a little bit taken aback in so far as they did have me fill out a questionnaire in which I was required to state my race, state this, state that, state the other. And, you know, as far as I'm concerned, well, what does that have to do? With a proper assessment of somebody's work. This concerns me. I'm concerned about the fact, you know, a little while ago, you mentioned, a little while ago, you mentioned the word Negro. And I was talking with colleagues a couple of months ago and somebody mentioned that this word had come up in their class because what had happened was one student was reading from a Supreme Court decision and the word Negro was part of what they read out. And another student held up his hand and said to the student who was reading, A, you should be careful because, you know, I find the word Negro offensive and you need to be careful about even saying a word that would be offensive to someone. And this person, and then, you know, the teacher was, you know, what should I say in those circumstances? What should I have said? And I volunteered, you know, and I said, well, guys, that's really interesting to see if that had come up in my class. I would have said, well, frankly, I don't, you know, I don't see what the, I don't even see what the big deal is because I use the word Negro. And, you know, Harvard University is not on some island that is apart from everything else that's happening in the world. If these things are happening in other places, if they're happening at Stanford, if they're happening at Yale, if they're happening at Columbia, you know, they're gonna happen at Harvard. But thus far, and I am most especially experienced in life at Harvard Law School. Harvard Law School is an open environment in which ideas are tested and they are tested fully. And it's because of that that I say I have been fully supported at Harvard Law School, feel that it is an excellent place in which to do work. I'm a fan, I am a fan, and I'm not embarrassed to say it. I am a fan of my workplace, Harvard Law School. </s><s>[INST] Very happy to be associated with Harvard Law School. Zooming out in general in education, there's something called critical race theory. Can you comment on what are your thoughts about this kind of perspective on race and race in America to the degree that it's becoming a part [/INST] of the education program? Okay, so the first thing I want to say. What is it? Well, the first thing I want to say about critical race theory is that critical race theory has become a term, so I'm gonna put quotation marks around the term critical race theory. We can, I mean, in a minute I'll talk about critical race theory without quotation marks, but to begin with, I want to talk about critical race theory because the reason why people are talking about critical race theory so much now is because politicians, mainly Republican right wing politicians, have created a boogeyman, critical race theory with quotation marks around it. They have created a boogeyman and they have tried to make it seem as though this boogeyman believes all sorts of ideas that Americans should loathe and that Americans should fear. And they've created this boogeyman and they've created it, and they've done a very good job of creating the boogeyman and they have mobilized sufficient public support such that there are a number of states that have passed laws prohibiting the teaching of so-called critical race theory. Now, the first thing I wanna say about this is that this campaign, these laws, these various policies, telling teachers don't teach this and don't teach that and you can't use this book, you can't use that book, this is a frightening encroachment on freedom, freedom of speech, freedom to learn, freedom to listen, freedom to read, that's terrible. And it's one of the most frightening things that has happened in American life in recent memory. So that's the first thing I wanna say about so-called critical race theory. Now, I'll say something, I'm gonna take the quotation marks off of the term critical race theory. Critical race theory is a sort of a, you could have a nice conversation about actually what it is. One way of viewing it is to say that, well, critical race theory is a community of ideas that comes from a community of people. The community of people would be people in legal academia in the period, 1908 starting and probably the middle of the 1980s. It would be associated with people like Derrick Bell, it would be associated with people like Kimberly Crenshaw, people like Charles Lawrence, people like Richard Delgado, people like Mary Matsuda. And these are folks who held, embraced a couple of, they articulated a couple of propositions. One of their propositions was that liberal race policy was insufficient. They would say that the racial policies of a person like my old boss, Thurgood Marshall, the liberal racial policies were insufficient to grapple fully with the pervasiveness and the depth and intensity of American racism. Their basic claim, and I think by the way, it was a good claim. Their basic claim was that American racism is more central, more deeply embedded in American life than most people perceived, including liberals. And I think there was a lot of strength to that proposition. But then they also took on some other propositions with which I was in very strong disagreement. So I think it's perfectly fine to say that racism is a force in American life that is deeper, more pervasive, more stubborn, more resilient than I think people often, often understand, often perceive. But then some of the folks in critical race theory pushed further. One of the propositions that some of the people in critical race theory took was the proposition that America was doomed to always be a country that would be governed according to the dictates of white supremacy. Derrick Bell, who was a colleague of mine and a friend of mine, took that position. He talked about the permanence of racism in American life. And he took the position that the various changes that had been wrought in American life were really mainly cosmetic. They didn't amount to a whole lot. I mean, Derrick Bell took the position, the second reconstruction, the civil rights movement. Well, yeah, it made changes, but at the end of the day, black people were still, after the second reconstruction, were still in a position of almost, I don't know, some of them would even say neo-slavery. Well, I think that's ridiculous. The second reconstruction changed a lot. And as for neo-slavery, neo-slavery, what are you talking about? A black American was president of the United States between the years 2008 and 2016. I mean, what are we talking about here? There's been a tremendous change, and I think people ought to understand that now. Am I saying that everything is peachy keen and all right? No, the United States is still, to a very large extent, still a pigmentocracy, but that doesn't mean that a lot hasn't changed, a lot has. So I disagree with certain tenets of critical race theory and have been very outspoken in my disagreement. There's another one, by the way, I need to mention, because we've talked so much in our discussion about freedom of speech, freedom to teach, freedom of listening. Another big problem that I've had with some of the people who talk of themselves as critical race theory people has to do with their attitude towards freedom, freedom of speech. Some critical race theory people think that the American legal system is wrong in the latitude that it gives to what they call hate speech or the latitude that it gives to what they would view as racist beliefs. Some of the people who associate themselves with critical race theory think that racist beliefs ought to be expunged with the aid of state power, if need be. Well, I'm against that. And I think we are at a moment, an ironic moment in which actually it's the right wing that has embraced some of the ideas that were championed by some of the people who call themselves critical race theorists. They say, oh, we ought to expunge hate speech. Well, the right wing is saying this critical race theory, that's hate speech, so let's expunge it. And so I, again, I've been very outspoken in my criticism of some of the illiberal dimensions of critical race theory. So I've been a critic of certain features of critical race theory. I have applauded certain features of critical race theory. Critical race theory, there's some aspects of it that I think have been useful. There's some aspects of it that I think have been profoundly wrong at it. So that's where I am. And I certainly, and, above all, I certainly am against any efforts to remove it from the intellectual universe. It is a part of our intellectual universe. People ought to know about it, and people ought to debate it, and people ought to be free to make up their minds to conclude what they will </s><s>[INST] about the strengths and weaknesses of critical race theory. And we'll talk about the pessimistic and the optimistic perspective on race in the history of the 20th century in America. I think you have very interesting perspectives there. But before that, I'd love to look at the current moment. And you had a conversation with Glenn Lowry and John McWhirter, and from there, it became clear to me, I think John made clear, how important to the conversation about race is policing in today's society. That that's where a lot of African Americans feel is sort of the pinnacle of racism sets the people that believe there's still racism in America. There's still a lot of racism in America. That's where it is. So to what degree do you think [/INST] there's widespread institutional racism in policing? Yeah, well, my first book was a book called Race, Crime, and the Law. 1997. 1997, wow. Time flies. Time flies. Unfortunately, unfortunately, the impetus behind that book stands. That book was propelled by a sense that with respect to the administration of criminal justice, African Americans feel deeply aggrieved and they feel deeply aggrieved with good reason, and they feel deeply aggrieved with good reason in at least two dimensions. On the one hand, African Americans suffer from under protection. And in fact, in that book, the central theme of that book was that Black Americans suffer from under protection. If you take a look at the broad, sort of the broad trajectory of American history and ask yourself, in what way have Black Americans been most oppressed? Well, take a look at the antebellum period, period before the abolition of slavery, before the abolition of slavery and the locales where most Black people resided, namely the slave states. In a lot of those areas, question, was there a crime called the murder of a Black person? Answer, for a long period, the answer was no. There might've been a tort, you know, so if a white person killed the slave, a killed a slave, that person could be sued because they had injured the property of another and would have to pay money to, you know, for that. But had they committed a crime, answer, no. In the antebellum period, were Black women protected against the crime of rape? In most states, the answer was no. There was no such crime. Let's go to after, you know, slavery is abolished, thank God, slavery is abolished. Slavery is abolished. Then, let's see, you know, what happens? What, you know, so we hear lynching. Lynching, from 1890 until, let's say, 1930. Well, you know, in 1890, there was probably, you know, I would say there was probably gonna average a lynching every day in the United States. You know, well over 300 lynchings. It goes down, that was the case in the 1890s, probably the first decade of the 20th century, and then it starts going down. What was lynching about? Lynching was about Black people being executed outside the law. Did the legal system do anything about that? Answer, no. You know, show me, show me cases in which people were prosecuted criminally for engaging in lynching. You come up in most places with a null set. Black people suffered the under protection of the law. Do Black people still suffer the under protection of the law? The answer is yes, and people talk about the Kerner Commission Report, 1968. Black people were asked, you know, with respect to the police, what's your main complaint? In many places, the main complaint was, we don't have police protection. You know, when things happen to us, when our houses are burgled, when our businesses are encroached upon by robbers, when our businesses are robbed, when we're assaulted, you know, nothing happens. The police protect white people, they don't protect us. Under protection, our society right now, if you take a look at the statistics, who is most liable to be raped, robbed, the victim of assault, what have you, Black people. I mean, and it's not even close. Under protection. So that's one way in which the administration of criminal justice harms Black people by not doing what government is supposed to do, which is protect us. Thus, 14th Amendment, you know, protect, equal protection, I underline protection of the law. So that was a big theme of race, crime, and the law. Now second thing, second, and this is the thing that gets most attention, and it's important, I think, that the under protection story does not get enough attention, but then there's a second story. The second story is that Black people have historically and still today, Black people are subjects of invidious racial discrimination when it comes to, when it comes to police action. So, you know, walking down the street, walking down the street. You have a Black person who's, let's say, 20 years old. You have a White person who's 20 years old. Let's make them men. Both just walking down the street. And the question, attitude of the police towards these two. An attitude, you know, is a complicated thing. It can show itself in various ways. It can show itself in a look. It can show itself in who gets the look. You know, Black persons, you know, walking down the street or running down the street, White persons walking down the street or running down the street. What happens with respect to the police? Let's suppose that, you know, who gets the second look? Who is followed? </s><s>[INST] Who is detained for a moment? Well, some of it is just on a small tangent. I apologize to interrupt, but attitude is an interesting one because a lot of it, a lot of the interaction doesn't show up in the data. So detained, for example, starts showing up in the data. But before then, the second look, the third look, the first look, this is where the gray area of conversation happens because- Very much so. Culture and society happens in the stuff [/INST] that doesn't often show up in the data. So I tell ya, this really came home to me. Several years ago, I was in New York City and it was at a time when there was a lot of discussion over the- Stop and frisk. Stop and frisk, basically, you know, racial profiling on the street. I was walking, I was in Harlem, I'm walking down the street. And frankly, you know, the police weren't bothering me. I'm just walking. Police weren't bothering me. But you know, I'm of a certain age. I did notice though, I was looking at the police and the way that the police attitude, you know, had to do with body posture. It had to do with, that's right, who got a second look. It had to, I noticed, I'm walking down the street, I'm walking in Harlem. There, you know, there are white people in the street. You know, most of the people that were black, some Hispanic, the level of contempt, the level of animus, the level of unfriendliness that was pouring off the cop. The police, they weren't, they didn't say anything. No, they didn't detain. They didn't say anything. Bring off. It was palpable. I could feel the attitude that was being directed at the young black men. And the thing is, see, the thing is, it's not as if this doesn't matter. It matters because the way I saw it, these young black men knew, they felt the contempt that the police were shedding. And this was gonna have a consequence. The consequence it was gonna have is, let's imagine that the police did say, excuse me, you know, what are you up to? Now, if you have been feeling this contempt, if you feel like the officer who was asking this question doesn't like you, doesn't know anything about you, but just doesn't like you on site, you might answer in a certain sort of way. You're not going to give the cop the benefit of the doubt and basically think, well, you know, policeman's just asking me this. Probably just trying to make the neighborhood safe. Well, if that's your feeling, policeman's just asking me this, trying to make the neighborhood safe, well, officer, the reason why I'm here is such and such, and you know, thanks for your service. That's one response. Another response is I'm not going to tell you anything. You know, I'm not going to tell you anything. I know that you don't mean me any good. I'm not going to tell you anything. Am I free to leave? And then the cop, having heard that, then says something bad, you know, after five minutes, what do you have, you have an altercation on your hand. And I felt that, and that is part, and you're absolutely right. That's not written down. It doesn't get to court. It's there, but it's an important part of street life. </s><s>[INST] It's an informal part of street. And it has ripple effects because that young black man will probably talk shit about that cop later that day. So the narrative persists, and then the cop will also talk shit. And then there's these narratives. [/INST] And I think the contempt is such a powerful thing. It's so hard to disentangle because you're absolutely right. The young man, let's suppose that the story ends, quote, well, he's going to go and he's going to be talking with his friends and he's going to say, let me tell you what just happened to me. And his friends are going to say, oh yeah, that doesn't surprise me. Let me tell you what happened to me. And for two hours, this goes on. The anger, the feeling of humiliation, the feeling of aggrievement grows. It's disseminated. And that's part of what we have. But that's not all of, that's an important part of what we have, but we have, it's even worse than that because then you ask the question, what about things we do know? I know this from my teaching. This was brought up, there was a lawsuit in New York City. And notice I didn't say, I didn't say Birmingham, Alabama. I didn't say Atlanta, Georgia. I didn't say Tallahassee, Florida. I didn't say the Deep South. I didn't say Montana. I didn't say Idaho, New York City, cosmopolitan place, metropolis. In New York City, the police were challenged with respect to their policies. A judge wrote a very lengthy opinion and the facts were rolled out and the facts were really quite horrifying. People, there were black men who had been stopped many, many times. It wasn't just once, over and over and over again, under circumstances in which they ought not have been stopped. And this has real consequences. It doesn't just show up here though, of course. It also shows up in other places with respect to the administration of justice. And we still have a big problem. Now you mentioned the police. If you ask yourself, who are the state agents that are most consequential? The police. I mean, you walking down the street, what other agents have guns on them? What other agents are authorized by the law to shoot you under certain circumstances? It's the police. The police are the most consequential agents of the state </s><s>[INST] that most people interact with. I mean, to push back a little bit of consequential in a physical sense, but if we return to the power of the psychological sense of contempt, I would say store clerks and stuff like that [/INST] can also be a source of contempt. They're not agents of the state. </s><s>[INST] Right. But if we look at the landscape of contempt, which throughout the 20th century, or the bus, right, you can experience the same kind of contempt in other aspects of society. [/INST] But yes, the cops have consequences. In other, but yes, the cops have consequences. I would still put the police. The policeman or the police person is the person walking down the street with a gun. Gun, yeah. And if you think about the way in which the law, the extent to which the police are authorized to use their force, the police have extraordinary, extraordinary authority. Look, you're driving your car and you're speeding. The police can arrest you right then and there and take you to jail. </s><s>[INST] That's an extraordinary path. But have they also have, because of that, the leverage, just one human to another, they have more leverage to be an asshole and to show contempt to you. They certainly do. To be the lesser, to lean into the lesser aspects of their nature as all humans can just to be an asshole to show contempt. You had a bad day. [/INST] They have the more freedom to do that. They certainly do, yes, and that's why, that's why police officers are very important. I recognize, I know police officers. They have a very difficult job, a very important job. Very important, again, remember what I just talked about, under protection. I want the police to protect me. I want the police to protect me from the rapist, the robber. So I, you know, the police, I'm with the police. We need good policing. But we need good policing and for good policing, we need accountability. And one of the scandals, one of the just absolute scandals of American law is the extent to which the police are not held accountable. It's absolutely remarkable the degree to which American law fails to properly hold police accountable. They have an important job, a difficult job. I want them to be very well paid. And as far as I'm concerned, you know, we should be, police should make more money. They should be given the importance of what they do. They should have more respect, more prestige, more money. With all of that, they should be held accountable. And the way things are now, they're not held accountable. And every day, we see the consequences in our newspapers or just, you know, </s><s>[INST] talking with people. So what do you make of the different perspective on this? From to bring up a person that I'll probably speak with Heather McDonald, who wrote a book called War on Cops and will often bring up the stuff that does show up in the data to show the disproportionate amount of homicides committed by African Americans. And we'll also justify racial profiling on that basis in stop and frisk programs. And we'll also bring up things like the Ferguson effect saying that because of this pushback and all the stuff we've been saying about police in those areas, the police will step back [/INST] and crime will increase. I was in one debate with her. And one of the things that I said is it was a debate that was sponsored by the Federalist Society, conservative legal group, conservative law students at Harvard Law School. We had a, she made a presentation and they asked me to respond. And one of the things that I said was when we're talking about the police, I'm disappointed with the reaction of some of my conservative colleagues. And I would consider her to be one of my conservative colleagues. Because what are the sort of the, what are some of the important precepts of conservatives? One very important precept of conservatives, limited government, limited government. conservatives talk about the tendency of government to overreach itself and governmental agents to overreach themselves. And I say, you're right. You're right. I just, you know, right on. Why is it that you somehow forget that when you're talking about the police? When you're talking about the police, you seem to be unaware of this tendency that is so much in your consciousness and other places. But now when you're talking about the police, you make it seem as though I'm, you know, other people are being paranoid when they talk about the danger of overreach. We need to be very careful about the danger of overreach. Another thing with respect to the police, what to conservatives, transparency in government, right? You're absolutely right. We need transparency in government. So why is it that so often when we're talking about policing, why is it that conservatives actually embrace police unions and are the enemies of transparency? Why is it that you want to prevent the citizenry from knowing that officer so-and-so has, you know, there have been 10 incidents in the last year in which citizens have complained about officer so-and-so. Don't you think that the citizenry ought to know that? Why is it that you want to keep that under wraps? So overreach, transparency, the tendency or the, you know, the problem of governmental agent corruption. Why is it that those sorts of things are forgotten about when some conservatives, by the way, not all conservatives, not all conservatives, there's some conservatives who have stuck and appropriately so to their guns and have said, hey, we need to make sure that the police stay in their lane. We need to make sure that the police do not overstep constitutional bounds. We need to be, we need to insist on transparency. There are some conservatives who have taken that line and I salute them. But there are a lot of conservatives, and I would say Heather McDonald was one of them, who all of a sudden become just, you know, totally uncritical status </s><s>[INST] when they're talking about the police. So the overstepping, overreach, the lack of transparency. Of course, we see this kind of stuff in foreign policy as well, which is starting military conflicts and a lot of the supporters, at least with the Iraq and Afghanistan wars were conservatives and hawks and so on. So there's a lot of hypocrisy in terms of principles and so on. But maybe one question is, in this discussion about racism and policing, there was a lot of cops that might listen to this and feel like they're not being, their profession is not being respected. They're not being heard. Not being respected to the difficulty of the problem they're facing. [/INST] Can I just interject? Remember a few moments ago. I mean, if I were in charge of things, if I were in charge of things, I'd pay police more, in fact, much more than they receive. I do, police have a very difficult job, extraordinarily difficult job. I mean, for one thing, sort of maintaining the law. The law, that's a very complicated thing, the law. That's not an easy thing. I mean, I teach law. I spend a lot of hours with very smart people trying to understand the law, very difficult. So here we expect people to understand the law at the same time that they are grappling with people, some of whom are violent. It's very difficult. I respect police officers. And I said, we need police officers. You did not hear me say, by the way, so let's get down to brass tacks. You did not hear me say, defund the police, did you? In fact, to the contrary, I said, defund, actually I want more funds for the police. I want to hold them accountable. I understand the difficulty of their job. I respect the police. I want people to respect the police. I also want the police to respect civilians and demand that they do. I am not a police abolitionist, far from it, far from it. Again, we need good policing. </s><s>[INST] For good policing, we need good people. To what degree, almost philosophically, maybe practically, do you think police should be doing racial profiling? [/INST] Profiling in general. </s><s>[INST] Okay. It's a very difficult philosophical, moral human question. [/INST] Yeah, so first thing we need to do, and here we get back to the early part of our conversation because we focus so much on, first part, a word. Here we have another word, profiling. Question, what is racial profiling? Now, here we have, in the weeds, we have people talking past one another. I've been in conversations with police officers and debates, and we talk past one another because we are defining racial profiling very differently. If you ask, I've been in conversations with police officers and they say, oh, I'm totally against racial profiling. Then I say, well, sir, what do you mean by racial profiling? And here's what they say. Racial profiling is when police officers act against somebody wholly on the basis of race that gets rid of the issue because most police officers don't act against anyone wholly on the basis of race. You could have the most racist police officer, and that police officer is not going to act adversely against the 90-year-old black woman walking down the street with a cane, okay? So it's always, you know, if you define racial profiling that way, you're getting rid of the issue. The issue is, the proper issue is this. Should the police be able to act against someone taking race into account as a factor? So let's imagine that a black person who's 25 years old is walking down the street right next to a white person who's 25 years old. Some people would say, you know what? Under those circumstances, it's okay for the police officer to give two looks at the black person and only one look at the white person. Why? Because the statistics tell us that the black 25-year-old, there's much more risk of that person acting in an unlawful way. If you take a look at, you know, crime statistics and ask the question, with respect to, you know, homicide, with respect to robbery, with respect to various, you know, crimes, is there, is there a difference between the white 25-year-old and the black 25-year-old? With respect to certain crimes, the answer is, in certain places, the answer is, yeah, there is a difference. And there is a greater risk that the black 25-year-old has engaged in various forms of criminality. I'm not, you know, that, okay. Under those circumstances, what do I say? Should the police officer, therefore, be allowed to take action vis-a-vis the black person, as opposed, you know, as against the white person? My answer is no. I'm fully willing to concede, let's concede for the point of, you know, for the point of discussion, that there is more risk. There might be, there might be. But, for reasons of constructing the sort of society I want, we should not empower agents of the state to act towards certain people in a way that's, you know, adverse to them. Let me try to break this down in a little different way. Let's go back to, let's talk about what happens when you wanna get on an airplane. You know, wasn't so long, you know, 9-11 wasn't all that long ago. It was a while ago, but it wasn't all that long ago. And this very issue came up with the respect of the profiling of Muslims. And there were some people who said, well, geez, you know, in the aftermath of 9-11, profiling of Muslims makes sense. You know, no hard feelings, but, you know, the 11 people who, you know, were on those planes, were all Muslims. Now, there is a rationale. You could just simply say, it's not prejudice, it's not animus, it's not invidious, it's just, you know, the facts take us this way. Well, the facts never take us this way. There are facts, and then there is our choice of how we want to respond to those facts. Now, you could respond by saying, well, we perceive Muslims to be more likely to, you know, do bad things on an airliner. You could respond in that way. On the other hand, you could say, no, we want a society in which people do not have to grapple with prejudice on the basis of their religion or on the basis of their race. And to deal with that, we are gonna demand, we're gonna demand that agents of the state act towards people in the same way. And so if that means that everybody getting on the airplane, before they get on the airplane, has to, you know, open up their luggage and it slows things down, but everybody has to open up their luggage. I would prefer that over a system in which we focus on people who are Muslim. And one of the reasons, and I'm gonna bring this back to the racial thing. One of the reasons why I wanna insist upon that is because if, you know, if we all have to open up our luggage, what that means is we're all paying a tax for more security. And we're all likely to ask ourselves, hmm, do we wanna pay this tax? Whereas if we focus simply on the Muslims and allow the Muslims to be the only ones who are sort of paying the tax, we'll foist that on them. Same in the, you know, black person, white person, 25 years old, walking down the street. Do we want to impose a racial tax on the black 25 year old? Some people would say, yes. I say, that's a mistake. Black people aren't stupid. They know that they're paying this tax. It is a violation of, it seems to me, the rules that we ought to want to have to govern our society. I say, spread the costs, make the police deal with everybody the same, and don't allow a situation to develop in which a group of people can accurately say, we are paying more of a cost </s><s>[INST] than these other people over here. So it's a better avoiding profile while it may have costs on security in the short term. In the long term, it's the embodiment of the principles that all men are created equal. So it has a much bigger benefit in representing the fairness that is at the core of the ideals of this country. Yes. Let me ask a big philosophical question. Why do you think there is racism in the world? [/INST] Yes. Oh, now you've, okay, fine. Now you've asked me a question </s><s>[INST] in which I throw up my hands and I don't know. Will there always be? Why is there tribalism? Are humans always finding this way to divide ourselves? [/INST] And how bad of a problem is that? It's a huge problem. I don't, you know, I mean, I don't, I'm not gonna pretend that I know enough to grapple in a satisfactory way with such a question. I mean, to really grapple with that question, one really has to have all, you know, a very broad knowledge base in which they can make comparisons. I mean, the world's a big place. Now from the little bit I know about the world, and I read, I read as much as I can. I've been, I'm a very privileged character. I mean, I live in a university. So I'm reading constantly and listening constantly. From what I gather, the problem of divided societies is a problem that is worldwide. Very broad, there's, you know, and it seems as though, it seems as though human ingenuity is such that humans will find something to divide over. You know, it might be texture of hair. It might be, you know, complexion of skin. Politically, ideology. Political ideology if the texture, if the texture of skin is the same. Politically, ideology, political, it'll then be, well, you know, you wear these sorts of clothes. You speak in this sort of way. You believe this, whereas I believe that. I mean, it seems like a human ingenuity is such, they will, humans will find some way of distinguishing themselves, and then they seem to want to embellish the distinction. It's not just a distinction. It's not just, you believe this and I believe this. Okay, that makes the world interesting. Let's talk about what you believe and what I believe. No, it's usually associated with you believe this. I believe this. Of course, my belief is superior to your belief, and I want to put you down. </s><s>[INST] And now we're headed towards war. The interesting thing is, if I were to step outside of this whole thing, from an alien perspective visiting Earth, I think America is one of the greatest, if not the greatest countries in the history of human civilization. And I think that the line between white and black, the racial struggle is the thing that in part made it a great nation. There's something about the division and the way you alleviate that division through the struggle for human rights that makes for a great nation. And so it's interesting that the division is almost the fuel for the greatness, for our discovery of what it means to be human, or what justice means of, and it's interesting that it seems like there's this struggle that you're elucidating now, but that struggle itself is our search, [/INST] a man's search for meaning and justice and freedom. I think there's something to that as you were speaking. I was immediately thinking of a person who most jumped to mind was the great Frederick Douglass. So I mean, here you have a person who in my view is one of the great people in the history of the world. And one of the things that ironically enabled him to become one of the great people of the world. He was born into slavery. His overcoming was the very thing that in a sense made him this larger than life figure. And I think there's something to it. I will say this because a minute ago you mentioned optimism and pessimism. And I'd say in the last few years, my feeling about the United States has changed and it's changed in a somber way. For most of my life, for most of my life, I've been in the optimistic camp with respect to my view of American race relations. The optimistic camp, that was the camp. That's the camp that believes we shall overcome. That's Martin Luther King's camp. Martin Luther King, you know, Martin Luther King, hours before he's killed. I've been to the mountain top. I might not get there with you, but I've glimpsed the promised land, optimism. Frederick Douglass would be in that tradition. There would be other people. </s><s>[INST] Wonderful, good people who would be in that tradition. Would you sort of interrupt put in the pessimistic camp, [/INST] would you put Malcolm X on it? On the pessimistic camp, the pessimistic camp is the more interesting camp. I mean it is, it's the more interesting camp because in the pessimistic camp you have, I mean, if I was going to list some of my pessimists, pessimists, number one, Thomas Jefferson, Thomas Jefferson, the author, you know, principal author declaration of independence he was also the author of, Notes on the State of Virginia. And he said in notes on the State of Virginia, basically we shall not overcome. He talked to, he said, you know, the black people will always know that their forebears were enslaved and they will always be resentful of that, always be aggrieved by that. Jefferson did not think that we would ever have in the United States a multiracial democracy. He was very critical of slavery. Now he was a hypocrite. He had slaves, he sold slaves. He was terrible in that way, but he did understand that slavery was horrible, but he did not want, he did not want to free the slaves for a variety of reasons. But in one reason was because he thought that it would be impossible to have a society in which blacks and whites were equal neighbors. He was thoroughly pessimistic. Another pessimist, Alexis de Tocqueville, thoroughly pessimistic. So who were some of the other pessimists? Abraham Lincoln, pessimistic. That's why he was so interested in colonization. He basically said, you know, I don't like slavery, but blacks and whites are not gonna be able to share the United States. Maybe the best we can do is just, you know, </s><s>[INST] put blacks, ship blacks someplace else. Can you elaborate on that? I think people would be surprised to hear that you will put Abraham Lincoln in the pessimist camp. [/INST] Oh yeah. Oh, Abraham Lincoln's thoroughly pessimistic. He was, he believed, he was anti-slavery, but he did not believe that blacks and whites would be able to share the United States together. And he was always very interested therefore in colonization. Even after the, even during the civil war, he was interested in, you know, maybe all black people, would all black people be interested in maybe going to Panama? Would they be interested in going someplace else? Because, you know, Lincoln was aware of how racist white people were, including himself, or including, and he did not think that black people and white people would be able to share the United States. Now, there's a black nationalist tradition. You mentioned Malcolm X. Well, before Malcolm X, you know, Marcus Garvey. My father, my father was a thoroughgoing pessimist. His view was A, the United States was born as a white man's country. It's gonna remain a white man's country. And that's the way it is. </s><s>[INST] He was thoroughly pessimist. You mentioned just a brief aside about your dad that when you moved to South Carolina, to Washington, DC, and you asked him why, his response to you was, because either a white man was going to kill me or I was going to kill a white man. Yes. So he saw race as an important line [/INST] that divided people in the United States. He certainly did. And he thought that the line... My father did not. My father had passed away before Obama was elected. </s><s>[INST] I would have loved to have talked with my dad. What do you think he would've said? And you wrote a book about the Obama presidency. [/INST] I did, I did, I did. And I never... What would my father have said? My father would have been delighted. My father would have been happy about his election. I do think, though... I do think that my father would have said, I'm happy that Barack Obama has been elected. Hold on to your seats. </s><s>[INST] Let's see how the white people respond. [/INST] So he would've predicted, Donald. I think that my father, I think that in 2016, I think that in 2016... You would've said, I told you. Yes, yes! I think that in 2016, my father would've said, all of you people who were talking about, I don't know what's happened to America, and how could this have happened, and you know, no. I think my father would've said, this is America being America, and what has happened is that America has been put off kilter by a black family being in the White House. It has deranged millions of white people, and now this is coming home to Ruth. So I think my father would've absolutely said in 2016, </s><s>[INST] I told you so. In 2016, as you're saying, is the reason that you have at least dipped your toe [/INST] outside of the Optimus camp into the pessimist camp. I'm, yeah, I wanna be careful here, and I don't wanna- </s><s>[INST] Don't give up on the Optimus camp. [/INST] I don't, I don't wanna, I don't. You're right, I don't wanna give up on the optimist camp. I don't, I have been, my optimism has definitely been dampened, has definitely been tested. I am certainly, no, I am not, I am not as triumphalist as I once was. I am not as indignant as I once was in my criticism of pessimists, but at this moment, as we speak, you know, am I more in the optimist camp than I'm in the pessimist camp? I'm still probably more in the optimist camp, but my optimism has been dampened. But as I speak, I have to say the following things, and I'd say the following things with my father, but again, whom I revere, great man. But if my father was sitting here with us, I would say, listen, Pop, it's absolutely true that the country is more racist than I had thought. That is true. It's also true, Pop, that the Vice President of the United States, as we speak, is a black woman. As we speak, it's true that the Secretary of Defense, now, Secretary of Defense, the Secretary of Defense is the head of the Pentagon. The Secretary of Defense knows where the button is, okay. This is not a little, you know, this is not a small out of the way thing. This is the Secretary of Defense is a black man. There are a slew of black generals. There have been black secretaries of state. There are black people who are the heads of police forces. There are black mayors. There are black people who are the heads of, you know, some of our foremost foundations. There are, you know, the president-elect of Harvard University is a black woman and we could go on and on and on and on. This is not, you know, we're not, when I was growing up, when I was growing up, when I was, let's say 10 years old, we got a magazine, Ebony Magazine, every month, and in Ebony Magazine, you could turn to the middle of Ebony and they would have Black firsts. The first black person to do this, the first black person to do this. You could read Ebony, and frankly, I could tell you all of those, I knew their names. Now, I read stuff, you know, the leading cadet, the chief cadet at the United States Naval Academy. I'm reading, I'm reading, then I see a picture. Black woman, I said, I'm reading, I didn't know that. Back in the day, I would have known that. Now, has the United States changed? Yes. Is there racism? Yes. Is it, you know, a substantial force in American life? Regrettably, tragically, yes. Has the United States changed? Yes. And again, if we want to go international, the United States is not the only country that is a country that has wrestled with deep division. You think about, I don't know, think about India. Think about, you know, the United Kingdom. Think about practically any large nation state. They've all grappled with divisions. If one asks about the United States and the race question, and one puts on the table that, you know, in 1865, now, you know, when I talk with students, I say 1865, they think, oh my God, you know, isn't that when dinosaurs roamed? No, it wasn't when dinosaurs roamed. 1865, frankly, is not all that long ago. In 1865, the great mass of black people in the United States had recently been released from chattel slavery. The great mass of black people in the United States in 1865 were illiterate. Now, I mean, it's absolutely, it's an absolutely extraordinary story. And so one of the difficulties I have at this moment is wrapping my head around two stories that are in such tension with one another. One is the continuing story of racism, which is an awful story, but the other story is a story that is encapsulated in the title of a great book of history by John Hope Franklin, From Slavery to Freedom. And, you know, those are two stories in American life and it takes an awful lot. </s><s>[INST] Put your mind around both stories and I'm trying to. Well, as an optimist, I think you put more value to the overcoming side of the story, the overcoming of hardship, the overcoming of slavery, of discrimination. Well, since you mentioned illiteracy from, what is it, 150 years ago, let me ask you about affirmative action. You wrote a book on the topic titled For Discrimination, Race Affirmative Action and the Law. First, what is affirmative action? And maybe we could talk about what your view is on it today. [/INST] Sure. Well, affirmative action refers to, racial affirmative action, because there's various sorts of affirmative action. I mean, you can have affirmative action for veterans, you can have affirmative action for in-state residents. Let's suppose you have a school, you know, the University of, you know, blah, blah, blah. And we're gonna, we want to reach a, we're gonna give a, reach out a hand to boost help people who live within this state. We're gonna have a boost for veterans. We're gonna have a boost for, you know, for women. We're gonna have a boost for men, in certain circumstances. Well, we're the most, the type of affirmative action that gets most attention, and that's worth noting as well, there's lots of, there's some sorts of affirmative action. But when you say affirmative action, the type of affirmative action that, </s><s>[INST] immediately people are thinking about is racial affirmative. Seems like race is at the core of this American experiment, part of in every part of it's- [/INST] Bingo. Bingo. Bingo. Why is it that we, again, there's various ways in which institutions reach out to help various sectors of our population. Why is it that this is the one that generates all of the pulling out of hair and gnashing of teeth? We can put that to the side for a moment. Racial affirmative action refers to efforts in which institutions, reach out to provide assistance to racial minorities. Now the reaching out can happen in different ways. A light form of affirmative action might be reaching out in terms of recruiting, making a special effort to make sure that young people, let's say in racial minority neighborhoods, know about your college, recruitment. On the other hand, racial affirmative action might take a stronger form, and might take the form of saying, okay, we have a competition. And we think that there will be too few racial minority kids who do well enough in this competition to be admitted to our school. So what we're gonna do is we are going to, in various ways, give a boost to the minority kids. If it comes down to you have two kids, they both, I don't know, have 99 on the test. There's one place left. We only have one spot left, two kids. One's a black kid, one's a white kid, they both got 99, we're gonna give it to the black kid. Why? Well, black kid, all there is to it. Black kid, we wanna maybe, and then our theory, maybe our theory is that black people have been done wrong in the United States, and we want our institution to contribute to making amends. That might be a theory, another theory might be, we think that we'll have a more interesting student body, we'll have a better student body, a better discussion if there are more black kids on campus. And unless we make a special effort to bring more black kids on campus, our student body will be overwhelmingly monoracial. We'll just have white kids, few Asian kids, a few Latino kids, if there are no black kids here, I don't know, it'll be lacking an important aspect of American life. So that's some sort of the so-called diversity story. So anyway, there are various theories. Some are grounded, like I said, in reparative justice. Some might be grounded in distributive justice. So for instance, when people say nowadays, we want a cabinet, we want a team, we want a student body that looks like America. That might be a distributive justice theory for why you want affirmative action. Unless we reach out and give a boost to certain groups, they won't be here. And we want a campus that looks like America, and we won't have a campus that looks like America unless we give a special boost to, I don't know, the Latino kids or unless we give a special boost to black applicants. So, reparative justice, distributive justice, or third, diversity. We just wanna have an interesting student body, and to have an interesting student body, we want kids from a wide array of places. We think that that'll make for a better campus, more interesting campus. Those are three justifications, all of which, however, are justifications for, in a competition, giving a special boost </s><s>[INST] to some people based on their race. So what's your sense? Can you make the case for affirmative action, [/INST] and can you make the case against it? Yeah, I can make the case for, and I can make the case against. The case for, I won't spend much time on this. Like I said, there are three main justifications. Your audience should know that the justification that actually led to affirmative action is a justification that you don't hear about in the courts, because the courts have said that that justification is insufficient. So the real justification behind affirmative action was in the late 1960s, in the aftermath of the Civil Rights Revolution, in the aftermath of the Civil Rights Revolution and the aftermath of the Civil Rights Movement. There was a feeling that well, okay, fine, we're not discriminating against black people anymore, but black people have been disadvantaged by the discrimination that has been put upon them. And this discrimination that was put upon them has disabled them. And so they go into competitions and it's unfair. Yeah, they score less well on the standardized test, but surprise, surprise, what the heck? They went to schools in which they got the leavings of the white folks. You know, the white folks gave the black folks the old textbooks. That's what the black kids read. The white kids read the newest textbooks, on and on and on. So, reparative justice. We're gonna try to repair the scars left by past racial injustice. And we're gonna, and so it's sort of an effort to overcome the vestiges of past misdeeds. That was one justification for affirmative action. And frankly, I think that's the justification that has always been the predominant justification, whether people owned up to it or not. But that's one justification. The distributive justice justification is there. Like I say, you know, people, we want an integrated America. We want an America that looks like America. In that justification, legitimacy is sometimes mentioned. So for instance, people will say things like, well, you know, if we're gonna, in the armed forces, you can't have an armed forces in which the people on the ground are, you have a lot of people on the ground who are people of color, but none of the people calling the shots, none of the generals, none of the may, you know, colonels are people of color. No, and then the people on the ground are not gonna stand for that. So for purposes of legitimation, we need to, for purposes of buy-in, we need to have a situation in which people get the sense that even if they're sort of low-down, they're still part of the story, they're part of the team. So that's part of the sort of, you know, </s><s>[INST] I dunno, distributive justice notion. Do you think there's power to that? I mean, do you think there's value, [/INST] there's correctness to that kind of idea? </s><s>[INST] I think there's some. Because for the application process for different universities, I think there's probably a driving narrative, justification for, well, affirmative action, I don't know where we put DEI efforts, because they overlap, [/INST] but they're not perfectly overlapping. The reason that the school, so yeah, as you know, there is a case, we'll know about it, it'll be announced sometime in the next month, well, month, month and a half. It's a case of the Supreme Court of the United States in which the affirmative action program at Harvard and the affirmative action program at the University of North Carolina are being challenged. Most people think, including me, that the Supreme Court of the United States is going to limit, if not totally seek to abolish affirmative action. So this is a very burning issue. As things currently stand, my university and other universities embrace affirmative action on the third ground, the diversity ground. And what they say is, we need affirmative action because affirmative action is good for pedagogical reasons. Now, frankly, do I think there's something to that? I think there's a little something to that with respect to some subjects. I don't think that's what's really going on for the most part. I mean, if that's what's really going on, why don't we have more foreign students? Why isn't there a greater effort to bring in more foreign students? Why isn't there a greater effort to bring in more, I don't know, religious fundamentalists? Why isn't there a greater effort to bring in, and you can just name various groups </s><s>[INST] that you hardly ever see them on campus. So you don't think this effort [/INST] of driving towards diversity is rigorous enough? I think it's often pretextual. I think, frankly, the real reason has to do with the belief, and I think it's a good belief. I associate myself with the belief. It's just that because of the legal rules, the authorities can't say this belief out loud, but it's still the case that a lot of institutions want to help American society overcome its racial past. That's the real animating force. Now this thing about, you know, we'll have better classroom discussions, you know, some discussions. I mean, you know, with some subjects, yeah, listen, I'm an ignoramus when it comes to physics. My sense of it is, however, that if you're talking about physics, you're talking about physics, and frankly, it doesn't much matter in terms of mastering physics, what the demographics of that classroom are. </s><s>[INST] You either know physics or you don't. The interesting thing I've noticed since doing this podcast is one way it does matter, it's really lonely when you do a thing and you don't see somebody that looks like you doing that thing. And it's such a seemingly stupid thing. Why does it matter if there's another person that looks like you in this very shallow sense? But it seems to matter to people. And when I talk to, for example, women on this podcast, a lot of women reach out saying how inspiring that is. That's interesting, right? Like, I think we're still human and we see people that look like us and this kind of narrow, shallow definition of diversity [/INST] still matters, I guess a lot. Okay, well, you know, I think you've made a good point and maybe so. So let's go back to the physics. I mean, let's suppose that under one scenario, there's a classroom and a kid sticks his head, a black kid sticks his head in the classroom and doesn't see anybody else black there and has to make a quick decision and says, yeah, you know, nah, this ain't for me versus they stick their head in the classroom. They see a smattering of other black people in the classroom. They say, oh, let me try this. And then they try it. And it turns out, damn it, they're Albert Einstein. So, you know, to that extent, I can see, you know, under that scenario, maybe it does matter. So, you know, I'll have to recalibrate. Still, those are the three, those are the three leading justifications for affirmative action. You asked me, where do I stay with respect to affirmative action? Oh, no. Before we get to that, are there criticisms? The answer is, yes. There are criticisms of affirmative action. Affirmative action is a policy like, you know, any policy. Any policy is going to have some downsides to it. And affirmative action's no different. Does affirmative action have some downsides? Yes, it does have some downsides. What are they? Well, let me mention a couple. One, stigma. Stigma. So if you have an institution that says that it reaches out to give a boost to certain people on a racial basis, there are going to be people who observe that and who are going to be thinking to themselves, hmm, if so-and-so is here and they were given a special boost, doesn't that mean that they were not as proficient as the other people who were here and who did not have that boost? So if they are not as proficient, that means that they might not be as good. They might not be as up to snuff. Is that part of our affirmative action world? Yes, it's part of our affirmative action world. Yes. I'm a professor at Harvard Law School. One of the subjects I teach is contracts. Actually, that's probably the subject I most enjoy teaching. I think I most enjoy writing about racial conflict and the legal system. But as far as teaching, I most enjoy teaching contracts. Well, on that very first day, on the very first day, when I, you know, the 80 students come, especially the first year students, they're nervous, I show up. I'm quite sure that there's some students there who are thinking, okay, well, is this guy as good as my other teachers? Because, you know, I know that, you know, institutions like Harvard have made a special effort to bring in people like this guy, Kennedy. Is he as good? Well, I mean, I'm sorry. If you have an affirmative action regime, people are gonna think that. And are they crazy to think that? No, they're not crazy to think that. What do you mean? No. That's a perfectly logical thing for somebody to think. Does it have an effect on me as the teacher? Yeah, actually, does have an effect on me, sure. I'm aware that some people are thinking that. It doesn't, I'm not, you know, it doesn't, you know, make me shake in my boots. Am I aware of it? Yeah, I'm aware of it. Does it have an effect? Yeah, it probably does have an effect. It probably does. It probably, it probably makes me, it probably makes me redouble my efforts because I don't want anybody to think justifiably that I'm less able than my colleagues. So, you know, it's funny. When I was growing up, my father used to tell me over and over again, Randy, tie, tie, you lose. Okay, brother, let me just tell you that. And he was telling me that because when he was, you know, in an earlier time, tie, tie, you lose, it was, you know, if it's even and there's a choice to be made, the white person is gonna get the benefit of the doubt. Now under affirmative action, there's been a switcharoo. Oftentimes it's the black person who gets the benefit of the doubt, but I'm still in a situation which- If to work hard. </s><s>[INST] Yeah, which. If to work hard. [/INST] Yes, yes. To avoid the stigmatization that is imposed by affirmative action. But is that stigma there? Yes, it's there. It is there. I'll tell you another way in which it comes up from a student's point of view. I'll never forget this. It was in my second year of law school. It was in tax class. We had a very famous tax teacher, wonderful tax teacher, on the very first day of class, Professor Bitker, wonderful man, wonderful teacher, Boris Bitker, called on. The very first person he called on was a black student. I remember this as if it were yesterday. Called on a black student, and it was a black woman student. And I remember when he called on her, I remember just I felt as if the room got quieter, really. I felt as if the room got quieter, and I know there was a real tenseness within me. He didn't call on me, because he was calling on somebody else. Was a black woman student and I felt different. I felt as if I was, I felt as if I was somehow at issue. I felt as if my place, I felt as if my status was some small degree at issue. In the positive direction of the negative. Just, at issue. At issue. </s><s>[INST] And so, now all of this is. [/INST] At issue. It's happening really quickly. He calls on the student. This is, you know, happening like, in seconds. Yeah. And she responded. And she responded really strongly. It was clear she, he asked her a question. She answered the question. She answered the question, you know, beautiful. I mean, you know, very strong, comprehensive, wonderful response. Now you might say, okay, well, you know, smart student. Okay, fine. Next. After class, after class, I went up to her. And I clearly remember this. I said, that was great. Thank you. Why? Because a black student, predominantly white institution, Yale Law School. And I felt some of the, again, you know, affirmative action. I felt some of the burden of this affirmative action stigma. </s><s>[INST] So it was almost like a thank you for showing [/INST] that we belong here. Yes. Perfect. Boom. Yes. That's exactly what the situation. And by the way, I looked, I wasn't the only one. It, well, I wasn't being idiosyncratic. I wasn't the only one. There weren't me black people in that class, but per all of us. And we laughed about it later. We laughed about it, but that was there, there. So there's, there's the stigma issue. And some people have made a lot of this. Some people have really made a lot of the stigma issue. My attitude towards a stigma issue. Yeah, it's there. It's, you know, again, it's, it's part of, you know, it's part of the situation, but I think that the benefits outweigh the burdens, but is that a burden? Yeah, that's a burden. What are some others? Resentment, resentment in society. And that's a, you know, so in these, in the fancy schools, and by the way, you know, remember when we're talking about affirmative action, most colleges and universities in the United States, there, there is no affirmative action issue because they're not selective. Hell, they'll take anybody who, you know, if you can pay, come on in. It's only a fairly small set of schools that are selective. But of course, those are the most elite schools. Those are the schools that people most want to get into. And that's one of the reasons why we have all this, you know, fighting over those schools. Now, you know, there's a whole, how many millions of people are there in America who have applied to various places? They didn't get in. And what do they say? The white person who applied to Harvard, applied to Yale, applied to Columbia, you know, applied to Georgetown, applied to NYU, you know, didn't get in. What did they say? I would have gotten it hadn't been for that racial affirmative action. They're resentful. Well, you know, should they be resentful? No, they shouldn't be resentful, but they are resentful. Does that have a consequence? Yeah, it has a consequence. It has a consequence on how they act towards other people. It has a consequence on how they vote. It has a consequence. And, you know, that's, that's something. Um, are there other things? Yeah. And, you know, in my book, I, I have a, you know, I go through various, um, I think that, uh, I think that there is a, I think that there is a certain sort of denialism that has accompanied the affirmative action debate. So because, you know, black people like myself want to avoid the stigmatizing burden of affirmative action. There's some people who to deal with that have said, Oh, actually there is no difference between, you know, the beneficiaries of affirmative action and the other kids, there is no difference. Um, if, if the affirmative action kids got, let's say a 500 and the other kids got a 750, uh, that doesn't make any difference. That's just BS there. You know, the only reason the kid who, you know, the 550 kid didn't get 750 is because the test asks all sorts of, you know, biased, culturally biased things like, you know, what is a yacht? Well, sorry. Uh, yes, there is a difference. There's a 200 point difference. Does the difference matter? Yes. The difference matters. And by the way, if you don't know what a yacht is, you can know what a yacht is without owning a yacht. Okay. And there's this denialism that I think has really seeped into not just the, you know, and into various conversations. That can have a slippery slope effect as beyond just this, this. Yes. And, you know, we see it in various ways. So, you know, this, this, you know, this attack on testing. It's not like I'm holding the, you know, uh, you know, some tests are not good tests. I think we should be skeptical of everything, but there are a lot of tests that yeah, they tell us something. All right. They tell us who knows what other, um, there's some people who are really, you know, dead set against testing because they're dead set against anything that might show a gap. Well, I think by the way, you know, are there gaps? Yeah, there are gaps. And what we need to do is be cognizant of those gaps and do things to make it so that if there's a gap, if you're, if you're deficient, no, no shame in being deficient, heck I'm deficient about a lot of things let's, you know, let's learn so that I catch up, but others, you know, but I think sometimes there've </s><s>[INST] been people who've been afraid of even acknowledging the gaps. Of course, there's, uh, I guess a colleague of yours, Michael Sandel, with, uh, with tyranny and merit, there's, uh, interesting, rigorous ways to kind of challenge ways on the flip side of that where obsessing with merit can go wrong also. [/INST] Yes. Uh, you mentioned Michael Sandel. He's a, uh, a wonderful colleague and he's a wonderful friend. I've known him a long time. I think he makes very important, uh, arguments, uh, about, uh, meritocracy. Um, I disagree with, uh, some of the points that he makes about meritocracy. You lean towards the, the importance of meritocracy. I think that, uh, yes. I think that, I think that there are values and meritocracy extremely important that in fact, you know, the, the, the movement from, you know, feudalism, the movement from status, the, the, the, the idea of, you know, I don't care who your father or mother was. I don't care from what part of town you come from. I don't care what your last name is. I don't care what your skull or of your skin is. Show me what you can do. And then somebody sits down. Ok, I'll show you what you can do. You know what I can do and they show it you're in. I think there's a lot to that and you know, the impulse, the sentiments behind that I resonate with that. I think that there's a lot there. What I want to do is I want to get rid of those features in society that deprive people of the, what you need to develop yourself, you know, sometimes those are psychological. Sometimes that's you know, you're not around people who've done things that give you the idea that you can do things. I want to get rid of that, but the idea of, you know, people. Um, the idea, by the way of a- uh, you know, distinguishing, you know, this is excellent and the people who are excellent, you know, they're here. And then there are people who are, are they excellent? No, they're not excellent. They're good. Uh, I wouldn't, I wanna, I'm not gonna, you know, close my </s><s>[INST] eyes to that distinction. And, uh, uh, highlight that distinction and yet at the same time, maintain a sense that, uh, their basic worth as a human being is equal. [/INST] Yes. So, uh, you know, uh, was it run BMC? What are the rap groups? No, you know, we're all written down on the same list. We're all written down on the same list. Yes. We're, you know, uh, so I want to recognize our fundamental humanity. Um, I don't think that that, I think that one can recognize our fundamental humanity and one can also recognize as far as I'm concerned that, um, we all collectively should make sure that we, we do all that we can to prevent people from sinking below a certain level and being, you know, in misery, um, you know, all for that, but I want to be careful about some of the attacks that I hear on meritocracy. So some of the people, including again, I have all the respect in the world for, for, for, for, for, for Michael Sandelli to, you know, it talks about the, the, the arrogance of the winners. Okay. I want to be, you know, I, I don't want the winners to be arrogant. That's right. Luck has a lot to do with things. You know, you were, you, you didn't have any control over the circumstances in which you were born in two. You were lucky that you were born healthy and that you were born with a, you know, well-working mind. You didn't have anything to do with that. That was pure luck. There's some people who don't have that walk. So don't, you know, you know, don't be, you know, Mr. Big stuff, okay. So I'm, you know, I'm against that sort of arrogance. You know, I'm entitled as if, as if I taught myself how to read. No, you didn't teach yourself how to read. There was people who did all sorts of things for you and you don't even know it. Okay. So, you know, I want to, you know, get rid of the arrogance, uh, have, have decent humility on all for that at the same time, you know, um, I want to be careful about the problem of envy. I want to be prob, I want to be careful about the problem of resentment. I want to be, I want to be careful about, you know, I've heard, you know. So let's not have, let's not give a trophy to the person who wins the race. Because to give a trophy to, to the person who wins the race will make the person who they defeated feel bad. No, no, no. No, no, no, I don't want that. I want to give a trophy to the person who wins the race because I think it's a good thing to valorize the best. </s><s>[INST] Yeah. It's a, it's a kind of celebration of, um, this whole human project that we're on. Yes. It's celebrating the best. You mentioned your father several times, so let me just linger on that. What, uh, what have you learned from, what have you learned about life from your father? [/INST] There's, I've been just such a lucky person. I mean, I, I feel like I've just lived an absolutely charmed life. And I live, I mean, the work that I do is what I love doing. Um, I would pay to do what I am paid to do. </s><s>[INST] Yeah. [/INST] I mean, it's, it's, you know, it's, it's great. And, um, I've been, I've been fortunate in so many ways. And one way in which I've been fortunate is, uh, my parents, my parents, um, Rachel Spann Kennedy, Henry Harold Kennedy, my mother born in Columbia, South Carolina. My father from, uh, uh, New Orleans, Louisiana, they were refugees from the Jim Crow South. Uh, they were people who put their all into their children. Um, I have an older brother of a younger sister. All three of us know beyond, you know, beyond any controversy that we were loved and dearly loved by our parents and they were great people. My father, um, very interesting man, very independent minded. He was perfectly willing to go his own way. And, uh, I learned much from him, including I learned, I learned things from him, even when I ultimately disagreed with him. So for instance, again, to go back to his pessimism. Yeah, he was pessimistic, thoroughly pessimistic. Um, but he was also, he was also willing to change in certain ways. In fact, both my parents, I mean, one of the most important things that happened to my parents was that I'd say when I was, let's say 10 years old, I was born in 1954. So in 1964, in 1964, I think my parents would have taken the position that, um, you definitely never under any circumstances trust a white person. If a black person trusts a white person, that person is a fool. Do not trust white people. All right. They are not to be trusted. And, um, it's the highly, highly, highly unusual one who is not prejudiced. Okay. So white people are not to be trusted and, you know, by and large are going to be your enemy. All right. So let's just face that. That's, that's was their, their point of view. I'd say that, I'd say that 10 years later, that point of view had been leavened somewhat. Um, I think, and you know, you say, well, what happened in those 10 years? Well, certainly in my life, uh, one of the things that happen in those 10 years is I, I was a student in various schools and I had a series of teachers. I've had wonderful black teachers. I've also had wonderful white teachers and my parents paid attention to who my teachers were and how my teachers treated me. And I think that they were affected by the way in which there were white people who really helped me and were on my side and were thoroughly on my side. And I think that that experience, uh, changed my parents in their general view. They, you know, skeptical. Yeah, but they were, um, the, the, the, the possibility, the possibility of a white person genuinely being the friend of a black person that they, they, they, that became alive to them and I give them a lot of credit because they were, they were adults and, you know, for an adult to change, that's a big deal, but </s><s>[INST] my, my parents did change in that transformation that was inspiring to [/INST] you was formative to you in terms of joining the optimist camp, hugely. And, you know, uh, the, the, the school, I mean, I, I, again, you know, I said a moment ago, how lucky I've been, heck, um, I teach it, I teach at Harvard law school, I attended, I ended Balliol college, Oxford. I got my law degree from Yale law school. I got my undergraduate degree at Princeton university. Those are some pretty good schools. They all were, they all were the most important school. However, that I attended the school that made the most difference in my education was my high school, St. Albans school for boys and at St. Albans I encountered a cadre of teachers. And by the way, uh, St. Albans when I went to St. Albans all these teachers were white, all of these teachers. There was one, the, the, the, the, the head of athletics, very important man, very impressive man, Brooks Johnson, was black. Otherwise white teachers. And these teachers made a huge difference in my life. And, you know, I can call their names, boom, boom, boom, boom, boom. The greatest of them all was a man by the name of, um, Jack McKeown. Yeah. We called him gentlemen, Jack, gentlemen, Jack McKeown. And, um, what subject did he teach? He taught me, uh, history. He was my advanced placement history teacher, but, um, John F. McKeown and we shared a birthday. Um, John F. McKeown was a fabulously good teacher and we developed a deep lifetime friendship. I was with Mr. McKeown the day before he died and, um, you know, he was a white man and, um, I've had other teachers who've some of whom have become colleagues of mine. Uh, you know, Sanford Levinson Sanford Levinson was a teacher of mine at Princeton. Uh, he's become a colleague of mine. I mean, it would be, frankly, it would be impossible for me to, you know, I hear P I can't make some sort of, you know, sort of blanket condemnation of white people with Sandy Levinson in my life. Well, John F. McKeown in my life with Eric Foner in my life with my colleague Martha Minow in my life, my colleague Cass Sunstein in my life, impossible. </s><s>[INST] You know, that speaks to the power of teachers and mentors. [/INST] Oh yeah. </s><s>[INST] And you're that to a lot of people. [/INST] Well, I, I've, I've taken that to, I hope, I hope, listen, I would be, I would listen, I would be absolutely overjoyed if there was a student who thought of me in the way that I think of gentlemen, Jack McKeown, if there, if, if, if that's the case, eat just one, just one, if that's the case, I'm overjoyed. </s><s>[INST] That's a, that's a life well-lived. What do you think, uh, of Martin Luther King's, uh, I have a dream. [/INST] You still share that dream? I think that Martin Luther King juniors, I have a dream speech is one of the great speeches, not only in American history, but in the history of the world. You know, there's, there's a tendency now for people to sort of poo poo that speech. Um, I think unfortunately the speech, you know, has been embraced by, you know, you know, advertisers and corporate America. It's been, it's been so, you know, it's, it's been, it's been heard so many times that it, it's sort of has been made to suffer from what some people might view as overexposure. </s><s>[INST] It's so unfortunate. I mean, uh, it's too bad. Well, when, uh, especially when Hollywood rolls in, they did that with, uh, John Lennon's Imagine, uh, recently, uh, which I think is one of the greatest songs ever, and the actors and actresses ruined it by trying to like sing along [/INST] and do this kind of cliche Hollywood thing, uh, recently, uh, recently thing. It has, but people have tried to make it into a cliche. The fact of the matter is it's the, the, the sentiment, the sentiment behind, I have a dream. Yeah, I'll associate myself with that. And anybody wants to, anybody wants to see some great oratory go watch a watch. And, um, and, um, you know, Martin Luther King Jr. I mean, he, he gave, he gave, you know, several great speeches, you know, his first speech. The first speech that he gave as a civil rights leader, the Holt street Baptist church, 1955, at the beginning of the Montgomery bus boycott, which was virtually an ex-temporaneous speech was one of his greatest. And he was, he was, I think 26 years old, great. His last speech, you know, his mountaintop speech, great speech, but I have a dream. I love it. Um, I will associate myself with those sentiments any day of the week. </s><s>[INST] Absolutely. So you still have hope for, um, a deep kind of, uh, multiracial, [/INST] a deep unity in the 24th century. I have that hope. And I think that the, I think the sentiments that Martin Luther King Jr. expressed in August, 1963, that represents the best of American life. And, um, I think it's a, you know, do I want to see that come to pass? Yeah. I want to see that come to pass and we'll, we'll work to, you know, push </s><s>[INST] that project along as far as it'll go. Well, thank you for carrying his spirit of optimism forward, uh, the spirit of your mother and father. Uh, thank you for all the amazing work you've done and thank you for just this conversation is a huge honor. This is awesome. I really. [/INST] Thank you, Randall. </s><s>[INST] Thank you. Thanks for listening to this conversation with Randall Kennedy to support this podcast, please check out our sponsors in the description. And now let me leave you with some words from Martin Luther King Jr. Darkness cannot drive out darkness. Only light can do that. Hate cannot drive out hate. Only love can do that. Thank you for listening and hope to see you next time. [/INST] </s>
<s>[INST] but you can also trust, I mean this is the difference between Reddit anonymity where you can easily create multiple accounts when you have only one account per person or at least it's very difficult to create multiple accounts then you can trust that the anonymous person you're talking to is a human being not about I try to be completely un anonymous. Uh now in my public interactions, I try to be as real in every way possible. Like zero gap between private me and public me. [/INST] Why exactly did you? It seems like this is an intentional mission. What made you want to sort of bridge that gap between the private sphere and public sphere because that's that's unique. I know a lot of intellectuals who would make a different decision. </s><s>[INST] Yeah, interesting. I had a discussion about what novel about this actually, when with with a few others that have a very clear distinction between public and private, [/INST] something I'm struggling with by the way personally and thinking about Mhm. </s><s>[INST] Mhm. So one on the very basic surface level is uh if you carry with yourself lies, small lies are big lies. It's extra mental effort to remember what you are like to remember what you're supposed to say. I'm not supposed to say. So that's on a very surface level of like, it's just easier to live life when you have the smaller the gap between the private you and the public you and the second is I think for me from an engineering perspective, like if I'm dishonest with others, I will too quickly become dishonest with myself and in so doing I will not truly be able to think deeply about the world and come up and build revolutionary ideas. There's something about honesty that feels like it's that first principles thinking that's almost like over used as a term. But it feels like that requires radical honesty, not radical asshole englishness, but radical honesty with yourself, with yourself. And I feels like it's difficult to be radically honest with yourself when you're being dishonest with the public. And also I have a nice feature honestly that um, in this current social context so we can talk about race and gender and uh, what are the other topics that are touchy [/INST] Felicity and um, nationality, </s><s>[INST] all those things? I mean like family structure, maybe I'm in eloquent in the way I speak about them, but I honestly when I look in the mirror, like I'm not deeply hateful of a particular race or even just hateful particular ways, um I'm sure I'm biased and I tried to like think about those biases and so on and also I don't have any creepy ship in my closet for women, like I haven't done, it seems like everybody, uh it seems like a lot of people got like did a lot of creepy stuff in their life and I just feel like that's really nice and deliberating and especially now, you know, it's funny because I've gotten a bit of a platform and uh I think it all started when I went, there's a Miss comedian, female comedian Whitney cummings and you know, I've gotten a lot of amazing women writing me throughout, but when I went on Whitney is like the number of DNS again on instagram for women. It's just ridiculous. And uh, I think that was a really important moment for me is like I speak and I feel, you know, I really value love long term monogamy with like one person and it's like I could see where a lot of guys would now continue that message in public and in private, just start sleeping around. And so like that's an important statement from you mentally. He's like, [/INST] nope, straight narrow. It just goes </s><s>[INST] straight and not out of fear, but out of like principal and just like live life honestly. And I just, I feel like that's truly liberating uh, as a human being, forget public all that because then I feel like I'm a sturdy ground when I say uh, difficult things and at the same time, sorry, I'm ranting on this, apologize, [/INST] I'm interested personally and stuff gone. </s><s>[INST] I, I honestly believe in the internet and people on the internet that when they hear me speak, they can see if I'm full of sh it or not. Like I won't be able to fake it. Like they will see it through. Uh, yeah, so I feel like if you're not lying about stuff, you have the freedom to truly be yourself and the and the internet, we'll figure it out. We'll figure who you are. [/INST] People have a natural tendency to be able to tell bullshit it makes sense from an evolutionary standpoint. Exactly. Like why, why would why, like, of all the things that we could evolve to be good at being able to detect honesty seems like one that would be particularly valuable, especially in the sorts of societies we developed into. </s>
<s>[INST] Thanks for listening to this conversation with Nicb Ostrom and thank you to our presenting sponsor cash app. Please consider supporting the podcast by downloading cash up and using code lex podcast. If you enjoy this podcast, subscribe on Youtube, review it with five stars on Apple podcast supporter on Patreon are simply connect with me on twitter Elex Friedman and now let me leave you with some words from Nicb Ostrom. Our approach to existential risks cannot be one of trial and error. There's no opportunity to learn from errors. The reactive approach. See what happens, limit damages and learn from experience is unworkable. Rather, we must take a proactive approach. This requires foresight to anticipate new types of threats and a willingness to take decisive preventative action and to bear the costs, moral and economic of such actions. Thank you for listening and hope to see you next time. [/INST] </s>
<s>[INST] wow, we covered a lot of ground and we're left with one of my favorite lines and there's many which is happiness is a cookie that brain begs itself. It's been a huge honor and a pleasure to talk to you. I'm sure our paths will cross many times again josh, thank you so much for talking today. Thank [/INST] you lex. It's so much fun. I enjoyed it, </s><s>[INST] awesome. Thanks for listening to this conversation with Yoshi back and thank you to our sponsors Express VPN and cash up. Please consider supporting this podcast by getting Express VPN at Express VPN dot com slash lex pod and downloading cash up and using collects podcast. If you enjoy this thing, subscribe on Youtube, review it. Five stars on apple podcast supported on patreon are simply connect with me on twitter Alexis Friedman and yes, try to figure out how to spell it without the E and now let me leave you with some words of wisdom from your shabak. If you take this as a computer game metaphor, this is the best level for humanity to play and this best level happens to be the last level as it happens against the backdrop of a dying world, but it's still the best level. Thank you for listening and hope to see you next time [/INST] </s>
<s>[INST] It might even be worthwhile to step back and uh talk about electricity and circuits and how circuits work. Before we talk about super [/INST] conductivity? </s><s>[INST] How does the computer work [/INST] Jeff? Well, I won't go into everything that makes a computer work. But let's talk about the basic building blocks. A transistor. So, and even more basic than that semiconductor material. Silicon say. So uh in silicon silicon is a semiconductor and what that means is at low temperature there are no free charges, no free electrons that can move around. So when you talk about electricity, you're talking about predominantly electrons moving to establish electoral currents and they move under the influence of voltages. So you apply voltages, electrons move around. Those can be measured as currents and you can represent information in that way. So, semiconductors are special in the sense that they are really malleable. So if you have a semiconductor material, it you can change the number of free electrons that can move around by putting different elements. Different atoms in lattice sites. So what is the lattice site? Well, a semiconductor is a crystal, which means all the atoms that comprise the material are at exact locations that are perfectly periodic in space. So if you started anyone adam and you go along the what are called the lattice vectors, you get to another atom and another atom and another atom. And for high quality devices it's important. That is a perfect crystal with very few defects. But you can intentionally replace a silicon atom with say a phosphorus atom. And then you can you can change the number of free electrons that are in a region of space that has that excess of what are called opens. So picture a device that has a left terminal and a right terminal. And if you apply a voltage between those two, you can cause electrical current to flow between them. Now we add a third terminal up on top there and depending on the voltage between the left and right terminal and that third voltage, you can you can change that current. So what's commonly done in digital electronic circuits is too leave a fixed voltage from left to right and then change that voltage that's applied at what's called the gate, the gate of the transistor. So, um what you do is you you make it to where there is an excess of electrons on the left, excessive electrons on the right and very few electrons in the middle and you do this by changing the concentration of different doping in the lattice spatially. And then when you apply a voltage to that gate, you can either cause current to flow or turn it off. And so that's sort of your zero and one. You if you apply voltage current can flow, That current is representing a digital one. And uh, from that, from that basic element, you can build up all the complexity of digital electronic circuits that have really had a profound influence on our society. </s><s>[INST] You're talking about electrons. Can you give a sense of what scale we're talking about when we're talking about in silicon being able to mass manufacture these kinds of gates? [/INST] Yeah, so scale in a number of different senses. Well, at the scale of the silicon lattice, the distance between two atoms there is half a nanometer. So, um, people often like to compare these things to the width of a human hair. I think it's some six orders of magnitude smaller than the width of a human hair. Uh, something on that order so remarkably small. We're talking about individual atoms here and electrons are of that length scale when they're in that environment. But there's another sense that scale matters in digital electronics. This is perhaps the more important sense, although they're related scale refers to a number of things, it refers to the size of that transistor. So for example, I said you have a left contact or right contact and some space between them where the the gate electrode sits, That that's called the channel with or the channel length. And what has enabled what we think of as moore's law or the continued increased performance in silicon microelectronic circuits is the ability to make that size that feature size ever smaller, ever smaller at a a really remarkable pace. I mean that that feature size has decreased uh consistently every couple of years for the since the 1960s. And that was That was what more predicted in the 1960s. He thought it would continue for at least two more decades and it's been much longer than that. And so um that is why we've been able to fit ever more devices ever more transistors ever more computational power on essentially the same size of chip. So a user sits back and does essentially nothing. You're running the same computer program. But those devices are getting smaller so they get faster, they get more energy efficient and all of our computing performance just continues to improve. And we don't have to think too hard about what we're what we're doing as, say, a software design or something like that. I absolutely don't mean to say that there's no innovation in software that the user side of things. Of course there is. But from from the hardware perspective, we just have been given this gift of continued performance improvement through this scaling that is ever smaller feature sizes with very similar um say power consumption. That power consumption is has not continued to scale in the most recent decades. But nevertheless we had a really good run there for a while and now we're down to gates that are seven nanometers which is state of the art right now. Maybe globalfoundries is trying to push it even lower than that. I can't keep up with where the predictions are that is going to end but seven nanometer uh seven nanometer transistor has just just a few tens of atoms along the length of the conduction pathway. So a naive semiconductor device physicists would think you can't go much further than that without some kind of revolution in the way we think about the physics of our devices. </s>
<s>[INST] wow. [/INST] And then uh the friend said let's make sure next time we have helmets, </s><s>[INST] but [/INST] it's also you know, I'm happy that nothing happened to me. It could have been the case that I I lost telling bar. So yeah, </s><s>[INST] but that's childhood uh of an engineering mind with a strong reward signal of an explosion. I love it. My there's some aspect of chemists, the chemistry, like my dad with plasma chemistry, plasma physics, he was very much into explosives to it's a worrying quality of people that work in chemistry that they love. I think it is that exactly is the strong signal that the thing worked? [/INST] There is no doubt </s><s>[INST] there's no doubt there's some magic. It's almost like a reminder the physics works that chemistry works. It's cool. It's almost like a little glimpse at nature that you yourself engineer. I that's why I really like artificial intelligence, especially robotics, is you create a little piece of nature [/INST] and in some sense, even for me with explosives, the motivation was creation rather than destruction. </s><s>[INST] Yes, exactly. In terms of advice, I forgot to ask about just machine learning and deep learning for people who are specifically interested in machine learning. How do you recommend to get into the field. [/INST] So, um, I would say rain plan and everything and also there is plenty, of course is </s><s>[INST] so like from scratch [/INST] and so on different levels of abstraction in some sense, but I would say Ray implement something from scratch, implement, something from a paper, rain clement, something you know from podcast that you have heard about, I would say that's a powerful way to understand things. So often the case that you read the description and you think you understand, but you truly understand once you build it, then you actually know what really method in the description. </s><s>[INST] Is there a particular topics that you find people just fall in love with? I've seen Mhm. I tend to really enjoy reinforcement learning because it's it's much more it's much easier to get to a point where you feel like you created something special like like fun games kind [/INST] of things that reward. I think </s><s>[INST] it's rewarding. Yeah. Uh as opposed to like re implementing from scratch more like supervised learning kind of things. It's [/INST] yeah, so you know, if if someone would optimize for things to be rewarding, then it feels that the things that are somewhat generative, they have such a property. So if you have for instance adversarial networks or you have just even generated language models and you can even see um internally we have seen this thing with our releases, so we have uh we released recently two models, there is one model called dolly that generates images and there is other model called clip that actually uh you provide various possibilities. What could be the answer to what is on the picture and it can tell you which one is the most likely. Mm And in some sense, in case of their first one dolly, it is very easy for you to understand that actually there is magic going on. And in the case of the second one, even though it is insanely powerful. And you know, people from vision community, they as they started probably get inside. They actually understood uh how far it goes. It's difficult for a person at first to see uh how well it works and that's the same as you said, that in case of supervisor, any models you might not kind of see or it's not that easy for you to understand the strength. </s><s>[INST] Even though you don't believe in magic to see the magic, that magic. It's a generative that's really brilliant. So anything that's generative because then you are at the core of the creation, you get to experience creation without much effort unless you have to do it from scratch. [/INST] But and it feels that you know, humans are wired. There is some level of reward for creating stuff. Like of course different people have a different weight on this reward. Yeah. </s><s>[INST] In the big objective function. That big objective fact of a person of a person. Uh you wrote that beautiful is what you intensely pay attention to. Even a cockroach is beautiful. If you look very closely, can you expand on this? What is beauty? [/INST] So what I'm I wrote here actually corresponds to my subjective experience that I had through extended periods of meditation. It's it's pretty crazy that at some point, the meditation gets you to the place that you have really increased uh focused, increased attention. And then you look at the very simple objects that were all the time around. You can look at the table around the pen or at the nature and you notice more and more details and it becomes very pleasant to look at it. And if the ones again, it kind of reminds me of my childhood, uh like a just pure joy of being. It's also I have seen even the reverse effect that by default, regardless of what we possess. We very quickly get used to it. And you know, you can have a very beautiful house. And uh if you don't put sufficient effort, you're just gonna get used to it and it doesn't bring any more regardless of what you have. Yeah, </s>
<s>[INST] just a sauna of sorts. [/INST] Yeah, yeah. You go there, you know, you feel refreshed after you come back, you know, but </s><s>[INST] if you stay there, I mean, so, okay, I take that as an assumption, this is a philosophical question, that a biological one. So you have a life that develops under these extremely hot conditions. [/INST] So let's see so much of the early evolution of mankind was driven by exploration, right? And the kind of interest and stars originated in part as a tool to guide that exploration. Right? I mean, that in itself, I think it would be a huge, you know, huge differential in the way that we, you know, our our evolution on this planet. </s><s>[INST] Yes. I mean stars, that's brilliant. So even in that aspect, but even in further aspects, astronomy just shows up Basically every single development in the history of science. Up until the 20th century, it shows up. So I wonder without that if we had would have if we would even get like calculus. [/INST] Yeah. Look, that's a great I mean, that's a great point. Newton in part developed calculus because he was interested in understanding explaining kepler's laws, right? In general, that whole mechanistic understanding of the night sky, replacing a religious understanding where you interpret, you know, this is, you know, this whatever fire God writing his, you know, a little chariot across the sky as opposed to, you know, this is some mechanistic set of laws that transformed humanity and arguably put us on the, on the course that we're on today, right? The entirety of the last 400 years and the development of kind of are technological world that we live in today was sparked by by that right, abandoning an effectively, you know, a non secular view of the natural world and, and kind of thing. Okay, this can be understood and if it can be understood, it can be utilized. We can create our own variants of this. Absolutely. We would be a very, very different species without astronomy. Um, this, I think extends beyond just astronomy. Right? There there are questions like why do we need to spend money on X where X can be anything like paleontology like, right, </s><s>[INST] The meeting patterns of penguins? [/INST] Yeah, that's like essential. That's right. Um, I think, you know, there's a tremendous under appreciation for the usefulness of useless knowledge. Right? I mean, uh, it's brilliant that I didn't come up with this, this was, there's a little book by uh, the guy who started the Institute for Advanced Studies, but um, You know, it's so true. So much of the electronics that are on this table, right, work on Maxwell's equations. Maxwell wasn't sitting around in the 1800s saying, you know, I hope one day, you know, uh, will make, you know, a couple mikes. So, you know, a couple of uh, you know, a couple of guys can have this conversation right? That there was no, at no point was that the motivation and yet, you know, it gave us the world that we have today and the answer is if you are a purely pragmatic person, if you don't care at all about the human condition, none of this, the answer is you can tax it right. Like useless things have been, have created way more capital than useful things. </s><s>[INST] And the sad thing, I mean, first of all, it's really important to think about and it's brilliant in the, in the following context like Neil Degrasse Tyson is this book about the role of military based funding in the development of science. And then so much of uh technological breakthroughs in the 20th century had to do with humans working on different military things. And then the outcome of that had nothing to do with military. It has some military application, but their impact was much much bigger than military [/INST] splitting of the atom is a kind of a canonical example of this. We all know that tragedy that arises from splitting of the atom and yet, you know, so much. I mean the atom itself does not care for what purpose it is being split. So </s><s>[INST] I wonder if if we took the same amount of funding as we use for war and poured it into like totally seemingly useless things like the mating patterns of penguins. We would get the internet anyway. [/INST] I I think so. I think so. And you know, perhaps more of the internet would have would have penguins, you know, so </s><s>[INST] we're both joking but in some sense like I wonder it's not the penguin because penguins is more about sort of biology, but all useless kind of tinkering and all kinds of, uh, in all kinds of avenues and also because military applications are often um burdened by the secrecy required. So it's often like so much, uh, the openness is lacking. And if we learned anything for the last few decades that when there's openness and science that accelerates the development of science, [/INST] that's right. That's true. The openness of science truly, you know, it benefits everybody the notion that if, you know, I share my science with you, then you're going to catch up and like know the same thing that is a short sighted because if you catch up and you open, you know, you discover something that puts me in a position to do the next step, right? It's just so I absolutely agree with, um, with all of this. I mean, uh, the kind of question of like military funding versus non military funding is obviously a complicated one. But at the end of the day, I think we have to get over the notion as a society that we are going to pay for this and then we will get that right. That's true. If you're buying like, I don't know, toilet paper or something, right? It's just not true in the intellectual pursuit. That's not how it works. And sometimes it will fail. Like sometimes like a huge fraction of what I do, right? I come up with an idea. I think it's great and then I work it out. It's totally not great fails. Immediately </s>
<s>[INST] Yeah, you know, I, I don't know if you're familiar with a philosopher named Ernest Becker, he wrote a book called denial of death and there's a few psychologists, Sheldon Solomon, I think he just spoke with him on his podcast who developed terror management theory, which is uh like Ernest Becker is a philosopher that basically said that uh um mortality, your mortality is at the core of it. Yeah. And so I I don't know if it's sounds compelling is an idea that we're all, I mean that all of the civilization have constructed is based on this, but it's [/INST] familiar with his work. Here's what I think, I think that yes, fundamentally the desire to survive is at the core of it. I would agree with that, but but how that expresses itself in your life ends up being very different. The reason you do what you do is, I mean, you could list the 100 reasons why you chose to write your tweet this way and that way, and it really has nothing to, with the survival part, it has to do with, you know, trying to impress fellow humans and surprise them and say something </s><s>[INST] so many things built on top of each other. But it's fascinating to think that in artificial intelligence systems, we want to be able to somehow engineer this drive for survival for immortality. I mean, because as humans, we're not just about survival. Were aware of the fact that we're going to die, which is a very kind of were aware like space [/INST] that </s><s>[INST] aren't [/INST] Confucius said uh he said, each person has two lives. The second one begins when you realize that you have just one. But but most people, it takes a long time for </s><s>[INST] most people to get there. I mean you could argue this kind of 40 something which Ernest Becker argues is they, it's they actually figured it out early on and the terror they felt was like the reason it's been suppressed and the reason most people, when I asked him about whether they're afraid of death, they basically say no. They basically say like um I'm afraid I won't get like submit the paper before I die. Like they kind of see they see death as a kind of inconvenient deadline for a particular set of like a book you're writing, It's as opposed to like what the hell? This thing ends at any moment. Like most people as if Evan counter do not meditate on the idea that like right now you could die, like right now, like it's like in the next five minutes it could be all over and you know, meditate on that idea. Um I think that somehow brings you closer to like the core of the motivations and the core of the human cognition my condition, [/INST] but like I said, it is not yeah, there's so many things on top of it, but it is interesting. I mean as the ancient poet said, uh death whispers at my ear live for I come. So it's it is certainly motivating when we think about that. Okay, I've got some deadline. I don't know exactly what it is, but I better make stuff happen. It is motivating, but I don't think, I mean, I know for just speaking for me personally, that's not what motivates me day to day, it's instead, oh, I want to get this, you know, program up and running before this, or I want to make sure my co author isn't mad at me because I haven't gotten this in. I don't want to miss this grant deadline or you know, whatever the thing </s><s>[INST] is, it's too, it's too distant in a sense. Nevertheless, it is good to reconnect, but for the Ai systems, none of that. Is there uh like a neural network does not fear its mortality. Uh and that that seems to be somehow fundamentally missing the point. [/INST] It's I think that's missing the point. But I wonder it's an interesting speculation about whether you can build an Ai system that is much closer to being a human without the mortality and survival piece. But just the thing of relevance. Just I care about this right now, if you have a robot roll into the room, it's gonna be frozen because it doesn't have any reason to go there versus there. It doesn't have any particular set of things about this is how I should navigate my next move because I want something. </s><s>[INST] Yeah. There's a that's the thing about humans is they seem to generate goals. They're like you said live wired. I mean it's very flexible in terms of the goals and creative in terms of the goals are generated when we enter a room, you show up to a party without a goal usually and then you figure it out along. [/INST] Yes. But this goes back to the question about free will, which is when I walk into the party, if you rewound it 10,000 times when I go and talk to that couple over there versus that person, like I might do this exact same thing every time because I've got some gold stack and I think, okay, well at this party I really want to meet these kind of people or I feel awkward or whatever, you know, whatever my goals are by the way. So there was something that I meant to mention earlier if you don't mind going back, which is this when we were talking about B. C. I. Um so I don't know if you know this, but when I'm spending 90% of my time doing now is running a company, do you know about </s><s>[INST] this? I I I wasn't sure what the company is involved in. [/INST] Right? So we'll talk about it. Yeah. Yeah. So when it comes to the future of BC I um you know, you can put stuff into the brain invasively. But my interest has been how you can get data streams into the brain non invasively. So I run a company called Neo sensory and what we build is this little um wristband, we've built this in many different factors. Yeah this is it and it's got these vibrate, Torrey motors in it. So these things as I'm speaking for example, it's you know, capturing my voice and running algorithms and then turning that into patterns of vibration here. So people who are deaf for example learn to hear through their skin, so the information is getting up to their brain this way and they learn how to hear. So it turns out on day one people are pretty good, like better than you would expect at being able to say, oh that's weird. It was that was that a dog barking? Was that a baby crying? Was that a door knock? A door bell. Like people are pretty good at it but with time to get better and better and what it becomes is a new quality a in other words a new subjective internal experience. So on day one they say whoa, what was that? Oh oh that was the dog barking. But by you know, three months later they say oh there's a dog barking somewhere, oh there's the </s>
<s>[INST] You've talked about this a little bit in the past, you kind of left the movie making business at an interesting time. Perhaps you saw the changes. Um, there's been a lot of excitement with netflix with tv. So the roll of film in society has changed. So what do you think is the future of movies versus tv? Like if you were as a business person, as a creator, as a consumer, as a technologist are thinking about the next 10, 20 years, what do you think is going to be the the godfather? The great Pieces that move us as a society in the next 10, 20 years is going to be TV? Is it going to be a movie? Is it going to be a tiktok uh clips? What is it? [/INST] Well, so I, and I, and I think the other category that I would add to that, that will be the next great medium is truly immersive, virtual reality, uh in which new storytellers will emerge, especially when you can go into VR and there's enough computing power to sustain it and to allow it to be social and, you know, for you to have different paths to go down. That'll be, I think the next realm of what storytelling and experience will will look like, </s><s>[INST] Do you think video game kind of world, or is it more movies, or is it more social network, or is it all of it kind of blending reality and gaming and movies? [/INST] Yeah, I thought uh if you saw Ready Player One, which I loved the book and and and the movie was cool too. But you know, that that's one version of it, right? Where you go in now, everybody's talking about the metaverse and all that, but you go into a world that's fully rendered as yourself and you interact with that world. The other side of it is to go in somewhere between being a passive observer, but being able to move around your point of view and experiences, which I think is interesting. And then I think another, another adventure, so to speak, I could think of is a blend of video games, so there's a mission, right? There's a there's obstacles, there's everything and you move through it, but it's immersive and it tells a story at the same time and that's why I think you're going to see new, amazing storytellers that we don't know yet that understand how to innovate and how to make you feel something in, in that environment. Um, And to your earlier point, you know, I saw probably around 2,015 when netflix decided to be bold, put out house of cards, put out all the episodes, leave you in charge of the pace at which you would view them uh which I thought was was great. </s><s>[INST] That's a gutsy move. [/INST] Yes, it was. And I can't tell you around Hollywood, anybody that says that everybody thought it was a great ideas not being truthful because everybody I talked to said this is they're idiots right there. What do they know about moviemaking and tv and what I saw happening was if you look at what netflix pulled off and they realized that there isn't really a moat around the studios, you really could make stuff. Um, and really good stuff. And so they started to create their own content that pulled in amazon, which pulled in google through youtube and, and then you had hulu, then you had Disney deciding that they're going to have Disney Plus and the next thing, you know, you have some of the, the biggest companies with the largest balance sheets on the planet being in the creative business, that's, you know, if you're an independent, that's, that's bringing a knife to a gunfight to be sure. And so, you know, I thought that was interesting. The other thing that it used to be, that movies were, where the big things happened and television was sort of, it is a small screen different experience. And you had something like game of Thrones come out which was not only in the same epic level visually and storytelling wise, but had the budget to be able to do it. And now I think you're you're seeing um you're seeing uh all kinds of different storytelling taking place and also like that, it's you're not pigeonholed into a time, like you've got two hours to tell the story, you can do a three part mini series, a five part mini series, you can do television, that's you know, all kinds of different format that I think is, it allows creators to do a lot more interesting things. </s>
<s>[INST] what kind of space. If you just intuitively think about the space of algorithms that that unlocks for us. So, there's a whole complexity theory around classical computers, measuring the running time of things and P so on. What kind of algorithms? Just intuitively do you think it's it unlocks for us. [/INST] Okay, so we know that there are a handful of algorithms that can seriously be classical computers and which can have exponentially more power. This is a mathematical statement. Nobody's exhibited this in the laboratory. It's a mathematical statement. We know that's true but it also seems more and more that the number of such things is very limited. Only very very special problems exhibit that much advantage for a quantum computer uh of standard problems to my mind as far as I can tell, the great power of quantum computers will actually be to simulate quantum systems if you're interested in a certain quantum system and it's too hard to simulate classically. You simply build a version of the same system, you build a version of it, you build a model of it that's actually functioning as the system. You run it and then you do the same thing, You would do that a quantum system. You make measurements on it. Quantum measurements on it. The advantage is you can run it much slower. You can see why bother. Why not just use the real system? Why not just do experiments on the real system? Well, real systems are kind of limited. You can't change them, you can't manipulate them, you can't slow them down so that you can poke into them. Uh you can't modify them in arbitrary kinds of ways to see what would happen if I uh if I change the system a little bit. So I think that quantum computers will be extremely valuable in in understanding quantum systems </s><s>[INST] at the lowest level of the fundamental laws. [/INST] They're actually satisfying the same laws as the systems that they're simulating. Okay, so on the one hand, you have things like factoring, Factoring is the great uh think of quantum computers factoring large numbers. That doesn't seem that much to do with quantum mechanics, it seems to be almost a fluke that that a quantum computer can solve the factoring problem in a short time. So and those problems seem to be extremely special rare and it's not clear to me that there's gonna be a lot of them. On the other hand, there are a lot of quantum systems, chemistry, there's solid state physics, there's material science, there's quantum gravity, there's all kinds of quantum quantum field theory and some of these are actually turning out to be applied sciences as well as very fundamental sciences. So we probably will run out of the ability to solve equations for these things. You know, solve equations by the standard methods of pencil and paper, solve the equations by the method of classical computers. And so what we'll do is we'll build versions of these systems, run them and run them under controlled circumstances where we can change them, manipulate them, make measurements on them and find out all the things we want to know. </s><s>[INST] So in finding out the things we want to know about very small systems right now, the is there something we can also find out about the macro level about? Something about the function, forgive me of our brain biological systems. The stuff that's about one m in size versus uh much much smaller. [/INST] Well what's all the excitement is about among the people that I interact with is understanding black holes, black holes. Black holes are big things uh there are many, many degrees of freedom. There is another kind of quantum system that is big. It's a large quantum computer and one of the things we've learned is that the physics of large quantum computers is in some ways similar to the physics of large quantum black holes. And we're using that relationship. Now. You asked you didn't ask about quantum computers or systems. You didn't ask about black holes. You asked about brains. </s><s>[INST] Yeah, well it's stuff that's in the middle of the [/INST] two, it's different. </s><s>[INST] So black holes are uh there's something fundamental about black holes that feels to be very different than the [/INST] brain and they also function in a very quantum mechanical way. Right, Okay. It is first of all unclear to me, but of course it's unclear to me. I'm not I'm not a neuroscientist. I have I don't even have very many friends who are neuroscientists. I would like to have more friends who are neuroscientists. I just don't run into them very often. Among the few neuroscientists I've ever talked about about this. They are pretty convinced that the brain functions classically that is not intrinsically a quantum mechanical system or it doesn't make use of the of the special features, entanglement, coherent superposition, are they? Right. I don't know. I sort of hope they're wrong just because I like the romantic idea that the brain is a quantum system but I think I think probably not the other thing. Big systems can be composed of lots of little systems. Okay materials, the materials that we work with and so forth are can be large systems, large piece of material. But they're big and they're made out of quantum systems now. One of the things that's been happening over the last good number of years as we're discovering materials and quantum systems which function much more quantum mechanically than we imagine. Topological insulators, this kind of thing, that kind of thing. Those are macroscopic systems but they just superconductors. Superconductors. I have a lot of quantum mechanics in them. You can have a large chunk of superconductor. So it's a big piece of material. On the other hand, it's functioning and its properties depend very very strongly on quantum mechanics. And to analyze them. You need the tools of quantum mechanics </s>
<s>[INST] I hope that's okay with you. [/INST] I love the </s><s>[INST] goal. Let's start with some hard questions. You called for quote thorough expert driven an objective inquiry into the origins of COVID-19. So let me ask, is there a reasonable chance that COVID-19 leaked from a lab? [/INST] I can't exclude that. I think it's fairly unlikely. I wish we had more ability to be able to ask questions of the chinese government and learn more about what kind of records might have been in the lab that we've never been able to see. But most likely this was a natural origin of a virus. Probably starting in a bat. Perhaps traveling through some other intermediate yet to be identified host and finding its way into humans </s><s>[INST] is answering this question within the realm of science. Do you think? Will we ever know? [/INST] I think we might know if we find that intermediate host. Um and there has not yet been a thorough enough investigation to say that that's not going to happen. Remember it takes a while to do this with SARS. It was 14 years before we figured out it was the Civet cat that was the intermediate host with murders. It was a little quicker to discover. It was the camel with SARS cov two. There's been some looking but especially now with everything really tense between the us and china. If there's looking going on, we're not getting told about it. </s><s>[INST] Do you think it's a scientific question or a political question. [/INST] It's a scientific question, but it has political implications. </s><s>[INST] So the world is full of scientists are working together. But in the political space in the political science space there's tensions. What is it like to do great science in a time of a pandemic? When there's political tensions, [/INST] it's very unfortunate Pasteur said science knows no one country he was right about that. My whole career in genetics especially has dependent upon international collaboration between scientists as a way to make discoveries, get things done. Scientists by their nature like to be involved in international collaborations. The human genome project for heaven's sake. 2400 scientists in six countries working together. Not worrying who is going to get the credit giving all the data away. I was the person who was supposed to keep all that coordinated. It was a wonderful experience and that included china that was sort of their first real entry into a big international big science kind of project and they did their part. It's very different now </s><s>[INST] continue on the line of difficult questions. Um Especially difficult ethical questions. In 2014, us put a hold on gain of function research in response to a number of laboratory by security incidents including Anthrax, smallpox and influenza In December 2017, NIH lifted this ban because quote gain of function research is important in helping us identify, understand and develop strategies and effective countermeasures against rapidly evolving pathogens that pose a threat to public health. All difficult questions have arguments on both sides. Can you argue the pros and cons of gain of function research with viruses? [/INST] I can and first let me say this term gain of function is causing such confusion that I need to take a minute and just sort of talk about what the common scientific use of that term is and where it is very different when we're talking about the current oversight of potentially dangerous human pathogens. As you know in science, we're doing gain of function experiments all the time. We support a lot of cancer immunotherapy at NIH right here in our clinical center there are trials going on where people's immune cells are taken out of their body treated with a genetic therapy that revs up their ability to discover the cancer that that patient currently has maybe even at stage four and then give them back as those little ninja warriors go after the cancer and it sometimes works dramatically. That's a gain of function. You gave that patient again and their immune function that may have saved their life. So we gotta be careful not to say, oh gain of function is bad. Most of what we do in science. That's good, involves quite a bit of the hat and we are all living with gains of function every day. I have a gain of function because I'm wearing these high glasses, otherwise I would not be seeing you as clearly I'm happy for that gain of function. So that's where a lot of confusion has happened. The kind of gain of function which is now subject to very rigorous and very carefully defined oversight is when you are working with an established human pathogen that is known to be potentially causing a pandemic and you are enhancing or potentially enhancing its transmissibility or its virulence. We call that E. P. P p enhanced potential pandemic pathogen that requires this very stringent oversight worked out over three years by the National Science Advisory Board on biosecurity. That needs to be looked at by a panel that goes well beyond NIH to decide are the benefits worth the risks in that situation. Most of the time, it's not worth the risk. Only three times in the last three or four years have experiments been given permission to go forward. They were all in influenza. So I will argue that if you're worried about the next pandemic, the more you know about the coming enemy, the better chance you have to recognize when trouble is starting. And so if you can do it safely studying influenza or coronavirus is like SARS MERS and SARS Cov two would be a good thing to be able to know about. But you have to be able to do it safely because we all know lab accidents can happen. And I mean look at SARS where there have been lab accidents and people have gotten sick as a result. We don't want to take that chance unless there's a compelling scientific reason. That's why we have this very stringent oversight. The experiments being done at the Wuhan Institute of virology as a sub award to our grant to Echo Health in new York did not meet that standard of requiring that kind of stringent oversight. I want to be really clear about that because there's been so much thrown around about it. Was it gain of function Well in the standard use of that term that you would use in science in general you might say it was. But in the use of that term that applies to this very specific example of a potential pandemic pathogen. Absolutely not. So nothing went on there that should not have happened based upon the oversight. There was an instance where the grantee institution failed to notify us about the result of an experiment that they were supposed to tell us where they mixed and matched some viral genomes and got a somewhat larger viral load as a result. But it was not E. P. P. P. It was not getting into that zone. That would have required this higher level of scrutiny. It was all bat viruses, these were not human pathogens. </s>
<s>[INST] It's an amazing place and it's a but there's different trajectories you can take. Yeah and like and that has to do with a lot of things including um does it is it stays even if we talk about robotics it could be the capital of the world in robotics. Um but currently if you want to be doing the best A. I work in the world you're gonna go to google or facebook um or Tesla or Apple or so on. You're not gonna be, you're not gonna be an M. I. T. So that that has to do, I think that's basically has to do with um not allowing the brilliance of the researchers to flourish. [/INST] Yeah. People say it's about money but I don't think it's about that at all. Like sometimes you have more freedom and can work on more interesting things and companies that's really where they lose people. </s><s>[INST] Yeah and some the freedom in all in in all ways which is why it's heartbreaking to get like people like Richard Stallman, there's such an interesting line because like Richard Stallman gigantic weirdo. That cross lines you shouldn't cross right? But we don't want to draw too many lines. This is the tricky thing. [/INST] There are different types of lines in my opinion. </s><s>[INST] But yes, your opinion, you have strong lines, you hold two. But then if administration listens to every line, there's there's also power in drawing a line like and there's, it becomes like a little drug you have to find the right balance licking somebody's arm is never appropriate. I think the biggest aspect there is not owning it learning from it growing from it from the perspective installment or people like that uh back when it happened like understanding seeing the being empathetic, seeing the fact that this was like totally inappropriate. Like not one that particular act but everything that led up to it to [/INST] no, I think there are different kinds of lines. I think they're like so Stallman crossed lines that essentially excluded a bunch of people and created an environment where we, their brilliant minds that we never got the benefit of because he made things feel growth or even unsafe for people. There are lines that you can cross where you're challenging an institution to like, I don't think he was intentionally trying to cross a line or maybe he maybe didn't care there are lines that you can cross intentionally to move something forward or to do the right thing. Like when it was like you can't put an all gender restroom in the media lab because like something permits whatever and Joey did it anyway, that's the line you can cross to make things actually better for people. And the line you're crossing is some arbitrary stupid rule that people who don't want to take the risk or like </s><s>[INST] yeah, for [/INST] sure. Ultimately, </s><s>[INST] I think the thing you said is like cross lines in a way that doesn't uh alienate others. So like for example, me wearing, I started for a while wearing a suit often at M. I. T. Which sounds counterintuitive, but that's actually um people always looked at me weird for that M. I. T. Created this culture, specifically the people I was working with, Like nobody wore suits. Don't [/INST] trust, </s><s>[INST] don't trust the suits. I was like, fuck you, I'm wearing a [/INST] suit that's </s><s>[INST] not really hurting anybody. [/INST] Right? Exactly. </s><s>[INST] It's [/INST] challenging people's perceptions. It's doing something that you want to do. </s><s>[INST] Yeah. But it's [/INST] not hurting people. </s><s>[INST] And and that that particular thing was um, yeah, it was hurting people. It's a good line. It's a good line like hurting ultimately the people that you want to flourish. Yeah. You tweeted a picture of pumpkin spice greek yogurt and asked grounds for divorce. Yes. No. So let me ask you what's what's the key to a successful relationship? [/INST] Oh my God, A good couple of therapists. </s><s>[INST] What what went wrong with the pumpkin spice greek Yogurt? What's exactly wrong. Is that the pumpkin, is it the greek? I don't understand. I stared at that tweet for a while. I [/INST] grew up in europe, so I don't understand the pumpkin spice in everything craze that they do every autumn here. Like I understand that it might be good in some foods, but they just put it in everything </s><s>[INST] and it doesn't belong in greek greek yogurt, [/INST] I mean I was just being humorous, I ate one of those yogurts and actually tasted pretty good. So </s><s>[INST] I think part [/INST] of the success of a good marriage is like giving each other a hard time humorously for things like that. </s><s>[INST] Is there a broader lesson because you guys seem to have a really great marriage from the external, I [/INST] mean every marriage looks good from the external, every I think Yeah, </s><s>[INST] that's that's not true. Yeah, [/INST] okay, No, but like, relationships are hard, relationships with anyone are hard and especially because people evolve and change and you have to make sure there's space for both people to evolve and change together. And I think one of the things that I really liked about our marriage vows was remember before we got married Greg at some point, like got kind of nervous and he was like, it's just it's such a big commitment to commit, like to something for life, and I was like, we're not committing to this for life, and he was like we're not and I'm like no, like we're committing to being part of a team and doing what's best for the team if what's best for the team is to break up, we'll break up like I don't believe in this. Like we have to do this for our whole lives and that really resonated with him too. So yeah. </s><s>[INST] Yeah. [/INST] That was our vows like that. We're just, we're going to be a team, </s>
<s>[INST] And I'm like, you know what? It's just about love. What does that say? So this says it's [/INST] It has vitamins and minerals, there's a bunch of them. It's in Russian, I don't believe it. </s><s>[INST] It sounds really strange to read like health information in Russian. [/INST] But look, there's a Yorshek like you have. Yorshek like you have. </s><s>[INST] He doesn't mean it. He doesn't mean it. Wow, strong words. But this is not, it's like hard candy, I don't know. [/INST] I think this, some of my friends sent me that's made with blood to give the kids iron. Who's blood? Like cow blood. Oh. Like with chocolate. All right. You can keep it. That's all you. All right, I'm keeping both of these. But can I, can I, can I speak something that you're talking about with emotion? Something that is very pernicious in terms of emotion is people denying the validity of their own emotions. And here's one example. Someone could be in an abusive relationship or have had an abusive childhood and they think, well, I didn't have a black eye. We had dinner on the table. It wasn't abusive because you hear some other story. So they feel their emotion is invalid or like, oh, he never lays hands on me. He gets drunk and is mean to me. He's still basically a good person. You're denying that emotion and that emotion is a response to something real. There's an expression. I have friends who are in 12-step programs. There's an expression there, which I think is very profound, which is if it's hysterical, it's historical. Meaning if some minor incident is having an extreme disproportionate impact on you, think, ask yourself, why am I responding in such an extreme way to some minor thing? And I will tell you, 10 times out of 10, you'll go back and you'll be like, oh, I'm feeling now like I felt when I was eight and my dad came home and he was a total jerk and I didn't do anything wrong and he thought I had and I was completely powerless. And now I'm in the same situation, my boss. I'm not that eight-year-old. In one sense, I am. In another sense, I'm not. But I feel the same way I did as a kid. And this is a very useful mechanism in terms of furthering one's happiness because you kind of deprogram all those things that you've picked up as a child. It's something you were talking about with him. But it's also, you know, if you're feeling something wrong, even though you're trying to rationalize in a way, you know, it's not abusive because he's not hitting me. No, the emotion is telling you something real about what's going on. So acknowledge it and fix the situation, right? So one of the powers emotions give you is they send you signals about something that might not be in cognition yet. Yeah. And when you examine the emotion, it brings it to cognition. Yeah, yeah. And now you can act on it. So maybe the boss is abusive. Yeah. But I didn't really think of it in those terms. My emotions are sending me signals and now that I signal it, I'm going to resign. I'm going to find another job. I'm going to complain to his boss or whatever. I'm going to take action. </s><s>[INST] Why do you think Ayn Rand is such a controversial figure? Last time I spoke with you on this particular podcast, the amount of emails I've gotten, positive and negative, and certainly negative. I don't usually get negative emails. [/INST] Yeah, but you did. Yeah, I can't relate. </s><s>[INST] I'm sure mine were a positive. Yeah, it was mostly women sending pictures for me to forward to you because… But you didn't send me any of them. Oh, surround the email address. I'm sorry. He kept bouncing. I was sending it to you. Oh, so this is love. [/INST] You didn't send me any of them. Oh, surround the email address. I'm sorry. Yeah, I was sending it to you. </s><s>[INST] Oh, this is Love. Love hurts. Okay. Yeah. she's such a divisive figure, why do you think that she provokes such emotion in both the positive and the negative side? I'd love to hear both of your [/INST] viewpoints on this. Yes, no, well, I think on the negative side, in both the positive and negative side, I think it's because she's radical. She's consistently radical. She up ends the premises, the ideas, that are prevalent in the culture, that were brought up on... you know, they're like milk and, you know, the basic stuff that we're growing up. You have to be altruistic. You have to live for other people. That's just basic stuff. Nobody challenges that. Nobody questions it. And if they do question it, they usually question it from the perspective of a cynic or a bad guy, right? You mentioned the Joker, right, before we started, right? You know, I'm going to upend the world because I don't care about other people, right? So they're presented with these two alternatives, and it's real in people's lives, right? You either live for other people or you're an evil SOB. And, you know, yeah, most people are in either one of those, but the ethic is right here. It's living for the people. And when you challenge that, they have no way cognitively to go with that. And the only place they can go with that cognitively is to the Joker. It's to the evil guy. It's to somebody who wants to smash everything and destroy. Because they don't have this alternative conception of, oh no, you can be rationally self-interested. And that does not involve destruction. And that does not involve exploiting other people. They can't conceptualize that. It's not in their framework. So it's the fact that she's so consistently on the side of self-interest, for example, on the side of capitalism, on the side of freedom. It's the fact that she dismisses faith to the extent that she does or to the extent that I do. That alienates people because that is completely different from what they brought up. Now, the flip side of that is it's also really interesting to some people. So, you know, a lot of you got some positives, right? And I got a lot of positives from that appearance. I know a lot of people came to my podcast because I appeared on your show. Why? Because they hear something that's completely fresh, new, different. They've never heard before. It appeals to something in them that maybe a lot of people say, I read Ayn Rand and it confirmed everything I believed. Now for me it didn't. It was the opposite. It turned upside down everything. But there are a lot of people out there who have a sense that something's wrong in the world. That altruism is wrong. That socialism, just the stuff in religion is wrong. But they don't religion is wrong, but they don't have an alternative. It hasn't coalesced and they listen to a lot of podcasts because they're trying to get ideas of what is it that I'm sensing that's wrong out there. And suddenly somebody comes out and gives them some clear explanation of things and they go, wow, that's what I've been looking for my whole life. So that's the positive for people. You know, and I read Ayn Rand, but it just all made sense. It all clicked and it made clear that everything I believed to that point was just wrong. It just didn't integrate. And I always knew to some extent it didn't integrate, but there was no alternatives. I believed it. What else was there? I remember saying to myself as a kid, probably 15, why is morality all about other people? Why is that? Well, that's just the way it is, right? And I couldn't come up with an explanation. She gave me the explanation and she gave me the explanation why it's wrong to do that. And I think, so I think that's why people respond. It's just too radical. It can't fit into their cognitive framework that they're being brought up on, that they've </s>
<s>[INST] You know, it's my- Wait a minute, wait a minute they're not, listen. No, as I did, I'm not even touching that one. It is true, it is true. The document, there is a- [/INST] There is a document, it is true. There is a documentary where they duked a bunch of scientists who are like oceanographers and they like showed them ancient footage of, you know, mariners saying that seals were mermaids. Who cares? It's, I was young, I got brought to Hollywood and I got spit out the other side, and that's on me. That's not their fault. You know, there's that parable about the frog who gives the scorpion a ride across the water and then at the end he says, I'll give you a ride just don't sting me and then I get to the other side and the scorpion stings them and the frog goes, why did you do that? And the scorpion goes, I'm a scorpion. </s><s>[INST] It's not their fault. That's my nature but now that you've become much more well known and much more successful at what you do, you have a platform. Can you return to those people and use it, the machine, to get more and more attention. Is that something you work on? [/INST] Or do you prefer to work completely outside? I think that most of the success that we've had now in protecting the rainforest and the levels that we've reached are so far. I think back to those barefoot days of catching snakes with JJ on the boat and now the massive ecological reserve we have and the team of rangers and the converted loggers and all of that is because of the ability to communicate and to show people, but that's all been through social media. And so I'm open to the fact, if somebody came and gave a sort of like Bourdainian pass where they said, look, you can be yourself, you can swear, you can fart, you can smoke, you can do whatever you wanna do, go out there and show us the real thing, I would love to. But now I know how those contracts need to be. I need to have right to refusal and they can't change them. And so I'd almost rather just do it like the way I think like Mr. Beast does stuff where it's like you just, you get a crew of guys and some seed money and go film the episodes and put it out exactly, I mean, a committee never helped real art be better. It has to come from the source of inspiration. So you get, I think, you know, you get JJ and a crew of people or the guys in Africa that I'm working with right now doing elephant conservation and like, but you gotta show real. I mean, look, that's why, I mean, look, that's why Joe Rogan is important right now. That's why you're important right now is because it's not being filtered through this ridiculous system of polishing it </s><s>[INST] and dumbing it down. Yeah, that's why Joe has been an inspiration. You don't need a crew of a bunch of people. You don't need a crew period. All you need is one or two other people and that's it. And in my case, you don't need anybody. I've been doing this by requirement. I just need to be by myself. There's a few other folks now that are helpful with the editing and so on, but it's just, they make life more awesome as opposed to a boss that tells, a creative director. Somebody told me, actually, I was visiting LA, I think it was in LA, where they were saying that now for all intimate scenes in Hollywood movies, there's an intimacy director. So when there's two people having sex, there's a third person that ensures that, on film, so it's not real, but there's still intimacy, there's a third person that ensures that everyone is comfortable and the actors say that this always ruins the chemistry of the scene. And so, it's a very Hollywood thing. I understand there's creepy people and so on. Yeah, I understand. Thanks, Harvey Weinstein. It's usually, I think, comes from the director pushing things too hard. If you just leave it to the actors, they know their boundaries, they can control their own boundaries. So the intimacy director is more for the director pushing things. [/INST] There's Werner Herzog, you know, there's Werner Herzog. I understand the logic. Let's make sure that we don't have anything happen here that shouldn't be happening. I get it, but I, yeah. But no, I think that authenticity is the greatest currency. And I think that in order for me to tell the stories that I can tell, like, you know, what changed the game for me was, I wanna tell you this story. So in 2019, the Amazon fire started popping off and we had just gone to film like a month earlier. We'd filmed like a small documentary and they'd been following me as if I was on a solo, which, you know, we did the best we could. I lived on my own. But as we were driving, we passed a spot where the flames were 70 feet tall. The forest was being destroyed. And I went out there with my phone, which overheated in like two minutes and said, you can't use it. But for a second, I was out there in the flames, picking up animals and throwing them off to try and just get them cooled off. I was trying to get snakes out of there. Everything was, the birds are flying, and I fucking lost it. I was red-eyed, I was crying, and I was going, this is happening every fucking day, I was screaming, and it's the first time that I'd done that. Because I've seen the burning so many times and I just lost it that day. And I don't know what made me pull out my phone because, usually, in those intense moments I say, forget the documentation, this is real life. we've got stuff to do and I'm doing, I'm not documenting. And then a month later, I'm home and I'm in New York and all of a sudden I see these articles like, the Amazon's burning worse this year than it was last year and blah, blah, blah. And I was like this, you know, fucking. And I threw it up on Instagram like eight o'clock at night and I'd never, like I'd never cursed on Instagram. I don't know why, I just never did. And my phone was on 100% and I put it on top of the refrigerator and I went to bed and I woke up in the morning and my phone was on the floor on 2% and it was ringing off the hook. And it was like the news. And they were are you the guy that posted that viral video about the Amazon? And I was like, what? And that was the start, that's where it broke. And that's where we went from barefoot in the Amazon to all of a sudden, I was talking head for three weeks and going around on all these news stations and all of a sudden I was like the spokesperson for the Amazon and JJ's calling me and he was like, go, go, go, go, go, like get us that support. and it was just, you know, so communicating with people and bringing them into that reality and whether it's, you know, rhino poaching and elephant poaching or the Amazon being destroyed. It's like, to me, it's like being able to take people </s>
<s>[INST] It is the best way to support this podcast. This show sponsored by thera gun, A handheld percussive therapy device that I use for muscle recovery. It's surprisingly quiet, easy to use, comes with a great app that guides you through everything you need to know. There's been long stretches of my life where I would exercise quite a bit, especially when it was jujitsu or grappling or wrestling or judo involved. There's many days where I would do two a days or three days, you know, training twice or three times a day for basically every single day of the week. There was an art there to recovery, but also an art to the training process itself to avoid overtraining, but still pushing yourself to the limit. Very much from the school of like Russian wrestling where drilling and exhausting the mind not the body is the goal of training. Anyway, try their gun for 30 days, they're gone, Gen four has an oled screen personalized their gun app and is both quiet and powerful starting at $199 go to third gun dot com slash lex. That's their gun dot com slash lex. This show is also sponsored by sun basket. They deliver fresh, healthy delicious meals straight to your door. They have prepared meals, meal kits and raw ingredients like just a nice new york [/INST] strip steak, </s><s>[INST] trout, sea bass, [/INST] salmon and much more. </s><s>[INST] I should mention here that one of my favorite activities is going fishing. I love being one on one with nature for many hours at a time in that sort of peaceful zen state where it's just you and the water. I'm mostly talking about freshwater fishing. I've actually never [/INST] been </s><s>[INST] deep sea fishing and I'm not exactly sure if I'm interested in that. It seems like a whole lot of the world, but I sadly haven't done it regularly for a few years, but I'd like to get back into it. Returning to nature regularly is a good mechanism for reminding me what's important in life. Anyway. Right now. Sun basket has a limited time offer, get 90 bucks off and four free gifts across your first four deliveries, including free shipping on the first box. When you go to sun basket dot com slash lex and enter code lex it check out that Sun basket dot com slash lex and our code lex for amazing discounts and gifts That offer expires on April 13. All good things come to an end friends, so hurry up. This show is also sponsored by Express VPN. It's a good tool to shift the asymmetry of power in the battle for free speech to the individual in the digital age. Your data, your private data is power and freedom is maintaining control over that data. There's a lot of tools that help with this. I think a VPN is just a very basic tool that all of us should be using for many of our interactions on the internet. Some technologies of course is just useful tools, useful hacks to get the job done, but they can also have profound philosophical ideas behind them. I think VPN is very much that the internet at its core is freedom. Of course, that can be chaotic, that can even be dangerous. But ultimately freedom wins and the internet always wins in the end. Anyway, go to Express VPN dot com slash lex pod to get an extra three months free. That's Express VPN dot com slash lex pod for the simple, beautiful design of a big red button. What else do you need in life Friends? This episode is also sponsored by indeed hiring website. I've used them as part of many hiring efforts have done for the teams have led. The main task is to quickly go from a huge number of initial applicants to a short list of great candidates. I recently had a discussion actually about the hiring process for engineers and the three things I've mentioned that I was looking for first as competence, extreme competence, so demonstrating they were able to dig into the details of a particular project that you worked on and demonstrate that there is both a skill and an obsession to getting every little detail right and innovating on every single detail and questioning how that can be done better. The second thing I look for is extreme passion. So just a love for, first of all, everything in this world, but really a love for projects that you've done in the past, I love for projects that you might do in the future. And the third thing is diversity broadly, which is I love the weirdos, I love, I love people that don't quite fit in the square pegs if you will, people that think differently in ways that are unlike my own. I mean, this is where indeed comes in as you want to filter out the initial set of candidates to where you can really dedicate your energy, your attention to a few people at the very end to see who is actually a really, really good fit. I think that's a lot of work, but if it's done well, it's one of the most rewarding things you can do is to be on a team of people you love with whom you can create brilliant things anyway right now get a free $75 credit at D. Dot com slash Friedman. That's their best offer anywhere. Get it at indeed dot com slash Friedman offer valley through March 31st terms and conditions apply. Indeed dot com slash Friedman. Speaking of which, this is the lex Friedman podcast and here is my conversation with Anthony pump liana. You served in the US Army for six years and spent 13 months in Iraq in 2008 09. Can you tell the story of why you joined the army and what were some of the moving difficult and maybe lasting experiences from the time he served. [/INST] Sure I joined when I was 17 years old, I needed my parents to basically sign uh in order to uh to join and uh I graduated a semester early from high school and I thought I was gonna go play football in college and kind of enroll in the spring semester. And when that didn't happen, basically was working at Chick Fil A and Quiznos and hide in my mind. Look this is probably not the path in life that I want. Um and so I knew I was gonna go to college, I knew I was gonna go play football in the fall, but I had this window of time. And so I walked into a recruiting office and just basically was like, I'm assuming you guys need some help and uh, you know, they give you the whole pitch and give you a signing bonus, you can go jump out of planes and go to all this crazy stuff. I just said, okay, let's </s><s>[INST] Do it. This was, this was close to 9 11, [/INST] This was in 2006, about five years after. </s><s>[INST] So what impact, I mean, do you remember 9, 11, what impact did that have on your thinking about this? [/INST] So I was in eighth grade, um, if I remember correctly, and I remember being in school when it happened and uh, I walked into a classroom and the entire class of somebody else's class, they were all talking to the teacher about something the second that me and a couple of the kids walked in and we got real quiet and the teacher was like, hey, go back to your home room. And so it was just kind of a weird like what's going on. Uh, and the next thing I know they called all the students into the cafeteria and this is back before, you know, every classroom really had a television in it and you know, cable and all that kind of stuff. And so when we were there, they basically just said, listen, there's been this event that's occurred, all of your parents are gonna come pick you guys up and they'll explain it to you. And so to, you know, a kid in 8th grade, you're basically like what happened? And so I got home and I remember talking to my dad about it and my dad basically gave me, you know, the core American kind of talking points, right? Somebody from another country came here and tried to kill Americans and was successful in doing that. Um, and to some extent he just said, and I'm willing to bet, you know, we're going to go back after him. </s><s>[INST] Did that wake you up a little bit to the idea that there's evil out there, that you know, even just the idea of terrorism for many people that was when it hits you in your own land, it really shakes up your mind in some sense. World War Two. That's why World War Two was fundamentally different for americans than it is for people like in Russia and England and France and uh in europe in general is, there's something about when there's a families, women, Children dying on your own land. That's different. And that was one of the first times in America where like on your, of course is Pearl Harbor. But like this is like in recent history, it's like they hit us here. That was like a profound idea. [/INST] Think America was very, very good at exporting the violence elsewhere for a long time. And uh, there was this element of complacency, but also this element of uh, you know, really just american superiority that doesn't happen here. Right? And I think that that woke people up, not only to um, kind of the idea that other places around the world may not like the american ideals may not like democracy and capitalism and, and that, but also, uh, maybe we aren't as big, tough and secure as we thought we were, right. And so obviously I think you see the kind of the over rotation with a lot of the kind of security theater that came after that of almost psychologically, let's make our citizens feel like they're safe, even if the things that we're doing don't necessarily, you know, kind of change that apparatus, but on top of that, I think that it really woke people up to, uh, extremism around the world. And uh, I don't know if necessarily there was a change in the extremism as much as it just was an awareness thing, right? How many people, you know, kind of drew a line from, was in 92 or 93 with the World Trade Center bombing to, you know, deep levels of extremism and hatred of kind of the american industrial complex, probably not that many, 2000 and one, a lot of people. And so I think that was, you know, again, as a young kid, you don't understand a lot of this stuff, you basically just, hey, somebody came here and tried to kill americans and so, you know, we should go fight back, right? Was kind of the, the response I think that I had, </s><s>[INST] What role did that have psychologically for you? Would you then in 2006 joined the Army. I mean this is a very different joining the army than in the time when like it's more peaceful here. You're essentially facing, I mean, I don't know if you see it that way, but you know, there is a war on terror and I know that people kind of uh criticize the whole formulation framework of thinking, but nevertheless, you are going to Iraq, you are going to Afghanistan, you're you're going to these places and are fighting these complicated like, I mean it's not even clear what you're fighting. Yeah, [/INST] but I think there's a couple of key pieces, right? So one like what the actual most impactful data points if you were or kind of stories for me was the Pat Tillman story. So I played football in high school and it was going to play in college. Um and seeing, you know, this NFL player who basically just one day said, hey, I'm gonna go and do this instead uh and walk away. Don't know necessarily if it was a, I want to pursue the same story and obviously he ended up dying and so not exactly the end result that you want, but I think it was almost like uh he made it okay if you were on a certain trajectory in life to go take this detour and to go do it. But the second thing is I was 17, pretty stupid. We're 17. Pretty naive when you're 17, right? And so I almost um kind of backed into the deployment because I signed up uh, as a reserve member. And so basically the plan was to sign up for the reserves was gonna go to basic training, get all the, you know, kind of education and qualification that's going to go to college and then after college, you know, maybe there's a chance that you will go and serve or do whatever For me. I ended up getting deployed when I was a junior in college that we got pulled out of school and so at 20 years old, it's not exactly what you thought you were signing up for it, especially to kind of leave school to go do it. And then on top of that I probably had an advantage over most people both on the entry to combat and the exit to kind of a combat situation in which it was football. So I always explain that in hindsight, you're in a male dominated, testosterone driven kind of combative sport where it's us first them and there's training and uh, you know, injuries and just kind of, all of the things that go into playing a combat sport like football to now they give you guns, but you should have a uniform on still male dominated, it's just a little bit more serious in terms of the injuries and potential death and things like that, but also on the exit from that deployment, most guys I was there with, they're going back to being, you know, prison guards, police officers working at the lumber yard, you know, just kind of every day americans and so I had the fortunate ability to go back into kind of combative environment, go back to play football and it was almost this like de escalation on the way out where they take your guns away. We still got a uniform, still male dominated, still combative and then eventually you're just a normal citizen. And so I think that in some weird way, I was very fortunate to kind of on the entry and exit have that experience where other guys didn't. </s><s>[INST] So what you were deployed to Iraq, were there any memories, experiences that changed you or in general? Like you're probably a different man on the other side of it. How did that time change you? [/INST] I think there was two main takeaways that I took, right, So one was um, not a specific moment, but on multiple occasions, I remember we were driving down the road and I would look and there would be a 10, 12, 14 year old kid and if you've never seen somebody who literally has hate and disdain in their eyes, would you just not necessarily to you personally, just to the uniform to what you stand for to all this stuff When you see it, you see it right? And I always think of um if you've ever watched the movie 12 strong and in it, they've got this Afghan Afghanistan warlord and he's talking to a bunch of soldiers and he says, you know, you don't have killer eyes, you do, you do. And he's just like, he can just tell what he's seen so many soldiers. And so I think that that was a memory on a number of occasions where I just saw young kids and I just said they hate us, right? And it's not you personally is what you stand for. But the really big event was when you first get to these combat zones, a lot of times, what will happen is you basically, your unit teams up with a unit that's leaving and there's a handoff and happens over a couple of weeks. And so you can imagine almost, you know, 1% of our team goes out with 99% of their team, then five 95, all the way until it's 5050 and then eventually it rotates and the majority of our team and a small number of their team. And so what a lot of people will explain is the two most dangerous times in war are actually the first two or three weeks in the last two or three weeks when you first get there, you don't know who the people are, you don't know the terrain, you don't know, you know kind of the local cultures and and who to look out for. What signs. All that stuff in the last two or three weeks is you basically think you've survived the deployment, you're looking forward to going home. So you become complacent, things like that. And so we made it through that transition period with no issues but the literally the very first mission that we went out as a team ourselves 100%. Um there was two separate incidents. One was we were driving them overnight and uh what we think was a sniper shot at a truck that I was in. I was standing up outside of it along with another guy and that was kind of just a wake up call again of never been shot at before. Right. And so I'll never forget uh you kind of heard this whiz go by. And the guy next to me was from a rural pennsylvania and he just said you know look I've never been shot at before. You could have done a lot of hunting and get the puck down. Okay. And so uh we kept driving that night. Um and uh later on in the night uh an I E. D. Went off a guy ran over an I. E. D. Who was at the front of the convoy and when that I E. D went off again. I had never been in a convoy that had been blown up before. But the training kicks in. And so immediately every single person starts screaming out, I E D I E D. And they started looking and trying to figure it out. And you realize the United States military did a fantastic job training us before we went, because in that moment nobody thought about anything. You just did what you had been programmed to do. Um, and so ultimately, kind of through the end of that event, uh, there was U. S. Soldiers ended up dying. He was shot in the head. And um, when we got back to the base, uh, kind of after that entire event, I think it just hit us. We are at war. And if we make mistakes here, that is the cost of, you know, kind of those mistakes. And this was somebody who I didn't know. It was somebody who literally showed up kind of as secondary support for our unit and basically was there to help us. Right? And so it was one of those weird situations where You have this emotional connection because it's somebody who shared an event with you, but you didn't know them, right? And you learn their name later and you understand that they have a family, they have young kids and all this stuff. And so again, as a 20 year old kid, you're kind of processing all this and you just realize like the gun I have in my arms, my hands, it's real for a reason, right? And we better take this seriously. This is not, you know, let's joking around and kind of the barracks and you know, all the things that you would expect you guys are doing the army. So I think that was like the moment where I said, hey, I'm gonna learn a lot here. Uh, and I gotta make sure I get home </s><s>[INST] and you're snapping into the training. But nevertheless, I mean, you're somebody who thinks philosophically about this world now, right? You're very intelligent and things deeply about the world. So looking back, you mentioned hatred in the 14 year old kids eyes there's death. So the way you kind of describe this whole story is like training kicks in this, this ship is serious, Like this is uh, you know, there's a reason, there's a gun in your hand. So there's a strategic element, there is like you have to get the job done. There's a task in hand at the same time. If you zoom out, there's a kid who has hate for you. Some of those kids would probably, if they could would kill you for the thing you stand for in the uniform and then there's bullets flying at you and then there's people that some of them you might already care for deeply are dying. What the hell do you make of that? Do you think about that? Does any of that haunt you? How do you think about the world? Having witnessed [/INST] that a lot of times when we would talk about, we were there if I was that kid, I would want to kill that person to write, I would have hatred as well. Right? Imagine if in the United States tomorrow, you and I woke up and there was tanks rolling down the street from another country and they were basically imposing their rules on us. Whether they thought it was the right thing to do or not, the soldiers were there, they were doing this, we would probably feel not so great about it, write a kind of a minimum and a maximum would be really really piste off. We would fight back. And so what you don't understand when you're in the heat of the moment is why does this person feel this way? And so what's very weird is, well what happens if a year ago U. S. Soldiers came through, they got shot at they returned fire and they killed that kids, uncle you'd be piste off. Right? And so you just start to understand like we look at war very black and white. We look at it very much from a clinical perspective we're gonna go, we're gonna go um kind of invade somewhere. We are the most dominant military in the world were very good at invading uh and we will crush wherever we invade, but when you're actually on the ground, what you understand is the humanity of it? All right. And so what becomes very interesting is um pretty much every veteran I know that comes back, there's some of the largest pacifists in the world and I always revert back to Marcus Luttrell was a famous navy seal. Um, and there's a movie made about him and his story. Uh, he gave a speech one time that I saw and he basically said, listen, if you're a politician, your job is to be the diplomat, do everything you possibly can not to send me and my friends anywhere, because when you send us, we're going to bring hell with us, right, and understand that is the business that we are in. But every single other person up until we get sent has a job to do to prevent having to send us. And I think that ultimately, that's where you see a lot of kind of this generation that has fought in Iraq and Afghanistan, that says, listen, maybe we shouldn't be running around the world being the police, maybe we shouldn't be going and invading all these different countries. Because when you actually get to see firsthand what happens, it's just something that we should avoid at all costs. But if we have to go or we have to actually send soldiers somewhere, understand what happens when that occurs and you know, the United States is the best in the world to do it. </s><s>[INST] Do you think thinking about that kid with the hatred, do you think there will always be hatred in the world, do you think, uh, from another perspective, do you think there will be war always? Is that a fundamental aspect of human nature, or is that something we can escape? [/INST] Yeah. So war I think has like very negative connotations in terms of bullets and bombs and death and kind of just very morbid type. Um, um, understanding conflict on the other hand, I think people look at and say, of course there'll always be conflict, right? You just can't have billions of people all on the same planet without some level of disagreement, whether that's a disagreement of ideas, disagreement over physical, you know, geography or something else. And so I think conflict will always exist. The question is, what form does war take moving forward? And so in my mind, you know, it's starting to look a lot more clinical, right? A lot more drones, a lot less soldiers on the ground, a lot more use of special forces and kind of these small, highly specialized teams rather than kind of big mechanical armies. Um, and then you get into like the information warfare and kind of cyber warfare. And you start to understand that we're at war with a lot of people right now, right? Doesn't mean we're necessary dropping bombs on their country's doesn't necessarily mean we're sending soldiers there, but on a daily basis we are engaged in these kind of, you know, cyber battlefields and so if that's where war starts to play out, um, it one changes the tools and tactics and techniques that we need to arm our country and other countries will arm themselves with. But it also changes the way that we think about war. Right? It's, it sounds a lot less worrisome. If I say, hey, we're going to go to war with a country, by the way, there's gonna be no death. Right? Okay. Like that doesn't sound nearly as bad as, hey, we're gonna go send 10,000 soldiers and you know, some percentage of them are going to die on the battlefield and then we're going to, you know, basically pipe back videos and articles saying that american soldiers are </s><s>[INST] dying. There does seem to be a fundamental difference between the, the genghis khan style. Like if I would feel differently if somebody like hand to hand with a knife, murdered my family versus cybersecurity where I stole all their data stole all their money stole everything they own falsified their identity. All that kind of stuff that, those are both traumatic events. But they do seem to be fundamentally different. But maybe that's actually very narrow style thinking because ultimately you have to think about what his life and what's happiness and it's like the summer I thinking, I'm not sure what's more painful if I take it to myself, like, I'm not sure what I would rather lift through being stabbed like to death or having my identity stolen all my money stolen or maybe reputation destroyed? Like with lies or something like that. That's very interesting to think about, if you think about quality of life and all those kinds of things, [/INST] it's finite, Right. one point and the other is kind of a long prolonged, almost torture. </s><s>[INST] Physical pain versus psychological pain. It's really interesting to, it's really interesting to think [/INST] about. And I think another key piece to this, which I don't have answers to, but there is an element of emotion and rage in the physical violence versus again, more of that clinical, you know, information warfare. And so, um, it's really easy to show a battlefield where there's death on both sides and bombs being dropped in buildings destroyed. Um, it fits very well into propaganda for everyone involved, right? Regardless of what side they're on. When you start talking about cyber warfare, how many times have we seen a big company get data hacked or information hacked than we all read the headlines. Maybe throw a tweet out and then move on with our day and don't remember it anymore. And so it's just very, very different. I think in the motion and response that invokes and people when they hear about it as well, </s><s>[INST] given the conflict, do you think people are fundamentally good. Are we all sort of like blank slates [/INST] that could be </s><s>[INST] evil given the [/INST] environment </s><s>[INST] or good given the environment? Or can we kind of is there some bass that we can rely on [/INST] that people </s><s>[INST] if left to their own devices will be good and, and trustworthy and honest, [/INST] I think you have to separate out intention from action. So if you talk to some of the most heinous criminals in the world, they've rationalized their actions and so you've got to ask yourself what is the level of which they understood what they were doing, that they intended to be malicious, nefarious, um, and kind of do bad things versus the actual actions themselves. And so, um, even as a society, you know, if, let's say for example, you were to walk down the street and you were to murder somebody on the sidewalk completely unprovoked. We would look at you and say you are a, you know, a sociopath, You have everything wrong with you and that is somebody that we do not want in our society and therefore we will levy, you know, the extent of rule of law against you in order to protect society from you. Right? And you become that monster, that beast, if in the same situation, somebody walks in your house with a knife and you murder them or you kill them. Now we put you up on a pedestal as a hero and there are two very, very different responses. They may be just as morbid. They may be just as violent. Uh, in terms of the actual actions, the intentions, the way it's perceived is very, very different. And so I think that as a world we like a very black and white clean cut, you know, good, bad. I think the world is a lot more messy than that. And I think that a lot of times when you look at intention, it's hard for us to tell what somebody's intention is. But I've looked at a lot of, you know, people who are both considered very good and also a lot of people are considered very bad and they sound very similar in terms of the motivations for their actions. And so I think that it's, it's just a really hard problem that probably doesn't have a perfect solution or an answer. </s><s>[INST] You give much value to the intention. Or do you think it is better to look at the results of the behavior? Uh, as opposed to the, the underlying ideology, the underlying intention of the behavior. [/INST] I think that intention gets at the question of like, are people inherently good or bad, right, is I think that they're generally inherently good and the intention is driving towards the thing that they believe is the best outcome or the best thing for them to pursue the action I think is where we spend most of our time focused on. Um, and frankly we actually maybe a better society or kind of kinder as a humanity to each other, if we spent more time looking at intention rather than action. Um but again, you know, if somebody walks down the street and murder somebody, uh it's really hard to have a conversation and it may be inappropriate for us to have a conversation about intention versus any level of of action. Right? </s><s>[INST] So, you're one of the prominent, I would say, even the faces of the world of Cryptocurrency, Bitcoin, that whole entire world, let's dive straight in and ask, uh do you think do you consider yourself a Bitcoin maximalist? [/INST] I think that the way I really look at it is I work backwards off of what is the maximal ism that I believe in, and the world that I believe in is kind of an automated world that is run on these open, decentralized protocols. Uh and what we ultimately do is we return sovereignty and individualism and kind of personal responsibility and liberty. Uh two people over institutions and what we end up doing is we end up kind of taking what has historically been a very analog or physical world economy, and geographic rule. And we then kind of put it in the cloud, and this digital economy becomes the prevalent way that we all uh conduct commerce, communicate, et cetera. And so it's less about any one single technology to me, right? I think that it's pretty stupid for people to um almost in a way uh put an inanimate object up for uh you know, some sort of obsession Uh to me it's much more about the ideals, the ethos. Uh and the most rational and likely path to that kind of end result or that world that I think, you know, is at this point, just a foregone conclusion. So </s><s>[INST] the distinction there and maybe people don't know the terminology maximum is um is basically saying, I really think this is a good idea. Like uh you know, if you prefer a certain kind of diet, you could be a keto maximalist saying like this is probably maybe it's not 100%, but probably the diet that's healthiest for humans kind of thing in the same sense. Bitcoin maximum is um is saying, you know, of course, we don't know, there's a lot of uncertainty, but this particular technology seems to be the best representations of some set of ideals that defines progress in in the future. But you're drawing a distinction between sort of uh cult like obsession about an object of any kind, whether it's keto or Bitcoin and just sort of believing that the technology is the best representation of a particular set of ideals. And you believe that sort of uh this moving into the cloud uh both the distributed nature of it, but also just the digital nature of it is something that's going to be a positive step for humanity. [/INST] Yeah, I would even take maximum a step further. And it's not just the kind of singular viewpoint of this is the best. It's also an element of its anti everything else. Right? So, you know, take keto, for example, the keto diet is not only the best diet, all the other diets are bad. Right? And so it's it's a very binary view of the world. Um, I think that what's probably most misunderstood about, let's take Bitcoin as a specific example is that most of the people who are labeled Bitcoin maximalist, they would be open minded if they believe that something else came along that was a superior technology or had a better um, kind of probability of achieving again that ultimate vision. I think where uh, there's this controversy and kind of clashing of ideas is that the Bitcoin community believes Bitcoin is the best way to do that and has very specific arguments as to why the other things are not right. And so what ultimately ends up happening, which is very weird in the investing world, right? It's unlikely that you and I are going to sit down, you're gonna Apple stock is the best stock and there's no other stock that's worth anything. Right. And uh, and then also it's very weird if you said to me, um, you know, this stock is worth zero and that's where everything that I own I've put on a short on one single company, right? There's diversification. There's much more kind of probabilistic thinking and finance in general when it comes to this specific world of Cryptocurrency and kind of digital assets if you will, uh is there's two main groups of people who are trying to build two very, very different things at the onset, but when you unpack it and you start to spend more and more time on it, you guys, they're actually trying to accomplish the same thing in two different ways. So, Bitcoin is seen I think as a digital currency, right? Kind of the idea that this is going to ascend to become the next global reserve currency. It's a programmatic kind of transparent um money and uh it's essentially just 180 degrees difference than the inflationary, you know, non transparent fiat currencies that exists in the world. You then look at kind of everything else, right? And you have a lot of smart contract platforms and various things that they're all going after that ethereum with kind of the world computer approach and you can kind of go down the line with all their other arguments. So what they're trying to build, I think the big difference just comes down to uh innovation for security. And when you simplistically look at it via that lens, you actually understand where both people are coming from. </s><s>[INST] When you say security, sorry to interrupt you mean financial security or do you mean like literally the security of the of the particular Cryptocurrency, [/INST] the technical security of a Blockchain. So when you look at, let's say Bitcoin versus ethereum, right. Bitcoin has decided in that community has decided security is the number one thing that you have to optimize for so decentralization um over everything else in terms of transaction speeds, cost anything that you could come up with that is uh something that would be important for a currency. The number one thing to optimize for security. And as we have seen with a lot of technologies, facebook's labor are now what's known as D. M. Is a great example, uh not having decentralization is susceptible to the nation state. And so a lot of these other platforms and block chains, uh they say security is important, but it's not the most important thing. We believe there's a trade off between, you know, a little less security and transaction speed or compose ability or whatever it is. And so take a theory as kind of the second largest community and Blockchain by market cap. It was created because somebody wanted to, a group of people wanted to do something on Bitcoin. They felt like they couldn't do it. And so they said, hey, we're going to go create something that has these smart contracts that we can then go do here again, This is technology. Right? So the tribalism of like you're right, you're wrong to me is a little childish just in the sense of like the market is going to decide what is most valuable and then when you go inside of that community, like there's a lot of dumb ideas, people trying to build around Bitcoin, there's also a lot of really, really great ideas, people trying to build around Bitcoin, same thing in the ethereum world. And so what you end up getting, I think is the tribalism really comes out of the idea that there's a ticker price that is attached to all of this, right? If you go back in history of technology, venture capitalists didn't sit around the table and yell and scream at each other in this like religious zealot way, right? Because you bet on one type of cloud computing platform and I bet on another one right? Just the market's gonna desirable is going to work on and try to make our successful, uh, here, I think that the sensitivity and mainly it comes out of the Bitcoin community is that a lot of this is being funded not only by venture capitalists and kind of professional money managers and asset allocators, there's also this element of including the retail investor and the public and so it, whether it's through I C E O s or some other forms of capital raising. Um, there's arguments for it saying, hey look, uh, this now gives kind of the little guy some sort of access and ability to do it, but there's also arguments against it. Some people say, hey, it's easier to dupe them and it's easier to run scams and kind of all this stuff and so Ultimately I think that crypto is this like arena of ideas, it is literally the war of attrition and uh, what will end up happening is 10 years from now. You and I will talk and we're going to say, well, the market said X was valuable and why wasn't? And so all of the tribalism from between, you know, here and there, uh, it's fun. It's, you know, engaging, whatever, but ultimately doesn't really matter </s><s>[INST] because the public is involved. There's a lot of personalities. And so a lot of times we focus on the extreme personalities that do a lot of maybe, uh, part of the french ship talking. And, and so we kind of focus on that, but that's not necessarily representative of the communities involved. [/INST] Let's talk about Bitcoin first, and then it'll help us use as a kind of comparison to a theory or whatever else. So when you think about what is money, right? That's kind of the first question people really kind of go down the rabbit hole on and ultimately, today it's a belief system, right? And you may believe that one currency has more value over another because it's backed by a certain military or a certain government has a monetary policy that you believe in or don't believe in. But ultimately it's a belief system that there's nothing backing this other than a government asks you to pay your taxes in it, right? And they can have a monopoly on violence, uh, in terms they can put you in jail. If you don't pay your taxes, uh, they can go to other countries and they can invade into all this stuff. It wasn't always like that, Right? It was historically a layer one. Technology was gold. And so gold was a fantastic store of value. You knew that if you held gold, it wasn't going to be inflated away. It was sound of money was outside the system and no one could create more of it. The reason why that's important is because that optimization for store of value served as the bedrock of the entire stack of, uh, money for 5000 years. And so the problem with that though, Again, trade off between store of value is it was really hard to transact with, right. If I came in here and I, and you said, hey, I want a couple of ounces of gold and I had a whole bar, I'd have to literally shave off the ounces of gold. Uh, it's heavy to carry around if you said to me, hey, you're in one city, mail it to me really expense. You know, there's all these issues with it. And so ultimately what people said was, well, let's create a second layer on top of that gold in order to make it easier to transact. And so we created paper claims on the gold. So hey, don't carry around the gold in your pocket anymore. Put it in a vault or a bank, they're gonna issue a paper claim. Now you and I can trade these paper claims around At any point if you want the gold, you just show up and you say give me three oz of gold or two bars or whatever. And so that actually made the store of value. It was allowed that to be the anchor and kind of the most important part the security of your purchasing power. But now it became easier to transact. And then eventually we built layers even on top of that. So everything from electronic money, uh kind of electronic use it all the way to credit and other systems on top of that goal, 1971 comes around and obviously we d peg from that gold right? It was a temporary measure at the time we ended up not going back to it. And so what you moved or transition from was sound money, which was outside the system, no one could create more to now the government had full control. They could create as much as they wanted to. They tried to be responsible and disciplined. But obviously hard to do. Sometimes we've been really good at it. Sometimes we've been less good at it and you go around the world and some countries have absolutely sucked at it and some have been good at it. And so when you look into the Bitcoin world, I think that when you look at the optimization for security similar to go store value. People hold it, purchasing power has gone up a lot year over year, it's like a 200% year over year compound annual growth for over a decade. Right? And so you measure this in kind of the US dollar exchange price etcetera. But there's still a lot of people who will yell and scream about it's slow, it's costly, right? All the things around those transactions that are obstacles or challenges. And so there's basically two schools of thought and this is where we kind of get into the bifurcation. Some people just said, hey, this technology is antiquated, we can't use it. It doesn't make sense. Uh And so what we're gonna do is we're gonna go build something new. And so you go get kind of all of the various versions there. The Bitcoin community says no, just like gold had paper claims and other things built on top and layer 2345, we're going to do that here. And so they have already started to build kind of this layer to where it's easier to transact is cheaper, it's faster etc. And so I actually think that both of those worlds are going to coexist in the future. The big question is just which one has more importance. Right? So again, get out of the ordinary, it's just probabilistic lee. And so my personal belief is that the security that the store of value component is the bedrock for a monetary system is essential, right? Like that is the most important thing because you can always improve the other components, but you can't go back and fix that kind of core piece. </s><s>[INST] So my money is uh, an idea that we all, it's like an emergent idea that we believe in your saying that security is one of the most fundamental catalysts or fuels for that idea to sort of take hold and be stable and sort of take over the world. The other stuff is really nice to have. But if you don't have the security, you're not going to like it. It's not going to spread in a viral sense in in our human brains. [/INST] Well, and especially in light of the kind of the macro economy. Right? So like what's so fascinating about the last 12 months is um, and investing in general the best returns to kind of put that in air quotes a little bit is something that is different than everything else and right. So being different and wrong just means you're an idiot, right? Being different and right. Means that that's where kind of the outsized returns are. And so if you look around the world at currencies today, they're all the same. They're all inflationary, unlimited supply controlled by a government done decisions made in a very non transparent process. And what we've watched is the manipulation of all of those currencies in the last 12 months in direct contrast to that is this thing. Bitcoin, which is outside of the system has a finite supply, transparent and programmatic monetary policy. And so when you see those two systems kind of um in comparison to each other in the United States, there's a lot of people who say the dollar works great for me. I can go to the ATM. Get out physical cash if I want to swipe a card, I could do that. My money in my bank doesn't lose 50% of its value in a day in terms of purchasing power. Like the dollar is pretty good when you go to other countries, that might not be the case. And so I do think that there's kind of a relative analysis that goes on here. If you compare Bitcoin to the dollar, there's all kinds of arguments to make that the dollar is better as a medium of exchange today. But if I go and I tell you what about in you know, these kind of extreme examples of Venezuela Zimbabwe, Turkey, etcetera. And so I think that that's kind of one perspective to view this through is security versus all of the innovative components of a medium of exchange etcetera. The second thing though, that I think is really, really important is around censorship. And so when you look at again, every currency in the world today, every single financial service. They're highly susceptible to censorship. And actually I would argue the United States is in the business of censorship in terms of how many countries around the world do we sanction and cut them off in either a minimal or a very material way from the global financial </s><s>[INST] system. So when you defy when you talk about censorship, do you mean just the censoring your ability to operate freely in the world? [/INST] We'll look at a little bit differently, which is that the United States has um kind of the american superior order because we have the bombs, the bullets of soldiers and that military might we basically pose our will around the world. And so uh there's a very strong argument to be made that there are certain countries around the world that are being sanctioned, that the people of those countries did nothing wrong now. The governments are bad, right in terms of the way that you and I would look at democratic rule or communism or whatever it is, but the people are being hurt as well. So there's a whole group of people who would have just argued, listen, we shouldn't hurt anyone at the expense of punishing one person or a group of people, there's other people argue against that. But I do think that if you really kind of zoom out and you say, I'm gonna take myself out of the Western world view, and I'm simply going to look at this as we're all part of the human race. It's censorship. And there might be an argument for censorship, but there also might be an argument against the censorship. And so what Bitcoin does as that specific kind of payment network? Is this as anyone in the world with an internet connection? I don't care where you are born, what language you speak, what religion you are. Your wealth status, your education status. Uh none of it matters if you have an internet connection, you can plug into this monetary system and you can move value around the world to anyone else without asking for permission. And in the United States we basically have that ability in the U. S. Dollar kind of traditional banking system. I can pretty much send money to almost anyone I want unless they're really bad person that's on some list or something. Most people in the world don't have that capability. And so what you're essentially doing is you're democratizing access to a true store value and a medium of exchange. Right? And so what you see in many of these countries is that when their currency starts to fail, the first thing that a government or a group of people in power and influence do is they lock the citizens into the currency with capital controls. Why? Because if you let them out, it exasperates the problem. And so now what we're seeing is we basically are giving a tool to billions of people around the world, that is a peaceful protest, Right? You and I had no say at all when not only the federal reserve and elected officials in the United States, but central banks around the world over the last 12 months decided to create trillions of dollars and injected into the monetary system, right? They have arguments and some of them are very good arguments as to why they should do that. They're trying to mitigate short term pain long term, they'll figure out the other issues right. They have very kind of um elaborate and well articulated, um kind of viewpoint as to why they're doing it, but you and I had no say. And so when you start to look at, we have a very small group of people in this world, both in our country and in countries around the world that make these decisions that have very, very far reaching um kind of impact. And on top of that in many cases, there's actually not that much kind of accountability because usually these are not elected officials who are making some of these decisions, these are appointed and you can argue that, hey, we elected somebody who appointed them, but at the same time, that accountability isn't quite there. And so I think ultimately when you just back out and you say, you know, what is Bitcoin, why is it important to the world? It is giving access to anyone in the world with an internet connection to a store of value and a monetary network that allows them to peacefully protest and to opt out of a system that pretty much is not working for majority of people in the world. </s><s>[INST] So it's moving the power from these centralized places. Sometimes I'm elected to the individuals and to the people. So the dollar does seem to work for for americans and for many people in the world but you kind of have a vision you you paint a picture of a future where potentially we moved to Cryptocurrency. So what kind of trajectory do you see where Bitcoin can become the main currency in the world or at least Cryptocurrency become the main way of storing value in the world and basically overtake the dollar. [/INST] Yeah, so I always go first to we don't need to have competition like in terms of like a direct competition between the dollar and Bitcoin. Right? Um if you look at most technologies in the world, the really valuable ones are actually market expanding technologies rather than simply just market share stealing technologies. Right? So if you look at Uber for example Uber didn't just say hey I'm gonna go take out all the taxis right? It actually drastically expanded the market for people. Now there's literally millions of people in the United States who don't have cars because they use Uber. Right? And so I think that Bitcoin is very similar in that um Yes there is a component of medium of exchange uh in terms of the dollar but also there is this component of the store value assets in general. And so when you start to look at Bitcoin specifically, I think that what you're seeing is you're seeing a generational gap where young people say I grew up with a phone in my hand, I'm digitally native. The whole idea of going to the bank and sending a wire or going to an A. T m getting physical cash is an antiquated idea in their mind, right? I one time I asked my brother he's 24 years old and I said, hey how do you send money to your friends? And then he gave me one answer which I expected, which was Venmo and the second answer I didn't expect, he said Uber, I said how do you send money via Uber? He said, well we get in a car together and at the end we split the ride. And so again, you and I have probably both done that, but I never thought of it as a way to send money to each other. And so it is a psychological difference between even me who's only, you know a decade older than him or so, uh and his peer group. And so I think as we're watching kind of Bitcoin continue this ascent. Ultimately what we're seeing is an entire generation of kids are saying listen, if I look at financial assets across the board, I have stocks, I have bonds have currencies and commodities. I know that bonds from a real rate return perspective is flat to negative, right, I'm gonna make no money on this because I have a belief that my dollar is being devalued and actually what we're starting to see is again, the internet has broken down these walled gardens and kind of the centralized hubs of information in that if you were to look at, let's say the stock market from 1971 to today in dollar terms, it's a 45 degree angle right up into the right, right. You know, it's kind of 78 10% growth every year. It's amazing just get invested in the stock market and you'll make money over a long period of time regardless of the dips along the way If you do nominate that same stock market in gold. The stock market is down since 1971. And so is it so much that the stock market is accruing true value or is it that the underlying currency in which it is denominated in is being devalued? Right. And I was being devalued in a very disciplined way, right? In terms of it's not like I want 50% devaluation in a short period of time, but still being devalued. And so I think that people are waking up to this idea that a traditional 60 40 type global portfolio doesn't work anymore, right? 40% of it uh in bonds uh is just not going to get it done. And so when you start to look at this, people first look at Bitcoin via two main ways. In my opinion, they look at it. One is a store value. Should I actually go and put some of my wealth there? Use it as a savings technology, right? We asked people uh, in the traditional world if you're a teacher fireman and accounting, you know, mid level manager, we say, hey, go do your job, the best in class as a fireman or as a teacher. And then, oh by the way, you'd be a professional investor as well. Because if you just put your dollars in your bank account, you're literally going to have your wealth devalued away over time. So you can't just save, you have to invest. That is a really tall task for people they have a hard enough time just doing their job right? Taking care of their family right now, they got to be an investor. So I think saving technology for Bitcoin standpoint is if you buy keto she's or Bitcoin over time it will increase from purchasing power standpoint because there's a fixed supply and demand continues to rise. But then you start to look at, well, what other assets do people put in their portfolios, whether it's art, it's real estate, it's precious metals or something else. Most of those assets are not because people actually think that they're going to go up in value over time using a store of value, right? The reason why somebody buys gold is because the store of value, right? Historically, that's a narrative driven uh type asset though. We tell people it's scarce. We tell people that it is a store of value. When you look at it though, we don't know how much gold exists in the world. We have a good estimate, right? But we don't actually, we can't prove how much there is, we don't know how much is coming out of the ground every day. Again, great, fantastic estimate, but we can't prove it and we don't know what the total supply </s><s>[INST] and that's what you mean by narrative driven, we can't really prove it mathematically, [/INST] you I and everyone else in the world has lived in a narrative driven world for the last couple of decades. Right? And with the internet and digital technologies have done, is it opened up the possibility and the desire from people to have a world now where I can validate things. So when I see that headline, I want to see you say whatever happened in the news, if you were the subject of the news rather than have somebody else tell me the story. If I see that you say something is scarce proved to me that it is scarce. And so I think that's kind of a psychological shift, the younger generation is starting to understand because ultimately, you and I probably grew up in a world where parents can tell us the story and we just believed it. You know, dad or mom says it, it must be true if my brother heard a story, what do you do because to google and he looks it up and he comes back and usually tells my parents that you got the story wrong, right? And so I think that, that, that prove ability or that that validation ends up becoming really, really important. And so, you know, look at something like gold. I think that people are drastically underestimating the shift that's underway right now, Gold is one down in value since April, I'm sorry, August of 2020. And so in a Time frame where central banks have had historic quantitative easing literally $6 trillion dollars in the United States, The one asset that historically has been the best store of value and has, uh, you know, in 2008, financial crisis hit an all time high based on the government response has actually suffered uh, for a main part of this financial crisis, you then look at central banks around the world who have been very large holders of gold for a long time and net buyers on a monthly basis for multiple months over the last six months, they've been net sellers of gold. And then you start to look at jewelry demand. So the actual non monetary value of gold And that demand for gold jewelry peaked in 2013 and has continued to fall since. And so what you start to say to yourself is take just the asset of gold, which about $10 trillion dollars market cap and you say, okay, well if jewelry demand continues to fall, even if it's at a slight rate, but it continues to contract. You have central banks that now at sometimes our net sellers and sometimes buyers. Right? So okay, again, contraction there and then from the investment standpoint, the actual price that the daily price of this continues to fall, which is a signal that there's a contracting demand from an investment perspective, That's 93% of all use of gold, only 7% of us used for actual technology and metal conduction and things like that. and we have a $10 trillion dollar asset that It appears and again, maybe data changes and I'll change my mind and other people change their mind, but it appears is on the decline. And so if that happens, you're going to get the contraction of a $10 trillion dollar asset. Well, where's all that value go? And what you're seeing is at the same time, that that asset is contracting. You're also seeing a massive influx from not only retail investors, not only kind of the wealthy and the elite, but also from financial institutions, corporations, pension funds, etcetera, into this kind of digital sound money. </s><s>[INST] So you're saying that there's a kind of shift from gold to Bitcoin because they have a lot of the same properties except one is in the physical space, the other in the digital space. So do you see like central banks quietly potentially switching out uh from sort of gold to Bitcoin? Like naturally just doing, seeing a pattern that you're referring to now, but more drastically into the future where there's a complete [/INST] shift, if you line up the gold community in the Bitcoin community next to each other, they'll agree on all the problems that they that they see in the world, right? They'll actually agree on the solution that Sound money is the solution where they differentiate is the gold community believes that is the analog application of sound money, right? The physical goal that is the solution. The Bitcoin community believes the digital application of sound money. Bitcoin </s><s>[INST] can be defined Sound money by the [/INST] way someone is just outside the system and no one can create more of it, so nobody controls it. </s><s>[INST] This is scarcity is fundamental exactly why scarcity important in money. [/INST] I think scarcity just has this very high correlation to value across all assets, not just money, right? Money happens to be the the unit of account that we use in terms of daily commerce. Um but whether it is um you know, as we're seeing now uh sneakers are, you know, whatever it is, uh scarcity ultimately is that signal of value I think and that's just been the way that humans uh derived value for literally, you know, thousands and thousands of years. </s><s>[INST] Yeah, I gotta say that's my view on life and love in general is scarcity is what makes it valuable. People talk about immortality, you know, I would like to be immortal, but it does, it does seem that when you let go of the fitness of life, I feel like that meals and the experiences you have get devalued significantly like the longer you live, the less value there are in an infinity if you live forever. I worry that all the meaning will dissipate and the same thing would love a quick criticism of sort of dating culture and all that kind of stuff. Like I haven't uh a shocking revelation that I've never been attended data or any of those things. I believe that scarcity and dating and interaction is like intensifies the value of when the interactions do happen, so when they like when love does happen. So in that sense there's something magical about scarcity in the more subjective psychological social world as well. And perhaps money is just another version of that, right? It's just, it's all about the stories and ideas we tell ourselves, [/INST] I think they're actually more interconnected than you're giving it credit for, right? Which is what is money, Money is time ultimately right? The the pursuit of the acquisition of money, right? Of whether it's a currency or true money is because that should give you more time. And so one of my favorite movies ever is uh it's funny because Justin timberlake is in it is this movie, I lose most people at that market in time in time. And basically the premise of the movie is that everyone has a clock that is embedded into their arms. And so uh if you go to work, you basically put your arm underneath when you leave and there's time that's deposited into your clock and if your clock ever hits all zeros, you're dead, you die on the spot. And so there's a number of scenes where people are basically running, you know, to get to you and I give you a little bit more time so that you can get to work on monday and then you work to acquire time. And so basically time becomes this currency. But what becomes very fascinating about it is there are sections in society where literally there's physical places, if you only have, let's say 72 hours or less, you're allowed to go to section one, Section five though because you have years and years and years on your clock. And in this movie, everyone at the age of 25 freezes from a biological aging standpoint, so everyone stays the same, but you may have lived for 1000 years. And so it becomes so fascinating about it is that rich people have time, poor people do not have time. And so in it Justin timberlake, the main character at one point essentially acquires a bunch of time and he's able to go to one of the higher levels. Um, and now he's attending all these Gallas and you know poker nights and all the stuff. And one of the first things that he learns is that in the lower end of society, everyone is running everywhere at all times in the movie because time is so finite and it is so scarce and so therefore why would I walk down the street? I must run down the street in the highest level of society. No one runs anywhere. And in fact if you run, you are seen as lower class because wealth is time. And so that movie is, you know, it's got a ton of kind of things that you can pull out of it. But to me is the perfect epitome of money is time. And so when you start to think about the acquisition of money right? It goes to this whole idea of time billionaire. And I know that um there's probably a lot of people have heard about this already, but If you think of a million seconds, it's about 11 days, A billion seconds is 31 years. And so if I said to somebody, you have to switch lives with Warren Buffett, would you do it? Some people would say, sure not be their initial reaction, but you have to be, you know, 92 years old is the money worth the lack of time, Most people would say no, there's this guy, Graham Duncan who really articulated this well, um and ultimately what ends up happening is you realize time is more valuable than the money, but you acquire the money to gain more time. </s><s>[INST] And the reason is valuable is because of the scarcity of time. We currently have the biology, the physics. It means that this is not just the narrative. We tell ourselves maybe just, I don't know, but it feels like pretty sure we're mortal in that sense. The scarcity there gives value to time. It's fascinating to think about all the thought experiments here of if that could actually be on the economy, if you can actually convert time in a frictionless way to money [/INST] Well, and if you start to pull on this little bit and say, Okay, a young person today, let's say somebody in their twenties has about two billion seconds left in their life, right? Kind of 60 years give or take based on life expectancy. They usually until they start to understand this concept, think of wealth in dollar terms, But dollars are being devalued and so, you know, $1 million dollars doesn't get you what it used to get right. It's kind of an old adage. And so what you're doing is you're pursuing something that ends up losing value. And so it's the constant rat race, it's how do I constantly try to get more, how do I get more dollars, how do I get more dollars? Because even if I say to myself, you know I'm going to retire when I get $100,000 When I get $200,000, $100,000.5 years from now it doesn't buy me what I thought it did. So now I need 500,000 or 200,000 or a million or whatever the number is. And so ultimately what ends up occurring is that the Bitcoin community and many people in kind of this idea of sound money is you want to be able to acquire an asset that not only will hold the value at the store of value over time, but it will actually appreciate over time. And so when you look at something like Bitcoin against the dollar against other types of assets, all of these assets are down compared to Bitcoin right now, some of that's just in the early days of kind of the pricing of an asset, you go from very small to something much larger. But now what you start to look at is well if you have a finite supply of something, what ends up happening is people begin to value it more. And so in a world where dollars are infinite and other fiat currencies are infinite. Bitcoin becomes very, very interesting, very special. Uh and something that is very aspirational. And so I think that's where you're starting to see people say wait a second, this is something where that finite secure store of value is essential to wealth generation and preservation over a long period of time. </s><s>[INST] And if Sam Harris is right, that free will is an illusion. This is really interesting to think about maybe uh time is the kind of Blockchain because you can't change anything and then the physical spacetime of the universe is a ledger, so maybe it won't be Bitcoin, there are places gold, maybe it'll be time once we crack open that. In fact the universe is fully deterministic. So maybe that's what like eric Weinstein is afraid of. Once you figure out the theories of everything of physics will be able to then start trading, create a market out of like the very fabric of reality and that way break it. [/INST] Well if you look at infinite inflationary type currencies you can't do that right because it constantly losing value when you look at a finite asset again that has the probability of the actual finite element to it. Ultimately the wealth is that market place. And so you know I always kind of try to highlight for people The top 55% of Americans, understand something that the bottom 45% don't they invest Right? The bottom 45% consume the top 55% invest and that's why we have a wealth inequality gap and it continues to get wider and wider and wider is because the people who are holding the devaluing assets and saving are watching their wealth be devalued away and there's arguments and controversy over how fast that's happening but it's happening. The people who are holding the assets that have any level of scarcity right? Real estate may not be finite but it's scarce, right? Or it may not be finite but it's scarce. Gold may not be finite but it's scarce. Those assets continue to appreciate against the devaluing currency. And so when you then say no, I have complete finite supply with probability and this transparency around it where everyone knows how much is there and what, where it's going now all of a sudden you and I can transact back and forth that value and it is a representation of time because what I can essentially do is if I gather or acquire more of that wealth, I then can apply leverage to my life, I can use machines, humans or some other resources and basically now free up my time. </s><s>[INST] Yeah, it's a fundamental way you are trading time. Maybe it's a little bit indirect but maybe not uh just because I brought up eric and uh you're on twitter, I'd love to hear your opinions. I talked to him a lot. He seems to have stepped into the beautiful dance of human communication and the social dynamics that is the big coin Cryptocurrency community. Do you have their thoughts on uh engaged theoretic concept conceptualization of the world is just eric in general. He's got a lot of love in his heart and he's got Grace and the way he communicates. But he's also loves to play with ideas and seems to have touched a sensitive point with the Bitcoin community. Is there anything you could say? Uh that's hopeful, inspiring about that whole dynamic that went down? [/INST] So I don't know all the details. Um but what I will say is I've listened to a number of his podcast um and him and there's a whole bunch of people like him, I basically put them in the bucket of their an independent thinker who are courageous enough to speak their truth, whatever that may be. Uh they are humble enough to revisit their ideas and say I got this right, I got this wrong information change, I'll change my mind obviously a sign of intelligence to be able to do that type of stuff. And I actually think that one of the most scarce things in our society are those independent thinkers were able to do all this right. </s><s>[INST] Speaking of scarcity. [/INST] And so to me uh I put eric and the whole host of other people kind of if you look at like the intellectual dark web is kind of a label that's been used, they're actually some of the most important people in our society because they're the people who are willing to stand up against the mass kind of thought process. They're willing to talk about things that others may think are taboo, right. They're willing to change their mind, which all of a sudden has become a bad thing rather than a good thing. And so when I see the exploration of ideas in public, I actually think that those are the people who are most open to the kind of vehement blowback as well, right? Because that's part of what they're doing is that they're eliciting, hey, I'm going to throw an idea into the arena. If it doesn't get attacked, they actually may be more nervous than if there is some level of, you know, kind of war of attrition if you will. And so what I've seen with a number of the people who have done this, everyone from some of the best hedge fund managers and kind of money managers in the world, all the way to what I consider some of the most uh intellectual people in the world is they play with these ideas and they play with the idea and they play with them and they put them and they all arrive at the same conclusion and sometimes takes a month, sometimes it takes years, but they arrive at this Bitcoin thesis. And what's so interesting about it is it highlights something that many people view as a bug. But I think people in the Bitcoin community view as a feature, which is that community. And so what ends up happening is when you have something that is as ambitious as creating a global reserve currency doesn't mean it needs to unseat any of the existing ones but become the global reserve currency of the internet, this digital economy, you need shepherds of it. And so just like a technology company wants to find those loyal fans that are willing to go out and market in the word of mouth and and kind of not only promote it, but also protect it. This technology that is this decentralized thing which uses a financial incentive in order to elicit the buy in, not from a financial perspective, but from a mental energy standpoint has built one of the most rabid, powerful and engaged communities on the internet. And what ends up happening is those people have thought more about these ideas and actually challenged those ideas more than anyone else in the world. And so I've got a lot of folks who will just say this guy marty bent who will talk all the time about the Bitcoin critics haven't done their homework in a lot of cases, so they show up and sometimes it's super intellectual lazy arguments, sometimes actually very well thought out arguments, you know, on the counter to the Bitcoin thesis, but ultimately what ends up happening is you're talking to somebody who's an expert, I don't think about it for 578, 10 years, right? They've gone through every simulation you possibly can and they show up with data examples um and responses now they're not always right, but they've just done the work and so what I actually like about folks like eric and others is as they're kind of going through this journey, they're incredibly smart, right? And they provide or are they apply a lot of intellectual rigor to some of these arguments And so what it does is what does it do, its marketplace, it keeps people honest. </s><s>[INST] Uh let me sort of make a few comments. It's kind of interesting as you're exactly right. Uh maybe the blowback is part of the mechanism that actually develops these ideas and so on. I do want to kind of speak to a little bit of the toxicity that I've experienced in the Bitcoin community. I kind of see it the Bitcoin community. I think you paint a really nice picture, which I kind of see it as an immune system that protects against of uh the viruses that are bad ideas that said the immune system can destroy a body, right? Uh and uh the thing you mentioned about eric and maybe about myself uh and in general, just people exploring ideas is there is a dunning Kruger effect which is when you first start exploring ideas deeply, you have um overblown level of confidence about like how much you understand and that's actually the process about learning and you realize you don't understand much what I've noticed that the Bitcoin community is uh they're not as a patient with the basics of the dunning Kruger effect, like if I step in and make declarative statements about Bitcoin like I, you know, I read a long time ago uh the white paper like at the cursory level I felt uh that I understand the technology, this is basic intuitions, you know, I didn't think about the social dynamics, I didn't think about any like financial implications and a lot of the deep actually the ongoing innovations and all that kind of stuff. But I thought I understood that technology and so I step in and make declarative statements, I think those are the first time you say, okay, what's the role of Bitcoin in the world? You start thinking about it deeply and then you make statements. The toxicity that you get in those first few statements is really off putting to me. I'm somebody that tries to communicate love and live that with everything I do. And uh there is a level of disrespect that I've experienced. Not directly just observing others. People have been mostly kind to me and I appreciate that. But if you're going to criticize me about my exploration of ideas in Bitcoin, do you have to also acknowledge that I'm a human being, they got like a PhD and stuff like I did some hardship uh that it could be in farming or it could be whatever, like I've lived life and I really thought deeply and I really care like I know a lot of shit and it's possible that I actually have a lot of ideas that you can learn from now, if it's agriculture find or if it's artificial intelligence find like I know what I'm talking about, about certain things and I could be wrong about a lot of things and there's like an exchange of ideas that's, that makes the, that mechanism that you talked about um more efficient sometimes when the blowback is too strong too early on, the development of ideas is just inefficient. And I'm not sure if there's uh, you know the way it was explained to me is that for so long that community was like bombarded with just like bad ideas like criticisms. There's just overly sensitive now to like two bullshit. They're like triggered by statements like they've heard it all before and they're like, oh there they go again with the same old arguments. But that doesn't mean that um, you know, you have to sort of, I guess developed patients and so on. Especially when you feel like in my case that the person is coming from a good place, right? I don't know if there's something you could say that's positive about the future of this kind of overcome this toxicity. [/INST] I think there's a couple of trends that are all kind of coalescing here, right? In these types of experiences. So one is when you look at a community, there's always a spectrum, right? In terms of, there's some people who over index on kindness uh and stupidity, right? And there's some people who over index on intelligence and basically just being an asshole, right? And then you get everyone in between. And so like uh naturally as we know, the extremist ends of any community end up being the loudest, usually right. The second thing is, um there is from the outsider view, like at the beginning of the exploration of ideas, uh it's very much a learning process, right? It's it's, I don't know if I understand this or not, but here's ideas, a BNC from the internal perspective, there's a trillion dollars of value at stake and we must protect it with our lives, right. The truth is probably somewhere in between there. Right? Again, the world is not black and white, there's there's this kind of more gray area that I think actually um is where most people exist. The other thing that's at play here is uh I think the Bitcoin community understands the internet and internet culture and narratives better than almost anyone. And so you see this with kind of the uh just complete destruction of narratives with memes and um just the visceral reaction and the use of things like Reddit and twitter and Youtube podcast, just areas where um I think a lot about uh if you are an upstart, right? And you are going to go challenge the most well respected elite uh kind of establishment institutions in the world. If you walk in in a suit and tie and you say, I'm here to debate you with ideas, you're gonna get your clock cleaned because they're going to try to out their lawyers, the regulators, their lobbyists, like all this stuff. If you instead say I'm going to me, me to death on the internet and I'm going to control the public narrative, </s><s>[INST] you've shifted the power, The asymmetry of power is [/INST] more symmetrical enough. The ultimate insurgency, right? If you bring it back to the Yes. And so when you think about this, you have to lean into the advantage that you </s><s>[INST] have. And [/INST] so what ends up happening is you and I would absolutely lose it if we saw Jpmorgan or Goldman Sachs with the Federal Reserve start tweeting memes right? It would almost the the validation that would give to the medium and the even playing field that it would provide would pull these establishments down to the level of what is this upstart. But now what you're starting to see is that the Bitcoin community, even though there is some level of toxic toxicity at times, even though there's this visceral reaction, sometimes there's even what I would call um bullying or or or kind of outward projection of things, right? Even though it may be a small percentage, it will happen every once in a while. What they do understand though is that these establishments are made up of humans and what you can actually do one of the best ways to pick apart an institution is to recruit from inside of them one by one. And so what you're starting to see now is I get the messages on twitter and linkedin all the time. Hey I'm a banker by trade, I'm a Bitcoin er at heart, right? And so what you're doing is you're essentially infiltrating the organizations not in in physical uh you know, population but with the ideas and with the philosophies, </s><s>[INST] banker in the streets Bitcoin and [/INST] the sheets I </s><s>[INST] like it. Uh that said in terms of ship posting and memes, I gotta say um uh like bring it on because I believe uh in terms of asymmetry of power, I believe in that love will save the world, not memes or at least uh good, good vibe memes as opposed to ship posting. It's a, it's an interesting battleground though, it's an interesting battleground to think about. [/INST] The other thing I would say two is um one of the elements that's always kind of funny to me is how much of the entertainment is love, right? So when you start to think about how many of the memes that are posted for example, or for outsiders versus insiders laser eyes right, Which seems absolutely ridiculous. Elementary and and frankly beneath anyone in any level of power or influence in the world somehow has congressmen and senators who have done it, they're not trying to convince their colleagues in elected positions to become Bitcoin ear's, they're speaking directly internally to the Bitcoin community. Yeah, </s><s>[INST] there's some sense in which yes, memes is love, even give hearing Bitcoin is love. They're trying to convert [/INST] me the one that you you have to laugh at. Probably my favorite one out of all that is I've seen on multiple occasions. Uh you know, Mark Cuban a couple of years ago, kevin O'leary who were, you know, wealthy people, billionaires, etcetera. And you have people on anonymous accounts who who knows who they are telling them have fun staying poor. It's just, you know, it's just again part of a community and I think it's it's a it's a feature, not a bug, there's bad aspects to it at times, but I do think it's a net positive, </s><s>[INST] just like the immune system. [/INST] It </s><s>[INST] does a lot of crappy stuff, but overall it's a, it's a major net positive. Maybe this is a bit of a personal question for me, it just out of my own curiosity, but I've talked to Ray Dalio a few times. So Ray Dalio I think was one of those people that took that journey. Uh the Bitcoin journey def def thoughts about him specifically about that whole world and about the journey maybe of others. They're going through the same process because Reyes at least from my perspective, I'm a bit of an outsider. He's one of the most uh insightful and deep thinkers about investment, about finance about economics in general, um actually about life. So it's interesting to see him go on that journey. You have something to comment about Ray or just those kinds of people in general. [/INST] So if we look at um what I'll just consider the legends of Wall Street in general, right? Um there's no denying that they're incredibly intelligent. Uh there's no denying that actually, especially in the hedge fund world, there's some of the most open minded people uh in terms of their willing to change their mind when they get new information. Uh there's no doubt that they are historians in the sense of having studied financial markets and cycles over time. Uh and also one of the things that I really respect about all those guys is almost all of them are willing to put ideas out via various writings that they do uh and accept the public criticism, right. Whether it's Howard Marks Ray or others, uh they will put this stuff out in public and uh sure there's a lot of people who are supportive and kind of are part of a fan base if you will, but there's a lot of people who also think that sometimes they say stupid things and so putting that out takes kind of courage, right? Um I think Ray is actually the most fascinating though, out of all of these kind of legends of Wall Street in that um he understands debt cycles, He understands currencies. He for a while now has been all over and famously said, you know, cash is trash, uh investable assets right? He just, he kind of like, just knew all of it and for a long time, bit corners said Ray, you understand the Bitcoin argument, you're just missing the last part, which is Bitcoin's the solution, right? And so he was gold and some other ideas, but I think that he's a perfect example of when you are part of uh, the establishment people view you in a very static way as the leader of a part of establishment, but whether it's Bill Gates, Ray Dalio or somebody else, each one of these people were innovators and challengers to a system, they were up starts at one point. And so it's kind of this idea that like if you live long enough you eventually become the man, right? And so, you know, Gates is a good example, right? Warren Buffett is a good example. Ray Dalio is a good example, etcetera. And so, uh, you have to give credit, I think, to Dalio in the sense of he kept an open mind about all of this and more so than many of his peers has continue to do the work and come around to this idea. Uh, and now I don't want to know if I wanted to say that he's a Bitcoin proponent as much as he believes it is one of, you know, a portion of assets that can be a solution. And so to me, when you start to convince those types of people, when it's, you know, paul Tudor jones, a Stanley Druckenmiller, Ray Dalio's Howard Marks, not even writing about it, saying, hey, you know, I was anti Bitcoin and put a ton of intellectual rigor into it, But thank God, my son bought a bunch of our family, right? And uh, and kind of, we've had exposure to it. I think what it does is more than anything, it's not going to convince somebody to go and um, you know, take it seriously or go ahead and make an allocation, it reduces career risk. And so if all of a sudden when paul Tudor jones and Stanley Druckenmiller come out and say, hey, I own Bitcoin, and here's why every other investor on Wall Street now can say to an investment committee, well, it's good enough for paul Tudor jones, it's good enough for Stanley Druckenmiller. And so I think that it's very interesting because Ray doesn't just represent Wall Street, I think Ray in some weird way, represents this like macro economic investor. And so some of those are in hedge funds and some of those people would be like, see IOS that organizations, some of them would be at corporations and some of them are just kind of retail investors. And so you can see this, um, kind of inflection point throughout the adoption of Bitcoin, right? There was infrastructure that got built, okay, that kind of led to more adoption, there was a certain individuals, right? Usually they were kind of technology oriented, entrepreneurial billionaires, they would buy it and come out and say it, okay, that led to inflection points. Uh, you started to have some of these kind of wall street legends come out sort of financial institutions started and now you're seeing corporations start to do it right eventually there's gonna be a central bank that does it. And so you kind of walk through that line and what you understand, it's like, it's the same thing every time it's just somebody new, right? That that path, right? That that Bitcoin is journey if you will. And I think that that is almost the beauty of it is uh if you short circuit the journey, it's almost like somebody doesn't appreciate it, right? If you take, let's say somebody who's a young kid and you just give him a bunch of money and they don't have to work hard for it. I don't really appreciate it </s><s>[INST] well. And Ray Ray actually has a book principles, right? And he talks about the hero's journey. So he's like living in some sense in terms of, you know, thinking about digital currency in general, like digital finance, it's a one of the big transitions transformations of our world in some sense, it's not just about money or you could argue that money is everything. I mean it's like money isn't just the narrow definition of money, Money is really everything. And so where you could argue that sort of Cryptocurrency is like the base layer of this transformation to the digital space and everything else would just be built on top of it. [/INST] I use a different word um that I think is kind of closer to your world, which is it's ultimately automation. And what I mean by that is uh you know, before 1970s or 1980, all the assets were analog. And so we have analog assets, physical stock certificates, physical bonds, right? Physical D Do a home. Uh you have to physically exchange them when we wanted to increase transactions and increase kind of global finance and access. We took those physical assets and we created electronic use iP assets. So now we have in centralized databases, kind of file represents the asset that's sitting somewhere in custody and you and I can transact them a little bit easier, but still centralist, there's still some bureaucracy and you know, maybe it takes two days to transact rather than actually mailing it across the world. Now, what we're seeing is a transition from the electronic uses to these digital assets. And so if you look at again, just let's say money or currency, every currency in the world is going to be digital. You're gonna have a digital dollar, a digital euro yen, R and B. You're going to have decentralized kind of open source uh money like Bitcoin, you're also gonna have private currencies like facebook's attempt at DM uh and there will be others that will try to do this. And so when you get everything digital right? I think that's the kind of the first step. Everyone focuses on the competition at the technology layer essentially goes away. You get some level of feature parity and sure there's bells and whistles on each kind of implementation of a digital currency. But at the end of the day, the technology is relatively the same. Uh And ultimately what it will do is it will facilitate the adoption of digital wallets. So you have to have a digital wallet regardless of what digital currency you have staying with me. Same with everybody else in the world. But what it does do is when you kind of push away and reduce the friction of competition at the technology layer, it moves the competition to the monetary policy layer. And so when you get to that layer now, it becomes interesting because all of the currencies are the same except for this one right now and maybe there will be others in the future. But but for sure, Bitcoin today and people may try to replicate in a private manner or something. But Bitcoin is kind of the the only finite scarce digital some money. And so when you then have that pretty big difference in that competition at the monetary policy layer, it's actually not going to matter where you get paid right. And what I mean by that is like you and I both live in a single currency environment, I get paid in dollars. I historically have saved in dollars. All of the assets in my life are denominated in dollars and I owe my debts in dollars, whether it's taxes or in the private market and I don't have to worry about foreign currencies, I don't exchange anything. The only time I would ever think about another currencies, I'm going to another country in their single currency environment and in order to change or exchange my currency, I go to the bank or go get ripped off at the airport. Like those are my two options. It was high friction to change between currencies when the competition of technology is kind of innovated away. Now I can get paid in dollars, these digital dollars and with a click of a button switch into any other currency in the world. And so what ultimately happens is value and liquidity is going to coalesce around the best monetary policy. And so you get in this very weird world where even if the United States says, hey, you're gonna get paid in dollars, you have to pay your taxes in dollars, you're gonna start to see people operating a multi currency environment where they say, okay, I got paid my digital dollar, click a button. I save in Bitcoin, it stays there tex or grows my purchasing power. Oh I need to pay my taxes. Let me switch back into dollars with a click of a button and pay when you go to a multi currency world, it's not just about currency, it's now multi asset world because not only is the currency digitized but that same technology is used to digitize stocks, bonds and commodities as well. And so today we live in a very fragmented financial world where basically I have a brokerage account, have a bank account. I may have an alternative asset account et cetera. When I can put all those assets in a single digital wallet and I can then go from asset to asset without having to go back to a single unit </s><s>[INST] of account. Like frictionless, going from acid acid. Yeah. [/INST] So now what you end up doing is you start to open up the possibility for machine to machine transactions. So today if you and I write software code for two machines to transact with each other, they can't transact physical currency and in many cases they can't actually transact the electronic, use it currencies or assets either because there's too long at settlement time so you can't get through automation right? So the whole idea of like the car is going to drive over a strip in the road is going to pay the toll right? That can't happen right now because a lot of the transaction won't go through, right? And so I always joke that like in an automated world, it's like a cd rom. What we're trying to take cassette tape player assets and put in the cd wrong. It's just incompatible technology </s><s>[INST] references, nobody understands at this point. By the way you [/INST] to update your reference, I probably do, it's like taking a cd rom trying to put an Mp three player into streaming. But, but I think that the reason why that becomes really interesting is when you start to create these digital assets now, you open up the world of possibilities. So when new technology is created, you can do two things. You can either create new things, the world's never seen before or you can use it to improve the old world most people because it's the easiest thing to think about, want to improve the old world. So an equivalent of this would be when the internet came along a media company that had newspapers, would say, hey, we should take a pdf of the newspaper and we should put it on a website and now anyone in the world can go to this website, they can read the newspaper today. That was valuable, but it missed out on the ability to change headlines to test to put multimedia, to distribute it differently to, you know, do all kinds of things that today, we understand the internet really empowered. And so what I think we're about to watch happen is we're going to digitize the assets. We're gonna put them all into these digital wallets, you're going to get automated technologies where machines cannot transact with each other and we're going to do simple things. Like why do we pay people once every two weeks? Why don't we just pay them at the end of every day or why don't I literally stream payments to you on an hour by hour basis based on the work you do. It would solve incredible economic issues in our country and in countries around the world. But historically businesses can't do this because the technology problem, they can't keep track of it all. How do they pay everyone every day? How they pay one every hour? Like you can't do it. </s><s>[INST] Yeah, it's funny the vision of the future you're painting, it's kind of an exciting one and it almost makes me sad looking into the future and we'll look back at this time. It's like is how incredibly inefficient financial transactions were, like the transaction of value of any kind. Like how like went to pay each other, like there has like processes, there's like payroll and all this kind of just the entirety of the transactions is just like painful. Almost all transactions are painful. And even and the companies that innovate to make the transaction is a little bit more frictionless, like amazon with one click purchase button, like went out huge. But even that's really painful, it's actually really interesting, especially when you start to move that into the space of data. There's a lot of people thinking about privacy and data and like we put can we uh like convert data into like the money. It's just so that you can pay for how much you reveal to the company's about your own private data that can then be used to assign value to you. So you can use the service for free if you hand over the data. But there's like explicit transaction going on so you can empower all those kinds of things that will just like fundamentally change our world. That's really really really exciting. [/INST] One of one of the most interesting things to me um is invested in a company called Bridget. What they told me was they said $8 billion dollars was paid to the top four banks last year on overdraft fees. So literally they took $8 billion from people who didn't have money in their bank account. Right? And so when you dig into why is that a lot of times it's not that the people don't have the money, it's actually a mismatch of the payments. So what ends up happening is you get paid on the first and the 15th but on the 12th your netflix bill hits On the 13th, you went grocery shopping and on the 14th your car payments hit You overdraft and then on the 15th to actually get the check and you're able to pay not only the overdraft but for the expenses that you have. And so something as simple as just getting paid at the end of every day immediately would eliminate, you know, some big percentage of those $8 billion dollars of value that flows to large institutions on overdraft </s><s>[INST] fees. Yeah. And also, I mean this whole process with overdraft fees and just many of the financial transactions we have to live through today forces many of us to be like accountants like to understand the different mechanism of financial, like the movement of money as opposed to you, which is what we want to do as human beings operating at higher layers of like providing services for others of like following your passions and like working for others, like doing cool ship or, or you know, basically providing value, exchanging value in the world and not thinking about the money, the money takes care of itself. And then you see the results of its your you're able to think in terms of money but not have to know how the, like the accounting works, [/INST] automation simply freeze humans up to do more creative </s><s>[INST] work. Right? Like [/INST] that, Like that's it and which </s><s>[INST] is why they use the term, which is why you use the term automation, which I think is kind of brilliant reframing of all of this [/INST] because ultimately digital technologies are merely the conduit to usher us into that world. And I think the most fascinating part of this entire industry is people who are trying to figure out now that we're going to have these digital technologies, how do we usher in that automated world faster. And so there's people who are building all kinds of incredible things, right? There's literally um uh some technologies where you can stream uh for paying for consumption of content, right? There's I saw somebody recently who they basically said, hey I have created something but it's not going to be released until everyone and almost like a go Fund me type situation pays for in combination that gets unlocked. And so when you start to think about this, it's um not only innovation on the technology front is innovation around the way that we form capital, it's the way that we organize resources, it's the way that we build companies, it's the business models, right? It's the application of those technologies, all that stuff starts to change and go back to 22007 when the iPhone came out, Uber wasn't possible, right? He's going on the line. All these companies that weren't possible before, when the digital technologies are kind of adopted on a global scale. I think that we all myself included drastically underestimate how fast and how big innovation can be because it's just hard, right? Like we like to think literally and that's not how the world works. </s><s>[INST] Yeah, I I do find it kind of interesting uh it is N. F. T. Base but I don't think it has to be uh this idea of I think big clout it's called or whatever. Uh The idea of sort of investing in individuals, it makes me immediately think about investing in ideas. So even just the words you speak having value and sort of if you have a frictionless like automated financial system then you could do a bunch of interesting things about what it means to add value to the world. They I don't know if bit Claude is currently an efficient representation of that but I am truly happy that however that thing works. I'm just one notch above Vladimir Putin which is one of the that's like one of the bucket list items for me to have a list where I'm one notch above [/INST] Putin. But I think you're talking about here is important because there's historical examples you could invest in a patent in some situations you can invest in an organization that has an idea, right? So these are super inefficient given kind of the vision that you're painting in terms of like investing directly in an idea in a super efficient automated fashion. But that's how the technology evolution works. Right? Is it's really hard to do it first and then it slowly kind of becomes easier and easier as technology uh is more prevalent. The other thing that I think is interesting is this whole idea of investing in people. If you really think about the origination of that is I would hire somebody right? I pay you money and then you're going to create production. But I take the lion's share and you don't now, there's things like these essays, these income sharing agreements where basically I will educate you on something, train you on something. I'll put up capital, right? And then over time you'll pay me back plus profits is some version eventually, I don't know what it looks like, but being able to get upside in somebody's success for having risk capital early on, doesn't seem that far off. See it in professional sports. You see, you know, a lot of these things. And so I just think that a lot of, um, the focus right now is on the technology. But ultimately, these are ideas that are very old and have had lots of success in traction. And we're just merely standing in the way of the evolution of these ideas with new technology. And so, uh, it's easy to get caught up in the technology. But when you really zoom out and look at it from the ideological stand point and kind of the progress of humanity, it's a foregone conclusion. This stuff is going to happen </s><s>[INST] just how I think the world is waiting. And some of us are trying to create that future world, which is like, what are the applications of this technology that will transform the world? And then, you know, I hate the term of killer apps, like cool ideas that are implemented effectively at scale that transformed the world. There's been there's been a lot of different ideas popping up like the there's a lot of ideas about social networks that are built on top of the technology and all that kind of stuff. So but let me actually drag us back down to something basic. If a person wanted to buy Bitcoin, store Bitcoin, how do they actually do it? [/INST] Yeah so there's a couple of different ways to kind of acquire Bitcoin and in every way you've got to exchange some form of value for Bitcoin right? Which is part of why it has value because you're giving up value. So um in one way is to exchange energy and computational power for Bitcoin? So you can mine it you can literally take a computer power that you have, you can rent it to the network and run that software and then it will pay you a portion of the kind of daily revenue off that system and you can acquire Bitcoin in exchange for your power uh and your computational um kind of contribution </s><s>[INST] and that's the fundamental principle behind Bitcoin is the proof of work. So I got 100 bucks uh like I used cash up Uh you know they there's going based there's all these exchanges like how do I convert my $100 to uh Bitcoin. Is there something disclaimer, this is not financial advice and this is just us talking and just your opinions that do not use this to invest. Um or take us financial expertise that said, uh, like uh, is there something you recommend? That's an easy entry point for somebody that's like, I wonder if I can convert this $100 into whatever amount of Bitcoin. What do you recommend? What are the options? [/INST] So there's a lot of options. I'm heavily biased that went out and I scoured the market, looked at all of them, I've invested a lot of money to company called Block Fi that basically um basically it's financial products for crypto investors. So you can go, you can take dollars or other currency you have, you can convert it through an exchange. You can leave it on uh, these interest bearing accounts, you can earn interest just like you would earn in a traditional account with higher levels of interest because it's this new thing. Um, or you can withdraw it and you can put it into cold storage on a hardware device, You can leave it in a software wallets, kind all these storage options. So block five is, you know, kind of the one that I'm biased towards </s><s>[INST] because the block fights or sorry to interrupt. So there's a block Fi is uh, Bitcoin only or is there an exchange with other [/INST] cryptids got a bunch of different ones? Yeah, they basically are agnostic to what it is. Um, but they provide a kind of financial, you know, products to crypto investors. </s><s>[INST] Okay, so you mentioned a few interesting ideas that'd be nice for people who may not be familiar with it. Cold storage, hot storage. What does that mean? So like I go to a website and I convert dollars to Bitcoin. That's a kind of storage that's like online banking. Right? What else is there? [/INST] So there's a couple of different things that you can do right? And let's use the legacy system as kind of an example. So if I want to get currency and I put in my bank account, it sits there. I have to trust that the bank doesn't go under. Nobody steals it. All this kind of stuff. There's insurance for it right there there's all these kind of benefits in the legacy system to make sure that as long as I don't have you know millions and millions of dollars there, I'm gonna be protected pretty much if anything happens through F. D. I. C. Insurance. If I want to do that. I'm taking that counter party risk though. So it's mitigated. But there's still counter party risk. I'm counting on that bank. But it is easier to move it around, right? If all of a sudden you call me up and say hey send me some money I can press a couple buttons on my computer and it will send it to if I want deeper level of security, I can go and I can get the physical dollars and I can go and I can you know, put under my mattress, right? And I can say you know what, it's not gonna be as easy to send it to you immediately. But if I really want to I can go underneath my mattress pretty quickly, I can grab it, I can get it back to the bank and then I can send you the money. The third thing I could do is I can basically take those physical dollars out of the bank and I could go and I could go put it literally uh you know in a vault somewhere that I don't have control over that's behind 10 passwords uh and biometric scanning. And like it's really difficult to even get to it right. So you can almost look at it like there's three stages of security that you could have in nutritional world. The same thing is true in Bitcoin. So you could buy Bitcoin on any exchange, you do it on Black Five, but you also can do it on places like coin based gemini cracking etcetera. </s><s>[INST] Also cash [/INST] up cash app, you can </s><s>[INST] do it cash. I think I I think there's still sponsoring this podcast. [/INST] I'm </s><s>[INST] not biased at [/INST] all. So once you get Bitcoin on any of these venues, you can leave it there on that venue. Now. The trade off is you're taking counter party risk. So somebody else is responsible for the security and the protection of it. Uh in many cases big well known companies who have billions and billions of dollars of assets, they have higher levels of security. That's why they're well known as white people, trust them whatever. But you are taking counter party risk. It is easier to quickly send to somebody. So the so the trade off of like ease of use but counter party risk is big. And then the Bitcoin community specifically is a huge thing of uh they really really have a cape for not leaving the Bitcoin. They're right for the obvious counterpart. The second thing you can do is you can basically get it off of an exchange and you can put it in some level of kind of what I call a second layer of storage that second layer storage could be hardware device that you can quickly just grab off your desk and plug into your computer and immediately use </s><s>[INST] that's what they call like a hardware [/INST] wallet. Where wall or you can have some sort of software wallet right? Where it's not on an exchange but there is some level of in between between the hardware wallet and the exchange in the software wallet. </s><s>[INST] But the software wallet is connected to the [/INST] internet. Yeah. And so um if you kind of think of it as like the exchange. Software wallet, hardware wallet and then there's something called deep storage, right? Or cold storage. Um And this is you know literally there was a company called Zap. Oh that would put things in deep cold storage and it was literally buried in a mountain. So like the odds that somebody physically going to go there. There's armed guards, there is, you know, kind of all this type of stuff. But again, you're taking some level of counter party risk because they have a Bitcoin. And so the saying or the phrase is not your keys, not your coins or as my buddy, Isaiah Jackson came up with, he said uh uh not your keys, not your cheese, right? In terms of uh sovereignty is important, right? And ultimately, this goes back to kind of the beginning of a conversation around Bitcoin's ethos, sovereignty. Right? Giving the power back to people, you don't have to rely on uh this infrastructure in order to be able to participate in this monetary uh kind of economy which you are now able to do as you're able to use digital sound money, you're able to keep control of it. You and you alone are responsible for it. So the idea of personal responsibility um and then also you and you alone make the decisions as to whether you hold onto it or you use it without censorship. No one can tell you what you can do with it or can't do with it. And so the purchase and the storage, um what I find is depending on who you are, there's varying degrees of kind of concern or decisions that get made there. And a lot of it comes down to personal preference. The Bitcoin community though absolutely will over optimize for uh sovereignty and kind of hardware or cold stores. </s><s>[INST] I wonder if you can sort of comment on that because you have uh, both sort of cash app and the block five and Coinbase, like you can store it that you can purchase and trade it there and store it there and so on. But ultimately they're saying, you wanna, you know, keep some of it there, but you want to move it to the hardware wallet and the cold storage of the hardware wallet is like, you can disconnect it from the computer because ultimately stuff that's connected to the Internet can be compromised, can be controlled by governments and other parties and so on. What are your thoughts about sort of practically speaking for maybe like a regular citizen, what's, what should be the role of the hardware wallet in their lives? [/INST] Yeah. So at the highest level, I just think that like learning about it is important, right? So even if you only have $5 equivalent of Bitcoin going and understanding here's how it works. Here's why it's important. Here's how I would actually withdraw from an exchange under the hard wall. Like that alone just as an intellectual exercise is a worthwhile pursuit. And I think people should go do that. </s><s>[INST] Actually go through the process of the steps. So you feel like you can, you can do it. Yeah. [/INST] It's kinda like if I said to you, you know, hey, we're going to go buy an asset and you never went and looked at it, you never went and uh, you know, made a decision like sure, maybe I did it, I didn't do it, but like you didn't actually experience it right? And so I think that that's an important part. The second thing is uh each person is different from a, how they view this asset. So there are some people who are speculating right? There's three use cases for Bitcoin, their store value, medium of exchange and speculation. And the people are speculating, they can't put it in deep cold storage because they need to be able to trade it. So what ends up happening is they fall in the bucket of like high risk, high reward, they're trying to trade, they're trying to do all these things and sure maybe there are profits that they can generate if they're good at it, but also they're introducing a lot of risk And so that person is very different than the person who says, Hey, you know, I bought one Bitcoin and I'm gonna save it for my child, right? I'm gonna give it to on their 18th birthday. And so when you start to look at this, what you end up saying is what are you actually purchasing this for kind of like, why are you doing it? And then what's your time horizon and what ends up happening is more and more people in the Bitcoin community have longer time horizon is one of the advantages to this community, right? If you look at the on chain metrics, 60% of Bitcoin haven't moved from the digital wallet in which they sit in the last 12 months. So even though it's appreciated hundreds of percent on the upside, There's been lots of volatility, a 50% drop in a single day in terms of the us dollar price still doesn't move. And so these are the kind of long term holders right? These are the iron fish or as recently it's become popular the diamond hands right hands they're just they're not going anywhere. And so I think that those people are much more likely to not have their Bitcoin on exchanges or in software walls they've got it in some sort of like highly secure environment. Uh and what and one in which they have deep sovereignty or some kind of prevalent sovereignty. And the reason for that is because they have that long time horizon they don't want to be um kind of convicted around Bitcoin sound money, macro environment all the stuff and then they make a mistake because they trusted a B. C. D. Company. Uh and that counter party risk that ends up actually being you know fatal or detrimental. </s><s>[INST] So again this is not financial advice disclaimer. But let me ask. So you in terms of investment advice on Bitcoin. So you see Bitcoin's potentially not just the thing that you speculate over like buy and sell buy and sell buy and sell, but it's something that you can just buy only. And I believe I've heard the own uh quite a large percentage of of your wealth in Bitcoin and you're basically buying only in storing long term. So that's something that's a legitimate way to approach Bitcoin in your recommendation. [/INST] Go to other cultures. So if we remove ourselves from the western world culture of investing in Gamification of financial markets and the Financial ization of everything, let's say we go to uh the culture of India for hundreds if not thousands of years, families basically saved their wealth in gold and in jewelry and in these hard assets with the expectation to pass it on to the next generation. And so it would be blasphemous to sell the family's gold in that culture right? You know your your great grandfather gave it to your grandfather, your grandfather gave it to your father, your father gave it to you. Right. And so in that culture, the long term kind of holding is the default. I think that what Bitcoin has presented again is a digital application of the exact same thing which is that while everything else in the world is being devalued that is denominated in a currency that is being inflated away whether it's quickly or not, this finite supply, this scarce asset ends up accruing more and more value over time. Right. And so um I think that for me personally, um I've got over 95% of my net, worth that's in this. </s><s>[INST] 90 over 95% of your net worth. [/INST] There's two important caveats to this one is I didn't buy some Bitcoin in 2011 or 12, right? And then also appreciated a bunch and it grew into that. But from a cost basis perspective, you know, put $100 and now it's a ton of money instead. What I did was I basically in 2018 saw Bitcoin from a US dollar price standpoint was falling and falling and falling and in december 2018 so take about 50% of my net worth and converted from dollar denominated assets into Bitcoin. So it's very kind of intentional decision with a very specific view on the world as to like why I was doing it. I then essentially just let it sit there grow whatever Until the spring of 2020. And when I saw the government step in and start to say, hey we're going to really be aggressive in terms of interest rate manipulation and quantitative easing. I then decided to go ahead and take basically the remainder and start to convert it as well. So became very aggressive in doing that. And so the way that I look at it is that's actually my savings, Right? And so in some weird way if I said to you know what's the dollar worth, you'd say, well a $1 bill is worth $1, right? Bitcoin to me, I did nominate my wealth in Bitcoin, so I think of one Bitcoin is worth one Bitcoin, not one Bitcoin is worth 115,000 or 70,000, right? I did nominate everything in Bitcoin when I make a purchase in my head, I'm calculating how much Bitcoin in my spending right now. Right, Well guess what happens when you have a devaluing currency as the denominator? It doesn't matter right? Like you're you're financially incentivized to spend or invest trying to consume uh when you have an appreciating currency all of a sudden you become much less consumptive in your behavior because you're actually trading off future purchasing power for the consumption today. It's </s><s>[INST] fascinating to think that if if uh when you move about this world, you think in Bitcoin, you behave differently is if you think in dollars, that's really fascinating [/INST] People, but but here's the thing is the last 50 years or so is actually the outlier in history. Most people used to think this way it's only when a fiat currency got introduced that one argument, the positive argument or perspective is there was an explosion in growth, but really it's because there was a financial incentive to consume, right and there's nobody better in the world than the United States at consuming and we consume anything and everything. And if you want to see a great example, look at how big the coca cola's are at Mcdonald's right, you know, you go to other places, they don't serve them that big. And so the other example, there are the negative argument is we have to consume Because if not you end up being the bottom 45% of Americans that help no investable assets and actually just having their wealth devalued way. So holding the dollars end up being a very bad economic decision. And so when you then switch to this sound money, you say, wait a second, why would I, if today I can trade one Bitcoin, you know, back in october of last year, one Bitcoin for $10,000 why would I spend that if at some point in the future, whether it's A month from now or 10 years from now, I could trade it for something much, much more than that. You just become much more of a um uh anti consumer and much more of a long term thinker. </s><s>[INST] Yeah. From the individual perspective, it's pretty powerful. I wonder, I mean, I think that's an interesting debate. What's better for the long term economy? No better for the growth of the civilization because capitalism, it's fascinating. Uh it seems to, it seems to work pretty well. There's this kind of like eric Weinstein says that one of the problems is for the past several decades this whole economy society is built on the idea that we have to keep growing, like it depends on that idea. And it's a good question whether that's going to result in huge problems or if like a college student on a deadline, the the dependence on growth will mean that we'll have to grow like the fear of [/INST] death were forces to grow. But I think there's a false equivalency between um we're dependent on growth. And then if the world was denominated and sound money, we don't grow, what I think ends up happening is we remove a lot of the society's bullshit because right now when the money is free of the currency is free, come with all kinds of crazy stuff and people will give it to you right? When all of a sudden it's really, really valued by the population. </s><s>[INST] The decisions are better. [/INST] You have to provide real value in the goods and services you provide letter to get them </s><s>[INST] to give it to you. There's less room for corruption, less room for manipulation. That's in like that's not actually productive. Uh definitely. So you said you moved a lot of your investment into Bitcoin is there uh, when you look to your special human being in many ways. Uh so you're like a strategic thinker, but you're also like a deep thinker about this whole thing. But when you look at a regular plug like me uh in terms of just investing in moving into uh thinking about Cryptocurrency, is there a strategy that you recommend? What are the different options about investing into Bitcoin? [/INST] Yeah so I think that there's just kind of timeless advice when it comes to uh investing or acquiring an asset in general dollar cost averaging is usually the best way to think about it. And what I mean by that is Um most people don't just have a pile of currency sitting there right? It's not like they have $1 million that situation aside what happens is they trade their hours and their effort for currency. And so as they get paid every two weeks let's say um the best way to acquire Bitcoin without having to worry about timing markets and being a professional trader is to simply take whatever the percentages that you want and to buy Bitcoin when you get a paycheck. So if you get paid on the first and 15th of every month On that day you should go take you know let's say it's 3% of your paycheck. take 3% go buy Bitcoin. Don't worry about what the price is. Just do that over time. And the reason why that's important is um if in december of 2017 when bitcoins at $20,000 it was the height of kind of this last big upwards movement, you have taken all of your money and you had put it into Bitcoin. You would have had to wait almost three years just to get back to quote unquote break even in us dollar terms. If at the same time you had simply bought then and over the next three years bought every two weeks, you would have been up hundreds of percent Three years later because what ended up happening was you bought a bunch of Bitcoin when it was at 15, 10 9, 834555, you know all the way back up on the other side. And so dollar cost averaging is one of these weird things that it almost sounds too easy but what we find is in America, we have a lack of financial education and so rather than try to be smarter than markets, what most people are better off doing is just saying, hey, you're, what's called asset allocation plan, I want 30% in stocks, I want 10% in real estate, I want this, this whatever and every time you get your paycheck, just think of it as a savings account, right? Just put it in based on those percentages and don't think about it. And over a long enough period of time, what we find is almost anyone in the United States, right? There's exceptions, but almost anyone in the United States can become a millionaire in their lifetime if they follow these plans and have that long term view and they allow compounding to work for them. </s><s>[INST] And so don't look at the price of Bitcoin and all that kind of stuff. Just pick a specific time specific day that you just by and you just keep buying that's probably a good investment advice across any kind of assets. [/INST] Like if you don't believe in Bitcoin and just want to, let's say you just want to the s. p. 500, You shouldn't try to time the market of the S&P 500 either, right? You should just every two weeks you should just buy something over a 20-year period. You're gonna end up buying it at all kinds of different prices. But you can get kind of a blended average and the more important thing is the compounding and the time in the market then, did you buy it at, you know, 2% higher or lower than where you bought? It doesn't really matter. </s><s>[INST] And buying off and makes you, I guess resistant, robust to the to the volatility of the market or volatility. The Bitcoin price and so on. That said, uh, you know, Bitcoin price is volatile. And you know, again, the argument, I've heard it's like everything that's going to be a lot more valuable in the future. Like if you look at the history like companies like Apple like Tesla's now, I mean, but let's look at companies that have now stabilized, right? Apple is a good example. It's like volatile in the beginning. And so the argument for Bitcoin is like yeah this is the early stages because it's going to be a lot more valuable right now it's volatile and this is why you have to have these kinds of strategies to write out the volatility. Of course everything that goes to zero is also volatile. Like the early days are volatile. Uh Do you see like this volatility is like a feature or a bug or is this just like a way of life? [/INST] So Amazon is the one that I know the numbers on in terms of the early volatility uh every year since it has gone public it's had a double-digit drawdown in that year. Uh the average is over 30 And one time I drew down over 95%. Sounds a lot like Bitcoin like oh I was just crazy But it's one of the best performing stocks in the last 20 years. If not the best performing stock. And so volatility is not positive or negative, it's positive or negative compared to the position you're in. So if you're long and its volatile to the upside, its positive, if you're long holding something and its volatile to the downside. You see it as a negative. It's all about perspective with that said um Another way that I look at this is every asset priced in Bitcoin is down significantly. So over the last 135 years the dollar priced in Bitcoin has crashed 99%. If you denominated stocks it's down like 80% 85%. If you didn't nominate gold if you denominated bonds, if you just go down the line, real estate etcetera it's all down massively against Bitcoin. Now you could argue that that's because Bitcoin is appreciating in us dollar terms or you could actually argue that the world is re pricing this assets doing price discovery on this asset. And it's essentially comparing it's saying hey Bitcoin versus the stock or Bitcoin versus this ounce of gold or Bitcoin verse you know this dollar which is more valuable and it continues to move up in the rankings in terms of the value that the world ascribes to this. Something is based on lindy effect. Just the longer it persists, the more likely it is to survive. Some of that's based on like the underlying fundamentals of how much computing power, the usage transaction volume, things like that. But some of it also is that as more and more people wake up to the fact that it's a finite supply asset that has a place in the world and demand increases. People just naturally compete ascribe more value to it. And so the volatility I think all comes back to like what do you price your life in for majority people that's dollars so we look at the U. S. Dollar price. You get all this volatility. The beauty of this is that 60%. That doesn't move regardless of price upward or downward and movement. Those people aren't looking at the day to day price. What they basically said is I've acquired X. Amount of Bitcoin and I'm just gonna hold it for years And every time somebody has done that right, if you bought Bitcoin at any point in the last 12 years and you held it till today you are up in us dollar terms. Now If we had this conversation 18 months ago, I couldn't say that. So it's all about not only the acquisition price if you will, It's also one of you looking at it right because there was a point in 2017 you could have said the same thing but in 18 you couldn't and so I tend to think a lot about humans are really really bad at short term uh decision making. Because we're so emotional especially when something has a </s><s>[INST] price tied to it. So it's in terms of our strategies and decision making which should be long term and have like a regular almost think like an algorithm that in that in that kind of way. So I think you've tweeted that you believe that Bitcoin has a chance of reaching one million. I don't know what it is currently. I think it's 5 16 sixties which is incredible. Mm [/INST] hmm I think I remember </s><s>[INST] when it was at least in the double [/INST] digits I think I remember </s><s>[INST] was in the signal digits of a dollar. [/INST] So the fact that is cross 50's </s><s>[INST] crazy. Uh But you're even crazier apparently thinking that it can reach a million. So do you think it's possible for it to reach a million? Is there some kind of transformative effects we'll have to see first when might reach a million. Like what are the signs that we would look for, [/INST] what's required for it </s><s>[INST] to reach a million? [/INST] So let's just look at it from a macro perspective, gold is a $10 trillion dollar asset. And when you compare the technology of gold to the technology of Bitcoin. Bitcoin is superior in every single way. Right? It's more portable, more divisible. Uh It's more verifiable it's more scarce on everything. And so some people would argue it's a 10 X. Improvement. Some people argue it's 100 X. Improvement from a technology standpoint. And so we don't need Bitcoin to actually kind of um capture the full 10 X. Or 100 X. Improvement from a market cap standpoint. If Bitcoin simply captures two X. The value be a $20 trillion market cap which would put Bitcoin at about a million dollars. Right? So kind of just from a macro perspective if you have a 10 X. 100 X. Improvement from a technology standpoint and you directionally get some value capture in that direction, you're hitting around a million or more dollar price </s><s>[INST] point? Can I ask a question which is uh what's the current market cap for Bitcoin, [/INST] the current market caps right around a trillion. Just over a </s><s>[INST] trillion dollars. And you're saying gold is 10 trillion. Uh sorry, where did you get? The 20 trillion? [/INST] 20 trillion would just be two X. Cold market cap. Got it. Right. So if it's a 10 X technology improvement, let's just say it only captures two X. The market cap, right? And so again, if it was to capture just gold market cap, kind of the equivalent push you around $500,000 right? So you can kind </s><s>[INST] of see there's Bitcoin. So if you capture the entirety of the gold market then it would be value a single Bitcoin. The price of a single Bitcoin would be $500,000. Okay. To reach a million. It would be doubled at that's what the 20 trillion comes from, correct. Got [/INST] it. So if you then say to yourself, okay, how does the pricing um kind of cycles work, right. Or or the boom and bust cycles. Gold is a very um kind of linear type supply schedule, meaning that uh there is a certain amount of gold that comes out of the ground each year. The inter year variation in that incoming supply is not much, right? Maybe there's an extra mining company that gets set up for a couple of them, everyone goes out of business. But for the most part the kind of inflationary uh increase to the supply of gold. It's pretty stagnant year over year. Bitcoin has a very unique feature which every four years there's a programmatic supply shock meaning that uh in the beginning 50 Bitcoin every 10 minutes was introduced into the supply. After four years of that happening every 10 minutes, it was cut in half. So on a, in a single moment it went from 50 to now, it was 25 four years every 10 minutes, 25 got cut in half again to 12.5. And then recently in May 2020 got cut to 6.25 when you have an asset that is determined the price based on supply and demand. You normally have two inputs to the equation. What is the supply and what is the demand in an asset like gold or a stock or anything else? We have to do our best guess at the supply, both the existing supply and the incoming supply and do our best guess at the demand. And we actually pretty good at this a lot of times in terms of directionally saying it's going to go up or down and here's kind of some price point milestones. Bitcoin is unique in that there is 100% verifiable proof Of the existing supply, the total supply and the incoming daily supply. So we know 100%. I can show you on the actual Blockchain or in the code that there's 21 million bitcoins. Uh and that's all there will ever be. I can show you that there's 18.6 million give or take Bitcoin that actually are in circulation today. Right. And I can go all the way back to every single transaction that ever occurred since January 2009. And then I can show you on a daily basis that 900 Bitcoin a day are coming into the circulating supply. And so when you have 100% confidence because you can prove the supply side of this equation, you can hold it constant. I know with 100% accuracy, the supply side. So now I've reduced the mathematical equation that I need to do to determine price movements to a 50% reduction. I only have to worry about demand. I don't have to worry about supply. And so when I look at demand I can do all kinds of things. I can take the demand of the last 10 years and the growth and just extrapolate it out, I can increase that. I can decrease it whatever. But what you find is that these supply shocks lead to significant price appreciation as the acid gets re priced because there there's a supply shock to And so probably the best thing that I've done over the last couple of years was in 2019. I started to talk about the idea that we were going to have both a supply shock and the demand shock in 2021. Uh, I'm sorry in 2020, I didn't know when this bull market that we were in was going to end. Nobody knows it's impossible to time these things, but you could tell that we were kind of at late stages of a cycle, there was inverted yield curves, there was re generations in the repo markets, a lot of Ceos leaving their jobs, you know, all this kind of stuff and all I said was at some point when the market turns over, the government's gonna have to step in, we were addicted to stimulus, they have to manipulate interest rates down. They're going to print money. I had no clue that there was gonna be a global pandemic that they were gonna have to step in in such an aggressive way and move rates not down but down to zero. And that they, not only we're going to print hundreds of billions but trillions of dollars, but the framework that I used to think about this was when they do that, everyone is going to run to store value assets, they're going to run the gold, they're going to run the Bitcoin etcetera and right as they do that, it appears at the same time there's going to be this supply shock, so you're gonna get a supply shock and a demand shock that are both positive for the price and I call it rocket fuel for Bitcoin. Well it happened and here we are I now look for and I say, okay we are likely going to see 100,000 Bitcoin, $100,000. Bitcoin this year at some point. I don't know when it happens but we're moving in </s><s>[INST] That 2021 we'll see 100,000. [/INST] That would be my most conservative view. I've said $100,000 since 2019 and people thought that was insane and crazy and all this stuff. Now I'm the conservative guy in the room because I stick with $100,000 and people are saying, you know, multiples of that number here. Uh so we'll see what happens. But I think that there's still a lot of room kind of a run from a US dollar price standpoint. What is on the horizon is in 2024 we will have another supply shock. And so that's what I think will carry us to the million dollar </s><s>[INST] Bitcoin 6 : 5 to [/INST] whatever. 50% reduction. Yeah. And so that's what I think will basically when we get that next supply shock that will carry us up over 100 are over $1 million Bitcoin price which if historical examples Per session again, sometimes it's hard to use historical examples to look at future events. Um but if that happens we would see $1 million 2026. </s><s>[INST] After that wave. [/INST] So 2024 basically is the supply shock and within you know, 18-24 months you would see the kind of top of the next market. </s><s>[INST] Hopefully without a coupling to the to another pandemic? [/INST] Yes we would like to do all of this without a public health crisis. </s><s>[INST] So that would take it to 20 trillion. You don't have to compare it to the dollar essentially in some sense that the dollar could also lose value. I mean there's a lot of kind of dynamics at play here now by like fundamentally there's going to be a huge move in your prediction of value into into Bitcoin. I mean that's a fascinating world to think about. Uh I mean but I do have to kind of ask you about the whole space of technology there because we're talking about the value of security, we're talking about the future which Bitcoin will be at the center of but from my perspective of thinking how like I and others can build technologies on top of this kind of decentralized world. I'm thinking about different different technologies out there, different cryptocurrencies out there a theory and being one but there's a lot of others. So I'd love to get your sort of ideas about some of these. But so first let me ask you about what the hell is shit coin. It's just connected to uh to our previous discussion of the meme uh the ship coin cover basically all coins that are not Bitcoin is it? Uh I mean is it beautiful? Is it's a mixture of both [/INST] as with most things in life depends who you ask. Um, uh, the most, um, uh, kind of enthusiastic and uh, parts of the Bitcoin community shit coin is anything else right? Kind of, if you ascribe to kind of a maximalist, IQ view of the world, ship can be anything. If you look at people who, I would say our Bitcoin proponents yet see value in other things, shit coin, maybe the bottom half of the other things. Right? So I think again, it's really important, kind of who you ask is how you'll </s><s>[INST] get that answer. So there's tears and the way you divide those tears might be different depending who you [/INST] ask, ultimately what it is is it's a meme and it's used to uh, articulate the idea that whatever you want to put in that bucket has no value. So shit coins are coins that have no value. Uh, what is fascinating about it and I think that again speaks to the power of the Bitcoin community. Is there was congressional hearings a couple of years ago. Oh no. And at one point, a congressman from Ohio Warren Davidson, who was definitely a open minded and excited about Bitcoin asked a, an individual on the congress floor during testimony to talk about these other coins and at one point basically read into the record the terminology of ship coin, </s><s>[INST] he said the words, [/INST] I can't remember if he said it first, somebody else or if the other person did and then he um you know repeated it but he definitely he was trying to get that read into the record for sure. And so uh you know you can imagine one again the meme speaking insulin early to the Bitcoin community was you know made him very very well liked but also to was um it does go back to this idea almost of uh if you and I sat down with 10 ceos and we interviewed each one of them and then we went in a room and we deliberated and we said we have to pick the person who is going to be the most successful one of the inputs, not all of the inputs but one of the inputs would be who is the person who we believe has the best ability to raise capital, recruit people and tell a story to the world that will get them to follow. And so somebody like Elon would probably the best example of this when you have decentralized products, you have no kind of leader right in the sense of somebody who is financially ascribed to be that leader and kind of the executive decision maker. So what you have to do is you have to look at these technologies in these communities and say well which volunteer teams or which technologies have been able to coalesce these groups around it and in some way build the same level of engagement and protection and things like that. And so you actually get tribalism but you also get things like Bitcoin because what it does is it's not only a kind of verbal attack towards others, it's a rallying cry for internal. What's so funny is that it was started with the Bitcoin community talking about everybody, but now you've seen adoption in other communities who use, you know, basically say well we're not a ship coin, it's the next guy. </s><s>[INST] Yeah, I mean the meeting to be honest, it's one it's off, it's sometimes misused I think like with anything it's like people adult memes that used to be brilliant are still brilliant and they're just not good at using them. So they become mean [/INST] uh </s><s>[INST] but when you do with Grace it can tear down an argument and at the same time have like love and respect underneath it. I mean it's a beautiful dance, they have to be good at like you know, people just can suck a communication and even uh like even a powerful weapon, like a meme in the wrong hands just uh fires in a way that doesn't get anything done. But this is like a war of humor and memes, it's kind of fascinating. Exactly like you formulated that there's asymmetry of power so you have to have Guerilla warfare in this internet game, especially when there's no leader like you said in a distributed [/INST] culture say here that is um is really important I think is from a society standpoint, we've become very soft and very kind of coddling and not not in a way that's like, I think people take this argument too far sometimes, but what I mean by that is, um it's almost like if you're the person who hold somebody accountable, you become the bad person, right? If you're the person who um says, hey, you know, that's wrong, you're the bad person, right? And so in a world where I think and um this kind of influence serie all positive, if you have any negative feedback or constructive criticism, like you're the bad person, uh it's the ultimate echo chamber, right? And so I think that what the Bitcoin world does in some crazy, crazy way to look at it is Bitcoin is ultimately about truth, not about narrative, not about feelings or emotions, it's math. You look at a Blockchain and you can prove something or you can't. And so naturally people were attracted to that have a very similar approach in life, right? They say, hey, you made exclaim prove it. And as you can imagine, you know, a great example is like the financial media meets Bitcoin ear's and it's a bloodbath in kind of the the arena of ideas because what do they do? The financial media is used to the soft, you know, opinion pieces, etcetera and big corners show up and they're like uh here's data point A B and C. Here's example, 12 and three and you're wrong. Um and then all the yell and scream about is like I'm wrong, I'm wrong, I'm wrong, like you can't say I'm wrong and like no like disprove what I just said and so you're getting this like very very weird. </s><s>[INST] It's fascinating, it's a fascinating benefit but I do want to say is I've been watching this, it's kind of interesting. I think that the pursuit of truth through like tearing down bad ideas can be done with grace and to do it with grace requires a lot of skill. Like what people don't realize about this agreement. They think that this agreement is easy like they they see the the lies or the inaccuracies in the statement and and they just think they can say wrong yes, you can say that, but if you want to be effective, it requires great skill. Like you look at, I don't know, a beautiful verbal shit poster which is Christopher Hitchens right? It requires a lot of skill through your words to tear down an argument to criticize and to take a step towards truth. Uh what I am disheartened by internet culture, like the negative side is people don't put a lot of effort in there tear downs like into your ship posting into your memes, you should put effort and see it as a skill that you want to, if you want to be a part of this culture, you want to ah Get good at it, like any skill to 10,000 hours get improved deliberate practice self criticism, all of those things just because you're anonymous doesn't mean you won't get deep joy and actually have an impact on the world if you get good at ship posting. [/INST] But I think this is really, really important, right? Because you're right in that uh it's all about intention verse action if your intention is to uh tell somebody that they are wrong in an effort to get them to see the truth. Yes, that's very different than if your intention is to tell someone they're wrong and hurt their feelings, right? And so when you can unpack intention in action, you really quickly can tell what somebody ultimately is trying to accomplish. I also think that one of the craziest things that I've seen play out is uh memes when I use that term, I'm not just talking about like a static photo, right? When I'm talking about these elaborate kind of edited videos and kind of all this stuff. Um when done right, it is the most articulate way to deliver a blunt message and it's done in such a way that is humorous and entertaining yet really hammers the point home. And so it's a skill set that many people don't have. I don't make those. I'm assuming you don't make them either, right? I see them, I share the ones that I like, right? Uh But it does take practice and you can tell, look, there's people who are fantastic meme lords and there are people who absolutely suck at it. And it's like anything, it's just how good are you at communicating. And I've heard the idea a bunch of times, so I don't know who to kind of credit for it, but whether it's emojis, it's gifts, it's memes, whatever this is, the extension and evolution of just how hieroglyphics like we have been doing this for literally centuries. It's just that now we're doing it on the internet and you can press a button and go to millions and millions of people immediately. </s><s>[INST] Uh, but speaking of means, what the heck do you think is up with Elon musk? Talking about dosh coin a lot sort of from the Cryptocurrency community. I uh, I've been talking to a lot of sort of technologists I guess and reading papers on Cryptocurrency, it's like nobody really ces does cohen as a revolutionary crypto technology. A lot of people talk about its security issues. There's a bunch of issues that has [/INST] nevertheless, </s><s>[INST] you did say that money is the kind of social construct, right? And uh Elon musk combination of humor and brilliant engineering and the various companies he runs combines to create a kind of value and excitement behind dash coin. It's like um, what is it he says uh, that the most amusing outcome is the most likely kind of idea, which sounds silly, but there could be like profound truth to it. It's like what do you make of dosh coin philosophically or technically is is it possible that dosh coin will overtake Bitcoin and run the [/INST] run the </s><s>[INST] entire world. I can't even because it could happen, it could happen but what if there's any serious way to answer that [/INST] question? Well we have to start with Techno King of Tesla and master of coin as they are so articulately called in the latest sec filing who </s><s>[INST] he officially changed his title, Techno King, [/INST] Techno King of Tesla and the Cfos new uh title is a master of coin. And so when you have a sense of humor and frankly a level of self confidence and uh an element of, an appreciation for irony in the world does coin is actually one of the least crazy things that you could talk about when you're willing to go to techno King of Tesla, master of coin uh and all this stuff and so I think that Ellen doesn't get enough credit frankly for his understanding of internet culture, understanding of memes and understanding of frankly human psychology and marketing and so in some crazy way every time he talks about dodge coin it's a rallying cry for an entire generation of kids it's a rallying cry for an entire industry in terms of cryptocurrencies and digital technologies but this is the flag yeah and this is the thing that he can yell and scream about and tweet about without worry of punishment. </s><s>[INST] So he could be talking about Bitcoin, he could be talking about Cryptocurrency, but that's not going to be uh, as beautifully [/INST] humorous and whatever the hell </s><s>[INST] internet culture is [/INST] as dark coin. He's finding the right </s><s>[INST] language, He's speaking the language [/INST] of the people of the, of the, in the digital age. If you want to reach weird people, you can't be serious </s><s>[INST] and most people are weird. The masses are weird. So he's speaking to the masses and the techno king. [/INST] And even further than that I think is he essentially is um, he's using dodge coin as a way to say I'm doing this because I can, yeah, he couldn't do it with securities, he couldn't do it with certain types of other assets, right? Like I almost look at it like a Venn diagram, what's the thing that a bunch of people know about, care about thinking it's funny, whatever and also overlay that with the things that he could actually talk about, they won't get in trouble for. </s><s>[INST] That's a big f you to the sec. I could see the people just freaking out. I, I mean, I love it, but um, I don't know if I would have the guts to do it myself, but I, I think he's an inspiration to a lot of us to be like, well maybe you should grow the guts [/INST] when you're the techno king, you can do whatever you want, right? Uh </s><s>[INST] I mean that's something to aspire to is to be the techno king in your own little world. [/INST] If you also think about it in the sense of when you're somebody on a mission to create interplanetary life, when you're trying to solve, they put a dent in the climate crisis or create electric vehicles and be the first american company and you know how far along frankly the sec or other things in your life that just don't, you don't ascribe that much importance to compared to those things. They're almost nuisances. And that's scary. I think for shareholders of a company when the person that you're trusting to lead you to the promised land and create shareholder value doesn't put value on certain things. But at the same time I always look at it as a tug of war how much of the actions of what he's doing and calling attention to actually changed the way that regulators, lawmakers, politicians, countries, whatever act, he may not be able to say do acts on the techno king and they go do it. But with every step he makes, he changes some of their behavior. And so I think that it's A really kind of game of like three d. Chess that frankly I'm not privy to write and I'm kind of watching from the sidelines and figuring out alongside everybody else. But I also don't think that it's just Ellen bought a bunch of does coin and tweets about it because things going to a dollar and he's going to make money right? Like I don't think I don't think it's an economic argument as to why he's so interested in. I think it's much more uh it's almost like meta message for a lot of other stuff. </s><s>[INST] Yeah, he's kind of trying to break apart internet communication from first Principles, like it does so many other problems. It's kind of fascinating to watch. I know he's been uh he's taught me quite a bit about communication and uh at least for me it's been liberating to not give a fuck about the old school way of things. I've been always bothered by a place I deeply admire, which is M. I. T. But there's problems, bureaucracies and hierarchies that hold back innovation, brilliant minds and um in that sense does is a kind of f you to the system that's kind of positive but also uh kind of. Uh but it was also an f you. So in that sense, I think Ellen has a perspective on the world is similar to Bitcoin folks, which I really like, which is like thinking long term how visionaries think is like how if I take these ideas, what and the ideas hold true, What will the world look like in 2030, 50 years and think about everything in that [/INST] way? Yeah, I like bazookas view, which is uh is essentially how do you minimize regret, how do you accelerate your life mentally and go to 80 90 100 150 years, whatever we end up being, you know, fortunate to live too and then look backwards and say this decision that I'm going to make, I have two options which one is going to be the one that at least regret and if you continue to make decisions that way one, you have that long term view kind of built things, you're working backwards two, you are ultimately going to optimize for minimal regret. But also three is Even if you only look forward 10 years, that's much much further than most people do. And so it gives you a significant advantage and I think that Bitcoin has kind of this like um, you know, proxy for time as we talked about uh inter plant planetary travel where there's multiple steps from creating a reusable rocket to landing it to, you know, all this stuff all the way to simple things, just like If you're simply trying to figure out where the world is going to be 30 years from now, You know, Bill Gates says that we overestimate what we can do in one year. Underestimate what we can do in 10. Well, To me, it's a um kind of degree of uh mistake if you will 10 years, maybe you're off by 10%. Well, if that line of progress continues 20 years, you may be off by 100 And 30 years, you may be up 5,000% right, like, like almost the further you go out, the more inaccurate you become. And so I think that people who want to iterate their way to success, there's a common thing in the startup world, end up actually following kind of the bread crumbs to where the world is taking them. But people like Elon musk, Jeff Bezos, a Jack Dorsey all the way down the line, all these innovators, they actually say to themselves, there is a point in time in the future where there is a world I want to construct and then they go and they construct it regardless of the short term iterations and incentives, it is just they're driving towards that point and I think that it's this whole idea of having this like, you know, kind of set vision and this refusal to kind of move or budge off of that, that's what makes them special. </s><s>[INST] One of the things that garnered a lot of excitement in the crypto community is N. F. T. S. I have no idea really. The depths, the fundamental technological froze, solid gold depths of the second of this technology, whether this is just like a little bit of a fad or there's some deep lessons to learn whether it's Bitcoin or Cryptocurrency in general about it. You have thoughts about like the long lasting, fundamental aspects of N. F. T. S. [/INST] I think there's probably both things happening fad and things to learn, right? And if we just start with like what is an N. F. T. It's a non fungible token meaning that um there's no fund ability and fund ability is a fancy word. Um I always describe it as if I took $100 bill and I put it on the table with a bunch of the $100 bills and we mix them up and I just grabbed $100 bill and left. I'm no worse as long as they're all you know official $100 bills because as long as I have $100 500 dollars I don't need that exact same bill back. So that means that those $100 bills are fungible. Non fungible would be like art if I took a Picasso and I put it down on the table and you brought three artists that no one's ever heard of before and we mix them up and it took any random piece of art. It wasn't the Picasso I lose because the Picasso is really important there. Right? So the non fungible it is important in art. What these non fungible tokens essentially are doing is they are creating scarcity and originality in a digital environment. And what I mean by that is um take a music file. If I had a music file and you wanted it you said send it to me. I press send it essentially creates a copy and you get one music file, I get another. We don't care. You can listen to music, I can listen to music. We're super happy if I instead though have a digital file. That entire premise is based on scarcity and I hit send and you get a copy and I keep the original or you get the original, I get a copy. There's a problem. And so ultimately what I think is playing out with N. F. T. S is it's a technology regardless of where it plays out from block chains or what in communities or environments that just brings true digital scarcity to the internet. And so naturally what people do, they look at the legacy world and they say, well what's scarce there that has value? How do we bring that to the digital? So art is a perfect example, right? And you know, frankly last year I started to look at this because it felt like this was gonna be really, really big. And the conclusion I came to was just as Bitcoin is going to be bigger than gold, right? The digital application of something is going to be bigger than the analog application. The same thing is gonna be true in art. The digital art world is even bigger than nutritional art world. People think that sounds crazy at first, until you start to realize very, very similar, the yard is more portable, it can be divisible, right? It's got a larger demand market in terms of the internet rather than an auction, right? All this kind of stuff when you display it, it can have motion and music and all of these aspects to it that are better than the traditional art. What the traditional art market has, that the digital art market has not had is the narrative narrative based world scarcity kind of in digital sense. And so what I think the entire world is going through right now is an exploration of how do we use this technology to create new things? Frankly, we're not going to be good at it for a while. And so the only place I've really focused on is digital art itself. And I've always been interested in art, but I wasn't gonna go buy a painting and hanging on the wall, right in the sense of uh that's how I was going to store value. What I find fascinating though is that I now can take that concept, which most of the wealthiest people in the world have a significant portion. Some, you know, some people have 20% in terms of, you know, a number of billionaires, 20% of their wealth is in art and you bring to this digital realm, which is much more um kind of natural to a digital native. And so the best way to describe the importance is imagine a serial number being placed on something. Take the Eiffel Tower, the only Eiffel Tower that has value is the first one, Every replica of it regardless of size location you know who made it, where they sent it, they have no value. Eiffel Tower 001 is the most important and so I think that's ultimately what we're starting to see here and What we're looking at probably 1% of what is going to grow into, </s><s>[INST] You're bullish, you're saying it could grow into something for 1%, it could grow into something significant like all kinds of different applications, [/INST] strip away all the applications right now and just think about is digital scarcity going to be important on the </s><s>[INST] internet moving all the things that are scarce in the physical world into digital space, us trying to figure out which things can be moved and not and also there's things in the digital space just like you're saying that don't exist in the physical world that might also benefit from gaining scarcity. Like you know people are I guess creating N. F. T. S. Out of like tweets or whatever so like you're you have you have a fun twitter account you know you could say like you could put value to a single tweet and then be able to invest in and trade it and buy parts of it and all those kinds of things. You know you can invest in people you can invest in you know art can be defined broadly as any kind of creation right in some sense this whole idea of scarcity can overtake the entirety of the digital world. It can consume the, all of the markets we see as financial markets and just turn everything into a [/INST] market. So if I take you on like a 10 year fast forward and I paint a picture of something today, that seems absolutely insane. But there's early signs that people are building this and let's just give them the benefit of the doubt that some of the early iterations will work. And some of our, most of them won't. There's a world where you and I are participating in a digital economy, in a virtual world where uh, whether it is a piece of art, it is a digital sculpture, it is a digital skin from a video game. It is a digital good that we purchased somewhere online and we bring it and we display it in a digital museum or virtual museum. And so now all of a sudden you can charge people for entry, You can consign digital goods. It's the replication of what happens in the analog world now, just in digital And when you do that, what you do is you take the addressable markets of these assets or these mechanisms and they explode in the digital realm. And so now all of a sudden, how fast does the human race accelerate when it comes to human production, intelligence, learning all in the digital output. It's just if if I said to you 20 years ago, I'm gonna give you a global education. I mean, I'm going to take you and I'm going to physically move you to geography after geography, after geography, it's gonna take time. It's gonna take resources and ultimately gonna take lots of effort. If I now said to you, hey, I'm going to transport you in this virtual world to multiple geography ease. But you're going to experience it in this virtual world and you're going to have digital goods that you can take from economy to economy or from location to location. All of a sudden you may get maybe you get 90% of all, you don't get 100% of the same value. We get 90% of value, but you can do it at a much faster pace. And so in a six month period you've actually made three times the progress then you would have if you had to do in the physical world. So that's where I think we're </s><s>[INST] heading. So there's digital art being displayed in the digital museum and people are being charged for access and perhaps we plug in our senses, which means we start to operate more and more in a virtual reality augmented reality virtual reality way with this digital world and increasingly go into this world basically lived most of our productive and social lives in this digital world and increasingly essentially create a simulation where the biological basis is just there to say sustained. The brain that's used to operate in the in the virtual world. Uh taking us back to the original when we started talking about war? I wonder what conflict looks like in that world, that the people who are born today, maybe we'll be fighting wars in the space in in that museum world, in that digital [/INST] world. Remember what I said, we're moving from a world of conflict surrounded and determined by bombs, bullets and soldiers to a battlefield that is determined by war of information and cyber capabilities. And so in that virtual world, is it about death and destruction of human life and the physical analog world? Or will it become more important to attack or defend virtual property and virtual life? And, you know, some level of virtual sovereignty, in my opinion, the latter is more likely. And so what you start to understand is, well, what do you truly value in your life? Is it the physical analog, materialistic, consumptive goods, or is it virtual? And in many cases something as simple as the ability to connect with somebody, it's really important. And so one of the most disruptive, combative, violent things that a country may do to another country in the future, simply take down the Internet. Mhm. And put people in isolation. Yeah, I don't need to physically harm you if I can psychologically harm you, I don't need to </s><s>[INST] terrifying. [/INST] Yeah, I don't need to actually convince you through a monopoly on violence on physical violence, What if I can psychologically change the way you see the world through misinformation through all sorts of nefarious activities. And I think that, you know, the United States has been struggling with this idea of the last couple of years in the political arena. But what happens when it starts to come to other aspects of our life? </s><s>[INST] And I think it's very likely it's almost obviously likely they were moving into the digital world. The one of the features of the digital world is that artificial intelligence systems can operate with much more power in a frictionless way in that world. Currently, as we understand it, it's hard to build robots that operate at scale and do like arbitrary large amount of impact damage or positive. In the physical world, it's much easier to do in the digital world. Do you have, do you ever think about ai systems just swimming about uh doing extraordinarily powerful destructive things in the digital world is something of a concern to you? Or is this something into a very distant future? [/INST] I think a lot of artificial intelligence is uh in the name, it's simply the replication of human intelligence at scale automated and and program programmatic meaning that in the analog world you could go hire 1000 employees or in an amazon case higher millions of employees and set a mission or a goal and push them to go do that? That requires recruiting retention, training resources, all that stuff in the virtual world or in this digital economy, what if you could just program the resources and gain the same leverage and do it at scale and do it in a very programmatic way and then have them actually make decisions in a way that doesn't require you to have thought of every single potential scenario or edge case. That's ultimately what we're talking about. We talk about artificial intelligence, right? And so when you look at that, when technology is created, everyone uses it for good or bad. But both get used. Right? And so whether we're talking about cell phones, beepers, the internet guns, whatever it's always used for good and bad. The big question is, and I think that, you know yourself and many other people have rightfully said this is the question really becomes, is the negative and nefarious uses of this inadvertent potentially or does it actually come from a malicious persons the intention militias. And to me that's what I, I don't know enough, you know much more about this And there's plenty of other people who do as well. But I do think that there will be nefarious actors and malicious people. We're going to treat them the same way we've always treated people who use technology portly. Right? We're gonna understand it. We're gonna identify it, we're gonna control it and then we're gonna end up reversing it or preventing them from doing them, it's the inadvertent things that I think are actually the most dangerous because when you have something that can think for itself, and there is no way to leverage a monopoly on violence for control. It's a very scary thing. </s><s>[INST] It couldn't I mean, the thing that's scary to me is that it can scale arbitrarily so it can outnumber humans very quickly, even if it's dumber than humans. And so, I don't know if we're able to reason about the world, like, let's look at the physical analog or all of a sudden uh let's talk about something kind of like humans, but doubling the humans, like chimps, okay, imagine that all of a sudden chimps could multiply arbitrarily quickly, and you could have like, a trillion chimps the next day when, when you, when you only had maybe a million the day before, Like, how does that world look [/INST] different when the fox, all the chips come from, and they </s><s>[INST] like, and then we can we can pretend to be like, well, let's hope the chimps, like, don't get violent because they don't seem to get violent when the resources aren't constrained, but like, we don't know, And the problem is it all starts by building that first chip, multiplier device and everyone's like, okay, yeah, there's a lot of good applications you want, you know, uh you can make all kinds of arguments for why you have more chips, maybe they can help you out around the house or something like that in the physical space, but ultimately it's the unintended consequences that you're referring to is you don't know what's going to happen. I'm really worried about dumb ai agents like having impact when they are multiplied to a million to a billion and are allowed to operate in the digital space, especially as we clearly are moving more and more of our lives into the digital space. So it's kind of terrifying because you know, a lot of people are terrified or like concerned about super intelligence systems. Uh I think I'm definitely much more concerned about super dumb systems at scale that that's terrifying. [/INST] I always think about the inadvertent, but as you're talking, what it made me think of is also the irreversible </s><s>[INST] reversible. [/INST] So, it's one thing if there's uh inadvertent negative impact, but we have reverse ability built into a system and we can fix our mistakes. I think the really scary part is when you overlay inadvertent mistakes with the irreversible aspect of it and therefore humans have no control. </s><s>[INST] Yeah, if you if you have the trillion chimps can't, they're not gonna like it when you try to start killing them off. Uh All right, But back to [/INST] Bitcoin, those chimps in the Bitcoin community, </s><s>[INST] anytime you bring up chimps, as some people say, joe Rogan entered the chat, Can I ask you about sort of learning about Bitcoin books and resources. You have an amazing podcast. That's not just about Bitcoin or Cryptocurrency, It's about everything including life but you do have a lot of really amazing conversations about this whole digital world but you obviously you also have a newsletter that's incredible on Substack and um but do you have recommendations? Maybe it would be great if you could talk about first of all your podcasts and the newsletter, but also other resources that you recommend. People should check out in order to learn about Bitcoin. [/INST] Yeah, so the podcast and uh email or with the two most selfish things I do because the podcast is a way for me to learn from other people so I get them to come on and tell me all the things are thinking about and I could ask some questions, what's it called by the way just to pump podcast. And so in doing that um it really is informative for me and I think that my whole goal is just like if I'm learning other people will be learning and then the email I read it every morning because it forces me to collect my thoughts and actually articulate them in somewhat of a coherent way. And so it's just something that um is like a practice that I probably would do even if no one read it and then by being able to publish it what does it do? It elicits? You know, both the good and bad responses and so people will let me know if you think I'm an idiot and they'll usually not responded to think that it's something smart. And so um those two things are really um educational for me and, and I think kind of forced me to uh to be able to articulate a lot of ideas, but a lot of what I share or learn on those things come from these other resources. </s><s>[INST] So I'm definitely subscribing, people should subscribe, but what are Bitcoin resources books that you recommend? [/INST] I think you gotta start with Bitcoin standard. Uh that one to me feels like it really lays out the picture nicely. Um There is Bitcoin money you can't funk with was written by a friend, Jason Williams. As you can imagine basically what it talks about. Uh There's another book, layered money um was written by Nick who has done a great job, kind of laying it out. Um There's a book called Bitcoin in Black America written by a guy Isaiah Jackson and he basically lays out the argument for why the black community um can benefit in a a symmetric way from something like Bitcoin. Um and there's a whole bunch more, I'm gonna forget them all. Um there's the, I think it's called the cost of Tomorrow, a guy, Jeff Booth, Jeff Booth wrote it um and just if you get on twitter, basically you're going to sell these books flying around. Um but I do have to say that from a psychological concept or philosophical concept, the number one book that I've ever read uh that aligns with Bitcoin ethos, but doesn't say a word about Bitcoin is a book called the DAO of Capital by Mark Spitznagel. And so what he essentially does is he just reiterates over and over and over again, long term thinking, outliers disruption all the stuff. And so he's a guy who he runs a fund that essentially they just do tail, risk hedging. and so in March or February of 2020, They're up like 4,000% right by the way, they pretty much lose money, you know, for 89 years then that happens. And so uh, but there's still one of the best performing funds if you look at it over, you know, years and years and so it's just this mindset of everyone is so short term focused and so I think it's just a great reminder of long term thinking. </s><s>[INST] Uh and also, I mean I've gotten quite a bit of value just reading the papers and that's perhaps more like for technical folks, there's quite active research community and also going back to the original white paper and just original documents. Old school old school is still uh what, like what a few years ago, Still really interesting to think about to look at what people were thinking about because the principles are carried through with the other cryptocurrencies as well, Like it's, it's all, it's all there, even in the early documents. So that's kind of fascinating to see that whole history from, if you're more like tech savvy and like you said, twitter is actually an interesting place if you can look past all the ship coin talk. Uh it's a, it's a fascinating place for news and resources. Is there books outside of all of this Cryptocurrency sort of technical fiction? Philosophical that an impact on your life because you have interests that are all over the place. Is there something that you would recommend to others? [/INST] So doubt capital is definitely probably my favorite book um books that have been impactful I read when I was 20 actually sitting in the desert of Iraq um rich dad, poor dad thinking girl Rich and the richest man in Babylon and I don't think I took a single thing and like implemented it from like an execution standpoint but it was a complete shift in mentality and understanding and relationship with money and um just kind of what I wanted to do with my life and stuff like that. So I think those three books I read them in succession were really impactful. Um and then I think one of the best books probably ever written is uh things called When breath becomes air or Air becomes breath, I can't remember but it's basically a doctor or medical professional who's dying and he essentially writes about the experience and thoughts and kind of all this stuff and I think that it's just one of these things where if you said to me, you know what's the number one thing I took out of my experience in Iraq, That's a book like that also gives you is we're all going to die right? And you and I can want to be as immortal as we want, but at some point we're gonna die and so it really does kind of focus you on time being that scarce asset and use it for enjoyment and happiness uh more so than anything else. And I think that's part of your message and it's a great one. </s><s>[INST] Do you do you think do you like literally meditate on your own mortality? [/INST] Necessarily think I meditate on it as much as um </s><s>[INST] are you afraid of death? Were you afraid of death when you're in Iraq and coming face to face with it, are you afraid of death today? [/INST] No, I think that it was just one of these things were like if you fixate on something and you worry about it then to at least to me like you become uneasy about it and so after an experience like going to war, I think that everything is just so not important compared to that, right? Like when I came back, I remember going back into the college environment and like things people are worried about. I was like listen, let me explain to you, you know what the real world's like right? But I think even today, right, if you talk to people who know me really well, don't get worked up about a lot of stuff, I don't get, you know, in either direction, good or bad anything because ultimately it just comes down to if that's the final result, let's enjoy it. </s><s>[INST] It's fascinating to ask you because this reformulation of money essentially buying time and uh, you know, there's the old question of this money buy happiness, do you [/INST] think money </s><s>[INST] can buy happiness in the context of money being able to buy time or as happiness? Something else that is beyond all of this. [/INST] When people talk about this question, I think that they really focus on money as a means to getting materialistic things. So they want a big house, they want to vote, they want a fast car, they want, you know, whatever they think that's the stuff that will make them happy. What I think about it is if you have resources, you can have time and if you have time and you spend it the way that you want to spend it, then that's ultimately happiness. So I always say to people, if you think that money doesn't buy you happiness, what if I told you that if you had more money, you can spend more time with your family. It reframes it and now it's all about, I want to do certain things in life, but there's a lot of people who spend their life not doing those things because they feel the need to pursue economic means as a way to provide a living or whatever. And so I explain that I said, listen in my opinion, against my opinion is what makes me happy if I can leverage financial resources to create more time to do the things I like, I'm happier, might not work for everybody, but like that's what works for me. And so there's this element of like, I don't care what other people think if they like that or not because they're not me right, Like, like there's almost this element of like you got to figure out what works for you and if it works for me then like </s><s>[INST] no, I think that resonate that that will resonate with a lot of people, I think that's a brilliant reframing of it. Uh that said uh you kind of imply there's uh there's a reason behind this whole existence of ours is a meaning to it. So let me ask, what is the meaning of life Anthony? Do you think about these ridiculous big questions that have no answer every once in a while or do you just enjoy the ship out of every day? [/INST] I answer it in a way that um isn't meant to be accurate, it's meant to um be the right answer for me, which is ultimately, you know, and I talked to a lot of people who always asked like what, what are you doing, what are you doing this? It's to be happy and the reason why I think of it that way. So I've got a friend Jonathan geller who talks about you know enough being enough and recently he talked about it in the context of Bitcoin and so big corners or have two things any Bitcoin if you talk to them, they believe the same two things one they don't want the U. S. Dollar price to go up because I actually wanna acquire more Bitcoin right? And then then like once they feel like they've got enough but two is no matter how much they only think that they don't own enough and they want to acquire more and so at some point you say yourself what is enough and I think that the whole meaning of life is to understand kind of what your level of satisfaction is and for some people that's a monetary thing, some people that's a freedom of time thing for some people it's an impact thing whatever but just understanding that's important and then going and accomplishing it and what I found is that the people who I know who have done this and been intentional about it, they accomplished on a much shorter timeline than people who don't But some people sort of think about when they're 60, Well naturally you're going to accomplish before you're 60 if you just start thinking about it 60 people don't think about it earlier can do it and so I think that's really it for me, it's just like the meaning of life is to enjoy it </s><s>[INST] the way I think about it because it's a really nice formulation. I almost like two sort of oscillate back and forth. The majority of the time is spent in the mode of enough is enough of gratitude basically being content with where you're at like deeply appreciative every moment and all the Bitcoin, whatever Bitcoin you have, being deeply appreciative and that being enough and then some fraction of time, perhaps it shrinks as you get older that maybe there's an optimal trajectory there, but some fraction of time is spent being like deeply self critical and nothing is enough. Nothing you've ever done is worth anything. It's the Marvin Minsky said like the secret to success is hating everything you've ever done. So like that mode of just hating everything you've ever done and just like trying to improve, trying to make stuff better. It's nothing is enough. It's never enough that kind of stuff. And then oscillating back and forth, like you don't have to have the same algorithm operating throughout the day. You could just like oscillating back and forth and maybe reserve that gratitude part the chill part two when you're hanging out with family and friends and loved ones and then when you're like alone or maybe a work is that the madman comes out kind of thing. [/INST] I also think it's um kind of purpose driven in the sense of there's a lot of people who have the uh I need to do more, but in somewhat altruistic way. So they're they're, you know, take Ellen as an example, the idea of colonizing mars sure if he is successful, he will be very rich. I don't think you or I or many people believe he's doing it for the money, right? There's a lot of other things you could do, they'll be much easier. That would make him tons of money. And so in some weird way, he has enough because he's able to free himself from the constraints of I need to acquire more resources and he can focus on what is the thing that I want to work on regardless of money. And so in that pursuit that is non economic, you can be as selfish as you want because ultimately you're not tied back to this like, measurement tool. And so it's this again, like altruistic, non monetary purpose and I think that there's a lot of people who spend their whole life looking for that and they don't know what it is. And so again, some people may not think of it that way, but if you can find something to do that, you win, </s><s>[INST] I don't think there's a better way to end Anthony and a huge fan, it's a huge honor that you waste all this time with me today. Uh you know, I thank you for just educating the world for, for teaching me uh, inspired me to learn more about this new set of technologies that look like they have a potential to change transform all of human civilization. So thank you for coming today and thank you for being who you [/INST] are. Absolutely. Thank you so much for having me. </s><s>[INST] Thanks for listening to this conversation with Anthony pomp liano and thank you to our sponsors, their gun muscle recovery device, Sun basket meal delivery service, Express VPN and indeed hiring website, click their links to support this podcast and now let me leave you some words from Mahatma Gandhi. Freedom is not worth having if it doesn't include the freedom to make mistakes, thank you for listening and hope to see you next time. [/INST] Yeah. </s>
<s>[INST] or how interesting is it's not about. But what was special about those days how those days come to be? Is it just, you got lucky. Like I like what you've just encountered Hutter prize on how can use or something like that. Um Like what? [/INST] But you see, I don't think it's just see, I don't think it's just that like I could have gotten lucky at any point. I think that in a way you were </s><s>[INST] ready at that moment. Yeah, exactly to receive the information. But is there some magic to the day today of like, like eating breakfast and it's the mundane things, [/INST] nothing. Now. I drift through the drift through life </s><s>[INST] without structure. [/INST] I drift through life hoping and praying that I will get another day like those days </s><s>[INST] and there's nothing in particular you do to uh to be a receptacle For another for day, # four. [/INST] No, I didn't do anything to get the other one, so I don't think I have to really do anything now. I took a month long trip to new york and the ethereum thing was the highlight of it, but the rest of it was pretty terrible. I did a two week road trip and I got I had to turn around, had to turn around him driving and uh in Gunnison, colorado passed through Gunnison. And uh the snow starts coming down this past up there called monarch pass in order to get through the Denver, you gotta get over the rockies and I had to turn my car around. I couldn't, I watched, I watched F150 go off the road, like, I gotta go back and like, that day was meaningful because like, like it was real, like, I actually had to turn my car around. Um It's rare that anything even real happens in my life, even as you know, mundane is the fact that there was snow, I had to turn around, stay in Gunnison and leave the next </s><s>[INST] day. Something about that moment for real. Okay, so actually it's interesting to break apart the three moments you mentioned if it's okay. So uh I always have trouble pronouncing his name but allows your kowski. So what how did your worldview change in starting to consider the the exponential growth of Ai and AGI that he thinks about and the threats of artificial intelligence and all that kind of ideas. Can you, is it just like, can you maybe break apart? Like what exactly was so magical to you is a transformational experience [/INST] today, everyone knows him for threats and AI safety. Um This was pre that stuff there was, I don't think I mentioned of AI safety on the page. Um this is this is old Makowski stuff. He'd probably denounce it all now. He'd probably be like, that's exactly what I didn't want to happen. Sorry man. Uh </s><s>[INST] is there something specific you can take from his work that you can remember? [/INST] Yeah, it was this realization that Uh computers double in power every 18 months and humans do not and they haven't crossed yet. But if you have one thing that's doubling every 18 months and one thing that's staying like this, you know, here's your log graph, here's your line, you know, you calculate that. </s><s>[INST] Yeah. And then the data, opened the door to the exponential thinking like thinking that like, you know what with technology, we can actually transform the world [/INST] it opened the door to human obsolescence, it opened the door to realize that in my lifetime humans are going to be replaced. </s><s>[INST] And then the matching idea to that of artificial intelligence with the Hutter prize. You know, I'm torn, I go back and forth and what I think about it. But the basic thesis is it's nice. It's a nice compelling notion that we can reduce the task of creating an intelligence system, general intelligence system into the task of compression. So you can think of all of intelligence in the universe. In fact as a kind of compression. Do you find that was that just at the time you found that as a compelling idea? Do you still find a compelling idea? [/INST] I still find that a compelling idea. Um I think that it's not that useful day to day. But actually um one of maybe my quests before that was a search for the definition of the word intelligence and I never had one. And I definitely have a definition of the word compression. It's a very simple uh straightforward one. And you know what compression is. You know what lost is lossless compression not lost. A lossless compression. And that that is equivalent to intelligence, which I believe, I'm not sure how useful that definition is day to day, but like I now have a framework to understand what it is. </s><s>[INST] He just 10 x. The the prize for that competition like recently a few months ago he ever thought of taking a crack at that. [/INST] I did oh I did I spent I spent the next after I found the prize I spent the next six months of my life trying it and uh well that's when I started learning everything about A. I. And then I worked a vicarious for a bit and then I learned read all the deep learning stuff and I'm like okay now I like I'm caught up to modern ai I had I had a really good framework to put it all in from the compression stuff right? Like some of the first some of the first deep learning models I played with were gpt gpt basically. But before transformers before I was still are an ends to do character prediction. </s>
<s>[INST] But what about for you? So is this akin to like systems like cellular automata where it's deterministic. But when you squint your eyes a little bit, it starts to look like there's agents making decisions at the higher sort of when you zoom out and look at the entities that are composed by the individual cells. Even though the there's underlying simple rules that make the system evolved in deterministic ways, it looks like there's organisms making decisions. Is that where the illusion of free will emerges that jump in scale, [/INST] it's a particular type of model. But this jumping skill is crucial. The jump in scale happens whenever you have too many parts to count and you cannot make a model at that level and you try to find some higher level regularity and the higher level regularity is a pattern that you project into the world to make sense of it. And agency is one of these patterns, right? You have all these cells that interact with each other and the cells in our body are set up in such a way that they benefit if their behavior is coherent, which means that they act as if they were serving a common goal and which that means that they will evolve. Regulation, mechanisms that act as if they were serving a common goal. And now you can make sense of these all these cells by projecting the common goal into them. </s><s>[INST] So for you then free will is an illusion. [/INST] No, it's a model. And it's a construct. It's basically a model that the system is making of its own behavior. And it's the best model that it can come up is under the circumstances and it can get replaced by a different model which is automatic behavior when you fully understand the mechanism under which you are acting. </s><s>[INST] But another word for model is what story. So it's a story you're telling. I mean, do you actually have control? Is there such a thing? Is that you and is there such a thing as you have in control? It's like are you manifesting your evolution as an entity [/INST] in some sense? The you as the model of the system that is in control. It's a story that the system tells itself about somebody who is in control and the contents of that model are being used to inform the behavior of the system. Okay, so the system is completely mechanical and the system creates that story like a loom and then it uses the contents of that story to inform its actions and writes the results of that actions into the story. </s><s>[INST] So how is that not an illusion? The story is written then or or rather we're not the writers of the story. [/INST] Yes, but we always knew that No, we don't know that. When do we know that? I think that's mostly a confusion about concepts. The conceptual illusion in our culture comes from the idea that you live in physical reality and that we experienced physical reality and that you have ideas about it and then you have this duelist interpretation where you have to substances rest extends to the world that you can touch. And that is made of extended things and raise competence, which is the world of ideas. And in fact both of them are mental representations. Oneness. The representations of the world is a game engine that your mind generates to make sense of the perceptual data and the other one's. Yes, that's what we perceive as the physical world, but we already know that the physical world is nothing like that, right? Quantum mechanics is very different from what you and me perceive as the world. The world you and me perceive is a game engine and no colours and sounds in the physical vote. They only exist in the game engine generated by your brain. And then you have ideas that are not cannot be mapped onto extended regions, right? So the objects that have a spatial extension in the game engine uh has extensive and the objects that don't have a physical extension in the game engine, our ideas and they both interact in our mind to produce models of the world. But </s><s>[INST] you know when you play video games, I understand that what's actually happening is zeros and ones inside of inside of a computer inside of a CPU and Gpu. But you're still seeing like the rendering of that and you're still making decisions whether to shoot to turn left or turn right. If you're playing a shooter or every time I started thinking about Skyrim and Elder scrolls and walking around the beautiful nature and swinging a sword, but it feels like you're making decisions inside that video game. So even though you don't have direct access uh in terms of perception to the bits to the zeros and ones, it still feels like you're making decisions and your decisions are actually feels like they're being applied all the way down to the zeros and ones. It feels like you have control even though you don't [/INST] direct access </s><s>[INST] to reality. [/INST] So there is basically a special character in the video game that is being created by the video game engine and this character is serving the aesthetics of the video game and that is you. Yes, but </s><s>[INST] I feel like I have control inside the video game. Like all those like 12 year olds that kick my ass on the Internet. [/INST] So for when you play the video game, it doesn't really matter that they're zeros and ones right? You don't care about the wheels of the bus, You don't care about the nature of the CPU, that it runs on what you care about the properties of the game that you're playing. And you hope that the CPU is good enough. Yes. And a similar thing happens when we interact with physics. The world that you and me are in is not the physical world, the world that you and me are in is a dream world. </s>
<s>[INST] So the idea of locality, the fact that locality is not fundamental uh to the nature of our existence sort of, you know, I guess in that sense modeling everything is the field makes sense to me stuff that's close by, interact stuff that's far away doesn't So what's what's locality and why is it not fundamental? And how is that even possible? [/INST] Yeah, I mean, locality is the answer to the question that Isaac Newton was worried about back at the beginning of our conversation, right? I mean how can the earth know what the gravitational field of the sun is? And the answer has spelled out by Laplace and Einstein and others is that there's a field in between and the way a field works? Is that what's happening to the field at this point in space only depends directly on what's happening at points right next to it. But what's happening at those points depends on what's happening right next to those, right? And so you can build up an influence across space through only local interactions, that's what locality means. What happens here is only affected by what's happening right next to it. That's locality. The idea of locality is built into every field theory, including general relativity as a classical theory. It seems to break down when we talk about black holes, and, you know, Hawking taught us in the 1970s that black holes radiate, they give off, they eventually evaporate away. They're not completely black. Once we take quantum mechanics into account, and we think we don't know for sure, but most of us think that if you make a black hole out of certain stuff, then, like La Plaza's Demon taught us, you should be able to predict what that black hole will turn into if it's just obeying the schrodinger equation. And if that's true, uh there are good arguments that can't happen while preserving locality at the same time, it's just that they're, the information seems to be spread out non locally and interesting ways </s><s>[INST] and people should uh you talk about holography with the Leonard Susskind and your mindscape podcast [/INST] podcast. I didn't even mention that. I'm terrible. I'm gonna I'm </s><s>[INST] gonna ask you questions about that too, and I've been not shutting up about, it's my favorite science podcasts or not. It's uh it's not even science podcast, it's like uh it's a scientist doing a [/INST] part. That's right, That's what it is. Absolutely, yes. Uh anyway, so holography is this idea when you have a black hole and black hole is a region of space inside of which gravity is so strong that you can't escape. And there's this weird feature of black holes that again, it's totally a thought experiment feature because we haven't gone and probed any yet. But there seems to be one way of thinking about what happens inside a black hole as seen by an observer who's falling in, which is actually pretty normal, Like everything looks pretty normal until you hit the singularity and you die. But from the point of the view of the outside observer, it seems like all the information that fell in is actually smeared over the horizon in a non local way. And that's puzzling. And that's so holography because that's a two dimensional surface that is encapsulating the whole three dimensional thing. Inside right? Still trying to deal with that. Still trying to figure out how to get there. But it's an indication that we need to think a little more subtly when we quantized gravity </s><s>[INST] because you can describe everything that's going on in the in three dimensional space by looking at the two dimensional projection of it means that locality doesn't it's not necessary. [/INST] Well, it means that somehow it's only a good approximation. It's not really what's going on, how we're supposed to feel about that. I just feel liberated. You know, space is just a good approximation and this was always going to be true once you started quantized gravity. So we're just beginning now to face up to the dramatic implications of quantized gravity. </s><s>[INST] Is there other weird stuff that happens to quantum mechanics in black hole? [/INST] I don't think that anything weird happen with quantum mechanics, that weird things happened with space time. I mean that's what it is, like. Quantum mechanics is still just quantum mechanics, but our ordinary notions of space time don't really quite work. And there's a principle that goes hand in hand with holography called complementarity, which says that um there's no one unique way to describe what's going on inside a black hole. Different observers will have different descriptions, both of which are accurate but sound completely incompatible with each other. So it depends on how you look at it. You know? The word complementarity in this context is borrowed from Niels Bohr who points out you can measure the position or you can measure the momentum, you can't measure both at the same time in quantum mechanics. </s><s>[INST] So, a couple of questions on many worlds, how does many worlds help us understand our particular branch of reality? So okay, that's fine and good, that is everything is splitting, but we're just traveling down a single [/INST] branch of it. So </s><s>[INST] how does it help us understand our little unique [/INST] branch? Yeah, I mean that's a that's a great question, but that's the point is that we didn't invent many worlds because we thought it was cool to have a whole bunch of worlds, right? We invented it because we were trying to account for what we observe here in our world and what we observed here in our world are wave functions collapsing. Okay. We do have a position of a situation where the electron seems to be spread out, but then when we look at it, we don't see it spread out, We see it located somewhere. So what's going on? That's the measurement problem of quantum mechanics. That's what we have to face up to. So many worlds is just a proposed solution to that problem. And the answer is nothing special is happening. It's still just the schrodinger equation, but you have a wave function too. And that's a different answer than would be given in hidden variables or dynamical collapse theories or whatever. So, the entire point of many worlds is to explain what we observe. But it tries to explain what we already have observed, right? It's not trying to be different from what we've observed because that would be something other than quantum mechanics. </s>
<s>[INST] Yeah. Political discourse is the kind of tree you're walking down [/INST] and I got it, and you're like taking more I used to keep my focus guided, so I'm not like running off on a weird tangent or responding to something I didn't say or something. </s><s>[INST] What about like doing research? It's just, is there a system to your note-taking? Because mentally you seem to be one of the most organized people I've listened to. So is there, is it in your mind [/INST] or is there a system that's on paper? A little of both. I feel like the human mind is a beautiful thing if you have interest in an area. So the, like what I'll tell people is, let's say there's like a totally new topic that I'm researching, I don't know anything. And I'll do a couple of these on stream. I think they're boring but people watch it. I might open a Wikipedia article and I'll read and I hit something I don't know and then I open the next Wikipedia article and I read into and then I might have like seven tabs open and I'll read and I'll read and I'll read. And I'll read a ton of stuff, maybe for an hour, two, three, four hours of stuff. And then by the end, you know, someone in chat will ask me like, do you even remember like this particular thing? And I'll say, not really, no, not too much. But what happens is, as long as you've seen it once, what will happen is like the next day, the day after, we'll read something else and we're like, I remember that thing from this thing. I remember like vaguely that, and then if you see it like a third time you're like, oh, this makes sense because, especially when it comes to, oh, here's like a little trick on stuff, if you're ever reading any news and there's a place that pops up, always look at it on a map because so much of history is like on a map. It's so important to like know the geography. It makes things make so much more sense. But, yeah, once I start to see stuff over and over again, just because I've like read it a few times, stuff will start to kind of connect in my mind and like, oh yeah, well this makes sense. sense of course these people believe this it because of this or of course this happened here. It's because that happened there, so yeah. It's a lot of that. If there's a topic that I'm doing specific research for, so like vaccine-related stuff is a big one. The Ukrainian-Russian conflict is a big one. That I'll break out a note, I'll probably get to a Google Doc and I'll just start writing an outline of the rough points of everything </s><s>[INST] just to organize my thoughts around different topics. We're just gonna go on tangent upon a tangent and upon a tangent. We'll return to the low point Always returning from the philosophy to the psychology. So you did the Ukraine topic. One question is what role does US play in this war? Could they have done something to avoid the war? Did they have a role to play in forcing Vladimir Putin's hand? Do they have a role to play in deescalating the war towards a peace agreement and the opposite? If it does escalate towards something like the use of a tactical nuclear weapon, are they to blame? [/INST] Are we to blame your life at some point? Oh man, somebody sent me an email a while ago with great words. There's a specific way to navigate a conversation where you can kind of like contribute to a negative event, but you're not really the one responsible for it. Like the classic example is a woman goes out late at night, gets a little bit too drunk, and then something happens, and it's like, while there might've been steps she could've taken to mitigate the risk, it's not her fault of what happened because the responsibility rests on the agent making the choice, right? There's a chooser at some point that is choosing to do wrong or evil. I don't believe in any of the arguments that say the United States has contributed to Russia's position on Ukraine or the actions that they've taken on Ukraine. There are several arguments that some people, some even political scholars are putting out there to say that the United States is to blame, but I find them completely unconvincing. I think that when you ask the question of like, what is the United States' role or what has our role been, I think it's really important for us, I don't think we even agree as a country on what our role should be, which I think is a hard one because you've got this kind of, there's this growing populist movement in the United States, it might be the far left and the far right, and I think populists tend to have this kind of isolationist view of the world where the United States should just be our own thing, we shouldn't be telling anybody what to do, we shouldn't be the world police, and then kind of more in these like, center-less center-right positions And then across a lot of Europe, you've got, well, okay, the United States is kind of like the big kid on the block. Like we're looking to them for guidance and leadership on situations like what's going on in Ukraine. So, insofar as the original question is like, what is the United States responsibility? I think we have a responsibility to ensure the relative like freedom, prosperity, and stability across Europe. I think that defending Ukraine's sovereignty and right to their borders is a part of that. And I don't believe that prior to the invasion in 2022, I don't think the United States was contributing to Russia invading that country. I know there are arguments given that like the expansion of NATO, you know, has, has something that's been threatening to Russia, but the Baltics joined and Russia didn't do anything about it. The invasion to Crimea was very clearly a response to the revolution in 2014. The invasion on the borders is clearly a response to Ukraine winning that civil war in the Southeast and the Donbass, and Russia becoming more aggressive. I don't think that you can blame any of that on NATO expansion. There's no NATO countries that are threatening Russia that weren't imitating Russia. </s>
<s>[INST] to know how we're going to interact with alien life. You think there's a lot of kinds of life that's possible. I guess that was the intuition. Yeah. You provided that the way biology itself, but even this particular kinds of biology that we have on earth is something that is just one sample of nearly infinite number of other possible complex autonomous self-replicating type of things that could be possible. And so we're almost unable to see the alternative versions of us. I mean, we'll still be able to detect them, we'll still be able to interact with them. We'll still be able to like, which, what's exactly is lost in translation? Why can't we see them? Why can't we talk to them? Because I too have a sense, you put it way more poetically, but it seems both statistically and sort of romantically, it feels like the universe should be teeming with life, like super intelligent life. And I just, I sit there and the Fermi Paradox is very, it's felt very distinctly by me when I look up at the stars, because it's the same way I feel when I'm driving through New Jersey and listening to Bruce Springsteen and feel quite sad. It's like Louis C.K. talks about pulling off to the side of the road and just weeping a little bit. I'm almost wondering like, hey, why aren't you talking to us? It feels lonely. It feels lonely [/INST] because it feels like they're out there. I think that there are a number of answers to that. I think the Fermi Paradox is perhaps based on the assumption that if life did emerge in the universe, it would be similar to our life and there's only one solution. And I think that what we've got to start to do is go out and look for selection detection, an evolution detection, rather than life detection. And I think that once we start to do that, we might start to see really interesting things. And we haven't been doing this for very long. And we are living in an expanding universe and that makes the problem a little bit harder. Everybody's always leaving. But I'm very optimistic that we will, well, I don't know, there are two movies that came out in the same within six months of one another, Ad Astra and Cosmos. Ad Astra, they're very expensive. Blockbuster, you know, with Brad Pitt in it and saying there is no life and it's all, you know, we've got a life on Earth has more pressures. And Cosmos, which is a UK production, which basically aliens came and visited Earth one day and they were discovered in the UK. Right. It was quite, it's a fun film. But I really loved those two films. And at the same time, those films, at the time those films are coming out, I was working on a paper, a life detection paper. And in fact, it was so hard to publish this paper. And it was almost I got so depressed trying to get this science out there that I felt the depression of the film in Ad Astra, like life, there's no life elsewhere in the universe. But I'm incredibly optimistic that I think we will find life in the universe, firm evidence of life. And it will have to start on Earth, making life on Earth and surprising us, we have to surprise ourselves and make non biological life on Earth. And then people say, well, you made this life on Earth, therefore, it's the you're part of the causal chain of that. And that might be true. But if I can show how I'm able to do it with very little cheating or very little information inputs, just creating like a model planet, some description, and watching it, watching life emerge, then I think that we will be even to persuade even the hardest critic that it's possible. Now with regards to the Fermi paradox, I think that we might crush that with the JWST. It's basically if I recall correctly, the mirror is about 10 times the size of the Hubble, that we're going to be able to do spectroscopy, look at colors of exoplanets, I think, not brilliantly, but we'll be able to start to classify them. And we'll start to get a real fit feel for what's going on in the universe on these exoplanets, because it's only the last few decades, I think, maybe even last decade that we even came to recognize that exoplanets even are common. And I think that that gives us a lot of optimism that life is going to be out there. But I think we have to start framing. We have to start preparing the fact that biology is only one solution. I can tell you with confidence that biology on Earth does not exist anywhere else in the universe. We are absolutely unique. </s><s>[INST] Well, okay, I love the confidence. But where does that confidence come from? You know, chemistry, like how many options does chemistry really have? [/INST] Many, that's the point. And the thing is, this is where the origin of life scam comes in, is that people don't count the numbers. So if biology, as you find on Earth, is common everywhere, then there's something really weird going on that basically written in the quantum mechanics, there's some kind of these bonds must form over these bonds, and this catalyst must form over this catalyst when they're all quite equal. Life is contingent. The origin of life on Earth was contingent upon the chemistry available at the origin of life on Earth. So that means if we want to find other lifelike, other Earth-like worlds, we look for the same kind of rocky world, we might look in the same zone as Earth, and we might expect reasonably to find biological-like stuff going on. That would be a reasonable hypothesis, but it won't be the same. It can't be. It's like saying, I don't believe in magic. That's why I'm sure. I just don't believe in magic. I believe in statistics, and I can do experiments. And so I won't get exactly the same sequence of events, I'll get something different. And so there is TikTok elsewhere in the universe, but it's not </s>
<s>[INST] But in a complimentary fashion somehow. And I think a lot of that has to do with the interaction, collaboration with robots and with AI systems. I'm hoping there's a lot of interesting possibilities there. [/INST] I think that could be really cool, right? If you can work in an interaction and really be helpful. Robots, you know, you can ask a robot to do a job you wouldn't ask a person to do, and that would be a real asset. You wouldn't feel guilty about it, you know? You'd say, just do it. </s><s>[INST] It's a machine and I don't have to have qualms about that. The ones that are machines, I also hope to see a future and it is hope. I do have optimism about that future where some of the robots are pets, have an emotional connection to us humans. And because one of the problems that humans have to solve is this kind of, a general loneliness, the more love you have in your life, the more friends you have in your life, I think that makes a more enriching life, helps you grow and I don't fundamentally see why [/INST] some of those friends can't be robots. There's an interesting long running study, maybe it's in Harvard, they just, nice report article written about it recently, they've been studying this group of a few thousand people now for 70 or 80 years. And the conclusion is that companionship and friendship are the things that make for a better and happier life. Maybe it's in Harvard, they just, and so I agree with you. And I think that could happen with a machine that is probably simulating intelligence. I'm not convinced there will ever be true intelligence in these machines, sentience, but they could simulate it and they could collect your history and they could, I guess it remains to be seen whether they can establish that real deep, when you sit with a friend and they remember something about you and bring that up and you feel that connection, it remains to be seen if a machine </s><s>[INST] is gonna be able to do that for you. Well, I have to say, inklings of that already started happening for me, some of my best friends at robots. And I have you to thank for leading the way in the accessibility and the ease of use of such robots and the elegance of their movement. Robert, you're an incredible person. Boston Dynamics is an incredible company. I've just been a fan for many, many years for everything you stand for, for everything you do in the world. If you're interested in great engineering, robotics, go join them, build cool stuff. I'll forever celebrate the work you're doing. And it's just a big honor that you sit with me today and talk, it means a lot. So thank you so much. [/INST] You're doing great. That's ability and the ease. Thank you, Lex. </s><s>[INST] I'm honored to be here and I appreciate it, it was fun. Thanks for listening to this conversation with Robert Plater. To support this podcast, please check out our sponsors in the description. And now, let me leave you with some words from Alan Turing in 1950, defining what is now termed the Turing test. A computer would deserve to be called intelligent if it could deceive a human into believing that it was human. [/INST] Thank you for listening and hope to see you next time. </s>
<s>[INST] Nevertheless, you were keeping track of the money and brought us uh one close to $2 million I think so, so that if it was for real money, if you were able to earn money, that was quite impressive and and inspiring achievement. Just a few details. What, what were the players looking at, were they behind a [/INST] computer? What what was the interface like? Yes, they were playing much like they normally do these top players when they play this game, they play mostly online. So they used to playing through a Ui and they did the same thing here. So there was this layout, you could imagine there's a table on the screen, there's the human sitting there and then there's the Ai sitting there and the screen source everything that's happening, the cars coming out and source the bets being made. And we also had the betting history for the human. So if the human, I forgot what had happened in the hand so far they could actually reference back and and and and so forth. </s><s>[INST] Is there a reason they were given access to the betting history for? Well, [/INST] we we just uh it didn't really matter that they wouldn't have forgotten anyway, these are top quality people, but we just wanted to put out there. So it's not a question of the human forgetting and the ai somehow trying to get advantage of better memory. </s><s>[INST] So what was that like? I mean, that was an incredible accomplishment. So what did it feel like before the event? Did you have doubt hope? Where was your confidence at? [/INST] Yeah, that's great. So great question. So uh 18 months earlier, I had organized a similar brains versus Ai competition without previous ai called cloudy Cool. And we couldn't beat the humans. uh so this time around it was only 18 months later and I knew that this new Ai Librettos was way stronger, but it's hard to say how you'll do against the top humans before you try. So I thought we had about a 5050 shot And the international betting sites put us as us as a 4-1 or 5-1 underdog. So it's kind of interesting that people really believe in people and over a I uh not just people, people don't just believe over believe in themselves, but they have over confidence in other people as well compared to the performance of Ai. And uh yeah, so we were at 4-1 of 5-1 underdog. And even after three days of beating the humans in a row, we were still 5050 on the international betting sites. </s><s>[INST] Do you think there's something special and magical about poker in the way people think about it in a sense you have, I mean, even in chess, there's no Hollywood movies, poker is the star of many movies and there's this feeling that certain human facial expressions and body language, eye movement, all these tells are critical to poker, like you can look into somebody's soul and understand their betting strategy and so on. So that's probably why possibly do you think that is why people have a confidence that humans will out because ai systems cannot in this construct perceive these kinds of towels, they're only looking at betting patterns and uh and nothing else, the betting patterns and and statistics. So what's more important to you if you step back on human players, human versus human, what's the role of these tells of these ideas that we romanticize? [/INST] Yeah. So I'll split it into two parts. So one is why do humans trust humans more than a. I and all have overconfidence in humans. I think that's that's not really related to tell a question. It's just that they've seen these top players, how good they are and they're really fantastic. So it's just hard to believe that the way I could beat them. So I think that's where that comes from. And and that's actually maybe a more general lesson about ai that until you've seen it over perform a human, it's hard to believe that it could. But then the tales, um, a lot of these top players, they're so good at hiding tells that among the top players, it's actually not really worth it for them to invest a lot of effort trying to find tells in each other because they're so good at hiding them. So yes, at the kind of friday evening game tell us are going to be a huge thing, You can read other people and if you're a good reader, you read them like an open book, but at the top levels of poker. Now the tale has become a less much much smaller and smaller aspect of the game as you go to the top levels. </s><s>[INST] The the amount of strategies the amounts of possible actions is uh is very large tend to the power of 100 plus. Uh So there has to be some I've read a few of the papers related uh there has it has to form some abstractions of various hands and actions. So what kind of abstractions are effective for the game of poker? [/INST] Yeah so you're exactly right. So when you go from a game three, that's 10 to the 161 especially in an imperfect information game, it's way too large to solve directly. Even with our fastest equilibrium finding algorithms. So uh you want to abstract it first. And abstraction in games is much trickier than abstraction in M. D. P. S. Or other single agent settings because you have these abstraction pathologies that if I have a final grand abstraction, the strategy that I can get from that for the real game might actually be worse than the strategy I can get from the coarse grained obstruction. You have to be very careful. </s>
<s>[INST] Let's go with a big question first. [/INST] Okay, I was a big question 1st. Yeah, I think it's very interesting hypothesis or idea and uh I have a back on the physics. So I know a little bit about physical theories, the standard model of particle physics and general relativity theory. And they are amazing and described virtually everything in the universe. And they're all in a sense computable theories. I mean they're very hard to compute and you know, it's very elegant, simple theories which describe virtually everything in the universe. So there's a strong indication that somehow the universe is computable, but it's a plausible hypothesis. </s><s>[INST] So what do you think? Just like you said, general relativity, quantum field theory, what do you think that the laws of physics are so nice and beautiful and simple and compressible? Do you think our universe was designed uh is naturally this way? Are we just focusing on the parts that are especially compressible. Our human minds just enjoy something about that simplicity and in fact there's other things that are not so compressible. [/INST] No, I, I strongly believe and I'm pretty convinced that the universe is inherently beautiful, elegant and simple and described by these equations. And we're not just picking that. I mean, if there were some phenomena which cannot be neatly described scientists who try that, right? And you know, there's biology which is more messy, but we understand that it's an emergent phenomena and you know, it's complex systems, but they still follow the same rules, right. Of quantum electrodynamics. All of chemistry follows that. And we know that, I mean, we cannot compute everything because we have limited computational resources. No, I think it's not a bias of the humans, but it's objectively simple. I mean, of course, you never know. You know, maybe there's some corners very far out in the universe or super super tiny below the nucleus of of um of atoms or well parallel universes where which are not nice and simple, but there's no evidence for that. And we should apply Occam's razor and you know, choose the simple street consistent with it. But also it's a little bit self referential. </s><s>[INST] So maybe a quick pause, what is Occam's razor? [/INST] So Occam's razor says that you should not multiply entities beyond necessity, which sort of if you translated to proper english means uh and and you know, in a scientific context means that if you have two theories or hypotheses or models which equally well describe the phenomenon your study or the data. You should choose the more simple one. </s><s>[INST] So that's just the principal sort of that's not like a provable law? Perhaps? Perhaps we'll kind of discuss it and think about it. But what's the intuition of why? The simpler answer is the one that is likely to be more correct descriptor of whatever we're talking about. [/INST] I believe the dot coms razor is probably the most important principle in science. I mean of course, well, logical deduction if we do experimental design. But um science is about finding, understanding the world, finding models of the world and we can come up with crazy complex models which you know, explain everything but predict nothing. But um the simple model seemed to have predictive power and it's a valid question why. And um there's two answers to that. You can just accept it. That is the principle of science and we use this principle and it seems to be successful. We don't know why, but it just happens to be or you can try to find another principle which explains or comes razor. And if we start with the assumption that the world is governed by simple rules, then there's a bias towards simplicity and planning or comes razor, um is the mechanism to finding these rules. And actually in a more quantitative sense. And we come back to that later in case of someone deduction, you can rigorously prove that used to assume that the world is simple, then Occam's razor is the best you can do in a certain sense. So </s><s>[INST] I apologize for the romanticized question. But why do you think outside of its effectiveness? Why do we do you think we find simplicity so appealing as human beings? Why does it just why does E. Equals M. C. Squared seems so beautiful to us humans [/INST] I guess mostly in general many things can be explained by an evolutionary argument and you know there's some artifacts in humans which you know are just artifacts and not an evolutionary necessary. But with this beauty and simplicity it's I believe at least the core is about like science um finding regularities in the world, understanding the world which is necessary for survival, right? You know if I look at a bush right and they're just the noise and there is a tiger. Right? And it's me then I'm dead. But if I try to find a pattern and we know that humans are prone to um find more patterns in data than they are, you know like mars face and all these things but these buyers towards finding patterns even if they're not. But I mean it's best of course if they are helps us for survival. </s><s>[INST] Yeah. That's fascinating. Haven't thought really about the I thought I just loved science but they're indeed from in terms of just for survival purposes there is an evolutionary argument for why why we find the work of Einstein is so beautiful. Maybe a quick uh small tangent could you describe what Solomon of induction is? [/INST] Yeah. So that's a theory which I claim and resolution of sort of claimed a long time ago that this solves the big philosophical problem of induction and I believe the claim is essentially true and what it does is the following. So, okay, for the picky listener um induction can be interpreted narrowly and wildly uh narrow means, inferring models from data and widely means also then using these models for doing predictions or predictions. Also part of the induction. So I'm a little sloppy sort of terminology and maybe that comes from so long enough, you know, being sloppy. Maybe I should say that we can't complain anymore. So let me explain a little bit this theory um in simple terms. So assume we have a data sequence. Make it very simple. The simplest one say 11111. And you see if 100 once, what do you think comes next? The natural order. I must speed up a little bit. The natural answer is of course, you know, one. Okay. And the question is why? Okay, well we see a pattern there. Yeah, okay, there's a one and repeat it. And why should it suddenly after 100 ones be different. So what we're looking for is simple explanations or models for the data we have. And now the question is a model has to be presented in a certain language in which language to be used in science. We want formal languages and we can use mathematics or we can use programs on a computer. So abstract liana touring machine influences. Or it can be a general purpose computer. So um and then of course lots of models of you can say maybe it's 100 ones and then 100 zeros and 100 ones. That's a model. Right? But They're simpler models. There's a model. Print one loop. Now that also explains the data. And if you push it to the extreme you are looking for the shortest program which if you run this program reproduces the data you have it will not stop. It will continue naturally. And this you take for your prediction and on the sequence of once it's very plausible. Right? At print one loop is the shortest program. We can give some more complex examples like 12345. What comes next? The short program is again you know counter. Um And so that is Roughly speaking how solemn oath of induction works. Um the extra twist is that it can also deal with noisy data. So if you have for instance a coin flip they are biased coin which comes up head with 60% probability. Um Then it will predict um if we learn and figure this out and after violet predict the next um coin flip will be heads with probability 60%. So it's a stochastic version of that. </s>
<s>[INST] you're looking for the echoes of the same kind of experience in order to predict what the future holds. Yeah, the victor, franco in his book Man's Search for meaning. Not sure if you've read describes his experience at the concentration concentration camps during World War Two, as a way to describe that finding identifying a purpose in life, a positive purpose in life, you can save one from suffering, first of all, do you connect with the philosophy that he describes there? [/INST] Not really. I mean, the so I can I can really see that somebody who has that feeling of purpose and meaning and so on, that that could sustain you uh I in general don't have that feeling and I'm pretty sure that if I were in a concentration camp give up and die, you know? So he talks he's he's a survivor and you know, he survived with that and I'm and I'm not sure how is central to survival. The sense is, but I do know when I think about myself that I would have given up uh oh yeah, this isn't going anywhere. Uh And there is there is a sort of character that that manages to survive in conditions like that. And then because they survived, they tell stories and it sounds as if they survived because of what they were doing, We have no idea they survived because the kind of people that they are and the other kind of people who survived and will tell themselves stories of a particular kind. So I'm not </s><s>[INST] so you don't think seeking purpose is a significant driver and are being. [/INST] It's a very interesting question because when you ask people whether it's very important to have meaning in their life, that's Oh yes, that's the most important thing. But when you ask people, what kind of a day did you have? And and you know, what were the experiences that you remember? You don't get much meaning. You get social experiences then. Uh and and some people say that for example, in and and child, you know, taking care of Children. The fact that they are your Children and you're taking care of them uh makes a very big difference. I think that's entirely true. Uh But it's more because the story that we're telling ourselves, which is a very different story when we're taking care of our Children or when we're taking care of other things, </s><s>[INST] jumping around a little bit in doing a lot of experiments, Let me ask a question. Most of the work I do for examples in the world, in the real world. But most of the clean good science that you can do is in the lab. So that distinction, do you think we can understand the fundamentals of human behavior through controlled experiments in the lab. If you talk about people diameter for example, it's much easier to do when you can control lighting conditions, right? Uh So when we look at driving lighting variation destroys almost completely your ability to use pupil diameter. But in the lab for, as I mentioned semi autonomous or autonomous vehicles and driving simulators, we can't we don't capture true honest human behavior in that particular domain. So your what's your intuition? How much of human behavior can we study in this controlled environment of the lab [/INST] a lot? But you'd have to verify it. You know, that your conclusions are basically limited to the situation to the experimental situation, then you have to jump that big inductive leap to the real world. Uh So and and that's the flare. That's where the difference. I think between the good psychologist and others that are mediocre is in the sense that that your experiment captures something that's important and something that's real and others are just running experiments. </s><s>[INST] So what is that like the birth of an idea to his development in your mind, to something that leads to an experiment is that similar to maybe like what Einstein or a good physicists do is your intuition you basically use your intuition to build up. [/INST] Yeah, but I mean, you know, it's it's very skilled intuition. I mean, I just had that experience actually. I had an idea that turns out to be a very good idea a couple of days ago. And and you and you have a sense of that building up. So I'm working with a collaborator and he essentially was saying, you know, what, what are you doing, you know, what's what's going on? And I was really I couldn't exactly explain it, but I knew this is going somewhere. But you know, I've been around that game for a very long time. And so I can you develop that anticipation that yes, this this is worth </s><s>[INST] following something. Something here [/INST] that's part of the skill </s><s>[INST] is that something you can reduce two words in describing a process in the form of advice to others. [/INST] No, </s><s>[INST] follow your heart essentially. [/INST] You know, it's it's like trying to explain what it's like to drive. It's not, you've got to break it apart and it's not and then you lose and then you lose the experience. </s>
<s>[INST] What do you think is the mechanism of how it works in the mind? Is it is it a mystery to you still, do you have inklings of how this essential thing for cognition works? [/INST] What I meant 35 years ago was of course they crude physics model to show the kind actually enable you to understand my old sons of understanding is a physicist because you could say ah I understand why this goes two stable states. It's like things going down downhill, right? And that gives you something with which to think in physical terms rather than only in mathematical terms. </s><s>[INST] So, you've created these associative artificial [/INST] network that's right now. If you if you look at what I did, I didn't at all describe a system which gracefully learns. I described as this is in which you could understand how things, how learning could link things together. How very crudely you might learn. One of the things which intrigues me is I re investigate that is to now to some extent is look, I see you, I'll see you if every second for the next hour or what have you each each look at you as a little bit different. I don't store all those Second by second images. I don't store 3000 images. I somehow compact this information. So I now have a view of you which can, which I can use. It doesn't slavishly remember anything in particular, but it compacts the information into useful chunks which are somehow these chunks which are not just activities of neurons, bigger things than that, which are the real entities which are which are useful which are useful to you </s><s>[INST] useful, useful to you to describe to compress this information. [/INST] You asked him present in such a way that if I get the information comes in just like this again, I don't bother your father to rewrite it or efforts to rewrite it simply do not yield anything because those things are already written and that needs to be not look this up somewhere. I started somewhere already got to be something which is much more automatic in the machine hardware. </s><s>[INST] Right? So in the human mind, how complicated is that process do you think? So you you've created, it feels weird to be sitting with john Hartfield calling them hot field networks, but it is weird. Yeah, but nevertheless that's what everyone calls him. So here we are. Uh so that's a simplification, that's what a physicist would do. You. And Richard feynman sat down and talked about associative memory now as a if you look at the mind where you can't quite simplify it so perfectly. Do you [/INST] love me back truck track just a little bit. Yeah, Biology is about dynamical systems. Computers are dynamical systems. Um you can answer if you want to mountain the bottle biology, there's one bottle neurobiology. What is the time scale? There's a dynamical system in which a fairly fast timescale in which you could say the synapses don't change much during this computation. So I'll think of the synapses fixed and just do the dynamics of the activity. Or you can say this is an episode changing fast enough that I have to have the synaptic dynamics working at the same time as the system dynamics in order to understand the biology most are if you look at the feed forward artificial neural nets there all done as learning. First of all, I spend some time learning not performing and I turn off learning and I perform right, That's not biology. And so as I look more deeply at neurobiology, even an associative memory, I've got to face the fact that the dynamics of the synapse changes going on all the time. And I can't just get by by saying I'll do the dynamics of activity with a fixed synapses. </s><s>[INST] So the synaptic the dynamics of the synapses is actually fundamental to the whole [/INST] system. And there's there's not there's nothing necessarily separating the time skills when the time skills can be separated. It's neat from the physicists at the mathematicians point of view but it's not necessarily true in neurobiology </s><s>[INST] so you're you're kind of dancing beautifully between showing a lot of respect to physics and then also uh saying that physics cannot quite reach the the complexity of biology. So where do you land or do you continuously dance between [/INST] the two? I continuously dance between them. Because my whole notion of understanding is that you can describe to somebody else how something works in ways which are honest. Unbelievable and still not describe all the nuts and bolts in detail. Whether I can describe whether as 10-32 molecules colliding in the atmosphere, I can stimulate whether that way I have a big enough machine, I'll simulate it accurately. It's no good for understanding. I understand I understand things, I want to understand things in terms of wind patterns, hurricanes, pressure differentials and so on. All things as their collective. And the physicist physicist and me always hopes that biology we'll have some things that you can be said about. It was they're both true and for which you don't need all the molecular details of the molecules colliding. That's what I mean from the roots of physics by understanding. </s><s>[INST] So what did, again? Sorry, But hot field networks help you understand what insight to give us about memory about learning. [/INST] They didn't give insights about learning. They gave insights about how things having learned could be expressed how having learned a picture of a picture of your reminds me of your name. That would but it didn't describe a reasonable way of actually doing the learning only instead if you had previously learned the connections of this kind of pattern will now be able to behave and then physical way with a day off, I part of the pattern in here. The other pattern part of the pattern will complete over here. I can understand that physics, if the right learning stuff had already been put in and you can understand why then putting in a picture of somebody else would generate something else over here. But it didn't not under that did not have a reasonable description of the learning process. </s>
<s>[INST] very akin to the different ways the memories stored in the computer. So there's RAM, there's hard drive, [/INST] you can make that mapping. Right? So I think the interesting thing is that based on the biology, we can have a more sophisticated, you know, I think we can revise some of our some of our computer engineering methods because there's some interesting things that biology does. We haven't done yet, but but you can but that map but that mapping is not bad. I mean I think it works in many ways. </s><s>[INST] Yeah, I wonder because I mean the way we build computers at the root of computer science is the idea of proof of correctness. We program things to be perfect, reliable. You know, this idea of resilience and robustness to unknown conditions is not as important. So that's what biology is really good at. So I don't know what kind of systems, I don't know how we go from a computer to biological system in the future. Yeah, [/INST] I think that, you know, you know the thing about biology like is all about making really important decisions really quickly on very limited information. I mean that's what Biology is all about. You have to act, you have to act now. The stakes are very high and you don't know most of what you need to know to be perfect. And so there's no not even an attempt to be to be perfect or to get it right in any sense. There are just things like active inference minimize surprise, optimize some some efficiency and and and some things like this that that that guides the whole the whole </s><s>[INST] business. I mentioned to offline that um somebody who's a fan of your work is on drake apathy and he's amongst many things. Also Rights, occasionally a great blog. He came up with this idea. I don't know if he coined the term but of software 2.0, where the programming is done in the space of configuring these artificial neural networks. Is there some sense in which that would be the future of programming for us humans where we're less doing like python like programming and more. Um, how would you, how would that look like? But basically doing the hyper parameters of something akin to a biological system and watching it go and keeping adjusting it and creating some kind of feedback loop within the system. So corrects itself and then we watch it over time, accomplish the goals we wanted to accomplish is that kind of the dream of the the dogs, the describing the nature paper. [/INST] Yeah, I mean that that's what you just painted is a is a very good description of our efforts at regenerative medicine as a kind of somatic psychiatry. So the idea is that you're not, you know, you're not trying to micromanage. I mean, think about the limitations of of a lot of the medicines today. We try to to interact down at the level of pathways. Right? So, so we're trying to micromanage it. What what's the problem? Well, one problem is that for almost every medicine other than antibiotics, once you stop it, the problem comes right back. You haven't fixed anything. You were addressing symptoms. You weren't actually curing anything again Except for antibiotics? Uh, that's one problem. The other problem is you have massive amount of side effects because you were trying to interact at the lowest level. It's right. It's like, I'm gonna, you know, I'm gonna I'm gonna try to program this computer by changing the melting point of copper. Like maybe you can do things that way. But my God, it's hard to to to program at the right at the at the hardware level. So, what what I think we're starting to understand is that And and by the way, this goes back to what you were saying before about uh that we could have access to our internal state, Right? So people who practice that kind of stuff, right? So yoga and and and biofeedback in those. Those are all the people that uniformly will say things like, well, the body has an intelligence in this area, like those two sets overlap perfectly. Because because that's exactly right? Because once you once you start thinking about it that way, you realize that the better locus of control is not always at the lowest level. This is why we don't program with a soldering iron. Right? We we take advantage of the high level intelligences that are there, which means trying to figure out, okay, which of your tissues can learn, what can they learn? Uh Why you know, why is it that certain drugs stop working after you take them for a while with this habituation. Right. And so can we understand habituation, sensitization, associative learning these kinds of things in chemical pathways. We're going to have a completely different way I think um we're gonna have a completely different way of of using drugs and medicine in general when we start focusing on the gold states and and on the intelligence of our subsystems as opposed to treating everything as if the only path was micromanagement from chemistry upwards. </s><s>[INST] Can you speak to this idea of somatic psychiatry? What are somatic cells? How do they form networks that use by electricity to have memory and all those kinds of things. What are somatic cells like basics [/INST] here? Somatic cells just means the cells of your body so much just means body. Right? So so somatic cells are just the same. I'm not even specifically making a distinction between somatic cells and stem cells or anything like that. I mean basically all the cells in your body, not just neurons, but all the cells in your body. They form electrical networks during embryo genesis during regeneration. What those networks are doing in part is processing information about what our current shape is and what the goal shape is. How do I know this? Because I can give you a couple of examples. 11 example is when we started studying this, we said, okay here's a here's a planetarium planetarium is a flatworm. It has one head and one tail normally. And the amazing that there's several amazing things about plan area. But basically they kind of, I think, I think plan area hold the answer to pretty much every deep question of life. For one thing, they're similar to our ancestors. So there they have true symmetry. They have a true brain. They're not like earthworms. They're, you know, they're much more advanced life form. They have lots of different internal organs, but they're these little um they're about, you know, maybe two cm in the centimeter to two in size. We have a bread head in the tail. And the first thing is plenary are immortal. So they do not age. There's no such thing as an old plan area. So that right there tells you that these theories of thermodynamic limitations on lifespan are wrong. It's not it's not that well over time of everything degrades. You know, plan area can keep it going for probably, you know, how long have they been? Around 400 million years. Right. So these are the actually, so the primary in our lab are actually in physical continuity. The area that we're here 400 million years ago. So </s>
<s>[INST] Again, that's simply safe dot com slash lex. This is the lex Fridman podcast and here is my conversation with Rodney brooks. What is the most amazing or beautiful robot that you've ever had the chance to work with. [/INST] I think it was domo which was made by one of my grad students, serenade Singer. It now sits in Daniel Russo's office Director of C sale and it was just a beautiful robot. And Aaron was really clever. He didn't give me a budget ahead of time. He didn't tell me what he was going to do, he just started spending money a lot of money. He and Jeff Webber who um was mechanical engineer who Aaron insisted he brings with him when he became a grad student built this beautiful gorgeous robot Doma which is a apple torso humanoid to two arms uh With fingers three fingered hands. Um uh And uh face eyeballs all uh not the not the eyeballs but everything else. Series elastic actuators. Uh You can interact with it um Cable driven. All the motors are inside and it's just gorgeous. </s><s>[INST] The eyeballs are actuated too. And now [/INST] the eyeballs are actuated with cameras and so had a visual attention mechanism. You know looking when people came in and look in their face and talking with him, </s><s>[INST] why was it amazing [/INST] the beauty of it? You said you said what was the </s><s>[INST] most beauty? What is the most beautiful? It's [/INST] just mechanically gorgeous as everything Aaron builds has always been mechanically gorgeous. It's just exquisite in the detail. </s><s>[INST] Are we talking about mechanically like literally the amount of actuators. The [/INST] actuators, the cables he um analyzes different parts different colors and it just looks like a work of </s><s>[INST] art. What about the face is that do you find the face beautiful and robots. Um [/INST] When you make a robot it's making a promise for how well it will be able able to interact? So I always encourage my students not to over promise. You know, </s><s>[INST] even with its essence like the thing it presents, it should not over promise. Yeah. [/INST] So that the joke I make, which I think you'll get is if your robot looks like Albert Einstein, it should be the smartest Albert Einstein. So uh the only thing in in demos face is uh the eyeballs. Um and because that's all it can do, it can look at you and pay attention. Um and so there is no, it's not like one of those um japanese robots that looks exactly like a person at all. </s><s>[INST] But see the thing as us humans and dogs do don't just use eyes for as attentional mechanisms. They also use it to communicate as part of the communication, like a dog can look at you looking at another thing and look back at you and that designates that we're going to be looking at that thing [/INST] or intent. You know? And I'm both Baxter and soya at rethink robotics. They had a screen with graphic eyes. So it wasn't actually where the cameras were pointing, but the eyes would look in the direction it was about to move its arms. So people in the factory nearby were not surprised by its motions because it gave that intent away </s><s>[INST] before we talk about Baxter, which I think is a beautiful robot. Let's go back to the beginning. When did you first fall in love with robotics? We're talking about beauty and love to open the conversation. This is great. [/INST] I've got these, I was born in uh, the end of 1954 and I grew up in the Adelaide south Australia. And I have these two books that I dated 1961. So I'm guessing my mother found them in a store in 62 or 63. How and why? Wonder books? Um, how am I Wonder book of electricity And how do I want? The book of giant brains and robots? And uh, I learned how to build circuits. You know, when I was eight or nine simple circuits and I read, you know, learned the binary system. And um, I saw all these drawings mostly of robots. And then I tried to build them for the rest of my childhood. </s><s>[INST] Wait 61 you said [/INST] this was when the two books, I've still got the at home. </s><s>[INST] What does the robot mean in that context? No, [/INST] they were some of the robots that they had were, uh, arms, you know, big arms to move nuclear material around, but they had pictures of welding robots that look like humans under the sea welding stuff underwater. Um, so they weren't real robots. Uh, but there were, you know what people were thinking about for robots? </s><s>[INST] What were you thinking about? Where you're thinking about humanoids. Where you think about arms with fingers when you think about faces or cars. No, [/INST] actually to be honest I realized my limitation on building mechanical stuff. So I just built the brains mostly out of different technologies as I got older. Um uh I built a a learning system which was chemical based and I had this ice cube tray each well was a cell and by applying voltage to two electrodes, it would build up a copper bridge. So over time it would it would learn a simple network. Um So I could teach it stuff and that was mostly things were driven by my budget and nails as electrodes and a ice cream. I mean ice cube tray was about my budget at that stage. Later I managed to buy transistors and then I could build gates and flip flops and stuff. </s><s>[INST] So 11 of your first robot was an ice cube tray. [/INST] Yeah, it was very cerebral because it went to add very </s>
<s>[INST] that's a weird american warrior ethos that I've picked up, but also having the, the, the Russian, the city of brothers that don't see it, I don't see it as that they, they don't get draw, they think that there is a tension between the art of the martial art and the violence of the martial artist is a poetic way. I could put it, but they're not so fascinated with this dan gable dominating another human. They think the effortless, the effortlessness of the technique and your mastery of the art is exhibited in its effortlessness, how much you lose yourself in the moment and the timing that just the beauty of a timing, like there's much more like one example in judo, but also in wrestling, you can look at the foot sweep wrestlers in America and even judo players in America and much of the world don't admire the beauty of the foot sweep, but a well timed foot sweep, which is a way to sort of off balance to find the right timing to just effortlessly uh, changed the tape, turned the tables of uh, dominate your opponent is, is seen as the highest form of mastery and, and Russian wrestling and in case of judo, it's in japanese judo, it's interesting. I'm not sure, I'm not sure what what that tension is about. I think it actually takes me back to, I don't know if you listen to dan Carlin's hardcore history and Genghis khan, if you've ever, [/INST] I read a great, great book on Genghis khan. </s><s>[INST] I'm still, I'm still trying to adjust most of my life said genghis khan, but the right pronunciation is uh actually changes con. There's a tension there. We kind of think, I don't know, We, I kind of thought as Genghis khan is a ultra violent, a leader of ultra violent men. But another view, another way to see them is the people who warriors that valued extreme competence and mastery of the art of fighting with weapons, with bows, with horse riding, all that kind of stuff. And I'm not sure exactly where to place them on. My sort of thinking about violence in in our human history. [/INST] I think in a context of like a combat sports, I think there's a difference between an athlete winning a contest under a certain set of rules and a fighter winning a fight under those exact same rules, there's a different approach to it and I don't think one is any better than the other. Um like in M. M. A. I think a great example would be George ST pierre, Georgian. NPR's a tremendous, it's a tremendous athlete and he considers himself to be a martial artist first. He's trying to win an athletic competition. Like Nick Diaz is trying to bust your ass right? There's a different approach to it and yes, they've had different results at the highest level of competition, but it's difficult to attribute the difference in results just to their approach to the sport because they're different human beings with different abilities and different different physical attributes. Um The city of brothers have that luxury of being able to talk about the beauty of a perfectly timed slide by, right, there are other wrestlers that will never be able to pull that off and therefore they have to pursue other ways to defeat someone. And maybe it is that dan gable, breaking a man's spirit by out working him type thing, which it's beautiful in its own way. Uh, but we, we, we tend to self select the ways in which we're able to be successful and then kind of take a deep dive into that. </s><s>[INST] What do you think is more beautiful, brute force or effortless execution of technique that dominates another human? [/INST] I think it's a subjective thing based on what skills you perceive yourself to have. I'm never, I've never been a slick, super athletic, dexterous competitor in anything. And I've always been more of, uh, I've got to outwork, you've gotta out grind you, I gotta out mean you. And so because I've lived that, I tend to see the beauty in that more because I have a perceptual awareness that I don't have for the people who have the luxury of being very slick and athletic and, and, and using beautiful technique. Now that said, there's a phenomenal little video the other day, I sent to a friend of a compilation of foot sweeps by Liotta Makita in M. M. A. And they're so beautiful and they're so awesome and it's not that I don't have an appreciation for those, but I can't emulate those because I lack the physical ability to do that, whereas I, I at least have a chance to emulate some of the people who do it through grit and throughout working people. </s><s>[INST] But I would love to uh return to Jenkins con and get your thoughts about like I have so many mixed feelings about whether he is evil or not, Whether the violence that he brought to the world had ultimately the fact that it had maybe kind of like dan Carlin describes cleansed the landscape. It's like a reset for the world through violence had ultimately Mhm. A progressive effect on human civilization. Even though in the short term it led to massive, you could say suffering. I don't know what to make of that man. What what are your thoughts on genghis khan? [/INST] Um I think it's always difficult to look at a historical figure and their actions of their time through a modern day lens because it's very, it's easy for us to kind of, you know, in pune their achievements and the things that they did and say, oh well, you know what he did was wrong? Well, of course that can be true. But a lot of times we don't actually have any real good context or concept of the times they were living in and what really was deemed wrong and what really wasn't. We're looking at it through a very cushy modern lens that being said from what I've read about Genghis khan. Uh yeah, he was a violent dude. But also he gave you an option, He, when he, when he got to a village, he said, look, I'm going to, we're going to, you have a choice. You can come with us or you can run. And you know, he gave them an option to join his legion of fighters who he took very good care of. You know, he was the first military leader, uh, to pay his soldiers families when they died. And he did that based on the booty that they got when they raided a village, He took that money, he took his share and they divided that up amongst the soldiers and then the soldiers families. I think he also is credited with, uh, first like horseback mail routes or something like that, right is neither godfather of modern postal system. There's something, something </s>
<s>[INST] So first of all the proof of work idea is kind of, I mean at least to me seems pretty fascinating. It is, I mean that's uh it's kind of a revolutionary idea. I mean is it is it obvious to come up with that you can use, you can exchange basically computational resources for for identity. [/INST] It's uh it actually has a pretty long history. It was first proposed in a paper by Cynthia dwork and nay or in 1994 I believe. And the original use case was combating email spam. So the idea is that if you send an email you have to send it with a proof of work attached and like this makes it reasonably cheap to send emails to your friends, but it makes it really expensive to send spam to a million people. </s><s>[INST] Yeah, that's a simple brilliant idea. So maybe also taking a step back. So what is the role of Blockchain in this? What is the Blockchain? [/INST] Sure. So the Blockchain, my way of thinking about it is that it is this uh and a system where you have this kind of one virtual computer created by a bunch of these uh nodes in the network. Um and the reason why the term Blockchain is used is because the data structure that these systems used at least so far is one where they kind of different nodes in the network periodically published blocks. And a block is a kind of list of transactions together with a point or like a hash of a a previous block that builds on top of. Um and so you have a series of blocks that that uh, nodes in the network create for each block points to the previous block. It so you have this chain of them </s><s>[INST] is a fault tolerance mechanism built into the idea of Blockchain. There's a lot of possibilities, you know, ways to make sure there's no funny stuff going on. [/INST] There are indeed a lot of possibilities. Um so any kind of just simple architecture as I just described the way the fault tolerance happens is like this. Right? So you have a bunch of notes and they're just happily and if occasionally creating blocks, building on top of each other's blocks. And let's say you have kind of one block, we'll call it kind of block one. and then someone else builds another block. Honestly, we'll call it block to, then we have an attacker. And what the attacker tries to do is the attacker tries to revert block too. And the way they revert block two is instead of doing the thing they're supposed to do, which is build a block on top of block two and they're going to build another block on top of block one. Um so you have block one, which has two Children. Block two, and then block to prime. Now this might sometimes even happened by random chance if two nodes in the network just happen to create blocks at the same time and then we'll hear about each other's things before they create their own. But this also could happen because of an attack. Now, if this happens, you have an attack then the note in the Bitcoin system, the nodes follow the longest chain. So if this attack had happened and when the original chain had more than two blocks on it. So if it was trying to kind of revert more than more than two blocks, then everyone would just would just ignore it and and everyone would just keep following the regular chain. But here, you know, we have blocked too and we have blocked to prime and so that you are kind of even and then whatever block the next block is created on top of so say block three is now created on top of block two prime, then everyone said agrees that block three is that you had um and Block two prime is just kind of forgotten and then everyone just kind of peacefully builds on top of the block three and the thing continues. </s><s>[INST] So how difficult is it to mess with the system? So how like if we look at the general problem, like how many, what fraction of people who participate in the system have to be bad players? [/INST] Mm hmm. In </s><s>[INST] order to message literally like what is there? Is there a good [/INST] Number there is? Um, well, depending on kind of what your model of the participants is and like what kind of attack we're talking about. It's anywhere between 23.2 and 50 </s><s>[INST] of what? [/INST] Of all of the computing power in the network? </s><s>[INST] Sorry. So 22 and [/INST] 23 point between 23.2 and 50 </s><s>[INST] and 50% can be compromise. [/INST] So like once your, once your your portion of the total beauty power in the network goes above the 23.2 level, then there's kind of things that you can mean things that you can potentially do. And ask your percentage of the network kind of keeps going up then the, your abilities that you mean things kind of goes higher. And then if you have about 50% then you can just break everything. </s><s>[INST] So how hard is it to achieve that level? Like it seems that so far historically speaking has been exceptionally difficult. So [/INST] this is a challenging question. Um, so the economic cost of acquiring that level of stuff from scratch is fairly high. I think it's uh somewhere in the low billions of dollars. </s><s>[INST] And when you say that stuff, you mean computational resources. [/INST] Yeah. So specifically specialized hardware. And if A six that people use to solve these puzzles is to do the mining these </s><s>[INST] small tangent. Uh Obviously I work a lot in deep learning with Gpus and Asics for that application and I tangentially kind of here that so many of these you know sometimes NVIDIA Gpus are sold [/INST] out because </s>
<s>[INST] So I think it's kind of fascinating if you look throughout history and race is just part of that is, uh, we create the other and uh, treat the other with disdain through the legal system. But just human nature. I tend to believe we mentioned offline network with robots. It sounds absurd to say, especially to you, especially because we're talking about racism and it's so prevalent today. I do believe that there will be almost like a civil rights movement for robots because with, I think there's a huge value to society of having artificial intelligence systems that are, that interact with humans at our and our human like and the more they become human like he was, they will start, they will start to ask very fundamentally human questions about freedom about suffering about justice and they will have to come face to face. Like look in the mirror in asking the question just because we're biologically based just because we're sort of uh well just because we're human, does that mean we're the only ones that deserve the rights again, giving forming another other group which is robots. And I'm sure there could be along that path. Different versions of other that we form. So racism. Race is certainly a big other that we've made. As you said, a lot of progress on throughout the history of this country. But it does feel like we always create as we make progress create new other groups. And of course the other the other group that perhaps is outside the legal system that people talk about is the essential. Now I eat a lot of meat but the torture of animals, you know that people talk about when we look back from, you know, a couple of centuries from now look back at the kind of things we're doing to animals. We might regret that we might see that in a very different light. And it's kind of interesting to see the future trajectory of what we wake up to about the injustice in our in our ways. Um but the robot one is the one I'm especially focused on because uh but at this moment in time it seems ridiculous. But I'm sure most civil rights movements throughout history seem ridiculous at first. [/INST] Well it's interesting sort of outside of my uh intellectual bailey wick robots as I understand the development of artificial intelligence. Uh though the the aspect that uh uh huh still is missing is this notion of consciousness. Uh and that it's it's consciousness, that is the thing that will will move uh if it were to exist. And I'm not saying that it can or will, but if it were to exist would move robots from machines to uh something different. That is something that experienced the world in a way analogous to what how we experience it. Um And also as I understand the science, there's a um unlike what you see on on television that we're not we're not there yet. In terms of this notion of the machines having a consciousness, um uh </s>
<s>[INST] You have to get stronger and stronger I think in the face of that. But actual assassination and perhaps it's me being hopeful because I have a situation with Russia that I hope I'm not under. Well, I don't care actually, but there's some aspect in which social media presence I thought protects you a little bit because just imagine the outrage uh, from an attempted assassination assassination of you. [/INST] What was outraged when johnny cash you got killed like that </s><s>[INST] was the social media presence large [/INST] over one million people, I don't have that problem. He was 1.6 million to their followers </s><s>[INST] and the outrage wasn't there? [/INST] No because Saudis spoke to amazon prime studio netflix. There were people made a documentary body but told everybody don't cannot get that deal. So there was a huge censorship on that. And people of course like I mean they can talk about it one day, some distance from Saudi got cared horrible. They move on the next cute puppy right then execute cat like that's what the nature of this new generation does. They desensitized, It doesn't affect them. They keep following this instant pleasure instant high. That's what Instagram does to you. It changes your brain like that. So I was reading this book the shallows. We became shallow and shallow and our brain changed permanently. So this is a generation, we can get them angry for like 10 minutes create hashtags for one day. But then as quick as that was, it goes down like instantly. And I think that's the, </s><s>[INST] well that means okay, so that means that there is uh, it's an effective way to get rid of opposition is by murdering them. And that means a United States. If it stands for freedom, if it stands for the freedom of exchange of ideas, should be protecting people like you. [/INST] But they don't, they be involved. They didn't even protect kim jong un who is giving information 10 years. He was in his life. That's what is so I mean working for CIA is not bad and I I don't I hope, I mean the thing is he was giving information to bring down the vision that is valuable. That is something noble about him. But then you don't go extra miles to that. That's when I lost my faith in the U. S. System as well. Like this country just cares about saving face what is most minimum cause they pay for anything. And I went to South Korea constantly every single day intelligence calling me. You like the north korean agent going this place, where are you going to the U. S. S. Came to us? Nobody this is when people say that Usa asian like I wish they called me. I really truly do. But nobody nobody does here. I'm sure they know what's going on. But the south korean agent is more like oh my gosh, we don't want you to get killed. A south korean citizen right? And now I'm trying to become a citizen. So it's in a way it's I don't know what's worse Are </s><s>[INST] you are you afraid for your life? [/INST] I was afraid for those ever 3, 4 years I was afraid and he was but I had it came terms really like in my enemy is not some crazy psychopath is a state with a nuclear power to attack the most powerful country. If kim jong un decides if I die I'm gonna die. It's not up to me right? So in a way or just liberating that you is that if you are like afraid of some maps or some like Gangsters on the street, it's almost like you have power over a little bit. You gotta be like thinking that's my fault. I went that way right? But when it comes to kim jong un I know like my enemy so much bigger than me, it's in a ways of liberation and also it was I just I live a lot. So I have seen a lot, I've seen everything. I don't have that much younger. I left here like okay I'm going to soon. You know it's like okay maybe it's time like that is a part of life. So </s><s>[INST] in some sense you're willing to accept death to keep fighting for freedom in your and at least in part to place you call home. [/INST] Yeah. Do </s><s>[INST] you hope that one day you can return to north Korea? [/INST] I hope so. I hope I bring my son and time. This is like where your ancestors from two, </s><s>[INST] it would look very different. Then the place you came from in your as you hope, do you hope that there's a democracy one day that North Korea looks like South Korea. Yeah [/INST] what they're being paradise right? That's it. But I'm a rational optimist. I'm not, I just optimistic because I have to be I think as long as there are people who have changed the word right? Like who believed in something and worked for it and like, I don't know like this. So like Alice Rose a few people holding entire list word, right? I really believe in that. I think as long as that continues, that can happen in my country, as long as people like you someday when I decided to do something on north korean, working for using your brain power to solve this puzzle. How fascinating would that be. That's why I continue to speak content recruit </s>
<s>[INST] You had that intuition right away. That was seemed obvious to [/INST] Yeah. Yeah. </s><s>[INST] It isn't that magical though, that from just a little bit of biology can emerge the full beauty of the human experience. Is that why is that so obvious to you? [/INST] Well, obviously, and not obvious at the same time. Um and I think about Darwin in this context to, because Darwin knew very early on that none of the ideas that anybody had ever offered gave him a sense of understanding how evolution could have worked, but he wanted to figure out how it could have worked, that was his goal. And he spent a lot of time working on this idea and coming, you know, reading about things that gave him hints and thinking they were interesting, but not knowing why drawing more and more pictures of different birds that differ slightly from each other and so on, you know, and and then then he figured it out, but after he figured it out, he had nightmares about it, he would dream about the complexity of the eye, and the arguments that people had given about how ridiculous it was to imagine that that could have ever emerged from some sort of, you know, unguided process, that it hadn't been the product of design. And and uh so he didn't publish for a long time, in part because he was scared of his own ideas, he didn't think they could probably possibly be true. Um, but then, you know, by the time the 20th century rolls around, we all, uh, you know, we understand that many people understand or belief that evolution produced, you know, the entire range of animals that there are. Uh and uh, you know, the cards idea starts to seem a little wonky after a while, right? Like, well, wait a minute. Um, there's the apes and the chimpanzees and the bonobos and you know, like they're pretty smart in some ways, you know? So what? Oh, you know, somebody comes up, oh, there's a certain part of the brain that's still different. They don't, you know, there's no hippocampus in the monkey brain is only in the human brain. Uh Huxley had to do a surgery in front of many, many people in the late 19th century to show to them, there's actually a hippocampus in the chimpanzees brain, you know, so, so the continuity of the species is another element uh that, you know, contributes to um this sort of, you know, idea that we are ourselves uh total product of nature. Um and uh, that to me is the is the magic and the mystery how how nature could actually um, you know, give rise to uh organisms that have the capabilities that we have. </s><s>[INST] So, it's interesting because even the idea of evolution is hard for me to keep all together in my mind. So, because we think of a human time scale, it's hard to imagine that like, like the development of the human, I will give me nightmares too because you have to think across many, many, many generations and it's very tempting to think about kind of a growth of a complicated object and it's like how is it possible for that, such such a thing to be built Because also me from a robotics engineering perspective, it's very hard to build these systems, how can through an undirected process can a complex thing be designed? It seems not, it seems wrong, [/INST] Yeah, so that's absolutely right and I you know, um a slightly different career path that would have been equally interesting to me, would have would have been um to actually study the process of embry a logical development flowing on into brain development and the the um exquisite sort of laying down of pathways and so on that occurs in the brain and uh I know the slightest bit about that, it's not my field but um there are you know, fascinating aspects to this process that eventually result in the, you know, the complexity of of uh various brains at least, you know, one thing we're um in in the field I think people have felt for a long time and it's in the study of vision, the continuity between humans and nonhuman animals has been has been second nature for a lot longer. I was having, I had this conversation um with somebody who's a vision scientist and you're saying no we don't have any problem with this, you know, the monkeys, visual system in the human visual system extremely similar um up to certain levels of course they diverge after a while. But the first, the visual pathway from the eye to the brain and the first few, um, layers of the cortex or cortical areas, I guess one would say are are extremely similar. </s><s>[INST] Yeah, so, and the cognition side is where the leap seems to happen with humans, that it does seem, what kind of special. And that's a really interesting question when thinking about alien life or if there is other intelligent alien civilizations out there is, how special is this leap? So one special things used to be the origin of life itself. However, you define that there's a gray area and the other leap, This is very biased perspective of a human is the, the origin of intelligence. And again, from an engineering perspective, it's a difficult question to ask. An important one. Is how difficult does that leave? How special we're humans did. Uh, a monolith come down to the aliens bring down a monolith? And some apes had to touch a monolith, but to get a lot like dark [/INST] day cards, uh, you know, </s><s>[INST] idea right? Exactly. It's, but it just seems that it seems one heck of a leap to get to this level of intelligence. Yeah, [/INST] and you know, so chomsky, um, argued uh, that, you know, some uh, genetic fluke occurred 100,000 years ago, and you know just happened that some human, some humming in predecessor of current humans had this one genetic tweak that resulted in language and language then provided this special thing that separates us from all other animals. Um I'm I think there's a lot of truth to the value and importance of language, but I think it comes along with um the evolution of a lot of other related things related to sociology and mutual engagement with others and um establishment of, I don't know, rich mechanisms for organizing an understanding of the world which language then plugs into. </s>
<s>[INST] meaningful and that latter thing I gotta say you do masterfully, You're one of the great communicators and educators out there today and it's a huge honor that you will sit with me for so many hours. This is awesome. Thanks for listening to this conversation with Richard Wolf. [/INST] To </s><s>[INST] support this podcast, please check out our sponsors in the [/INST] description </s><s>[INST] and now let me leave you with some words from Karl Marx. The philosophers have only interpreted the world in various ways. The point however, is to change it. Thank you for listening and hope to see you [/INST] next time mm </s>
<s>[INST] The following is a conversation with Jordan Peterson, an influential psychologist lecturer, podcast host and author of maps of meaning, 12 rules for life and beyond order [/INST] and </s><s>[INST] now a quick few second mention of each sponsor. Check them out in the description is the best way to support this podcast. We've got weights and biases for machine learning notion for startups, Inside Tracker for longevity, eight sleep for napping and blankets for nonfiction, choose wisely my friends and now on to the full ad reads. I never do ads in the middle because those are annoying. I hate those. They distract they interrupt the conversation. A lot of my favorite podcasts do them. It's fine, I understand it. But even if I lose a lot of money because of it, I get to control which ads go aware. So let's just do them in the beginning. Now if you skip these ads it's [/INST] okay. I </s><s>[INST] hope you don't. But if you must please still check out the sponsors, I enjoy their stuff. Maybe you will too. And if you want to support this podcast, one of the best ways, probably the best ways by supporting the sponsors this show is brought to you by weights and biases. The company helping machine learning teams build better models faster. They do basically everything that means debug models, compare, reproduce models, play around with different architectures and hyper parameters. All of this while collaborating with a teammate and multiple teammates on it. Just honored and really excited. They would be supporting this podcast because I'm a huge supporter of theirs and please if you care about machine learning, if you just want to support the community go support these guys, they're good for the community. They have tools that are free for personal use and their teams features available for free to academic researchers, companies like open AI and video, i robot and many more used weights and biases tools every day to build their models, weights and biases give you a better way to stay organized and to be more productive, join over 200,000 machine learning engineers and data scientists when you sign up at lex Friedman dot com slash W N. B. This show is also brought to you by notion a note taking and team collaboration tool. They combine note taking, document sharing, wikis, project management and much more all in one place that's simple, powerful and beautifully designed. All the legit people I ask people that care a lot about productivity and sort of organization and note taking. They all go to notion notion is like what all the cool kids are using. Of course there's different levels of cool, like if you ask the cool kids what programming language to use, I think you're gonna get a lot of answers but the people that answer c is still cool. They're just cool in a very different kind of way. But notion also wants me to let you know that it's bigger than just individual organization is great for teams for startups. They basically provide a full on operating system for running every aspect of your company as well. It's running a special offer for startups. You can get up to $1,000 off of the team plan which is almost one year free for a team of 10. Go to notion.com slash startups. This show is also brought to you by Inside Tracker, a service. I used to track biological data. They have a bunch of plans. Most include a blood test that gives you information to make decisions about your health. And then they use machine learning algorithms to take the blood data, the D. N. A. Data, the fitness tracker data to provide you with a prediction with a clear picture of what's going on inside you and what you should do about it. It's obvious that this is the future of medicine, of health advice of nutrition science, all that kind of stuff. It should be personalized, data driven machine learning. The doctor shouldn't be making predictions based on the data. We should be collecting a huge amount of time series data and making predictions based on that. And Inside Tracker is at the forefront of that so you shouldn't just support them. You should also just support this very idea. I really think this approach to medicine is gonna help a lot of [/INST] people </s>
<s>[INST] Like I said, I just talked to Don Kanye and he believes that 2% of the world population have something weird with their brain that they're geeks, they understand computers are connected with computer. He put it exactly 2%. Okay, so uh [/INST] this specific guy, </s><s>[INST] very specific, he says I can't prove it but it's very empirically there uh is there something that attracts you to the idea of optimizing code? He seems like that's one of the biggest coolest things about, you [/INST] know, that's one of the major things it does. So, um I got into that because of a person actually. So when I was in my undergraduate, I had an advisor or a professor named steve Video and he, I went to this little tiny private school, there were Like seven or 9 people in my computer science department, students in my class. So it's a very tiny uh very, very small school. It was kind of a wart on the side of the math department, kind of a thing at the time, I think it's evolved a lot in the many years since then, but um but steve Bechtel was a compiler guy and he was super passionate and he, his passion rubbed off on me. And one of the things I like about compilers is that there are large complicated software pieces. And so one of the culminating classes, that many computer science departments at least at the time did was to say that you take algorithms and data structures and all these core classes. But then the compilers class was one of the last classes you take because it it pulls everything together and then you work on one piece of code over the entire semester. And um and so you keep building on your own work, which is really interesting. It's also very challenging because in many classes, if you don't get a project done, you just forget about and move on to the next one and get your, you know, your B or whatever it is, but here you have to live with the decisions you make and continue to reinvest in it. And I really like that. And uh, and so I did an extra study project with him the following semester and he was just really great and he was also a great mentor in a lot of ways. And so from from him and from his advice, he encouraged me to go to graduate school. I wasn't super excited about going to grad school, I wanted the Master's degree, but I didn't want to be an academic and um, but like I said, I kind of got tricked him to sing and was having a lot of fun and I definitely do not regret it. </s><s>[INST] Well, the aspects of compilers were the things you connected with. So L V M, there's also the other part, this is really interesting if you're interested in languages is parsing and just analyzing like, yeah, analyzing the language, breaking down parsing and so on. Was that interesting to you, where you more interested in optimization? For [/INST] me, it was more so I'm not really a math person. I could do Math. I understand some bits of it when I get into it. Um, but math is never the thing that attracted me. And so a lot of the parts are part of the compiler has a lot of good formal theories that Dawn, for example, knows quite well, still waiting for his book on that. But, um, but the, uh, but I just like building a thing and and seeing what it could do and exploring and getting to do more things and then setting new goals and reaching for them. And, um, and with in the case of in the case of L V M, when I started working on that, my research advisor that I was working for was a compiler guy. And so I suppose he and I specifically found each other because we're both interested in compilers. And so I started working with them and taking his class and a lot of L V M initially was it's fun implementing all the standard algorithms and all the, all the things that people have been talking about and were well known. And they were in the curricula for advanced studies and compilers. And so just being able to build that was really fun. And I was learning a lot by instead of reading about it, just building. And so I enjoyed that. </s><s>[INST] So you said the compilers of these complicated systems, can you even just with language tried to describe, you know, how you turn a C plus plus program? Yes. Into code. Like what are the hard parts? Why is it [/INST] so hard? So, I'll give you examples of the hard parts along the way. So, C plus plus is a very complicated programming, which is something like 1400 pages in the spec So C plus plus by itself is crazy complicated. </s><s>[INST] Can we just pause? What makes the language complicated in terms of what's sin tactically like? [/INST] Uh, so it's what they call syntax. So the actual how the characters arranged. Yes, it's also semantics, how it behaves. Um it's also in the case of C plus Plus, there's a huge amount of history people supposed to build on top of C. You play that forward and then a bunch of suboptimal in some cases, decisions were made and they compound and then more and more and more things keep getting added to C plus Plus and it will probably never stop. But the language is very complicated from that perspective. And so the interactions between subsystems is very complicated. There's just a lot there. And when you talk about the front end, one of the major challenges which clang as a project, the C, C plus plus compiler that I built and many people built well, the challenges we took on was we looked at gcc gcc at the time was like a really good industry standardized compiler that had really consolidated a lot of the other compilers in the world and was a standard, but it wasn't really great for research. Um, the design was very difficult to work with and it was full of global variables and other other things that made it very difficult to reuse in ways that it wasn't originally designed for. And so with playing one of the things that we want to do is push forward on better user interface, so make their messages that are just better than gcc s and that that's actually hard because you have to do a lot of bookkeeping in an efficient way to be able to do that. We want to make compile time better and so compile time is about making it efficient, which is also really hard when you're keeping track of extra information we wanted to make new tools available. So re factoring tools and other analysis tools that the gcc never supported, also leveraging the extra information we kept. Um but enabling those new classes of tools that then get built into I D s and so that's been one of the, one of the areas that clang has really helped push the world forward in is in the tooling for C and C plus plus and things like that, but C plus plus and the front end pieces complicated. And you have to build syntax trees and you have to check every rule in the spec and you have to turn that back into an error message to the human. Human that the human can understand when they do something wrong, but then you start doing the what's called lowering. So going from C plus plus in the way that it represents code down to the machine and when you do that there's many different phases you go through. often there are, I think Alabama is something like 150 different what are called passes in the compiler that the code passes through and these get organized in very complicated ways which affect the generated code in the performance and compile time and many of the things. What are they </s>
<s>[INST] Yeah, those, all those figures are just fascinating. All the people have passed through M. I. T. Is really fascinating. Is there a let me ask you to put on your big wise man hat, is there advice that you can give to young people today, whether in high school or college who are thinking about their career, who are thinking about life, how to live uh, a life they're proud of a successful life. [/INST] Yeah, so many people ask me for advice and have asked and I get, I talked to a lot of people all the time And there is no one way um you know there's a lot of pressure to produce papers um that would be acceptable and be published. Uh maybe I was, maybe I come from an age where I would, I could be a rebel against that and and still succeed. Maybe it's harder today. But I think it's important not to get too caught up with what everyone else is doing and if you if it depends on what you want to life, if you want to have real impact, you have to be ready to fail a lot of times. So you have to make a lot of unsafe decisions. And the only way to make that work is to keep doing it for a long time and then one of them will be work out and so that that will make something successful or not. Yeah you made or you just made you know end up you know not having a, having a lousy career. I mean it's certainly part taking the risk because the thing. So, but but there's no way to to uh make all safe decisions and actually really contribute. </s><s>[INST] Do you ah think about your death by your mortality. [/INST] I gotta say when Covid hit, I did because you know in the early days we didn't know how bad it was gonna be. And I that made me work on my book harder for a while. But then I started this company and now I'm doing full time with more than full time of the companies of the books on hold, but I do want to finish this book when you think about it, are you afraid of it? I'm afraid of dribbling. Uh you know, I'm losing </s><s>[INST] the details of Okay. Yeah, yeah, but the fact that the right ends, [/INST] I've known that for a long time. Um So it's </s><s>[INST] yeah, but there's knowing and knowing. It's such a [/INST] Yeah, it really </s><s>[INST] sucks. It feels it [/INST] feels a lot closer. So my in in my my blog with my predictions, my sort of push back against that was because I said I'm going to review these every year for 32 years and that puts me into my Mid 90s. So, you know, that </s><s>[INST] the whole every every time you write the blog posts, you're getting closer and closer to your own prediction, that's true of your death, what do you hope your legacy is you're one of the greatest roboticist ai researchers of all time. [/INST] Um What I hope is that I actually finished writing this book and that Who's there was one person who reads it and see something about changing the way they're thinking and that leads to the next big </s><s>[INST] And then they'll be on a podcast 100 years from now saying, I once read that book that changed everything. Mhm. What do you think is the meaning of life, This whole thing, the existence, the all the hurried things we do on this planet. He thinks the meaning of it all. [/INST] Well, you know, I think we're all really bad at it. Life </s><s>[INST] for finding meaning or both. Yeah, [/INST] we get caught up in, in, in the it's easier to get easier to do the stuff that's immediate and not through the stuff, it's not immediate. So the big picture were bad. Do </s><s>[INST] you have a sense of what that big picture is? Like, why you ever look up to the stars and ask why the hell are we here? [/INST] You know, my my my my atheism tells me it's just random, but you know, I want to understand the way random in the and that's what I talk about in this book, how order comes from disorder. Um </s><s>[INST] but they kind of sprung up like most of the whole thing is random, but this little pocket of complexity that we call earth that [/INST] like why the hell does that happen? And what we don't know is how common that put those pockets of complexity are, or how often because they may not last forever, </s><s>[INST] which is uh more exciting slash sad to you if we're alone or if there is infinite number of, [/INST] I think I think it's impossible for me to believe that we're alone. Um That was just too horrible. Too cruel. It </s><s>[INST] could be like the sad thing, it could be like a graveyard of intelligent civilizations. [/INST] Oh everywhere. Yeah, that might be the most likely outcome. </s><s>[INST] And for us [/INST] to Yeah, exactly. Yeah. And all </s><s>[INST] of this will be forgotten. Yeah. Including all the robots you build everything forgotten. [/INST] Well on average everyone has been forgotten in history, right? Most people are not remembered beyond the generation or two. Um </s><s>[INST] I mean Yeah, well not just on average basically Very close to 100% of people who have ever lived or forgotten. [/INST] Yeah, I mean no long arc if I don't know anyone alive who remembers my great grandparents because we didn't meet them. So </s>
<s>[INST] and which reminds me there's also another signal where users can say, I don't know if it was recently added, but I really enjoy it. Just saying I don't, I didn't something like I I don't want to see this video anymore or something like, like this is uh like there's certain videos to just cut me the wrong way. Like just just jump out at me is like I don't want to I don't want this and it feels really good to clean that up to be like I don't that's not that's not for me. I don't know. I think that might have been recently added, but that's also a really strong signal. [/INST] Yes, absolutely. Right. We don't want to make a recommendation that uh, people are unhappy with </s><s>[INST] and that makes me that particular one makes me feel good as a user in general and as a machine learning person because I feel like I'm helping the algorithm, my interaction on Youtube don't always feel like I'm helping the algorithm. Like I'm not reminded of that fact. Like for example, uh Tesla on autopilot and you know, I must create a feeling for their customers with people that own test is that they're helping the algorithm of testing. Like they're all like are really proud, they're helping complete learn. I think Youtube doesn't always remind people that you're helping the algorithm gets smarter. And for me, I love that idea. Like we're all collaboratively, like Wikipedia gives that sense. They're all together creating a beautiful thing. Youtubers uh doesn't always remind me of that, that's uh this conversation is reminding me of that but uh well that's a good tip. [/INST] We should keep that fact in mind when we designed these features. I'm not sure. I I really thought about it that way but that's a very interesting perspective. </s><s>[INST] It's an interesting question of personalization that I feel like when I click like on a video I'm just improving my experience, it would be great. It would make me personally, people are different but make me feel great if I was helping also the Youtube algorithm broadly say something, you know what I'm saying? Like there's a that I don't know if that's human nature, but you want the products you love and I certainly love Youtube like you want to help you get smarter smarter smarter because there's some kind of coupling between our lives together. Being better if youtube is better than my life will be better and that's that kind of reasoning, I'm not sure what that is and I'm not sure how many people share that feeling. It could be just a machine learning feeling but at that point how much personalization is there in terms of next video recommendations. So is it kind of all really boiling down to clustering like you find in years clusters to me and so on and that kind of thing or how much is personalized to meet the individual completely? [/INST] It's very, very personalized. So um your experience will be quite a bit different from anybody else's who's watching that same video at least when they're logged in. And um the reason is is that we we found that that users often want to different kinds of things when they're watching a video, sometimes they want to keep watching more on that topic or more in that genre. And other times they just are done and they're ready to move on to something else. And so the question is, well, what is this something else? And one of the first things one can imagine is, well maybe something else is um the latest video from some channel to which you've subscribed and that's going to be very different from for you than it is for me. Right. And and even if it's not something that you subscribe to, it's something that you watch a lot. And again, that will be very different on a person by person basis. And so um even the watch next as well as the home page of course is quite personalized. </s><s>[INST] So what we mentioned, some of the signals, but what does success look like? What does success look like in terms of the algorithm creating a great long term experience for a user or put another way, if you look at the videos I've watched this month, how do you know the algorithm succeeded for me? [/INST] I think first of all, if you come back and watch more youtube, then that's one indication that you found some value from </s><s>[INST] it. So just the number of hours is a powerful indicator. [/INST] Well, I mean, not the hours themselves, but um, uh, the fact that you return on another day, um, so that's probably the most simple indicator. People don't come back to things that they don't find value in, right? There's a lot of other things that they could do. Um, but like I said, I mean ideally we would like everybody to feel that Youtube enriches their lives and that every video they watched is the best one they've ever watched since they've started watching Youtube. And so that's why uh, we surveyed them and asked them like is this 1 - five stars. And so our version of Success is uh, every time someone takes that survey, they say it's five stars. And if we asked them, is this the best video you've ever seen on Youtube? They say yes every single time. So, um, it's hard to imagine that we would actually achieve that maybe ask them. Typically we would get there. But, but that would be what we think successes. </s>
<s>[INST] those, those kind of simulations incorporate all the betting strategies and everything else like that. So they, so as opposed to some kind of very crude mathematical model of what's the probability you went just based on the quality of the card, it's including everything else to the game theory of it. [/INST] Yes, yeah, essentially. And what's interesting is that nowadays, if you want to be a top pro and you go and play in these really like the super high stakes tournaments or tough cash games, if you don't know this stuff, you're gonna get eaten alive in the long run, but of course you could get lucky over the short run and that's where this like luck factor comes in because luck is both a blessing and a curse. If luck didn't, you know if there wasn't this random element and there wasn't the ability for worse players to win sometimes then poker would fall apart. You know the same reason people don't play chess professionally for money against you don't see people going in hustling chess, like not knowing, trying to make a living from it because you know, there's very little luck in chess, but there's quite a lot of luck in poker. </s><s>[INST] Have you seen a beautiful mind that movie [/INST] years ago? </s><s>[INST] Well what do you think about the game theoretic formulation of what is it the hot blonde at the bar? Do you remember? [/INST] Like the way </s><s>[INST] they illustrated it is they're trying to pick up a girl at a bar and there's multiple girls, they're like friends, it's like a friend group and you're trying to approach. I don't remember the details, but I remember, [/INST] don't you like then speak to her friends? </s><s>[INST] Yeah. That [/INST] feigned disinterest classic pickup artist, you know, </s><s>[INST] and they were trying to correlate that somehow that being an optimal strategy game theoretically. Why what what like I don't think, I remember, I [/INST] imagine that there. I mean there's probably an optimal strategy, is it, does that mean that there's an actual nash equilibrium of like picking up girls, do </s><s>[INST] you know the the marriage problem? It's optimal, stopping. [/INST] Yes. </s><s>[INST] So where it's an optimal dating strategy where you, do you remember? [/INST] Yeah, I think it's like something like you, you you know, you've got like a set of 100 people you're going to look through and after, how many do you now after that, after going on this many dates out of 100? At what point do you then go, okay, the next best person I see, is that the right one? And I think it's like something like 37% </s><s>[INST] want e whatever that is [/INST] right? Which I think is, </s><s>[INST] yeah, we're gonna fact check [/INST] that. </s><s>[INST] Um Yeah, so but it's funny under those strict constraints then yes, after that many people, as long as you have a fixed size pool, then you just pick the next person that is better than anyone [/INST] you've seen before. </s><s>[INST] Um Have [/INST] you, have you tried this, have you incorporated in </s><s>[INST] one of those people? Were, and we're going to discuss this. I and what do you mean? Those people, I try not to optimize stuff, I tried to listen to the heart, I don't think I, like, my mind immediately is attracted to optimizing everything. And I think that if if you really give into that kind of addiction that you lose the joy of the small things, the minutia of life, I think. I don't know. So I'm concerned about the addictive nature of my personality in that regard? [/INST] In some ways while I think on average people under try and quantify things or try under optimize. Um there are some people who, you know, it's like with all these things it's a, you know, it's a balancing act, </s><s>[INST] I've been on dating house but I've never used them. I'm sure they have data on this because they probably have the optimal stopping control problem because there aren't a lot of people that use social like dating apps are on there for a long time. So the the interesting, the interesting aspect is like, alright, how long before you stop looking before it actually starts affecting your mind negatively such that you see dating as a kind of um [/INST] game, </s><s>[INST] a kind of game versus an actual uh process of finding somebody that's going to make you happy for the rest of your life. That's really interesting. Uh They have the data, I wish they would be able to release that data and I do want to [/INST] take you right? I think they ran a huge, huge study and all of their </s><s>[INST] Yeah, they're more data driven, I think Ok, Cupid folks are, I think there's a lot of opportunity for dating apps and you know, even bigger than dating apps. People connecting on the internet. I just hope they're more data driven and it doesn't seem that way. I think like I've always, I always thought that good reads should be a dating app, like [/INST] good </s><s>[INST] reads, good reasons just list, like books that you've read and comment on the books you read and what books you're currently reading. But the giant social networks of people reading books and that seems to be a much better database of like interest of course to constrain you to the books you're reading. But like that really reveals so much more about the person allows you to discover shared interests because books are kind of window into the way you see the world. Also like the kind of places people you're curious about the kind of ideas you're curious about. Are you a romantic, are you called calculating rationalists? Are you, are you into iron rand? Are you into Bernie Sanders? Are you into whatever? And I feel like that reveals so much more than like a person trying to look hot from a certain angle and a Tinder profile. [/INST] It would also be a really great filter in the first place for people selected people who read books and are willing to go and rape them and give feedback on them and so on. So that's already a really strong filter. Probably the type of people you'd be looking for. </s>
<s>[INST] and they just have, I mean the best of enterprise probably just has a very large dataset or deep learning can probably shine. [/INST] That's correct. That's right. And then they, I think the other pieces that they weren't again with two point or the developer summit we put together is the whole tensorflow extended piece, which is the entire pipeline. They care about stability across doing their entire thing. They want simplicity across the entire thing. I don't need to just train a model, I need to do that every day again over and over again. </s><s>[INST] I wonder to which degree you have a role in. Uh, I don't know. So I teach a course on deep learning, I have people like lawyers come up to me and say, you know, say one is machine learning going to enter legal legal realm the same thing and um, all kinds of disciplines, uh immigration insurance. Often when I see what it boils down to is these companies are often a little bit old school and the way they organized the day. So the data is just not ready yet. It's not digitized. Do you also find yourself being in the role of and an evangelist for like uh let's get organized your data folks and then you'll get the big benefit of tensorflow. Aw, do you get those? Have those conversations? [/INST] So yeah, you know, I get all kinds of questions there from, Okay, what can I, what do I need to make this work right to really need deep learning. I mean they're all these things. I already use this linear model. Why would this help? I don't have enough data or let's say, you know, or I want to use machine learning to have nuclear where to start. So it really starts to all the way to the experts who wise for very specific things. It's interesting </s><s>[INST] is there a good answer. It boils down to. Oftentimes digitizing data. So whatever you want, automated, whatever day you want to make predictions based on, you have to make sure that it's in an organized form you like with within intensive for ecosystem, there's now you're providing more and more data sets and more and more pretrained models. Are you finding yourself also the organizer of datasets? [/INST] Yes, I think the tensorflow datasets that we just released that's definitely come up where people want these datasets. Can we organize them and can we make that easier? So that's, that's definitely one important thing. The other related thing I would say is I often tell people, you know what, I don't think of the most fanciest thing that the newest model that you see make something very basic work and then you can improve it. There's just lots of things you can do with their </s><s>[INST] Yeah, I started with the basic truth. One of the big things that makes it makes sense of flow even more accessible was the appearance whenever that happened of caress the care is standard sort of outside of tensorflow. I think it was carrots on top of piano at first only and then uh paris became on top of tensorflow. Do you know when uh paris chose to also add tensorflow as a back end. Who was the, was it just the community that drove that initially? Do you know if there was discussions, [/INST] conversations? Yeah. So Francis started the campus project before he was at google and the first thing with piano. I don't remember if that was Africans flows created away before and then at some point in tensorflow started becoming popular, there were enough similarities that you decided to okay create this interface and and pretends flows back in um, I believe that might still have been before he joined google. So I, you know, we weren't really talking about that. He decided on his own and I thought that was interesting and relevant to the community. In fact, I didn't find out about him being a google until a few months after he was here. He was working on some research ideas and doing caress and his nights and weekends project and </s><s>[INST] so interesting. So he wasn't like part of the tensorflow, he didn't join, she [/INST] joined research and he was doing some amazing research, has some papers on the iron research he's done, he's a great researcher as well. And at some point we realized, oh he's he's doing this good stuff. People seem to like the FBI and he's right here. So we talked to him and he said, okay, why don't I come over to your team and work with you for a quarter and let's make that integration happen. And we talked to his manager and he said sure, my quarters fine. And that quarter has been something like two years now and so he's fully on this. </s><s>[INST] So chara's got integrated into tensorflow like in a deep way And now with 2.0 Tensorflow 2.0, sort of caress is kind of the recommended way for a beginner to interact with which makes that initial sort of transfer learning or the basic use cases even for enterprise? Uh Super simple. Right? So what what was that decision like? That seems like uh uh it's kind of a bold decision uh as well, we [/INST] did spend a lot of time thinking about that one, we had a bunch of api somebody by us, uh there was a parallel layers api that we were building and when we decided to do keras in parallel, so they were like okay, two things that we're looking at, and the first thing we was trying to do is just have them look similar, like being as integrated as possible, share all of that stuff. They were also like three other mps that others had built over time because we didn't have a standard one. Um but one of the messages that we keep kept hearing from the community, okay, which one do we use? And they kept saying like, okay, here's a model in this one and here's a model in this one which is like pick. Um so that that's sort of like, okay, we had to address that straight on with two point. Oh, the whole idea is you need to simplify, you had to pick one based on where the where you're like, okay let's see what what are, what are the people like and carries was clearly one that lots of people loved, there were lots of great things about it. Uh so pretty settled on night, </s>
<s>[INST] And it took a really long time. It [/INST] took two billion </s><s>[INST] years and it [/INST] hasn't happened since to the best of our knowledge. So it looks as if it's genuinely difficult and if you think about it then from from from just an informational perspective you think bacteria have got they structure their information differently. So a bacterial cell has a small genome, you might have 4000 genes in it. But a single e coli cell has access to about 30,000 genes potentially it's got a kind of meta genome where other E coli out there have got different gene sets and they can switch them around between themselves and so you can generate a huge amount of variation. And you know they've got more of an e coli meta genome is larger than the human genome. We have 20,000 genes or something. So and they've had four billion years of evolution to work out what can I do and what can't I do with this meta genome? And the answer is you're stuck, you're still bacteria. So they have explored genetic sequence space far more thoroughly than new characters ever did because they've had twice as long at least. And they've they've they've got much larger populations and they never they never got around this problem. So why can't they? It seems as if you can't solve it with information alone. So what's the what's what's the problem? The problem is structure if if if sells if the very first cells needed an electrical charge on their membrane to grow and in bacteria it's this it's the outer membrane that surrounds the cell which is electrically charged, you try and scale that up and you've got a fundamental design problem. Not an engineering problem. And there are examples of it and what we see in all these cases is what's known as extreme polyp Lloyd which is to say they have tens of thousands of copies of their complete genome which is energetically hugely expensive. And you end up with a large bacteria with no further development. What you need is to incorporate these electrically charged power packed units inside with their control units intact and for them not to conflict so much with the host cell that it all goes wrong. Perhaps it goes wrong more often than not. And then you change the topology of the cell. Now you don't necessarily have any more DNA than a giant bacterium with extreme polyp Lloyd. But what you've got is an asymmetry, you now have a giant nuclear genome. We're surrounded by lots of subsidiary energetic genomes that do do all the the the control units that are doing all the all the all the all the all the control of energy generation. </s><s>[INST] Could this have been done gradually or does it have to be done? The power pack has to be all intact and ready to go. And [/INST] I mean it's a kind of step change in the possibilities of evolution. But it doesn't happen overnight. It's going to still require multiple multiple generations. So it could take you know it could take millions of years. It could take shorter times. There's another thing I would like to put the number of steps and try and work out what's required at each step. And we we are trying to do that with sex for example. You can't have a very large genome unless you have sex at that point. So what are the changes to go from bacterial recombination to eukaryotic recombination? What what do you need to do? Why do we go from passing around bits of D. N. A. As if it's loose change to fusing cells together, lining up the chromosomes, recombining across the chromosomes and then going through two rounds of cell division to produce your your gametes, all your carrots do it that way. So again, you know why switch what are the drivers here? So there's a lot of there's a lot of times a lot of evolution. But as soon as you've got cells living inside another cell, what you've got is a new design. You've got new potential that you didn't have before. </s><s>[INST] So the cell living inside another cell that design allows for better storage of information, better use of energy, more delegation. Like a hierarchical control of the whole thing. And then and then somehow that leads to ability to have multi cell organisms. [/INST] I'm not sure that you have hierarchical control necessarily. But you you've got a system where you can you can have a much larger information storage depot in the nucleus. You can have a much larger genome and that allows multicellular charity. Yes because it allows you </s><s>[INST] it's [/INST] A it's a funny thing you to have to have an animal where I have you know 70% of my genes switched on in my brain and a different 50% switched on in my liver or something? You've got to have all those genes in the egg cell at the very beginning? And you've got to have a program of development which says, okay you guys switch off those genes and switch on those genes and you guys you do that. But all the genes are there at the beginning. That means you got to have a lot of genes in one cell and you've got to be able to maintain them. And the problem with bacteria is they don't get close to having enough jeans in one cell. So they would, if you were to try and make multicellular organism from bacteria, you bring different types of bacteria together and hope they'll cooperate. And the reality is they don't </s><s>[INST] that's really, really tough to do coming in. We [/INST] know they don't because there doesn't exist. </s>
<s>[INST] That would be surreal to be able to interact in some way with the thing that's out there on another surface, direct connection. Um I think about artificial intelligence in that same way which is like building robots, put some mirror to us humans. It makes us like wonder about like what is intelligence, What is consciousness and what is actually valuable about human beings when when ai system learns to play chess better than humans. You start to let go of this idea that humans are special because of intelligence. It's it's something else. Um Maybe the flame of human consciousness, it's the capacity to to feel deeply to sort of to both suffer and to love all those things and that they somehow ai to me to put some mirror to that you mentioned uh hal 9000 you have to bring it up with with with the swarm bots crawling on the surface of your cocoon in space. I mean all right, let me steal man. The the hal 9000 [/INST] perspective. </s><s>[INST] The poor guy just wanted to maintain the mission and the astronauts were I mean I don't know if people often talk about that but you know um like doctors have to make difficult decisions to when there's limited resources, you actually do have to sacrifice human life often because you have to make decisions and I think how is probably making that kind of decision about what what's more important the lives of individual astronauts or the mission and I feel like a eyes on other humans will need to make these decisions and it also feels like a I systems will need to help make those decisions. I don't know. Um I guess my question is about greater and greater collective intelligence by systems. Um do you worry about that? What is the right way to sort of solve this problem keeping a human in the loop? Do you think about this kind of stuff or are they sufficiently dumb now the robots that that's not yet on the horizon to think about? [/INST] I think it should be on the horizon. It's always good to think about these things early because we make a lot of technical design decisions at this phase working with swarm robots that it would be better to have thought about some of these questions early in the lifecycle of a project, there is a real interest in Nasa right now. Thinking about the future of human robot interaction? H. R. I. And what is the right synergy in terms of level of control for the human versus level of dependence or control for the robot. And we're beginning to test out more of these scenarios. For example the Gateway space station which is meant to be in orbit around the moon as a staging base for the surface operations is meant to be able to function autonomously with no humans in it For months at a time because I think it's going to be seasonal. They think we might not be constantly staffing it. So this would be a really great test of I don't know that anybody is yet worried about how 9000 evolving but certainly just the robustness of some of these Ai systems that might be asked to autonomously maintain the station while the humans are away um or detection algorithms that are gonna say you know if you had a human pilot they might see debris in orbit and steer around. It will be a lot of autonomous navigation that has to happen. That'll be one of the early test beds where we'll start to get a little bit closer to that future. </s><s>[INST] Well the HR I component is really interesting to me and especially when the I includes like almost friendship because people don't realize this. I think that we you know we humans long for connection and when you have even the basic interaction that's just like it's supposed to be just like serving you or something. You still project. It's still um there is still a source of Meaning and connection and so you do have to think about that. I mean how 9000 you know the movie maybe doesn't portray it that way. But I'm sure there's a relationship there between the astronauts and the and the robot. Especially when you have greater and greater level of intelligence. Maybe that addresses the the happiness question too. [/INST] I think there's a there's a great book by kate darling who's one of my colleagues. </s><s>[INST] Yeah she's amazing. We've been she's already been on this podcast but we talk all the time and we're supposed to talk and we've been missing each other and we're going to make it happen soon coming down in texas. All right. Anyway. Yeah she's amazing. And she has this book and she has her whole work is about this [/INST] connection with </s><s>[INST] this beautiful connection that we have with robots. But I think it's greater and greater importance when it's out in space because it could help alleviate some of the loneliness. [/INST] One of the projects in the book that I gave you just a catalog of the projects that we worked on over the last five years is the social robot that was developed at the media lab. And we one of the first years and 2017 that we flew a zero G. Flight. We took the social robot along and tried to do a little bit of a very scaled down human study to look at these questions because you do imagine that we would form a bond a real bond with the social robots that might be not just serving us on a mission, but really be our teammates on a future mission? And I do think that that could have a powerful role in the mental health and just the stability of a cruise to have some other robot friends come along. </s>
<s>[INST] So I can't make sense of new york in this physical reality, but yeah, I mean, but you said pain and walking into things, well you can create a pain signal and as long as it's consistent that certain things result in pain, you can start to construct a reality. There's some, maybe, maybe you disagree with this, but I think we are born almost with a desire to be convinced by our reality, like a desire to make sense of our reality. So there's an imperative, so whatever that reality is given to us, like the table hurts, fire is hot, I think we want to be deluded in a sense that we want to make a simple, like Einstein simple theory of the thing around us, we want that simplicity And so um maybe the hunger for the simplicity is the thing that could be used to construct a pretty dumb simulation that that tricks us, so maybe tricking humans doesn't require building a universe. [/INST] No, I don't, I mean, I know this is not what I work on, so I don't know how close to it we </s><s>[INST] are, [/INST] but I I agree with you. Yeah, I'm not sure that it's a morally justifiable thing to do, but it's it's is it possible in principle? Um I think it'd be very difficult, but I don't see why in principle it wouldn't be possible. And I agree with you that it's it's that we try to understand the world, we try to integrate the century inputs that we have and we try to come up with a hypothesis that explains what's going on. I think though that we have huge input from the social context that we're in, we don't do it by ourselves, we don't kind of blunder around in a in a universe by ourselves and understand the whole thing. We're told by the people around us what things are and what they do and languages coming in here and so on, so it would have to be an extremely impressive simulation to simulate all of that. </s><s>[INST] Yeah, simulate all of that, including the social construct the thing that the spread of ideas and the exchange of ideas, I don't know, and but those questions are really important to understand as we become more and more digital creatures. It seems like the next step of evolution is us becoming partially all the same mechanisms we've talked about are becoming more and more plugged in into the machine were becoming cyborgs and there's an interesting interplay between wires and biology um you know, zeros and ones and the biological systems. And I don't think you can just I don't think we'll have the luxury to see humans as this joint from the technology we've created for much longer. We are in organisms. That's um [/INST] Yeah, I mean I agree with you but we come really with this too consciousness. And is there a distinction there? Because what you're saying, the natural end point says we are indistinguishable that if you are capable of building a an ai which is sufficiently close and similar that we merge with it then then to all intents and purposes that ai is conscious as we know it. Um and I don't I don't have a strong view but I have a view. Um and I wrote about it in the epilogue to my last book because 10 years ago I wrote a chapter in in a book called life ascending about consciousness and the subtitle of life ascending was was the 10 great inventions of evolution and I couldn't possibly write a book with a subtitle like that that did not include consciousness and specifically consciousness as one of the great inventions. And it was in part because I was just curious to know more, and I read more for that chapter. I never worked on it, but I've always how can anyone not be interested in the question? Um and I was left with the feeling that A nobody knows and B. There are two main schools of thought out there with a big kind of skew in distribution. One of them says, oh, it's a property of matter is an unknown law of physics. Panpsychism, Everything is conscious, the sun is conscious, it's just a matter or a rock is conscious. It's just a matter of how much and I find that very unpersuasive. I can't say that it's wrong. It's just that I think we somehow can tell the difference between something that's living and something that's not. And then the other, the other end is it's a it's an emergent property of a very complex central nervous system. Um and I am I never quite understand what people mean by words like emergence. I mean, there are genuine examples which I think we very often tend to um use it to to plaster over ignorance </s><s>[INST] as [/INST] a biochemist. The question for me then was, okay, it's a it's a concoction of a central nervous system, a deep polarizing neuron gives rise to a feeling, to a feeling of pain or to a feeling of love or anger or whatever it may be. So, what is then a feeling in biophysical terms in the central nervous system which bit of the wiring gives rise to? I've never seen anyone answer that question in a in a way that makes sense to me </s><s>[INST] and that's an important question to answer. [/INST] I think if we want to understand consciousness that's the only question to answer. Because you know I certainly an Ai is capable of out thinking and it's only a matter of time. Maybe it's already happened in terms of just information processing and computational skill. I don't think we have any problem in designing a mind which is at least the equal of the human mind. But in terms of what we value the most as humans, which is to say our feelings, our emotions are sense of what the world is in a in a very personal way. Um That's I think means as much or more to people than their information processing. And that's where I don't think that ai necessarily will become conscious because I think it's the property of life. </s>
<s>[INST] makes no sense. The possible, I agree with you. But the possible world in which it might make sense is if the, the good guys, which is a whole another problem defining who the good guys are, but the good guys are like an order of magnitude higher competence and so they can stay ahead of the bad actors by just being very good at the defense by very good not meaning like a little bit better, but in order of magnitude better. But of course the question is in each of those individual disciplines, is that feasible? Can you, can the bad actors, even if they don't have the competence leapfrog to the place where the good guys are. Yeah, [/INST] I mean, I would agree in principle um with pertaining to this particular plan of like that, you know, with the thing I describe this deep vision thing where at least then that would maybe make sense for steps one and step two of like getting the information, but then why would you release it? The information to your literal enemies? You know, that's that makes that that that doesn't fit at all in that perspective of like trying to be ahead of them. You're literally handing them the weapon, </s><s>[INST] but there's different levels of release, right? So there's a kind of secrecy where you don't give it to anybody, but there's a release where you incrementally give it to like major labs. So it's not public release, but it's like you're giving it to you. [/INST] But </s><s>[INST] the problem there is it's going to if you go anywhere beyond like complete secrecy, it's gonna leak. [/INST] That's the thing. It's very hard to keep secrets. </s><s>[INST] And so that's still [/INST] so </s><s>[INST] you might as well release it to the public is that argument? So you either go complete secrecy or you release it to the public. So which is essentially the same thing. It's going to leak anyway. If you don't do complete secrecy, [/INST] right? Which is why you shouldn't get the information in the first place. </s><s>[INST] I mean, in that, I think, [/INST] well that's a solution, the solution is either don't get the information in the first place or be keep it incredibly, incredibly contained. </s><s>[INST] See, I think I think it really matters which discipline we're talking about. So in the case of Biology, I do think you're a very right, we shouldn't even be, it should be forbidden to even like think about that meaning don't collect don't just even collect the information but like don't do I mean gain of function research is a really iffy area. Like you start [/INST] it's all about cost benefits, right? There are some scenarios I can imagine the cost benefit of a gain of function. Research is very, very clear where you've evaluated all the potential risks factored in the probability that things can go wrong and like you know, not only known unknowns but unknown unknowns as well. Try to quantify that and then even then it's like orders of magnitude better to do that. I'm behind that argument. But the point is is that there's this like naive a. T. That's preventing people from even doing the cost benefit properly on a lot of the things because you know, I get it the science community that again, I don't want to bucket the science community but like some people within the science community just think that everyone's everyone's good and everyone just cares about getting knowledge and doing the best for the world. And unfortunately that's not the case. I wish we lived in that world but we don't. </s><s>[INST] Yeah, I mean there's a lie. Listen, I've been criticizing the science community broadly quite a bit. There's so many brilliant people that brilliance somehow hinder it sometimes because it has a bunch of blind spots and then you start to look at the history of science, how easily it's been used by dictators to any conclusion they want. And it's it's it's dark how you can use brilliant people that like playing a little game of science because it is a fun game. You know, you're building, you're going to conferences, you're building on top of each other's ideas, breakthroughs high. I think I realized how this particular molecule works and I can do this kind of experiment and everyone else is impressed. So cool. No, I think you're wrong. Let me show you why you're wrong. And that little game, everyone gets really excited and they get excited. Well I came up with a pill that solves this problem and it's gonna help a bunch of people. And I came up with a giant study that shows the exact probability is gonna help or not and you get lost in this game and you forget to realize this game just like Mullick, you can have like unintended consequences that might destroy human civilization or or divide human civilization or have dire geopolitical consequences. I mean the effects of, I mean it's just so the most destructive effects of Covid have nothing to do with the biology of the virus. It seems like um it's I mean I could just list them forever. But like one of them is the complete distrust of public institutions. Uh the other one is because of that public distrust, I feel like if a much worse pandemic came along, we as a world have not cried wolf, and when, if an actual wolf now comes, people will be like masks, fuck everything. And they they won't be, they'll distrust every single thing that any major institution is going to tell them. And because [/INST] that's the thing like that, there were certain actions made by certain health public figures where they told they very knowingly told it was a white lie. It was intended in the best possible way, such as, you know, early on, when there were, there was clearly a shortage of masks. And so they said to the public, so don't get masks, they don't, there's no evidence that they work there or they're, you know, don't get them, they don't work. In fact, it might even make it worse. You might even spread it more like that, That was the real, like, stinker. Uh Yeah, no, no, there's nothing to do. Probably are gonna make that you're gonna get sicker or you're more likely to get them to catch the virus, which is just absolute crap and they put that out there and it's pretty clear the reason why they did that was because there was actually a shortage of masks and they really needed it for health workers, which makes sense. Like, I agree. Like, you know, but the cost of lying to the public to the to the public when that then comes out. People aren't as stupid as they think they are as you know, and that's that's I think where this distrust of experts, experts has largely come from a they've lied to people over overtly. But B people have been treated like idiots. Now, that's not to say that there are a lot of stupid people who have a lot of wacky ideas around Covid and all sorts of things. But if you treat the general public like Children, they're going to see that they're going to notice that and that is going to just like absolutely decimate the trust in the public institutions that we depend upon and honestly the best thing that could happen. I wish like if like Fauci, you know, and these other like leaders who, I mean, God, I would, I can't imagine how nightmare his job has been over the last few years. Hell on earth. Like, so, you know, I I, you know, I have I have a lot of sort of sympathy for the position he's been in, but like if he could just come out and be like, okay, look guys hands up, we didn't handle this as well as we could have. These are all the things I would have done differently in hindsight, I apologize for this and this and this and that would go so far, maybe I'm being naive, who knows, maybe this would backfire, but I don't think it would like to someone like me even because I've like I've lost trust in a lot of these things. I'm unfortunately at least no people who I can go to, who I think are good, like have good epidemics on this stuff. Um, but you know, if they, if they could sort of put their hands on and okay, these are the spots where we screwed up this, this, this, um, this was our reasons. Yeah. We actually told a little white lie here. We did it for this reason. We're really sorry where they just did the radical honesty thing, the radical transparency thing that would go so far to build rebuilding public trust. And I think that's what needs to happen. I </s>
<s>[INST] But I would say I'm deeply within the scientific community and and sometimes disheartened by the elitism of the thinking, sort of not allowing yourself to think outside the box. So allowing the possibility of going against the conventions of signs, I think is is uh beautiful part of some of the greatest scientists in history. [/INST] I don't know, I'm impressed by scientists every day and uh revolutions in our knowledge of the world occur only under very special circumstances. It is very scary to challenge conventional thinking and and and risky because let's go back to elitism and ego, right? If you just say, you know what I believe in the spirits of my body and all forces are actually created by invisible creatures that transfer themselves between objects. If you ridicule every other theory and say that you're you're you're correct then ego gets involved and you just don't go anywhere. But the fundamentally the question of, well, what is a force um is incredibly important. We need to have that conversation, but it needs to be done in this very political way of like let's be respectful of everyone and let's realize that we're all learning together and not shutting out other people. And so when you look at a lot of revolutionary ideas, um they were not accepted right away and you know Galileo had a couple of problems with the authorities and later thinkers day cart was like all right, look I kind of agree with Galileo but I'm gonna have to not say that I'll have to create and invent and write different things that keep me from being in trouble. But we still slowly made progress </s><s>[INST] revolutions are difficult in all forms and certainly in science before we get to a eye on topic of revolutionary ideas. Let me ask on reddit A. M. A. You said that is the Earth Flat is one of the favorite questions you ever answered. Speaking of revolutionary ideas, so your video on that people should definitely watch is really fascinating. Can you elaborate why you enjoyed answering this question so much? [/INST] Yeah, well it's a long story. I remember A long time ago I was living in New York at the time, so it had to have been like 2009 or something. I visited the flat earth forums and this was before the flat earth theories became as sort of mainstream as they are, </s><s>[INST] started to ask the dumb question forms online forms. Yeah, [/INST] the flat earth society. I don't know if it's dot com or dot org, but I went there and I was reading, you know, their ideas and how they responded to typical criticisms of well, the Earth isn't flat because what about this? And I could not tell and I mentioned this in my video, I couldn't tell how many of these community members actually believed the earth was flat or we're just trolling. And I realized that the fascinating thing is how do we know anything and what makes for a good belief versus a maybe not so tenable or good belief. And so that's really what my video about Earth being flat is about. It's about, look, there are a lot of reasons uh the earth is probably not flat. Um but a flat Earth believer can respond to every single one of them, but it's all in an ad hoc way. And all of these, all their rebuttals aren't necessarily going to form a cohesive, non contradictory whole. And I believe that's the episode where I talk about Occam's razor and Newton's flaming laser sword. And then I say, well, you know what, wait a second, we know that space contracts as you move. And so to a particle moving near the speed of light towards earth, Earth would be flattened in the direction of that particles travel. So to them, Earth is flat, like we need to be, you know, really generous to even wild ideas because they're all thinking they're all the communication of ideas and what else can it mean to be a human? </s><s>[INST] Yeah. And I think I'm a huge fan of the flat earth theory, quote unquote in the sense that to me feels harmless to explore some of the questions of what it means to believe something, what it means to explore the edge of science and so on. It's because it's a harm. It's to me nobody gets hurt whether the earth is flat around. Not literally, but I mean intellectually when we're just having a conversation that said again to elitism, uh I find that scientists roll their eyes way too fast on the flat earth, the kind of dismissal that I see to this even notion they haven't like sat down and say what are the arguments that are being proposed and this is why these arguments are correct. So you know, that should be something that scientists should always do even to the most sort of ideas that seem ridiculous. I like this is almost it's almost my test when I ask people what they think about flat earth theories to see how quickly they roll their eyes. Uh [/INST] Well yeah, I mean let me go on record and say that the earth is not flat. It is a three dimensional spheroid. However, I don't know that and it has not been proven. Science doesn't prove anything. It just reduces uncertainty. Could the Earth actually be flat mm extremely unlikely. Extremely unlikely. And so it is a ridiculous notion if we care about how probable and certain our ideas might be. But I think it's incredibly important to talk about science in that way and to not resort to well it's true, it's true in the same way that a mathematical theorem is true. And I think we're kind of like being pretty pedantic about defining this stuff. But like sure I could take a rocket ship out and I could orbit Earth and look at it and it would look like a ball, right? But I still can't prove that I'm not living in a simulation that I'm not a brain in a vat that this isn't all an elaborate ruse created by some technologically advanced extraterrestrial civilization. So there's always some doubt and that's fine. That's exciting. </s>
<s>[INST] he also draws a line between the United States versus the rest of the world, [/INST] right? And there's one thing true about that, which is that polarization has been rising much faster in the US than in any other major country. So he's right about that. So we're talking about an article by matt Matthew against cow. Uh and a few other research is a very important article. We've got it in the, in the political dysfunction um database. </s><s>[INST] And we should say that in this study there's um like I started to say there's a lot of fascinating questions that are it's organized by whether studies indicate yes or no. Question one is does social media make people more angry or effectively polarized. Question two is the social media create echo chamber. These are fascinating really important questions. Question three is the social media amplified posts that are more emotional, inflammatory or false. Question for is the social media increase the probability of violence. Question five is the social media enable foreign governments to increase political dysfunction in the US and other democracies. Question six. The social media decreased trust seven is the social media strengthen populist movements. And then there's other sections as you mentioned. [/INST] That's right. But if you once you once you operationalize it as seven different questions. Um you know like so one is about polarization and there are measures of that the degree to which people say they hate the other side. And so in this study by by boxing against Cowan Shapiro 2021 They looked at all the measures of polarization. They could find going back to the 1970s for about 20 different countries. And they show plots you have these nice plots with red lines showing that in some countries it's going up like the United States, especially in some countries it's going down and in some countries is pretty flat. And so Mark says well you know if if polarization is going up a lot in the U. S. But not in most other countries. Well maybe facebook isn't responsible but so much depends on how you operationalize things. Are we interested in the straight line regression line going back to the 70's and if so well then he's right and what he says, but that's not the argument. The argument isn't that You know it's been rising, falling since the 70s. The argument is it's been rising and falling since 2012 or so. And for that now I just spoke with, I just I've been emailing with the authors of the study and they say there's not really enough data to do it statistically reliably because there's only a few observations after 2012. But if you look at the graphs in their study and they actually do provide, they pointed out to me, they do provide a statistical test. If you break the data at the year 2000. So actually polarization is going up Pretty widely. If you just look after 2000, which is when the Internet would be influential. Um and if you look just after 2012 you have to just do it by eye. But if you do it on their graphs by eye, you see that actually a number of countries do see a sudden sharp upturn. Not all, not all by any means, but my point is mark asserts he points to one study, points this over and over again. I have had two conversations with him. He pointed this study both times. Um He asserts that this study shows that polarization is up some places down other places? There's no association? Um but actually we have another section in the google doc where we review all the data on the decline of democracy and the high point of democracy. Of course it was rising in the nineties. But if you look around the world by some measures, it begins to drop in the late two thousands, around 22,007, 2000 and eight by others. It's in the early to mid 2010s. The point is there is a by many measures, there's a drop in the quality and the number of democracies on this planet that began in the 2010s and so yes, mark can point to one study, but if you look in the google doc, there are a lot of other studies that point the other way and especially about whether things are getting more polarized or less more polarized, not in all countries, but in a lot. </s><s>[INST] So you've provided uh the problem several proposals for solutions, do you think, Mark, do you think Ellen or whoever is at the head of twitter uh would be able to implement these changes or does there need to be a competitor social networks to step up if you were to predict the future? Now this is you giving so the financial advice to me know [/INST] that </s><s>[INST] I can [/INST] give you advice, do the opposite of whatever I've done. </s><s>[INST] Okay, excellent. But what do you think, Uh, when we talk again in 10 years, what do you think would be looking at if it's a better world? [/INST] So you have to look at each the dynamics of each change that needs to be made and you have to look at it systemically. And so the biggest change for teen mental health, I think, is to raise the age from 13 was set to 13 in Coppa in like 1990 seven or 6 or whatever that was eight, whatever it was, It was set to 13 with no enforcement. I think it needs to go to 16 or 18 with enforcement. Now there's no way that Facebook can say. Um actually, so look at Instagram the ages 13, but they don't enforce it and they're under pressure to not enforce it because if they did enforce it, then all the kids would just go to Tiktok, which they're doing anyway. But if we go back a couple of years When they, they were talking about rolling out Facebook for kids because they need to get those kids, they need to get kids under 13, there's a business imperative to hook them early and keep them. So I don't expect facebook to act on its own accord and do the right thing because exactly when you have a social dilemma, you know, like what economists call like a prisoner's dilemma? Or social dilemmas generalized to multiple people? When you have a social dilemma, each player can't opt out because they're going to lose, you have to have central regulations. I think we have to raise the age. Um The U. K. Parliament is way ahead of us. I think they're actually functional. The U. S. Congress is not functional. Um so the parliament is implementing the age appropriate design code that may put pressure on the platforms globally to change Anyway. My point is we have to have regulation to force them to be transparent and share what they're doing. There are some good bills out there. So I think that if the companies and the and the users, if we're all stuck in a social dilemma um in which the incentives to the incentives against doing the right thing are strong. We do need we do need regulation on certain matters and again it's not about content moderation, who gets to say what, but it's things like the platform accountability and transparency act, which is from Senators coons Portman and Klobuchar, this would force the platforms to just share information with what they're doing. Like we can't even study what's happening without the information. So that I think is just common sense. Um Senator Michael Bennet introduced the digital platforms, Commission Act of 2022 which would create a body tasked with actually regulating and having oversight right now. The U. S. Government doesn't have a body, I mean the FTC can do certain things, We have things about antitrust but we don't have a body that can oversee or understand these things that are transforming everything. And possibly I'm severely damaging our our political life. Um So I think there's a lot of o and then the the The state of California is actually currently considering a version of the UK is um the age appropriate design code. Which would force the companies to do some simple things like not be sending alerts notifications to Children at 10 or 11:00 at night just things like that to make make platforms just less damaging. So I think there's an essential role for regulation and I think if the U. S. Congress is too paralyzed by politics if the U. K. And the EU. And the state of California and the state a few other states if they enact legislation the platforms don't want to have different versions in different states or countries. So I think there actually is some hope even if the U. S. Congress is dysfunctional. </s>
<s>[INST] winds up leading to all the best answers. So the meaning of life is following locally, wherever the gradient descent takes you. This was an incredible conversation, officially the longest conversation I've ever done in the podcast, which means a lot to me because I get to do it with one of my heroes, John. I can't tell you how much it means to me that you would sit down with me. You're an incredible human being. I can't wait what you do next, but you've already changed the world. You're an inspiration to so many people. And again, we haven't covered like most of what I was playing to talk about. So I hope we get a chance to talk someday in the future. And I can't wait to see what you do next. [/INST] Thank you so much again for talking to me. </s><s>[INST] Thank you very much. Thanks for listening to this conversation with John Carmack. To support this podcast, please check out our sponsors in the description. And now let me leave you with some words from John Carmack himself. Focused hard work is the real key to success. Keep your eyes on the goal and just keep taking the next step towards completing it. If you aren't sure which way to do something, do it both ways and see which works better. [/INST] Thank you for listening and hope to see you next time. </s>
<s>[INST] they can flow back. So it's not just a river flowing. One way, it's maybe a smaller stream, go back and backwash. You wanna backwards. You want to incorporate that into the simulations into your understanding of those distant objects. When you're trying to make sense of the various observations and so on. That's fascinating. I gotta ask you some people think that uh many of the observations that you're describing could be described by a primordial black hole first, what is a primordial black hole? And what do you think about this [/INST] idea? So primordial black hole is a black hole which is made not through the usual pathway of making a black hole Um which is that you have a star which is more massive than, you know, 1.4 or so solar masses. And basically when it runs out of fuel, runs out of its nuclear fusion fuel, it can't hold itself up anymore. And just the whole thing collapses on itself, right? And you create a uh I mean, one, I guess a simple way to think about it is you create an object with zero radius that has mass but zero radius that singularity. Um Now that's such black holes exist all over the place. And the galaxy there is in fact a really big one at the center of the galaxy. That's like the fact that that one is always looking at you when you're not looking right and it's always talking about you </s><s>[INST] and when you turn off the lights it wakes up. That's right. [/INST] Um You know, so such black holes are all over the place. We when they merge, we get to see, you know, incredible gravitational waves that they emit etcetera etcetera. One kind of plausible scenario, however, is that when the universe was forming basically during the Big Bang, you created a whole spectrum of black holes, Uh some with masses of five earth masses, some with masses of 10 earth masses. Like the entire, you know, mass spectrum sized some the massive asteroids now on the smaller end over the lifetime of the universe. The smaller ones kind of evaporate and they're not there anymore. At least this is what we what the calculations tell us, but five earth masses is big enough to not have evaporated. So one idea is that Planet nine is not a planet and instead it is a five earth mass black hole and that's why it's hard to find. Now. Um Can we ride away from our calculations say that's definitely true. That's not true. Absolutely not. We can in fact, our calculations tell you nothing other than the orbit and the mass. And that means the black hole. I mean it could be a five earth mass, you know, cup it could be a five earth mass hedgehog or a black hole or really anything that's five earth masses will do because the gravity of a black hole is no different than the gravity of a planet, right? If the sun became a black hole tomorrow, it would be dark. But the Earth would keep orbiting it. And like this notion that black holes suck everything in it. It's not that's like a sci fi </s><s>[INST] notion. It's just mass. What would be the difference between the black hole and a planet in terms of observation a league, [/INST] uh, observation early. The difference would be that you will never find the black hole. Right. The truth is, they're kind of, I'm actually not, you know, I never looked into this very carefully, but there are some constraints that you can get just statistically say, okay, if the sun has a binary companion, which is a five earth mass black hole, then that means such black holes would be extremely common. And you know, you can sort of look for lensing events and then you say, okay, maybe that's not so likely. But that said, I want to emphasize that there is a limit to what our calculations can tell you. That's the orbit and the mass. </s><s>[INST] So I think there's a bunch like Ed witten I think wishes it's a black hole because I think one exciting things about black holes in our solar system is that we can go there and we can maybe study the singularity somehow because that allows us to understand the fundamental things about physics. If uh, it's a planet for Planet Nine, we may not, you know, and we go there, we may not discover anything profoundly new. The interesting thing, perhaps you can correct me about planet Nine is like the big picture of it, the whole big story of the kuiper belt and all those kinds of things. It's not that Planet Nine would be somehow fundamentally different from um from, I don't know, Neptune in terms of, in terms of the kinds of things we can learn from it. So I think that there's kind of a hope that it's a black hole because it's an entirely new kind of object. Maybe you can uh correct me. Uh [/INST] Yeah, I mean of course here, my own biases creep in because I'm interested, you know, in planets around other stars. And I would say I would disagree that, you know, we wouldn't find things that will be truly, you know, fundamentally new because as it turns out, the galaxy is really good at making five or three earth mass objects, right. The most common type of planet that we see that we discover orbiting around other stars is a few earth masses in the solar system there's no analog for that. We go from one earth mass object, which is this one and two skipping to Neptune and uranus, which themselves are actually relatively poorly understood, especially uranus from the interior structure point of view. If Planet nine is a planet going there will give us the closest window and to understanding what other planets look like and um I will, you know, I'll say this that, you know, planets kind of in terms of their complexity on some logarithmic scale, fall somewhere between a star and an insect. Right? And the insect is way more complicated than a star, right? Just all kinds of physical processes and really biochemical processes that occur inside of an insect that just make a star look like, you know, somebody is like playing with the spring or something, right? So the I I think, you know, it would be, you know, arguably, you know, more interesting to go to um you know, to go to planet nine if it's a planet because black holes are simple, they're just kind of there basically macroscopic like particles. </s>
<s>[INST] all. There's a kind of morality, like a big statement that Wall Street bets made in terms of like the elites can't just push us around, they can't bully around, but at the same time, you know, they're also interested in making money, right? Is uh what's your sense, you said that some of the people in the Wall Street bets might have broken off and and short of the stocks, are they more interested? There was an emergent like morality that emerged and and said like, we're not gonna put up with the centralized elites, but is that going to continue, are they going to fight the power structures that are bad for society? Are they going to now? Like, I mean, are they ultimately going to introduce more chaos that's going to damage the economy and damage the world, or they're going to continue being the good guys and fighting the uh the, the evils that manipulate the market. What's your sense? [/INST] You know, it, it really feels like the Dark Knight series of films where like some people just want to see the world burn and I think there is a contingent of people who just literally want to see chaos, Like, you know, that contingent on some of these, you know, forums who just want to create chaos, right? Um so there's certainly that chaos contingent, but I think overall what the ark will show is a group of people getting massively educated, you see it in crypto as well, there was like a three year period where all of these failed entrepreneurs who I knew who couldn't build companies were then coming back to me after their companies have failed or after they gave up or couldn't clear market raising money with the venture capital community and they were doing I ceos and I was like, I met you before, right? And they're like, yeah, yeah, yeah, no, I'm doing an I C E O now, I'm like, okay, where is your company? And they're like, here's a white paper and I was like this white paper with spelling errors in it that says you're going to destroy Airbnb because everybody's apartment is going to be on an immutable ledger. Like, wouldn't that be better in a regular database that was private and not public? Like why does it need to be an immutable ledger can't change. I'm like not changing the database is a feature that does not seem like a good feature and they couldn't explain it. They were like, well, just people are interested in I C E O S and those that I C O mania. And what it showed was there was a global appetite for risk, People want to try new things. This is one of the great things about the human spirit is one of the great things about capitalism. And one of the things that concerns me most about where and society is the sort of socialism, communism, you know, entrepreneurship is bad, technology is bad and polarization of wealth and you know, people getting rich is a bad thing when I grew up, I'm 50 now, but when I was a gen xer growing up, we kind of maybe too much idolized Bill Gates and people who are doing interesting things in the world and we thought capitalism was a force for good. I still believe capitalism is a force for good because when a group of people build a product or service that changes the world and it, and it gets globally distributed, whether it's Tesla or SpaceX or google or Airbnb or Uber or Robin Hood, you know, everybody gets to benefit from that product or service having to compete. And if you look at the places where there's no competition, like public education or less, you know, you know, uh, you know, established, you know, college is something that less competition for accreditation degrees, like things tend to get a little weird, don't they? Um, and people tend to be protected and that's not good. You need, you need competition. Um, doesn't mean that, you know, people shouldn't have global health care, It doesn't mean that, you know, we shouldn't have a safety net, but we need to keep capitalism vibrant, especially because china has now co opted capitalism and created their own version of capitalism, which is communism with capitalism. It's like this weird operating system. Like we still want to keep communism so we can take any of your gains at any time, but we'd like you to be entrepreneurial and then you have somebody like, you know, um, you know, the founder of Alibaba, Jack Ma, who disappears for a couple of weeks, who's that Jack exactly who's Jack Ma's like, he kind of disappears for a couple of weeks and then he comes back and he's really sorry about the things he said and then he disappears again and like you know, we have to be very careful if china wins capitalism, this is going to be but existential threat for humanity. The chinese are no joke, I mean they are seriously focused um and they are picking the winners. </s><s>[INST] It's a very weird system because it is in fact, I don't know what you call it like communism, capitalism such overloaded terms, but they do encourage entrepreneurship but they and they do a good job of it, but then they're like, they're like the surveillance thing and they're controlling things in a way. It's weird because it seems to work really well for them uh in the short [/INST] term it's definitely a short term </s>
<s>[INST] Yeah. Well as far as I know psilocybin, so mushrooms, magic mushrooms. Uh as far as I know in terms of the studies they're running I think have no over like they're allowed to do what they're calling heroic doses. So that one does not have a toxicity. So they can do like huge doses in a clinical setting when they're doing study on cell assignment. Which is kind of fun. [/INST] Yeah it seems that most of the psychedelics work in extremely small doses. Which means that the effect on the rest of the body is relatively low and M. D. M. A. Is probably the exception. Maybe ketamine can be dangerous and larger doses because you can depress breathing and so on. But the LSD and psilocybin berg and very very small doses at least the active part of them of psilocybin analyses only the active part and the but the effect that you can have on your mental wiring can be very dangerous. I think. </s><s>[INST] Let's talk about a I a little bit What are your thoughts about gpt three and language models trained with. So supervised learning. Yeah it came out quite a bit ago but I wanted to get your thoughts on it [/INST] In the 90s. I was in New Zealand and I had an amazing professor Ian bitten who realized there was bored in class and put me in his lab and he gave me the task to discover grammatical structure in an unknown language and the unknown language that I picked was english because it was the easiest one to find Corporates for construct one. And he gave me the largest computer at the whole university. It had two gigabytes of ram, which was amazing. And I wrote everything and see with some in memory compression to do statistics over the language. And uh first would create a dictionary of all the words which basically tokenize is everything and compresses things so they don't need to store the whole word, but just a code for every word. And then I was taking this all the parts and sentences and I was trying to find all the relationships between all the words and the sentences into statistics over them. And that proved to be impossible because the complexity is just too large. So if you want to discover the relationship between the article and the noun and there are three adjectives in between, you cannot do engram statistics and look at all the possibilities that can exist at least not with the resources that we had back then. So I realized I need to make some statistics over what I need to make statistics over. So I wrote something that was pretty much a hack that did this for at least first order relationships. And I came up with some kind of mutual information graph that was indeed discovering uh something that looks exactly like the grammatical structure of the sentence just by trying to encode the sentence in such a way that the words would be written in the optimal order inside of the model. And what I also found is that if we would be able to increase the resolution of that and uh just use this model to reproduce grammatically correct sentences, we would also be able to correct stylistically correct sentences by just having more bits in these relationships. And if he wanted to have meaning we would have to go much higher order. And I didn't know how to make higher order models back then without spending more years in research on how to make the statistics over what we need to make statistics over. And this thing that we cannot look at, the relationships between all the bits in your input is being solved in different domains in different ways. So in computer graphics, the computer vision standard methods for many years now is convolutional neural networks, convolutional neural networks. Hierarchies of filters that exploit the fact that neighboring pixels and images are usually semantically related and distance pixels and images are usually not semantically related. So you can just by grouping the pixels that are next to each other hierarchically together, reconstruct the shape of objects. And this is an important prior that we built into these models so they can convert quickly. But this doesn't work on language for the reason that adjacent birds are often but not always related in distant words are sometimes related while the words in between or not. All right. So how can you learn that apology of language? And I think for for this reason that this difficulty exists that the transformer was invented in natural language processing not envision and what the transformer is doing. It's a hierarchy of layers. Every layer learns what to pay attention to in the given context in the previous layer. So what to make the statistics over </s><s>[INST] And the context is significantly larger than the adjacent ward. [/INST] Yes. So the context that the GTT three has been using the transform itself is from 2017 and it wasn't using that large of a context open Ai has basically scaled up this idea as far as I could at the time. And the context is about 2048 symbols, tokens in the language. These symbols are not characters, but they take the words and project them into a vector space where words that are statistically co occurring a lot our neighbors already. So it's already a simplification of the problem a little bit. And so every word is basically a set of coordinates in a high dimensional space. And then they use some kind of trick to also include the order of the words in a sentence or in the not just sentence, but 2,048 tokens is about a couple of pages of text or 2.5 pages of text. And so they managed to do pretty exhaustive statistics over the potential relationships between two pages of text, which is tremendous. Right? I was just using a single sentence back then and I was only looking for a first order relationships and they were really looking for much, much higher level of relationships and what they discover after they fed this with an enormous amount of training and they are pretty much the written internet or the subset of it that had some quality but substantial portion of the common troll that they are not only able to reproduce style but they are also able to reproduce some pretty detailed semantics like being able to add three digit numbers and multiply two digit numbers or to translate between programming languages and things like that. So the results that gpt three got I think were amazing </s>
<s>[INST] It's distributed computing versus centralized computing. You know, we kind of brought up religion and Joseph Campbell and myth and the propagation of ideas. And it kind of, before I forget, I wanted to ask your thoughts about this. You know, Jordan Peterson, I haven't really understood exactly, like be able to pin him down exactly what he sees as the role of religion in human society, but it feels like he's describing it as having value for us. The ideas of myth are valuable. There are valuable mechanisms toward, I think you mentioned kind of directing us in this world as a human society. Do you think about myth? Do you think about religion? What's the use of it in this construct of markets in this framework of where ideas are ultimately [/INST] the fundamental thing that makes societies work? Yeah, I think Jordan Peterson, who I'm a huge fan of, he's been very influential on my thinking and influential on my own religious views as well. I think his position would be, and he said this before, that he acts as if God exists. And I've had some arguments about this before, but to me that points towards the preeminence of action and how important action is versus your cognitive beliefs necessarily. And I think there is a lot of utility in that, that if you follow the moral code of something like the Bible, you do reap benefits from that, society reaps benefits from that. And this is not, and sometimes I bring up this point and people are like, oh my God, are you kidding me? Have you read the Old Testament? They're clobbering people with rocks when they do the wrong thing. The Bible doesn't claim to be this, do everything that was done in the Bible. It's more like charting this moral progression where we came from this very barbaric society into something more like the New Testament where we're honoring individual sovereignty above the state and things like that. So I think that mythology itself is another form of data compression. If you look at these stories, Cain enables a good example, or Peterson makes the point that it's a tiny story. It's a paragraph-ish long, but it contains so many layers of meaning in regards to violence, evil, betrayal, work, the divergence between intention and result, because I think Cain is actually making, he's making the effort to sacrifice for God, but the sacrifices he's making are not, God doesn't find them useful, right? And so he sort of rejects them. Again, we're organized by these useful fictions, right? These Hararian imagined orders. I think mythology is kind of the original version of that, where we were learning to organize ourselves around stories to best coordinate our action across space and time. And so I think it's very foundational. And back to what we were saying in the beginning that if value truly is fundamental, I think it's interesting that all these stories point towards often common moral values. They're not perfectly aligned, but it does speak to just the evolutionary importance of morality and the subjectivity of morality, where morality sort of evolves over time based on, frankly, the capital stock we've accumulated. The more capital stock we've accumulated, the easier life is, the less barbaric we have to be. Whereas if we're living in conditions of true scarcity, then we tend to be a bit more barbaric towards one another. And that too, to dovetail this into something largely unrelated, but I think is really important, is inflation. Inflation, by artificially increasing the prices of goods and services in the world, we're injecting more dollars chasing the same level of goods and services, we are artificially increasing scarcity. Perceived scarcity, right? And when you increase perceived scarcity, you are amplifying divisiveness. This natural, the natural state of man is when everything is scarce and you really have to fight hard just to eat or drink water that day. So it's decivilizing in a way by artificially amplifying the perceived scarcity </s><s>[INST] in the world. Can you elaborate how does inflation increase [/INST] the perceived scarcity in the world? So we can think the price itself is an indication, it's a data packet, if you will. The price is a data packet on supply and demand, right? It's telling you how much supply there is of something in the world relative to the demand. So when you print money and artificially increase that price, it's diverging away from supply and demand. It's becoming just more of a product of policy than it is of free market fundamentals. The more expensive something is, that is a signal to the marketplace and to market actors that it is scarce, right? That's why Leonardo painting might sell for $16 million. There's only one, there's a lot of demand for it. Maybe my numbers are off, but you get the point. It's the reason mask spiked in price after the COVID announcement, right? There was not a lot of supply, toilet paper, et cetera, et cetera. So inflation is not a lot of supply. And by inflation, I specifically mean arbitrary fiat currency supply inflation by legal monopoly. Not, inflation's a commonly misunderstood word. That is amplifying the perception of scarcity among market actors in the world. And I would argue that it actually amplifies divisiveness. I think this is the key maybe to looking at the connection between the monopolization of money and things like cancel culture, because it's increasing the, it's increasing our natural predilection to be combative with one another because we think there's more scarcity in the world than there actually is. Versus in a world where you're not increasing the money supply, prices are declining every year. As prices decline, this is a signal to market actors in the market that scarcity is declining. There's less need to fight over things. And all of this ties back into the old bastion saying that if goods don't cross borders, soldiers will. So if we're not trading with one another, if we're not acting interdependently and we're not becoming more intelligent as a market, and that that increased intelligence or increased knowledge is reflected in decreased prices. Because prices are just the exchange ratios of things. So the smarter we can solve problems, the better we can solve problems, the less prices would be. </s>
<s>[INST] the following is a conversation with Kevin Systrom co founder and longtime ceo of instagram including for six years after facebook's acquisition of instagram if you want to support this podcast, the best way is to check out the following sponsors in the description. First, it's their gun device I use for post work on muscle recovery. Second is an I a company that helps engineers solve the world's toughest problems. Third is give well a directory for best most effective charities. 4th is blink ist the app. I used to read summaries of books and 5th fund rise, a platform for investing in private real estate. So the choice is [/INST] muscle recovery </s><s>[INST] engineering, optimal charity books or investment choose wisely. My friends and now onto the full ad reads as always no ads in the middle. I try to make this interesting, but if you skip them, please still check out our sponsors. I enjoy their stuff. Maybe you will too. This show is brought to you by a flare gun, handheld because of therapy device that they used after workouts for muscle recovery. It's surprisingly quiet, easy to use comes with a great app that guides you through everything you need to know. This has been um, a tool I use often throughout all the physical pursuits I've been under from cardio to weight lifting too grappling, but it has been recently, especially relevant because of a hamstring injury I have and it's been really helping me on the physical therapy side on the recovery, getting back 200%. I mean I can't sing enough praise, they're gonna, has been just a great device for that. [/INST] Anyway, tries, </s><s>[INST] they're going for 30 days at thera body dot com slash lex. They're gone, Gen four has an oled screen personalized their gun app and is both quiet and powerful starting at $199. This show is also brought to you by an I formerly known as national instruments and I is a company that has been helping engineers solve the world's toughest challenges for 40 years. Their motto is engineer ambitiously. I don't think a better model can possibly exist for any company ever. I love ambition. I love engineering. So engineering ambitiously is, uh, pretty much as good as I guess. They have a podcast called testing 123. They have amazing articles, engineering related articles on N I dot com slash perspectives. They cover [/INST] engineering </s><s>[INST] innovation, talking to people and getting their insights about how, um, testing, how failure, how rigorous controlled air making that leads to learning and improvement is a part of their success. So it's so beautiful to be honest about your failures and uh, to accept them as part of the process. I mean, that is what testing is, Testing is fundamental to engineering. It's not about getting it perfect in the design stage. It really is actually, uh, testing it through rigor as it meets the real world. Anyway, [/INST] engineer </s><s>[INST] ambitiously with N. I at N I dot com slash perspectives. That's N I dot com slash perspectives. This show is brought to you by give. Well they research charitable organizations and only recommend the highest impact evidence-backed charities. Over 50,000 donors have used give well to donate more than $750 million. The idea of giving optimally of optimal charity is core to this whole concept that I and a bunch of other people joe Rogan Sam Harris have had a lot of conversation about effective altruism. This is such a great implementation of that because you don't have to worry that your money if you're giving uh donating money to charity that it's not being used optimally not only does give well make it easy for you to not get into trouble. The charities that don't do a good job, but they help you pick out the very best, the highest impact and always backed by real evidence of of a track record of previous performance. So check them out. Go to give well dot org, pick podcast and select lex Friedman podcast at checkout. Once again, let's give well dot org pick podcast and select a lex Friedman podcast at checkout. Good luck my Friends. This episode is also brought to you by blink ist my favorite after learning new things bleakest takes the key ideas from thousands of nonfiction books and condenses them down into just 15 minutes you can read or listen to. They have some of my favorite nonfiction sapiens meditations by Marcus Aurelius. Beginning of infinity by David Deutsch, the Snowden book, the list goes on and on and on. I use blink kissed for several reasons. So one is to review books that I've already read. Two is to select books that I would like to read next in full and three is get a summary of books I'm never going to get a chance to read likely but are still important to our culture so that I can understand where people's ideas are. In fact blink is just does a remarkable job of summarizing books. I feel like sometimes the key insights that blanca's presents just captures the entirety of the book. It's almost like you didn't need to read the book. Of course the magic of reading is if you spend a long time with those ideas, you kind of marinating those ideas. But that doesn't mean you can't have the key ideas and that's what blink is. Does masterfully go to blankets dot com slash lex to start your free seven day trial and get 25% off of a blink is premium membership. That's blinking dot com slash lex spelled B L I N K I S T blink ist dot com slash lex. This show is also sponsored by fund arise spelled F U N D E R I S E. It's a platform that allows you to invest in private real estate. If you're looking to diversify your investment portfolio. This is a good choice. I don't know. I keep hearing that people don't diversify or at least don't diversify as much as I would prefer. I still believe in this age of Cryptocurrency in this age of all kinds of financial investment opportunities. It's still wise to diversify it uh, reduces not only the risk, but also that reduces the load on your mental anxiety associated with investing in something. And I think fund rise and private real estate is a really interesting sort of orthogonal solution to diversification is good too. Allocate some of your funds to this kind of investment. [/INST] Anyway, I'm still a big </s><s>[INST] fan of diversification, but what do I know, definitely don't take my advice for it, but you should check out fun dries at fundraise dot com slash lex 150,000 investors use it. It takes just a few minutes to get started at fundraise dot com slash lex. That's fund rise dot com slash lex. This is the lex Friedman podcast. And here is my conversation with kevin Systrom at the risk of asking the rolling stones to play satisfaction. Let me ask you about the origin story of instagram. So maybe some context you like. We were talking about offline, grew up in massachusetts, learn computer programming there, like to play doom [/INST] to uh </s><s>[INST] worked at a vinyl record store, then you went to stanford turned down mR uh Mark Zuckerberg and facebook went to Florence to study photography, there's just some random, beautiful and possibly brief glimpses into a life. So let me ask again, can you take me through the origin story of instagram? [/INST] Given that contact, basically set it up? All right. So, uh, we have a fair amount of time. So I'll go into some detail. But basically what I'll say is um, instagram started out of a company actually called bourbon and it was spelled B U R B N and uh, a couple of things were happening at the time. So if we zoom back to 2010, not a lot of people remember what was happening in the dot com world then. Uh, but check in apps were all the rage. So what's the checking out Gowalla foursquare hot potato. </s><s>[INST] So I'm gonna place, I'm going to tell the world that I'm at this place. It's right. What's, what's the idea behind this kind of app by the way? [/INST] You know what, I'm going to answer that. But through what instagram became and why I believe instagram replace them. So the whole idea was to share with the world what you were doing specifically with your friends, right? Um, but there were all the rage and foursquare was getting all the press and I remember sitting around saying, hey, I want to build something, but I don't know what I want to build, What if I built a better version of foursquare? And I asked myself, Why don't I like 4square or how could it be improved. Um, and basically I sat down and I said I think that if you have a few extra features it might be enough. One of which happened to be posting a photo of where you were, there were some others, it turns out that wasn't enough. My co founder joined, we were going to attack you know, foursquare and the likes and try to build something interesting Um and no one used it, no one cared because it wasn't enough, it wasn't it wasn't different enough, right? So one day we were sitting down and we asked ourselves, okay, come to jesus moment, are we going to do this start up and if we're going to we can't do what we're currently doing, we have to switch it up. So what do people love the most? So we sat down and we wrote out three things that we thought people uniquely loved about our products that weren't in other products, Photos happen to be the top one so sharing a photo of what you were doing where you were at the moment was not something products let you do really Facebook was like post an album of your vacation from two weeks ago, right, twitter allowed you to post a photo but their feed was primarily text and they didn't show the photo in line at least I don't think they did at the time. So even though it seems totally stupid and obvious to us now at the moment, then posting a photo of what you were doing at the moment was like not a thing. So we decided to go after that because we noticed that people who used our service, the one thing they happen to like the most was posting a photo. So that was the beginning of instagram and yes like we went through and we added filters and there's a bunch of stories around that but the origin of this was that we were trying to be a check in app, realized that no one wanted another check in app. It became a photo sharing app but one that was much more about what you're doing where you are and that's why when I say I think we've replaced checking apps, it became a check in via a photo rather than saying your location and then optionally adding a photo </s><s>[INST] when you were thinking about what people like from where did you get a sense that this is what people like you, you said you sat down and we wrote some stuff down on paper, where is that intuition that seems fundamental to the success of an app. Like instagram. Where does that idea? Where is that list of three things come from? Exactly. [/INST] Only after having studied machine learning now for a couple of years, I like I have a, you have </s><s>[INST] understood yourself, [/INST] I've started to make connections like we can go into this later but obviously the the connections between machine learning and the human brain I think are stretched sometimes right? At the same time being able to back prop and being able to like look at the world, try something figure out how you're wrong, how wrong you are and then nudge your company in the right direction based on how wrong you are. It's like a fascinating concept, right? And I don't we didn't know we were doing it at the time, but that's basically what we were doing, right? We put it out to call it 100 people and you would look at their data, you would say, what are they sharing? What? Like what resonates what doesn't resonate? We think they're going to resonate with X. But turns out they resonate with why. Okay, shift the company towards why. And it turns out if you do that enough quickly enough, you can get to a solution that has product market fit. Most companies fail because they sit there and they don't either they're learning rates to slow, they sit there and they're just they're adamant that they're right, even though the data is telling them they're not right or they are learning rates too high and they wildly chase different ideas and they never actually set on one where they don't groove, right? And I think when we sat down and we wrote up those three ideas, what we were saying is What are the three possible whether they're local or global maxima in our world right, That users are telling us they like because they're using the product that way. It was clear people like the photos because that was the thing they were doing and we just said, okay, like what if we just cut out most of the other stuff and focus on that thing. Um and then it happened to be a multibillion dollar business and it's not easy by the way. </s><s>[INST] Yeah, I guess so. Um Well nobody ever writes about neural networks that miserably failed. So this, this particular neural networks succeeded this [/INST] all the time. Right? But </s><s>[INST] nobody writes default state is failing. Yes. Um when you said the way people are using the app is that the loss function for this neural network or is it also self report. Do you ever ask people what they like or do you have to track exactly what they're doing? Not what they're saying. [/INST] I once made a thanksgiving dinner. Okay. And it was for relatives and I like to cook a lot and I worked really hard on picking the specific uh dishes and I was really proud because I had planned it out using a Gant chart and like ready on time and everything was hot. Like I don't know if you're a big thanksgiving guy but like the worst thing about thanksgiving is when the turkey is cold and some things are hot and something anyway, </s><s>[INST] you had a gan chart, you actually have a [/INST] chart. Yeah. Omni plan fairly expensive like Gant chart thing that I think maybe 10 people have purchased in the world, but I'm one of them and I use it for recipe planning only around big holidays. </s><s>[INST] That's brilliant by the way, do people do this kind of [/INST] over engineering? It's not over, </s><s>[INST] it's just engineering is planning. Thanksgiving is a complicated uh set of events with some uncertainty with a lot of things going on. You should be able, you should be planning in this way, there should be a chart, it's not [/INST] over here. So what's funny is, um brief aside, uh, I love cooking, I love food, I love coffee and I've spent some time with some chefs who like know their stuff and they always just take out a piece of paper and just work backwards in rough order. It's never perfect, but rough order, it's just like, oh, that makes sense. Why not just work backwards from, from the end goal, Right? And put in some buffer time. And so I probably over specified at a bit using a gan chart. But the fact that you can do it, it's what professional kitchens roughly do. They just don't call it a Gant chart at least. I don't think they do. Um Anyway, I was telling a story about thanksgiving. So here's uh here's the thing, I'm sitting down, we have the meal and then I'm, you know, I got to know Ray Dalio fairly well over maybe the last year of instagram, um and one thing that you kept saying was like, feedback is really hard to get honestly from people. And I sat down at after dinner, I said, guys, I want feedback, what was good and what was bad and what's funny is like literally everyone just said everything was great and I like personally knew I had screwed up a handful of things, um but no one would say it. And can you imagine now not something as high stakes as thanksgiving dinner, Okay, thanksgiving there, it's not that high stakes, but you're trying to build a product and everyone knows you left your job for it and you're trying to build it out and you're trying to make something wonderful and it's yours, right? You designed it. Now try asking for feedback. I know that you're giving this to your friends and your family. People have trouble giving hard feedback. People have trouble saying I don't like this, or this isn't great or this is how it's failed me. In fact, um you usually have two classes of people, people who just won't say bad things. You can literally say to them, please tell me what you hate most about this and they won't do it, they'll try but they won't and then the other class of people are just negative period about everything and it's hard to parse out like what is true and what isn't, So my rule of thumb with this is, you should always ask people but at the end of the day it's amazing what data will tell you and that's why with whatever project I work on even now collecting data from the beginning on usage patterns, so engagement, how many days of the week do they use it? How many? I don't know if we were to go back to Instagram how many impressions per day. Right. Is that growing? Is that shrinking and don't be like overly scientific about it. Right? Maybe you have 50 baby users or something. But what's fascinating is that data doesn't lie. People are very defensive about their time. They'll say oh I'm so busy, I'm sorry I didn't get to use the app like I'm just you know, um but I don't know you're posting on instagram the whole time. So I don't know at the end of the day like at facebook there was before time spent became kind of this loaded term there the idea that people, people's currency in their lives is time and they only have a certain amount of time to give things whether it's friends or family or apps or tv shows or whatever. It's there's no way of inventing more of it at least not that I know of if they don't use it, it's because it's not great. So well the moral of the story is you can ask all you want but you just have to look at the data and data doesn't lie. </s><s>[INST] I mean there's metrics there's um data can obscure the key insight if you're not careful. So so time spent in the app that's one there's so many metrics you can put out this and that will give you totally different insights especially when you're trying to create something that doesn't obviously exist yet. So you know um measuring maybe why you left the app or measuring special moments of happiness that will make sure you return to the app or moments of happiness that are long lasting versus like dopamine short term all of those things. But I think I suppose in the beginning you can just get away with just asking the question which features are used a lot. Let's do more of that. And how hard was the decision? And uh I mean maybe you can tell me what instagram looked in the beginning but how hard was it to make pictures the first class citizen. That's a revolutionary idea like um whatever point instagram became this feed of photos. That's quite brilliant. Plus I also don't know when this happened but they're all shaped the same. [/INST] It's like I have to tell you why. That's the interesting part. </s><s>[INST] Why is that? [/INST] So a couple of things. one is data data like you're right you can overinterpret data like imagine trying to fly a plane by staring at I don't know a single metric like air speed. You don't know if you're going up or down. I mean it correlates with up or down, but you don't actually know will never help you land the plane. So don't stare at one metric, like it turns out you have to synthesize a bunch of metrics to know where to go. Um but it doesn't lie like if your speed is zero, unless it's not working right? If it's zero, you're probably gonna fall out of the sky. So generally you look around and you have the scan going and you're just asking yourself, is this working or is this not working? But people have trouble explaining how they actually feel. So just it's about synthesizing both of them. So then instagram, right? Uh we were talking about revolutionary moment where the feed became square photos basically </s><s>[INST] in photos 1st and [/INST] then square foot. Yeah. Um it was clear to me that the biggest, so I believe the biggest companies are founded when enormous technical shifts happen and the biggest technical shift that happened right before instagram was founded was the advent of a phone that didn't suck the iphone right? Like in retrospect, were like, oh my God, the first iphone almost had like it wasn't that good. But compared to everything else at the time it was amazing. And by the way, the first phone that had an incredible camera that could, that could like do as well as the point and shoot you might carry around was the iphone for and that was right when instagram launched and we looked around and we said, what will change because everyone has a camera in their pocket. And it was so clear to me that the world of social networks before it was based in the desktop and sitting there and having a link you could share. Right? And that was going to be the case. The question is, what would you share if you were out and about in the world? If not only did you have a camera that's in your pocket. But by the way that camera had a network attached to it that allowed you to share instantly. That seemed revolutionary and a bunch of people saw it at the same time. It wasn't just instagram. There were a bunch of competitors. Um, the thing we did I think was not only, well we focused on two things. So we wrote down those things, we circled photos and he said, I think we should invest in this. But then we said what sucks about photos. one. They look like crap. Right? They just at least back then now my phone takes pretty great photos right back then they were blurry. Not so great compressed right to uh, it was really slow. Like really slow to upload a photo And I'll tell a funny story about that and explain to you why they're all the same size and square as well. Um, and three and if you wanted to share a photo on different networks, you have to go to each of the individual apps and select all of them and upload individually. And so we're like, all right, those are the pain points. We're gonna focus on that. So one instead because they weren't beautiful. Um were like, why don't we lean into the fact that they're not beautiful? And I remember studying in Florence, my photography teacher gave me this whole get camera and I'm not sure everyone knows what a whole game cameras, but they're these old school plastic cameras. I think they're produced in china at the time. And there, I want to say the original ones like from the 70s or the 80s or something. They're supposed to be like $3 cameras for the every person. They took nice medium format films, large, large negatives, but they kind of blurred the the light and they kind of like light leaked into the side. And there was this whole resurgence where people looked at that and said, oh my God, this is a style, right? And I remember using that in Florence and just saying, well why don't we just like leaning into the fact that these photos suck and make them suck more? But in an artistic way? And it turns out that had product market fit people really like that. They were willing to share their not so great photos if they looked not so great on purpose. Okay, It's the second part </s><s>[INST] that's where the filters come [/INST] into the picture. So </s><s>[INST] computational modification of photos to make them look extra crappy toward becomes art. [/INST] Yeah, I mean add light leaks, add like an overlay filter, make them more contrast than they should be. The first filter we ever produced was called X pro two and I designed it while I was in this small little bed and breakfast room in Toto santos. Mexico is trying to take a break from the, the bourbon days and I remember saying to my co founder, I just need like a week to reset and that was on that trip, worked on the first filter because I said, you know, I think I can do this and I literally iterated one by one over the RGB values in the array that was the photo and just slightly shifted basically there was a function of our function of G, function of B that just shifted them slightly. It wasn't rocket science. Um and it turns out that actually made your photo look pretty cool. It just mapped from one space to another color space. It was simple, but it was really slow. I mean if you applied a filter, I think it used to take two or 3 seconds to render only eventually what I figure out how to do it on the GPU and I'm not even sure it was GPU but was using open jail but anyway, um I would eventually figure that out and then it would be instant. but it used to be really slow by the way anyone who's watching or listening, it's amazing what you can get away with in a startup, as long as the product outcome is right for the user like you can be slow, you can be terrible, you can be as long as you have product market fit, people will put up with a lot. And then the question is just about compressing uh making it more performance over time so that they get that product market fit instantly. </s><s>[INST] So fascinating because there's some things where that those three seconds would make or break the app but some things you're saying not it's hard to know when you know it's what it's the problem. Spotify solved making streaming like work. Mhm. And uh like delays in listening to music is a huge negative even like slight delays but here you're saying, I mean how do you know when those three seconds? Okay we're just gonna have to try it out because to me my intuition would be those three seconds would kill the app. Like I would try to do the open jail [/INST] thing so I wish I were that smart at the time. Um I wasn't I just knew how to do what I knew how to do right and I decided okay like why don't I just iterate over the values and change them. And what's interesting is that Compared to the alternatives. No one else used open jail so everyone else was doing that the dumb way and in fact they were doing it at a high resolution now comes in the small resolution that will talk about for a second. Um by choosing 512 pixels by 512 pixels which I believe it was at the time. We iterated over a lot fewer pixels than our competitors who were trying to do these enormous output like images. So instead of taking 20 seconds, three seconds feels pretty good. Right? So on a relative basis we were winning like a lot. Okay so that's answer number one. Answer number two is uh we actually focused on late and see in the right places. So we did this really wonderful thing um when you uploaded. So uh the way it would work is you know you take your phone, you take the photo and then you'd go to the you'd go the edit screen where you would caption it. And on that caption screen start typing you think okay what's a clever caption? And I said to mike hey when I worked on the Gmail team, you know what they did when you typed in your user name or your email address even before you've entered in your password like the chant probability once you enter in your user name that you're going to actually sign in is extremely high. So why not just start loading your account in the background, not not like sending it down to the desktop, That would be a security uh issue, but like loaded into memory on the server, get it ready to prepare it. I always thought that was so fascinating and un intuitive and I was like mike, why don't we just do that? But like we'll just upload the photo and assume you're going to upload the photo if you don't forget about it, we'll delete it. Right? So what ended up happening was people would caption there uh photo they press done or upload and you'd see those little progress bar just go, it was lightning fast. Okay. We were no faster than anyone else at the time, but by choosing 5 12 by 5 12 and doing in the background, it's almost guaranteed that it was done by the time you captured and everyone when they used it was like how the hell is this thing so fast? But we were slow, we just hit the slowness. It wasn't like these things are just like it's a shell game, you're just hiding the latency that that mattered to people like a lot. And I think that so you were willing to put up with a slow filter if it meant you could share it immediately. And of course we added sharing options which let you distribute it really quickly. That's the third part. Um So latency matters. But relative to what and then there's some tricks you get around to just hiding the latency. Um Like I don't know if Spotify starts downloading the next song eagerly. I'm assuming they do. They're a bunch of ideas here that are not rocket science. That that really helped. </s><s>[INST] And all of that was stuff you were explicitly having a discussion about like those designs and argument. You were having like arguments discussions. I'm [/INST] sure it was arguments. I mean I'm not sure if you've met my co founder mike but he's a pretty nice guy. He's very reasonable and uh and we both just saw eye to eye and we're like yeah it's like make this fast. Really seem fast. It'll be great. I mean honestly I think the most contentious thing and he would say this to initially was um I was on an iphone three G. So like the not so fast one. He had a brand new iphone four. I was </s><s>[INST] cheap. [/INST] Um And his feet loaded super smoothly. Like when he would scroll from photo to photo buttery smooth right? But on my phone every time you got to a new photo it was like a chunk ka chunk allocate memory like all this stuff right? I was like mike that's unacceptable. And he's like oh come on man just like upgrade your phone basically. You didn't actually say that he's nicer than that but I could tell he wished like I would just stop being cheap and just get a new phone. But what's funny is we actually sat there working on that little detail for a few days before launch and that polished experience plus the fact that uploading seemed fast for all these people who didn't have nice phones I think meant a lot because far too often you see teams focus not on performance, they focus on what's the cool computer science problem they can solve right, can we scale this thing to a billion users and they've got like 100 right? Yeah. You talked about loss functions So I want to come back to that. Like the loss function is like do you provide a great, happy, magical, whatever experience for the consumer and listen, if it happens to involve something complex and technical and great. But it turns out I think most of the time those experiences are just sitting there waiting to be built with like not that complex solutions but everyone is just like so stuck in their own head that they have to over engineer everything and then they forget about the easy </s><s>[INST] stuff and then also maybe to flip the last function there is you're trying to minimize the number of times, there's unpleasant experience, right? Like the one you mentioned where it, when you go to the next photo, it freezes for a little bit. So it's almost as opposed to maximizing pleasure. It's probably easier to minimize the number of like the friction. [/INST] Yeah. And as we all know, you just, you just uh, you just make the pleasure negative and then minimize everything. So </s><s>[INST] we're mapping this all back and your networks. [/INST] But actually can I say one thing that, which is, I don't know a lot about machine learning but I feel like I've, I've tried studying a bunch that whole idea of reinforcement learning and planning out more than the greedy single experience I think is is the closest you can get to like ideal product design thinking where you're not saying, hey, like can we have a great experience just this one time? But like what is the right way to onboard someone, what series of experiences correlate most with them hanging on long term. Right? So not just saying, oh did the photo load slowly a couple times or did they get a great photo at the top of their feed? But like what are the things that are going to make this person come back over the next week? Over the next month? And as a product designer asking yourself, okay, I want to optimize not just minimize bad experiences in the short run, but like how do I get someone to engage over the next month and I'm not going to claim at all that I thought that way at all at the time because I certainly didn't, but if I were going back and giving myself any advice would be thinking, what are those, what are those second order effects that you can create? And it turns out having your friends on the service enormous wind. So starting with a very small group of people that produce content that you wanted to see which we did, we seeded the community very well I think ended up mattering and </s><s>[INST] so yeah, you said that community is one of the most important things. So it's from a metrics perspective from maybe a philosophy perspective building a certain kind of community within the app. So I wasn't sure what exactly he meant by that when when I heard you say that maybe you can elaborate but as I understand now it's can literally mean get your friends onto the app. [/INST] Yeah, I think of it this way you can build an amazing restaurant or bar or whatever right? If you show up and you're the only one there is it like doesn't matter how good the food is, the drinks whatever. Um no um these are inherently social experiences that we were working on. So the idea of having people there like you needed to have that otherwise it was just a filter out. But by the way part of the genius, I'm going to say genius even though it wasn't really genius was starting to be marauding is a filter app. It was awesome. The fact that you can, so we talk about single player mode a lot which is like can you play the game alone and instagram, you could totally play alone, you can filter your photos and a lot of people would tell me, I didn't even realize that this thing was a social network until my friend showed up. It totally worked as a single player game and then when your friends showed up all of a sudden it was like, oh not only was this great alone, but now I actually have this trove of photos that people can look at and start liking and then I can like there's, and so it was this bootstrap method of how do you make the thing not suck when the restaurant is empty? </s><s>[INST] Yeah, but the thing is when you say friends were not necessarily referring to friends in the physical space, so you're not bringing your physical friends with you, you're also making new friends. So you're finding new community. So it's not immediately obvious to me that it's like it's almost like building any kind of community. [/INST] It was, it was both and what we learned very early on was what made instagram special and the reason why you would sign up for it versus say just sit on facebook and look at your friends photos of course we were alive and of course it was interesting to see what your friends were doing now, but the fact that you can connect with people who like took really beautiful photos in a certain style all around the world, whether they were travelers, it was the beginning beginning of the influencer economy is these people who became professional instagrammers way back when Right. Um, but they took these amazing photos and some of them were photographers, right? Um, like professionally and all of a sudden you had this moment in the day when you could open up this app and sure you can see what your friends were doing. But also it was like, oh my God, that's a beautiful, beautiful waterfall or oh my God, I didn't realize there was that corner of England or like a really cool stuff. Um, and the beauty about instagram early on was that it was international by default, you didn't have to speak english to use it right? You can just look at the photos works great. We did translate, we had some pretty bad translations, but we did translate the app and uh, you know, even if our translations were pretty poor, the idea that you could just connect with other people through their images was pretty powerful. </s><s>[INST] How much technical difficulties there with the programming, like what programming language you were talking about [/INST] zero. Like maybe it was hard for us, but I mean we, there was nothing, the only thing that was complex about instagram at the beginning technically was making its scale and we were just plain old objective C for the client. So </s><s>[INST] it was iphone [/INST] only only </s><s>[INST] as an android person. I'm deeply offended, but go ahead again, [/INST] This was 2010. Oh sure sure Androids getting a lot better. So, um, I take it back if I were to do something today, I think it would be very different in terms of launch strategy, right? Androids enormous to uh but anyway, back to that moment, it was objective. C uh and then we were python based, which is just like, this is before, python was really cool. Like now it's cool because it's all these machine learning libraries like support python and right now it's super. And I was like, cool to be pilot back then, it was like, oh, google uses python, like maybe you should use python, facebook was PHP Like I had worked at a small startup of some ex googlers that used python. So we used it and we used a framework called Django still exists and people use for basically the back end and then through a couple interesting things in there. I mean, we used Postgres which was kind of fun. It was a little bit like hipster database at the time, My my sequel, Like everyone used my sequel. So, like using Postgres was like an interesting decision, right? Uh but we used it because it had a bunch of geo features built in because we thought we were going to be a checking out, remember it's also </s><s>[INST] super cool now, So you were into python before it was cool and you were into Postgres before. It [/INST] was cool. We were basically like, not only hipster hipster photo company, hipster tech company, right? Uh We also adopted read this early and like I loved it. I mean it solves so many problems for us and turns out that's still pretty cool. But the programming was very easy. It was like sign up a user have a feed, there was nothing, no machine learning at all. zero. </s><s>[INST] Can you get some context how many users at each of these stages? We're talking about 100 users. 1000 users. [/INST] So the stage I just described, I mean that technical stack lasted through Probably 50 million users. Um, I mean seriously, like you can get away with a lot with a pretty basic stack, like I think a lot of startups try to over engineer their solutions from the beginning to really scale and you can get away with a lot That being said most of the first two years of instagram was literally just trying to make that stack scale and it wasn't, it was it was not a python problem. It was like literally just like where do we put the data? Like it's all coming in too fast. Like how do we store it? How do we make sure to be up? How do we, like how do we make sure we're on the right size boxes that they have enough memory. Those were the issues. But </s><s>[INST] can you speak to the choices you make at that stage when you're growing so quickly, do you use something like somebody else's computer infrastructure or do you build in house? [/INST] I'm only laughing because we when we launched we had a single computer that we had rented in some color space in L. A. I don't even remember what it was called because I thought that's what you did when I worked at a company called Odio that became twitter, I remember visiting our space in san Francisco, you walked in, you had to wear the ear things and it was cold and fans everywhere right? And we had to you know plug one out, replace one and I was the intern so I just like help things but I thought to myself oh this is how it goes. And then I remember being in a VCS office, I think it was benchmarks office and I think we ran into another entrepreneur and they were like oh how are things going? We're like you know trying to scale this thing. They were like well I mean can't you just add more instances? And I was like what do you mean? And they're like instances on amazon I was like what are those? And it was this moment where we realized how deep in it we were because we had no idea that a W A W. S existed nor should we be using it anyway that night we went back to the office and we got on AWS but we we did this really dumb thing where I'm so sorry to people listening but we brought up an instance which was our database, it's going to be a replacement for our database. But we had it talking over the public internet to our little box in L. A. That was our observer. Yeah that's how sophisticated we were. And obviously that was very very slow. Um didn't work at all. I mean it worked but didn't work. Did we? Only like later that night did we realized we had to have it all together. But at least like if you're listening right now and you're thinking you know I have no chance, I'm going to start to start but I have no chance. I don't know. We did it we made a bunch of really dumb mistakes initially. I think the question is how quickly do you learn that you're making a mistake? And do you do the right thing immediately right after? So </s><s>[INST] you didn't pay for those mistakes by by failure? So yeah. How quickly did you fix it? I guess there's a lot of ways to sneak up to this question of how the hell do you scale the thing uh other startups? If you have an idea. How do you scale the thing is just a W. S. And you try to write the kind of code that's easy to spread across a large number of instances and then the rest is just put money into it [/INST] basically. I would say a couple things. First off. Don't even ask the question just find product market fit, duct tape it together, right? Like if you have to, I think there's a big caveat here, which I want to get to. But generally all that matters is product market fit. That's all that matters if people like your product Do not worry about when 50,000 people use your products because you will be happy that you have that problem when you get there. I actually can't name many startups where they go from nothing to something overnight and they can't figure out how to scale it. There are some, but I think nowadays it's a, when I say a solved problem, like there are ways of solving it. The base cases typically that starts way way too much about scaling way too early and forget that they actually have to make something that people like that's the, that's the default mistake case. But what I'll say is um, once you start scaling, I mean hiring quickly, people who have seen the game before and just know how to do it, it becomes um, it becomes a bit of like, yeah, just throw instances of the problem right? But the last thing I'll say on this that I think did save us, um, we were pretty rigorous about writing tests from the beginning that helped us move very, very quickly when we wanted to rewrite parts of the product and know that we weren't breaking something else. Tests are one of those things where it's like you go slow to go fast and they suck when you have to write them because you have to figure it out. There are always those ones that break when you don't want them to break and they're annoying and it feels like you spent all this time. But looking back, I think that like long term optimal even with a team of four, it allowed us to move very, very quickly because anyone could touch any part of the product and know that they weren't going to bring down the site released </s><s>[INST] in general at which point do you know, product market fit? How many users would you say? Is it all it takes is like 10 people or is it 1000 is it 50,000? [/INST] I don't think it is generally a question of absolute numbers. I think it's a question of cohorts and I think it's a question of trends. So you know, it depends how big your business is trying to be, right. But if I were signing up 1000 people a week and they all routine like the retention curves for those cohorts looked good healthy and even like as you started getting more people in the service, maybe those earlier cohorts started curving up again because now there are network effects and their friends are on the service or totally depends what type of business you're in. But I'm talking purely social right? Um, I don't think it's an absolute uh, number, I think it is. Uh, I guess you could call it a marginal number. So I spent a lot of time when I work with startups asking them like, okay, have you looked at that cohort versus this cohort, whether it's your clients or whether it's people signing up for the service, But a lot of people think you just have to hit some mark, like 10,000 people are 50,000 people, but really seven ish billion people in the world, most people forever will not know about your product. There are always more people out there to sign up. It's just a question of how you turn on the spigot. So </s><s>[INST] at that stage, early stage yourself, but also by way of advice, should you worry about money at all how this thing's gonna make money or do you just try to find product market fit and uh, get a lot of users to enjoy using your thing? [/INST] I think it totally depends. And that's an unsatisfying answer. Um, talking with a friend today who he was one of our earlier investors and he was saying, hey, like, have you been doing any angel investing lately? I said, not really, I'm just like focused on what I want to do next. And he said the number of financings have just gone bonkers, like just bonk, like people are throwing money everywhere right now. Um, and I think the question is, do you have an inkling of how you're going to make money or you really just like waving your hands? I would not like to be an entrepreneur in the position of well I have no idea how this will eventually make money. That's not fun. Um If you are in an area like, let's say you wanted to start a social network, right? Not saying this is a good idea of it, if you did, there's only a handful of ways they've made money and really only one way they've made money in the past and that's adds um So you know, if you have a service that's amenable to that and then I wouldn't worry too much about that because if you get to the scale you can hire some smart people and figure that out. I do think that is really healthy for a lot of startups these days, especially the ones doing like enterprise software slacks of the world etcetera to be worried about money from the beginning, but mostly as a way of winning over clients and having stickiness um I like of course you need to be worried about money, but I'm going to also say this again, which is, it's like long term profitability, if you have a road map to that, then that's great, but if you're just like, I don't know, maybe never like we're working on this metaphors thing. I think maybe someday, I don't know like that seems harder to me? Um So you have to be as big as facebook to like finance that debt right. </s><s>[INST] Do you think it's possible? You said you're not saying it's necessarily a good idea to launch a social network, Do you think it's possible today? Maybe you can put yourself in those shoes to launch a social network that achieves the scale of a facebook or a twitter or an instagram and maybe even greater scale. [/INST] Absolutely. How do you do it </s><s>[INST] asking for a friend? [/INST] Yeah, if I knew I probably doing it right now sitting here. So </s><s>[INST] I mean there's a lot of ways to ask this question. One is create a totally new product market fit, create a new market, created something like instagram did, which is like create something kind of new or literally out compete facebook at its own thing or I'll compete twitter at its own thing. [/INST] The only way to compete now if you want to build a large social network is to look for the cracks, look for the openings. Um, you know, no one competed. I mean no one competed with the core business of google. No one competed with the core business of Microsoft. You don't go at the big guys doing exactly what they're doing instagram didn't win, quote unquote because it tried to be a visual twitter, Like we spotted things that either twitter wasn't going to do or refused to do images and feed for the longest time right or that facebook wasn't doing or not paying attention to because they were mostly desktop at the time and we were purely mobile, purely visual. Often there are opportunities sitting there, you just have to, you have to, you have to figure out like I think like there's a strategy book, I can't remember the name but talk about moats and just like the best place to play is where your competitor like literally can't pivot because structurally they're set up not to be there and that's where you win. Um, and what's fascinating is like, do you know how many people are like images facebook does that twitter, does that mean? How wrong were they really wrong? And these are some of the smartest people in Silicon Valley. Right? But now instagram exists for a while. How is it that Snapchat could then exist. Makes no sense. Like plenty of people would say, well there's facebook, no images. Okay, Okay. I mean instagram, I'll give you that one but wait now another image based social networks kind of get really big and then Ticktock comes along like the prior. So you asked me, is it possible? The only answer and reason I'm answering yes is because my prior is that it's happened once every, I don't know 34 or five years consistently and I can't imagine there's anything structurally that would change that. Um, so that's why I answered that way not because I know how I just when you see a pattern you see a pattern and there's no reason to believe that's going to stop. </s><s>[INST] And it's subtle too because like you said Snapchat and Tiktok, they're all doing this same space of things, but there's something fundamentally different about like a three second video, in a five second video, in a 15 2nd video, in a one minute video. In a one hour video, like fundamentally different, [/INST] fundamentally different. I mean, I think one of the reasons Snapchat exists is because instagram was so focused on posting great, beautiful, manicured versions of yourself throughout time. And there was this enormous demand of like, hey, I really like this behavior, I love using instagram, but man, I just wish I could share something going on in my day. Like do I really have to put it on my profile? Do I really have to make it last forever? Do I really? Um, and that opened up a door. It created a market right. And then what's fascinating is instagram had an Explorer page for the longest time. It was image driven, right? Um, but there's absolutely a behavior where you open up instagram and you sit on the Explorer page all day that is effectively ticktock, but obviously focused on videos and it's not like you could just put the explore page in tick tock form and it works. It had to be video, it had to have music, These are the hard parts about product development that are very hard to predict. But they're all versions of the same thing with varying if you line them up in a bunch of dimensions. They're just like kind of on, they're different values of the same dimensions. Which is like, I guess easy to say in retrospect, but like if I were an entrepreneur going after that area, I'd ask myself like where's the opening? What needs to exist because Tiktok exists now. </s><s>[INST] So I wonder how much things that don't yet exist and can exist is in the space of algorithms, in the space of recommend er systems. So in the space of how the feat is generated. So we kind of talk about the actual elements of the, the content. That's what we've been talking. The difference between photos between short videos, longer videos. I wonder how much disruption it's possible in the way the algorithms work because a lot of the criticism towards social media is in the way the algorithms work currently. And it feels like first of all talking about product market fit, there is certainly a hunger for social media algorithms that do something different. I don't think anyone, everyone said complaining this is not doing this is, this is hurting me and this is hurting society. But I keep doing it because I'm addicted to it and they say we want something different, but we don't know what it feels like. Uh just different. Uh, it feels like there's a hunger for that. But that's in the space of al grams. I wonder if it's possible to disrupt in that space. [/INST] Absolutely. Um, I have this thesis that the worst part about social networks is that there, uh huh is the people, it's a line. That sounds funny, right? Because like that's why you call it a social network. Um, but what does social networks actually do for you just think, you know, like imagine you're an alien and you landed and someone says, hey, there's this site, it's a social network. We're not going to tell you what it is, but just what does it do you have to explain it to them? Just two things. One is that people, you know, and have social ties with, uh, distribute updates through whether it's, uh, photos or videos about their lives so that you don't have to physically be with them, but you can keep in touch with them. That's one that's like a big part of instagram. That's a big part of snap. It is not part of Tiktok at all. So there's another big part which is, there's all this content out in the world that's entertaining, whether you want to watch it or you want to read it. Um, and matchmaking between content that exists in the world and people that want that content turns out to be like a really big business discovery. Would you search and discovery, but my point is it could be video. It could be text. It could be websites, it could be, I mean think back to um think back to like dig right? Or stumble upon or Right, </s><s>[INST] nice. But [/INST] like what do those do? Like they basically distributed interesting content to you? Right. Um I think the most interesting part are the future of social networks is going to be making them less social because I think people are part of the cause of the problem. So for instance, um often recommend our systems, we talked about two stages, there's a candidate generation step which is just like of our vast trove of stuff that you might want to see, what small subset should we pick for you. Okay, typically that is grabbed from things your friends have shared Right then there's a ranking step which says, Okay, now, given these 100 200 things, depends on the network, right. Let's be really good about ranking them and generally rank the things up higher that get the most engagement, right? So what's the problem with that 1, is we've limited everything you could possibly see to things that your friends have chosen to share or maybe not friends, but influencers, what things do people generally want to share? They want to share? Things that are going to get likes that are going to show up broadly. So they tend to be more emotionally driven, they tend to be more risque or whatever. So why do we have this problem? It's because we show people things people have decided to share and those things self select to being the things that are most divisive, so how do you fix that? Well, what if you just imagine for a second that why do you have to grab things from things your friends have shared? Why not just grab things that's really fascinating to me? And that's something I've been thinking a lot about and just like, you know, why is it that when you log on to twitter, you're just sitting there looking at things from accounts that you followed for whatever reason, and Tiktok I think has done a wonderful job here, which is like you can literally be anyone and if you produce something fascinating, it'll go viral. But like you don't have to be someone that anyone knows, you don't have to have built up a giant following. You don't have to have paid for followers, You don't have to try to maintain those followers. You literally just have to produce something interesting. That is, I think the future of social networking, that's the that's direction things will head. And I think what you'll find is it's far less about people manipulating distribution and far more about what is like is this content good and good is obviously a vague definition that we spend hours on, but different networks, I think we'll decide different value functions to decide what is good and what isn't good and I think that's a fascinating direction. So </s><s>[INST] that's almost like creating an internet. I mean that's what google did for web pages that did, uh, you know, page rank, search discovery. You don't, you don't follow anybody on google when you use a search engine, you just discover web pages. And so what Tiktok does is saying, let's start from scratch. Let's like, like start a new internet and have people discover stuff on that new internet within a particular kind of pool of people. [/INST] What's so fascinating about this is like the field of information retrieval, like always talked about as I was studying this stuff, we always use the word query in document. So I was like, why are they saying aquarium documents? Like they're literally imagine like if you just stop thinking about query is like literally a search query and inquiry could be a person. I mean a lot of the way I'm not going to claim to know how instagram or facebook machine learning works today. But you know, if you want to find a match for a query, the query is actually the attributes of the person their age, their gender where they're from maybe some kind of summarization of their interests and that's a query, right? And that matches against documents and by the way, documents don't have to be text. They can be videos there, however long, I don't know what the limit is on Tiktok these days. They keep changing it. My point is just, you've got a query which is someone in search of something that they want to match and you've got the document, it doesn't have to be text, it could be anything. And how do you match make? And that's one of these, like, I mean I've spent a lot of time thinking about this and I don't claim to have mastered it at all, but I think it's so fascinating about where that will go with new social networks. </s><s>[INST] See what I'm also fascinated by is metrics that are different than engagement. So the other thing from an alien perspective, what social networks are doing is they, they in the short term bring out different aspects of each human being. So first let me say that an algorithm or a social network for each individual can bring out the best of that person or the worst of that person or there's a bunch of different parts to us. Parts. We are proud of that, that we are parts we're not so proud of When we look at the big picture of our lives when we look back 30 days from now, am I proud that I said those things are not my problem that I felt those things and my problem that I experienced or read those things or thought about those things just in that kind of self reflective kind of way and so coupled with that I wonder if it's possible to have different metrics that are not just about engagement but are about long term happiness growth of a human being when they look back and say I am a better human being for having spent 100 hours on that app. And that feels like it's actually strongly correlated with engagement in the long term, in the short term. It may not be, but a long term, it's like the same kind of thing where you really fall in love with the product, you fall in love with an iphone, you fall in love with the car. That's what makes you fall in love is like really being proud and just in a self reflective way, understanding that you're better human being for having used the thing and that's like where uh, that's a great relationships for me from it. It's not just like you're hot and we like being together or something like that. It's more like I'm a better human being because I'm with you and that feels like a metric that could be optimized for by the algorithms. Um, but you know, anytime I kind of talked about this with anybody, they seem to say, yeah, okay, that's going to get out competed immediately by the engagement if it's ad driven especially, I I just don't think so. I don't, I mean a lot of it's just implementation [/INST] say a couple of things. One is to pull back the curtain on daily meetings inside of these large social media companies, a lot of what management or at least the people that are tweaking these algorithms spend their time on our trade offs. And there's these things called value functions which are like, okay, we can predict the probability that you'll click on this thing or the probability that you'll share it or the probability that you will leave a comment on it or the probability you'll dwell on it. Individual actions, Right? And you've got this neural network that basically has a bunch of heads at the end and all of them are between zero and one and great. They all have values right? Or they all have probabilities. Um, and then in these meetings, what they will do is say, well, uh, how much do we value a comment versus a click versus a share versus uh, and then maybe even some downstream thing. Right. Um, that has nothing to do with the item there. But like driving follows or something. And what typically happens is they will say, well, what are our goals for this quarter at the company? Oh, we want to drive, sharing up. Okay, well let's turn down these metrics and turn up these metrics and and they blend them right into a single scaler with which they're trying to optimize. That is really hard because invariably you think you're solving for, I don't know something called meaningful interactions, right. This was the big facebook pivot and I don't actually have any internal knowledge, like I wasn't in those meetings, but at least from from what we've seen over the last month or so it seems by actually trying to, trying to optimize for meaningful interactions. It had all these side effects of optimizing for these other things. Um, and I don't claim to fully understand then, but what I will say is that trade offs abound and as much as you'd like to solve for one thing, if you have a network of over a billion people, you're going to have unintended consequences either way and it gets really hard. So what you're describing is effectively a value model that says like can we capture this is the thing that I spent a lot of time thinking about, can you capture utility in a way that like actually measures someone's happiness that isn't just a, what do they call it? A surrogate problem where you say, well I kind of think like the more you use the product, the happier you are, that was always the argument at facebook by the way, it was like, well people use it more. So there must be more happy turns out there like a lot of things you use more that make you less happy in the world not talking about facebook, just you know, let's think about whether it's gambling or whatever like that you can do more of, but doesn't necessarily make you happier. So the idea that time equals happiness, obviously you can't map utility and time together easily, There are a lot of edge cases. So when you look around the world and you say well what are all the ways we can model utility? There is like one of the please if you know someone smart doing this introduced me because I'm fascinated by it and it seems really tough but the idea that reinforcement learning like everyone interesting I know and machine learning, like I was really interested in recommend er systems and supervised learning and and the more I dug into it was like literally everyone smart is working on reinforcement learning, like literally everyone, </s><s>[INST] you just made people at open ai and deep mind very happy. Yes, [/INST] but I mean but what's interesting is like it's one thing to train a game and like I mean that paper that where they just took Atari and they used a continent to basically just like train simple actions, mind blowing, right? Absolutely mind blowing, but it's a game great. So now what if you're constructing a feed for a person, right? Like how can you construct that feed in such a way that optimizes for a diversity of experience a long term happiness right? But that reward function, it turns out in reinforcement learning again as I've learned like reward design is really hard and I don't know like how do you design a scalar reward for someone's happiness over time? I mean do you have to measure dopamine levels? Like do you have to? </s><s>[INST] Well you have to have a lot of, a lot more signals from the human being currently, it feels like there's not enough signals coming from the human being users of uh of this algorithm. So for reinforcement learning to work well used to have a lot more data, [/INST] needs to have a lot of data and that actually is a challenge for anyone who wants to start something which is you don't have a lot of data, so how do you compete? But I do think back to your original point, rethinking the algorithm, rethinking reward functions, rethinking utility. That's fascinating. That's cool. And I think that's an open opportunity for a company that figures it out. </s><s>[INST] I have to ask about April 2012 when uh instagram Along with its massive employee base of 13 people or sold to Facebook for $1 billion. What was the process like on a business level engineering level? Human level, what was that process of selling to facebook? Like what did it feel like? [/INST] So I want to provide some context which is, I worked in corporate development at google, which not a lot of people know, but corporate development is effectively the group that buys companies right you sit there and you acquire companies and I had sat through so many of these meetings with entrepreneurs. We actually fun fact, we never acquired a single company when I worked in corporate developments, I can't claim that um I had like a lot of experience. Um But I had enough experience to understand okay like what prices are people getting and what's the process. And And as we started to grow, you know, we were trying to keep this thing running and we were exhausted and we were 13 people and I mean we were trying to think back probably 27 37 now. So young and on a relative basis, right? And uh we're trying to keep the thing running and then you know, we go out to raise money and we're kind of like the hot startup at the time. And I remember going into a specific VC and saying our terms we're looking for are we're looking for a $500 million dollars valuation. And I've never seen so many jobs drop all in unison, right? And I was like thanked and walked out the door very kindly after. And then I got a call the next day from someone who was connected to them and said they said We just want to let you know that like it was pretty offensive that you asked for $500 million dollars valuation and I can't tell if that was just negotiating or what. But it's true. Like no one offered us more, right? So </s><s>[INST] Can you clarify the number again? We said how many million? 500? million? [/INST] 500 million? Half a billion. So in my mind I'm anchored like okay well literally no one's biting at 500 million and eventually we would get sequoia and Greylock and others together at 500 million basically post it was 450 pre I think we raised $50 million But just like no one was used to seeing $500 million dollar companies then like I don't know if it was because we were just coming out of The hangover 2008 and things were still in recovery mode but then along comes Facebook and after some negotiation we have two x to the number from half a billion to a billion. Yeah, it seems pretty good. You know? And uh I think Mark and I really saw eye to eye that this thing could be big. We thought we could, their resources would help us scale it. And in a lot of ways it de risks. I mean it reads a lot of the employee's lives for the rest of their lives, including me, including mike, right? Um I think I might have had like 10 grand in my bank account at the time, right? Like we're working hard, we had nothing. Um So on a relative basis it seems very high and then I think the last company to exit for anywhere close to a billion was Youtube that I could think of And uh and thus began the giant long bull run of 2012 2 all the way all the way to where we are now where um I saw some stat yesterday about like how many unicorns exist and it's absurd. But then again, never underestimate technology and like the value it can provide and man costs have dropped and man scale has increased in. You can make businesses make a lot of money now. But on, on a fundamental level, I don't know like how do you describe the decision to sell a company with 13 people for a billion dollars </s><s>[INST] first of all? Like how Did it take a lot of guts to set a table and say 500 million or one billion with Mark Zuckerberg? It seems like a very large number with 13. Like especially [/INST] like doesn't seem it is, </s><s>[INST] it is, especially like you said before the unicorn [/INST] parade, I like that I'm going to use that unicorn parade. Yeah. The uh, you </s><s>[INST] were at the head of the unicorn parade. It's [/INST] the, yeah, it's a massive unicorn parade. Um Okay. So no, I mean we knew we were worth quote unquote a lot, but we didn't, there was no market for instagram. I mean it's not, you could mark, you couldn't mark to market this thing in the public markets. You didn't quite understand what it would be worth or was worth at the time. So in a market an illiquid market where you have one buyer and one seller and you're going back and forth and well, I guess there were like VC firms who were willing to, you know, invest at a certain valuation. So I don't know, you just go with your gut and uh, and at the end of the day, I would say um the hardest part of it was not realizing uh like when we sold it was tough because like literally everywhere I go restaurants, whatever. Like for a good six months after it was a lot of attention on the deal, a lot of attention on the product, a lot of attention. It was kind of miserable. All right. And you're like, wait, like I made a lot of money, but like why is this not great? And because it turns out, you know, and I don't, I don't know, like I don't really keep in touch with Mark, but I've got to assume his job right now is not exactly the most happy job in the world. It's really tough when you're on top and it's really tough when you're in the limelight. So the decision itself was like, oh cool, this is great. How lucky are we? Right, </s><s>[INST] okay. There's a million [/INST] questions. Yeah. Go </s><s>[INST] first of all, First of all, why? Why is it hard to be on top? Why did you not feel good? Can you dig into that? It always um I've heard like olympic athletes say after what they win gold, They get depressed. [/INST] Is </s><s>[INST] it something like that where it feels like it was kind of like a thing you were working towards some some loose definition of success and this shirts like feels like uh at least according to other startups, this is what success looks like and now why don't I feel any better? I'm still human, I still have all the same problems. Is that the nature or is it just like negative attention of some kind? What [/INST] I think it's all of the above, but to be clear there was a lot of happiness in terms of like, oh my God, this is great. Like we like won the super bowl of startups, right? Anyone who can get to a liquidity event of anything meaningful, feels like, wow, this is what we started out to do. Of course we want to create great things that people love. But um like we want in a big way. But yeah, there's this big like, oh if we won, what is like what's next? I don't, so they call it that we have arrived syndrome um which I need to go back and look where I can quote that from. But I remember reading about it at the time, I was like, oh yeah, that's that. I remember we had a product manager leave very early on when we got to facebook and he said to me, I just don't believe I can learn anything at this company anymore. It's like it's hit its apex, we sold it great. I just don't have anything else to learn. So from 2012 all the way to the day I left in 2018 like the amount I learned and the humility with which I realized, Oh we thought we won billion dollars is cool but like there are a $100 billion dollar companies and by the way on top of that we had no revenue. We had, we had a cool product but we didn't scale it yet. There's so much to learn and then competitors and how fun was it to fight Snapchat? Oh my God. Like it </s><s>[INST] was [/INST] like Yankees red sox, that's great. Like that's what you live for. Um you know, you win some, you lose some, but uh the amount you can learn through that process. Uh what I've realized in life is that there is no, and there's always someone who has more, there's always more challenge. Just a different scales and uh sounds like a little buddhist but everything is super challenging, whether you're a small business or an enormous business. I say choose the game you like to play right? You've got to imagine that if you're an amazing basketball player, you enjoy to some extent practicing basketball, it's gotta be something you love. It's gonna suck. It's going to be hard. I have injuries right? But you gotta love it and the same thing with instagram which is um, we might have sold, but it was like great. There's one super bowl title, can we win five, what else can we do now imagine you didn't ask this, but okay, so I left, there's a little bit of like, what do you do next, right? Like what do you, how do you top that thing? It's the wrong question. The question is like when you wake up every day, what is the hardest, most interesting thing you can go work on because like at the end of the day we all turn into dirt doesn't matter right? But what does matter is like, can we really enjoy this life? Not in a hedonistic way because that's the, it's like the reinforcement learning learning like short term for as long term objectives. Can you wake up every day and truly enjoy what you're doing? Um, knowing that it's going to be painful, Knowing that like no matter what you choose, it's going to be painful. Um, whether you sit on a beach or whether you managed 1000 people or 10,000, it's going to be painful. So choose something that's fun to have pain. Um, but yes, there was, there was a lot of, we have arrived and um, it's a maturation process you just have to go through. So </s><s>[INST] no matter how much successes there is how much money you make, you have to wake up the next day and choose the hard life, whatever that means next. That's fun. The fun slash hard life, hard life. That's fun. [/INST] I guess what I'm trying to say is slightly different, which is just that no one realizes everything's going to be hard, even chilling out. It's hard and then you just start worrying about stupid stuff like, I don't know, like did so and so forget to paint the house today or like did the gardener come or whatever. Like I'm so angry in my shipment of wine didn't show up and I'm sitting here on the beach without my wine. I don't know, I'm making shut up now. But like </s><s>[INST] it turns out that even chilling Ak meditation is hard [/INST] work. Yeah. And at least meditation is like productive chilling where you're like actually training yourself to calm down and be, but backing up for a moment, everything's hard. You might as well be like playing in the game you love to play. I just like playing and winning and, and I'm, I'm on the, on the, I'm still on the, I think the first half of life knock on wood. Um, and I've got a lot of years and what am I going to do? Sit around and the other way of looking at this by the way. Um, Imagine You made one movie and it was great. Would you just like stop making movies? No, generally you're like, wow, I really like making movies, let's make another one a lot of times by the way, The second one, the third one, not that great, but the fourth one awesome and no one forgets the sex or everyone forgets the second and the third one. So there's just this constant process of like can I produce and is that fun? Is that exciting? What else can I learn? So this machine learning stuff for me has been this awesome new chapter of being like Man, that's something I didn't understand at all. And now I feel like I'm 1/10 of the way there and that feels like a big mountain to climb. Uh so I distracted us from the original question when </s><s>[INST] we return to the machine learning because I love to explore your interests there. But I mean speaking of sort of challenges and hard things, is there a possible world where sitting in a room with Mark Zuckerberg With a $1 billion dollar deal, you turn it down? [/INST] Yeah of course. </s><s>[INST] What does that world look like? Why would you turn it down? Why did you take it? What was the calculation that you were making [/INST] thus enters the world of counterfactual and not really knowing and if only we could run that experiment </s><s>[INST] with the universe exists, It's just running in parallel to our [/INST] own. It's so fascinating. Right? Um I mean we're talking a lot about money, but the real question was um I'm not sure you'll believe me when I says, but could we strap our little company on the side of a rocket ship and like get out to a lot of people really, really quickly with the support with the the talent of a place like facebook, I mean people often ask me what I would do differently at instagram today </s><s>[INST] and I said well I probably [/INST] hire more carefully because we showed up just like before I knew it, we had like 100 people on the team Than 200 and 300. I don't know where all these people were coming from, I never had to recruit them, I never had to screen them, they were just like internal transfers, right? So </s><s>[INST] it's like relying on the facebook hiring machine which is quite sort of I mean it's an elaborate machine, it's [/INST] great by the way they have really talented people there. But my point is um the choice was like take this thing, put it on the side of a rocket ship. That you know is growing very quickly. Like I had seen what had happened when EVs sold blogger to google. Then google went public. Remember we sold before facebook went public, There was a moment at which the stock price was $17 by the way, Facebook stock price was $17. I remember thinking what did I just do? Right uh now at 320 ISH, I don't know where we are today but like okay like the best thing by the way is like when the stock is down, everyone calls you dope and then when it's up they also call you a dope but just for a different reason right? Like you can't win </s><s>[INST] lesson in there somewhere so but you know the choices to strap yourself to a rocket ship to build your own, you know Mr Elon built his own literally with the rocket ship. That's a difficult choice because there's a world [/INST] actually I would say something different which is Ellen and others decided to sell Paypal for not that much. I mean how much was it? About a billion dollars or </s><s>[INST] something like that? [/INST] I mean it was early and um it's worth a lot more </s><s>[INST] now to build a new rocket ships. So this [/INST] is the cool part right? If you are an entrepreneur and you own a controlling stake in the company, not only is it really hard to do something else with your life because all of the value is tied up in you as a personality attached to this company, right? But if you sell it and you get yourself enough capital and you like have enough energy You can do another thing or 10 other things. Or in Elon's case like a bunch of other things, I don't know like I lost count at this point and it might have seemed silly at the time and sure like if you look back man, paypal is worth a lot now right? But I don't know like do you think Ellen cares about like are we gonna buy Pinterest or not? Like I just, he is, he created a massive capital that allowed him to do what he wants to do and that's awesome. That's more freeing than anything? Because when you are an entrepreneur attached to a company, yeah. Stay at the company for a really long time. It's really hard to remove yourself, </s><s>[INST] but I'm not sure how much. He loved Paypal versus SpaceX and Tesla. I have a sense that you love instagram. [/INST] Yeah. I loved enough to like Work for six years beyond </s><s>[INST] that, which is rare, which is very rare. You chose. [/INST] But can I tell you why it's, um, please, there are not a lot of companies that you can be part of where the pope's like, I would like to sign up for your product. Like I'm not a religious person at all. I'm really not, but when you go to the Vatican and you're like walking among giant columns and you're hearing the music and everything and like the pope walks in and he wants to press the sign up button on your product. It's a moment in life. Okay. Um, no matter what your persuasion. Okay. The number of doors and experiences that, that opened up was, it was incredible. I mean, the people, I got to meet, the places I got to go. Um, I assume maybe like a payments company is slightly different, right? But that's why I like, it was so fun. And plus I truly believed we were building such a great product and I loved, loved the game. It wasn't about the money? it was about the game </s><s>[INST] do you think, do you think you had the guts to say no, is that? So here's I often think about this, like how hard is it for an entrepreneur to say no because the peer pressure, so every basically the sea of entrepreneurs in Silicon Valley is going to tell you this is their dream. The thing you were sitting before was is a dream to walk away from that is really, it seems like nearly impossible. Mhm because instagram could in 10 years be, you know, you can talk about google, you could be making self driving cars and building rockets that go to mars and compete with SpaceX totally and so that's an interesting decision to say, am I willing um to risk it? And the reason I also say it's an interesting decision because it feels like prior previous discussion, if you're launching a social uh social network company, there's, there's going to be that meeting, whatever that number is. If you're successful, if you're on this rocket ship of success, there's going to be a meeting with one of the social media social network companies that want to buy you whether it's facebook or twitter, but it could also very well be google who seems to have like a graveyard of failed social networks and it's I mean I don't know, I think about that, how difficult it is for an entrepreneur to make that decision. How many have successfully made that decision? I guess it's a big question, it's sad to me to be honest, that too many make that decision perhaps for the wrong reason to, [/INST] when you say make the decision, you mean to the </s><s>[INST] affirmative, to the [/INST] affirmative? Yeah, There are also companies that don't sell right and take the path and say we're going to be independent and then you've never heard of it again. Like I, I remember, uh, Path right was one of our competitors early on. Uh, there's a big moment when they had Caramel wrote, it was like $110 million Google or something. It might have been larger. I don't know. Um, and I remember there was like this big techcrunch article that was like, they turned it down after talking deeply about their values and everything and I don't, I don't know the inner workings of four square, but like I'm certain there were many conversations over a time where there were companies that wanted foursquare as well. Um, recently, like, I mean what other companies, there's clubhouse right? Like, I don't know, maybe people were really interested in them to like, there are plenty of moments where people say no and we just forget that those things happen. We only focus on the ones where like, uh, they said yes and like, wow, like what if they had stayed independent? So I don't know, I, like, I used to think a lot about this and now I just don't because I'm like, whatever. You know, like things have gone pretty well, I'm ready for the next game. I mean think about an athlete where I don't know, maybe they, they do something wrong in the World series or whatever and like if you let it haunt you for the rest of your career, like why not just be like, I don't know, it was a game, next game, next shot. Right? If you just moved to that world, like at least I have a next shot, right? </s><s>[INST] No, that, that's, that's beautiful. But I mean just insights. Uh, and it's funny you brought up clubhouse. It is very true. It seems like clubhouse is uh, you know, on the downward path and it's very possible to see a billion plus dollar deal at some stage, maybe like a year ago, half a year ago from facebook from google. I think facebook was flirting with that idea too. And I think a lot of companies probably wore, I wish it was more public. You know what? There's not like a badass public story about them making a decision to walk away. We just don't hear about it and then we get to see the results of that success or the failure more often failure. [/INST] So a couple of things. One is, I would not assume clubhouse is down for the count at all. They're young. They have plenty of money. They're run by really smart people. I'd give them like a very fighting chance to figure it out there a lot of times when people called twitter down for the count and they figure it out and they seem to be doing well right. Um, so just backing up like, and not knowing anything about their internals, like there's a strong chance, they will figure it out and that people are just down because they like being down about companies, they liked assuming that they're going to fail. So who knows? Right? But let's take the ones in the past were like, we know how it played out. There are plenty of examples where people have turned down big offers and then you've just never heard from them again, but we never focus on the company's because you just forget that those were big, but inside your psyche, I think they're um, it's easy for someone with enough money to say money doesn't matter. Which I think is like, it's bullshit. Of course money matters to people. Um, but at the moment you just can't even grasp like the number of zeros that you're talking about. It just doesn't make sense, right? So to think rationally, in that moment is not something many people are equipped to do. Especially not people where I think we had founded the company a year earlier, maybe two years earlier, Like a year and a half were 13 people, but I will say, I still don't know if it was the right decision because I don't have that counterfactual I don't know that other world. I'm just thankful that by and large most people love instagram still do By and large people are very happy with like the time we had there um And I'm proud of what we built. So like I'm cool like we're now now it's next shot right </s><s>[INST] well if we could just linger on this uh Yankees versus red Sox the fun of it. The competition over I would say over the space of features. So uh there are a bunch of features like there's photos, there's one minute videos on instagram there's I. G. T. V. There's stories, there's reels, there's live. So that sounds like it's like a list of too much stuff but it's not because it feels like there they're close together but they're somehow like we were saying fundamentally distinct. Like each of the things I mentioned maybe can you describe the philosophies that design philosophies behind some of these. How you were thinking about it during the uh the historic war between Snapchat and instagram or just in general like this space of features that was discovered. [/INST] There's this great book by Clay Christiansen called competing against Luck. It's like a terrible title but within it there's effectively an expression of this thing called jobs to be done Theory and it's unclear if like he came up with it or some of his colleagues but everyone there are a bunch of places you can find with people claiming to have come up with these jobs to be done theory. The idea is, if you, if you like zoom out and you look at your product, you ask yourself, why are people hiring your product? Like imagine every product in your life is effectively an employee. You know, you're ceo of your life and you hire products to be employees effectively. They all have roles and jobs, right? Why are you hiring a product? Why do you want that product to perform something in your life? And what, like what are the hidden reasons why you're in love with this product instagram was about sharing your life with others visually period, right? Why? Because you feel connected with them, you get to show off, you get to feel good and and cared about right with likes and um, and it turns out that that will, I think forever define instagram and any product that serves that job is going to do very well. Okay Stories, let's take as an example, is very much serving that job. In fact it serves it better than the original product because when you're large and have an enormous audience, you're worried about people seeing your stuff or you're worried about being permanent. So that a college admissions person who's going to see your photo of you doing something. And so it turns out that that is a more efficient way of, of performing that job than the original product was the original product still has its value. Um But at scale these two things together work really really well now I will claim that other parts of the product over time didn't perform that job as well. I think I G. T. V. Probably didn't. Right. Shopping is like completely unrelated to what I just described but in my work I don't know right um products I think products that succeed our products that all share this parent node of like this job to be done that is in common and then there's just like different ways of doing it right? Apple I think does a great job with this right? It's like managing your digital life and all the products just work together. They sink. They like it's beautiful right? Even if they require like silly specific chords to work but they're all part of a system. It's when you leave that system and you start doing something weird that people start scratching their head and I think you are less successful. So I think one of the challenges facebook has had throughout its life is that it has never fully I think appreciated the job to be done of the main product and what it's done is said ooh there's a shiny object over there that starts getting some traction, let's go copy that thing and then they're confused why it doesn't work like why doesn't it work? It's because the people who show up for this, I don't want that. It's different. </s><s>[INST] What's the purpose of facebook's? I remember I was a very early facebook user, I was, the reason I was personally excited about facebook is um because you can first of all use your real name, like I can exist in this world. It could be like formally exist. There's I I like anonymity for certain things, read it and so on, but I wanted to also exist uh not anonymously so that that can connect with other friends of mine who non anonymously and there's a reliable way to know that I'm real and they're real and they were connecting and though it's kind of like I liked it for the for the reasons that people like linked in I guess, but like without the for like not everybody is dressed up and being super polite, like more like with friends, but then it became something much bigger than that. I suppose there's a feed, it became this um I mean it became a place to get discover content to share content that's not just about connecting directly with friends. I mean it became something else. I don't even know what it is really. So you said instagram is a place where you visually share your life. What is facebook [/INST] Well let's go back to the founding of facebook and why it worked really well initially at Harvard and then Dartmouth and stanford and I can't remember, I probably admit there were like a handful of schools in that first tranche, right? Um, it worked because there are communities that exist in the world that want to transact and when I say transact, I don't mean commercially, I just mean they want to share, they want to coordinate, they want to communicate, they want a space for themselves and facebook at its best I think is that if actually you look at the most popular products that facebook has built over time, I feel like at things like groups, marketplace groups is enormous and groups is effectively like everyone can found their own little stanford or Dartmouth or MIT right? And and find each other and share and communicate about something that matters deeply to them. That is the core of what facebook was built around and I think today is where it stands most uh, most strongly </s><s>[INST] as brilliant as the groups. I wish, I wish groups were done better. It feels like it's not a first class citizen. I know, I may be saying something without much knowledge but it feels like it's, it's kind of bolted on while being used a lot. It feels like there needs to be a little bit more structure in terms of discovery in terms of [/INST] like, I mean look at Reddit Reddit is basically groups public and open and a little bit a little bit crazy, right? In a good way. Um, but there's clear product market fit for that specific use case and it doesn't have to be a college. It can be anything, it can be a small group, big group, it can be group messaging facebook shines. I think when it leans into that, I think when there are other companies that just seemed exciting and now all of a sudden the product shifts in some fundamental way to go try to compete with that other thing. That's when I think consumers get confused. Um, even if you can be successful, like even if you can compete with that other company, even if you can figure out how to bolt it on eventually you come back and you look at the app and you're like, I just don't know why I opened this app like why like too many things going on and that was always a worry. I mean you listen to all the things that instagram and I almost gave me a heart attack like way too many things, but I don't know entrepreneurs get bored, they want to add things they want to like right. Um, I don't have a good answer for it except for that. Um, I think being true to your original use case and not even original use case, but sorry, actually not use case, original job. There are many use cases under that job being true to that and like being really good at it over time and morphing as needs change. I think that's how to make a company last forever. And I mean honestly I like my main thesis about why facebook is in the position it is today is if they have had a series of product launches that delighted people over time I think they'd be in a totally different world. So she's just like imagine for a moment and by the way Apple is entering this. But like Apple for so long just like product after product, you couldn't wait for it. You stood in line for it, you talked about it, you got excited, amazon makes your life so easy. It's like wow, I needed this thing and it showed up at my door two days later and like both of these companies, by the way, amazon Apple have issues right? There are labor issues whether it's here in the U. S. Or in china, there are environmental issues. There are but like when's the last time you heard like a large chorus being like these companies better pay for what they're doing on these things, right? I think facebook's main issue today is like uh you need to produce a hit if you don't produce hits. It's really hard to keep consumers on your side. Then people just start picking on you and for a variety of reasons whether it's right or wrong, I'm not even gonna place a judgment right here and right now. I'm just going to say that it is way better to be in a world where you're producing hits and consumers love what you're doing Because then they're on your side and I think that's, it's the past 10 years for Facebook has been fairly hard on this dimension. </s><s>[INST] So, and by hits, it doesn't necessarily mean financial hits. It feels like to me what you're saying is something that brings joy, a product that brings joy to some fraction of the population. [/INST] Yeah, I mean, Tiktok isn't just literally an algorithm in some ways, Tiktok's content uh an algorithm have more sway now over the american psyche than facebook's algorithm, right? It's visual, it's video by the way. It's not defined by who you follow. It's defined by some magical thing that by the way if someone wanted to tweak to show you a certain type of content for some reason that could, right. Um people love it. </s><s>[INST] So as a ceo let me ask you a question, because leadership matters. It's a complicated question. Why is Mark Zuckerberg distrusted, disliked and sometimes even hated by many people in public. [/INST] Right? That is a complicated question. Um Well, the premise, I'm not sure I agree with the premise </s><s>[INST] and I can I can expand that to include even a more mysterious question for me. Bill Gates. Hm [/INST] Well, what is the Bill Gates version of the question? Do you think people hate Bill Gates? </s><s>[INST] No distrust So uh take away one. It's a checklist. There is. I think Mark Zuckerberg's distress is the primary one, but there's also like a like a dislike, maybe hate is too strong a word, but just if you look at like the articles that are being written and so on, there's a dislike and it makes it's confusing to me because it's like the public pick certain individuals and they and they attach certain kinds of emotions to those individuals. [/INST] So someone once uh just recently said there's a strong case that founder led companies have this problem and that a lot of Mark's issues um come today come from the fact that he is a visible founder with this story. The people have watched in both the movie and they followed along and use this boy wonder kid who became one of the world's richest people and and he's no longer marked the person, he's marked this this image of of a person with enormous wealth and power. And in today's world we have issues with enormous wealth and power for a variety of reasons, one of which is we've been stuck inside, you know, for a year and a half, two years, one of which is a lot of people were really unhappy about not the last election, but the last last election. And where do you take out that anger, who do you blame? But the people in charge. That's one example or one reason why I think um a lot of people uh express anger or resentment or unhappiness with with Mark at the same time, I don't know, I pointed out to that person. I was like, well I don't know, like I think a lot of people would really like Ellen, like Elena arguably like he kept his factory open here throughout covid protocols, which arguably a lot of people would be against um </s><s>[INST] while saying a bunch of crazy offensive things on the internet, they still [/INST] like, basically, you know, gives the middle finger to the sec, like on twitter and like, I don't know, I'm like, well there's a founder and like people kind of like him. So </s><s>[INST] I do think that the, so like the founder and slash ceo of a company that's a social network company is like an extra level of difficulty if life is a video game, you just chose the heart [/INST] of it again. </s><s>[INST] So I mean that's why it's interesting to ask you because you're the founder and Ceo of a social [/INST] network, right? Exactly. </s><s>[INST] Exactly. So, but but you're one of the rare examples. Even Jack Dorsey is this light not to the degree, but it just seems harder when you're running a social media company. [/INST] It's interesting. I never thought of Jack is just like, I think generally he's well respected. </s><s>[INST] Yeah, I think so. I think you're right, but like he's but he's not loved. [/INST] Yeah, </s><s>[INST] and I feel like you mean to me twitter is an incredible thing [/INST] again, can I just come back to this point, which seems over simplistic, but like I really do think how a product makes someone feel, they describe that feeling is the founder. Uh, so so make people feel good. So think about it. Like let's just go with this thesis for sure. Like it though, amazon is pretty utilitarian, right, delivers brown boxes to your front door, sure you can have Alexa and you can have all these things, right? But in general it delivers stuff quickly to you at a reasonable price, right? I think Jeff Bezos is wonderfully wealthy, thoughtful, smart guy, right? But like people kind of feel that way about them. They're like, wow, this is really big, were impressed that this is really big and but he's doing the same space stuff Ellen is doing, but they don't necessarily describe the same sense of wonder, right? Um, now let's take you on and again, this is pet theory. I don't have much proof other than my own intuition. Um he is literally about living the future mars, it's about wonder. It's about going back to that feeling as a kid when you looked up to the stars and asked is there life out there, people get behind that because it's a sense of hope and excitement and innovation and like you can say whatever you want, but we describe that emotion to that person. Now let's say you're on a social network and people make you kind of angry because they disagree with you or they say something ridiculous or they're living a foam a type life were like, wow, I wish I was doing that thing. I think instagram if I were to think back by and large when I was there was not about fomo was not about this influencer economy, although it certainly became that way closer to the end, it was about the sense of wonder and happiness and beautiful things in the world and I don't know, I mean like I don't want to have a blind spot but I don't think anyone had a strong opinion </s><s>[INST] about for the longest time the way people explain to me. I mean if you want to go for toxicity, you go to facebook or twitter, if you want to go to make feel good about life, you go to instagram to enjoy celebrate life that was [/INST] my experience been talking to people is they gave me the benefit of the doubt because of that. But if your experience of the product is kind of makes you angry. It's where you argue. I mean a big part of Jack might be that he wasn't actually this year for a very long time and only became recently, so I'm not sure how much of the connection got made. Um, but in general, I mean if you hate, you know, I'm just thinking about other companies that are in tech companies, if you hate like what a company is doing or or it makes you not feel happy. I don't know, like people are really angry about Comcast or whatever or even called Comcast anymore, it's like Xfinity or something, right? They had to rebrand, they became right. Um, </s><s>[INST] it's like, but [/INST] my point is, if it </s><s>[INST] makes you that's beautiful. Yeah. But the thing is, this is me saying this, I think your thesis is very strong and correct has elements of correctness, but I still personally put some blame on individuals. Of course. I think, uh, you said Ellen looking up, there's something about childlike wandered him like to his personality, his character, something about, I think more so than others where people can trust them and there's uh, I don't know, sunday brunch is an example of somebody. It was like, there's some kind of, it's hard to put into words, but there's something about the human being where he's trustworthy, he's human in a way that connects to us. And the same with Sergeant Adela. I mean some of these folks, um, something about us is drawn to them even when they're flawed. Even like, uh, so like your thesis really holds up for steve jobs because I think people didn't like steve jobs, but like he delivered products and then they fell in love every time. I guess you could say that the ceo the leader is also a product if they keep delivering a product that people like by being a public and saying things that people like that's also a way to make people happy. But from a social network perspective, it makes me wonder how difficult it is to explain to people why certain things happen. Like to explain machine learning to explain why certain the woke mob effect happens or the certain kinds of like bullying happens, which is like it's human nature combined with the algorithm and it's very difficult to control for how the spread of quote unquote misinformation happens, it's very difficult to control for that. And so you try to decelerate certain parts and you create more problems then you solve and anything that looks at all like censorship can create huge amounts of problems. It's a slippery slope and then you have to inject humans to oversee the machine learning algorithms and anytime you inject humans into the system it's gonna create a huge number of problems. And I feel like it's up to the leader to communicate that effectively to be transparent. First of all designed products that don't have those problems and second of all when they have those problems to be able to communicate with them, I guess that's all going to, when you run a social network company, your job is hard. [/INST] Yeah, I will say the one element that you haven't named that I think you're getting at is just bedside manner which steve jobs. I never worked for him. I never met him in person um had an like an uncanny ability in public to have bedside manner. I mean some of the best clips of steve jobs from like, say Maybe the 80s when he's on this stage and getting questions from the audience about life for, and he'll take this question that is like, how are you going to compete with blah and super boring and I don't even know the name of the company? And his answer is, is if you just asked like your grandfather the meaning of life and you sit there and you're just like, what, like, and there's that bedside manner. Um, and if you lack that, or if that's just not intuitive to you, I think that it can be a lot harder to gain the trust of people and then add on top of that missteps of companies, right? It's, I don't know if you have any friends from the past where like maybe they crossed you once or like maybe you get back together and you're friends again, but you just never really forget that thing. It's human nature not to forget, </s><s>[INST] I'm Russian, you crossed me once [/INST] we </s><s>[INST] solve the problem. [/INST] So my point is there is humans don't forget, and if there are times in the past where they feel like they don't trust the company or the company hasn't had their back. That is really hard to earn back, especially if you don't have that bedside manner. Um, and again, like I'm not attributing this specifically to mark because I think a lot of companies have this issue where one you have to be trustworthy of the company and live by it and live by those actions. And then to I think you need to be able to be really relatable in a way that's very difficult if you're worth like what these people are. </s><s>[INST] It's really hard. Yeah, Jack does a pretty good job of this by being a monk, but [/INST] I also like jackets, shoes, attention. Like he's not out there almost on purpose. He's just working hard, doing square and right. Like I literally shared a desk like this with him at a rodeo. I mean this normal guy who likes painting, I like, I remember he would leave early on Wednesdays or something to go to like a painting class and he's creative, he's thoughtful. I mean, money makes people like more creative and more thoughtful, like extreme versions of themselves. Right? Um and this was a long, long time ago you </s><s>[INST] mentioned that he uh he asked you to do some kind of javascript thing. [/INST] We're working on some javascript together. I like </s><s>[INST] hilarious, like pre twitter early twitter days. You and Jack Dorsey are in the room together talking about javascript solving some kind of menial problem, [/INST] terrible problems. Yeah, I mean not terrible, just like boring, boring widget problem. I think it was the audio widget we were working on at the time, I'm surprised anyone paid me to be in the room as an intern because I didn't really provide any value. I'm very thankful to anyone who included me back in the day. Uh, it was very helpful. So thank you if you're </s><s>[INST] listening. I mean is there uh, Odio, that's a precursor to twitter. First of all, did you have any anticipation that this Jack Dorsey guy could be also ahead of a major social network and um, second did you learn anything from the guy that like, do you think it's a coincidence that you two were in the room together? And it's the coincidence meeting. Like why does the world play its game in a certain way where these two founders of social networks? I don't know. [/INST] It's so weird, right? Like, I mean it's also weird that Mark showed up, you know, in our fraternity, my sophomore year and we got to know each other then long before instagram. It's, it's a small world, but let me tell a fun story about Jack. Um, we're at a rodeo and I don't know, I think ev was feeling like people weren't working hard enough for something and I can't remember exactly what he created this thing where every friday, if it was every friday, I only remember this happening once, but he had a like a statuette. It's like mary and in the bottom it's hollow, right? And I remember on a friday, he decide have decided he was going to let everyone vote for who had worked the hardest that week. We all voted closed ballot right? We all put in a bucket, you tally the votes and then whoever got the most votes as I recall got the statuette and in the statue it was 1000 bucks or as I recall there was 1000 bucks a night, might have been 100 bucks, but let's call it a thousands more exciting that way. Like it did to me for sure. I actually got two votes. I was very happy we were a small company. But as the intern I got at least two votes, </s><s>[INST] everybody knew how many votes they got individually. [/INST] Yeah, I think it was one of these self accountability things. Anyway, I remember Jack just getting like the vast majority of votes from everyone and I remember just thinking like I couldn't imagine he would become what he'd become and do what he would do. But I had a profound respect that the new guy who I really liked worked that hard and you can see his dedication even then and that people respected him. That's the one story that I remember of him like working with him specifically from that </s><s>[INST] summer can take a small tangent on that. Of course there's kind of a push back in Silicon Valley a little bit against hard work. Can you speak to the sort of the thing you admire to see the new guy working so hard, that thing. What is the value of that thing in a company, [/INST] This is like just to be very frank, it drives me nuts. Like I saw this really funny video and tick tock tick tock, it was like I'm taking a break from my mental health to work on my career, I thought that was funny. Um so I was like, oh it is kind of phrase that way, the opposite often. Right, okay, so a couple of things uh I uh I have worked so hard to do the things that I did like mike and I lost years off of our lives, staying up late, figuring things out the stress that comes with the job. I have a lot more gray hair now than I did back then, it requires an enormous amount of work and most people aren't successful right, but even the ones that do don't skate by um I am okay if people choose not to work hard because I don't actually think there is anything in this world that says you have to work hard um but I do think that great things require a lot of hard work, so there's no way you can expect to change the world without working really hard and by the way even changing the world, you know the folks that I respect the most have nudged the world in like a slight direction, slight, very, very slight, like even if Elon accomplishes all the things he wants to accomplish, we will have have nudged the world in a slight direction but it requires an enormous amount of there was an interview with him where he was just like he was interviewed I think at the Tesla factory and he was like work is really hard, this is actually unhealthy and I can't recall the exact, but he was like visibly shaken about how hard he had been working and he was like this is bad and unfortunately I think to have great outcomes, you actually do need to work at like three standard deviations above the mean. But there's nothing saying that people </s><s>[INST] have to go see the thing is, but what I would argue this is my personal opinion is nobody has to do anything. First of all they certainly don't have to work hard. But I think hard work in a company should be admired. [/INST] I do </s><s>[INST] too and you should not feel like you shouldn't feel good about yourself for not working hard. Like it's just so for example, I don't have to work out, I don't have to run, I hate running but like I certainly don't feel good if I don't run because I know for my health like there's certain values I guess is what I'm trying to get. There's certain values of the oven life. It feels like there's certain values that companies should have and hard work is one of the things um I think that should be admired. I often ask this kind of silly question Uh just just to get a sense of people wouldn't like if I'm hiring and so on, just ask if they think it's better to work hard and work smart. It was helpful for me to get a sense of people from that because you think like the writers both was [/INST] that the </s><s>[INST] answer is both. I usually try not to give them that, but sometimes I'll say both if that's an option, but a lot of people kind of a surprising number will stay work smart. And there are usually people who don't know how to work smart and uh they're literally just lazy, not just there's two, there's two effects behind that is, one is laziness and the other is [/INST] ego </s><s>[INST] when you're younger. And you say it's better to work smart, It means you think, you know what it means to work smart at this early stage to me, people that say work hard or both, They have the humility to understand, like I'm going to have to work my ass off because I'm too dumb to know how to work smart and people who are self critical in this way in some small amount you have to have some confidence, but you have, if you have humility, that means you're going to actually eventually figure out what it means to work smart and then to actually be successful, you should do both. [/INST] So I have a very particular take on this, which is that um No 1's forcing you to do anything. All choices of consequences. So if you major in, I don't know theoretical literature, I don't even know if that's a major, I'm just making something else </s><s>[INST] as opposed to regular literature, like [/INST] literature. Think about like theoretical spanish lit from the 14th century, like just make make up your esoteric thing and then the number of people I went to stanford with who get out in the world, they're like, wait what? I can't find a job, like no one wants a theoretical, like there are plenty of counter examples of people have majored in esoteric things and gone on to be very successful. So I just want to be clear, it's not about the major, but every choice you make, whether it's to have kids. Like I love my Children, it's so awesome to have two kids and it is so hard to work really hard and also have kids. It's really hard and there's a reason why certain very successful people like don't have are not successful, but people who run very, very large companies and startups have chosen not to have kids for a while or chosen not to like prioritize them. Everything is a choice and like I choose to prioritize my Children because I want to do that, right? So everything is a choice now, once you've made that choice, I think it's important that the contract is clear, which is to say, let's imagine you were joining a new startup, it's important that that startup communicate that like the expectation is like we're all working really, really hard right now, you don't have to join the startup. But like if you do just know like it's almost as if you join, I don't know pick your, pick your, pick your like sports team, like let's go back to the Yankees for a second. You want to join the Yankees but you don't really want to work that hard, you don't really want to do batting practice or pitching practice or whatever for your position right? Um That to me is wacko and that's actually the world that it feels like we live in and text sometimes where people both want to work for the Yankees because it pays a lot but I don't actually want to work that hard That I don't fully understand because if you sign up for some of these things just sign up for it. But it's okay if you don't want to sign up for it, there's so many wonderful careers in this world that don't require 80 hours a week. But when I read about companies going to like four day work weeks and stuff just like I chuckle because I can't get enough done with the seven day week, I don't know how and people will say oh you're just not working smart. It's like no I worked pretty smart. I think in general like I would have gotten to this point if I hadn't like some amount of working smart and there is balance though. So I used to be like a pretty big cyclist. I don't do it much anymore just because of kids and prioritizing other things, right? But one of the most important things to learn as a cyclist is to take a rest day. But to me and to cyclists like resting is a function of optimizing for the long run. It's not like a thing that you do for its own merits. It's actually like if you don't rest, your muscles don't recover and then you're just not as like you're not training </s><s>[INST] as efficiently. You should probably the successful people I've known in terms of athletes, they hate rest days, but they know they have to do it for the long term. They think their opposition is getting stronger and stronger and that's the feeling. But you know, it's the right thing and usually need a coach to help you. [/INST] Yeah, totally. So I mean, I use this thing called training peaks and it's interesting because it actually mathematically shows like where you are on the curve and all this stuff, but you have to like, you have to have that rest, but it's a function of going harder for longer. Again, it's this reinforcement learning like planning the aggregate and long. But a lot of people will hide behind laziness by saying they're trying to optimize for the long run and they're not, they're just not working very hard. But again, you don't have to sign up for, it's totally cool. Like I don't think less of people for like not working super hard, just like don't sign up for things that require working </s><s>[INST] super hard. And some of that requires for the leadership to have the guts, the boldness to communicate effectively at the very beginning. I mean sometimes I think most of the problems arise from the fact that the leadership is kind of hesitant to communicate this socially difficult truth of what it takes to be at this company. So they kind of say, hey, come, come with us, there's with snacks, but [/INST] unlimited vacation. And you know, Ray at Bridgewater is always fascinating because, you know, people, it's been called like a cult on the outside or cultish and but what's fascinating is like they just don't give on their principles. They're like, listen, this is what it's like to work here, we record every meeting, we're like brutally honest and that's not gonna feel right to everyone. And if it doesn't feel Reggie totally cool, just go work somewhere else. But if you work here, you are signing up for this and that's, that's been fascinating to me because it's honesty upfront. It's a system in which you operate. Um and if it's not for you, like no one is forcing you to work there, right? </s><s>[INST] I actually did. So I did a conversation with him at uh kind of got stuck in a funny moment which is uh at the end I asked him to give me honest feedback of how I did in the interview and that was, I don't think so. He was super nice. He asked me, he's like, well tell me did you accomplish what you were hoping to accomplish? I was like that's not, that's not, I'm asking you as an objective observer of two people talking. How do we do today? Hm And then he's like, well I'm, he gave me this politician answer. Well I I feel like we've accomplished successful communication of like ideas which is I'd like, I'd love to spread some of the ideas in that principles and so on. [/INST] Back to my original point, it's really hard to get </s><s>[INST] even for radar. Really [/INST] hard to give feedback. And one of the other things I learned from him and just people in that world is like man, humans really like to pretend like they've come to uh that they've come to some kind of meeting of the minds. Like if there's conflict, if you and I have conflict, it's always better to meet face to face, right or on the phone slack is not great write emails, not great but face to face. What's crazy is you and I get together and we actively try to, even if we're not actually solving the conflict, we actively try to paper over the conflict. Oh yeah, it didn't really bother bothering me that much. Oh yeah, I'm sure you didn't mean it. I'm, but like, no in our minds were still there. Um, so this is one of the things that as a leader you always have to be digging, especially as you </s><s>[INST] ascend to the [/INST] conflict as you ascend, no one wants to tell you you're crazy, no one wants to tell your, your idea is bad and you can, you're like, oh, I'm going to be a leader. And the idea is I'm just going to ask people want tells you. So like you have to look for the markers knowing that literally just people aren't going to tell you along the way and be paranoid. I mean you asked about selling the company, I think one of the biggest differences between me and a lot of other entrepreneurs is like, I wasn't completely confident, we could do it, like we could be alone and actually be great and if any entrepreneurs honest with you, they also feel that way, but a lot of people are like, well I have to be cocky and just say I can do this on my own, I we're going to be fine, we're going to crush everyone. Some people do say that and then it's not right and they fail, but </s><s>[INST] being honest in that moment with yourself with those close to you [/INST] and also you talked about the personality of leaders and who resonates and who doesn't, it's rare that I see, uh, leaders be vulnerable, rare. And one thing I tried to do at instagram at least internally was like, say when I screwed up and like point out how I was wrong about things and point out where my judgment was off. Everyone thinks they have to about 1000, right? Like that's crazy. The best quant hedge funds in the world, about 50.1%. They just take a lot of ETS right renaissance. They might, they might get 51% right. But holy hell, like the question isn't, are you right? Every single time? And you have to seem invincible. The question is, how many at bats do you get in on average? Are you, are you better on average right? With enough bets and enough at bats that your aggregate can be very high. I mean steve jobs was wrong and a lot of stuff. The newton is too early, right max, not quite right. Um, there was even a time where, and he said like no one will ever want to watch video on the ipod totally wrong, but who cares if you come around and realize your mistake and fix it, </s><s>[INST] It becomes just like you said harder and harder when your ego grows and the number of people around you that say positive things towards you grows and [/INST] I actually think it's really valuable that Like let's manage and counterfactual where Instagram became worth like $300 billion dollars or something crazy, right? Um I kind of like that my life is relatively normal now and when I say relatively you get what I mean, I'm not making a claim that I live a normal life, But like I certainly don't live in a world where there are like 15 Sherpa is following me like fetching me water, like that's not how it works. I actually like that I have a sense of humility of like I may not found another thing that's nearly as big, so I have to work twice as hard or I have to like learn twice as much. I have to read my, we haven't talked about machine learning it, but my favorite thing is all these like famous, you know, uh tech guys who have worked in the industry pontificating about the future of machine learning and how it's going to kill us all and like, and like I'm pretty sure they've never tried to build anything with machine learning themselves. </s><s>[INST] So there's a nice line between people that actually build stuff with machine, like actually program something or at least understand someone's fundamentals and the people that are just saying philosophical stuff for journalists and so on. It's it's a, it's an interesting line to walk because the people who program are often not philosophers, [/INST] so we don't have the attention, they can't write an op ed for the Wall Street Journal. Like it doesn't </s><s>[INST] work. It's nice to be both a little bit like to have elements of both? [/INST] My point is the fact that I have to learn stuff from scratch or that I choose to or </s><s>[INST] like tumbling? [/INST] Uh yeah, I mean again I have a lot of advantages I like, but my point is it's awesome to be back in a game where you have to fight. That is that's fun. So being humble, being vulnerable, it's an important aspect of leader and I hope it serves me well. But like I can't fast forward 10 years to know I'm just that's my game plan </s><s>[INST] before I forget. I have to ask you one last thing on instagram, what do you think about the whistleblower Francis? How good recently coming out and saying that facebook is aware of the instagrams harmful effect on teenage girls as per their own internal research studies in the matter. What do you think about this baby of yours instagram being under fire? Now as we've been talking about under the leadership of facebook? [/INST] You know, I often question, where does the blame lie? Is the blame at the people that originated the network? Me right. Uh is the blame? Like the decision to combine the network with another network with a certain set of values um is the blame at how it gets run after I left? Like is that the driver, is that the car? Right. Um is it that someone enabled these devices in the first place if you go to an extreme right? </s><s>[INST] Or is it the users themselves just human nature. Is it is it just the way of human nature? [/INST] Sure. And like the idea that we're going to find a mutually exclusive answer here is crazy. There's not one place. It's a combination of a lot of these things. And then the question is, is it true at all? Right? Like I'm not actually saying that's not true or that it's true, but there's always more nuance here. Do I believe that social media has an effect on young people? Well, it's God do they use it a lot? And I bet you there are a lot of positive effects and I bet you there are negative effects just like any technology and where I've come to in my thinking on this is that I think any technology has negative side effects. The question is as a leader, what do you do about them? And are you actively working on them or do you just like not really believe in them? If you're a leader that sits there and says, well we're gonna put an enormous amount of resources against this. We're gonna acknowledge when there are true criticisms were going to be vulnerable and that we're not perfect and we're gonna go fix them and we're going to be held accountable along the way? I think that people generally really respect that. Um, but I think that where facebook I think has had issues in the past is where they say things like I can't remember what mark said about misinformation during the election. There was that famous quote where he's like, it's pretty crazy to think that facebook had anything to do with this election. Like that was something like that quote and I don't remember what stage he was on and but who, that did not age well right? Like you have to be willing to say, well maybe there's there's there's something there and wow, like I want to go look into it and truly believe it in your gut. But if people look at you and how you act and what you say and and don't believe you truly feel that way. </s><s>[INST] It's not just the words you say but how you say them and people believe they actually feel the pain of having caused any suffering. [/INST] So to me it's um it's much more about your actions and your posture post event than it is about debugging the why? Because I don't know is it like I don't know this research, it was written well after I left right. Like is it the algorithm is that the explorer page? Is that the people you might know unit connecting you to you know ideas that are dangerous like I really don't know. Um so we have to have a much deeper I think dive to understand where the blame lies, </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] with my life. Well let me just say, I just, it's a really hard problem that probably facebook and twitter are trying to solve. I'm actually just fascinated by how hard this problem [/INST] is. There are fundamental issues that facebook in tone and in an approach of how product gets built and the objective functions and um and since people organizations are not people so young and fair, right? Like there are a lot of really great people who like literally just want to push reinforcement learning forward. They literally just want to teach a robot to touch feel lift, right? Like they're not thinking about political misinformation, right? But there's a, there's a strong connection between what funds that research and an enormously profitable </s><s>[INST] machine [/INST] That has trade offs and one cannot, one cannot separate the two, you are not completely separate from the system. So I agree. It can feel really frustrating to feel if your internal internal there that you're working on something completely unrelated and you feel like you're groups good. I can understand that </s><s>[INST] but there's some responsibility still you have to act now. It's like the right value thing. You have to look in the mirror and see if there's problems and you have to fix those problems. Yeah, you mentioned machine learning reinforcement quite a bit. I mean to me, social networks is one of the exciting places recommended systems where machine learning is applied, where else in the world, In the space of possibilities over the next 5, 10, 20 years, do you think we're going to see impact of machine learning when you try on a philosophical level, on a technical level, what do you think or within social networks themselves? [/INST] Well, I think the obvious answers are climate change right? Like think about how much fuel or just waste there is an energy consumption today because we don't plan accordingly because we take the least efficient route or </s><s>[INST] the logistics and stuff. Supply chain, all that kind of stuff. [/INST] Yeah. I mean listen, if we're going to fight climate change, like one really weigh one awesome way to do it is figure out how to optimize how we operate as a species and and minimize the amount of energy we consume to maximize whatever economic impact we want to have because right now those two are very much tied together and I don't believe that that has to be the case. There's this really interesting, you've read it um for people who are listening, there's really interesting paper on reinforcement learning and energy consumption inside buildings. It's like one of the seminal ones, right? Um But imagine that at massive scale. That's super interesting. I mean they've done like resource planning for servers for peak load using reinforcement learning, I don't know if that was like google or somewhere else but like okay great you do it for servers but what if you could do it for just capacity and general energy capacity for cities and planning for traffic and of course there's all the self driving cars and I don't know like I'm not going to pontificate a like crazy ideas uh using reinforcement learning or machine learning, it's just so clear to me that humans don't think quickly enough. </s><s>[INST] So it's interesting to think about machine learning, helping a little bit at scale, so a little bit to a large number of people that has a huge impact. So if you optimize It's a Google maps, something like that trajectory planning or would a map quest 1st uh [/INST] getting here. I looked and it was like he was the most energy efficient around, I was like I'm gonna be late, I need to take the fastest </s><s>[INST] route as opposed to enrolling the map like and that's going to be very inefficient no matter [/INST] what I was definitely the other day like part of the epsilon of epsilon greedy with ways where like I was sent on like a weird route that I could tell there like we just need to collect data on this road. We just the and they are definitely going to be the guinea pig and great </s><s>[INST] now we have, did you feel pride? [/INST] Oh going through it? I was like oh this is fun. Like now they get data about this weird shortcut. Actually I hit all the green lights network, I'm like this is a problem, bad data, bad data. They're just going to imagine. </s><s>[INST] I could see it [/INST] slowing down and stopping </s><s>[INST] at a green light just to give them the right kind of data. [/INST] But to answer your question like I feel like that was fairly unsatisfying and it's easy to say climate change, but what I would say is at instagram everything we applied machine learning to got better for users and it got better for the company and I saw the power, I didn't fully understand it as an executive and I think that's actually one of the issues that uh I want to say, I understand, I mean the mathematics of it, like I understand what does I understand that it helps but there are a lot of executives now that talk about it in the way that they talk about the internet are they talked about the internet like 10 years ago, they're like we're gonna build mobile and you're like what does that mean? They're like we're just gonna do mobile and you're like okay um So my sense is the next generation of leaders will have grown up having had classes in reinforcement learning, supervised learning whatever and they will be able to thoughtfully apply it to their companies and the places that it is needed most. And that's really cool because I mean talk about efficiency gains, uh it's that's what excites me the most about </s><s>[INST] it. Yeah, so there's it's interesting just to get a fundamental first principles understanding of certain concepts of machine learning. So supervised learning from an executive perspective supervised learning, you have to have a lot of humans label out of data. So the question there is okay, can we gather a large amount of data that can be labeled well? And that's the question Tesla asked, can we create a data engine that keeps um sending an imperfect machine learning system out there. Whenever it fails, it gives us data back, we label it by human and we send it back and forth. So this way then there is a young raccoons excited about this self supervised learning where you do much less human labeling and there's some kind of mechanism for the system to learn it by itself on the on the human generated data and then there's the reinforcement learning which is like basically allowing it's it's applying the Alpha Zero uh technology that allow through self play to learn how to solve the game of go and achieve incredible levels at the game of chess. Can you formulate the problem you're trying to solve in a way that's amenable to reinforcement learning and can you get the right kind of signal at scale? Because you need a lot, a lot of signal and that's, that's kind of fascinating to see which part of the social network can you convert into reinforcement learning problem? [/INST] The fascinating thing about reinforcement learning, I think, is that we now have learned to apply uh neural networks to guess ah you know, Q like the Q function basically the values for any state in action. And that is fascinating cause we used to just like, I don't know, I have like a linear regression, like hope it worked and that was the fanciest version of it. But now you look at it, I'm like trying to learn this stuff and I look at it, I'm like, they're like 17 different acronyms of different ways. You can try to apply this. No one quite agrees. </s><s>[INST] Like what's [/INST] the best? Generally, if you're trying to like build a neural network, they're pretty well trodden ways of doing that. Yeah, use adam. Use rare blue. Like there's just like general good ideas and reinforcement learning. I feel like the consensus is like it totally depends and by the way, it's really hard to get it to converge and it's noisy and it's like, so there are all these really interesting ideas around building simulators um you know like for instance and self driving, right? Like you, I don't want to like actually have someone getting in an accident to learn that an accident is bad. So you start simulating accents, simulating aggressive drivers, just simulating crazy dogs that run into the street, wow, fascinating, right? Like that my mind starts racing and then the question is, okay, forget about self driving cars. Let's talk about social networks, how can you produce a better, more thoughtful experience using these types of of algorithms and honestly in talking to some of the people that work at facebook and, and old instagrammers, Most people are like yeah, we tried a lot of things, didn't quite ever make it work for the longest time. Facebook ads was effectively a logistic regression. Okay, I don't know what it is now, but like if you look at this paper they published back in the day, it was literally just a logistic regression, made a lot of money. Um So even at these extremely large scales, if we are not yet touching what reinforcement learning can truly, do imagine what the next 10 </s><s>[INST] years looks like, How cool is that? It's amazing. So I I really like the use of reinforcement learning as part of the simulation for example, like self driving cars. It's modeling pedestrians. So the nice thing about reinforcement learning, it can be used to learn agents within the world so they can learn to behave properly. Like you can teach pedestrians too. Like you don't hard code the way they behave, they learn how to behave in the same way I do have a hope was that Jack Dorsey talks about healthy conversations, He talked about uh meaningful interactions. I [/INST] believe </s><s>[INST] like simulating interactions so you can learn how to manage that is fascinating. So where most of your algorithm development happens on in virtual worlds and then you can really learn how to design the interface, how you design much of aspects of the experience in terms of the, how you select what's shown in the feed, all those kinds of things that it feels like if you can connect reinforcement learning to that that's super exciting. [/INST] And uh, I think if you have, if you have a company and leadership that believe in doing the right things and can apply this technology in the right way, some really special stuff can happen. It is mostly like likely going to be a group of people we've never heard about start up from scratch right? Um, and you asked if like new social networks could be built, I've got to imagine there will be and whoever starts, it might be some kids in a garage that took these classes from these people you write like and they're building all of these things with this tech at the core. So I'm trying not to be someone who just like throws around reinforcement learning as a buzzword. I truly believe that is the most cutting edge in what can happen in social networks. And I also believe it's super hard, like it's super hard to make it work. It's super hard to do it at scale. It's super hard to find people that truly understand it. So I'm not going to say that like I think it will be applied in social networks before we have true self driving. Yeah, we </s><s>[INST] can argue about this for a long time, but yes, I agree with you. So I think self driving is way harder than people realize. [/INST] Absolutely. </s><s>[INST] Let me ask you in terms of that kid in the garage or those couple of kids in a garage, what advice would you give to them if they want to start a new social network or a business, what advice would you give to somebody with a big dream and a young startup [/INST] to me, you have to choose to do something that even if it fails like you, it was so fun. Right? Like we never started instagram knowing it was going to be big. We started instagram because we loved photography, we loved social networks. I had seen what other social networks had done and I thought maybe we put a spin on this, but like nowhere was our feet predestined. Like it wasn't like it wasn't written out anywhere that everything was going to go great. I often think the counterfactual like what if it had not gone well it would be like, I don't know, that was fun. We raised some money, we learned some stuff and and does it position you well for the next experience, That's the advice that I would give to anyone wanting to start something today, which is like, does this meet with your ultimate goals? Not wealth, not fame? None of that. Because all of that, by the way is bullshit. Like you can get super famous and super wealthy and like I think generally those are not things that yeah, again, it's easy to say with like a lot of money that somehow, like it's not good to have a lot of money. It's just I think that complicates life enormously in a way that people don't fully comprehend. So I think it is way more interesting to shoot for. Can I make something that people love that provides value in the world that I love building that I love working on that, right? That's um that's what I would do if I were starting from scratch and by the way, like in some ways that I will do that personally, which is like choose the thing that you get up every morning. You're like, I </s><s>[INST] love this [/INST] even when it's painful, </s><s>[INST] even one is painful. What about a social network specifically if you were to imagine, put yourself in the mind and compete [/INST] against myself, I can't give out ideas, you </s><s>[INST] know, but it's like high level you like focus on community and yeah, [/INST] I, I said that as a, as a half joke um in all honesty, I think these things are so hard to build that like ideas are a dime a dozen, but </s><s>[INST] you have to talk about keeping it simple, [/INST] Can I tell you </s><s>[INST] which is a liberating idea? It's [/INST] three circles and they overlap one circle is what do I have experienced that? Such, what am I good at? I don't like saying what am I good at? Because it just seems like what do I have experiencing? Right? What can I bring to the table? What am I excited about? Is the other circle? What gets it's just super cool, right that I want to work on because even when this is hard. Um I think it's so cool, I want to stick with it and the last circle is like, what does the world need? And if that circle ain't there, it doesn't matter what you work on because there are a lot of startups that exist that just no one needs or very small markets need. But if you want to be successful. I think if you're like, if you're good at it, you have it, sorry if you're good at it, you're passionate about it and the world needs it. I mean it sounds simple, but not enough people sit down and just think about those circles and think do these things overlapping and can I get that middle section? It's small, but can I get that middle section? Um I think a lot about that personally, </s><s>[INST] and then you have to be really honest about the circle that you're good at and really honest about the circle that the world needs. And I suppose really honest about the passion. Like what do you actually love? Yeah. As opposed to like some kind of dream of making money, all those kind of stuff. Like literally love [/INST] do I had a former engineer who decided to start a startup and I was like, are you sure you want to start a company versus like join something else? Because um being a coach of an NBA team and playing basketball are two very, very different things and like not everyone fully understands the difference. I think you can kind of do it both. Um And I don't know, jury's out on that one because like they're in the middle of it now, so, but it's really important to figure out what you're good at. Not be full of yourself, truly look at your track record. Um What's the saying? Like it ain't bragging if you could, if you can do it. Um But too many people are delusional and like think they're better at things than they actually are or think there's a bigger market than there actually is just when you confuse your passion for things with a big market. That's really scary, right? Like just because you think it's cool, doesn't mean that it's a big business opportunity? So like what evidence do you have again? I'm a fairly like I'm a strict rationalist on this and like sometimes people don't like working with me because I'm pretty pragmatic about things like I'm not, I'm not feeling like I don't sit and make bold proclamations about visiting mars like that's just not how I work. I'm like, okay, I want to build this really cool thing that's fairly practical and I think we could do it and it's in this way. And what's cool though is like, that's just my sweet spot. I'm not like I just, I can't, I can't with a straight face talk about the metaphors. I can't, I just, it's not me. What </s><s>[INST] do you think about the facebook we're naming? It seems [/INST] to me that is a dig. I just like, I'm fairly, I like to live in the next five years and like what, what things can I get out in a year that people will use that scale. And um so it's just again, those circles I think are different for different people, but it's important to realize that like market matters you being good at it matters and having passion for it matters your question. Sorry? </s><s>[INST] Well unless less on this topic in terms of funding is there by way of advice? Mhm. Was funding in your own journey helpful unhelpful like, is there a right time to get funding? Venture funding or anything boss? Some money from your parents? I don't know what you like. Is money get in the way, Does it help? Is the timing important? Is there some kind of wisdom you can give there because you were exceptionally successful very quickly? [/INST] Funding helps? As long as it's from the right people that includes yourself. And I'll talk about myself funding myself in in a second, which is like, because I can fund myself doing whatever projects I can do, I don't really have another person putting pressure on me except for myself. And that creates strange dynamics, right? But let's talk about people getting funding from a venture capitalist initially, uh we raised money from matt Cohler at benchmark, it's brilliant, amazing guy, very thoughtful and he was very helpful early on, but I have stories from entrepreneurs where they raised money from the wrong person or the wrong firm where incentives weren't aligned, they didn't think in the same way. Um and bad things happen because of that. The border room was always noisy. There were fights like that. We just never had that matt was great. I think you like Capital these days. It's kind of a dime, a dozen, right? Like as long as you're fungible like it seems like there's money out there. This is what I'm hearing. Um it's really important that you are aligned and that you think of raising money as hiring someone for your team rather than taking money if capital is plentiful, right? It provides a certain amount of pressure to do the right thing that I think is healthy for any startup and it keeps you real and honest because they don't want to lose their money, they're paid to not lose their money. The problem, you know, maybe I could depersonalize it, but like I remember having lunch with Elon, it's only happened once, and I asked him like, I was trying to figure out what I was doing after instagram, right? And I asked him something about like angel investing and he looked at me with a straight face and was like, why the f would I do that? Like why? Like it was like, I don't know, like you're connected. Like seems like he's like, I only invest in myself. I was like, okay, you know, like not the confidence. I was just like, what a novel idea. It's like, yeah, if you have money, like why not just put it against your bag and like enable your visiting mars or something, right? Like that's awesome. Great. But I had never really thought of it that way. But also with that comes an interesting dynamic where um you don't actually have people who are going to lose that money telling you, hey don't do this or hey, you need to face this reality. So you need to create other versions of that truth teller. Mhm. And I whatever I do next, that's going to be one of the interesting challenges is how do you create that truth telling situation? Um And that's part of why, by the way, I think someone like Jack when you start square you have money but you still you bring on partners because I think it creates a truth telling type environment. Um I'm still trying to figure this out. Like I like it's an interesting, it's an interesting dynamic </s><s>[INST] today. You're thinking of perhaps launching some kind of venture where you're investing in yourself. I mean [/INST] I'm 37 going on 38 next month. I have a long life to live. I'm not definitely not going to sit on the beach, right? So I'm gonna do something at some point. And I got to imagine I will I will like help fund it, right? So the other way of thinking about this is you can park your money in the SNP and this is bad because the S. And P. S. Done wonderfully well last year, right? Or you can invest in yourself. And um if you're not gonna invest in yourself, you probably shouldn't do a startup. It's kind of the way of thinking about it </s><s>[INST] and you can invest yourself in the way Ellen does which is basically go all in on this investment. Maybe that's one way to achieve accountability is [/INST] like you're kind of screwed </s><s>[INST] if you're if you fail. Yeah that's. [/INST] Yeah </s><s>[INST] I personally like that like burning bridges behind me so that I'm fucked if it fails, [/INST] uh It's really important though. One of the things I think Mark said to me early on that, that sticks with me that I think is true. We were talking about people who had left like operating rules and started doing venture or something. He was like, a lot of people convince themselves they work really hard, like they think they work really hard and they put on the show and in their minds they work really hard, but they don't work very hard. There is something about lighting a fire underneath you and burning bridges such that you can't turn back that I think, you know, we didn't talk about this specifically, but I think you're right, there is, you need to have that because there's a self delusion at a certain scale. Oh, I have so many board calls, oh, like we have all these things to figure out. Like this is one of the hard parts about it being an operator. It's like there are so many people that have made a lot of money not operating but operating. It's just one of the hardest things on earth. It is just so effing hard, is stressful. It is you're dealing with real humans, not just like throwing capital and and hoping it grows. I'm not undermining the VC mindset. I think it's a wonderful thing and needed and so many wonderful vcs I've worked with, but yeah, like when you're asses on the line and it's your money, it's, But to me in 10 years, </s><s>[INST] we'll see how it goes. Yeah. But like you're saying that as a source when you wake up in the morning as uh, and you look forward to the day full of challenges. That's also where you can find happiness. Let me ask you about love and friendship. What's the role in this heck of a difficult journey you've been on of love of friendship was through all of love and the human condition? [/INST] Well, first things first, the woman I married my wife, Nicole. No way I could do what I do if we </s><s>[INST] weren't together, she had to filter idea. [/INST] Exactly. We didn't </s><s>[INST] go over that story. [/INST] Um, everything is a partnership, right? And to achieve great things. It's not about like someone pulling their weight in places, it's not like someone supporting you so that you could do this other thing. It's literally like, you know, mike and I and our partnership as co founders, it's fascinating cause I don't think instagram would have happened without that partnership, like either him or me alone. No way we pushed and pulled each other in a way that allowed us to build a better thing because of it. Nicole. Sure. Like she pushed me to work on the filters early on and yes, that's a, it's a fun story, right? But the truth of it is being able to level with someone about how hard the processes and have someone see you for who you are before instagram and know that there's a constant you throughout all of this and be able to call you when you're drifting from that, but also support you when you're trying to stick with that. That's, I mean that's as true friendship slash love, whatever you wanna call it. Um, but also for someone not to care. I remember Nicole saying, hey, like I know you're gonna do this instagram thing. You should, I guess it was bourbon at the time. You should do it because um, even if it doesn't work, we can move to a smaller apartment and it'll be fine, we'll make it work. How beautiful is that? </s><s>[INST] Right? It's almost like a superpower that gives you permission to fail and somehow that actually leads to success. [/INST] But also she's like the least impressed about instagram of anyone. She's like, yeah, that's great. But like I love you for you. Like, I like that you like a decent cook. Beautiful. It's </s><s>[INST] beautiful with the, with the gant chart and thanksgiving, which I still think is a brilliant, I think idea. Uh big ridiculous question. Have you, uh, you're, you're old and wise at this stage. So have you discovered meaning to this whole thing? Why the hell are we descendants of uh apes here on earth? What's the meaning of it, what's the meaning of life. [/INST] I haven't and I am. So the crazy said the best learning for me has been like, no matter what level of success you achieve, you're still worried about similar things, just maybe in a slightly different scale, you're still concerned about the same thing, You're still self conscious about the same things as like and actually that moment going through that is what makes you believe there's got to be like more machinery to life or purpose to life and that, that we're all chasing these materialistic things, but you start start realizing like um it's almost like, you know the Truman show when he gets the edge and he knocks against it, he's like, what? Like there's this awakening that happens when you get to that edge that you realize, oh, like sure it's great, it's great that we all chase money and fame and success. You hit the edge and I'm not even claiming I had an edge. Like Elon's hit an edge, like there's clearly larger scales, but what's cool is you learn that like it doesn't actually matter and that there are all these other things that truly matter. Um that's not a case for working less hard, that's not a case for taking it easy. That's not a case for the four day work. We what that is a case for is designing your life exactly the way you want to design it because I don't know, I think we go around the, you know the sun a certain number of times and then we die and then that's it, </s><s>[INST] that's me. Are you afraid of that moment? [/INST] No, not at all. In fact at </s><s>[INST] least not yet. [/INST] Listen, I'm like a pilot, like I do crazy things and I like um no, like if anything, I'm like ooh I got to choose uh mindfully and purposefully the thing I am doing right now and not just fall into it because you're going to wake up one day and ask yourself why the hell you spent the last 10 years doing X, </s><s>[INST] y or Z. [/INST] So I guess my like shorter answer to this is doing things on purpose because you choose to do them so important in life and not just like floating down the river of life, hitting branches along the way because you will hit branches right? But rather like literally plotting a course and not having a 10 year plan, but just choosing every day to opt in that I think has been more like I haven't figured out the meaning of life by any stretch of the imagination, but it certainly isn't money and it certainly isn't fame and it certainly isn't travel and it's like and it's way more of like opting into the game you love playing </s><s>[INST] every day opting in [/INST] just opting in and like don't let it happen to you opt in </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] A thing. Not a personality based one... Can it be both? Anyway but let's... Nooo. We have nothing to do with... Back to Iran? [/INST] No. It has nothing to do with Rothbard. Back to it. It has nothing do with Rothbard. You don't know that. You're not a psychic or a necromancer. You didn't know that. The only way we're going to resolve this is our wrestling. Right? It's through violence. Our wrestling is not violence. Okay. Words are violins, areas are violins. Words are violins. Words are violins. grassroots killer emotions are violins. Wait, what's... He throws me off with his stuff. That's the problem. He's very, very good and not fact or truth. I mean, there's distortions and arbitrary statements because your statement about Rothbard is an arbitrary statement that has no cognitive standing and therefore, I can dismiss it, so, I'm not doing like this, because I want... It has no cognitive status. The fact that she disliked Rothbard Doesn't mean that everything he said she was going to dismiss because she just thought It has no I agree with you. But what I'm saying is it would not be impossible, but there's no evidence. I'll give you some talk I'll give you some evidence as human psychology. It is not impossible That if you hate some what's his name? What's that guy's name? Right. It's not impossible that if Richard Wolff said something that you would otherwise agree with you hold on Let me finish you'd be dismissive or less likely to give him credit for it being a human being that's all I'm saying It's as silly as to say what but came up with his theory of anarchy Because he he he was pissed off at Ayn Rand and wanted to write some I don't know </s><s>[INST] Yeah, bring it down because bring it down so that he can speak to and let's let's let's keep it because I don't think I'm getting agitated. No, you guys aren't no Yeah, yeah, yeah, no bring it down not in terms of in terms of a give more pauses Oh, okay, Michael can insert himself. That's what I mean. See private government which is that five or no? [/INST] I know you guys aren't no Okay, see private government point of that private nit </s><s>[INST] this is Geographic law of the lens point I I do think that Michaels I mean that's interesting that you disagree with this No, not, look, it's private governance. It's multiple private governance. I'm trying to establish this geographic law of the land. That's not a point. I do think that Michael's, I mean, that's interesting that you disagree with this. I do believe that psychology has an impact on ideas and Ayn Rand, you don't think Ayn Rand had grudges that impacted the way she saw the world? [/INST] I woo with the law of the land, I don't know. I like to think that. I don't think any of her grudges entered into philosophical statements, at least not that I can tell and I don't see, and given the centrality Ayn Rand gave to the role of government, to the existence of government, and to the need for government to established real freedom and the way she defines freedom, which is very different than Rothbard and the way she defines government to say, then, that her opposition to anarchy is because of, I think is just an arbitrary- I didn't say because of. I didn't say because, I said colored by. And I don't see why psychology would enter it. Now, maybe the tone in which you responded to answer might have been motivated by that or something like that. But given the amount of thought she gave to the world of government and human society and why government was needed and why you needed laws in order to be free, that freedom didn't proceed, you needed the right hierarchy. I think that we could say that it, given at least the respect that she, this was, she might have been wrong, but she had a particular theory that rejected anarchy and the thought anarchy was wrong. Okay, hold on. I didn't say because of. And not. I didn't say because, I said colored by. Okay, hold on. I really resent, and I don't want to say you're doing this, the implication that if Rand was guided by her passions, that somehow is the criticism of her or lessens her. I think Rand was a very passionate person. I think she loved her husband enormously. She despised certain people enormously, and I don't think that there's anything wrong with that. Don't think she would change her philosophical position about something because she disliked somebody. I agree, but what I'm saying. Given the amount of thought she gave to that philosophical position. All I'm saying is it is possible that if someone comes across ideas that she had not considered before, if she regarded this person as a bad actor, like all of us, she would be less likely to take them under consideration. Sure. That's all I'm saying. Sure. That's all I'm saying. Sure. And I think other people confronted her with ideas of anarchy, I don't think Rothbard was the only one. Correct, Roy Charles as well. Yeah, Roy Charles certainly did. And she rejected them, and she rejected them because she had, and whether you agree with her or not, she had a thought out position about why you needed to have this particular structure in place so that markets and human freedom could exist. It's just really interesting because this is the one time, in my view, and please correct me if I'm wrong, where she invokes need as a basis for political activity. Let's suppose you want this federal government, whatever you want, you don't want it like it is now, like your version of the government. I don't see why it's an issue for you, for me and Lex, to say, we're not privy to Washington, we're going to do our own thing. And given if we go about our lives not initiating force and being productive actors, why she would have an issue with this? Why would I care? Well, you would care because if you're saying the government has a monopoly on force between these two oceans- You can do that as long as you don't violate somebody else's rights. Sure, but what I'm saying is we just declare ourselves sovereign, we're not going to pay any income taxes, we're going to be peaceful people, and when Lex and I have disputes, we're going to call Joe. That's Joe Rogan. You're never going to get to meet him, but he's a good guy. I know. You can do that as long as you don't buy- We're going to call Joe, and Joe's going to resolve it between us. He's so good at needling and getting you off topic that way. He's really effective at it. He's a commoner in your show- I always say when I debate communists, I always say to them- You mean Lex? Yeah, maybe Lex. Maybe I should do the same. Comrade, I love you. Comrade, I love you. That if they really believe- Burgundy, not red. If they really believe in what they think, then they should be advocates of capitalism because under capitalism, under my system of government, capitalist government, they could go and start a commune. They can live in copy notes. live to each according to his needs, from each according to his ability, all they want and live their pathetic miserable lives that way. And the government would never intervene because the whole view of capitalism is freedom, is we live in the real world. As long as you're not violating my rights, as long as you're not taking my property, as long as you're not engaging. So in that sense, yeah, you and Lex can form your own thing. I don't believe in compulsory taxes anyway. So you and Lex can do your own thing, never pay taxes. As long as you're not violating the laws, and the laws are very limited, right? Because they're only there to protect individuals. So as long as you're not violating somebody else's property rights or inflicting force on anybody else, you're peaceful. You can do what you want. Don't have sex with kids. I will stop immediately. </s>
<s>[INST] the following is a conversation with Peter Nordvig. He's the director of research google and the co author with Stuart russell of the book artificial intelligence and modern approach that educated and inspired a whole generation of researchers, including myself, to get into the field of artificial intelligence. This is the artificial intelligence podcast. If you enjoy it, subscribe on Youtube, give five stars in itunes, support on Patreon are simply connect with me on twitter. Elex Friedman spelled F R I D M A N. And now here's my conversation with Peter Narvik. Most researchers in the AI community including myself own all three editions, red, green and blue of the artificial intelligence, a modern approach, a field defining textbook. As many people are aware that you wrote with Stuart Russell. How is the book changed and how have you changed in relation to it? From the first edition to the second to the third and now, fourth edition, as you work on [/INST] it. So it's been a lot of years, a lot of changes. One of the things changing from the first to maybe the second or third was just the rise of computing power. Right? So I think in the in the first edition we said uh here's predicate logic, but that only goes so far because pretty soon you have millions of short little Medicaid expressions and they couldn't possibly fit in memory. Uh so we're going to use first order logic. That's more concise. And then we quickly realized, oh, Predicate logic is pretty nice because there are really fast sat solvers and other things. And look there's only millions of expressions and that fits easily into memory or maybe even billions fit into memory now. So that was a change of the type of technology we needed just because the hardware expanded </s><s>[INST] even to the second editions. And resource constraints from loosened significantly [/INST] second. And that </s><s>[INST] Was early 2000's 2nd edition. [/INST] Right? So 95 was the first and then uh 2000 2001 or so. And then moving on from there, I think we're starting to see that again with the GPU s and then uh more specific type of machinery like the TP us and you're seeing custom a six and so on uh for deep learning. So we're seeing another advance in terms of the hardware. Then I think another thing that we especially notice this time around is in all three of the first editions, we kind of said, well we're gonna find a i as maximizing expected utility and you tell me your utility function. And now we've got 27 chapters were the cool techniques for how to optimize that. I think in this edition we're saying more, you know what maybe that optimization part is the easy part and the hard part is deciding what is my utility function, what do I want. And if I'm a collection of agents or society, what do we want as a whole. </s><s>[INST] So you touch that topic in this edition, you get a little bit more into utility. [/INST] Yeah, that's </s><s>[INST] really interesting on a technical level or almost pushing the philosophical, [/INST] I guess it is philosophical. Right? So we we've always had a philosophy chapter which which I was glad that we were supporting. And now it's less kind of the uh you know, chinese room type argument and more of these ethical and societal type issues. So we get into uh the issues of fairness and bias and uh and just the issue of aggregating utilities. </s><s>[INST] So how do you encode human values into a utility function? Is this something that you can do purely through data in a learned way? Or is there some systematic Obviously there's no good answers yet there's just beginnings to this uh even opening majority. [/INST] So there is no one answer. Yes. There are techniques to try to learn that. So we talk about inverse reinforcement learning, right? So reinforcement learning uh you take some actions, you get some rewards and you figure out what actions you should take. An inverse reinforcement learning, you observe somebody taking actions and you figure out well this must be what they were trying to do if they did this action. It must be because they wanted. Of course there's restrictions to that. Right? So lots of people take actions that are self destructive or their sub optimal in certain ways. So you don't want to learn that you wanna somehow learn the perfect actions rather than the ones they actually take. So so that's a challenge for that field than another big part of it is just kind of theoretical of saying what can we accomplish? And so you look at like this this work on the programs to uh predict recidivism and decide uh who should get parole or who should get bail or whatever. Uh and how are you going to evaluate that? And one of the big issues is fairness across protected classes. Protected classes being things like sex and race and so on. And uh so two things you want is you want to say, Well if I get a score of say uh six out of 10, Then I want that to mean the same whether no matter what race I'm on, right? So I want to have a 60% chance of uh re occurring regardless. Uh huh. And the makers of the uh one of the makers of a commercial program to do that says that's what we're trying to optimize. And look, we achieved that we've we've reached that kind of balance. And then on the other side, you also want to say uh well, if it makes mistakes, I want that to effect both sides of the protected class equally. And it turns out they don't do that, right? So they're twice as likely to make a mistake that would harm a black person over a white person. So that seems unfair. So you'd like to say, well, I want to achieve both those goals. And then turns out you do the analysis and it's theoretically impossible to achieve both those goals. So you have to trade them off one against the other. So that analysis is really helpful to know what you can aim for and how much you can get that. You can't have everything. But the analysis certainly can't tell you where should we make that trade off point? </s>
<s>[INST] Yeah, but so yeah, sticking with the representative and basically the american system of regulation and markets and the economy will have going on is a pretty good one for mars. [/INST] If you start from scratch. If you don't start from scratch, you wouldn't, you wouldn't want to send it where 16% of the population has half the seats. Uh you probably would want one, which is, you know more actually more representative than what we have. Um and the details. It's unclear. I mean, the uh we uh when times are good, all of the various Representative democracy systems, whether it's um uh parliamentary democracies or a US style system, whether you have a prime minister or the head of state has an elected president. They all kind of work well and they all when times are good and they all have different modes of breakdown. So I'm not sure I know what the answer is but but something like that uh is given what we've seen through history. It's the least bad system out there. I mean I don't know. Uh huh. Yeah if you uh I'm a big fan of the tv series, the expanse and it's kind of gratifying that out there. The uh it's the martian congressional Republic. Okay </s><s>[INST] in a brief sense, so amongst many things, you're also an expert at international trade. What do you make of the complexity? So I can understand trade between two people say to neighboring farmers, it seems pretty straightforward to me but international, we need to start talking about nations and nations trading seems to be very complicated. So from a high level why is it so complicated? What are all the different factors that way? The objectives need to be considered an international trade and maybe feeding that into a question of um do you have concerns about the two giants right now of the U. S. And china and the intention that's going on with international trade there with the trade war? Well, [/INST] first of all, international trade is not really that different from trade among individuals. It's it's vastly more complex and there there are many more players. But in the end the reasons why countries trade are pretty much the same as the reasons why individuals trade countries trade because they're different and they can um derive mutual advantage from concentrating on the things they do relatively well. And um also there are economies of scale. You know you don't not uh individuals have to decide whether to be a surgeon or a uh or an accountant is probably not a good idea to try and be both in countries benefit from specializing uh just because of the inherited advantages of specialization. And that's so now the fact it's a big world and uh they were talking about millions of products being traded and in today's world often uh trade involves many stages. So that made in china iphone is actually assembled from components that are made all over the world. Uh But it doesn't really change the fundamentals all that much. Um There is a recurrent. I mean the bake the big the dirty little secret of international trade conflict is that actually it's not conflicts among countries are really not that important. Most trade is beneficial to both sides and uh to both countries. But it has big impacts on the distribution of income within countries. So uh the growth of U. S. Trade with china has made both U. S. And china richer. But it's been pretty bad for people who were employed in the north Carolina furniture industry who did find that their jobs were displaced by a wave of imports from china? And so that's where the complexity comes in. Um Not at all clear to me. I mean, they we have some real problems with china. They don't really involve trade so much as, as things like um respect for intellectual property. Uh not clear that those real problems that we do have with china have anything to do with the current trade war, Current trade war seems to be driven instead by a fundamentally wrong notion that when we sell goods to china that's good and when we buy goods from china, that's bad and that's that's misunderstanding. The whole point </s><s>[INST] is a trade with china and both directions a good thing. [/INST] Yeah, we would be poor if it wasn't for it. But but there are there are downsides as there are for any economic change. It's like any new technology makes us richer, but often hurts some, some people trade with china makes us richer but hurt some people. And uh I wouldn't undo what has happened, but I wish we had had a better policy for uh supporting and compensating the losers from that growth. </s><s>[INST] So we live in a time of radicalization of political ideas, Twitter mobs and so on. And yet here you are in the midst of it, both tweeting and writing in new york times articles with strong opinions riding this chaotic wave of public discourse. Do you ever hesitate or feel a tinge of fear for exploring your ideas publicly and unapologetically, [/INST] oh, I feel fear all the time. Uh it's not too hard to imagine scenarios in which this is gonna, you know, I might personally find myself uh kind of in the in the crosshairs. Uh huh. I mean I am the king of hate mail, I get them amazing correspondence. Uh um </s><s>[INST] does it affect you? [/INST] It did it did when it started these days? I've I've developed a very thick skin. Uh so I I know I don't usually get in fact if I if I don't get a wave of hate mail after a column, then then I probably wasted the that that day. </s>
<s>[INST] Yeah, it's for us that like final Air or some particular layer is very important. The one that tells us that it's our dog or like it's a cat or a dog. But, you know, each layer is probably equally as important in the grand scheme of things. Like there's no reason why the cat versus dog is more important than the lower level activations. It doesn't really matter. I mean, all of it is just this beautiful stacking on top of each other and we humans live in this particular layers. For us. For us it's useful to to survive to to use those cat versus dog predator versus prey, all those kinds of things. It's fascinating that it's all continues. But then you then ask, you know, the history of artificial intelligence you ask, are you able to introspect and convert the very things that allow us to tell the difference the cat and dog into uh logic into formal logic. That's been the dream, I would say that's still part of the the dream of symbolic ai and um I've recently talk to Doug Leonard who created psych and that's that's a project that lasted for many decades and still carries a sort of dream in it, right? Um we still don't know the answer, right? It seems like connection is um is really powerful, but it also seems like there's this building of knowledge. So [/INST] how do we </s><s>[INST] how do you square those two? Like do you think the connections can contain the depth of human knowledge and the depth of what uh Dave Rummelhardt was thinking about of understanding? [/INST] Well that remains the $64 question. And um </s><s>[INST] with inflation that [/INST] Number, </s><s>[INST] dollars, maybe [/INST] It's a $64 billion uh uh you know, I think that um yeah, from the emergent aside which, you know, uh I placed myself on. So I I used to sometimes tell people I was a radical eliminated connection ist because I didn't want them to think that I wanted to build like anything into the machine. But I don't like the word eliminated, I've uh anymore because it makes it seem like it's wrong to think that there is this emergent level of understanding and um I disagree with that. So I think you know, I would call myself an a radical emergent ist uh connection ist rather than eliminated connection ist right? Because I want to acknowledge that that these higher level kinds of aspects of our cognition are are real, but they're not, they don't they don't exist as such. And so there was an example that Doug Hofstadter used to use that I thought was helpful in this respect. Just the idea that we can think about sand dunes as entities and talk about like how many there are even. Um but we also know that a sand dune is a very fluid thing. It's it's it's a it's a it's a pile of sand that is capable of moving around under the wind and and and um you know, reforming itself in somewhat different ways and and if we think about our thoughts is like sand dunes as being things that you know emerged from uh just the the way all the lower level elements sort of work together and are constrained by external forces, then we can we can say yes, they exist as such, but they also, you know, we shouldn't treat them as completely monolithic entities that we we can understand without understanding sort of all of the stuff that allows them to change in the ways that they do and that's where I think the connection ist feeds into the into the cognitive, it's like, okay, so if the under if the substrate is parallel distributed connection ist um then it doesn't mean that the contents of thought isn't you know like abstract and symbolic and but it's more fluid maybe than uh is easier to capture with a set of logical </s><s>[INST] expressions. Yeah, that's a heck of a sort of thing to put at the top of a of a resume radical emergen ist connection ist. So there is just like you said, a beautiful dance between that between the machinery of intelligence, like the neural network side of it and the stuff that emerges. I mean the stuff that emerges seems to be um I don't know, I don't know what that is that it seems like maybe all of reality is emergent. What I what I think about this has made most distinctly rich to me when I look at cellular Tamina look a game of life that from very, very simple things, very rich, complex things emerge that start looking very quickly like organisms that you forget that forget how the actual thing operates, they start looking like that moving around, they're eating each other. Some of them are generating offspring. You forget very quickly. And it seems like maybe it's something about the human mind that wants to operate in some layer of the emergent and forget about the mechanism of how that emergency happens. So it's just like you are in your radicalness. I'm uh also it seems like unfair to eliminate the magic of that emergent? Like eliminate the the fact that that the emergence is real. [/INST] Yeah, no, I agree. I'm not that's why I got rid of eliminated. </s><s>[INST] Right? Yeah. [/INST] Because it seemed like that was trying to say that, you know, it's all completely like </s><s>[INST] an illusion of some kind of, well, [/INST] it, you know, who knows whether there isn't, there aren't some illusory characteristics there. Um, and and I think that philosophically, um, many people have have confronted that possibility over time, but, but uh, it's still important to, um, you know, accept it as magic, right? So, you know, I think of Fellini in this context. I think of others who have appreciated uh, the role of magic of actual trickery in creating illusions that that move that move us. You know, And Plato was onto this too. It's like somehow or other these shadows, you know, give rise to something much deeper than that. And that's that's so, you know, we won't try to figure out what it is. We'll just accept it as given that that that occurs. And um, you know, but he was still on to the magic of </s>
<s>[INST] So it's cool with a warm blanket, just like when you have a cold ice cream with hot chocolate on top. The mixture between cool and warm is heaven. That's the best way I can put it. Any way you can go to eight sleep dot com slash lex to check out their prod pro cover and save 200 bucks at checkout. Eight sleep currently ships within the U. S. Of a Canada and the United Kingdom. That's a sleep dot com slash lex. This is the lex Fridman podcast to support it. Please check out our sponsors in the description and now Dear friends, Here's Salma Gonzalez. [/INST] You said that you did a lot of reading when you were growing up and you mentioned fear and loathing in las Vegas by hunter? S Thompson. So from the reading you've done in those early days, how did you see the world? Was it to you a beautiful place or a cruel </s><s>[INST] place? [/INST] I don't think I thought about the world. You were focused on family just basic day to day life. I think I was focused on day to day, had an awareness of not fitting in. But I think back then it felt like something was wrong versus some people are just that way. And speaking of books I read a book called um party of one by a woman named Anneli Rufus that somebody gave me and suggested I read and that helped a lot. That was, that was one book that made me feel like it made me understand things from the past that I hadn't understood before, specifically kind of feeling out of place, even among my family, which is where you're not supposed to feel out of place. Yeah, I'm not sure where I saw it, but I think you mentioned that you were a bit of a loner and I also think I saw somewhere pictures of you with with green hair in high school and a wild haircut. Was that about? Is that is that real? Am I just imagining No, you're not imagining it. It's strange because I was kind of a loner. So it would be strange to do something that calls so much attention to yourself because back then, I mean I grew up in a suburb of boston um in Newton and anybody that was there around that time probably if you said you know that girl with green hair, blue hair was blue. Most of the time they would remember like seeing me walking down the street because it stood out like crazy, especially back then now it wouldn't stand out so much, but back then it really stood out. So I was trying to think about why I did that when I was kind of a kind of shy and on the one hand wouldn't want to bring attention to myself, but I did something that did um and it wasn't my family to their credit, they were fine with it, so it wasn't a rebellion against them or anything like that, they were fine with it, I don't think they loved it. But your dad was a physicist at M. I. T. Yes, so uh so he he was he was cool here with your green hair when your rebellion, that's just the way of life. He was fine with the green hair, </s><s>[INST] but I think in [/INST] some ways maybe they had to be fine with it because I didn't cause problems otherwise and I got good grades in school. I was a very low maintenance child, I think </s><s>[INST] even with the green hair. [/INST] Uh so Hunter? S Thompson wrote a lot of good stuff, he has a lot of just brilliant quotes, a lot of brilliant lines. Um So one of the ones I love is life should not be a journey to the grave with the intention of arriving safely in a pretty and well preserved body, but rather to skid in broadside in a cloud of smoke, thoroughly used up, totally worn out and loudly proclaiming, wow, what a ride, What do you think about that? Is that good life advice from Hunter? S Thompson? I think so, I think he followed it right somewhere. Um I heard recently what he consumed in a day and it was kind of astonishing. It's funny when I was in college, they were always really interesting people coming through speakers and whatnot, and I tended to not go to events and whatnot, but in the four years I was there, I mean really interesting people came through and gave talks, you know, I don't know, just a lot of famous people. And um but then one day, Hunter? S Thompson came to speak and it was the only one I attended was the only interesting person who came to speak on the campus that I attended was Hunter? S Thompson and he had a, you know, he had a glass of whatever it was, whiskey and I don't remember a whole lot about it, but it was, it was entertaining and yeah, I mean later in his life he started making less and less sense, but he was still somehow like embodying the crazy that he represented throughout his life, the boldness, this fearlessness, the wildness, all that kind of stuff. And we'll talk about johnny Depp a little bit too funny enough. There's like a echo, obviously he johnny Depp played him or he started unloading and they hung out together and it just seemed to somehow like the universal rhymes in these two individuals, they're both mad men and in different kind of ways. So you also told me that leon the professional is one of your favorite films. It's also the reason you named your dog leon. So what do you find beautiful and powerful about this film? I've watched it a bunch of times, but it's been a while since I've watched it. Um so for people who haven't watched it, there's a guy named leon played by john, you know, there's a Um a young girl 13 14 Matilda played by Natalie Portman and she's abused, She has a really hard life, Her parents are spoiler alert uh murdered and then she finds protection under this um fella uh leon who's also happens to be a professional assassin and he is also kind of a forrest gump type character, like he's a really simple, simple human. Um he almost, he seems to be like the immature one or like rather the one who is young and she seems to have a wisdom far beyond her age because of the hard life she had to live through and then, and then they're here huddling together from the cruelty of the world um in and finding connection. Yeah, I think it's one of those films where there's so many interesting things about it, but you know, I'm sure one of them is just the contradiction of him being a caring person and reluctant to get attached to her. You know, he tries to, I think he knows he's he's very reluctant to get attached to her in the beginning. Um and so you see all of his humanity, but yet he's also an assassin that kills people. So um that's interesting and I think probably a psychoanalyst would have a field day with why I like that so much. Um and I haven't, I haven't gone there myself, but there's something I think about she, even in the brief part that depicts her in the beginning, it seems clear that she's sort of out of place in her family. Um and um and then yeah, there's all kinds of interesting things about their relationship along the way, what I like about that movie and I had to think about it recently because I've read stuff about it that bothered me or it bothered me the fact that I haven't really thought about it before for people haven't watched the movie. So here's a young underage girl who kind of comes on to him. First of all, I think she actually just doesn't know what like familiar love is. So this is the only way she knows how to express love. That's one and two is, you know, a lot of bad people in this world would take advantage of that, right? And the fact that um she finally met a human being who doesn't and is just there to protect her. That's a real sort of um I don't know, a powerful statement of what it means to be sort of like a father figure, I suppose a protector. So that that to me, I I love the idea of being sort of the protector. That there's something like uh something worthwhile in this world to protect amidst all the cruelty that's all around. That's that's a beautiful kind of you're basically saving this young humans or you're repairing this young humans path to love to real love in life. Because that idea of love was destroyed for her just family. Everything is is everything is uh sort of everything around is broken. And he's kind of repairing it by reestablishing what that kind of love can be. I don't know. And the plant they they saved the plant also. Well there's also just a simple the simplicity of the film. Just some cinematic perspective is beautiful, the music, the way it looks, the minimalism, even the violence was beautiful. Yeah, violence. It was over the top and also the bad guy, the bad cop played by um Gary Oldman. Yeah, I think he was listening to Beethoven or something like that and you're taking some sort of pills and drugs and some kind and uh so there was a kind of like, like like it's part of the orchestra. Like the violence was part of the of some kind of musical creation. Yeah. It's interesting because I turn away from violence or films usually that have violence or tv or anything that has that sort of um element to it except in certain cases where um where the violence is beautiful. Yeah. Yeah. Or um </s><s>[INST] did [/INST] you see the movie True Romance? Uh Yes, that's my second favorite movie. Okay that's probably my favorite movie. Oh well interesting. That's my second favorite movie. Um that's that's a more simple kind of love but also with the violence that is beautiful you could say. Yeah. And my um my favorite scene is the one with Patricia Arquette and James Gandolfini. Oh yeah. Was she? There's a shotgun involved. Yeah. Yeah. And then it actually makes me cry every time I see it for some reason. So for people who haven't seen the film I think I think he's actually he think he's hitting her or um like there's blood and violence and so on because she's resisting being murdered. Yeah there's a lot of violence and then you know he throws her into the glass um the shower thing and she's all cut up and beat up and she laughs. Yeah, there's just so much passion in it. You know, she's she knows she's gonna or in that moment she knows or thinks she knows that she's going to die anyway because she she knows he's going to kill her. So she kind of gives it her gives it all she has and um but she also just has guts, she's not afraid. Yeah. Well, and also she's um you know, she loves Clarence. Yeah. The love comes through through that violence. Yeah. Just like Clarence. Her fellow in that film has the same kind of thing when he visits. It's Gary Oldman again, it was Gary Oldman again. That's right. The pimp Drexel. Yeah. And he's also fearless in that interaction saying she's not mine. It's interesting that movie is so romantic and that happy ending. Spoiler alert and that's what I like about it too, because I feel like some movies should come with, I don't want to watch a movie if it's gonna be devastating usually. Unless it's worthwhile in some other way, but I'm kind of sensitive and I don't want um I don't like </s>
<s>[INST] Austin. Thanks, thanks for listening to this conversation with Scott Aaronson and thank you to our sponsors eight Sleep, simply safe express VPN and better help please check out these sponsors in the description to get a discount and to support this podcast. If you enjoy this thing, subscribe my Youtube, review it with five stars on Apple podcast, follow on Spotify, support on Patreon or connect with me on twitter Elex Friedman and now let me leave you with some words from Scott Aaronson that I also gave to you in the introduction, which is if you always win, then you're probably doing something wrong. Thank you for listening and for putting up with intro and outro in this strange room in the middle of nowhere, in this very strange chaos of a time we're all in and I very much hope to see you next time In many more ways than one. [/INST] </s>
<s>[INST] Well, it could be, you know, you could have the Ernest Becker theory of denial of death where at the core of that the warm of the core, as young said, is the fear of death. So were the longing for the perfect thing. It has to do with sort of becoming immortal is um reaching beyond the absurdity, the cruelty of life that all things come to an end for, for no particularly good reason whatsoever. One we can rationally explain. [/INST] I know, you know, I wonder about that all the time. Like I know obviously there's that idea from Becker and throughout philosophy and the tale of Gilgamesh about the idea that the thing we're longing for most of all is immortality, </s><s>[INST] but [/INST] I feel like it's not only that, I think it's more so or also let's say, um, a longing for the lions to lay down with the lambs. Finally, you know, for like the, the fundamental calculus of the universe to be different where life doesn't have to eat life in order to survive. And yeah, just a completely different situation, immortality would not solve. </s><s>[INST] I wonder that could be a very kind of modern thing because surely so much of human history is defined by violence and glorified violence. That doesn't give inklings of this lions and the lambs so much. Yeah, I [/INST] mean, I know all the other stuff is in the bible, </s><s>[INST] there's other stuff in the bible and the bible and that particular aspect doesn't necessarily reveal the fundamental motivation of human nature. That could be deeper stuff, you know? But yeah, that is a beautiful, that is a beautiful picture. But is it just about humans or is it all about about all of life? And you have to think about what is the perfect world look like? It's not just the lines and lambs laying together is you know, how many lines and how many [/INST] lambs and </s><s>[INST] uh you know what, having just had a few very technical conversations about marxian economics versus kensi and economics versus neoclassical economics. [/INST] What does the </s><s>[INST] economic and the government system look like for the lines and the labs that were longing [/INST] for? So </s><s>[INST] that then you start to build society on top of all those things and but you still, you return to this, what is it? What are we longing for and what's the role of love and that what's the role of that sad melancholy feeling? The feeling of loneliness is the feeling of loneliness fundamental to the human condition, Like? Are we always striving sort of channel that feeling of loneliness um to connect with others? Like we want that feeling of loneliness, otherwise we wouldn't be connecting. Is that fundamental? That feeling like you're alone in this, even when you're with other people sort of alone together, you're born alone, you die alone. Maybe loneliness is fundamental. [/INST] I think the longing for Union is fundamental. It's just that it looks so different for different people, you </s><s>[INST] know? Yeah. [/INST] Coming back to where we were, what we were talking about at the beginning, you know, Union looks incredibly social for a lot of people and hardly social at all for others, but everybody needs some version of union. </s><s>[INST] Yeah. People have been telling me recently about polyamory and all those kinds of things. Some having probably grown up in a certain part of the world. I'm very, I think I'm very monogamy centric, not in a judgmental way. Just for me, what makes me happy is one person feel for my whole life, basically just dedication. Because I've just seen through relationships with people and objects in my life, the longer we stay together, the deeper the tie. So that's just the empirical thing. And yes, that probably it's a personalized thing that's just true for me, it could be very different for others. Maybe it's connected to the introverted thing? Maybe not Who knows before before, because you mentioned songs, sad songs? What um what are we talking about? What's a good what what what song do you remember last crying two? [/INST] Oh gosh, well, I mean that's you know, I I </s><s>[INST] literally [/INST] literally dedicated my book to Leonard Cohen, he's played such a huge role in my life, I love him, I love him. Um and I loved him with this crazy love that I've never been able to understand for decades. I think I understand it a little better now, </s><s>[INST] but you guys, so you're better friends with him than me? I'm so um does it make you, is it the the musician or the human too? Because the human is a is a tortured soul in a way, [/INST] I'd say it's the musician, it's the musician and I actually was thinking about this the other day. I mean obviously he's not alive anymore, but I was kind of running the thought experiment, you know, if he were alive still and I had the chance to meet him </s><s>[INST] in person, [/INST] would I want to do that? And I'm not really sure that I would because he represents for me symbolically everything. Well everything else in the sentence right there. And so and I think that's okay, you know, I think people can can express something through their art that they might or might not express if you were just like hanging out with them and having a coffee and I'm happy to know him that way. </s>
<s>[INST] I had not anticipated that. And what is the nature of the letter or the op-ed that you write on why they shouldn't be disciplined [/INST] or if they, to the degree they should be or shouldn't be? There's not been one case, there's not been one case that has come to my attention in which it was even remotely sensible for the teacher to be disciplined. And what I say is that, number one, frankly, I go through, what I write is almost a synopsis of my book. Number one, this is an important word in American history. It is a word that is explosive, that's why people get so upset. It's a word that's volatile, it's a word that has typically been used in a terrible way. It's a word that is part of the soundtrack of racial terrorism in the United States. So people ought to know about this word. I mean, if you're interested in knowing the real history of the United States, if you're interested in knowing about lynching, if you're interested in knowing about the way in which black people have been terrorized in the United States, you need to know this word. You need to know that history. So you need to know why it is that people are upset about the word. But it doesn't end there. You have to know that. And if you know that, then that knowledge should equip you to be careful. It should equip you to know that, to know the range of context in which this word appears. But again, it doesn't just end there because especially young people, you tell that to young people, they nod, they read, they understand that. But then what? But then they turn on their radios and they turn on, they listen to Spotify. They listen to some of their favorite entertainers. They listen to Dr. Dre. They listen to the ghetto boys. They listen to Snoop. And they listen to NWA. What are they here? They listen to standup comedians. They listen to Dave Chappelle. They listen to Cat Williams. What do they hear? They hear the word nigger or nigga being used in a lot of different ways. And so they need to know about that as well. What are people doing? How does one explain the fact that Dick Gregory, Dick Gregory was a comedian, activist, friend of Martin Luther King Jr., a true activist? I mean, he had a flourishing career as an entertainer that he abandons in order to struggle for racial justice throughout the United States and including the Deep South. How does one explain the fact that he wrote several memoirs but his first memoir is called Nigger, a memoir. How does one explain that? How does one explain the way in which, how does one explain Richard Pryor? I mean Richard Pryor's best album is that niggers crazy. Well, was Richard Pryor trying to put down Black people? How does one explain that? One can only explain that by getting deeper into the word, by understanding that, yes, this is a word that has been used in a derogatory way. This is a word that has been used to put people down. This is a word that has been used to terrorize people. You gotta know that, but you also have to know that this is a word that has also been put to other uses. There are artists, there are entertainers who have used this word, like Dick Gregory used it, to put up a mirror to American society and say, look at this word and look at the terrible way in which it's been used. We don't want you to look away. No, don't look away. No euphemism, no asterisk, no n-word, no nigger. Now we want you to look at that and we wanna talk about that. James Baldwin, there was a documentary about James Baldwin a couple of years ago, highly lauded documentary. The title that was given in this documentary was, I Am Not Your Negro. That's not what James Baldwin said. Anybody can go to YouTube right now, take a look. James Baldwin said, I am not your nigger. And then he went on to talk about that. Well, James Baldwin wasn't, again, he wasn't starting to cover up anything. He wanted people to face the facts of American life. And it seems to me that if you're a teacher and you want to have your students face the facts about American life, well, you've got to grapple with the word nigger. Now, let me just quickly say, teachers have a tough job. And if we're talking about students, of course, there's a wide range of students. Am I saying that one ought to give my book to kindergartners? No, kindergartners are probably not ready for such a book. Third graders, probably no, not third grade. If we're talking however, about people in the 10th grade, do I think the 10th graders can read my book? Yeah, sure, absolutely. 11th graders, 12th graders, people in college, there are people in college, there are people in college, there are people in law schools. Teachers in law schools have been disciplined for, because the word nigger has come out of a teacher's mouth. Why? A couple of cases recently, a teacher would be reading a court opinion. The word appears in the court opinion, the teacher pronounces the word, students get up, leave in a huff, report the teacher. There's some instances in which teachers have been under those circumstances, have been disciplined. In my view, that's bad. And people ought to say it's bad. It's bad pedagogically. And frankly, in many of these instances, it's not only bad, it's stupid. And I don't mind saying that. I think that some of these instances in which teachers have been disciplined, absolutely stupid. People say, well, the teacher used the word, excuse me, used the word. It'd be one thing, it'd be one thing if a teacher looked at a student and called the student nigger. Get out of here, nigger. That'd be one, that'd be, you know, fine. Discipline, that's teacher, that's bad, but that's not what's going on. You don't have, none of these are cases in which you have an individual who is a stranger to another individual and this word just sort of comes out, no. What we have here is a class involving a person who is a teacher interacting with students, talking about subjects in which it would be perfectly understandable why this word would emerge as a subject of conversation. Now, under those circumstances, it's somehow wrong for a teacher to utter this word. In my view, the answer is no. And, you know, I said that 20 years ago, </s>
<s>[INST] Yeah, and it starts with believing the impossible, which is kinda interesting. One of the things that's really inspiring to me is to see people out there which which sadly are rare, who kind of have ah a combination of two things. One is they have a worldview that it involves that includes a lot of ideas that are crazy and the second part is they're exceptionally focused and competent in bringing that whatever the ideas in that worldview to reality. So there's certainly a lot of people crazy ideas, you know, there's a lot of conspiracy theories, they have way out their beliefs about things but they're not doing much to like make the like build stuff grounded like they're not engineers or whatever. They're just like espousing different crazy ideas. But that's why you get like the almost type characters and the reason I bring him up a lot because like there's not many others to bring up. It's like there's not many examples of it through history, the people, I mean the guy's convinced that we're going to colonize mars and basically everybody on earth thinks that's insane. [/INST] Everyone except the guy that's gonna do it </s><s>[INST] except that's going to do it. And like you can imagine like a couple of 100 years from now, people will, I mean, first of all they won't certainly won't remember the haters, they won't remember all the people if if they do remember them, they'll remember him in a sense, like people were silly to think that this isn't the obvious pass forward. Like from a perspective, that's what that's what Ellen talks about. Like it's obvious that we're going to expand throughout the universe. [/INST] Like so from his perspective from his perspective, </s><s>[INST] like, but to me it is also obvious because like either we destroy ourselves or will expand beyond earth. Like uh like there's not many, you know, Well maybe it's not completely obvious. I I guess I share that world view. There is the other possibility that we humans find a sort of of an inner peace or the forces of capitalism will calm down and we'll all just meditate and do yoga and jiu jitsu and like relaxed with this whole tech thing where we keep building new technologies, but it's cool to have those kinds of people that just believe the big ambitious crazy dreams because that's where it starts. If you want to build something special, you have to first believe that [/INST] when you also have to believe strongly enough that you're not vulnerable and I'm speculating, but it's like, I can only imagine how many people have told Ellen that what he's doing is crazy. So not only did he dream it up, he dreamed it up, went with it and also went with it in the face of being told that it's not gonna work and then any time and then also stepped away from the bitterness because he's done a series of really crazy impressive things. Uh, and that's only those little things that I'm aware of. But and also staying away from the bitterness of every single time you did something good. Initially I all I do is talk down about you and then eventually I acted. Of course, of course I never apologized and yet you don't let that dampen your spirits for the next innovation, which is pretty incredible to me to watch. </s><s>[INST] Yeah, it's kind of cool. I mean, it's contagious to spend time with the guy because he's not. Rogan has the same look to him, which is interesting about these people is uh, like there's like a hater shield, but he's like, he doesn't even like sense them. It feels like like it doesn't, he doesn't, he thinks to, uh, to Elon's like, it's obvious. I mean, he keeps calling it like first principles, thinking like physics says is true therefore through like he has convinced himself that like his beliefs are grounded in the fundamental fabric of the way the universe works. Therefore the haters don't matter. And I mean that's kind of like a system of thought. He developed himself through all the difficulties, through all the doubt. He's able to take huge risks with basically putting everything he owes on the line multiple times throughout his life amidst all the drama missed all the doubts amidst all, like the he's still able to make just clear, clear headed decisions, it's, I don't know what to make of it, but it's inspiring his health. [/INST] Well, it's, I think it's something it's funny. I think like I can only imagine, you know, history will look back on him as a brilliant person, but that's not the only, there's, there's a lot of maybe not, not statistically speaking, but a lot numerically on a giant planet of billions of people, a lot of brilliant people. Well, I'm, you know, time, place, luck, fortune and all that other stuff, but at the same time that clearly isn't the only determining thing in making Elon musk, Elon musk. And obviously, I don't know the guy from Adam and but it's an interesting thing that it's not just his intellect, his belief system is structure, how he's viewing the world like that's did he the reason his way to that. Did he not what other factors came in? I'm really curious about that because I guess coming it's again, I feel really strongly about people's belief structure and and this, the, how they view the world being more important than the engine behind it. You know, it makes someone resilient or not, it makes someone positive or not because you could have 10,000 I think about this for competitive stuff, You could have 10,000 things going properly and one thing going improperly. If you focus on the improper, you'll probably fix it at a certain point, which is good Facilitated for development in the long term. But if you had to go and try to perform a task in the next five minutes and you're focusing on the negative, your confidence and your, your, your belief in the positive outcome of the future is likely to be damaged or as you could have a 25 things going wrong. But you go, man, I sure am happy to be alive. How fortunate I am? This is great. I can't, this is, I have problems to solve. This is awesome versus I list the problems and I start dishing about them. Both of them are technically accurate, but it's, I guess different lenses and I think that's a really neat thing to see. You know, someone, you know, exemplifying that for us. </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] When you say teens, what do you mean? Do you mean literally like 13, [/INST] 13 - 17, 13 - 19? </s><s>[INST] And that's where sort of, that's when you really accelerate your development. So you're saying like in America, when you're young, like before, you know, 9, 10, 11, 12, you stick in judo, you can progress quite a bit. But then I guess the other competition there, if you're into uh, two people, uh, you know, doing stuff to each other in a combative way. Uh, the other competitor in America is wrestling. So Judah almost primes you that could teaches you how to be a great wrestler as well. And so then you have to have a hard decision because you can probably be a collegiate wrestler. You can you can you have like a clear plan of where you're going to go if you want to be a wrestler or judo. That plan is more um it is less clear. So you you have to be on your own a bit with your coach, that kind of thing. Okay, so when you're on your own with your coach, to me, that's just a fascinating journey because then it's just like the purity of it. It's a coach and the athlete and the dream. It's all about the dedication. The 5, 6, 7 days a week competing. What once a month? Twice a month. Okay. And just but also you probably don't have that conversation. I don't know if you do, Maybe you do saying like we're gonna do this for the next eight [/INST] years. </s><s>[INST] You ever said dot, would you just take it to David Goggins way, which is like, let's just take it one step at a time. [/INST] Let's hope we're there in eight years. Yes. Hope were there. Do you actually like right now you have to think about the Olympics is going to be in Los Angeles in 2028. So it's really interesting now. Now would be the time and now is the time to identify talent and get commitment out of students That in seven years you can make a US Olympic team because we're gonna have a full team. Uh America is gonna have 14 athletes compete in those games, one in every weight class. So now is the time if you're going to go on a journey to the olympics and stay with the sport of judo now would be the time to do it, </s><s>[INST] you know? And so what uh you show up to the Pedro judo center and how much drilling, how much technique, strategy discussions, how much rendering or like live sparring, how much conditioning and strength training, how much of all that, how much of cross training to other gems or something like that traveling abroad. Is there something to be said about us? Um Some aspects of that system [/INST] for sure. Um You need it all what you just said we needed all of it and we do do all of that right now. We have a young group of kids at the academy you'll see tonight. Some of them are 14, 13, 15, 17. Are they good? Yeah really good. Okay wait there right around your way. They're just young boys but they've been training hard through covid. Um We've been Travis and myself have been training them, we share responsibilities. Um They're doing grand jury like five nights a week, you know we have them doing rendering Tuesdays, Wednesdays Thursdays Fridays and Sundays is when they're doing mandatory, they're coming to the dojo friday night and sunday night to do training. Um We also have technical sessions for them and they're in school now so it's a little bit challenging but they come five o'clock in the afternoon and they do a technical session through covid. They were coming every morning doing technical sessions. </s><s>[INST] What's the technical session? Your [/INST] it's an hour of repetitive throwing or repetitive drilling to to reinforce movements that we deem important to our successful uh uh system. So no waza positions, groundwork positions where we want them to be put in this position and they're gonna drill it 50 times. You know with resistance in big groups, you know, doing drills over and over again, picking apart the details of the technique and what they're doing wrong, showing them how to fix it. But now we've done it so much that now we can do a whole drill session with them where they know all the different techniques inside and out and they can move from </s><s>[INST] position to position really quickly. Do they do it for a period of time like two minutes five minutes? Or is it like 1? Do they are actually counting? [/INST] No, it's sometimes it's both. So sometimes we do it for reps, sometimes we do it for time. So sometimes it might be as many as they can do in in 60 seconds or as many as they can do in two minutes and sometimes it might just be, I want to do every position five times </s><s>[INST] in terms of throws we're not talking about on a crash pad? Right. It's, it's just, we're talking [/INST] about free moving around the mat </s>
<s>[INST] do you think he should not have been banned from all these platforms, [/INST] I don't think, I do think that if you are a private company, right? I do think, and this is where you run into this this problem, like I I don't know if these tech companies were government utilities, would that decrease people's likelihood of being banned? I don't know. Right? So I'm I'm I understand the benefit of them being treated like public utilities and people thinking they have the right to a twitter. I've never I don't know, I have very little confidence. I mean the government trying to roll out a vaccine in California and we vaccinated like five people. I mean in terms of what we need to do in the state, right? So maybe if it was a government utility, I I do think someone like Alex, just like there should be some process, so if you're going to get rid of someone, they should have a way to defend themselves, there should be more democratic uh process that you can go through than just being unilaterally taken off something. But like then you run into the like, am I going to say that everyone deserves no if you're threatening or harassing people are threatening to kill them, publishing their private information if you're committing crimes on these platforms, obviously the people that own these platforms are gonna be like, we're not gonna allow this to happen. So I understand that there is a line, right? There is some like people that say there is no line aren't really thinking like there is a line. Uh I just thought that line seems to be moving all the time and it seems to be a very hard thing to police, but I don't think you can remove a guy off everything and then also bank accounts won't give him debit cards or credit cards, I don't know if you talk to him about that, but like you know, there were financial institutions that were refusing to let him, you know, park his money there. So I mean it really does get pretty terrifying pretty quickly um probably </s><s>[INST] without any transparency from those companies, so you're right, it feels like there should be a process of just having for him to defend themselves. I think [/INST] there needs to be a process for people to defend themselves. I every day I wake up and I go, can is something I said in the video gonna get taken out of context, is somebody gonna get angry? Is somebody gonna be, you know, I say wild stuff because that's what makes me laugh, that's what makes my friends laugh and that's what makes my audience laugh. So I never ever people, you know, whatever whatever political side you come down on, I think if you make your living speaking, it's always interesting to me if you are pro the the platform, </s><s>[INST] that's odd, it's interesting to consider a kind of a jury uh context to where you know, there's transparency about why you're a video about bombing um Disney world might be taken down, like it's uh it gets taken down and then there is uh it's almost like creating a little court case, a mini court case and not in a legal sense, but in the in the public sphere. And then people should be able to have, you know, you pick representatives of our current society and have a discussion about that and make a real vote. You know, just have like, jury locks himself up in a discussion that kind of, that kind of process might be necessary right now. What happens is twitter is completely first of all, they're just mostly not aware of everything they're doing, there's too much stuff, but the stuff they're aware about, they make the decision in closed doors uh meetings and without any transparency to the rest of the company actually, but also transparency to uh the rest of the world. And so, and then all they say is we're doing, we're making these decisions because the people, they use things like violence. So violence equals bad. And if this person is quote unquote inciting violence, therefore, that gives us enough enough reason to bend them without any kind of process. It's, I mean, it's interesting, I'm, I'm torn in the whole thing if if it was indeed there's no transparency about it, but if parler was indeed inciting violence, like if there was brewing of violence, potential violence where, you know, thousands of people might die because of some kind of riot like the, this is scary thing about mob about when a lot of people get together or good people like legitimately good people that love this country that don't see enemies yet uh, around them. But if they get excited together and there's guns involved and then some cop gets nervous and shoots one person, another person shoots the cop. And then there's a lot of shooting involved and then it goes from five people dying in the capital to thousands of people dying in the capital. [/INST] Well, in fairness to to defend the people of cap, they didn't shoot the cop. They bludgeoned him to death with a fire extinguisher. Yes. So I do, I do wanna just kind of put that out as a, as a defense of them. Listen, I'm sure there was some wild ship going on on parler. And I think the problem here's the problem, right? There's a lot of people that just want to go on these sites and say they want to kill everyone. And the problem is, you know, at what point do you shut them all down? Like, I think a lot of people are just living in a world with their powerless. They don't have any political power. They don't have any economic power, right? They can't throw their money around. Uh, they don't have healthcare, their their job security isn't great. Uh, there might be living in a community that doesn't have the resources, they would like it to have. Uh they're they're not happy and thrilled and then they have these sites where they can go on and just say, man, I'd like to fucking burn it all down and distinguishing a guy blowing off steam and saying wild stuff from a genuine threat is a very hard thing to do. You know? Like I have, I've threatened to kill uh I got banned from Airbnb. I threatened to kill the people. Um That band be comedically comedically, this is a joke. I'm not going to kill you. This is a joke cause I'm blowing off steam and I'm angry. Do you know how many people that my parents like my dad's like, I'm gonna fucking kill this guy, my mom like I'm gonna fucking kill and they were talking about each other but it's, but none of it ever happened. But we should be, I think you, you have to create a space for people to threaten to overthrow the government. As long as they don't violently do it? Like I mean does that make any sense? Like I mean as long as they're not going to go hurt innocent people, what are you gonna do? Like there's so many people out there that she's that's why a lot of these things like, you know, four chan these sites, a lot of people going on there, They just want to say the most fucked up ship because they, it's the thing that gives them, they can laugh or they can release steam and it's, it is a mature, it is stupid. It's not productive. It's not, you know, but at the end of the day, if you're not going to give people health insurance, you gotta give them something. It's like when someone in this country dies that everyone disagrees with right political figure, media figure a lot of people dance on their grave online and then everyone people goes, the and the other side will always do it like a conservative dies and everyone goes great conservatives goes, and this is grotesque that you, and then when RBG dies, they all have parties and the conservatives go great. Um, you have to let people in this country enjoy the deaths of their enemies. </s>
<s>[INST] What do you mean by everything? So the, [/INST] like there's just some, you know, there's ideas that, um, when you're a coach, uh, that aren't there beneath the surface and you've got to find them? </s><s>[INST] Mm hmm. So when your communication comes [/INST] in. Yeah. But you're talking about, yeah, we got to move forward. Well, what does that mean? Well, I know what that means, but how many, how many guys really know what that means in their program. You know, there's so many levels of that </s><s>[INST] you said before the winning is everything. Ah, and that means people lose. Most people lose. You know, there's, there's really in whatever the context is only one winner in many parts of our world today, outside of wrestling. That concept, the brutal honesty of that is uncomfortable for people. So how do you think about this very philosophical, difficult concept of, you know, there only being one winner, that winning is everything. It's kind of really painful idea. [/INST] I don't think that that's a bad thing to have that mentality. I mean, I think a Kalashnikov, um, I remember a story I read about him, he comes to mind, um, you know, um, sorry Goose. I remember when he lost in London and I remember the look on his face and those are some of the greatest wrestlers in the history of the sport freestyle wrestling. And um, you know what, it's what works for you. You can talk about being at peace with your results and, and that the approaches and the journey is what it's about. But um, and that's great and that relaxes some champions and that makes some champions really, really tick. Um, but not everybody. So it's okay. It's okay. And if that wigs you out, that that really makes you uptight, then then then go the other route, You have to find what works for you and that takes a lot of work if you're lazy, forget it, forget it. </s><s>[INST] So you and terry, but in general, how do you find the line between extremely physical, extreme physical wrestling and rough wrestling or angry wrestling? So to which degree has anger, whether it's in your wrestling room these days or in your own career entered wrestling? Do you see it as a tool that can be used in the [/INST] rest of matching, there's a balance and you're not even a balance, There's a line that you go up to and you can't cross it. Sportsmanship is everything you can get dinged for points. You can get thrown out of tournaments. There's rules with um flagrant misconduct where you kicked out of the match, other team gets the points and then you have to sit the next meet. So it's very serious. The N. C. A. A. Sends a message very serious message about sportsmanship. And so we talk about that. The other thing with wrestling in and there's rules and wrestling. These guys that are tough guys outside of the rules. That's that's what you want in your opponent. That means they're frustrated. You've got to be a you've got to be a tough guy inside the rules of the sport. That's that's more honorable than cold cock and somebody and knocking them out. </s><s>[INST] So yeah, anger doesn't mean breaking the rules, but I mean, you know you, a lot of people know you just watching you as a coach. There's quite a bit of passion there. [/INST] We'll come and do what you're doing tonight. I mean, break bread with me in my kitchen and see how big of a jackass I am. You're pretty nice guy. Well, I'm not asking for that necessarily, but thanks, I'm saying. You know what you you as a coach. I mean, come, okay, come spend a month in our program and you'll see really what kind of what kind of people we are and there's a stigma out there because they are very threatened by our program. There's nobody else that threatens the sport of wrestling like we do. And that's the truth. </s><s>[INST] There's a legend to Iowa resting. There's uh, it's one of the most [/INST] intimidating sort of legend to john smith. It's the same thing. But if they get up for john smith and get up for Oklahoma State, then get up for Penn State. My question is, Okay. I'll answer it this way. I'll give you, I'll give you an example in my coaching career. I coach at Virginia Tech for 22 months. We recruited the # one recruiting class. We got the administration to change 100% 1 80 How they looked at wrestling. Here's the thing. And because of how serious we were and because we weren't idiots, we were able to do that with our administration. But my point is this, we tried to win. We tried to win. Even at Virginia Tech. It wasn't a stepping stone for me and ended up being one quickly And looking back on it? I was a fool to think that I'd be there for 20 years </s><s>[INST] that you believed you would [/INST] be. I did. I did. I did. </s><s>[INST] So do you remember a time that you really pushed yourself to your limits? So gable talks about having to be carried off the mat. Have you really found that [/INST] level? I said something about that too in a book And I think I was misquoted one time. And actually it was Gables quote, I was trying to make the point that Gables quote was like this and you know, they were making it like, it was my own words. I think it was the first wrestling tough book, but </s><s>[INST] good book, [/INST] it's a good book. But the story's Gables and I don't know if there's anybody that has done that besides him. And I think that's a very rare quality. Um, but I've definitely been in that Nirvana level of, you know, either you can go all day long and it doesn't, you have to, you have to shoot me to stop me. Yeah, but there's a balance because you're not going hard with and holding your breath. It's not a it's a relaxed and like you got a guy cornered and who's most dangerous. Well, the guy that's cornered and so that's where you relax. I'm not bum rushing him. I'm relaxed. I'm still moving fake and very fluid guy falls down his face and run around behind him. That's offense. You don't have to just grunt to the leg and call that offense offense as a in and out smooth. </s>
<s>[INST] So what's the connection of Frosty elsewhere? [/INST] The person logging into the philadelphia backup server. The name of the computer was Frosty? Another clue in my </s><s>[INST] world. And that's it. The name is there? The connection to the philadelphia server and then to Iceland is there. And so the rest of the small details in terms of uh or is there interesting details [/INST] now? I mean there's some electronic surveillance that find Ross Ahlberg living in a house and is there, you know, is a computer at his house attaching to uh you know, does it have tour traffic at the same time? That DPR is on another big </s><s>[INST] clue [/INST] matching up time frames </s><s>[INST] again. Just putting your email out there, putting your name out there like that. Like what I see from that just at the scale of that market, what what what it it just makes me wonder how many criminals are out there that are not making these low hanging fruit mistakes and are still successfully operating. To me it seems like you could be a criminal, much it's much easier to be a criminal on the internet. What else do you is interesting to understand about that case of us and and Silk Road and just the history of it from your own um relationship with it from a cybersecurity perspective, from an ethical perspective, all that kind of stuff like when you look back, what's interesting to you about that case, I [/INST] think my views on the case have changed over time. I mean it was my job back then. Um so I just looked at it as of, you know, I'm going after this, I sort of made a name for myself in the bureau for the anonymous case and then this one was just I mean this was a bigger deal. I mean they flew me down to D. C. To meet with the director about this case. Um The President of United States was going to announce this case, the arrest. Unfortunately the government shut down two days before. Um so it was just us and that's really the only reason I had any publicity out of it is because the government shut down. And the only thing that went public was that affidavit with my signature at the end. Um Otherwise it would have just been the attorney general and the president announcing the rest of this, this big thing and you wouldn't have seen me. </s><s>[INST] Did you understand that this is a big case? [/INST] Yeah, I knew the yeah the new design, </s><s>[INST] was it because of the scale of it or what it stood for? I [/INST] just knew that the public was gonna really going to react in a big way. Like the media was now did I think that it was gonna be on the front page of every newspaper and the day after the arrest? No, but I could sense it like I went like three or four days without sleep. Um when I was out in san Francisco to arrest ross, I had sent three guys to Iceland to um so it was a three pronged approach for the takedown. It was get ross, get the Bitcoins and sees the site like we didn't want someone else taking control of the site and we wanted that big splash of that banner. Like look, the government found this site, like you might not want to think about doing this again. So you </s><s>[INST] were able to pull off all three, [/INST] maybe that's my superpower. I'm really good about putting smarter people on that than I am together and on the right things. Um You know, </s><s>[INST] the only way to do it [/INST] in the business I form, that's what I did. I hired only smarter people than me and I, you know, I'm not that smart, but you know smart enough to know who the smart people are. The </s><s>[INST] Team was able to do all three. [/INST] Yeah, we were able to get all three done. Um Yeah and the one guy, one of the guys, the main guys I sent to Iceland man, he was so smart, like I sent another guy from the FBI to um to France to get that part and he couldn't do it. So the guy in Iceland did it from from Iceland, they had to pull some stuff out of memory in a computer. Um you know, it's live process stuff. I'm sure you've done that before, but </s><s>[INST] I'm sure you did look look what [/INST] you're doing, you're </s><s>[INST] it's like a multi layer interrogation going on. Uh was there a concern that somebody else will step in and control, say [/INST] absolutely, we we we didn't have insight on who exactly had control. So </s><s>[INST] it turns out that us had, like, dictatorial control. So it wasn't easy to delegate to somebody else. [/INST] He hadn't, I think he had some sort of ideas. I mean, his diary talked about walking away and giving it to somebody else, but he didn't, he couldn't give up that control and anybody apparently, </s><s>[INST] which makes you think that power corrupts and his ideals were not as strong as he espoused about? Because if if it was about the freedom of being able to buy drugs, if you want [/INST] to, then </s><s>[INST] he surely should have found ways to delegate that power. We [/INST] changed over time. You could see it in his writings, um that he changed like, so people argue back and forth that there was never murders on Silk Road when we were doing the investigation to us, There were six murders. Um, so there there was, the way we see him saw him at the time was ross ordered people to be murdered. Um you know, somebody people stole from him and all that. It was sort of an evolution from, oh man, I can't deal with this, I can't do it. It's too much to the last one was like, the guy said, well, he's got three roommates. Uh it's like we'll kill them too. </s>
<s>[INST] And then the rest is what you're saying, it's uh maybe you mean it's not technically sophisticated but it's social engineering sophisticated, [/INST] very sophisticated on that end. Very sophisticated. </s><s>[INST] It's a fascinating study of [/INST] that establishment of trust and then using that trust to defraud that victim. That is something </s><s>[INST] I wish obviously all of these folks are really good at hiding. I wish you could [/INST] tell </s><s>[INST] their stories in a way, which is why you're fascinating as you're able to tell these stories now because it is studying human nature [/INST] by </s><s>[INST] exploiting it. But you get to understand like our weak points are um our hope, our desire to trust others also sort of the the weak points and the failures of of digital systems and at scale humans have to connect. It's fascinating is um this is a weird question um asking for a friend uh is spearfishing itself illegal? What's the legality here? [/INST] Oh it's all illegal. Absolutely, it is. But </s><s>[INST] absolutely. So here here's what, Okay, let me let me construct an example. So if if my friend were to spearfish like a ceo right and get their information and after they get controls they have their twitter account, they tweet something loving and positive? What's the crime? [/INST] Unauthorized access of advice? </s><s>[INST] What will be the punishment? Do you think [/INST] that becomes questionable. So, so no monetary loss or was there a monetary loss? Probably not. Alright, so you have to figure out who the victim is before charges are pressed now the crime would be another unauthorized access. All right. But no real victim on that unless you know the person whose account you took over takes, you know, exception to that. Um no monetary loss. But </s><s>[INST] there's not really standard like fines [/INST] is going to happen. </s><s>[INST] Right? I mean, that's that's kind of interesting because it's, it's, so when I got the ransom where um, when I get with the zero day attacks on the Qnap Mass, you know, they basically say the criminal is Qnap the company for having so many security vulnerabilities there. Uh like you are the victim of Q naps incompetence. That's the way they kind of phrase it. [/INST] And see, I don't agree with that. I don't agree with that at all. So solar winds, let's let's so I've got 100 and 30 page class action lawsuit printed out at the house. I've been going through it. That catalogs how solar winds lied for years about their vulnerabilities and they lied to investors. The people who came in, the auditors would, who they would hire would, you know, they would uh not pay attention to them when they said, you know, you've got these issues? They would say go away. I should like that for years until solar winds, you know the attacks become apparent. Um my view on that is that the only person responsible for the crime are the criminals who did the attacking the actual criminals? Not not solar winds now, does that mean the solar winds isn't isn't all funked up? They are and there needs to be some accounting in place. But the the the only individual, the only people responsible for crime are the criminals and that's either online in the physical world, what have you can be being an idiot is not being, being, being criminally negligent is and I think that that solar winds is certainly responsible not not responsible, they're culpable for what happened. </s><s>[INST] Can you actually tell folks about solar winds? What is it? Um what what what was what are some interesting things that you're aware of? The [/INST] solar winds was very it was it provided a background, a backbone of security for hundreds thousands of different companies. If you looked at, a lot of security companies were using solar winds that would that would allow you to get a snapshot of the entire system that they were working on. So what happens is is you get a Russian group that comes in and they basically they hack into solar winds and get access to it and it allows them to view every single thing. I mean every single thing about every single client that solar winds had at that point. So entire snapshots of all the I. P. That were that was going on all the emails, all the communications, every single secret that was going on with those companies. If the company had software like Microsoft it allowed them to look at the source code of everything that was going on. I mean it's just a complete and total nightmare alright. And something that you are not going to to recover from. You're not I mean it's done at that point. Um you know, there's not been a lot of news lately about it but the fact of the matter is is that's the type of attack that's a catastrophic attack. </s><s>[INST] So there's a huge amount of information that was red saved elsewhere probably. And so now there's people sitting on information. [/INST] Absolute. So think about one of the attack vectors is has been Microsoft Outlook 365 things like that. This allowed the Attackers to look at the source codes of that. So they have the source code now. So they go through it line by line or other vulnerabilities, let's find new vulnerabilities new zero days and you know, I said zero days aren't common but this opens up an entire new threat surface all of a sudden. So it's a it's a completely catastrophic attack. Once all the chips are down, everything is tallied up, people are gonna be like yeah we're done, we're </s><s>[INST] done alright. This whole computer [/INST] thing, we tried it we were walking away. That's </s><s>[INST] terrifying because so you're saying that there's not been obvious big negative impact from that yet, but like [/INST] there's been a lot of negative impact. But we're just starting, </s>
<s>[INST] And you can have a public profile, more so of a public profile. You can be a public rockstar. I mean it's the same thing as uh sort of the military. There's a lot of um there's a lot of well known sort of people commenting on the fact that veterans are not treated as well as they should be, but it's still the fact that soldiers are deeply respected for for defending the country, the freedoms, the ideals that we stand for and in the same way, I mean in some ways the cyber security, defense of the soldiers of the future. [/INST] Yeah, and you know, it's interesting, I mean, in in cybersecurity, the differences oftentimes you see the more interesting threats in the private sector because that's where the attacks come. You know, when when cybercriminals and nation state adversaries come for the United States, they don't go directly for cyber command or the NSA No, they go for banks, they go for google, they go for Microsoft, they go for critical infrastructure. And so those companies, those private sector companies get to see some of the most advanced sophisticated attacks out there. And you know, if you're working at Fireeye and you're calling out the solar winds attack for instance, I mean, you just saved God knows how many systems from, you know, that compromise turning into something that more closely resembles sabotaged. Um, so, you know, go go be a hacker and um or go be a journalist. </s><s>[INST] So you wrote the book, this is how they tell me the world ends as we've been talking about, of course, referring to cyberwar cybersecurity. Uh, what gives you hope about the future of our world, if it doesn't end, how will it not end? [/INST] That's a good question. I mean, I have to have hope, right, because I have a kid and I'm another on the way and if I didn't have hope, I wouldn't be having kids. Um, but it's a scary time to be having kids and and now it's like pandemic climate change disinformation increasingly advanced, perhaps deadly cyber attacks. Um what gives me hope is that I share your worldview, that I think people are fundamentally good and sometimes, and this is why the metaverse scares me to death, but where when I'm reminded of that is not online, like online, I get the opposite, you know, you start to lose hope in humanity when you're on twitter half your day. Um it's like when I go to the grocery store or I go on a hike or like someone smiles at me um or you know, or someone just says something nice, um you know, people are fundamentally good, we just don't hear from those people enough and my hope is, you know, I just think our our current political climate, like we've hit rock bottom, this is as bad as it gets, we can't do anything well, but I think it's a generational thing, you know, I think baby boomers, like it's time to move along, I think it's it's time for a new generation to come in and I actually have a lot of hope when I look at, you know, I'm sort of like this, I guess they called me a geriatric millennial or a young gen x, but like we have this unique responsibility because I grew up with and without the internet and without social media, but I'm native to it. So I know the good and I know the bad and that's true on so many different things, you know, I grew up without climate change anxiety and now I'm feeling it and I know it's not a given, we don't have to just resign ourselves to climate change, um you know, same with disinformation and I think a lot of the problems we face today have just exposed the sort of inertia that there has been on so many of these issues and I really think it's a generational shift that has to happen and I think this next generation is going to come in and say like we're not doing business, like you guys did it anymore, you know, we're not just going to rape and pillage the earth and trying to turn everyone against each other and play dirty tricks and let lobbyists dictate, you know, what we do or don't do as a country anymore. Um and that's really where I see the hope, </s><s>[INST] it feels like there's a lot of low hanging fruit for young minds to step up and create solutions and lead. So I whenever, like politicians or leaders that are older, like you said are acting shitty, I see that as a positive, they're inspiring a large number of young people to replace them. And so it's yeah, I think you're right, there's going to be, it's almost like you need people to act shitty to remind them, oh wow, we need good leaders, we need great creators and builders and entrepreneurs and scientists and engineers and [/INST] journalists, you </s><s>[INST] know, all the discussions about how the journalism is quote unquote broken and so on, that's just an inspiration for new institutions to rise up that do journalism better, new journalists to step up and do journalism better. So I, and I've been constantly, when I talk to young people, I'm constantly impressed um by the ones that dream to build solutions and so that's, that's, that's ultimately why um I put the hope that the world is a messy place, like we've been talking about, it's a scary place. [/INST] Yeah, and I think you hit something hit on something earlier, which is authenticity, Like No one is going to rise above that is plastic anymore, you know, people are craving authenticity, you know, the benefit of the internet is it's really hard to hide who you are on every single platform, you know, on some level it's going to come out who you really are. And so you hope that um you know, by the time my kids are grown, like no one's going to care um if they made one mistake online, so long as they're authentic, you know, and I used to worry about this, my nephew was born the day I graduated from college and I just always, you know, he's like born into facebook and I just think like how is a kid like that ever going to be president of the United States of America because if facebook had been around when I was in college. You know like jesus, um you know what, how is how are those kids are going to ever be president? There's going to be some photo of them at some point making some mistake and that's going to be all over for them and now I take that back now, it's like no, everyone is going to make mistakes, there's going to be a picture for everyone and we're all going to have to come and grow up to the view that as humans, we're going to make huge mistakes and hopefully they're not so big that they're going to ruin the rest of your life. But we're going to have to come around to this view that we're all human and we're going to have to be a little bit more forgiving and a little bit more tolerant when people mess up and we're gonna have to be a little bit more humble when we do and like keep moving forward otherwise you can't cancel everyone. </s>
<s>[INST] Do you think authoritarian systems emerge naturally like that's the natural state of things. If you take if you incorporate what human nature is? Well there is they're always going to be corrupt people. The rise to the top and we almost have to um construct systems that protect us against ourselves kind of thing. Another way to ask that is what kind of systems protect us from our own human nature. [/INST] We started with authoritarianism or autocracy right, ruled by one or a small group oligarchy and all humans lived under this structure for the virtual you know, bulk of all human existence only until pretty recently that we start having actual democracy. Uh the idea that we should be ruled by rules not by rulers very powerful um invented in many places across the world. Western africa had this idea and so did the ancient Greeks. Um and they started to implement it, although as most, no, we didn't have full democracy for a long, long time because it was only property owners are only men, only people of a certain race. But this idea that that we can like rotate our rulers and that we could be ruled by rules is extremely powerful. And it really like for me the ideas behind this um I think unlocked a lot of the industrial revolution, these small personal freedoms that were allowed in some countries but not others and then locked a lot of the scientific innovation over the last few 100 years. Um and to me there's like a really straight line between scientific enquiry, free speech freedoms and then more prosperity and more effectiveness as a civilization. So I think that democracy ruled by the people is definitely an upgrade from autocracy or oligarchy which would be ruled by by one or ruled by a small group. And I think that the democratic revolution has been an incredible thing for our world and it's it's you know, you can do half glass full, half glass empty, half glass full is that almost half the world lives under democracy like that. That's an incredible achievement, </s><s>[INST] but just under half, [/INST] just under half. </s><s>[INST] So [/INST] uh but that's billions of people </s><s>[INST] is billions of people and if you look at the progress of things is getting better and better and better. I mean if you [/INST] were a little bit of a stalemate here, uh democracy is really blossomed between World war two and the year 2000, especially in the eighties and nineties, you had an incredible wave of fall, you know, where many, many authoritarian regimes fell and were replaced by democracies I think around 22,015 the acceleration kind of Came to a standstill a little bit. Um there's some good news in some countries and there's bad news and others. Um like in the last 10 years you've had, for example, the Philippines has gone backwards. Um Thailand has gone backwards, Bangladesh has gone backwards, Turkey has gone backwards. That's that's like a half billion people right there. So you've had some positives um like you know, there was positive movement forward in Armenia Malaysia, some other countries. Um but we're kind of at a stalemate right now and what most people fear them about where we are right now, who I respect is what is the digital transformation of the world due to this like progress of democracy or of open societies and and that's what concerns me the most, Oh </s><s>[INST] interesting, so I've uh we'll talk about, well one of the most fascinating technologies, which is Bitcoin how it can help. But I have a sense that technology like most technological innovations will give power to the individuals. We'll give will fight fight authoritarian governments are supposed to give more power to authoritarian governments. But your senses there's ways to give for technology to be utilized as a tool for the abuse of the citizenry. [/INST] I've seen both in my work at a draft. I started by helping to put together backpacks with foreign information that we sent to the Cuban underground library movement. So in cuba to own a book at the time you have to have the government's permission. There's very little internet penetration. Okay, so we would send in movies v for vendetta dubbed into spanish and people would sit inside their homes and they'd watch it and they would answer questions with each other and it's very powerful. And then after that I worked with people inside North Korea. We would send in flash drives, we have this program called Flash drives for Freedom. We've sent over 100,000 flash drives in our work into North Korea, a country about 25 million people. That's a lot. It's a big big difference that's many, many millions of hours of films books, movies et cetera. So I've seen the power that technology can have where in the 60s and 70's get to break an information blockade, you had to send in crates of books into a communist country. So now all of a sudden you can send the entire contents of what was once the library of alexandria on something the size of your thumbnail. That's remarkable. So obviously I've seen the positives of technology will certainly get into Bitcoin but I'm very concerned about essentially big data analysis like what people call a I or general, you know specific specific kinds of A. I like very concerning. I think these are very authoritarian. I mean it's very hard to make a case that AI is going to be good for human rights. Very difficult. In my opinion. It may be good for health, it may be good for our efforts to protect the planet. It may be good for a lot of scientific things. I find it very hard to believe it will be good for civil liberties. </s><s>[INST] Oh that's fun. This is fun because I disagree. Uh [/INST] your examples, I'm serious. What Ai applications will improve civility. I </s>
<s>[INST] So it is calories. That was my only source of calories, whiskey. And I, so I didn't trust myself with carbs when I'm drunk. I just don't enjoy it because I'll forget and I just enjoy eating like a strict healthy diet when I'm drunk because um, I'd rather eat more food that's healthy versus not. And so anyway, so then we went to Vegas together and then uh just kept doing wild thing after another wild thing. Uh Rogan opened up for Whitney cummings. He just like showed up in a random party that he wasn't invited and he did a thing. He almost started a fight because some guys said, stop spreading, yelled at him said, stop spreading misinformation. Uh, and then, uh, we run into David Goggins of all, this is my first time meeting David. I've talked to David a lot over the phone and we were supposed to do a thing together and this is me trash out of my mind meeting David for the first time with his incredible wife. Rogan's wife was there. By the way, joe Rogan's wife. David's wife made me realize that I really want to be married because they're not, they make um, their partners better like that. I was um, there's a certain aspect of marriage that I'm afraid of, that. Like your partner takes you away from life, you don't get to experience life as much. Um, but this was like, they were enriching them. I don't know, it's like the world's most powerful support group. It was cool. Anyway, so then of course drunk lex is uh, challenges God against the push ups. [/INST] I saw this on instagram, Whatever we're in the </s><s>[INST] middle of, in this suit, in the middle of casino, there's a crowd gathering. Like its joe Rogan, me and David Goggins and I'm just doing pushups with him and Rogan is like commentating and yelling and screaming. It is surreal and just going on to the next thing and next thing and next thing like this and then drove, um, all the way from Vegas back to uh, to L. A. With, with joe and Whitney and his wife and It was like, what, what is this? And all of it is done in 24 hours. The one valuable lesson is don't fast and drink like excessively. So I've learned that because what happens is, um, liquor hits your mind my mind. Sorry, I'll speak about my particular mind. Like the intellectual part of my brain got hit really hard really fast. So I was not able to even more so than usual stitched together sentences. I understood every really well. [/INST] So like major an immigrant again. </s><s>[INST] So like meeting David, I want to say so many things. He's so inspiring to me. Right? But all I said was like hello. And then like I remember like opening my mouth to like try to say more and I was like, and then I would just close my mouth and not be able to say anymore. And this [/INST] is why this is one of the reasons I don't drink ever. </s><s>[INST] It removes certain barriers. Like it allows you to maybe have fun that you wouldn't otherwise. But yeah, definitely for a person who values intellectual, [/INST] but I also hate being hungover </s><s>[INST] hungover party. That's [/INST] the worst. And you also like I did this to myself. Yeah. </s><s>[INST] But it also teaches me that this too shall pass because I've been hungover and I've quit drinking so many times in my life that it realizes it makes you realize that all the unpleasant feelings all you have to do is just wait it [/INST] out. But it took me a long time to realize that that expression means the other thing. What's the other thing if things are going great, this too shall pass? Yeah, I always thought about, you know, I always thought about it as being more like don't worry, things are bad, it will pass. It's like, it's also like if something's going great, it's not gonna be this way forever. </s><s>[INST] It's like Bukowski said love is a fog that fades with the first daylight of reality. Do you think love can last? [/INST] Oh yeah, we're gonna win. </s><s>[INST] Who's we? The good guys didn't Hitler also think he's the good guys [/INST] cause you know why why didn't win? So I </s><s>[INST] think it's permanent. So that this one time the good guys winning, it will last. It won't pass. Mm hmm Because I think all of it passes, unfortunately, [/INST] I think we're going to win and win big in the not so distant future. </s><s>[INST] Do you have specific things in mind or no or just a sense about human civilization about society waking up. [/INST] I don't know about waking up, but I think the increased understanding on all sides of the political spectrum that um corporate America and corporate news outlets are self motivated actors and those motivations are often inimical two what others would regard as desirable is something that I think is happening with increasing frequency. </s><s>[INST] So what do you think about the political landscape in general? You had a great conversation with Glenn Beck and he said that Uh he talked to Trump and believes that Trump is Donald Trump is definitely running in 2024 or very likely running in 2024. I think he said he thinks he'll have a good chance of winning or I don't remember that, but The fact that he was running was a surprise to you, do you think Donald Trump would be running in 2020 [/INST] 4? Given that Glenn Beck, you know, has a much better relationship with trump than I do. To put it mildly. If Glenn Beck is certain this is going to happen, I would defer to Glenn Beck's judgment. </s><s>[INST] Um Do you think he has a chance of winning? Do you think he'll win [/INST] anyone in a binary political system who's the nominee has a chance? Like whoever the republican democrat has has a chance. I think also it's a lot easier to vote for someone that you have voted for in the past. So that's why incumbents have a big advantage, there's not that psychological barrier to cover. I think it's also useful for trump, that he's banished for social media because then he doesn't have to have the responsibility of governing. Um and the all the costs of that, you know, because no matter what decisions you make while governing, some people aren't gonna like that. Um, so he gets to kind of be above the radar or below the radar rather just to some extent, I don't think it's at all a given that he would get the nomination when I say the good guys are going to win, I certainly don't mean donald trump. I don't think victory is gonna come as a consequence of Washington. </s>
<s>[INST] Yes. So in a new series does then we could speak more broadly. There's a let's talk about the people constructing those algorithms which in our modern society, Silicon Valley, those algorithms happen to be a source of a lot of income because of advertisements. So let me ask sort of a question about those people. Are there are current concerns and failures on social media. Their naivety, I can't pronounce that word well, are they naive? Are they? Uh huh. I use that word carefully but evil and intent or misaligned and intent. I think that's uh do they mean well and just go have unintended consequence or is there something dark in them that that results in them creating a company results in that super competitive drive to be successful. And those are the people that will end up controlling the algorithms [/INST] at a guess. I'd say there are instances of all those things. So, so sometimes I think it's naivety, sometimes I think it's extremely dark. Um, and sometimes I think people are are not being naive or dark and then in those instances are sometimes generating things that are very benign and and other times generating things that despite their best intentions are not very benign. It's something I think the reason why I don't get anxious about ai in terms of uh, or at least A I. S. That have uh, I don't know, a relationship with some sort of relationship with humans is that I think that's the stuff we're quite well equipped to understand how to mitigate the problem is is issues that relate actually to the power of humans or the wealth of humans. And that's where that's where it's dangerous here and now. So, so what I see, I'll tell you what I sometimes feel about Silicon Valley is that It's like Wall Street in the 80s. Um, it it's rapidly capitalistic, absolutely rapidly capitalistic and it's rapidly greedy. But whereas In the 80s, the Sense One had of Wall Street was that these people kind of knew they were sharks and in a way relished in being sharks and dressed in sharp suits and and kind of lauded over other people and felt good about doing it. Silicon Valley has managed to hide its voracious Wall street like capitalism behind hipster t shirts and you know, cool cafes in the place where they set up there and, and so that obfuscates what's really going on, what's really going on is the absolute voracious pursuit of money and power. So, so that's where it gets shaky for me. </s><s>[INST] So that veneer and you explore that brilliantly, uh, that veneer virtue that Silicon Valley has, [/INST] which they believe themselves. I'm </s><s>[INST] sure. So, okay. I, I hope to be one of those people. Ah, and I believe that so as a, maybe a devil's advocate term poorly used in this case, what if some of them really hard trying to build a better world? I can't, [/INST] I'm sure, I think some of them are, I think I've spoken to ones who I believe in their heart feel they're building a better work. </s><s>[INST] Are they not able [/INST] to know they may or may not be, but it's just a zone with a lot of bullshit flying about. And there's also another thing which is, this actually goes back to, I always thought about some sports that later turned out to be corrupt in the way that the sport like who won the boxing match or how a football match got thrown or cricket match or whatever happened to be. And I just think, well, look if there's a lot of money and there really is a lot of money people stand to make millions or even billions you will find a corruption that's going to happen. So so it's it's in the nature of its of its voracious appetite that some people will be corrupt and some people will exploit and some people will exploit whilst thinking they're doing something good. But there are also people who I think are very, very smart and very benign and actually very self aware and so I'm not I'm not trying to I'm not trying to wipe out the motivations of this entire area, but I do know there are people in that world who scared the hell out of me. Yeah. Sure. </s><s>[INST] Yeah, I'm a little bit naive and that like I I don't care at all about money and so I'm uh [/INST] you might be one of the good guys. </s><s>[INST] Yeah, but so the thought is but I don't have money. So my thought is if you give me a billion dollars, I would it would change nothing and I would spend it right away on in resting right back and creating a good world but your intuition and is that billion, there's something about that money that may be slowly corrupts the people around you. There's somebody gets in that corrupts your souls of you the way you view the [/INST] world, money does corrupt, we know that, but but there's a different sort of problem aside from just the money corrupts, you know thing that we're familiar with in, throughout history. Um, and it's, it's more about the sense of reinforcement and individual gets, which is so effectively works like um, the reason I earned all this money and so much more money than anyone else is because I'm very gifted, I'm actually a bit smarter than they are or I'm a lot smarter than they are and I can see the future in the way they can't. And maybe some of those people are not particularly smart, they're very lucky or they're very talented entrepreneurs. And there's a difference between, so in other words, the acquisition of the money and power can suddenly start to feel like evidence of virtue and it's not evidence of virtue might be evidence of completely different things. </s>
<s>[INST] copy editors. So some of it money, like if we become brave enough to go outside the solar system, can we afford to financially? [/INST] Well, I think that that's not really the issue. The issue is, look what Ellen did. Well he amassed a lot of money and then he, you know, he plowed it back in and he spun, spun the wheel and he made more money and now he's got F you money. Now the problem is is that a lot of the people who have F. U. Money are not people whose middle finger you ever want to see, I want to see Elon's middle finger, </s><s>[INST] I want to see what you mean by that. Or like when you say fuck it, I'm gonna do the biggest country whatever the fucky wants, right, [/INST] fuck you fuck anything that gets in his way that he can afford to push out of </s><s>[INST] his way and you're saying he's not actually even doing that enough. No, I mean he's not going please, I'm gonna go, [/INST] Ellen is doing fine with his money, I just want him to enjoy himself have the most, you know Dionysus, </s><s>[INST] but you're saying mars is playing it safe, [/INST] he doesn't know how to do anything else. He knows rockets. Yeah. And he might no some physics at a fundamental level. </s><s>[INST] Yeah, I guess. Okay, just let me just go right back to how much physics do you really? How much brilliant breakthrough ideas on the physics side do you need to get off this planet? [/INST] I don't know. And I don't know whether, like in my most optimistic dream, I don't know whether my stuff gets us off the planet, but it's hope it's hoped that there's a more fundamental theory that we can access that we don't need. Um you know whose elegance and beauty will suggest that this is probably the way the universe goes. Like you have to say this weird thing, which is this I believe and this I believe is a very dangerous statement. But this I believe I believe that my theory points the way now Ellen might or might not be able to access my theory. I don't know. I don't know what he knows but keep in mind why are we also focused on yuan? It's really weird. It's kind of creepy too, </s><s>[INST] why he's just a person who was just asking the the obvious questions in doing whatever he can. But he [/INST] makes sense to me. You said craig venter makes sense to me. Jim Watson makes sense to me, </s><s>[INST] but we're focusing on Ellen because he's somehow is rare. [/INST] Well that's the weird thing. Like we've come up with a system that eliminates all Ellen from our pipeline and Ellen somehow uh snuck through when they weren't quality adjusting everything, you know? </s><s>[INST] And this this idea of uh of disk distributed idea suppression complex, is that what's bringing the echelons of the world down? [/INST] You know? It's so funny, like he's asking joe Rogan, like, is that a joint? You know? It's like, well what what will happen if I smoke it? What will happen to the stock price? What will happen if I scratch myself in public? What will happen if I say what I think about Thailand or covid or who knows what? And everybody's like, don't say that, say this, go do this, go do that. Well, it's crazy making, it's absolutely crazy making and if you think about what we put through people through um we we need to get people who can use F. U. Money, the F you money, they need to insulate themselves from all of the people who know better because the my nightmare is that why did we only get one, Ellen? What if we were supposed to have thousands and thousands of gallons? And the weird thing is like this is all that remains. You're you're looking at like Obi one and Yoda and it's like this is the only this is all that's left after ex uh Order 66 has been executed and that's the thing that's really upsetting to me is we used, we used to have Elon's five deep and then we could talk about Ellen in the context of his cohort. But this is like if you were to see a giraffe in the arctic with no trees around you'd think why the long neck what a strange sight. You know </s><s>[INST] how do we get more nylons? How do we change these? So I I think the U. S. So we know M. I. T. [/INST] And Harvard. </s><s>[INST] So maybe returning to our previous conversation, my sense is that the villains of the world are supposed to come from M. I. T. And Harvard. And how do you change? [/INST] Let's think of one that M. I. T. Sort of killed have any names in mind, Aaron Swartz leaps to my mind. Yeah. Okay. Are we Emmett supposed to shield the Aaron Swartz is from I don't know journal publishers or are we supposed to help the journal publishers so that we can throw 35 year sentences in his face or whatever it is that we did that depressed him. Okay so here's my point. I want it to go back to being the home of Aaron Swartz and if you want to send Aaron Swartz to A state where he's looking at 35 years in prison or something like that. You are my sworn enemy. You are not mitt you are the traitorous uh irresponsible middle brow pencil pushing green eye shade fool that needs to not be in the seat at the presidency of M. I. T. Period the end, get the funk out of there and let one of our people sit in that chair </s>
<s>[INST] So it's it's nice to focus not on those brains states, but instead on the shifting [/INST] right I do. This morning I woke up a little bit earlier than I would have liked. I used this reverie app. That's research backed R E V E R I dot com, there's a free version of it and or you can try it for free. So I feel </s><s>[INST] that hypnosis [/INST] for hypnosis and I do a self hypnosis to put me back into sleep and if I can't sleep, just put me into a state of deep relaxation. I would I would put hypnosis under the category of NsD our yoga mudra under the category of NsD are there now some N. S. D. R. Scripts online? If you just go to Youtube that are you can just listen to and </s><s>[INST] do you like those? [/INST] I do, yeah. I think the one from Made for is quite good. I have an affiliation with them but it's free. So I feel comfortable mentioning it. I do. I I really like the reverie app. Um I can vary and as you the more you do them, the more quickly you can shift your brain into a state of deep relaxation. I will sometimes stop mid podcast if it's sometimes our recordings to go 78 hours and I'll stop and I'll do a one minute hypnosis. They have one minute hypnosis. Inside reverie you're only going to you're only going to find that one minute hypnosis is effective if you Are routinely doing 10 and 15 minute hypnosis. In addition to that meaning, I do it every other day or so. 10 or 15. </s><s>[INST] So there is there a Youtube one minute hypnosis. [/INST] There are but inside of reverie as well you can find them online a really </s><s>[INST] good [/INST] um Yeah so reverie is good. And then Michael Sealey, S. E. A. L. E. Y. He has some long hypnosis scripts. But again these are all free and you know there's a lot of good research now on the neural networks and it shifts your so called default network, the default mode network, it shifts how much of your forebrain you're using. And it also is very, very good if you, I get so many questions about, hey, I'm really upset. I found out about my girlfriend's sexual past or hey, I'm so upset. I found out that my boyfriend was cheating or oh, someone so died. How do I get over these emotions? How do I deal with them? And hypnosis has shown to be very useful for people to learn to bring themselves into a state of deep relaxation to literally project in their mind's eye. These very intense things that they don't like. And then for people to associate with other emotions in their body to learn to be calm while feeling your feelings to dissociate the mind body communication to some extent, just observe the feelings, observe them and start to associate them with positive experiences. You're an android guy so soon it should be available on android and </s><s>[INST] then it doesn't exist for me. [/INST] Yeah, I know, you know, I don't get </s><s>[INST] android is the device of the people. All you elitist people with your iphone. [/INST] But tell me this about android now now you want to, this is the one thing that gets me because I'm very close to someone who uses an android phone. I feel like that. </s><s>[INST] So you, you have great people in your life that's good to know [/INST] know the messages always look green to me, but I answer yours despite that. Um but they, I feel like the android phones are very trigger happy, like anything I touch does something whereas the apple phone is kind of built for like a Macaque monkey to be able to operate, which is great for me because I'm more of a Macaque monkey and you're a more sophisticated ape. I think like you have to be </s><s>[INST] more sensitive. You [/INST] have, you have, you have, you know, I mean I've got fat fingers, you know, clumsy fingers, </s><s>[INST] you know the android is too well, maybe you need to soften your touch. [/INST] What I would do is go into the most sort by most popular um because there's some older ones that I really like and it generally skills with that. So I'll do the this one, the hypnosis for clearing subconscious um negativity, that's an hour long one, the sleeping anxiety 1 40 minutes. But those you listen to as you fall </s><s>[INST] asleep as you fall asleep, [/INST] we're going to do this now </s><s>[INST] let's listen to it. [/INST] And I have created this hypnosis recording for you to help you and </s><s>[INST] this is the voice. How often does the voice pop up [/INST] and at the same time you don't watch it, you just listen to your anxiety. Now. One of the most important things of any self hypnosis experience is to know and understand people really should know that stage hypnosis is about the hypnotist getting you to do things you wouldn't normally do self hypnosis which is what we're talking about here reverie and this is about you getting your brain into the state that you want. And um again I mean there's a ton of neuroimaging data and work on trauma and pain relief. And our labs are working on this with David Spiegel's lab. I really encourage people to explore Nasdr. And if this feels a little too wacky and out there then I would just put in N. S. D. R. Into Youtube and there's some good honest er scripts. </s><s>[INST] Yes that's by the way, uh Sandra is a is a fan of your podcast that's okay, we don't [/INST] need to play. Yeah so I don't know him and uh but I would get a lot of media outlets picked up on his love of N. S. D. R. And I have to imagine running google involves a lot of juggling a lot of </s>
<s>[INST] It's kind of fascinating to think that the universe created us. Mhm. Yeah. And eventually we've built telescopes to look back at it, to look back at its origins and to wonder how the heck the thing works. [/INST] It's magnificent. Needn't have been that way, right? And this is one of the, you know, the multiverse sort of things. You know, you can alter the laws of physics or even the constants of nature, seemingly inconsequential. Things like the mass ratio of the proton and the neutron, you know, wake me up when it's over, right? What could be more boring. But it turns out you play with things a little bit like the ratio of the mass of the neutron to proton. And you generally get boring universes only hydrogen or only helium or only iron. You don't even get the rich periodic table, let alone bacteria. Para mi je slugs and humans. Okay, I'm not even anthropomorphic and anthropology centralizing this to the degree that I could even a rich periodic table wouldn't be possible if if certain constants weren't this way. But but they are and that to me leads to the idea of a multiverse that you know that the dice were thrown many many times and there's this cosmic archipelago where most of the universes are, are boring and some might be more interesting, but we are in the rare breed. That's really quite darn interesting and if there were only one and maybe there is only one, well then that's that's truly amazing. </s><s>[INST] We're lucky, [/INST] we're lucky but I actually think there are lots and lost just like there are lots of planets. Earth isn't special for any particular reason. There are lots of planets in our solar system and especially around other stars and occasionally there are gonna be ones that are conducive to the development of complexity culminating in life as we know it. And that's a beautiful story. </s><s>[INST] I don't think there's a better way to end it, Alex is a huge honor. One of my favorite conversation I've had in this podcast. Thank you so much for talking with us [/INST] for the honor of of having been asked to do this. </s><s>[INST] Thanks for listening to this conversation with Alex Filippenko and thank you to our sponsors neuro the maker of functional sugar free gum and mints that I used to give my brain a quick caffeine boost. Better help. Unlike therapy with a licensed professional master class, online courses that I enjoy from some of the most amazing humans in history and cash app. The app I used to send money to friends. Please check out these sponsors in description to get discount and support this podcast. If you enjoy this thing, subscribe on Youtube, review it with five stars on apple podcast, follow on Spotify. Support on patreon, connect with me on twitter Alexis Friedman and now let me leave you with some words from Carl Sagan, the nitrogen in our DNA, the calcium in our teeth, the iron in our blood. The carbon in our apple pies were made in the interiors of collapsing stars. We are made of star stuff. Thank you for listening and hope to see you next time. [/INST] </s>
<s>[INST] humility. I think in your mind, you're on humility somehow tied to the Christian concept of humility. [/INST] And so you're kind of allergic to the word. Well, absolutely. Well, absolutely. Because it's part of, if you look at the cardinal virtue as a cardinal sins in Christianity, pride is a cardinal sin and humility is a cardinal virtue. But they don't mean it in this sense because they're happy to tell you how to live. They're happy to be philosopher kings over your life and they believe that's being humble. And you should be humble, by the way, in listening to the Pope or listening to God because what do you know? You know nothing. God knows everything. So you should shut up and do what you're told. That's the sense in which I don't think you should be humble. I mean, it's a sense in which I always use the example of Abraham, right? God comes to Abraham and says, go kill your oldest son, your only son, right? Your only son, go kill him. It's like, and what does Abraham do? He says, yes, sir, I'll follow. And he's a moral hero for Judaism, Christianity, and Islam. He's a moral hero because he follows orders, because he's humble. I would tell God to go to hell. Screw you. I'm not killing my son. There's no way. I mean, he killed his son, so it's only fair. Well, this is before he kills us. I didn't know that. But no, but part of the evil, part of the evil of Christianity is that he's killed his son in the most torturous form of death possible. I mean, the whole story of Jesus is one of the most immoral, unjust stories ever told, and that Christians elevate this to a position of... I'd love to have this conversation with Jordan, right? Jordan Peterson. The idea of elevating... That'll never happen. No, it won't. But elevating Jesus, exactly. Elevating Jesus to a superhero status for one of the most immoral acts in human history is horrific. So yeah, I mean, I'm opposed to God sacrificing his own son, never mind my son. That'll never happen. No, it won't. Let him go do it to his own son. But he didn't kill Isaac. He killed the goat. The story's about Abraham, not about God. First of all, God is mean, right, to put Abraham through that. But Abraham has to assume that he's going to kill his son and he's going to do it, and he stopped. So the whole point is obedience. That's what humility leads to. It leads to the opposite of the story you were telling. It leads to people saying, yes, I should be told what to do. Where's the authority who actually knows something? Because I don't know anything. No, I know a lot, and I know a lot about my life. So you stay away from my life because I have pride in my life. The science is settled, right? Look at these experts. Who am I to argue with these experts? They tell me to drink dog pee? What am I, not to drink dog pee? </s><s>[INST] No. We're on island again. Back to the island. Let's go to the island- I live on an island. Everything's an island in some context. Earth is an island. This universe is an island in a multiverse. Um, I live on there's no multiverses. There's only one universe. All right, so [/INST] So let's invite jordan peterson to this island. You wish you wish hold on Hey girl, what's she doing? Lex Lex friedman </s><s>[INST] Look him up. Stop it [/INST] Lex who? </s><s>[INST] I don't know. Lex says it's big of a following almost. He's getting us jordan. I know jordan. I know his family actually through Jim keller who's his relative. He's an engineer. So, uh, and I just talked to sam Who is perhaps a little bit aligned in some sense on your perspective on religion and so on So let me ask is there some other things? [/INST] Sam harris. Yeah. Oh, sorry. Sam harris. Is there some Legion? Yes, but but other things no He's on first name relationship with these guys </s><s>[INST] I simply you know that you went out the window i'm just a natural language processing model That uh, I assume that once I mention jordan peterson, it becomes an obvious statement what sam means This is how neural networks think this is how robots think michael. You should know this Um, I thought by now you'd be a scholar Humility Everything can teach you something even a robot. Okay So, uh, do you think there's value in religion or broader? Do you think there's value in myth and as we've been talking about the value of reason? Do you think it's possible to argue in society as we grow this the population of our little island? That there's some value of common myths of common stories of common religion [/INST] There was value. There is no value today so Human beings need explanations, right? They need a philosophy to guide their life. They need ethics. They need Some explanation of what's going on in the world, right? And it's no accident that the early religions had a river god and it had a a Sun god and a moon god because they everything they didn't understand they they made god, right? So so they had multiple gods because they didn't understand very much As human understanding evolved increased as we knew reality more Right. We we came to the conclusion of you know, this is very inefficient to have all these gods This is a genius of judas. And right let's just have one bucket to put all the stuff we don't know it and we'll call it one god. As we gain new knowledge, we can just take it out of the bucket that's god and put it into the bucket of science. At some point though, at some point, and that point suddenly came during the scientific revolution, I think, we could come to the conclusion that no, we don't need this bucket that's called god to explain the things that we don't know. We can say we don't know and we're learning and slowly our knowledge is increasing and yet there's a lot more that we don't know, but we don't need to throw it into some bucket that's called god in order to have it. I think that's true for morality and it's true for everything else. As we gain the tools to understand what morality requires, we don't need a set of commandments. We can figure out morality from human nature and from reality. I don't think we need religion anymore. I think religion needed to die probably about 200 years ago and was dying, I think, up until Kant. It seemed to be dying and one of Kant's missions, as he says, is to revive religion against attack of reason and enlightenment. Now mythology is a little different because it depends what you mean by mythology. Certainly we need stories and certainly we need art. Rand writes about this a lot and she's an artist and she writes and I'm a huge fan of the romantic manifesto, which I think is one of her underappreciated masterpieces. Oh, I hate it. Okay, that's okay. Yeah, so I think we have a real need as a conceptual being. We have a need for aesthetic experiences. We have a need to concretize abstractions, to concretize abstract ideas, to concretize the complex nature of the world out there. And that's what painting sculpture, to an extent music, but painting sculpture literature, does for us. So to the extent that mythology serves that purpose, it's just art. To the extent it serves another purpose, that is that it's a way for the gods to communicate with us so it fit some kind of of pre-existing mental construct that we have, again, kind of a conscientious perspective, right, that we have these categorical imperatives and this mythology links up to that, then I think it's false, it's not helpful and destructive. So I believe religion today is a destructive force of planet Earth. I think it's always been a destructive force. It was just a necessary force, right? You needed an explanation. People needed something to believe in. Once you get philosophy, and once you get philosophy that starts explaining real life, real world, you don't need religion anymore. And indeed, it becomes a destructive force. And you look around the world today, it's an unbelievably destructive force. Everywhere touches is bad for life. Again, mythology depends. Art is </s>
<s>[INST] You know what I mean? So there's- Oh, you mean like that particular vehicle will not be returning back to Earth. It'll need to be modified. Because the ultimate is to have one Starship that goes to Mars, lands on Mars and takes off of Mars, lands back on Earth and is reused again, [/INST] over and over and over. And there's a chance that you have just a cycler, just if you're at the end of the day, you're just really trying to see what is most feasible, what's the most efficient? You literally have a vehicle dedicated to Mars. Mars is easy to do a single stage orbit. It's a lot lower gravity, a lot thinner atmosphere. You can easily do a single stage orbit, you get into orbit, you'd park to a dedicated, you know, transfer vehicle that goes between Earth and Mars. It only stays in space. You don't have heat shields, you don't have landing legs, you don't have all these things that you need. And ideally, it's nuclear powered, so it's super efficient. That gets you back to Earth. Once you're at Earth, rendezvous again with another landing starship. And that starship might be a horizontal runway starship. You know like, there's no, I don't see the, and I think ultimately it'll win out where we don't have a one size fits all. I think that's the flaw of the space shuttle, really is that it was trying to do everything and ended up kind of doing nothing well. But that's, I think what SpaceX has proven, I mean, SpaceX already has variants coming. There's already going to be a dedicated lunar lander for NASA, for the Artemis program. There's already going to be a tanker variant. There's already going to be likely just a pure cargo version. There's likely going to be a human version. We'll likely see evolutions of this thing happen, </s><s>[INST] you know, relatively quickly. And once it's all working, it's only a matter of weeks before people riding on it will be complaining about the speed of the wifi. As the old like Lucy K joke with like, you're flying on a chair through the air. It's incredible. [/INST] You didn't even- Air. It's incredible. </s><s>[INST] But no, this existed and now you're complaining about it. It's great. Exactly. So you tweeted fun fact about Starship by doing the flip around 500 meters versus higher up, like 2000 meters. The difference in Delta V is 500 meters per second. That's a 20 ton fuel saving, which means basically 20 tons more you can put into orbit. That's more than a Falcon 9 has ever launched just by flipping later. That's really interesting. So there that was the decision too, to flip close to the ground. Yeah. [/INST] Yeah. The closer to the ground, the better. The more again, the more the atmosphere is doing work. And you know, we get into that video. Really dives into like gravity losses and gravity drag. The more time you're spent, every second that your rocket engine is running, earth is stealing 9.8 meters per second of acceleration against you. There's just inherently 9.8 meters per second squared of acceleration. So every second that engine is running, the first big majority of your thrust is actually being just stolen by Earth's gravity well. So if the longer you're fighting that, the more inefficient it is. So the best thing would be you flip at 100 meters off the ground, you light all your engines to maximum thrust, and you pull 50 Gs, you land on a dime, basically. Obviously there's no margin there, and there's diminishing returns on that gravity loss thing in your high thrust weight ratios. So that's a pretty good compromise. Yes, it looks scary, but they could be a lot more aggressive with that yet and squeeze out even a little bit better performance, but there are diminishing returns. So that's kind of the magic number we've seen so far today, but we'll likely see that be </s><s>[INST] played with. You've attended some of these, what does it feel like to see Starship in person? First of all, when it's just sitting there stacked, and second of all, when it's doing some of these tests, some of these maneuvers. [/INST] Well, first off, if you have the freedom of traveling and happen to live within a reasonable, either by plane or car, it's worth going down to South Texas. So Starbase is right on the border of Mexico and the United States and the various other Antipa, Texas, right along the Rio Grande. And it's insane because it's right along a public highway. You can literally, anyone can drive down this, assuming it's not closed for testing, because they do close the highways during the week, a decent amount while they're doing tests. But sans any of those days, anyone can just drive down and see these things up close and personal with their own eyes. Like we're talking from 100, 200 meters away. So two football fields away from the world's biggest, most powerful rocket. Imagine being able to do that during the Soviet Union and during the N1 and the Saturn V. Imagine just being able to drive up right next to the launch pad. There's no way. And so to have this kind of access to this program is so incredible. The craziest thing is when you're driving out on Highway 4, it's bumpy, it's riddled with potholes now because of all the insane amount of trucks having to go out there and traffic and you're going through this, it's just this weird, you're like, where am I? You occasionally are seeing, like you can kind of see the, I mean, you can see Mexico out your right window as you're driving down this highway, you're just sitting there, like where am I? Where am I going to turn this corner? And the trees and the brush kind of clear out and all of a sudden you get a sense of everything on the horizon. And at that point you're pretty much five miles on the nose or eight kilometers away. And from there you can just see through the heat haze, through the atmospheric distortion and you just see this weird, like it looks like a city almost on the horizon. There's tons of these tall buildings, there's a weird ominous launch tower thing with arms wide open and sometimes, and a giant metal rocket. And it just looks so, so weird. I mean, the word surreal, I think by definition, I think if you are expecting it, it's not surreal. I think surreal kind of means like unexpected surprise or whatever, you know? Even if you're expecting it, even if you've seen pictures, even if everything, it is surreal. </s>
<s>[INST] So taking the the physical intuition literally and then having that drive the the mathematics by [/INST] now, we have so confident about many such examples that has affected modern mathematics in ways like this that we are much more confident about our understanding of what string theory is. These are another aspects other aspects of why we feel string theories, crisis still doing these kind of things. </s><s>[INST] I've been hearing your talk quite a bit about string theory, Landscape and the swamp land. What the heck are those two [/INST] concepts? Okay, very good question. So, let's go back to what I was describing about Fine man. Fine man was trying to do these diagrams for gravitas on and electrons and all that. He found that he's getting infinities. He cannot resolve. Okay, the natural conclusion is that field theories and gravity and quantum theory don't go together and you cannot have it. So, in other words, a few theories and gravity are inconsistent with quantum mechanics. Period string theory came up with examples but didn't address the question more broadly. That is it true that every field theory can be coupled to gravity in a quantum mechanical way. It turns out that final was essentially right. Almost all particle physics theories, no matter what you add to it. When you put gravity in, it doesn't work. Only a rare exceptions work. So string theory. Are those rare exceptions. So therefore the general principle that Fireman found was correct. Quantum field theory and gravity and quantum mechanics don't go together except for jules, exceptional cases. There are exceptional cases. Okay. The the total vastness of quantum field theories that are there. We called the set of quantum field theories, possible things which ones can be consistently coupled to gravity. We call that subspace the landscape. The rest of them we call the swampland. It doesn't mean they're bad quantum field theories. They're perfectly fine. But when you couple them to gravity, they don't make sense unfortunately. And it turns out that the ratio of them, then the number of theories which are consistent with gravity to the one which without the ratio of the area of the landscape To the swamp land. In other words, is measured zero. </s><s>[INST] And so the swamplands infinitely large. [/INST] The swamplands infinitely large. So let me give you an example, take a theory in four dimension. With matter. With maximum amount of supersymmetry. Can you get It turns out a theory in four dimension? With maximum amount of supersymmetry is characterized just with one thing a group, what we call the gauge group. Once you pick a group, you have to find the theory. Okay, so does every group makes sense? Yeah. As far as quantum field theory, every group makes sense. There are infinitely many groups. Their infant many quantum field theories. But it turns out there are only a finite number of them which are consistent with gravity out of that same list. So you can take any group but only five number of them. The ones who is what we call the rank of the group. The ones whose rank is less than 23. Anyone bigger than ranked 23 belong to the swamp land. There are infinitely many of them. They're beautiful field theories, but not when you include gravity. So, so then this becomes a hopeful thing. So in other words in our universe we have gravity. Therefore we are part of that dual subset. Now is this jewel subset, small or large. It turns out that subset is humongous but we believe still finite. The set of possibilities infinite. But the set of consistent ones. I mean the set of quantum features are infinite, but the consistent ones are finite but humongous. The fact that the humongous is the problem. We are facing a strength theory. Because we do not know which one of these possibility is the universe we live in. If we knew we could make more specific predictions about our universe, we don't know. And that is one of the challenges when string theory, which point on the landscape, which corner of this landscape do we live in? We don't know. So what do we do? Well, there are there are principles that are beginning to emerge. So I will give you one example of it. You look at the patterns of what you're getting in terms of these good ones, the ones which are in the landscape compared to the ones which are not. You find certain patterns, I'll give you one pattern you find in the older ones that you get from string theory. Gravitational force is always there, but it's always always the weakest force. However you could easily imagine field theories for which gravity is not the weakest force for example, take our universe if you take mass of the electron, if you increase the massive electron by a huge factor, the gravitational attraction of the electrons will be bigger than the electric repulsion between two electrons and the gravity will be stronger. That's all it happens. That is not the case in our universe because electronic is very tiny and mass compared to that just like our universe, gravity is the weakest force we find in all these other ones which are part of the good ones. The gravity is the weak force. This is called the weak gravity conjecture. We conjecture that all the points in the landscape have this property, our universe being just an example of it. So there are these qualitative features that we're beginning to see. But how do we argue for this? Just by looking patterns? Just by looking strictly has this No, that's not enough. We need more more reason. More better reasoning. And it turns out there is the reasoning for this turns out to be studying black holes, ideas of black holes turn out to put certain restrictions of what a good quantum filter it should be. It turns out using black hole. And the fact that the black holes evaporate the fact that the black holes evaporate gives you a way to check the relation between the mass and the charge of elementary particle. Because what you can do, you can take a charged particle and throw it into a charge black hole and waited to evaporate. And by the looking at the problems of evaporation, you find that if it cannot evaporate particles whose mass is less than their charge, then it will never evaporate, you'll be stuck. And so the possibility of what I call it operation forces you to have particles whose mass is sufficiently small so that the gravity is weaker. So you connect this fact to the other facts. So we begin to find different facts that reinforce each other. So different part of the physics reinforce each other and once they all kind of come together, you believe that you're getting the principal correct. So we gravity conjecture is one of the principles we believe in as a necessity of these conditions. So these are the predictions strength we are making. Is that enough? Well, it's qualitative. It's a semi quantity. It's just a mass of the electron should be less than some number. But that number is if I call that number one, the mass of the electron turns out to be 10 to the minus 20 actually. So it's much less than one. It's not one. But on the other hand, there's a similar reasoning for a big black hole in our universe. And if that evaporation should take place, gives you another restriction, tells you mass of the electron is bigger than 10 is now in this case bigger than something. It shows bigger than 10 to the minus 30 in the blank unit. So you find uh huh The mass of the electron should be less than one but bigger than 10 to the minus 30 in our universe. The mass of the electron sense the minus 20. Okay, now this kind of you could call post diction but I would say it follows from principles that we now understand from strength Three. First Principles. So we are making beginning to make these kinds of predictions which are very much connected to aspects of particle physics that we didn't think are related to gravity. We thought just take any electron mass you want. What's the problem? It has a problem with gravity. </s>
<s>[INST] You're of course the scientists are studying humans as a collective. I tend to be just one person's scientist of just looking at myself and you know, I play when these deep thinking deep work sessions, I'm very cognizant like in the morning that there's times in my mind is so like eloquent at being able to jump around from ideas and hold them all together. And I, I'm almost like I stepped back from a third person perspective and enjoy that whatever that mine is doing. I do not waste those moments. I, and I'm very conscious of this like little creature that woke up that's only awake for if we're being honest, maybe a couple hours a day early part of the day for the early part of the day, not always early part of the day for me is a very fluid concept. You're one of the yeah, yeah, you're being single one of the problems single and no meetings. I don't schedule any meetings. I I will, I've been living like a 28 hour day so I like uh drifts so it's all over the place, but after a traditionally defined full night's sleep, uh whatever the heck that means, I find that like in in those moments there's a clarity of mind that's just that everything is effortless and it's the, it's the deepest dives intellectually that I make and I I'm cognizant of it and I try to bring that to the other parts of the day. They don't have it And treasure them even more in those moments because they only last like five or 10 minutes. Because of course in those moments you want to do all kinds of stupid stuff that are completely, is worthless. Like check social media or something like that. But those are the most precious things in, in, in an intellectual life is those mental moments of clarity and I wonder I'm learning how to control them. I think caffeine is somehow involved. I'm not sure exactly. Well, [/INST] because if you learn how to titrate caffeine, everyone's slightly different with us what they need. But if you learn to titrate caffeine with time of day and the kind of work that you're trying to do, You can bring that autonomic arousal state into the close to perfect place and then you can tune it in with, you know, sometimes people want a little bit of background music, sometimes they want less these kinds of things. The early part of the day is interesting because the one thing that's not often discussed is this transition out of sleep. So there's a book um I think it's called Winston Churchill's nap and it's about naps and and the transition between wake and sleep as a valuable period. Um I've a long time ago um someone who I respect a lot, I was mentoring me, said be very careful about bringing in someone else's sensory experience early in the day. So when I wake up I'm very drowsy, I sleep well but I don't emerge from that very quickly. I need a lot of caffeine to wake up and whatnot. But there's this concept of getting the download from sleep, which is, you know, and sleep. Your you were essentially expunging the things that you don't need. The stuff that is meaningless from the previous day, but you were also running variations on these algorithms of whatever it is you're trying to work out in life on short time scales like the previous day and long time scales like your whole life and those lateral connections in layer five of the of the neocortex are very robustly um active and across sensory areas and you're running a an algorithm or, you know, a brain, it's a brain state, they will be useless in waking, you wouldn't get anything done, you'd be the person talking yourself in the hallway or something about something that no one else can see. But in those states you do that. The theory is that you arrive at certain solutions and those solutions will reveal themselves in the early part of the day unless you interfere with them by bringing in social media is a good example of you immediately enter somebody else's spacetime sensory relationship. Someone is the conductor of your thoughts in that case. And so many people have written about this um what I'm saying isn't entirely new, but allowing the download to occur in the early part of the day and and asking the question, am I more in my head or extra um I'm more of an introspective or extra receptive mode and depending on the kind of work you need to do, it sounds like for you, it's very introspective in the end. Very you've got a lot of thinking going on, a lot of computing going on, allowing yourself to transition out of that sleep state and arrive with those solutions from sleep and plug into the work really deeply and then and only then allowing things like music news, social media doesn't mean you should talk to loved ones and see faces and things like that, but some people have taken this to the extreme when I was a graduate student at Berkeley, there was a guy. Um there is a professor, brilliant, odd, but brilliant. Um who was so fixated on this concept that he wouldn't look at faces in the early part of the day because he just didn't want to be anything else to impact him. Now, he didn't have the most um rounded life I suppose. But if you're talking about cognitive performance, this could actually be very beneficial. </s>