Datasets:

ianiket23

/

podcast_llama_chat_format-5k

like 0

<s>[INST] Is your style relatively unique in the 81 kg [/INST] division, It was relatively unique for Kayla I and jimmy Up until 2016. Now, since 2016, you can see a lot of what we used to do throughout most of Europe and even Asia, like you're starting to see some of those techniques that you didn't see before starting to get implemented because when I was When I was gearing up for 2015, I had such a slew of injuries that entire calendar year that I never should have made it to Rio, I should have called it quits at the end of 2015 because I suffered that major concussion in february, I stepped on a mat in May for the first time, I lost five straight tournaments, I left the national team, went to Japan one Pan am Games, got a bacterial infection at the world's almost had my leg cut off, tore my S. I. Joint later on that year and then took fifth in Japan. And when you look at like the calendar year as a whole, like the world should have treated me like I was washed up. Like this guy hasn't been training, he hasn't been doing anything, but I took fifth in Japan. Now how does a guy that hasn't trained all year? Take 5th at one of the hardest tournaments in the world on two weeks of training? Because they were fighting the guy I used to be not the guy I was at the tournament, which means they were competing under the idea of like, what is he really capable of not? What have I brought to the table today? Mm </s><s>[INST] And that just gave you the confidence [/INST] and that told me that like, well if I can take fifth and I'm this baggage, you know right now, wait until I'm healthy and I'm back in shape, then they're not gonna know what hit them. </s><s>[INST] One of the essential components of being the number one in the world are up in that places, that confidence to self belief [/INST] and the rest of the world believing it, you can have all the confidence in the world. But if the rest of the room doesn't buy it, it's nothing </s><s>[INST] that's funny. It's like there's certain people right with Tyson, [/INST] uh, my guys all understand he could not train and they're still scared. Yeah, right? Like he doesn't have to work out that hard anymore. </s><s>[INST] There's several judo, you know, this way better. But from a spectator perspective, like Ilias Iliadis is like that. He's one of them. It's like [/INST] he's portrayed over the years. I </s><s>[INST] was so scared of that guy. It's interesting. People were scared of you too. [/INST] People just gave a certain level of respect to my skill set and whether I had a bad way cut, it didn't have a bad way cut or not trained for the last three months, which never happened. I'm just saying they were going to fight the persona And it's an important distinction when you're looking at the top five because everybody coming up their training against the persona, not who you are. Even I did that at a younger age. That's why I would always go to people's hometowns because like, I don't, I don't care about the persona. I want to know what you do day in and day out when I couldn't be the Russian, I told jimmy sent me to Russia, I need to, I need to understand and see it with my own eyes, what they do out perform so that I can believe that I can beat them. </s><s>[INST] You can ask. And this is a small tangent. Uh Dagestan has produced some incredible wrestlers. I don't know what the story with judo is, where the source of source of greatness in Russia is for judo. But what do you make of Dagestan? Why why what is it in the culture of their or Russia broadly that produces greatness. [/INST] Specifically in the combat sports? </s><s>[INST] I don't know. Yeah, specifically in the combat sports, sorry, But I don't know if you want to draw a distinction between wrestling and judo. Almost curious. Do you understand the difference? Is there in the culture [/INST] are still a combat sport to them? They're still in that same like realm of they're taking young kids and that that's what they do. </s><s>[INST] So it could be speaks very highly of judo. Yeah, like it's funny, could be Vladimir Putin, [/INST] people don't get it, but like judo is like one of the premier sports in the world, but we don't understand </s><s>[INST] it. It's not just popularity, so definitely popularity, but also like this respect. And there's a certain thing which is why I really value judo internationally. You don't get this in the United States, but internationally there's an understanding like later in life when you're a scientist meeting a businessman when you both have done judo, there's this like nod of respect. It's so interesting. Uh there's very few sports like that. You know, basketball doesn't have. I mean, I don't know almost any sport like that and it's [/INST] fascinating wrestling has that in the US it is the U. S. Only the rest of the world doesn't </s><s>[INST] do that. There's a few like you could see that in like Iran or something like that with respect. Rustling in that kind of way. Yeah it's um [/INST] Put Judo on like a global scale is probably that only one due to its like physicality and the hardships that you have to go through to reach that upper level. </s><s>[INST] So why do you think Dagestan, why do you think could be as as good as he is? Is there is this just the raw genetics of the human or is there something about the system, [/INST] the system, it all has to do with the system. </s>

<s>[INST] But nevertheless it's how big of a psychological burden is that? [/INST] It's huge. It's terrible. I mean it's </s><s>[INST] very it's very comforting to be the parental. I mean I don't know. I I treasure I mean we were just talking about M. I. T. We can until I can intellectualize and agree with everything you're saying. But there's a comfort a warm blanket of being with an institution and up [/INST] until um Aaron Swartz, let's say in other words now if I look at the provost and the president as Mommy and daddy, you did what to my big brother, you did what to our family? You sold us out. In which way, what secrets left for china you hired? Which workforce you did what to my wages? You took this portion of my grant? For what purpose? You just stole my retirement through a fringe. Right? What did you </s><s>[INST] do? But can you still, I mean thing is about this view you have is it often turns out to be sadly correct. What is the thing? And but let me just in this silly hopeful thing, do you still have hope? And institutions, can you within your psychologically I'm referring not intellectually because you have to carry this burden. Can you still have a hope? Like, within you jake when you sit home alone? And as opposed to seeing the darkness within these institutions, seeing a hope [/INST] Well, but this is the thing I want to confront. Not for the purpose of ab dust up. I believe, for example, if you've heard episode 19, that the best outcome is for Carol Greider to come forward, As we discussed in episode 19 </s><s>[INST] with your brother. But and say, you know what I screwed up. [/INST] He did call, he did suggest the experiment. I didn't understand that it was his theory that was producing it. Maybe I was slow to grasp it, but my bad and I don't want to pay for this bad uh choice on my part, let's say um for the rest of my career, I want to own up and I want to help make sure that um we do what's right with what's left </s><s>[INST] and that's one little case within the institution. They would like to see made. I [/INST] would like to see em it very clearly come out and say, you know, Margot O'toole was right when she said, David Baltimore's lab here um produced some stuff that was not reproducible with Teresa Mini, She carries research. I want to see the courageous people. I would like to see the Aaron Swartz wing of the computer science department. Yeah, I wouldn't know. Let's think about it. Wouldn't that be great if they said, you know, an injustice was done and we're gonna we're going to right that wrong. Just as if this was alan turing, </s><s>[INST] which I don't think they have righted that wrong. [/INST] Well then let's have the turing Schwartz </s><s>[INST] wing during short, they're they're starting a new college of computing. It wouldn't be wonderful to call it the [/INST] way I would like to have the madam wooing of the physics department and I'd love to have the Emmy nerdier statue uh in front of the math department. I mean like you want to get excited about actual diversity and inclusion. Yeah, Well let's go with our absolute best people who never got there because there is structural bigotry, you know? But if we don't actually start celebrating the beautiful stuff that we're capable of when we're handed heroes and we fumble them into the trash. What the hell? I mean, licks this is such nonsense. We just pulling our head out, you know on everyone's seek them. Should be tattooed if you can read this, you're too close, </s><s>[INST] beautifully put and I'm a dreamer, just like you. Uh so I don't see as much of the darkness genetically or due to my life experience, but I do share the hope from my teeth institution that we care a lot about. You both do. Yeah. And the Harvard Institution, I don't give a damn about, but you do. So I love Harvard, I'm just kidding, [/INST] I love Harvard to it and I have a very difficult relationship and part of what you know when you love a family that isn't working, I don't want to trash, I I didn't bring up the name of the president of M. I. T. During the Aaron Swartz period. It's not vengeance. I want the rot cleared out. I don't need to go after human beings. Yeah, </s><s>[INST] just like you said with the disc formulation, the individual human beings aren't don't necessarily carry the [/INST] it's those chairs that are so powerful that in which they sit, </s><s>[INST] it's the chair's not the human, it's not the humans without naming names. Can you tell the story of your struggle during your time at Harvard? Maybe in a way that tells the bigger story of the struggle of young bright minds that are trying to come up with big bold ideas within the institutions that we're talking about. [/INST] You can start, I mean in part it starts with coffee with uh a couple of Croatians in the math department at MIT. And we used to talk about uh music and dance and Math and physics and love and all this kind of stuff is Eastern Europeans uh love to and I ate it up and my friend Gordana who was an instructor in the MIT Math department when I was a graduate student at Harvard said to me and I'm probably gonna do a bad version of her accent. Here we go. Yeah um will I see you tomorrow at the secret seminar and I said what secret seminar? Eric don't joke? I said I'm not used to this style of humor. Gordon? She's the secret seminar that your advisor is running? I said what are you talking about? Ha ha ha uh you know your advisor is running a secret seminar on this aspect. I think it was like the Chern Simon's in variant, I'm not sure what the topic was again but she gave me the room number and the time and she was like not cracking a smile, I've never known her to make this kind of a joke and I thought this was crazy and I was trying to have an advisor, I didn't want an adviser but people said you have to have one. So I took one and I went to this room like 15 minutes early and there was not a soul inside, it was outside of the Math department and it was still in the same building the science center at Harvard and I sat there and I let five minutes go by let seven minutes go by 10 minutes go by. There is nobody. I thought okay so this was all an elaborate joke And then like three minutes to the hour this graduate student walks in and sees me and does a double take and then I start to see the professor's in geometry and topology start to file in and everybody's like very disconcerted that I'm in this room. And finally the person who was supposed to be my advisor walks in to the seminar and sees me and goes white as a ghost. And I realized that the secret seminar is true, that the department is conducting a secret seminar on the exact topic that I'm interested in, not telling me about it. And that these are the reindeer games that uh, the Rudolph's of the department are not invited to. And so then I realized, okay, I did not understand it. There's a parallel department and that became the beginning of an incredible odyssey um in which I came to understand that the game that I had been sold about publication about blind refereeing about openness and uh scientific transmission of information was all a lie. I came to understand that at the very top there's a second system that's about closed, closed meetings and private communications and agreements about citation and publication that the rest of us don't understand. And that in large measure that is the thing that I won't submit to. And so when you ask me questions like, well why wouldn't you feel good about, you know, talking to your critics or why wouldn't you think the answer is, oh, you don't know like if you stay in a nice hotel, you don't realize that there is an entire second structure inside of that hotel where like there's usually a worker's cafe in a resort complex that isn't available to the people who are staying in the hotel. And then there are private hallways um, inside the same hotel that are parallel structures. So that's what I found, which was in essence just the way you can stay hotels your whole life and not realize that inside of every hotel is a second structure that you're not supposed to see as the guest. There is a second structure inside of academics that behaves totally differently with respect to how people get dinged, how people get their grants taken away, how this person comes to have that thing named after them and by pretending that we're not running a parallel structure. Um, I have no patience for that one anymore. So I, I got a chance to see how the game, how hard ball is really played at Harvard and I'm now eager to play hardball back with the same people who played hardball with me. </s>

<s>[INST] He's like, look [/INST] at that shiny piece of metal that actually has if you're hungry and you have a choice between a carrot and a lump of gold in the desert. Most people are going to go for the carrot. But his point is is that, uh, the allure of money is that it's basically a concentrated symbol of wealth, but because it doesn't spoil Locke said, you're entitled to have as much money as you're able to garner. All right, then, he says, well, the reality is is that some people are more the word that he used was industrious. He said, some people more industrious than others. All right. Today, we would say smarter, less lazy, more ambitious. He just said that's natural. It's also true. Therefore, he argued over time, some people are going to have a whole lot of property and other people not much at all inequality for lock is natural and beneficial for everyone. His argument was that, you know, the rising tide lifts all boats and that the truly creative and innovative are entitled to relatively unlimited worth because we're all better off as a result. So the point very simply is that, well, that's base. And then you have Adam smith, you know, in the next century with the invisible hand, where Adam smith says everyone pursuing their own selfish, that's not necessarily pejorative. If everyone pursues their own selfish interests, we will all be better off as a result. And </s><s>[INST] what do you think is the flawed in that way as well? [/INST] There's two flaws. One is is that um well one flaw is first of all that, that it is based on an erroneous assumption to begin with, which is that there never was a time in human history when we are, in a social species, </s><s>[INST] in a sense, you don't feel like that where there's uh this emphasis of individual autonomy is a flawed premise, like where there's a there's something fundamentally deeply interconnected between us [/INST] do. I think that Plato and Socrates, you know, and the credo were closer to the truth When they started with the assumption that we were interdependent, then they derived individual autonomy is a manifestation of a functional social system, so when Margaret Thatcher, you're too young, you know, in the 1980s, she said, societies, there's no such thing as societies, there's just individuals pursuing their self interest. So, uh, so that's one point where I would take issue respectfully with john Locke point number two is when Locke says in 16 90 while England's filled up. Um so if you want some land, just go to America, it's empty. Or maybe there's a few savages, they're just kill them. So, and Melville does the same thing in Moby Dick, where he thinks about, will there ever come a time where we run out of whales? And he says no, but we have run out of whales. And so locke was right maybe in 1690 that the world was large and had infinite resources. He certainly wrong today, in in my opinion, also wrong is the claim that the unlimited pursuit of personal wealth does not harm those around us. There is no doubt that radical inequality is tragic psychologically, and physically, it's poverty is not that terrible. It's easy for me to say because I have a place to stay and something to eat. But as long as you're not starving and have a place to be, poverty is not as challenging as being, having the impoverished and close proximity to those who are obscenely wealthy. </s><s>[INST] So it's not the any absolute measure of your well being is the inequality of that well being is painful. Um so maybe just uh, linger on the Jordan Peterson thing in terms of your this agreement in this world, You see, he went through quite a bit, you know, there's been quite a bit of fire, right? And in his defense or maybe his opposition of the idea of equality of outcomes. So looking at the inequality that's in our world, looking at, you know, certain groups measurably having an outcome that's different than other groups, and then drawing conclusions about fundamental uh unfairness, injustice, inequality in the system. So, like systematic racism, systematic sexism, systematic anything else that creates inequality. And he's been kind of uh saying pretty simple things uh to say that uh you know, the system for the most part is not broken or flawed, that the inequality is part of the the inequality of outcomes as part of our world. What we should strive for is the uh you know, equality of opportunity. [/INST] And I do not dispute that as an abstraction. But again, to back up for a second, I do take issue with Jordan's fervent devotion to the free market and his cavalier dismissal of Marxist ideas which he has in my estimation, miss characteristic in his public depictions. Let's </s><s>[INST] get into. So he just seems to really not like um socialism, Marxism communism historically speaking, sort of. Uh I mean, how would I characterize it? I'm not exactly sure, I don't want to, Again, he will eventually be here to defend himself, john locke, Unfortunately not here to defend. Exactly. But what's, what's your sense uh, about Marxism and, and uh, the uh, the way Jordan talks about the way you think about it from the economics, from the philosophical perspective. [/INST] Yeah, well, if we were all here together, I'd say we need to start with Marx's economic and philosophical manuscripts of 1844 before Marx became more of a polemicist. And I would argue that Marx's political philosophy, he's crappy economist. I don't dispute that, but his arguments about human nature, his arguments about the inevitably catastrophic, psychological and environmental and economic effects of capitalism. I would argue every one of those has proven quite right. Marks maybe did not have the answer. But he saw in the 18 whenever he was writing, um, that inevitably capitalism um, would lead to massive inequity that it was ultimately based on the need to denigrate and dehumanize labor to render them in his language a fleshy cog in a giant machine. And uh, it would create a tension and conflict between those who own things and those who made things that overtime would always, you know, the thomas Pickard the guy who writes about capital and just makes the point that return on investment will always be greater than wages. That means the people with money are going to have a lot more, That means there's going to come a point where the economic house of cards falls apart. No, the joseph shoppers of the world, they're like, that's creative destruction, bring it, that that's great. So I think it's Niles Ferguson. He was, he's a historian, he may be at stanford now, he was at Harvard, You know, he writes about the history of money and he's like, yeah, there's been 20 or whatever depressions and big recessions uh, in the last several 100 years, and when that happens, half of the population or whatever is catastrophically inconvenienced, but that's the price that we pay for progress, other people would argue and I would agree with them that I will happily sacrifice the rate of progress in order to flatten the curve of economic destruction to put that in plainer english, um I would um direct our attention to the social democracies that forgetting for the moment of whether it's possible to do this on a scale in a country as big as ours, on all of the things that really matter, you know, gross domestic GDP or whatever, that's just an abstraction. But when you look at whatever the United Nations says, how we measure quality of life, uh, you know, life expectancy, education, you know, rates of alcoholism, suicide and so on. The countries that do better are the mixed economies, their market economies that have high tax rates and exchange for the provision of services that come as a right for citizens. So, </s>

<s>[INST] Can you actually link it, before we turn to the giant magnet and maybe even talk about Spark and all the amazing stuff going on at MIT? What is ITER? What is this international nuclear fusion mega project [/INST] being built in the South of France? So its scientific purpose is a worthy one that it's essentially an anti-fusion device. The thing that you want to see is more and more relative amounts of self-heating. And this is something that had not been seen, although we had made fusion reactions and we'd seen small amounts of the self-heating, we never got to a dominant, this actually goes to this QP business, okay? The goal of ITER, and it shifted around a little bit historically, but fairly quickly became, we want to get to a large amount of self-heating. So this is why it has, its primary feature is to get to QP of around 10. And through this, this is a way to study this plasma that has more higher levels of self-determination around on it. But it also has another feature, which was let's produce fusion power at a relevant scale. And actually they're linked together, which actually makes sense if you think about it, is that because the fusion power is the heating source itself, this means that they're linked together. And so ITER is projected to make about 500 million watts of fusion power. So this is a significant amount, </s><s>[INST] like this is what you would use for powering cities. So it's not just the research, they're really, it is the development of really trying to achieve scale here. [/INST] So self-heating and scale. Yeah, yes. So this meant then too, is the development of an industrial base that can actually produce the technologies like the electromagnets and so forth. And to do it with, it is a Tokamak, it is one of these, yes. But very interesting, it also revealed limitations of this as well too. Like what? Well, it's interesting is that it is clearly a, on paper and in fact, and in practice as well too, the world and very different political systems and you consider at least geopolitical or economic rivals or whatever you want to use it. Like working towards a common cause and one that we all think is worthy is very like, okay, that's very satisfying. But it's also interesting to see the limitations of this. </s><s>[INST] It's because, well, you've got seven chefs in the kitchen. [/INST] It is one of these, yes. So what is this meant in terms of the speed of the project and the ability to govern it and so forth? It's just been a challenge honestly around this. And this is, I mean, it's very hard technically what's occurring, but when you also introduce such levels of, I mean, this isn't just me saying it. There's like GOO reports from the US government and so forth. It's hard to like steer all of this around. And what that's tended to do is make it, it's not the fastest decision making process. My own personal view of it was, it was interesting because you asked, you said about the magnet and Commonwealth fusion systems. It was, I worked most of my career on ITER because when I came into the field in the early 1990s when I completed my PhD and started to work, this was one of the most, like you can't imagine being more excited about something like, we're going to change the world with this project. We're gonna do these things. And we just like port like an entire generation and afterwards as well too is just poured their imagination and their creativity about making this thing work. Very good. But also at some point though, when, you know, when it got to being another five years of delay or a decade of delay, you start asking yourself, well, is this what I want to do? Right, am I going to wait for this? So it was a part of me starting to ask questions with my students. I was like, is there another way that we can get to this extremely worthwhile goal? But maybe it's not that, maybe it's not that pathway. And the other part that was clearly frustrating to me because I'm an advocate of fusion. You asked me about, was I, you know, I was like, well, it's laser fusion or inertial fusion or magnetic fusion. I just want fusion energy, okay? Because I think it's so important to the world is that, but the other thing, if that's the case, then why do we have only one attempt at it on the entire planet, which was ITERF? It's like, that makes no sense to me, right? We should have multiple attempts at this with different levels of whatever you want to keep. Think about it, technical, schedule, scientific risk, which are incorporated in them. And that's going to give us a better chance </s><s>[INST] of actually getting to the goal line. With that spirit, you're leading MIT's effort to design Spark, a compact high field DT burning tokamak. How does it work? What is it? What's the motivation? What's the design? [/INST] What are the ideas behind it? Yeah, yeah, yeah. At its heart, it's exactly the same concept as ITER. So it's basically a configuration of electromagnets. It's arranged in the shape of a donut. And within that, we will do the same thing that happens in all the other tokamaks and including an ITER and in this one. Is it namely you put in gas, make it into a plasma, you heat it up, it gets to about 100 million degrees. The differentiator in Spark is that we use the actual deuterium tritium fuel. And because of the access to very high magnetic fields, it's in a very compact space. It's very, very small. What do I mean by small? So it's 40 times smaller in volume than ITER. But it uses exactly the same physical principles. So this comes from the high magnetic field. So in the end, like why does this matter? What it does is it does those things and it should get to the point where it's producing over 100 million watts of fusion power. But remember, it's 40 times smaller. So ITER was 500 megawatts. Technically, our design is around 150 megawatts. So it's only about a factor of three difference despite being 40 times smaller. And we see QP large, order of 10 or something like this. At that state is a very important scientifically because this is basically matches what ITER is looking to do. The plasma is dominated by its own heating. That's very, very important. And it does that for about 10 seconds. And the reason it's for 10 seconds is that in terms of that, that basically allows everything to settle in terms of the fusion in the plasma equilibrium, everything is nice and settled. So you know, you have seen the physical state at which you would expect a power plant to operate basically for magnetic fusion, like wow, right? But it's more than that. And it's more than that. It's because about who's building it and why and how it's being financed. So that scientific pathway was made possible by the fact that we had access to a next generation of magnet technology. So to explain this real quick, why do we call it? You said it in the words, a superconducting magnet. What does this mean? Superconducting magnet means that the materials which are in the electromagnet have no electrical resistance. Therefore, when the electric current is put into it, the current goes around unimpeded. So it could basically keep going around and around, you know, technically for infinity. And what that mean or for eternity. And what that means is that the, when you energize these large electromagnets, they're using basically zero electrical power to maintain them. Whereas if you would do this in a normal wire, like copper, you basically make an enormous toaster oven that's consuming enormous amounts of power and getting hot, which is the problem. That was the technical breakthrough that was realized by myself and at the time my students and postdocs and colleagues at MIT was that we saw the advent of this new superconducting material, which would allow us to access much higher magnetic fields. It was basically a next generation of the technology. And it was quite disruptive diffusion, but namely what it would allow that if we could, if we could get to this point where we can make the round 20 Tesla, we knew by the rules of Tokamaks that this is going to be, is going to allow us to vastly shrink like the sizes of these devices. So it wouldn't take, although it's a worthy goal, it wouldn't take a seven nation international, treaty basically to build it. You could build it with a company and a university. </s>

<s>[INST] up. So it gives you hope. It's funny that we don't generate, again, we don't often think about, I think it's very useful to think about positive visions of the future when we're trying to design technology, there's a lot of sort of in public discourse, a lot of people are thinking about kind of how everything goes wrong. It's important to think about that sometimes, but in moderation, I think because you there's not enough in my little corner of artificial intelligence world, people are very kind of fear monger centered. There's a lot of discussions about how everything goes wrong important to do, but it's also really important to talk about how things can go right, because we ultimately want to guide the design of the systems to create, to make things right? And I think with hope and optimism, not naive nous, but optimism, you can actually create a better world, like you have to think about a positive, a better world as you create, because then you can actually create it. Um yeah, I'm one of the people who thinks that having an optimistic view of the world is better for design and creativity than having a pessimistic one? It's hard to design when you're in fear. Uh do you have advice for young people? Speaking of being excited about and hopeful about the future world, do you have advice for young people today and uh computer science world and software engineering world in crypto world, but maybe in any world whatsoever uh for life how to pick a career or how to live life in general. [/INST] I think the thing that young people should do is not any one specific thing for any, anyone specific young person. I think what they should do is what they won't be able to do in the later stages of their life. And the way in my opinion from a framework point of view to think about that is that the amount of obligations and the amount of time that a person has seems to just diminish over time. Right? So the amount of free time they have. Right? So you started your job, you get a bunch of responsibilities, some something with your partner spouse, more responsibilities, kids probably even more responsibilities and soon enough the time that you have to educate yourself to travel to experience the world however, create whatever creative endeavor you're interested in. Um slowly but surely disappears. I think this is something that you know, young people don't fully realize. They assume that the world as it is now. And the amount of free time that they have to travel to educate themselves to make new friends to do all these things will somehow May be diminished by 10%. It won't diminish by 10% diminished by 90% and the 10% that you have, you'll be resting to get back to work and get things done. So what I think young people should do and this is why it's very different for each of them, right? I can't tell young people, hey, you should study philosophy, travel and start your own enterprise to achieve something worthwhile in the world, right? That might be something that's good for me with my values and my um kind of worldview. But for other people might be something else. I think the way that they should conceptualize it is imagine if Over the next um 10, 12 years, the amount of choice that you had about what you could do was cut down by 90%,, what would you? And this is, you know, copying from this kind of just Jeff Bezos regret minimization framework In that framework. It's like what would I regret not doing at 80 and that's kind of meant to create this long term view and make these decisions now. That will get you to a long term future that you can look back on and be proud of your life right. What I think young people should do is they is they should say to themselves, look if I never get the chance to travel for as long as I live Assuming that after 25, after 27, after 29, that's the case. How will I feel about that? If I never get to start a company after 25 after I get married after I have kids, how will I feel about that? And whatever they feel the worst about is what they should do. Whatever they feel like when they say to themselves, you know, if I don't travel now, I will never travel And they feel horrible about that. They just have an overwhelming fear and disgust at themselves in that type of state. At 25, 27, 29, that's what they should do and they shouldn't listen to anybody else. Um I let me put it this way, if you're really smart, you're gonna make it anyway. There's a lot of people putting a lot of pressure on you because they're afraid whether you're gonna make it, if you're really smart you're gonna make it anyway. If you're not really smart, you're screwed anyway. So either way just relax with it and </s><s>[INST] use your time well to do the things you would most regret not doing. That's really fascinating. [/INST] I wouldn't I wouldn't say relax. I would say very much cherish the free time. The discretionary time that you have From the age of 18 to maybe 25. Because at 25 everyone's gonna start looking at each other and asking what if what if I like my friends have achieved? I haven't achieved and then by the time you get to 30 you're gonna look at each other again and go, well my friends have a family or a company or a PhD or whatever, what do I have. And the pressure will just increase and it'll increase so much that even if you want to go And do the fun thing, it will not be fun because the pressure of comparing yourself to your friends at 25 or your peers at 30 will be so great that you will no longer, it will no longer be normal for you to be in a hostel at 30. You know, kind of like living it up, right? If if and and and this is why I also can't tell you specifically what it is for me. It was getting an education and philosophy that was rigorous and in depth. It was traveling and it was starting an enterprise that I thought were, that was worthwhile that I directed that I could make into something great. That's what it was for me for other people. It might be something with a band, it might be something with painting, It might be an education. Um You, by the way, should also should not assume that your ability to get an education will um improve all of those responsibilities will take away your ability to get an education. So if you value having an education, if you value being a deeply educated, well rounded person with a wide array of knowledge on a wide array of topics. Capitalism will force you to specialize. That's what it's good at is gonna take you. It's gonna fashion you into a very specific tool for a very most people into a very specific set of tasks. If you want to have an education, something, get it Now, if you want to travel somewhere, travel there now, if you want to, you know, do some kind of creative endeavor that you doubt whether you'll have time for in the future, do it now, you won't have time for it in the future, You won't have time to read philosophy books all day. Unfortunately, you won't have time to fly to, you know, italy and kind of hang out with people if you're serious about your life, you're going to get more responsibilities, you're gonna get more stuff to do. And so my advice to you is do not piss away this rare, unique discretionary time. And if your friends are get new friends get smarter friends get people who are using the limited time they have better. Um, that's my advice. </s>

<s>[INST] It's gone. Yeah. It's gone. Yeah. And so the internet with this verification that grounds you to physical reality, it's a really, really interesting idea. [/INST] Why hasn't that been done? I think you need two things. You need an idea like a digital asset, like Bitcoin, that's a bearer instrument for final settlement. And then you need a high-speed transaction network like Lightning, where the transaction cost might be a 20th of a penny or less. And if you roll the clock back 24 months, I don't think you had the Lightning network in a stable point. It's really just the past 12 months. It's an idea you could think about this year. And I think you need to be aware of Bitcoin as something other than a scary speculative asset. </s><s>[INST] So I really think we're just the beginning. The embryonic stage. I have to ask Michael Saylor. You said before, there's no second best to Bitcoin. What would be the second best? Traditionally, there's Ethereum with smart contracts, Cardano with proof of stake, Polkadot with interoperability between blockchains, Dogecoin has the incredible power of the meme, privacy with Monero, that just can keep going. [/INST] There's, of course, after the block size wars, the different offshoots of Bitcoin. I think if you decompose or segment the crypto market, you've got crypto property, Bitcoin is the king of that, and other Bitcoin forks that wanted to be a bear instrument store of value would be a property, a Bitcoin cash or Litecoin, something like that. Then you've got crypto currencies. I don't think Bitcoin's a currency because a currency I define in nation state sense, a currency is a digital asset that you can transfer in a transaction without incurring a taxable obligation. So that means it has to be a stable dollar or a stable euro or a stable yen, a stable coin. So I think about crypto currencies, Tether, Circle, most famous. Then I think you've got crypto platforms, and Ethereum is the most famous of the crypto platforms, the platform upon which with smart contract functionality, et cetera. Then I think you've got just crypto securities. It's just like my favorite, whatever, meme coin, and I love it because I love it and it's attached to my game or my company or my persona or my whatever. I think if you push me and said, what's the second best, I'd say the world wants two things. It wants crypto property as a savings account, and it wants cryptocurrency as a checking account, and that means that the most popular thing really is going to be a stable coin dollar. There's maybe a fight right now, it might be Tether, but a stable dollar because I feel like the market opportunity, it's not clear that there'll be one that will win. The class of stable dollars is probably a one to $10 trillion market easily. I think that in a crypto platform space, Ethereum will compete with Solana and Binance Smart </s><s>[INST] Chain and the like. Are there certain characteristics of any of them that stand out to you? Don't you think the competition is based on a set of features? The set of features that a cryptocurrency provides, but also the community that it provides, especially the community matters, the adoption, the dynamic of the adoption, both across the [/INST] developers and the investors. If I'm looking at them, the first question is, what's the regulatory risk? How likely is it to be deemed a property versus security? The second is, what's the competitive risk? The third is, what's the speed and the performance? All those things lead to the question of what's the security risk? How likely is it to crash and burn and how stable or unstable is it? Then there's the marketing risk. There are different teams behind each of these things and communities behind them. I think that the big cloud looming over the crypto industry is regulatory treatment of cryptocurrencies and regulatory treatment of crypto securities and crypto platforms. I think that won't be determined until the end of the first Biden administration. For example, there are people that would like only US FDIC insured banks to issue crypto currencies. They want JP Morgan to issue a crypto dollar backed one-to-one, but then in the US right now we have Circle and we have other companies that are licensed entities that are backed by cash and cash equivalents, but they're not FDIC insured banks. There's also a debate in Congress about whether state chartered banks should be able to issue these things. Then we have Tether and others that are outside of the US jurisdiction. They're probably not backed by cash and cash equivalents. They're backed by stuff and we don't know what's stuff. Then finally you have UST and DAI, which are algorithmic stablecoins that are even more innovative further outside the compliance framework. If you ask who's going to win, the question is really, I don't know, will the market decide or will the regulators decide. If the regulators got out of the way and the market fought out, well then it's an interesting discussion. Then I think that all bets are off if the regulators get more heavy-handed with this. I think you could have the same discussion with crypto properties. The DeFi exchanges and the crypto exchanges, the SEC would like to regulate the crypto exchanges. They'd like to regulate the DeFi exchanges. that means they may regulate the crypto platforms and at what rate and in what fashion. And so I think that I could give you an opinion if it was limited to competition and the current regulatory regime, but I think that the regulations are so fast moving and it's so uncertain that you can't make a decision without considering the potential actions </s>

<s>[INST] when I interact with leg of robots, I see there's magic there and I just feel like the person who hears the music and others don't and I don't know what that is and I'd love to explore that because it seems to, it's almost like uh, the future talking. And I'm trying to hear what it's saying. Is this a dangerous world or is this a beautiful [/INST] world? Well, I can certainly understand your enthusiasm for that. Those used to be things that I found overwhelmingly exciting. And I'm not sort of closed off from that anymore. I mean I'm not now closed off from that even though my views are are changed and I don't work in that world. But I do think, I think it's interesting to figure out what's at the ground of that, of that response. </s><s>[INST] We talked about meaning quite a bit throughout in a secular age. But let me ask you the big, ridiculous question almost too big. What is the meaning of this thing we've got going on? What is the meaning of life? [/INST] You're saving the softball for the end? I don't know what the meaning of life is. I think there's something that characterizes us that's not the thing that people normally think characterizes us the traditional thing to say in the philosophical tradition, even in the ai tradition, which is a kind of manifestation of philosophy from plato for the traditional thing to say is that what characterizes us as our rationality that were intelligent beings that we're the ones that, that I think, and I think that's certainly part of, of what characterizes us. But I think there's more to it too. I think we're capable of experiencing simultaneously the complete and utter ungrounded nous of everything that's meaningful in our existence and also the real significance of it, and that sounds like a that sounds like a contradiction. Like how could it really be significant and not be based on anything? But I think that's the contradiction that somehow characterizes us. And I think that we're the being that sort of has to hold that weird mystery before us and live in the light of it. That's the thing that I think is really at our core. And so how do we do that? I will say this one thing. Um and I learned it from a philosopher from a guy named Albert Borgmann who's joe german philosopher lived in Montana, now taught in Montana for his whole career. And when I I say this to my students at Harvard now, he said this is the way that I think about my life. And I hope you'll think about your life too. He said, you should think about your life, hoping that there will be many moments in it about which you can say there's no place. I'd rather be, there's no thing, I'd rather be doing, There's nobody I'd rather be with and this, I will remember. Well, mhm and I think if you can aim to fill your life with moments like that, it will be a meaningful one. I don't know if that's the meaning of life, but I think if you can hold that before you, it will help to clarify this mystery and this sort of bizarre situation in which we find ourselves </s><s>[INST] sean this conversation was incredible and those four requirements have certainly been fulfilled. For me, this was a magical moment in that way, and I will remember it well, thank you so much. It's an honor that you spend your valuable time with me. This is great. Thank you. [/INST] Thank you for having me lex. I really, really enjoyed it. Thanks for listening to this </s><s>[INST] conversation with Sean kelly. To support this podcast. Please check out our sponsors in the description and now let me leave you with some words from Albert camus in the depth of winter. I finally learned that within me there lay an invincible summer. Thank you for listening and hope to see [/INST] you next time. </s>

<s>[INST] Is it always shrinking? Or is there sort of as you get surprised? I mean, it's always just an estimate. So does it ever expand based on sort of chaotic, unpredicted, unpredicted, surprising behavior of the players. [/INST] It really should never expand. The range of hands should always get smaller. Right? Like, again, we start with the full the full scope and then you should factor in like, okay, these are all the possible hands you can have on the flop now, right, we can't have new hands on the turn. And if you if you if you get to that point where you think, oh well maybe he has this hand, then you then you sort of misjudged his range prior. So you're not thinking clearly, it should always shrink from the full scope to, you know, hopefully just </s><s>[INST] a couple. Well in that video, you also talk about, it used to be that you would play your hand, but now you're playing a range that you're representing? a range, you're not even just playing your hand. So what does it mean to represent a certain range? [/INST] Yeah. So that's another big thing that's different about poker from you know my day to today Is that back in our day we would like put people on one hand like you probably have King nine or you have jacks or something like that. Now people are cognizant of the idea that you could have an entire range of hands. So then you ask yourself in situations, alright. I know what I have but what I could have in his mind or my opponent's mind is any one of these hands, what would I do with the entirety of these hands? And so a lot of people that are trying to play optimally, you know, game theory, optimal They think in terms of what their range of hands would do rather than their very specific hand. </s><s>[INST] So it is bluffing in that context, essentially misrepresenting the range of hands that you have to know how you think about it. [/INST] Not exactly because so an optimal range. Like if I bet the river, if I'm playing game theory optimal. A portion of my range is going to be, I have it, I got I got the best hand and a portion of my range is gonna be bluffs and they'll be balanced. So in theory no matter what you </s><s>[INST] do, no [/INST] matter what you do, you call or you fold. In theory, it's just you're printing a zero, as we say, you're not you're not getting gaining or losing any E. V. If you were to do it that </s><s>[INST] way E. [/INST] V. Is expected value, right? So every play that you make, you know it either is going to in the long run, you know, make you some money or it's it's just a losing play. And as a professional, you try to make the fewest amount of minus Cv plays. You can. And the only reason you would make these minus Cv plays is potentially if you were trying to set up your opponent for something later, right? So I might make some minus Cv plays, right? So that I can exploit you later, right? </s><s>[INST] Building up building up an image [/INST] something that I'm gonna I'm gonna plant seeds in your mind so that I can exploit them later. So for example, why would players like show a big bluff, like what would be the reason for that? They show a big bluff so that, you know, they're capable of it. But maybe in their mind, they're never gonna do that again. But now they think, you know, he bluffed me last time, maybe he's doing it again, but that's a what we call like a level A. Leveling more because, you know, you can go back and forth with whether or not okay, this guy might know that like he showed a bluff because he's never gonna bluff me again. So that that's where it gets a little, </s><s>[INST] so that that's a little bit different though when we're talking about hand rangers, that's different than building up a mental model of what your opponents, what your opponents think of you and what your opponents think that you think of them and and so on so forth. Are you trying to construct those kinds of mental models? And is that separate from the hand ranges? [/INST] They go hand in hand? Right. So if any given in a given situation, right? My range has this many value hands and this many bluffs. Okay, so in theory if I want to be balanced, you know, this is my range and this is what it looks like. I'll bet this 50% of the time, but this 50% time. However, if I know that you think that I bluff too much right, then I'm not gonna bluff as much. I'm gonna start instead of betting these hands that I would 50 50. Now, what I'll do is I'll do like 70 30 where I'm basically value betting most of the time against you, You know, or vice versa, if I know you always fold because you think I have it, I'm going to hear the other way and instead of bluffing 50%, 70, 80% of the time to take advantage of your perception of me. </s><s>[INST] So to be successful, do you have to construct a solid model of all the players in the game or can you ignore them? [/INST] I think it's really important like when I play I have in my phone I have a player profile with everyone that I play with. Whenever I pick up whether it's physical tells or tendencies they like to you know that that they have. Um And overall that's just gonna you know that's gonna allow you to exploit more right? So like if I played with somebody never played before I'm probably just going to play optimally or at least as optimal as I know how until I start to you know gain some information on that player so that I can start to exploit them. </s>

<s>[INST] as long as that knowledge is transferred forward. Something tells me that the greatest of all time lived a few 1000 years ago and it's forgotten some of the greatest warriors. You can imagine the kind of grapplers, we just the history didn't record them that there could have been small tribes where they developed many U. F. C. S. And they've developed the kind of things we, you have to think of like the gracie's just a small family was able to develop so much so quickly. [/INST] I I often as this this discussion with john and I think it's very important to mention. I asked you very several times like what would happen if we would take a fighter of modern days facing the champion of Japan creation. </s><s>[INST] This is an interesting question and [/INST] you brought something incredible good point and and people don't don't realize </s><s>[INST] it. You know you know I think um one of the great tragedies of martial arts history is our loss of uh the historical records of pan creation, like most of what we know was from what I'm told is actually lost in the fires of the library of alexandria. And we're left with only a pitiful amount of information on Pan Creation manages. But what we do know is that there was a very large participation in the sport and that it was why they considered the most popular sport in the ancient olympics and that it was represented in the ancient olympics for many hundreds of years plus a long period of time before its introduction into the ancient olympics. And so the development time that it may have had would have been very significant as far as we know, most of the development would have been in the major greek city states for literally hundreds of years of development um given its prestige as an olympic sport, then the best athletes would have been doing it. Some of the sharpest minds that we know of and human history were involved in the sport. Plato, the great philosopher, was a pan creationist in his youth. In fact, his name Plato is a nickname, platypuses like plate, it means broad or big guy, like the big guy and uh he spoke often about pan creation and his written works. Um imagine people with the intelligence of plato thinking about grappling technique for hundreds of years, in the most popular olympic sport of that time, significant numbers of people with financial backing as city states put great prestige upon olympic success, they would have funneled athletes and brought in the best coaches and they had that for many hundreds of years. It's quite conceivable that the best plan creation athletes were of the absolute first quality. And uh, it's, it's so sad to think. We'll never know what was their skill level. And uh, it's interesting to think about what kind of techniques have developed, whether there's stuff we haven't discovered yet in class, you're talking about the most effective take down strategy and wrestling and collegiate wrestling. So maybe let me ask first, because we offline talked about this to what is the highest percentage submission in grappling overall. You have to go with the rear naked, strangle strangles from the back. If you look at most tournaments, most rule sets, it has success across all rule sets, all weight divisions, all body types. It doesn't require any kind of specific physical advantage, such as height in order to be effective. Um, It works equally well in both fighting and grappling. Um it will work regardless of how physically and mentally tough your opponent is. Okay here, Hawk is a very high percentage technique in modern day competition, but if your opponent simply makes up his mind that he's not going to tap and is willing to take the physical damage. It won't result in the end of the match a stranglehold by contrast, will always end the match regardless of your opponent's mental toughness. So, um, I believe it's fair to say that at the end of the day, the single most high percentage method of submitting people and grappling is a redneck its frame. So when you look at an athlete, maybe Gordon? You can speak to this. Like what, what's the best you mentioned Gary with the guillotine? What's the best submission to really invest in? Is it the rear naked choke to really invest your development? Like understanding the entirety of the system that leads into that? [/INST] I think that, I mean you have to do them all obviously, but if I had like one submission that I would only one submission, I could pick for the rest of my life. It would definitely be a rear naked. </s><s>[INST] Can you explain maybe some of the actual technical details of why that's the case? [/INST] Well, as john's book about their different in joint locks, whereas you don't have to tap, you can just let your leg break and then keep going with the strangle this. There's no, uh, there's, there's none of that. Um, and then it's just an inherent advantage you have being behind someone. Um, whereas if you go for an arm bar, you stop, you start from top mountain, you're facing the guy and then you put them down and you're not directly behind them with leg locks, you're facing the guy. Whereas when you're on someone's back, you have them in a pin where you can, your chest back have a body triangle and you you're paying the guy in place, you can't explode out. He can't grease his way out most of the time. Uh, and there's an inherent advantage you have being behind him due to the fact that were poorly set up to deal with threats behind us. </s><s>[INST] So it would just say that's the most dominant position, jujitsu, like more than Mt, more than side control. [/INST] More than I think. If you look at most matches historically, most guys who get stuck in positions for long amounts of time are guys that they're back taken. Um If you get an explosive guy from Bottom Mountain can bridge and he can off balance you and lock half guard maybe and then work back to guard. But someone locked the body triangle on your back. Um That's where you see most guys getting pinned in place for long amounts of time. </s>

<s>[INST] Well, I mean, it's because you're the intuition is like, okay, not that there's a vaccine, you're either going to take the vaccine or get infected and then it'll be herd immunity over. Like it would be very quick. So, you know, that's the intuition but it seems like that's not happening. It seems like work in this constant state of fear mongering for different reasons. It's almost uh it's almost like the virus got deeply integrated, not into just our biology, but in the game of politics and in the fear mongering around the news because the virus now started being together with the vaccine and the masks and it started getting uh integrated into uh the division that's so effective at uh monetizing social media for example. And so it's like, all right, so, how do you get [/INST] out of that? </s><s>[INST] Because you can always kind of present certain kinds of numbers about the number of cases or how full hospitals are and and start making claims about there were still, this is as bad as it's ever been, those kinds of statements. And so I'm not sure exactly what the way out is, except the same way out as it was originally, which is testing this information. It's information. [/INST] And I think we can do that. We can keep outbreaks suppressed with testing because it's information like people keep thinking of tests as big medical things. They're not their information. It can allow us to control things just like we drive down a road and we look at the cars and we don't hit other cars because we have the information that they're not lying next to us. And they're moving over like that's just information. Like </s><s>[INST] you said, glow green. The problem, the virus you don't have, you don't see your walking around and everybody is a potential uh, like infectious creature. So if you see the world as a potential potential for infection, you're going to be terrified of [/INST] that. Exactly, right. And that is what has happened. And I and that's why I've been pushing so hard for for these tests because they can allow people, if you use them at a community level, you can have enough people know that they're positive enough people are good people that they won't go out and infect others. And the other great thing about them is again, a 10 day isolation period, especially for a vaccinated person. But in either case is also an information problem. We don't have to isolate for 10 days if we're infected. What if we're only infectious for two Especially were vaccinated? Why are we telling people? The only reason the CDC ever and the W. H. O. Ever suggested a 10 day isolation or 14 day quarantine is because we didn't know when people stop being infectious. There's actually some people stay infectious for 14 days rare, but there's a lot of people stay infectious for like four and that's a whole another week that we're asking people to isolate people would probably be much more likely to comply if they only have to isolate as long as they wake up each morning. See two lines because you're actually seeing it for your own two eyes. You're being empowered To make your own decision. You're not being told you need to isolate for 10 days and you're sitting there thinking, I feel fine. I don't know, you know, there's a lot of asymptomatic spread. But if you see the two lines every day, then you actually get to you're doing a little experiment for yourself to prove to yourself today, I'm still infectious. Let's hope it's tomorrow. Come on immune system, You can do this. You know, and then you get to day four and boom you start being negative. That's a much more tolerable thing because you are, you are being able to make that decision based on true data that is empowering you and it really does change changes everything because it's all fear and and empowerment and these are empowering devices. </s><s>[INST] Well I wanted to have this conversation with you because obviously it's a great solution. Let's keep talking about it. People who listen to this should uh I guess pressure local politicians [/INST] write articles, write articles with the title like do your potus you know, please designate these as public health tools or just start talking about in the media. Talk it talk about social media anywhere. Testing is a public health good testing is a public health good. We all like it should not be considered a medical device. I shouldn't have to pay to keep you safe. Like testing should generally be free for that matter like subsidized by the government, these tools exist that we should all and I think the more people that generate noise to just say a public health test is a public health tool, you know, period like you can't even argue with it. I think </s><s>[INST] if you talk about it enough than certain people that have even a bigger platform like Elon musk's under part II those folks that have power to really do like large scale manufacturing also influence governments will pay attention and that's that's the whole enough people talk about [/INST] it. I think business leaders like business leaders obviously have so much power here. You know, they pay the lobbyists who you know make things happen. Like, let's be honest, there's people who pull levers that are not the politicians themselves and I do think business leaders have so much to gain from these tools to keep their businesses safe, to not have to quarantine and lockdown. And I hope that all of them here this message to say, let's let's ask the president or the people around the president too, designated as public health tools, change the system. And if you can't change every aspect of the system, then figure out how to change the system enough so that you're doing everything in a safe way that is not endangering anyone. But it is only protective. </s>

<s>[INST] Well, first of all, it's not certain that that's true, it's it's possible, possible, like Sean carroll, you know, uh especially with quantum mechanics based on certain interpretation of quantum mechanics, that's that's very possible. But the question is, can you access those universe is [/INST] the </s><s>[INST] more, the more sort of specific practical question is this local pocket of the universe, our galaxy or neighboring Galaxies. Are there aliens there? What did they look like? Are they? So you can have this panspermia idea where a much larger, like uh, like daddy civilization, uh, like uh rolled by and just planted a few aliens at a similar time. Yes, a different, you know, throughout the galaxy. And those are the ones who might be interacting with their all kind of dumb as we are relatively, you know, maybe a few million years apart. And then those are the ones who are interacting with and then we have a chance to actually connect with them and communicate with them. Or it could be like much more wide open and you have these gigantic alien civilizations that are expanding very, very quickly. And the interesting thing is when you look up at the sky and you see the stars that's light from those stars, we might not be seeing the alien civilizations until they're already here, meaning like you start expanding once you get really good at expanding, you're going to be expanding very close to the speed of light. So right now we don't see much in in the sky, but there could be 11 day we wake up and it's just like everywhere and they're here? [/INST] Right? Because the amount of time the light takes to reach us? Yeah. And then the thing that I've been really fascinated by is these alternative forms of transportation that they're discussing, like the ability to harness wormholes and the, the ability to, to do things that were uh a Type three civilization is capable of. I had Mikio Kaku on my podcast recently. Fantastic. I love that guy. He's so, he's so good at taking extremely complex concepts and boiling them down for digestion and, and you know, and saying them in a way that other people can appreciate </s><s>[INST] and not being hesitant about saying wild, crazy ship that's out there, but grounded in what's actually possible. [/INST] Yeah, he's all in on this Ufo phenomenon now he's now he's like now the burden of proof is to people for people to come up with some sort of a conventional explanation for these things. He goes, because these things are defying all the concepts of physics that that we're, we currently know in terms of what our capabilities are and and propulsion systems and and so many other things that, you know, what we know about, what current science is capable of reproducing as far as what we know the problem is like these um military projects that are top secret, like how much money do they have? They have a lot of money like, but is it possible and maybe you could speak to this, Is it possible that there could be some propulsion systems that have been developed and implemented that are far beyond just a simple burning of rocket fuel, pushing the fire out the back, which forces the rocket at extreme speeds forward. That's something that does harness gravity. Something that can distort space and time and can make travel from one point to another. Uh, like preposterously fast. </s><s>[INST] Well not only is it possible, I think it's likely that that kind of stuff would be kept a secret. It's just everything you see about these um, about the way either if it's contractors like Lockheed martin or if it's due to the, the, the, the, the actual Department of Defense, they operate in complete secrecy. Just even looking at the, the history of the stealth fighter, just even stealth technology was kept a secret for a very, very long time and not until you're ready to use it and need to use it, does it become public and not officially public? It's just is being detected out in the wild. So there's going to be a process where you're secretly testing it and that might creep up, which is maybe what we're seeing and then it's waiting for the next big war, the next big reason to use the [/INST] thing. </s><s>[INST] And and so yeah, there's there's definitely technologies now, there might not be propulsion technologies that could be a i surveillance technologies that could be different kinds of stealth drones. There could be, it could be also in cyberspace, like cyber war weapons, all that kind of stuff that they're obviously going to become a secret. [/INST] I'm I'm very skeptical lately and the reason why I'm skeptical is the government keeps talking about it, The Pentagon keeps talking about it. Nasa keeps talking about it. I'm skeptical that it's their aliens. I think most likely it's a smokescreen and most likely these are some sort of like incredibly advanced drones that they've developed that they want to pretend don't exist. That seems the more likely scenario because otherwise my take is like what's the benefit of them discussing these things? Like what's the benefit of them discussing these things openly. These are, you know what the way they described it off world crafts not made from this earth. Like why why would they, why would they tell us that? I mean, unless there's an imminent danger of us being invaded and they want to prepare people so they don't freak out as much, you know, like maybe freak them out a little bit say that publicly. The new york Times article, the Pentagon discussing it all these different things. Yeah, well let let people know that this is a thing or my take is like that. I don't think they do that. I don't think they tell us. I think they, I think, I think the government has a lot of contempt for for the citizens. I really do. I think they have contempt for our intelligence. They have contempt for our need to know things. And I also think they think that they are running us. It's not we're all in this together and the government works for the people and the government is of the people. I don't think they think that way. </s>

<s>[INST] crazy, crazy [/INST] like inconceivable like how fast all of this happened. So you know, it's not surprising that we haven't figured out what to do yet, but like we gotta we gotta really like lean into this set of problems because like we basically have three millennial worth of work to do about how to deal with all of this and like probably what amounts to the next decade worth of time. </s><s>[INST] So since we're on the topic of tough, you know, tough, challenging problems, let's look at uh more on the tooling side in ai that Microsoft is looking at the face recognition software. So there's there's a lot of powerful positive use cases for face recognition, but there's some negative ones and we're seeing those in different governments in the world. So how do you, how does much, I think about the use of face recognition software as a platform and governments and companies, how do we strike an ethical balance here? [/INST] Yeah, I think we've articulated a clear point of view. So brad smith wrote a blog post uh last fall, I believe that's sort of like outlined like very specifically what uh you know what our what our point of view is there and you know, I think we believe that there are certain uses to which face recognition should not be put and we believe again that there's a need for regulation there. Like the government should like really come in and say that you know this is this is where the lines are and like we very much wanted to like figuring out where the lines are, should be a democratic process. But in the short term like we've drawn some lines where uh you know, we push back against uses of face recognition technology. Um you know like this city of SAN Francisco for instance, I think has completely outlawed any government agency uh from using face recognition tech. Uh and like that may prove to be a little bit overly broad. Um but for like certain law enforcement things like you, you really, I would personally rather be overly cautious in terms of restricting use of it until like we have, you know, sort of defined a reasonable, you know, democratically determined regulatory framework for uh like where we could and should use it and you know, the other thing there is um like we've got a bunch of research that we're doing in a bunch of progress that we've made on bias there. And like there are all sorts of like weird biases that These models can have. Like all the way from like the most noteworthy one where you know, you may have um underrepresented minorities who are like underrepresented in the training data and then you start learning uh like strange things. But like they're even, you know, other weird things like we've uh I think we've seen in the public research like models can learn strange things like all doctors are men for instance. Uh Yeah, I mean and so like it really is a thing where it's very important for everybody who is working on these things before they push publish uh they launched the experiment. They, you know, push the code, you know online. Are they even publish the paper that they are at least starting to think about what some of the potential negative consequences are. Some of this stuff. I mean this is where you know, like the deep fake stuff I find very worrisome just because they're going to be some very good beneficial uses of like gan generated uh imagery and like and funny enough like one of the places where it's actually useful is we're using the technology right now to generate synthetic synthetic visual data for training some of the face recognition models to get rid of the bias. Uh So like that's one like super good use of the tech but like you know, it's getting good enough now where you know, it's gonna sort of challenge normal human being's ability to like now you're just sort of say like it's it's very expensive for someone to fabricate a photo realistic fake video. And like gans are going to make it fantastically cheap to fabricate a photo realistic fake video. And so like what you assume you can sort of trust is true versus like be skeptical about is about to change. Uh like we're not ready for it. I don't think </s><s>[INST] the nature of truth, right? That's uh it's also exciting because I think both you and I probably would agree that the way to solve to take on that challenge with technology right? There is probably going to be ideas of ways to verify which which kind of video is legitimate, which kind of not. So uh to me that's an exciting possibility most most likely for just the comedic genius that the internet usually creates with these kinds of videos and hopefully will not result in any serious harm. [/INST] And it could be, you know, like I think we will have technology too that may be able to detect whether or not something is fake or real, although the fakes are pretty convincing even like when you subject them to machine scrutiny. But you know that we we also have these increasingly interesting social networks you know that are under fire right now. Um for some of the bad things that they do. Like one of the things you could choose to do with the social network is like you could you could use crypto and the networks to like have content signed, where you could have a like full chain of custody that accompanied every piece of content. So like when you're viewing something and like you want to ask yourself like how you know how much can I trust this? Like you can click something and like have a verified chain of custody that shows like oh this is coming from you know from this source and it's like signed by like someone whose identity I </s>

<s>[INST] I still wonder what kind of man it takes, what kind of human being it takes to do that. Because I've been studying Vladimir Putin quite a bit and he's still, I believe he still has popular support that that's not fully manipulated because I know a lot of people in Russia and actually almost the entirety of my family in Russia are big supporters of Putin, everybody I talked to. So if that's not just like on social media, like the people that live in Russia seems to seem to support him. It feels like this will be in a George Washington way. Now would be the time that Putin, just like Yeltsin could relinquish power and thereby, in the eyes of Russians become in in like the long arc of history, be viewed as a great leader. You look at the economic growth of Russia, you look at the rescue from the collapse of the soviet union and Russia finding its footing and then relinquishing power in a way that that perhaps if Russia succeeds forms a truly democratic state, this would be how Putin can become one of the great leaders in Russian history, At least in the, in the, in the context of the 21st century, [/INST] I think there are two reasons why this is really hard for Putin and for others, one is the trappings of power are very seductive as you said before. They're corrupting. This is a real problem, right? If it's in the business context, I don't want to give up that private jet. Uh, if it's in Putin's context, it's billions of dollars every year that he's able to take for himself or give to his friends. It's not that he'll be poor if he leaves, he'll still be rich and he has billions of dollars stored away, but he won't be able to get the new billions. And so that's part of the trappings of power are, are a big deal. And then second in Putin's case in particular, he has to be worried about what happens next. Will he be tried? Well, someone, you know, try to come and arrest him with someone try to come and assassinate him. Um Washington recognized that leaving early LTD the corruption and limited the enemies that you made. And so it was a strategic choice. Putin is at this point, Brennan power too long. And this comes back to your core insight. It's a cliche, but it's true power corrupts. No one should have power for too long. This was one of the best insights. The founders of the United States had that power was to be held for a short time as a fiduciary responsibility, not as something you owned, right? This is the problem with monarchy with aristocracy that you own power, right? We don't own power. We were holding it in trust. </s><s>[INST] Yeah, There's uh there's some probably like very specific psychological study of how many years it takes for you to forget that you can't own power. That's right. There's, you know, that could be a much more rigorous discussion about the length of terms that are appropriate. But really There's amount like Stalin had power for 30 years. Like Putin is pushing those that many years already. Mhm There's a certain point where you forget the person you were before you took the power. That's right. You forget to be humble in the face of this responsibility and then there's no going back. That's right. That's how dictators are born. That's how the evil like authoritarians become evil or well, that's not used the word evil but uh counterproductive destructive to the, to the idea that they initially probably came to office with. [/INST] That's right. That's right. One of the core historical insights is people should move </s><s>[INST] jobs it supplies for Ceo is probably [/INST] absolutely they can go become Ceo somewhere else but don't stay Ceo one place too long. It's a problem with startups, right? The founder, you can have a billion founder and that founder doesn't want to let go. Yeah, it's the same issue </s><s>[INST] at the same time. I mean, this is where Elon musk and a few others like uh larry page and Sergey brin. That stayed for quite a long time and they actually were the beacon, they on their shoulders carried the dream of the company where everybody else doubted so, but that seems to be the exception right versus the rule. [/INST] And even Sergey for example, right has stepped back, right? He plays less of a day to day role and is not running google on the way. </s><s>[INST] The interesting thing is you step back in a quite tragic way from what I've seen, which is I, I think google's mission, an initial mission of making the world's information accessible to everybody is one of the most beautiful missions of any company in the history of the world. I think it's what google has done with a search engine and um, and other efforts that are similar like scanning a lot of books. Just incredible. It's similar to like Wikipedia. But what he said was that it's not the same company anymore. And I know maybe I'm reading too much into it because it's more maybe practically saying just the size of the company's much larger, the kind of leadership that square. But at the same time they changed the model from, you know, don't be evil too, is becoming corporatized and all those kinds of things. And it's sad. It um, [/INST] they're also recycles, right? History is about cycles right? There there there cycles to life. Their cycles to organizations. </s>

<s>[INST] actually the question is brilliant, curious minds. It even at that age, it was uh definitely a huge loss but on his game of life, Which was, I think he developed in the 70s is almost like a side thing. A fun little experiment of life [/INST] is this um It's a very simple algorithm. It's not really a game per se in the sense of the kinds of games that he liked, where people played against each other. And um but essentially it's a game that you play with marking little squares, initiative, graph paper. And in the seventies, I think he was like literally doing it with like a pen on graph paper, you have some configuration of squares, sum of the squares and the graph people are filled in. Some are not. And then there's a rule, a single rule that tells you um at the next stage which squares are filled in and which squares are not. Sometimes an empty square gets filled in that's called birth. Sometimes the square that's filled in gets a race that's called Death and there's rules for which squares are born which squares die. Um It's um the rule is very simple. You can write it on one line and then the great miracle is that you can start from some very innocent looking little small set of boxes and get these results of incredible richness. And of course nowadays you don't do it on paper. Nowadays you do in a computer. It's actually a great ipad app called Golly, which I really like that has like Conway's original rule and like, Gosh, like hundreds of other variants and it's lightning fast. So you can just be like, I want to see 10,000 generations of this rule play out like faster than your eye can even follow. And it's like amazing. So I highly recommend it if this is it all intriguing to you getting golly on your uh IOS </s><s>[INST] device and you can do this kind of process, which I really enjoy doing, which is almost like putting a Darwin head on or a biologist head on and doing analysis of a higher level of abstraction. Like the organisms that spring up. Because there's different kinds of organisms. Like you can think of them as species and they interact with each other. They can, there's glider, they shoot, there's like things that can travel around. There's things that can glider guns that can generate those gliders. They use the same kind of language as you would about describing a biological system. [/INST] So it's a wonderful laboratory and it's kind of a rebuke to someone who doesn't think that like very, very rich, complex structure can come from very simple underlying laws. Like it definitely can. Now, here's what's interesting if you just picked like some random rule, you wouldn't get interesting complexity. I think that's one of the most interesting things of these uh one of the most interesting features of this whole subject that the rules have to be tuned just right, like a sort of typical rule set doesn't generate any kind of interesting behavior. Yeah, but some do I don't think we have a clear way of understanding which doing, which don't maybe Stephen thinks he does, I don't know. </s><s>[INST] But no, no, it's a giant mystery with Stephen, Stephen Wolfram did is um now there's a whole interesting aspect of the fact that he's a little bit of an outcast in the mathematics and physics community because he's so focused on a particular, his particular work. I think if you put ego aside, which I think unfairly some people are not able to look beyond. I think his work is actually quite brilliant. But what he did is exactly this process of Darwin, like exploration is taking these very simple ideas and writing 1000 page book on them, meaning like, let's play around with this thing, let's see. And can we figure anything out? Spoiler alert? No, we can't. In fact he does, he does a challenge. I think it's like Rule 30 challenge, which is quite interesting just simply for machine learning people, for mathematics people is, can you predict the middle column for his? It's a it's a one d cellular Tamara, can you predict generally speaking, can you predict anything about how a particular rule will evolve just in the future? Very simply, just looking at one particular part of the world, just zooming in on that part, you know, 100 steps ahead. Can you predict something? And uh the the challenges to do that kind of prediction so far as nobody's come up with an answer. But the point is like we can't we don't have tools or maybe it's impossible or I mean he has these kind of laws of your disability. They hear first about his poetry. It's like we can't prove these things. It seems like we can't that's the basic, it almost sounds like ancient mathematics or something like that where you like, the gods will not allow us to predict the seller your time with a But uh that's fascinating that we can't I'm not sure what to make of it. And there is power to calling this particular set of rules. Game of Life is Conway did because not exactly sure. But I think he had a sense that there's some core ideas here that are fundamental to life too complex systems to the way life emerged on earth. Uh [/INST] huh. I'm not sure. I think Conway thought that it's something that Conway always had a rather ambivalent relationship with the Game of Life because I think he saw it as it was certainly the thing he was most famous for in the outside world. And I think that he his view which is correct is that he had done things that were much deeper mathematically than that, you know. And I think it always like aggrieved him a bit that he was like the Game of Life guy when you know, he proved all these wonderful theorems and like did I mean created all these wonderful games Like created the serial numbers. Like I mean he did I mean he was a very tireless guy who like just like did like an incredibly variegated array of stuff. So he was exactly the kind of person who you would never want to reduce the like one achievement. You know what I mean? </s>

<s>[INST] of what we're doing on this planet. It's interesting, the thing about the Big Bang is basically from our current perspective of what we're able to detect, [/INST] it's the time when things were forgotten. </s><s>[INST] Yes. It's the time of the reset, from our limited perspective. And so the question is, is it useful to ever study the thing that was forgotten? Or should we focus just on the memories [/INST] that are still there? Well, the point I was trying to make about the experiment is I was trying to say both things. And I think perhaps yes from the following point of view, if you could then imagine what was forgotten and then work forwards, you will have different consequences. So then it becomes testable. So as long as we can find tests, then it's definitely worth thinking about. What I don't like is when physicists say what happened before the Big Bang and before, before, before, without giving me any credible conjecture about what we would, how would we know the difference? But the way you framed it is quite nice. I like that. </s><s>[INST] It's like, what have we forgotten? Is there a room for God in assembly theory? [/INST] Who's God? I like arguments for a necessary being better than God. Well, I think I said it earlier. What's a necessary- Like something that has to exist. Well, I think I said it earlier. </s><s>[INST] What's a necessary- Oh, so you like, I mean, you like the shortest path. [/INST] Like does God need- No, no, no. I mean, I, well, you can go back to like Thomas Aquinas and arguments for the existence of God. But I think, I think most of the interesting theological arguments are always about whether something has to exist or there was a first thing that had to exist. But I think there's a lot of logical loopholes </s><s>[INST] in those kinds of arguments. Well, so God here, meaning the machine [/INST] that creates, that generates the stuff. But God- So what I was trying to say earlier is- Isn't that just the universe. That's what I was trying to say earlier is- Isn't that just the universe? </s><s>[INST] Yeah, yeah, yeah. Yeah. Yeah, well, yeah. Yeah, yeah. Well, yeah. Well, yeah. Well, but I, there's a difference between... Should I imagine like a black box, like a machine? Yeah. That's then I would be more comfortable [/INST] calling that God. </s><s>[INST] Yeah. That because it's a machine. [/INST] You go into a room and there's a thing with a button. Yeah. I don't like the great programmer in the sky version. </s><s>[INST] Can I? You know? Yeah, but if it's more kind of, Like to don't like to think of, if you look at a cellulared autonomous, If it's the cells and the rules, that doesn't feel like God that generates a bunch of stuff. But if there's a machine that runs the cellular automata and set the rules, then that feels like God, in terms of terminology. So I wonder if there's a machine that's required to generate this universe. [/INST] That's very important for running this in the lab. So as I said earlier, I think I said this earlier, that I can't remember the phrase, but something like, I mean, does God exist in our universe? Yes. Where does God exist? God at least exists in the abstraction in our minds, particularly of people who have religious faith they believe in. But let's then take your, but you're talking a little bit more about generic, say, well, is there a mechanism beyond the universe you're calling God? I would say God did not exist at the beginning, but he or she does now, because I'm saying the mechanism. </s><s>[INST] Well, you don't know if he didn't exist in the beginning. So this could be us in our minds trying to just listen to gravitational waves, detecting gravitational waves. It's the same thing. It's us trying to go back further and further into our memories to try to understand the machines that make up, that make up us. And so it's possible that we're trying to grasp at possible kind of what kind of machines could create. There's always a tweet. There's always a tweet. If the universe is a computer, then God must have built it because computers need creators. There you go. And then Joachim Bach replied, since there's something rather than nothing, perhaps existence is the default. If existence is the default, then many computers exist. Creator gods are necessary computers, unnecessarily computers too. I'm very confused by that. [/INST] But that's an interesting idea that existence is the default versus non-existence. </s><s>[INST] I agree with that, but the rest is not. And then Lee responds, perhaps this reasoning is incomplete. That's how scientists talk trash each other on Twitter, apparently. [/INST] Which part don't you agree with? And he said, if existence is the default, then many computers exist. This comes back to the inventor and discovery argument. I would say the universe at the beginning wasn't capable of computation because there wasn't enough technology, enough states. So what you're saying is if God is a mechanism. So I might actually agree, but then the thing is lots of people see God is more than a mechanism. For me, God could be the causal graph in assembly theory that creates all the stuff and memories we know. And the fact that we can even relate to each other is because we have the same, we share that heritage. And why we love each other or we like to see God in each other is it's just we know we </s>

<s>[INST] 1000 by 1000 by 1000 [/INST] Adams </s><s>[INST] that's a really clean way of putting [/INST] It. Well fan like a modern transition. If you look at the fan it's like 120 atoms wide. But we can make that thinner and then there's there's a gate wrapped around it and then their spacing, there's a whole bunch of geometry and you know, a competent transistor designer could count both Adams in every single direction. Uh huh. Like there's techniques now to already put down atoms in a single atomic layer. Right? And you can place Adams if you want to it's just you know, from a manufacturing process placing Adam takes 10 minutes and you need to put you know 10 to the 23rd atoms together to make a computer. It would take a long time. So the the methods are you know, both shrinking things and then coming up with effective ways to control what's happening, </s><s>[INST] manufacture stable and cheaply. [/INST] Yeah. So so the innovation stocks pretty broad, you know there's there's equipment, there's optics, there's chemistry, there's physics, there's material science, there's metallurgy, there's lots of ideas about when you put them from materials together, how they interact with a stable, stable over temperature, you know like are the repeatable, you know, there's like there's like literally thousands of technology is involved. </s><s>[INST] But just for the shrinking, you don't think we're quite yet close to the fundamental limits of physics. [/INST] I did a talk on moore's law and I asked for a road map to a path about 100 and after two weeks They said we only got 2, 50, </s><s>[INST] 100, extra 100 x drink [/INST] 50. And I said, Why don't you give it another two weeks? Well, here, here's the thing about moore's law, right? So I believe That the next 10 or 20 years of shrinking is going to happen right now as a computer designer, you have two stances. You think it's going to shrink, in which case you're designing and thinking about architecture in a way that you'll use more transistors or conversely not be swamped by the complexity of all the transistors you get right, you have to have a strategy, </s><s>[INST] you know, so you're open to the possibility and waiting for the possibility of a whole new army of transistors ready to work. [/INST] I'm expecting expecting more transistors every two or three years by a number large enough that how you think about design, how you think about architecture has to change. Like imagine you're, you you build build brick buildings out of bricks and every year the bricks are half the size or every two years. Well, if you kept building bricks the same way, you know, so many bricks per person per day, the amount of time to build a building when we go up exponentially. Right? But if you said I know that's coming. So now I'm going to design equipment and moves bricks faster, uses them better because maybe you're getting something out of the smaller bricks more strength in their walls, you know, less material efficiency out of that. So once you have a road map with what's going to happen, transistors they're gonna get we're gonna get more of them. Then you design all this collateral around it to take advantage of it and also to cope with it. Like that's the thing people understand, it's like if I didn't believe in moore's law and moore's law, transistors showed up, my design teams are all drowned. </s><s>[INST] So what's the what's the hardest part of this in flood of new transistors? I mean even if you just look historically throughout your career, what's what's the thing what fundamentally changes when you had more transistors in the task of designing and architecture? [/INST] Well there's there's two constants, right? One of those people don't get smarter, </s><s>[INST] by the way, there's some signs showing that we do get smarter but because the nutrition whatever. [/INST] Sorry to bring that in effect. Yeah, familiar with it, nobody understands it, nobody knows if it's still going on, so that's on it </s><s>[INST] or whether it's real or not. But yeah, it's a [/INST] I sort of anyway, but I believe for the most part of people aren't getting much smarter, </s><s>[INST] the evidence doesn't support it, right [/INST] and then teams can't grow that much. Alright, alright, so human beings Under, you know, we're really good in teams of 10, you know, up to teams of 100 they can know each other beyond that. You have to have organizational boundaries. So you're kind of you have those are pretty hard constraints right? So then you have to divide and conquer like as the designs get bigger, you have to divide it into pieces, you know, the power of abstraction layers is really high. We used to build computers out of transistors. Now we have a team that turns transistors and logic cells and another team that turns them into functional. It's another one that turns into computers. All right. So we have abstraction layers in there and you have to think about when you shift gears on that. We also use faster computers to build faster computers. So some algorithms run twice as fast on new computers but a lot of algorithms are in squared. So a computer with twice as many transistors and it might take four times times as long to run. So you have to re factor the software like simply using faster computers to build bigger computers doesn't work. So you have to think about all these things. </s>

<s>[INST] I'm a silly little kid trying to do a bit of good in this world. Thank you for having my back through all of it, all of my mistakes. Thank you for the love. And now, a quick few second mention of each sponsor. Check them out in the description, it's the best way to support this podcast. We got House of Macadamia's for snacks, Linode for Linux systems, Onit for supplements, Inside Tracker for bio monitoring, and ExpressVPN for security and privacy. Choose Wise and my friends. And now, on to the full ad reads. Never any ads in the middle, I hate those, I tried to make these interesting but if you [/INST] skip them, please still check out our sponsors, I enjoy their stuff, maybe you will too. </s>

<s>[INST] Oh, you mean like a Nobel Peace prize for maybe maybe, you [/INST] know, maybe a Nobel Peace prize. Yeah, I think so. </s><s>[INST] I mean, he had a very young age got the touring award for his work and algorithms and so on. So like an incredibly they're gonna I think it's an It might be even the 60s, but I think it's the seventies that so when he was really young and then he went on to do like incredible work with his book and uh yeah with with tech that people don't know [/INST] and going back just one on the reason why we ended up because I think this is interesting the reason why we ended up using the name Firmas library. This was because of farmers last year. Um and from us last year was actually a funny story. So Pierre de Firma, he was like a lawyer and he wrote like on a book that he had a solution to Fermat's last theorem, which but that didn't feed the margin of that book. And so from us last year basically states that there is no solution. If you have uh integers A, B and C. There is no solution to A to the power of and plus B to the power of N equals two C. To the power of when and if and is bigger than two. So there's there's there's no solutions. And it said that And that problem remained open for almost 300 years I believe. And a lot of the most famous mathematicians tried to tackle that problem. No one was able to figure that out until Andrew Wiles Uh I think was in the 90s was able to publish the solution which was I believe almost 300 pages long. And so it's kind of an an anecdote that you know, there's a lot of knowledge and insights that can be trapped in the margins then and there's a lot of potential energy that you can release if you actually um spend some time time trying to digest that and that was the the origin story </s><s>[INST] for for the name, you actually can share the contents of the margins with the world. Exactly inspire a solution or communication at the least a solution. [/INST] But and if you think about the papers like papers are as, as john was saying probably one of the densest species of, of texted any human can read. And you have these researchers like some of the brightest minds in these fields working on like new discoveries and publishing this work on journals that are imposing them restrictions in terms of the number of pages that they can have to explain a new scientific breakthrough. So at the end of the day, papers are not optimized for clarity and for a proper explanation of that content because there are so many restrictions. So there's, as I mentioned, there's a lot of potential energy that can be freed. If you actually try to digest a lot of the contents of papers. </s><s>[INST] Can you explain some of the other things? Some margins Liberian journal [/INST] club. So Journal Club is what a lot of people know is for where we every week we release an annotated paper and in all sorts of different fields with physics. Yes, Math margins is kind of the same software that we used to run the Journal Club and to host the annotations, but we've made that available for free to anybody that wants to use it. And so folks use it at universities and, and for running journal clubs and, and, and so we just made that freely available. And then librarian is a browser extension that we developed. That is sort of an overlay on top of archive. So it's about bringing some of the same functionality around comments, plus adding some extra, uh, niceties to archive. Like being able to very easily extract the references of a paper that you're looking at or being able to extract the big tech in order to cite that paper yourself. Um, so it's an overlay on top of archive. It is that you can have that commenting interface without having to leave archive. It's kind </s><s>[INST] of incredible. I didn't know about it, and once I've learned of it, it's like, holy shit, why isn't it more popular given how popular archive is? Like, everybody should be using it. Archive sucks in terms of uh, let me rephrase that. It's limited [/INST] in terms of the archive is a pretty incredible project, right? And it is in a way, it's, </s><s>[INST] you know, [/INST] The growth has been completely linear over time. If you look at like a number of papers published on archive, like, you know it's just been it's pretty much straight line for the past 20 years. Especially for you know like if you're coming from a startup background and then you are trying to do archive you'd probably try like all sorts of growth acts and like try to to then maybe like have paid features and things like that and and that would kind of maybe ruin it. And so there's there's a subtle balance there and I don't know what aspects you can change about it for some tools in science it just takes time for them to archive. Just turned 30 I believe for people that don't know, archive is this kind of online repository where people put pre prints which are versions of the papers before they actually make it to journals </s><s>[INST] A. R. X. I. Ve exactly people who don't know and it's actually a really vibrant place to publish your papers and in the aforementioned uh communities of mathematics and computer science, [/INST] It started with mathematics and physics and any over the last 30 years it evolved. And now actually computer computer science now it's it's a more popular category than physics and math on archive. </s>

<s>[INST] be a company. And you were on a ton of medication throughout the whole process. [/INST] And my mom being the tenacious truck driver she is, she was driving for Kevin Hart's what now tour. And so she got, she just harassed them, was like, you need to meet my daughter. Yeah, I saw the picture of you and Kevin Hart at school. But he just gave me a good piece of advice. Hey, if you're going to make this something, you can't really, if you want it to be for everyone, you can't call it her wearables. I was like, cool. And then we drove home that night and then he tweeted it out to people to 24 million people. This was before he was like, who is now? And that was a giant deal. And then my husband kind of looked at me and being, he's so brilliant. He looked at me and goes, all right, yeah, we got to come up with a rename. Let me start thinking, let me start brainstorming. Like, let's make, you want to make this real? Let's make this real. Mm-hmm. And so we did and he was like, what do you think about like we were doing like brass collective co brass this butter I just knew I wanted brass in the name. Mm-hmm. And then he's a little bit brass and unity You're trying to like unify people. Like why wouldn't you do that? That's a great name well, he's a brilliant person it's annoying Yeah So the idea of losing this thing that I we had just built and just got me kind of functioning with was devastating Mm-hmm. Yeah, I saw the picture of you and Kevin Hart. That's cool. Yeah. Yeah, that's a great name going Yeah, so I got this opportunity given to me by griff combat flip-flops Again Brady my husband was like, hey you should get sponsors for your podcast Hey, have you heard of this company combat flip-flops? Remember we watched him on Shark Tank and then I reached out He emailed me back. He's like, yeah, we go to together like peanut butter and jelly or companies. That sounds great And then I was like, hey also, like do you think one of your owners would want to come on the podcast? just like tossing it out there kind of like I did with you and He was like, yeah I'd love to come on and I was like Mm-hmm and he came on the podcast and it went great and then at the end of it We stopped recording and he just kind of did this thing. He he does this. She's like leans in real close goes, looks into your soul and goes, how are you doing? And they're like, great. He's like, I really do. Just this whole, just like waterworks happen. And he goes, listen, have you ever heard of ayahuasca? And I was like, yeah, like in movies and like psychedelics in the seventies, you know? And he's like, no, no, no, no. Let's like have a talk. And he goes, I've got an opportunity for a spot. I'm going with this charity called heroic hearts. Um, they have, they have, uh, spaces in UK, Canada, and the United States. They're owned by an army ranger named Jesse Gould. Um, you know, they're really trying to help vets and this has worked. Would you want to come? And before he even said like, would you, before I even got like an invite, I was like, can I come? When can I, when, when, when do we, when do we go? And he's like, oh, it's in like three weeks. Um, you can't be on any SSRIs. If you're on any, you're going to have to wean off. And at the time I was on my last one, and so I was like, I called my doctor and I was like, listen, and he was like, wordnet, and I was like, guess what I'm about to do. And he's like, I'm like going to go do ayahuasca. And he goes you going to, he does the same where he just goes, guess what, all right. Cause he knows he's not going to win. He knows I'll just fight him on it. </s><s>[INST] He knows I'll just fight him on it. That's just called that, like the the Jaco reset. [/INST] Yeah, because he does it. Yeah, pretty much. Yeah, exactly. Then he goes, I said, But here's the kicker. I have to go off of this medication. And it was well, you know we're supposed to do that in the summer months when the depression is not, you know, let us listen. I hear you, but I'm doing it, whether you want me to or not. So I'm letting you know, hey, this is going to happen. And he's like, OK, just try to do it properly. I was like, yeah, yeah. I know the drill. I know the drill or whatever, whatever once will be a paramedic. I don't the drill. I'll go off of a proper like Like drop that... Within a week that stuff was, I was done taking it. And I was going through like the world's worst just withdrawals. It was like, I'm letting... You were at a rock concert and your head was banging up and down, but you were sitting perfectly still. </s><s>[INST] It was horrible. But you had like a thing to look forward to with the sidewalk today. [/INST] I had a light at the end of the tunnel. I had a light at the end of the tunnel. And I knew if I got to the light was the worst that's gonna happen. Just get to the light. But at that point, again, I had a son, I had a husband, I had a great company, I have a great house, I have a nice car, I have everything. Why did I want to die every minute of the day? I was at that point again. And I'm like, this has got it, something's got to give. And so I went and I got there and she is the most intense, beautiful, divine deity or entity or visualization, whatever you want to deem ayahuasca as, mama ayah is the real and she takes no prisoners. She shows you exactly what you need to see to help yourself. But she does not discriminate against whether you're ready or not, if you've ingested it, she's coming for you. She's going to be either gentle or she's going to beat your ass and sometimes that's what you need. </s>

<s>[INST] What do you think is the best movie sequel of all time? Speaking of Part 2? Because like because most of them suck [/INST] movie </s><s>[INST] Sequels and you tweet about movies. So just a tiny tangent is there? What's your, what's like a favorite movie sequel? Godfather? Part two. Um Are you a fan of Godfather cause you didn't even tweet or mention the Godfather. [/INST] Yeah, I don't love that movie. I know it hasn't </s><s>[INST] edit that out. We're going to edit out the hate towards The Godfather? How dare you [/INST] Think will make a strong statement? I don't know why. I don't know why, but I basically don't like any movie before 1995. Something like that. </s><s>[INST] Didn't you mention Terminator [/INST] 2? Okay, Okay. That's like a terminator two was a little bit later, 1990. </s><s>[INST] No, I think terminator two was in there [/INST] And I like terminator one as well. So okay, so like a few exceptions, but by and large, for some reason I don't like movies before 1995 or something, they feel very slow. The camera is like zoomed out, it's boring, it's kind of naive. It's kind of weird. </s><s>[INST] And also Terminator was very much ahead of its time. [/INST] Yes. And The Godfather, there's like no, A G. I joe </s><s>[INST] I mean, but you have Good Will Hunting was one of the movies you mentioned and that doesn't have any A G. I either. I guess that's mathematics. I [/INST] guess occasionally I do in the movies that don't feature or </s><s>[INST] like anchorman that has no, that's that [/INST] is so good. </s><s>[INST] I don't understand. Um Speaking of A G. I because I don't understand why Will Ferrell is so funny. It doesn't make sense. It doesn't compute there's just something about him and he's a singular human because you don't get that many comedies these days and I wonder if it has to do about the culture or the like The Machine of Hollywood or does it have to do it just we got lucky with certain people in comedy came together because he is a singular human. That was a ridiculous tangent, I apologize, but you mentioned humanoid robots. So what do you think about optimus? About Tesla body? Do you think we'll have robots in the factory in in in the home in 10 2030, 40, 50 years? [/INST] Yeah, I think it's very hard project, I think it's going to take awhile but who else is going to build human robots at scale? And I think it is a very good form factor to go after because like I mentioned that the world is designed for human in form factor. These things will be able to operate our machines, they will be able to sit down in chairs, potentially even drive cars. Uh basically the world is designed for humans, that's the form factor you want to invest into and make work over time. Uh I think you know, there's another school of thought which is okay, take a problem and design a robot to it. But actually designing a robot and getting a whole data engine and everything behind it to work is actually incredibly hard problem. So it makes sense to go after general interfaces that okay, they are not perfect for any one given task but they actually have the generality of just with a prompt with english able to do something across and so I think it makes a lot of sense to go after a general uh interface um, in the physical world. And I think it's a very difficult project. It's going to take time. Um, but I see no other, no other company that can execute on that vision. I think it's going to be amazing. Like uh basically physical labor, like if you think transportation is a large market, try physical labor insane, </s><s>[INST] but it's not just physical labor. To me, the thing that's also exciting is the social robotics. So the relationship will have on different levels with those robots. That's why I was really excited to see optimists like um people have criticized me for the excitement, but I've I've worked with uh a lot of research labs that do humanoid legged robots, boston dynamics, unitary. A lot there's a lot of companies that do legged robots, but that's the the elegance of the movement is a tiny tiny part of the big picture. So integrating the two big exciting things to me about Tesla doing humanoid or any legged robots is clearly integrating into the data engine. So the data engine aspect, so the actual intelligence for the perception and the and the control and the planning and all that kind of stuff integrating into this huge the fleet that you mentioned, right. Um and then speaking of fleet, the second thing is the mass manufacturers just knowing uh culturally uh driving towards a simple robot that's cheap to produce at scale and doing that well, having experience to do that. Well, that changes everything. That's why that's a very different culture and style than boston dynamics who by the way, those those robots are just the way they move. It's like, it'll be a very long time before Tessa can achieve the smoothness of movement. But that's not what it's about. It's, it's about, it's about the entirety of the system. Like we talked about the data engine and the fleet. That's super exciting. Even the initial sort of models but that too was really surprising that in a few months you can get a prototype [/INST] and the reason that happened very quickly is as you alluded to, there's a ton of copy paste from what's happening in the autopilot a lot. The amount of expertise that like came out of the woodworks at Tesla for building the human robot was incredible to see like basically Ellen said at one point, we're doing this. And then next day, basically like all these cad models started to appear and people talking about like the supply chain and manufacturing and people showed up with like screwdrivers and everything like the other day and started to like put together the body and I was like, whoa! Like all these people exist at Tesla and fundamentally building a car is actually not that different from building a robot the same. And that is true, not just for the hardware pieces and also, let's not forget hardware, not just for a demo, but um, manufacturing of that hardware at scale. It's like a whole different thing, but for software as well, basically this robot currently thinks it's a car. Uh, it's gonna </s>

<s>[INST] Unweighted is 30%, you said? Yeah, 30%. It's insane. I'd like to see the worst ones, the people that are tracking that average up. But 14% is still an incredibly high, high number. [/INST] And so you're saying that, sorry, that's the average over the century, or the past 100 years? Over the past 60 years, 1960s to 2020, we get World Bank data on that, pretty reliable data on World Bank and European Union OECD data. I ran the numbers on that weighted average, something like 14%. And what effect that has on time preference? The effect is now it's much, much, much harder for everybody to provide for their future. Everywhere in the world, it's much harder. So how do I get the equivalent of the old gold coin that I could just put under my mattress and expect it to be there 10 years from now? Well, gold itself isn't cutting it. Gold can't keep up with inflation. And the reason for that is that gold is not being used as a money anymore in that you can't send it internationally. You can't use it to settle trade internationally, which therefore means demand for it monetarily is limited. And so it's becoming more and more an industrial metal. And as a result, as a result of the fact that its value doesn't keep up with inflation, it becomes economical to use it in industry. So we're seeing gold become like silver, in that it gets used in industry. So the stockpile declines, and so the stock to flow ratio declines as well, and it becomes more and more of an industrial metal. And it can't protect your wealth over time very well. So what do you do? Well, you could invest, and this is kind of the obvious answer that Keynesian will give you is, well, you just put your money in an investment. But investment is different from saving. Saving, the whole point of saving is that the thing is liquid and that the thing carries little uncertainty. You know, you just held the gold coin and it just sat there, it did nothing, it didn't take risk. You knew that it was going to be there in 10 years. Investment means you give the gold coin to somebody to go and do something with it. And it could work, it could not work. If it works, you get a positive return, you get more gold back. If it fails, you might not get any of your gold back. So taking on risk is something very different from saving. Saving is just a way of buying the future. Everything is taking on a risk and you could lose everything with it. What ends up happening, and this is the Keynesian objection, I think, is very wrong and bad because investment is a job in itself. To figure out what to do with your money in order to beat inflation is something that there are professionals out there on Wall Street that have PhDs in finance, that have enormous computers, and they have enormous staffs of PhDs and master's degrees and math nerds that are crunching numbers and figuring out how to allocate your portfolio so that you can beat inflation. And guess what? The majority of them don't beat inflation. The majority of them can't beat inflation. Not as measured by CPI, which is completely fraudulent, but if you remember- 14%. Yeah, that 14% or even the 7%. If you look at just the increase in the money supply, which I think is a much better metric, and this is what's reflected on the desirable goods. If you look at the price of real estate in Miami Beach, as Michael Saylor mentioned in your example, it goes up at around 6%, 7% per year on average over the last century. If you want to live in a nice area, that's what's happening to real estate. If you want to go to the good universities, that's what's going up. It's going up at a rate that's similar to the increase in the money supply. You can beat CPI, but CPI is designed so you can beat it, but you can't really beat the appreciation in the things that you actually want to buy, the price of good food, the price of good real estate. Most investment professionals fail at doing that. What hope does a doctor or an engineer or a scientist or an athlete have in doing those things? Investment is hard, and savings should be easy. Exactly. Saving is essential for us as a civilization. What Fiat did is it took that away from us, and then it forced everybody to become an investor or more accurately a gambler, because the money itself is broken, because the money itself is constantly changing in value. Investing is becoming more of a crapshoot. Value investing is completely underperforming compared to market analysis. You listen to the Fed, and what matters to the price of individual companies is monetary policy much more than it is their own performance. Basically you need to be a junkie watching the Fed and following all of the world's central banks. I need to learn macroeconomics, and you need to learn what all the central banks are doing, you need to understand how commodity markets work, and you need to understand how equity markets work, and bond markets, and real estate markets. You need to do all those things just in order to be able to save and earn and keep the money that you've already earned. That's the criminal thing about it. I've already earned that money being a doctor, being a dentist, being an athlete, being an I built a house for somebody and I got that money, and all I want to do is just make sure that I can have it 10 years from now. The only way to do so is to become a crappy engineer, because you have to spend half your time not doing engineering, and instead spend half of that time learning about Japanese central bank monetary policy and commodity markets and what's going to happen to copper and what's going to happen to oil and what's happening in the wars and what's happening with foreign policy. and Russia and the US and all those things. Under the gold standard, you didn't care about any of that stuff. Your gold coin worked regardless of all of those things. So what this means is the future, so first of all, you know, we have all of the problems </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] Yeah, the the expanse is huge and so much cool stuff could be going out there. And um the scary thing of course is if they haven't visited us yet, the there has to be a good reason for it. And the set of scary reasons of all the fact that they maybe once we get sufficiently advanced in your development, you destroy yourself naturally as humans seem to be approaching. Now. We we more and more have the tools to destroy ourselves completely in terms of our weapons systems and we're developing them more and more and they're becoming better and better. And then we're starting to get angry and anger on twitter and instagram with each other. There's a good point. You're raising [/INST] hysteria starts us that everything that lives one day will die. So we will we will </s><s>[INST] perish one day. There's also just the sheer difficulty of um of of travel through space like space is an unimaginably inhospitable environment and to the best of our knowledge, even the theoretical speeds that we can attain in space even if we could travel at the speed of light were not even remotely close to that. Still, the distances that need to be traveled to get to even relatively close solar systems very very long. If you look at astronauts who have spent significant amounts of time and space just orbiting the earth, it has severe health effects on them when, which is not built for space, we're supposed to be in a gravitational environment. But we you're referring to your biological meat back that's containing the essence of the mind that is john Donna her. Maybe we can transfer the mind alone in the bag. The meat. The meat bag is not designed for space, but maybe the contents of the mind. It's possible. But what do you think of concrete evidence with you folks who like difficult things? What do you think about Elon musk going to colonize Mars, is this something you find interesting or a um Amos pursuit? [/INST] I think it's a mass or a salvation. We need to leave at some point the planet because historically in the past we know that we've been bombarded by asteroids volcano. There are crazy things happen here. It's very unstable, you know? Well, if you look at it to to a lifetime of a human being, it's nothing but Just looked 12,000 years ago, what happened? You know, so, so there is a cataclysm that happened all the time. It's very unstable. So if we want to survive as a species, I think it's, it's, we need to get out to be able to get out and spread </s><s>[INST] our seed. So these are the early steps on on a really long journey. But is there something about like, you know, we, we don't get that exploration from most of modern society. You know, the kind of exploring that people did throughout the centuries of uh, you know, coming to the north America just throughout, we were shrouded in physical uncertainty of what's out there. And now we get to do the same kind of exploration with Mars, is there? So, I mean, is there any aspect of you that wants to travel out to space that wants to travel to Mars there, you know, the goal is to allow civilians to travel perhaps in our lifetime meaning affordably, you can do so now unaffordable e [/INST] traveling to space and traveling to MARS are two different things. I think I would like to travel into space. I don't know if I would like to travel all the way to </s><s>[INST] MARS because of the risks involved [/INST] just because </s><s>[INST] boring. Is there some part of you that I [/INST] think that if I was like towards the end of my life, I would like to travel tomorrow. Just just the experience. Yeah, but if I go to MArs, I'm not coming back Like that's it. one way ticket with the technology we have now maybe in the future maybe are the Children of our Children will will be able to experience that to go to the weekend on MArs. </s><s>[INST] Uh well the the whole design of the starship that SpaceX is working on is supposed to come back. It's supposed to be reasonable. So it's not it's not a one way ticket. That's the whole point. It's always going back and forth, back and forth. [/INST] What's the timeframe between two planets? I like to travel from, </s><s>[INST] I think the current thing you'd be stuck on Mars for two years. [/INST] But how long does it take to get from Earth to Mars? </s><s>[INST] Oh, it's pretty, I'm not exactly sure, but it's pretty quick. That's pretty quick. Like, I don't know. And the scale of months, not scale of years, [/INST] you might not be healthy when you come back. You know, all the astronauts, the experience, health issues, you know, they lose a lot of muscle mass, bone density. So I don't think the technology is good right now. I mean </s><s>[INST] let's say that [/INST] it is. I would love to be doing it for a weekend if it's safe. I wouldn't be the first one to do it </s><s>[INST] for a professional fighter who sacrificed his body for something. So there's some sacrifice we do in life, right? [/INST] I wouldn't want to be the first, I wouldn't want to leave the other one, but when I know it's it's safe. Okay. Count me </s><s>[INST] in. So one of the things that people say and this is something I wonder about is it's like having Children or something. Once you see once you're out in space and you look out and you see earth, you look back at Earth. That's an experience. It's not like anything else. Like you can't replicate it here. Um is to look back at that like blue dot [/INST] and that nerve racking, you see like Earth disappear into the distance. </s>

<s>[INST] Yeah, I would love there to be open conversations and a lot of great research being released internally and then also externally it um it doesn't make me feel good to see press obviously get way more clicks when um they say negative things about social media. Listen objectively speaking, I can just tell that there's hunger to say negative things about social media and I don't understand how that's supposed to lead to an open conversation about the positives and the negatives, the concerns about social media, especially when you're doing those kind of that kind of research, I mean, I don't know what to do with that, but let me ask you as a father, there's a way heavy I knew that people get bullied on social networks, so people get bullied in their private [/INST] life, </s><s>[INST] but now, because so much of our life is in the digital world, the bullying moves from the physical world to the digital world, so you're now creating a platform on which bullying happens and some of that bullying can lead to damage to mental health and some of that bullying can lead to depression, even suicide. There's a way heavy on you that people have committed suicide or will commit suicide based on the bullying that happens on social media. [/INST] Yeah, I mean, this is a there's a set of harms that we basically track and build systems to fight against and bullying and you know, self harm are, you know, I mean, these are these are some of the biggest things that we that we are most focused on um, for bullying. Like you say, it's going to be while this predates the internet, then it's probably impossible to get rid of all of it. Um You want to give people tools to fight it, um, and you and you want to fight it yourself, and you also want to make sure that people have the tools to get help when they need it. So, I think this isn't like a question of, can you get rid of all bullying? I mean, it's like, all right. Um, I mean, I have two daughters and you know, they fight and you know, push each other around and stuff too. And the question is just how do you how do you handle that situation? And there's a handful of things that I think you can you can do. Um we talked a little bit before around some of the ai tools that you can build to identify when something harmful is is happening. It's actually it's very hard and bullying because a lot of bullying is very context specific. It's not like you're trying to fit a formula of like, you know, if if like looking at the different harms um you know, someone promoting a terrorist group is like probably one of the simpler things to generally find because things promoting that group are going to, you know, look a certain way or feel a certain way, bullying could just be, you know, someone making some subtle comment about someone's appearance that's idiosyncratic to them </s><s>[INST] and it could look at just like humor, humor to one person exactly destructive to another [/INST] with bullying. I think there are there are certain things that you can find through AI systems um but I think it is increasingly important to just give people more agency themselves. So we've done things like making it so people can turn off comments or you know, take a break from um you know, hearing from a specific person without having to signal at all that they're going to stop following them or or or kind of make some some stand that okay, I'm not friends with you anymore, I'm not following you, I just like I just don't want to hear about this, but I also don't want to signal um at all publicly that um or to them that that there's been an issue. Um and then you get to some of the more extreme cases like you're talking about where someone is thinking about um self harm or suicide and um in there we found that that is a place where ai can can identify a lot as as well as people flagging things, you know, people are um expressing something that is, you know, potentially they're thinking of hurting themselves. Those are cues that you can build systems and you know, hundreds of languages around the world to be able to identify that. And one of the things that I'm I'm actually quite proud of is we've we've built the systems that I think are clearly leading at this point, that not only identify that but then connect with local um first responders and have been able to save. I think at this point it's you know in thousands of cases be able to get first responders, two people um through these systems who really need them um because of specific plumbing that we've done between the Ai work and being able to communicate with with local first responders, organizations were rolling that out in more places around the world and um and I think the team that that worked on that just did awesome stuff. So I think that that's a long way of saying, yeah, I mean this is this is a this is a heavy topic and there's you want to attack it in a bunch of different ways um and also kind of understand that some of nature is for people to to to do this to each other, which is unfortunate, but um but you can give people tools and and build things that help, </s>

<s>[INST] everything changed. We're [/INST] gonna be in a different environment, different circumstances. And is Ukraine still as central at that point as it seems to be right now? I don't know the answer to that question. </s><s>[INST] Let me ask two rapid fire questions. You're only allowed to have one minute and it's about predicting the future? Okay, Question one, Vladimir Putin, when will he no longer be in office? And will he step down or be overthrown? What's your prediction and a brief explanation of that prediction. Now, nobody can predict the future. But what's your sense? Now, some people are saying the pressure is building, he's going to be overthrown or stepped down at the end of this year, as some people say, surely he's going to last outlast Stalin's rule of 30 plus years [/INST] no evidence of a coup yet, none whatsoever yet. Um, he's pretty much at life expectancy for a Russian male. Those are bad numbers. He's what, 69 gonna be 70. So he's lived the life of a Russian mail already. But he's got better doctors than the majority of the Russian males in that let's say comparison set. So he could live a very long time with good doctors. So there could be a coup at some point, but there's none today in evidence. He could go because he's reached the life expectancy or he could stay for a long time. The thing to watch about this is an organization that nobody pays attention to the Fso the federal nice grainy which is the Pretoria in guard, the self standing bodyguard directorate. The only one the only organization in Russia that has any access to him. We've seen no disloyalty, no breaking of ranks, no defections. Nothing in the public realm. And open source is about any divisions or problems in the Fso in the Pretoria In guard. So if you can't break that change that, huh, illicit defections there. You can't overturn </s><s>[INST] him. Authoritarian [/INST] regimes, lex they're terrible. They fail at everything. They know, they can't feed their people. They have trouble achieving any goals. They only have to be good. However, one thing, they only have to be good at the complete suppression of political alternatives. If you can suppress political alternatives, you can fail at everything else. But you can survive as an authoritarian regime. So, you watched Navalny, </s><s>[INST] that was that's [/INST] Question # two, That's My Question Number. </s><s>[INST] That's my the second rapid fire question is what happens to Navalny? What are the possible conclusions of what you said? Quite possibly the second most influential powerful figure in Russia? Uh, is there is he going to dying in in jail? Will he become the next president of Russia? Well, what are the possible, [/INST] I wish I knew lex I've been surprised that he's still alive. I've been worried that he will be killed in prison in a staged fight. You know, some security officer, Prison guard puts on a prison outfit, takes a lead pipe goes into the cell. They have a quote fight and Navalny is killed. I've been afraid of that, but he's still alive, even though he's serving a long sentence. So that leads me to guess that people inside the Putin regime and maybe President Putin himself, understand that Navalny is their ticket to lift sanctions. That Navalny is even more popular outside of Russia than he is inside of Russia. You know, he's the leader in many ways of the up political opposition in the country. Even while still in prison, his organization has been destroyed, but he doesn't have majority support in the population by any stretch of the imagination, but he's a big figure in the west, including here in the US. And so Navalny could be their ticket there kind of get out of jail card meaning they release him from prison. He gets appointed, I don't know, Prime Minister even by the Putin regime if he were willing to accept such a position and I have my doubts about that. And then that's how they lobby to remove the sanctions against them. So he's a card that President Putin could play. And so maybe that's the reason he's still alive or maybe there are other reasons that we don't know. And so uh, some alternative to Putin is more likely to arise inside his gang Putin sky shaker as they say right inside his gang where they tire of his mistakes, they tire of his self defeating actions and they say patriotic li for Russia, we need to do something against move against this guy because he's hurting our country and also because I could do better. I'm ambitious as well as patriotic. But once again the problem there lex is Putin is surrounded by this cocoon known as the fso he's he meets on zoom predominantly with the rest of the government, including with the defense and security officials. They don't have frequent access to his person. And as you were alluding earlier to the pandemic, they have to quarantine for two weeks before every meeting with him. And moreover, you know, lex, they don't know where he is. You see when they're on zoom with him and in the room, it's the valdai, his office in the valdai region looks the same as his office in Sochi or his office outside of Moscow and nova over there made up to look very similar on zoom and sure some signs they're looking where is it? Maybe they don't know. And so you're gonna move on him and you're gonna jump him in his Kremlin, his Dacha outside outside Moscow. And it turns out he's in Sochi or vice versa. And it turns out the fso is loyal to him and and won't let you anyway, so lex we don't know, but we watched this fso really closely and we think that the elites if not Putin, but maybe Putin to understand Navalny as a really big potential political card that they could play. </s>

<s>[INST] people are still playing chess and even go, [/INST] yeah, and I in this in the near term, even some people are advocating basic income, replace jobs, but if you if the government is going to be willing to just hand out cash to people for doing nothing, then one should also seriously consider whether the government should also hire a lot more teachers and nurses and the kind of jobs which people often find great fulfillment in doing right, we get very tired of hearing politicians saying, oh we can't afford hiring more teachers, but we're going to maybe have basic income if we can have more, more serious research and thought into what gives meaning to our lives and the jobs give so much more than income, right? And then think about in the future. one of the roles, Yeah. What are the roles that we want to, how people continually stealing empowered by machines? </s><s>[INST] And I think sort of um I come from the Russia, from the Soviet Union and um I think for a lot of people in the 20th century, going to the moon, going to space was an inspiring thing. I feel like the universe of the mind. So Ai understanding creating intelligence is that for the 21st century. So it's really surprising. And I've heard you mention this, it's really surprising to me both on the research funding side that it's not funded as greatly as it could be, but most importantly, on the politicians side that it's not part of the public discourse except in the killer bots terminator. Kind of view that people are not yet. I think perhaps excited by the possible positive future that we can build together. [/INST] So we should be because politicians usually just focus on the next election cycle, right? The single most important thing I feel we humans have learned in the entire history of science is there were the masters of underestimation, we underestimated the size of our cosmos again and again, realizing that everything we thought existed, there's just a small part of something grander, right? Planet, solar system, a galaxy, you know, clusters of Galaxies, universe and we now know that's we have, the future has just so much more potential than our ancestors could ever have dreamt of this cosmos. Imagine if all of earth was completely devoid of life except for Cambridge massachusetts. I would wouldn't it be kind of lame if all we ever aspired to was to stay in Cambridge massachusetts forever and then go extinct in one week. Even though earth was gonna continue on for longer than that, that sort of attitude. I think we have now on the cosmic scale we can life can flourish on earth, not for four years, but for billions of years. I can't even tell you about how to move it out of harm's way when the sun gets too hot and and then we have so much more resources out here which today maybe there are a lot of other planets with bacteria or cow like life on them. But most of this all this opportunity seems as far as we can tell to be largely dead, like the Sahara desert. And yet we have the opportunity that help life flourish without this billions of years. So like let's quit squabbling about when some little border should be drawn one mile to the left to right and look up the skies. You realize, hey, you know, we can do such incredible things. </s><s>[INST] Yeah. And that's I think why it's really exciting that yeah, you and others are connected with some of the working man mosque is doing because he's literally going out into that space, really exploring our universe. And it's wonderful. [/INST] That is exactly why Elon musk is so misunderstood, right? Misconstrue him as some kind of pessimistic dooms their, the reason he cares so much about AI safety is because he more than almost anyone else appreciates these amazing opportunities that will squander if we wipe out here on earth, we're not just going to wipe out the next generation for all generations. And this incredible opportunity that's out there and that would really be a waste an AI for people who think that they were better to do without technology. Well, let me just mention that if we don't improve our technology, the question isn't whether humanity is going to go extinct. Question is just whether we're gonna get taken out by the next big asteroid or the next super volcano or something else dumb, that we could easily prevent with more tech, right? And if we want life to flourish throughout the cosmos, aI is the key to it. Yeah. As I mentioned, a lot of detail in my book right there, even many of the most inspired sci fi writers, I feel have totally underestimated the opportunities for space travel, especially to other Galaxies, because they weren't thinking about the possibility of a G. I've, which just makes it so much easier, </s><s>[INST] Right? Yeah. So that that goes to your a view of a G. I. That enables our progress that enables a better life. So that's a beautiful that's a beautiful way to put it and something to strive for. So max. Thank you so much. Thank you for your time. Today has been awesome. [/INST] Thank you so much joy. </s>

<s>[INST] Whitten gets a pass on which aspect, [/INST] the stream theory? Yeah, that m theory is correct. I mean, here is, let me just, Hawking gets the ultimate pass. Hawking would say things like m theory, there's zero evidence for it. I mean, there's the famous meme that went around this weekend, like what a string theory predicted and it's nothing. And by the way, that's actually wrong. I talked toAKumRUN, I know you talked toAKumRUN. Colorin has that string theory does make predictions. It predicts the mass of the electron and lies between 10 to the minus one, Planck mass and 10 to the minus 30 Planck mass. </s><s>[INST] Okay, whatever, you know, our electro mass. [/INST] It's a big range. It's a huge range. Imagine Comrade comes up, and again, he's just some nobody, but he actually, he doesn't have a profile, he's not a Harvard, has zero H in an X or whatever Eric's is. Why do we not like, in other words, </s><s>[INST] why are we more harsh on people that are trying? You know the answer to that. So I get a million emails, just like you said, you yourself, where they provenize in my world this artificial intelligence, the equivalence of that, is I figured out how to build consciousness, how to engineer intelligence, how to, and sometimes- [/INST] You should send your emails to me, </s><s>[INST] and I'll send my emails to you. And we'll reply to you. I mean, and I don't want to sort of mock this, because I think it's very possible that there is either kernels of interesting ideas or in whole like, there is geniuses out there that are unheard, but because there's so much noise- [/INST] No, I'm not either. </s><s>[INST] Because I think you do have to weigh like, hire the Ed Wittens of the world when they make statements. And that's why you build up a track record, as you said with Ray Dalio, you have to show that you can like, if you're a Pollock and you show us a painting of a bunch of chaos, you have to, and this is a bad example, probably, because he probably never showed this proof. I think he could do it, right? Yeah, it's much more comforting to see that they can paint a good, accurate picture. Still life. Of still life, of an apple on the table. So there's- Meteorite at a time. Because then, I mean- [/INST] I think he could do it, right? </s><s>[INST] Meteorite at a time. Because then there's something about the scientific community that they have perhaps an oversensitive bullshit sensor to where they're not going to give the full effort of their attention if you don't have the track record. Now, you could say that's a kind of club that only, you have to like, you have to have 10, you have to have this, yes, that exists. But there's some aspect in which you have to play the game a little bit to get the machine of science going. Otherwise, if you're always saying, well, I have my ball and I don't wanna play your game, your game sucks, [/INST] then nobody's gonna wanna play with you. That's true in there. Look, inherent in all of this is an underlying grandiosity. Look, how could you talk about doing what Kaku said on here and elsewhere? We're looking for the umbilical cord that connects our universe to another universe that will then reveal in a one-inch equation that will surely win a Nobel Prize, </s><s>[INST] the mind of God, the universe. That's like a prerequisite, I guess, [/INST] to tackle these questions. I think it's detrimental. I think doing that, first of all, I think there's an element of almost snarkiness because none of these scientists are believing, you know, Gnostics, they're not theists, right? So they're using it as kind of a stand-in and they always talk about Einstein and he was like a Spinoza and he wasn't a theist. God doesn't play dice. God doesn't play dice. Yeah, Einstein's mentions of God, yeah. Yeah, and then Stephen Hawking says, if when we come, we get an M theory understood, we'll know the mind of God. That's the title of Kaku's book, The God Particle, The God Equation. You know, do any of them really believe in God? No, is that a prerequisite? No, I'm not saying that. But the point being, you're talking about something that has to do with God, right? I mean, where else do you go from there? I mean, I think God for now enjoys a little bit more, you know, kind of PR than Elon or Joe or whatever, right? So like, you know, God's got a pretty good, you know, H-index himself. </s><s>[INST] God doesn't play dice. God doesn't play dice. Yeah, Einstein's mentions of God, yeah. He has, by the way, a Twitter account, just so you know, it's pretty good. It's the tweets of God. [/INST] Yeah, that's sweet of God. Pretty good. It's the tweets of God. Yeah, that's sweet of God. So if you look at that, you have to go in there. Again, you have to go in with some swagger. You have to have a little bit of arrogance, but you should, I agree, mix with a little bit of humility. So he's doing something, he comes from outside of academia. Now, if he rails against, I'm talking about Eric, no. If he's just railing, oh, the system, and I'm not gonna publish because F that, and that's only created by greedy journals, I don't think he's doing himself any favors. On the other hand, if he's shopping it, if he's talking it, if he's willing to expose it to criticism and to even embrace people who may not have the purest intentions, perhaps, but in the sense of they're not arguing solely to get to the truth with a capital T, what they're trying to do is take down Eric. Hopefully those people aren't out there. But on the other hand, looking at what Eric does for other people, looking at the fact that he has courtesy, he will look at Wolfram, he will look at Lisi, who's one of his closest friends. I mean, he calls him his nemesis, right, right. </s>

<s>[INST] And then it was over, it was, the story was written. It was over, it was, the story was written. Yep. Let's, if it's okay, just zoom out to, you mentioned power and good power a few times. So if we can just even talk about it, your book is called Good Power, Leading Positive Change in Our Lives, Work and World. What is good power? [/INST] What's the essence of good power? So the essence of it would be doing something hard or meaningful, but in a positive way. I would also tell you, I hope one day I'm remembered for how I did things, not just for what I did. I think that could almost be more important, and I think it's a choice we can all make. So the essence to me of good power, if I had to contrast good to bad, let's say, would be that first off, you have to embrace and navigate tension. This is the world we live in. And by embracing tension, not running from it, you would bridge divides that unites people, not divides them. It's hard thing to do, but you can do it. You do it with respect, which is the opposite of fear. A lot of people think way to get things done is fear. And then the third thing would be, you gotta celebrate some progress versus perfection. Because I also think that's what stops a lot of things from happening. Because if you go for whatever your definition of perfect is, it's either polarization or paralyzation. I mean, something happens in there. Versus, no, no, no, I can, don't worry about getting to that actual exact end point. If I keep taking a step forward of progress, really tough stuff can get done. And so my view of that is like, honestly, I hope it can, I said it's like a memoir with purpose. I'm only doing it, it was a really hard thing for me to do because I don't actually talk about all these things. Then I had to, nobody cares about your scientific description of this. They want the stories in your life to bring it alive. So it's a memoir with purpose. And in the writing of it, it became the power of me, the power of we, and the power of us. The idea that you build a foundation when you're young. Mostly from my work life, the power of we, which says I kind of, in retrospect, could see five principles on how to really drive change that would be done in a good way. And then eventually you could scale that, the power really of us, which is what I'm doing about finding better jobs for more people now that I co-chair an organization called 110. So that essence of navigate tensions, do it respectfully, celebrate progress, and give me, indulge me one more minute, these sort of, again, it's retrospect that I didn't know this in the moment. I had to learn it, I learned it. I am blessed by a lot of people I worked with and around. But some of the principles, like the first one says if you're gonna do something, change something, do something, you've gotta be in service of something. Being in service of is really different than serving, super different. And, like I just had my knee replaced. And I interviewed all these doctors. You can tell the difference that the guy who's gonna do a surgery, hey, my surgery's fine. I really don't care whether you can walk and do the stuff you wanted to do again. because my surgery is fine. Your hardware is good. I actually had some trouble. And I had a doctor who was like, you know, this doesn't sound right. I'm coming to you. The surgery was fine. It was me that was reacting wrong to it. And he didn't care until I could walk again. Okay, there's a big difference in those two things. And it's true in any business you have. A waiter serves you food. Okay, he serves his food, he did his job. Or did he care he had a good time. So that thought to be in service of it took me a while to get that like to try to write it to get that across because I think it's like so fundamental. If people were really in service of something, you got to believe that if I fulfill your needs, at the end of the day, mine will be fulfilled. And that is that essence that makes it so different. And then the second part, second principle is about building belief, which is I got to hope you'll voluntarily believe in a new future or some alternate reality. And you will use your discretionary energy versus me ordering you, you'll get so much more done. Then the third change and endure, we kind of talked about that earlier, focus more on the how and the skills. And then the part on good tech and being resilient. So anyways, I just felt that, like good tech, everybody's a tech company, I don't care what you do today. And there's some fundamental things you got to do. In fact, pick up today's any newspaper, right? I mean, chat GPT, you're an AI guy. All right. I believe one of the tenets of good tech is it's like responsibility for the long term. It says, so if you're going to invent something, you better look at its upside and its downside. Like we did quantum computing. Great, a lot of great stuff, right? Materials development, risk management calculations, endless list one day. On the other side, it can break encryption. That's a bad thing. So we work equally hard on all the algorithms that would sustain quantum. I think with chat, okay, great. There's equal in there, people working on it, but like, okay, the things that say, Hey, I can tell this was written with that, right? Because the implications on how people learn, right? If this is not a great thing, if all it does is do your homework, that is not the idea of homework as someone who liked to study so hard, but anyways, you get my point. It's just the upside and the downside. </s>

<s>[INST] sound that it translates into his offensive confidence. When you talk about memory recall, which is interesting, I can't help but see parallels between him and Magnus Carlsen, who's a chess player, who's the number one in the world. The arguably the best ever, certainly the best ever if you just look at absolute numbers. The chess has the luxury of having a rating, which you cannot have in jiu-jitsu because it's a game of human chess. Chess is just a board game, so you can actually calculate the probability that you could win. So he is the highest ELO rating ever, and he's maintained that rating. Without competing against the number two in the world, he can just prove that he's the number one in the world for many years. Anyway, there's certain similarities. One's ability to recall. So memory recall of information is fascinatingly good. And the other one is not so much a love for perfection, which is something you mentioned, but the flip side of that, which is what you also mentioned, is the hate of imperfection. Now, in the case of Magnus, it almost creates a level of anxiety for him that's almost destructive. So the thing he seems to hate the most is imperfection against people he knows are worse than him. So the thing he loves is competing against people that are close to skill level. Or the favorite is people who are, might actually be better than him, especially in certain positions. He loves competing against them. He hates competing against people that are still from the perspective of everyone else. what are called super grandmasters, so top three in the world. But he knows he's much better than them. And the anxiety of being not perfect against those people, that's why he, I don't know if you're paying attention, but he stepped away. He's not going to defend his world championship because he hates the anxiety of playing people worse than him. [/INST] Interesting. </s><s>[INST] He figures they would somehow make him look bad or? No, he just, for him, at least the language he uses, it's just not fun. And he likes having fun. To him, it was fun to win no matter the skill level, the world championship the first time. But then defending it is a very grueling process. With classical chess, you play these many hour, it could be seven hour long games. And on top of that, he really hates the fact that it's only, I forget what it is, but it's single digit number of games. He says it's low sample. So I can't, I would like to play 20, 30, 40, 50 games if we're going to do it this way. But then they're too long, it's going to take too long. So he's really emphasizes the fun of it and the clear demonstration of who's the best. Now chess is an interesting game. It's probably different than grappling because it's been played for centuries. So there's this giant body of people that are playing it. Like there's other Gordon Ryans out there. Imagine a world where there's multiple Gordon Ryans or something like that, just different dimensions, but you have like sharks everywhere. And so there is fun to be had even at the very, very, very, very top. But the memory recall is the thing that stands out and the hate of imperfection more intense than anybody else in the game. Fascinating, fascinating. That takes us back to the final. Yes. So here Gordon is facing Nicky Rod, former training partner. [/INST] And again, the intention here is this has to be put in the context that Gordon will be fighting the greatest ACC grappler of all time in a few hours after this. So what we're looking for is a quick resolution. Still the shortest possible match. Now there's a complicating factor here. Nicky Rod was a wrestler before he was a jiu-jitsu player. On paper, the way his route to win is via wrestling. He's not gonna be able to submit Gordon Ryan and he's not gonna be able to pass his guard. So he has to win by wrestling. In the ADCC finals, you cannot set the guard. So the approach that Gordon used earlier that we saw on video cannot be used in the finals. Gordon must wrestle his opponent. So on the way out, Gordon and I were talking and we'd had discussions obviously during the cam what's the appropriate thing to do here. And there had been some matches earlier in the event where it was becoming obvious that stalling was being heavily punished by referees. So I said to Gordon on the way out, just give him your leg, let him take you down because in the first 10 minutes of the finals, takedowns don't score anything. There are no means of scoring the first 10 minutes but you can't set the guard. That will award you a negative point. So I said, just let Nicky Rod take you down. And he's like, Nicky Rod's not gonna take the bait. </s><s>[INST] And I said, if he doesn't, they'll call him for stalling. And so. And then Craig Jones also commented after the fact is I don't know why Nicky Rod took the bait. [/INST] So if we see the start of the match, you see Gordon comes out and offers a leg. Now, it's not that Nicky Rod is smart. He knows what's happening here. And what's he gonna do, stall for 10 minutes and get like five stalling calls put against him. So Gordon gives him the takedown. That way they go to the ground immediately with no effort. And the match now favors Gordon because Gordon is significantly more skilled on the ground. The question is how can we make this match as short as possible? </s>

<s>[INST] Books and ideas perhaps outside of computer science and the technical fields? [/INST] I think because I'm spending a lot of my time at MIT and previously in other institutions where I was a student, I have limited ability to interact with people. So a lot of what I know about the world actually comes from books ah and there were quite a number of books that had a profound impact on me and how I view the world. Let me just give you one example of such a book. I've um maybe a year ago read a book called the Emperor of all maladies. It's a book about it's kind of a history of science book on how the treatments and drugs for cancer were developed. And that book, despite the fact that I am in the business of science really opened my eyes on the home, imprecise and imperfect the discovery process is and how imperfect our current solutions ah and what makes science succeed and be implemented. And sometimes it's actually not the strength of the idea but devotion of the person who wants to see it implemented. So this is one of the books that you know at least for the last year quite changed the way I'm thinking about scientific process just from the historical perspective and what do I need to do to make my ideas really implemented. Let me give you an example of a book which is not a kind of which is a fiction book is a book called Americana and this is a book about a young female student who comes from africa to study in the United States and it describes he'll pass you know within her studies and her life transformation that you know in a new country and kind of adaptation to a new culture. And when I read this book I saw myself in many different points of it. But it also kind of gave me the lands on different events and some of them that I never actually paid attention when the funny stories in this book is how she arrived to new college and she starts speaking in english. And she had this beautiful british up accent because that's how she was educated in her country. Uh this is not my case and then she notices that the person who talks to her you know talk to her in a very funny way, in a very slow way and she's thinking that this woman is disabled and and she's also trying to get enough to accommodate her. And then after a while when she finishes her discussion with this officer from her college, she sees how she interacts with the other students with american students. And she discovers that actually uh she talked to her this way because she saw that she doesn't understand english and uh he said wow this is a fun experience. And literally within a few weeks I went to L. A. To a conference and I asked somebody in in the airport you know how to find like a cab or something. And then I noticed that this person is talking in a very strange way and my first thought was that this person have some you know, pronunciation issues or something and I'm trying to talk very slowly to human language with another professor Aaron frankel and he's like laughing because it's funny that I don't get that the guy's talking in this way because he said that I cannot speak. So it was really kind of mirroring experience. And it let me think a lot about my own experiences moving you know from different countries. So I think that books play a big role in my understanding of the world, </s><s>[INST] on the on the science question. You mentioned that it made you discover that personalities of human beings are more important than perhaps ideas. Is that what I heard? [/INST] It's not necessarily that they are more important than ideas, but I think that ideas on their own are not sufficient and many times at least in the local horizon is the personalities and their devotion to their ideas is really that locally changes the landscape. Now if you're looking at a I like, let's say 30 years ago, dark ages of Ai or whatever what the symbolic times you can use any word. You know, there were some people now we're looking at a lot of that work and we're kind of thinking this is not really maybe a relevant work, but you can see that some people managed to take it and to make it so shiny and dominate the, you know, the academic wall and make it to be the standards. If you look at the area of natural language processing it is well known fact. And the reason the statistics in NLP took such a long time to became to become mainstream because there were quite a number of personalities which didn't believe in this idea and then stop research progress in this area. So I do not think that you know kind of as sympathetically maybe personalities matters but I think locally it does make quite a bit of impact and </s><s>[INST] it's [/INST] generally, you know, speed up speeds up the rate of adoption of the new ideas. </s><s>[INST] Yeah. And uh and the other interesting question is in the early days of particular discipline, I think you mentioned in that book was his ultimate book of cancer. [/INST] It's called the Emperor of all maladies. </s><s>[INST] Yeah, they and those melodies included. They're trying to the medicine was that center around. [/INST] So it was actually centered on, you know how people thought of Cuban council like like for me it was really a discovery how people, what was the science of chemistry behind drug development that it actually grew up out of that dying like coloring industry that people who develop chemistry In 19th century in Germany and Britain to do you know the really new dice. Uh they looked at the molecular and identified that they do certain things to cells and from there the process started and you know like historical. Yeah. This is fascinating that they managed to make the connection and look under the microscope and do all this discovery. But as you continue reading about it and you read about how chemotherapy drugs socially developed in boston and uh some of them were developed and um um Farber dr farmer from dana Farber, you know how the experiments were done that, you know, there was some miscalculation, let's put it this way and they tried it on the patients and then just and those were Children with leukemia and they died and they tried another modification. You look at the process, how imperfect is this process. And you know, like if we're again looking back like six years ago, 70 years ago, you can kind of understand it. But some of the stories in this book which were really shocking to me, were really happening, you know, maybe decades ago and we still don't have a vehicle to do it much more fast and effective and you know scientific the way and taking computer science scientific. </s>

<s>[INST] concept. So [/INST] that's the kind of reason why it figures out the guitar thing, right? It will observe the same sound across multiple different videos and it figures out maybe this is the common factor that's actually doing it. </s><s>[INST] I wonder I used to have this argument with my dad a bunch for creating general intelligence. Whether smell is an important uh like if that's important sense of information, mostly we're talking about like falling in love with the Ai system and for for him, smell and touch are important and I was arguing that it's not at all, it's important, nice and everything, but like you can fall in love with just language really, but voice is very powerful and vision is next and smell is not that important. Can I ask you about this process of active learning? You mentioned interactivity. Alright. Is there some value within the self supervised learning context? To select parts of the data in intelligent ways, such that they would most benefit the learning process. [/INST] So I think so, I think, I mean I I know I'm talking to an active learning fan here of course. I think first </s><s>[INST] you were talking bananas and now you're talking about active learning. I love [/INST] it. I think </s><s>[INST] Yonah Cohen told me the active learning is not that interesting. I I think back back then, I didn't want to argue with him too much, but when we talk again that we're gonna spend three hours arguing about active learning, my sense was you can go extremely far with active learning, you know, perhaps farther than anything else. Like the to me there's this kind of intuition that similar to data augmentation, you can get a lot from the data, from intelligent optimized usage of the data. I'm trying to speak generally in such a way that includes data augmentation and active learning. That there's something about maybe interactive exploration of the data that um at least this part of the solution to intelligence, like an important part, I don't know what your thoughts are on active learning in general. [/INST] I actually really like active learning. So back in the day we did this largely ignored CpR paper called Learning by asking questions. So the idea was basically retain an agent that would ask a question about the image. It would get an answer and basically then it would update itself, it would see the next image, it would decide what's the next hardest question that I can ask to learn the most. And the idea was basically because it was being smart about the kinds of questions that was asking, it would learn in fewer samples, it would be more efficient at using data. And we did find to some extent that it was actually better than randomly asking questions. Kind of weird thing about active learning is it's also a chicken and egg problem because when you look at an image to ask a good question about the image, you need to understand something about the image. You can't ask a completely arbitrary random question. It may not even apply to that particular image. So there is some amount of understanding or knowledge that basically keeps getting built when you're doing active learning. So I think after learning and by itself is really good and the main thing we need to figure out is basically how do we come up with a technique to first model what the model nose and also model what the model does not know. I think that's the sort of beauty of it, right? Because when you know that there are certain things that you don't know anything about asking a question about those concepts actually going to bring you the most value. And I think that's the sort of key challenge. Self supervised learning by itself, like selecting data for it and so on. that's actually really useful. But I think that's a very narrow view of looking at active learning, right? If you look at it more broadly, it is basically about if the model has a knowledge about end concepts and it is weak basically about certain things. So it needs to ask questions either to discover new concepts or to basically like increase its knowledge about these end concepts. But that level, it's a very powerful technique. I actually do think it's going to be really useful even in like simple things such as like data labeling. It's super useful. So there is like one simple way that you can use active learning for example, you have yourself supervised model which is very good at predicting similarities and dissimilarities between things. And so if you label a picture as basically say a banana, uh now, you know that all the images that are very similar to this image are also likely to contain bananas. So probably when you want to understand what else is a banana, you're not going to use these other images. You're actually going to use an image that is not completely dissimilar but somewhere in between which is not super similar to this image but not super dissimilar either. And that's going to tell you a lot more about what this concept of a banana </s><s>[INST] is. So that that's kind of a heuristic. I wonder if it's possible to also learn learn ways to discover the most likely the most beneficial image? So like, so not just looking a thing that's um, somewhat similar to a banana, but not exactly similar, but have some kind of more complicated learning system, like learned discovery mechanism uh, that tells you what what images look for, like how I yeah, like actually in a self supervised way, learning strictly a function that says, is this image going to be very useful to me, given what I currently no, [/INST] I think there's a lot of synergy there. It's just, I think it's going to be explored. </s>

<s>[INST] Is there something that we could say in by way of advice for when this episode is released in a chaos of emotion side and all better term that's just flying around on social media. What's uh [/INST] well, actually, I think it is it is a motion in the following sense, you know, and it sounds a little bit like it sounds a little bit like artificial when I in the way I'm about to say it, but I really think that this is what's happening. You know, one thing we haven't talked about is, you know, brains evolved didn't evolve for you to see they didn't evolve for you to hear they didn't evolve for you to feel they evolved to control your body. That's why you have a brain, you have a brain so they can crawl your body. And the metaphor, the there's a scientific term for predictably controlling your body is a lost Asus your brain is making um is attempting to it's tempting to anticipate the needs of your body and meet those needs before they arise so that you can act as you need to act. And the metaphor that I use as a body budget, you know, your brain is running a budget for your body, it's not budgeting money, it's budgeting glucose and salt and water and instead of having you know one or two bank accounts, it has gazillions, there are all these systems in your body that have to be kept in balance and it's monitoring very closely. It's making predictions about like when is it good to spend and when is it good to save and what would be a good investment? And am I going to get a return on my investment? Whenever people talk about reward or reward prediction error or anything to do with reward or punishment, they're talking about the body budget, They're talking about your brain's predictions about whether or not there will be a deposit or withdrawal. So when you when your brain is running a deficit in your body budgets, you have some kind of metabolic imbalance. You experience that as discomfort. You experience that as distress when your brain, when things are chaotic, you can't predict what's going to happen next. So I have this absolutely brilliant scientist working in my lab. His name is um Jourdan Theriot and he's published is really terrific paper on um a sense of should like why do we have social rules? Why do we um you know uh Adhere to social norms? It's because if I make myself predictable to you, then you are predictable to me. And if you're predictable to me, that's good because that that is less metabolically expensive for me, novelty or unpredictability at the extreme is expensive. And if it goes on for long enough, what happens is, first of all, you will feel really jittery and antsy, which we describe as anxiety, it isn't necessarily anxiety, it could be just Mhm. Something is not predictable and you are experiencing arousal because the chemicals that help you learn increase your feeling of arousal basically. But if it goes on for long enough, you will become depleted and you will start to feel really, really, really distressed. So what we have is a culture full of people right now who are their body budgets are just decimated. Yeah. And there's a tremendous amount of uncertainty when you talk about it as depression, anxiety. It makes you think that it's not about your metabolism, that it's not about your body budgeting, that it's not about getting enough sleep, or about eating well, or about making sure that you have social connections. Um It's, you know, you think that it's something separate from that. But depression anxiety are just a way of being in the world. They're a way of being in the world when things aren't quite right with your predictions, </s><s>[INST] It's such a deep way of thinking. Like, the brain is uh maintaining homeostasis [/INST] is actually a state </s><s>[INST] of stasis, I'm sorry. Uh and it's constantly making predictions and metabolically speaking, it's very costly to make novel, like constantly be learning to making adjustments. And then over time there's, you know, there's uh cost to be paid uh if you're just Yeah, in in a place of chaos, where there's constant need for adjusting and learning and experience novel things. [/INST] And so part of the problem here, there are a couple of things that I said, you know, it's a perfect storm. There isn't a single cause, there are multiple cause multiple things that combine together. It's a complex, it's a complex system, Multiple things. Part of it is that um people are, they're they're metabolically encumbered and they're distressed and in order to try to have empathy for someone who is very much unlike you, you have to forage for information, you have to explore information that is novel to you and unexpected, and that's expensive and at a time when people feel, What do you do when you are running a deficit in your bank account, you stop spending, what does it mean for a brain to stop spending? A brain stops moving. Very much stops moving the body and it stops learning, it just goes with its internal model brilliantly </s><s>[INST] put, yep. [/INST] So empathy requires to have empathy for someone who is unlike you. Yeah, requires learning and practice foraging for information. I mean, it is something I talk about in my in the book, in 7.5 lessons about the brain. I think it's really important. It's hard but it's hard, I think it's, you know, it's hard for people to have to be curious about views that are unlike their own um when, when they feel so encumbered and I'll just tell you I had this epiphany really, um I was listening to robert Reich's um the system, he was talking about oligarchy versus democracy. So oligarchies where very wealthy people like extremely wealthy people um shift power so that they become even more wealthy and even more insulated and from the, you know, the pressures of the common person, um it's actually the kind of system that leads to the collapse of civilizations if you believe Jared diamond just say that. But anyways, I'm listening to this and I'm listening to him describe in fairly decent detail how The ceos of these companies uh there's been a shift in what it means to be a ceo and not not being no longer being a steward of the community and so on, but like in the 1980s that sort of shifted to this other model of being like an oligarch. And he's talking about how, you know, it used to be the case that um that Ceos uh, Made like 20 times what their um Their employees made and now they make about 300 times on average whether employees made. So where did that money come from? It came from the pockets of the employees? And they don't, they don't know about it, right, No one knows about it. They just know they can't feed their Children, they can't pay for health care, they can't take care of their family and they worry about what's going to happen to their, you know, their living like, you know, months a month, basically. Anyone big bill could completely, you know, put them out on the street. So there are a huge number of people living like this. So all they what their experience, they don't know why they're experiencing it. So it's, and then someone comes along and gives them a narrative. Well, somebody else butted in line in front of you and that's why you're this way, that's why you experience what you're experiencing just for a minute. I was thinking, I had deep empathy for people who have beliefs that are really, really, really different from mine, but I was trying really hard to see it through their eyes. And did it cost me something metabolically? I'm sure, I'm sure. </s>

<s>[INST] yourself [/INST] because </s><s>[INST] I am 34 [/INST] 100 take the pawn and be like I win </s><s>[INST] it back [/INST] and even if you did you would suffer. It would make you win it back in the most annoying way. It would make you tie your shoes together and </s><s>[INST] but [/INST] not at 99% of the </s><s>[INST] rating ladder which is [/INST] funny, </s><s>[INST] interesting. Um But you like to play this, I [/INST] play this against G. M. I play both, I move my bishop, I </s><s>[INST] pushed it and what are the different ways that evolves like then the rest doesn't matter. So this is just like a pawn structure thing. [/INST] Yeah and I mean deeper </s><s>[INST] most openings [/INST] so </s><s>[INST] It's anywhere from like two moves to like 10 moves kind of thing. [/INST] Yeah you can be out of theory very very quickly to move to move three like basically on your own. You have a general idea but you don't remember games. I mean I I no carro con games from start to finish </s><s>[INST] because I've played it [/INST] since 2011. </s><s>[INST] So you know all the different branches that goes with that down. [/INST] Yeah I think I know every opening in chess basically. I think most most titled players know every opening but we don't know we can't play it competitively because we would be but what </s><s>[INST] are some of the weirder openings that like slightly suboptimal but might be explored like Magnus might play them just to funk with the [/INST] opponent. He played something recently actually against this german prodigy Vincent timer, which was a specific move order in a very popular opening. So it's basically a position had been reached thousands of times, but the move order magnus chose with white was played maybe point oh 5% of the time, which is crazy, thousands of games and it's supposed to be not good, meaning it allows black to equalize because that's what black is going for, not winning the game, but equalizing because you go second, that says, I don't care about equalizing, I just wanna position, I don't want my opponent to know the answers to the test. And </s><s>[INST] that's so interesting because also fox you psychologically it throws you off and just always keep you on your toes. He's in a weird position, but he also has the advantage of being able to intimidate. I wonder how many people um [/INST] how </s><s>[INST] much is that? A roll of it? Like being scared of the other person [/INST] was huge. I think I think some of the top guys would deny it, but you know when you're in the seventh hour and you're playing magnus? It's a very different feeling than some of the other when magnus is messing around in the opening. It's very different than another person messing around in the opening. You just kind of like expect to for something to be there. Um we'll see if it translates to poker for him, but I think he got, he gets a little bit maybe less respect in the poker world, in the chess world, he sort of gets a lot of respect. </s><s>[INST] I just talked to Danielle on the ground and he gets, gets [/INST] the only </s><s>[INST] person that doesn't respect magnus Carlsen. Honestly, either in chess or poker is magnus Carlsen, [/INST] that's </s><s>[INST] true, but like this is hilarious. I mean when he talks about his rating is like, that's pretty good when he talks about how good he is, this poker and I suck. But you know, I think that's self critical view that he, I think he honestly believes uh to a degree is probably part of the, the, the engine that fuels them to get better and better and better and better. Yeah. [/INST] Well, what I'm saying is if you, if you're face to face with magnitude of chess board, it's not the same as being a nine handed poker table with him, you kind of keep an eye on him maybe and, and then he's a mysterious guy, but chess is different because you're like, this is the man, </s><s>[INST] Yeah, there's very few people, Yeah, so in, in poker they talk about Phil Ivey that [/INST] way. It's </s><s>[INST] like the super intimidating. I think that's, that's, it's [/INST] probably harder </s><s>[INST] to intimidate in poker actually. I don't know, I don't know, there's something intimidating about like excellence in a deterministic game. That's just terrifying. Like your, I mean it's like playing stock fish like you're fucked. This thing will suffocate [/INST] you </s><s>[INST] and especially when you makes moves that you don't understand this to me. The most beautiful thing honestly is the sacrifices that the, the engines do just the, it's such a funk. You like, I could sacrifice pieces and I'll get them back and I'll get them back more and I [/INST] don't even, I don't even have to get them back. Your position is so bad. I give you full material and there's nothing you can do about it. Yeah. </s><s>[INST] That's terrifying. [/INST] Yeah, that's </s><s>[INST] terrifying. That's like that transfers to Ai systems in general, like, like a system that plays weak just to fool you for [/INST] people </s><s>[INST] who are trying to get better at chess beginners or at any stage of their development. What, what advice would you give about? Getting better? Except watch [/INST] of course, Watch my videos, check out dot com. That's, we're gonna scale the courses too. Uh, but no, on a serious note, you have to be prepared to lose way more than win. My mom gave me advice when I was Maybe 13 or 14 and I just discovered that I liked girls. She said you're gonna get a lot more nose in life than yes. Uh that even happened with, with my wife actually, our whole journey is, is quite, quite fascinating </s><s>[INST] is paved with rejection [/INST] paved with, yes, various ghost things over the course of years, but we got married and we love each other very much so. Um, it's a, it's a, it's a wonderful tale, but it's the, it's the same in chest. You're gonna lose a lot and you have to be for adults. I noticed kids and adults learn chess very differently. Kids yell out in class and they're very excited and they don't realize how many times they get something wrong. Adults never wanna talk during lessons because they're afraid of being wrong. Adults will preface correct answers with, this is probably wrong, but like shut up, you're paying for a, for a private lesson. This is the place to be wrong, you know? So adults especially think that being dominant in a career where they've dedicated a lot of their brain power and a lot of their work ethic and a lot of their study time, it's gonna translate to chest. They do their own kids, the helicopter, their own kids because they try to apply a lot of the same stuff chest studying chest is different than studying anything else. Anything else. Same could be argued for martial arts I guess. But yeah, </s>

<s>[INST] think uh you you seriously concerned about this kind of thing where the ideas of sovereignty and that Bitcoin espouses would would actually one day be tested. Do you have like a legitimate concern because you said like one day very well might. Do you think it might [/INST] Yeah. Well, first of all, Bitcoin has been attacked again many times and we talk about the, you spoke about this with nick carter on your show, the sort of protocol wars or conflict or whatever. Right? And they almost died a whole bunch of times during that and ended up surviving. </s><s>[INST] Oh wow, I didn't, I didn't know how bad [/INST] it got it was, it was sort of a very existential threat and the queen survived and that's why I am so intrigued by it is that it basically survived an attack in an environment several years ago when Bitcoin was much more vulnerable than it is today. Um It survived an attack by a conglomeration of chinese billionaires, Silicon valley corporations and a ton of people who owned the majority of the hash rate and all this infrastructure, </s><s>[INST] They had 83 [/INST] percent of all the hash rate and they couldn't get what they wanted. And that was so intriguing to me. Like why didn't why didn't get killed? So as Nick said, I think you should read the block size war which is a book that you can get on amazon by Jonathan beer. Really good kind of like really important to understand the scaling conflict and the visions over the different visions of what the coin should be and you know, again, people like me believe it should be a freedom tool, not like a payments technology for retail and I'm just I'm glad it worked out the way it did because it almost didn't. </s><s>[INST] Do you think humans civilization will destroy itself? So if we think about all the threats facing human civilization, nuclear war, natural or engineer pandemics, You know, we talk about human rights violations, we talk about, uh, authoritarian governments, uh, taking control of the money supply. But do you have a great grander concerns for the future of human civilization? Do you have hope for us becoming multi planetary species? [/INST] Yeah, I mean, I guess long term we want to decentralize, right? We don't want a single point of failure in the earth is a single point of failure. Um, but no, I mean, you look at all this kind of like space fiction and I mean, who would want to live on mars man? It's like a freaking desert. I mean, the earth is so beautiful. I hope we can save it. You know, it's just so gorgeous when you look at the earth compared to any other like exoplanet or whatever you look at it. I mean, the earth is so spectacular and wondrous and singular. I think we've got to do everything we can to save it here. </s><s>[INST] That's funny. I mean, I uh, sure a lot of people would have said that about europe before the explorers ventured out columbus and the rest into the unknown. The thing about human nature is that we are explorers to some small fraction of us are insane enough to exploring the most dangerous grounds. And I'm pretty sure there's quite a few people that would love to take the first step on mars the first few steps on MArs in the harshest of environments, even when the odds of survival extremely low. And I'm thankful for those people because I sit back and drink my vodka back here on earth and enjoy [/INST] good friendships because </s><s>[INST] I think ultimately that step to MArs is going to be a first step into a multi into uh exploring and colonizing the rest of the galaxy. Mars might be a harsh environment, but maybe space is not uh, like uh other planets, other exoplanets, but also forget planets, just creating colonies that float about in space. Um, there's exciting technologies that are yet to be discovered yet to be engineered and built that I think require that first painful step. Like uh yeah, the journey of 1000 miles starts with one step. I think MArs is that first step. [/INST] Yeah, No, I was born the day before the challenger blew up. And it was always so tragic for me to look back on that because that really like altered our arc in terms of space exploration. Like that had not happened, we'd be in a very different arc and I do respect and admire people pushing for exploration, but at the same time, I just want to recognize like we just, you know, we know how unique earth is and I do think we got to do everything we can to to protect them. </s><s>[INST] But I think you have would answer the question if we're going to destroy ourselves, [/INST] I guess? Yeah. Yeah. I guess you do not Okay fine. If we do not decentralize properly out into different physical space is probably I guess. Yeah. </s><s>[INST] And I mean, do you have concerns that are immediately facing you? So um not in terms of the injustices on the world, but nuclear [/INST] war? Look, I'm a lot more concerned about what's happening right now. Like what is destroying ourselves? If you were to go and see what's happening in Xinjiang or North Korea right now or Eritrea that is destroying ourselves and it's already happened. So I guess the end, that's why I said yes, I mean if you don't decentralize and powers completely under one person, um life is destroyed as we know it. And you know, you don't have to go into science fiction to know what a totalitarian hellscape dystopia is. There's several that exists already. And you know, let's try to help those people at the same time as we're trying to like push out into space would be my leg counter I guess. </s>

<s>[INST] just teenagers [/INST] tina. I mean it'll be clean. It'll be adults. Um, there's actually an age demographic that's optimal for technology adoption. Um, and you can actually find them and they're actually pretty easy to find just based on their habits based on. Um, so someone like me who wouldn't wasn't a roboticist would probably be the optimal kind of person, right? Early adopter, okay with technology very comfortable and not hypersensitive, right? I'm just hypersensitive because I designed this stuff so there is a target demographic that will swing. The other one though is you still have these humans that are on the road, that one is a harder, harder thing to do um and as long as we have people that are on the same streets, that's going to be the big issue. Um and it's just because you can't possibly want you can't possibly map the some of the silliness of human drivers, right? Like as an example when you're next to that car that has that big sticker called student driver, right? Like you're like, oh either I am going to like go around like we are, we know that that person is just gonna make mistakes, that make no sense, right? How do you map that information? Um or if I am in a car and I look over and I see you know, to fairly young looking individuals and there's no student driver bumper and I see them chit chatting to each other, I'm like oh that's an issue, right, so how do you get that kind of information and that experience? And two uh basically an autopilot </s><s>[INST] and there's millions of cases like that where we take little hints to establish context, I mean you said kind of beautifully poetic human things, but there's probably subtle things about the environment about is about it being maybe um, time for commuters start going home from work and therefore you can make some kind of judgment about the group behavior of pedestrians, [/INST] blah blah blah and so on Are even cities right? Like um if you're in boston, how people cross the street like lights are not an issue versus other places where people will, will actually wait for the crosswalk </s><s>[INST] Seattle or somewhere peaceful and, but what I've also seen just even in boston, that intersection to intersection is different. So every intersection is a personality of its own. So that certain neighborhoods of boston are different. So we kind of uh, and based on different timing of day at night, It's all it's all there's a, there's a dynamic to human behavior that we kind of figure out ourselves. We're not be able to, we're not able to introspect and figure it out, but somehow we are brain learns it [/INST] do. </s><s>[INST] And so you're, you're saying is there [/INST] a shortcut </s><s>[INST] is there a shortcut though for or is there something that could be done? You think that you know that's what we humans do? It's just like bird flight, right this example they give for flight. Do you necessarily need to build a bird that flies or can you do an airplane? So [/INST] I think that the shortcut is and I kind of uh I talk about it as a fixed space. Um where so imagine that there is a neighborhood that's a new smart city are a new neighborhood that says, you know what? We're going to design this new city based on supporting self driving cars and then doing things knowing that there's anomalies knowing that people are like this, right? And designing it based on that assumption that like we're going to have this, that would be an example of a shortcut. So you still have people, but you do very specific things to try to minimize the noise a little bit. Um, as an example </s><s>[INST] and the people themselves become accepting of the notion that there's a thomas cars, right? [/INST] Right? Like they move into. So right now you have like a, you will have a self selection bias, right? Like individuals will move into this neighborhood knowing like this is part of like the real estate pitch, right? Um and so I think that's the way to do a shortcut when it allows you to deploy, it allows you to collect then data with these variances and anomalies because people are still people, but it's um, it's a safer space and it's more of an accepting space. I. E. When something in that space might happen because things do because you already have the self selection like people would be, I think a little more forgiving than other places. </s><s>[INST] You said three things that we cover all of them. [/INST] The third is legal law liability, which I don't really want to touch. But it's still it's still of concern. </s>

<s>[INST] bad. That's actually on a psychological level. One of the fundamental benefits of effective altruism is is uh I mean I guess it's the altruism part of effective altruism is exposing yourself to the suffering in the world allows you to be more yeah, happier and actually allows you in sort of meditative introspective way. I realized that you don't need most of the wealth you have to to be happy. [/INST] Absolutely. I mean, I think effect has been this huge benefit for me and I really don't think that if I had more money that I was living on that, that would change my level of well being at all. Whereas engaging in something that I think is meaningful, that I think of stealing humanity in a positive direction that's extremely rewarding. Um and so yeah, I mean, despite my best attempts to sacrifice, um you know, I think I've actually ended up happier as a result of engaging in effective altruism than I would have done. </s><s>[INST] This is an interesting idea. So let's let's talk about animal welfare? Sure, easy question, what is consciousness [/INST] especially </s><s>[INST] as it has to do with the capacity to suffer. I think there seems to be a connection between how conscious something is the amount of consciousness and its ability to suffer and that all comes into play a bus us thinking how much suffering there is in the world with regard to animals. So how do you think about animal welfare and consciousness? [/INST] Okay well consciousness. Easy question. Yeah. I mean I think we don't have a good understanding of consciousness. My best guess is it's got and by consciousness I'm meaning what it feels like to be you the subjective experience that seems to be different from everything else we know about in the world. Yeah. I think it's clear it's very poorly understood at the moment. I think it has something to do with information processing. So the fact that the brain is a computer or something like a computer. So that would mean that very advanced ai could be conscious um information processes in general could be conscious with some suitable complexity </s><s>[INST] but that also some suitable complexity. It's a question whether greater complexity creates some kind of greater consciousness which relates to animals. Right. Is there if it's an information processing system and it's smaller and smaller is an ant less conscious than a cow, less conscious than a monkey. [/INST] Again, this super hard question. But I think my best guess is yes. Like if you if I think well consciousness it's not some magical thing that appears out of nowhere. It's not you know, day car thought it was just comes in from this other realm and then enters through the pineal gland in your brain and that's kind of soul and it's conscious. Um, so it's got something to do with what's going on in your brain. Um uh, A chicken has won 300th of the size of the brain that you have ants. I don't know how small it is. Maybe it's a millionth the size. My best guess, which I may well be wrong about because this is so hard. Is that in some relevant sense, the chicken is Um experiencing consciousness to a lesser degree than the human and the ants significantly less. Again, I don't think it's as little as 300th as much. I think there's evolutionary reasons for thinking that like the ability to feel pain comes on the scene relatively early on and we have lots of our brain that's dedicated stuff that doesn't seem to have to do anything to do with consciousness. Language processing, and so on. So </s><s>[INST] it seems like the easy, So there's a lot of complicated questions there that we can't ask the animals about. But it seems that there is easy questions in terms of suffering, which is things like factory farming that could be addressed. [/INST] Yeah. </s><s>[INST] Is that, is that the lowest hanging fruit, if I may use crude terms here, of animal welfare. [/INST] Absolute. I think that's the lowest hanging fruit. So at the moment we kill with ease and kill about 50 billion animals every year. How many? 50 billion? Uh, yeah, so for every human on the planet, um, several times that number are being killed and the vast majority of them are raised in factory farms where basically, whatever your view on animals, I think you should agree. Even if you think, well, maybe it's not bad to kill an animal, Maybe if the animals these good conditions, that's just not the empirical reality. The empirical reality is that they are kept an incredible cage confinement. They're de beaked or detailed without uh, an aesthetic, you know, chickens often pack each other to death um, like otherwise because they're in such less, uh, it's really, you know, I think when a chicken gets killed, that's the best thing that happened to the chicken um, in the course of its life and it's also completely unnecessary. This is in order to save, you know, a few pence for the place of meat or place of eggs. And we have indeed found it's also just inconsistent with consumer preference as well. People who buy the products if they could, they, they, when you do surveys are extremely against suffering in factory farms, it's just, they don't appreciate how bad it is. And, you know, just tend to go with easy options. And so then the best, the most effective programs I know of at the moment are non profits that go to companies and work with companies to get them to take a pledge to cut um certain sorts of animal products like eggs from cage confinement out of their supply chain. And it's now the case that the top 50 food retailers and fast food um companies have all made these kind of cage for the pledges. And when you do the numbers, you get the conclusion that every dollar you're giving to these nonprofits result in hundreds of chickens being spared from cage confinement and then they're working to other um other types of animals, other products too. </s>

<s>[INST] when I was a google that's what we worked on is and there's a lot of ways to call it active authentication, passive authentication. So basically used biometric data not just like a fingerprint but everything from your body to identify who you are. like movement patterns. So basically create a lot of layers of protection where it's very difficult to fake, including um like face unlock, checking that it's your actual face, like the Liveness tests. So like from video, so unlocking it with [/INST] video, </s><s>[INST] voice, the way you move the phone, um the way you take it out of the pocket, that kind of thing. All of those factors. It's a really hard problem [/INST] though, </s><s>[INST] and ultimately it's very difficult to beat the password. Different security. [/INST] Well, there's a company that I actually will call out and that's abnormal security. So they work on email attacks and it was started by a couple of guys who were doing I think ad tech at twitter, so, you know, add technology now, like it's a joke how much they know about us. You know, you always hear the conspiracy theories that, you know, you saw someone's shoes and next thing, you know, it's on your phone, it's amazing what they know about you and they're basically taking that and they're applying it to attacks. So they're saying, ok, you know, if you're this is what your email patterns are, it might be different for you and me because we're emailing strangers all the time. Um but for most people, their email patterns are pretty predictable and if something strays from that pattern that's abnormal. And they'll block it, they'll they'll investigate it, you know, and and that's great. You know, let's start using that kind of targeted add technology to protect people. And yeah, I mean it's not going to get us away from the password and using multifactor authentication. But yeah, the technology is out there and we just have to figure out how to use it in a really seamless way because it doesn't matter if you have the perfect security solution, if no one uses it. I mean when I started at the times when I was trying to be really good about protecting sources, I was trying to use PGP encryption and it's like it didn't work. You know the number of mistakes I would probably make just trying to email someone with PGP just wasn't worth it. Um and then signal came along and and signal made it wicker. You know, they made it a lot easier to send someone an encrypted text message. So we we we have to start investing in creative minds um in good security design. You know, I really think that's the hack that's going to get us out of where we are today. </s><s>[INST] What about social engineering? Do you worry about this sort of hacking people? [/INST] Yes. I mean this is the worst nightmare of every chief information security officer out there. Um you know social engineering. We work from home now I saw this this woman posted online about how her husband it went viral today. But it was her husband had this problem at work. They hired a guy named john and now the guy that shows up for work every day doesn't act like john I mean think about that. Like think about the potential for social engineering in that context. You know, you apply for a job and you put on a pretty face, you hire an actor or something and then you just get inside the organization and get access to all the organization's data. A couple of years ago, Saudi Arabia planted spies inside twitter. You know why? Probably because they were trying to figure out who these people were, who were criticizing the regime on twitter. You know, they couldn't do it with a hack from the outside. So why not plant people on the inside. And that's like the worst nightmare. And it also unfortunately creates all kinds of xenophobia and a lot of these organizations. I mean if you're going to have to take that into consideration, then organizations are going to start looking really skeptically and suspiciously at someone who applies for that job from china. Um and we've seen that go really badly at places like the Department of Commerce where they basically accused people of being spies that aren't spies. So it is the hardest problem to solve. And it's never been harder to solve than right at this very moment when there's so much pressure for companies to let people work remotely. </s><s>[INST] That's actually why I'm single I'm suspicious of china and [/INST] Russia </s><s>[INST] every time I meet somebody or trying to plant, get insider information. So I'm very, very suspicious, I keep putting the touring test in front. No, um [/INST] no, I have a friend who worked inside Vanessa and was one of their top hackers and he's like, every time I go to Russia I get hit on by these tents and I come home, my friends are like, I'm sorry, you're not a 10, like, </s><s>[INST] common [/INST] story. </s>

<s>[INST] Bernie's level of popularity. Still, I wish that the bias wasn't towards what could be negatively turned to deep state, towards the bureaucracy, towards the momentum of the past, which I think Joe Biden kind of represents, versus new ideas, which is funny to say that Bernie Sanders somehow represents new ideas [/INST] because he's also an older gentleman. Well, it's a lot of framing. And the other aspect of that is, on paper, Joe Biden's platform was arguably the most progressive of any Democratic candidate, who won the nomination. Now, of course, there were people who challenged the nominations who were to Joe Biden's left. A lot of this is perspective. And that's how you end up saying the guy who's a couple years older than Biden is actually the guy with the fresh perspective, </s><s>[INST] which is interesting because I don't disagree with you. Yeah, and you also have to say the perspective doesn't always align with the policies. You're right and the actual policies of Joe Biden [/INST] are different than the, maybe the perception of Joe Biden. Or what he ran on. I mean, just two examples I would give are during his campaign, he played up a little bit his interest in doing student loan forgiveness and something on cannabis. I never bought it. I told my audience, I think he's saying this stuff because this is the way the tide is kind of, the wind is blowing and he's being advised to say this stuff. I don't think he's going to do very much on either of these things. He did actually do some student loan stuff, </s><s>[INST] but that would be two examples, I think. Okay, let's go to something you alluded to, which is the pros and cons of a particular candidate. Well, what do you, as a critic of Trump, what do you are the pros, the strengths of Donald Trump [/INST] and what do you are as big as weaknesses? The strengths of Trump, let's see how I can frame them in a way that is both accurate and accurately assesses my feeling about it. </s><s>[INST] It can be taken out of context most masterfully through the clipping process. [/INST] Yes, yes. Trump's strengths are mostly superficial and in terms of presentation. Trump was able to, I call it a grift. Some on the right say he's just so good at relating to different types of people. Trump, as a rich guy from New York City, was able to convince people that he spent most of his life trying to be kept isolated from, that he had their best interests in mind, that he knew why they weren't doing well in the 2016 economy and that he had solutions that he was going to bring forward. The truth is, he never really liked those people and as soon as they weren't useful to him for a brief period of time, he, you know, that love affair with his followers stopped and then now it's back that he needs them again. He didn't really understand the causes of the problems that those folks were experiencing and his solutions were laughable, right? Like Jared was going to solve the Israeli-Palestinian conflict in year one. He was going to replace Obamacare in 2017. Things that were never going anywhere, anywhere. But what he did really well was he put up a united front of I know what is ailing you. I know how to fix it and I know how to fix it, I guess because he's a businessman and he's been above the fray of politics for so long, knowing how to use political donations to his advantage. He called that smart, et cetera. </s><s>[INST] I think that's his greatest strength. Why do you say that the Jared plan for Israel and Palestine and the plan for healthcare to improve Obamacare? [/INST] Why do you say that's laughable? Well, only someone, I would include the North Korea plan as well, which I'm glad to talk about, only someone who doesn't know anything about the size and scope of these issues could so arrogantly say that they could solve them in that way and on that timeframe. I'm all for optimism and bringing a new face to things. Absolutely, without a doubt. But, you know, a wall with Mexico that Mexico will pay for at the end of my first term. I know there are people who believed it because they would call into my show and say, I'm voting for Trump because of it. But it's hard to believe that anybody serious would fall for that unless you were deliberately wanting to just believe whatever was being fed to you. Or you just hadn't ever thought about these issues before. The healthcare plan, you know, in 2017, they proposed one would have led to 24 million or so people ending up without healthcare. It didn't go anywhere because it was so terrible. And then in August of 2020, Trump said in two weeks, I'm going to finally have my healthcare proposal. It's 2023, we still never got it. You know, with all of these things, when you think them through, it was just sort of arrogance. And I get the perspective of I want optimism and I liked that optimism. It worked. I mean, fair. A lot of people saw it and liked it. As someone who followed a lot of those issues closely, </s>

<s>[INST] the words you used to talk about it the way you thought about it. Was it more scholarly in the jewish tradition? Or did you, um, go to the feeling? [/INST] No, I went to the feeling, I said quote cabriolet, which means respect or honor for God's creations. Um, and, and caring for other human beings and understanding. Um, it wasn't scholarly because I knew that that this, the objections were not scholarly objections. Um, they were. And, and I, and I had so many, I had many beautiful and also painful stories as a result, some of which can be told and some of which really can't. But what I tried to impress also on people was how painful it is to not be able to tell the world even your own parents who you are and your sexuality is not a trivial part of who you are. I mean it's core to people. Um so it's one of the reasons why it evokes such reactions. But I but I would say to them the the same reason that you're reacting so strongly tells you how strongly, you know. Um anyway it was it was a very powerful experience at and and it for that I have you know, I have nothing. I I feel good about it afterwards. I the other thing that I again said to my daughter afterwards after it all died down and after all the bad things were said, I told her the Churchill once said that it's exhilarating to be shot at without result. You know, if you go into a battle and you make it through and you're still okay. That's good. </s><s>[INST] The problem is when you're in the battle you don't know. [/INST] No, you don't know. </s><s>[INST] So how did it feel like, I mean looking back um you've been you know uh to use the word canceled a couple of times I guess when you ask when you're dealing with the most difficult question. How did just as a human being for a community that you really deeply care about some part of it saying that you have failed. [/INST] I wasn't canceled the way. Like I didn't lose my job, I didn't lose my home. Um, but I hurt people that I cared about and that was the hard, like I went into this, you know, to be someone who brings people together and then I would sit there and, and do even now, like as you're well aware with stuff that's going on now. Um, I sit there and people are really upset at me who I either am or used to be close to </s><s>[INST] do. Those people in time come around when you, when you look now because those are real feelings in the moment and we can learn that about social media people, especially during Covid, there's this intensity of feeling about stuff. And have you learned something about the passing of feeling that turns into wisdom? [/INST] No question about it. The sermon I gave this saturday was about how you know, um, moses came down the mountain, he saw the golden calf and he broke the tablets. If he'd sat with it for a little while, I probably would have broken the tablets. But the instant reaction is always anger and in our age, unfortunately, the instant reaction gets put on social media forever and ever and ever and, and by the way, once you've actually said that it becomes harder to back down. If you keep quiet for a day or two, then then you can back down because you haven't put yourself out there. But once you said this is terrible what you did, what you did. It's harder to write and say, I'm sorry, I shouldn't have said that. </s><s>[INST] Yes. So it almost becomes, I mean I actually, it's a really powerful statement that the downside of saying something on the internet is that it actually pulls you into this current, you both create the current and it pulls you into it to where it's actually very hard to escape. So when in two days later you feel different. There's a momentum, There's now a tribe of people that feel this way and there's a momentum with it, [/INST] there's a momentum and also you don't want to betray your own tribe because then people will get upset at you. I really think that a lot of the antagonism is not so much that you don't want to give ground to the people who oppose you. It's that you don't want to break with the people who are behind you? And that's really hard. </s><s>[INST] Can you tell the story of this recent controversy sermon you [/INST] just gave, you went </s><s>[INST] to the Super Bowl? [/INST] I think a lot </s><s>[INST] of people would relate to this because to me personally, I apologize to anybody who was hurt by this, the absurdity of it is deeply intense. [/INST] So here's the story, the l A County mandates masking Children in school and all the kids in our school are masked and many of the parents are extremely upset about that. I will just leave that at that. Um, I went to the Super Bowl, There were 70,000 people Frank Luntz whom we know. Wonderful Guy gave me a ticket. Um, So, and so I was at the Super Bowl. I did, I maybe saw two masks among the 70,000 people. I didn't even think about it, which was foolish on my part. No question. I took a picture of myself unmasked at the Super Bowl and people were, I mean many, many people thought, oh, great, wonderful, glad you're having a good time. So on. And so whether I don't want to diminish at all. The many people who said that a lot of people were livid. They were livid and they weren't, um, what was, what was instructive about it was they didn't say, nobody wrote me a private note and said, you know, I think that this was a bad idea. You should have thought about this. No, they were, you're a hypocrite, You're a clown, You're an idiot. How could you do this? This is a disgrace. This is, oh yeah, on, on, on my instagram. You can still see, I left the remarks up because I really thought it was important. If I started, I only deleted the really vile comments because I thought that shouldn't stay up. But I left them up because I thought like people should see and I should remind myself what I did. And I didn't want to just delete the picture as though it didn't happen because it did happen. And I did do it. And I felt terrible about that and I felt terrible that I had not, not about. I mean the comments believe me weren't weren't pleasant. I didn't like it. Um nobody likes it. But I felt worse that I had hurt all these people that I'm close to. And I defended all these people who were really upset that their kids were wearing masks and now they their kids says, why don't you grab? I have to wear a mask. Well, </s>

<s>[INST] we've got a lot of time in my office. Yeah, yeah, yeah. And so then we went on our merry way, everyone went to different places, Charles landed at Georgia tech, which was, uh, what he always dreamed he would do. And so that worked out well. Um, I came up with a saying at the time, which is luck favors the Charles, it's kind of like luck favors the prepared, but Charles like, like he wished something and then it would basically happen just the way he wanted. It was, it was inspirational to see things go that way things worked out and we stayed in touch and then, um, I think it really helped when you were working on, I mean you kept me in the loop for things like threads and, and the work that you're doing at Georgia tech. But then when they were starting their online Master's program, he knew that I was really excited about moocs and online teaching and he's like, I have a plan and I'm like, tell me your plan. He's like, I can't tell you the plan yet because they were deep in negotiations between Georgia tech and Udacity to make this happen and they didn't want it to leak. So Charles wood kept teasing me about it, but wouldn't tell me what was actually going on. And eventually it was announced and he said, I would like you to teach the machine learning course with me. I'm like, that can't possibly work. Um, but it was a great idea and it was, it was super fun. It was a lot of work to put together, but it was, it was really great and was that the first time you thought about, first of all, was it the first time you got seriously into teaching? I mean, you know, I'm trying to get the findings like this is already and I had after you jump too, so like there's a little bit of jumping around in time. Yeah, sorry about that, big jump in time, so like the moocs thing, so Charles got Georgia tech and he may be Charles, maybe this is [/INST] A 2002, </s><s>[INST] He got to Georgia Tech in 2002 and but and worked on things like revamping the curriculum, the undergraduate curriculum so that it had some kind of semblance of modular structure because computer science was at the time moving from a fairly narrow specific set of topics to touching a lot of other parts of of of intellectual life and the curriculum was supposed to reflect that. And so um Charles played a big role in in kind of redesigning that and then [/INST] and for my and for my my labors I ended up to his associate dean </s><s>[INST] right, he got to become associate Dean of charge of educational stuff. Be a valuable lesson if you're good at something, uh they will give you responsibility to do more of that thing until you show competence. Don't show competence. If [/INST] you know what the responsibility, here's what they say. Uh the reward for good work is more work. The reward for bad work is less work, which I don't know depending on what you're trying to do that week. One of those is better than the other. One of the problems with the word works are to interrupt </s><s>[INST] is that it seems to be an antonym in this particular language. We have the opposite of happiness, but it seems like they're they're like, that's one of, you know, we talked about balance. It's always like work life balance always rubbed me the wrong way as a terminal. And I know it's just words like the opposite of work is play ideally work his play. [/INST] Oh, I can't tell you how much time I spend. Certainly was a bell Labs would except for a few very key moments as a professor I would do this to. I just cannot believe they're paying me to do that because it's fun. It's something that I would I would do for a hobby if I could anyway, so that's what it worked. I'm sure you want to be saying </s><s>[INST] that when this is being recorded as [/INST] a dean, that is not true at all. I need to raise. But but I think here with this that even though a lot of time passed, you know, Michael, I talked almost everywhere. We texted almost every day during the period </s><s>[INST] Charles. At one it took me there was the I. C. M. L. Conference, the machine learning conference was in Atlanta. I was the chair. The general chair of the conference Charles was my publicity chair or something like that or fundraising chair. Yeah. Um, but he decided to be really funny if he didn't actually show up for the conference in his own home city. Uh, so he didn't, but he did at one point, picked me up at the conference in his Tesla and drove me to the Atlanta mall and forced me to buy an iphone because he didn't like how it was to text with me and thought it would be better for him if I had an iphone, the text would be somehow smoother. And it was, and it was, [/INST] and it is and his life has been in </s><s>[INST] my life is better. And so, but, but it was, yeah, Charles forced me to get an iphone so that he could text me more efficiently. I thought that was an interesting moment. It [/INST] works for me anyway, so we kept talking the whole time and they eventually did the, we did the teaching thing and it was great and there's a couple of reasons for that by the way. One is, I really wanted to do something different. Like you've got this medium here, People claim it can change things. What's the thing that you could do in this medium that you could not do otherwise? Uh, besides edit. Right. I mean, what could you do and being able to do something with another person with that kind of thing. It's very hard. I mean you can take turns, but teaching together, having conversations very hard. Right? So that was a cool thing. The second thing you may excuse to do more stuff with </s>

<s>[INST] No, we're not not even close. [/INST] Well, I </s><s>[INST] mean, yeah, okay, I mean, like be able to sort of play with black holes, that kind of thing. So we're talking about a whole another different order of magnitude of masses, then it may be very effective to send signals via gravitation ways. [/INST] I actually, my sense is that all of these things are genuinely difficult to predict. You know, and I don't mean like to kind of shy away. I just I really mean if you think if you take um imagination of what the future looked like from, you know, 500 years ago, right, it's just it is so hard to conceive of the impossible. Right? So, um it's it's almost like um you know, it's almost limiting to try and imagine things that are an order of magnitude uh or two orders of magnitude ahead in terms of progress just because, you know, you mentioned cars before, you know, if you were to ask people what they wanted in 1870s, faster buggies. Right? So, um so I think the whole, like kind of you know, alien conversation inevitably gets, gets limited by by our entire kind of collective um astrophysical lack of imagination. </s><s>[INST] I so to to push back a little bit, I find that it's really interesting to talk about these wild ideas about the future, whether it's aliens, Whether it's ai with brilliant people like yourself who are focused on very particular tools of signs we have today to solve very particular, like rigorous scientific questions and it's almost like putting on this wild dream, he had like some percent of the time and say like, what are like, what would alien civilizations look like? What would alien trash look like? What would our own civilization that sends out trillions of ai systems out there? Like how 9000, 10,000 out there, what would that look like? And you're right, anyone prediction is probably going to be horrendously wrong, but there's something about creating these kind of wild predictions that kind of opens up. [/INST] So there's a huge magnetism to it, right? And some of some of it, um you know, I mean some of the jules verne novels did a phenomenal job predicting the future, right? Uh that that actually was a great example of what you're talking about, allowing your imagination to run free. I mean, I just hope, I just hope there's dragons, that's, there's no question that I love dragons, dragons are the best. </s><s>[INST] Uh but see the cool thing about science fiction and these kinds of conversations, it doesn't just predict the future. I think some of these things will create the future, planting the idea, this is the humans are amazing, like fake it till you make it. Humans are really good at taking an idea that seems impossible at the time and for any one individual human. That idea is like a, it's like planting a seed that eventually realize itself. It's weird, it's weird how like science fiction can, creates a line [/INST] drive, some of the drives designs. I agree with you. And uh, and I think in this regard, you know, I'm like a sucker for sci fi. Uh, it's all I listen to like now when I, when I run and, and some of it is completely implausible, right? And it's just like, I don't care. It's so, it's uh, it's both entertaining and uh, you know, it's just like it's imagination, you know about the black clouds book. I think this by fred hoyle, this is like, this has great connections with sort of a lot of the advancements that are happening in NLP. Um, right now write with transformer models and so on. But you know, it's this black cloud shows up in, in the solar system and then people try to sand radio and then it learns to talk back at you. You know? So anyway, we don't have to talk at all about it, but it's just, that's something worth checking out with </s><s>[INST] that on the alien front with the black cloud to me. I'm exactly in the LMP front and also just explain ability of ai, it's fascinating just the very question Stephen Wolfram looked at this with the movie arrival. It's like what would be the common language that we would discover, the reason? That's really interesting to me is we have aliens here [/INST] on earth. </s><s>[INST] Japanese. [/INST] Japanese is the obvious answer. </s><s>[INST] Japanese. Yeah, that would be the common. Maybe it would be music actually, that's more likely. It wouldn't be a language, it would be art that they will communicate. But you know, I I do believe that we have, I'm with Stephen Wolfram and it's a little bit that, to me computation like programs, we write that, you know uh that they're kind of intelligent creatures. And I feel like we haven't found a common language to talk with them. Like our little creations that are artificial, are not born with whatever that anything that produces language with us. And like coming up with mechanisms for communicating with them uh is uh is an effort that feels like it will produce some incredible discoveries. You can even think of if you think that math is discovered, mathematics in itself is a kind of uh [/INST] oh yeah, it's an innate construction of of the world we live in um I think we are, you know, part of the way there because Pre 1950 right computers who were, were human beings that would carry out arithmetic. Right? And I think it was cool. Um um who worked in Los Alamos at the at the time, like towards the end of the Second World War wrote something about how, you know, in the future, right? Computers will not be just arithmetic tool, but will be truly an interactive you know thing with which you could do experiments at the time? The notion of doing an experiment not like in the lab with some beakers but an experiment on a computer designing an experiment on the miracle experiment was a new one that's like You know 70% of what I do is I designed you know I write code terrible code to be clear like but you know I write code that creates an experiment which is a which is a simulation. So in that sense I think we're beginning to interact with the computer in a way that you're saying not as just a you know fancy calculator not it's just a you know call and request uh type of I think. But but you know something that can generate uh generate insights that are otherwise completely unattainable right there. Unattainable by doing analytical mathematics. </s>

<s>[INST] That's one way to maintain privacy, right? Is like in order to protect the contents of this conversation for example, we could just generate like millions of deepfake conversations where you and I talk and say random things. So this is just one of them and nobody knows which one is the real one. This this could be fake right now. [/INST] Classic steganography technique. </s><s>[INST] Okay. Another absurd question about intelligent life because uh you know, you're you're an incredible programmer outside of everything else. We'll talk about just as a programmer. Uh Do you think intelligent beings out there, the civilizations that were out there had computers and programming? Did they do we naturally have to develop something where we engineer machines and are able to encode both knowledge into those machines and instructions that process that knowledge, process that information to make decisions and actions and so on. And would those programming languages if you think they exist be at all similar to anything we've developed. [/INST] So I don't see that much of a difference between quote unquote natural languages and programming languages. Uh huh um Yeah, I think there's so many similarities. So when asked the question, what do alien languages look like? I imagine they're not all that dissimilar from ours and I think translating in and out of them uh wouldn't be that crazy. </s><s>[INST] It was difficult to compile like DNA to python and then to see that there is a little bit of a gap in the kind of language as we use for for touring machines and the kind of language is nature seems to use a little bit maybe that's just we just haven't we haven't understood the kind of language that nature uses well yet. [/INST] DNA is a CAD model, it's not quite a programming language, it has no sort of cereal. Uh huh, execution. It's not quite uh yeah, it's a cat model. Um so I think in that sense we actually completely understand it. The problem is um you know, uh well simulating on these CAD models, I played with it a bit this year is super computational intensive if you want to go down to the molecular level where you need to go to see a lot of these phenomenon like protein folding. Um So yeah, it's not that it's it's not it's not that we don't understand it, it just requires a whole lot of compute to kind of compile it </s><s>[INST] for human minds, it's inefficient. Both for the problem for the data representation and for the programming, [/INST] it runs well on raw nature. Everyone's well in raw nature. And when we try to build emulators and simulators for that. Uh well the man's law and I've tried it. </s><s>[INST] It runs in. Yeah, you've commented elsewhere. I don't remember where that one of the problems is simulating nature is tough and if you want to sort of deploy prototype, I forgot how you you put it, but it made me laugh. But animals or humans would need to be involved in order to in order to try to run some prototype code on. Like if we're talking about Covid and viruses and so on. If you were trying to engineer some kind of defense mechanisms like a vaccine against Covid or all that kind of stuff that doing any kind of experimentation, like you can with like autonomous vehicles would be very technically cost technically and ethically costly. [/INST] I'm not sure about that. I think you can do tons of crazy biology and test too because I think my bigger complaint is more, all the tools are so bad, </s><s>[INST] like literally you mean like, like I'm not crazy and [/INST] I'm not high petting shit like you're handing me up. I got to know. No, no, there has to be some uh </s><s>[INST] huh like automating stuff and and like the Yeah, but human biology is messy. Like it seems like [/INST] look at those Theranos videos, they were a joke. It's like it's like a little Gantry Xy Gantry high school science project with the pipe at like </s><s>[INST] really something you can't [/INST] build like nice micro fluid IX and I can program the, you know, computation to bio interface. This is going to happen. But like right now if you are asking me to pipette 50 ml of solution amount, it was just so crude. </s><s>[INST] Okay, let's get all the crazy out of the way. So a bunch of people asked me since we talked about the simulation last time we talked about hacking the simulation, do you have any updates? Any insights about how we might be able to go about hacking simulation If we indeed do live in a simulation? [/INST] I think a lot of people misinterpreted the point of that South by talk. The point of the south by talk was not literally to hack the simulation. Uh I think that this, this is, this is an idea is literally just I think theoretical physics, I think that's the whole, you know, the whole goal. Right? You want your grand unified theory? But then okay, build a grand unified theories for exploits right? I think we're nowhere near actually there yet. My hope what? That was just more to like like are you people kidding me with the things you spend time thinking about? Do you understand like kind of how small you are you are, you are bites and God's computer really? And the things that people get worked up about, you </s><s>[INST] know? so basically it was more a message of, we should humble ourselves that we get to like what, what are we humans in this bike code. [/INST] Yeah. And not just not just humble ourselves, but like, like I'm not trying to like make you feel guilty or anything like that. I'm trying to say. Like literally look at what you are spending time on. Right? </s>

<s>[INST] So everyone is focusing on, what is adaptation? So you can adapt to- Adapt infrastructure, right? Yes. The physical and the digital infrastructure. Yes. You're basically focusing on reducing carbon emission versus innovating on alternate energy. [/INST] You're basically focusing on putting the existing solar panels or wind turbines, which are either just about inefficient or inefficient, instead of making the next generation, or it's more likely the 10th generation after that, that comes with lots of battery backup power or 4th generation nuclear, or Craig Venter has this great idea. Craig Venter, the guy who cracked the human genome back in 2000, he has this idea of growing algae out on the ocean surface. These algae, they'd be genetically modified and they would basically soak up sunlight and CO2 and produce oil. Then we could basically just grow our own Saudi Arabia out on the ocean surface and we'd harvest it. We'd keep our entire fossil fuel economy, but it'd not be net zero because we'd just </s><s>[INST] soaked up the CO2 out there. $1 invested in the portfolio of different ideas. [/INST] Gives $11 back. Yeah. Gives $11 back. I first wrote about that in the New York Times. It was one of my actual page one stories. In 2006, it was declining R&D in energy at a time of global warming and the baseline is so low for this that it's a super bargain. We were in, during the energy crisis, the first energy crisis in the 70s before the current one, our annual spending in the United States on constant dollars on R&D, research and development for energy, was about $5 billion and then it's just dribbled away since then. Recently now, there's a big burst of new money coming through these new bills that got passed. What I was told over and over again by people in that arena is you can't just have these little bubbles of investment. You don't get young people away from thinking about Wall Street for jobs towards thinking about energy innovation if there isn't like a future there. A lot in the United States and Europe, the presumption was the wage of that future was taxing carbon, make that so punitive that you're basically leveling even in the landscape for cleaner stuff that's more expensive, that has failed completely. There are little examples in Europe where it's working. What's happened now is, well, the United States, this big chunk of money is designed to take us over a finish line that was started with not just innovation but with the production efficiency too. This is one thing I've got wrong, I think, a little bit in my reporting. I was so fixated on the innovation part just because I love science too. I saw this untapped possibility that others were saying, no, no, production efficiency, the more people are producing batteries, the cheaper they'll get. This is Elon Musk's path and many others, and it really is both. When you were talking about purchasing power for governments, for example, that can stimulate production capacity for batteries or whatever the good thing is and take you down faster. It's all about getting that margin of the new thing, of competing the old. It's not just innovation, it has so many parts of the pipeline that need to be nurtured. The other thing is relative cost. The United States, when I was writing about this in 2006, our budget for DARPA, the Advanced Research Project Agency for the Defense Department, just for science, it was $80 billion a year. For health, for medical frontier research on cancer and stuff, $40 billion, energy was two or three. We weren't taking this remotely seriously. Now, if we get that up, to me, there's this level, you know we're taking something seriously when it's in the tens of billions for R&D. It's not that R&D will solve the problem, but it's a proxy for what we really care about. We care shitload about defense. What's the defense budget in the United States now, like $800 billion? </s><s>[INST] It's some insane number. Who's counting when you're having fun? [/INST] Yeah, yeah, yeah. Innovation is not just for the better camera, the better solar panel, the better battery. Social innovation actually matters hugely. Like the guy in Nairobi I mentioned with a company doing micropayment, gas to get people off charcoal. We need that as much as this. And actually, I interviewed Bill Gates. We had to spend an hour with him in Seattle in 2016 when he was rolling out his breakthrough energy thing. I got to spend, it was 45 minutes, me and Bill Gates, which was pretty fun. But I brought this up. I said, you know, because he's all about the new nuclear thing that will solve the world's problems. And yes, yes, yes. </s><s>[INST] But we also- He brought up nuclear? Sorry to interrupt. Oh, he did. [/INST] Oh, sure. So he's interested in one of the- Oh, he's investing heavily in nuclear, but he invests in everything. You know, he's got a big portfolio. But I brought up a guy I met in India who runs a little outfit called Selco that they do really interesting cool village to village. They're like an energy analyst who'll come to your house here in the States and tell you how to weatherize your house, but they do it at the village scale. And in a village that has, where they're milling wheat, he'll put in a solar powered wheat mill. And that's not going to solve the world's problems, but it gives them a way to control their energy. They don't have to buy something to grind their wheat. And that needs just as much attention as the things I really like too, the cool technologies. And I thought I cornered Bill Gates. I was like, because he really does focus on these big wins, the big nuclear that will make net zero completely doable. And I said, well, you know, what about like New York city where I was still living at the time or near and I said, it's got a million buildings, New York city has 1 million buildings. And in 2013, the Bloomberg government analyzed, they said, looking ahead to 2050, 75% of the buildings in New York city that will exist in 2050 already exist. Think about these brave new futures, right? Like, we're just going to like come in, have these shiny, cool passive house cities. And so I put this to Bill and I said, so how do you do that? How do you retrofit all those boilers, many of which were coal fired like 20 years ago to get a zero energy in New York city. I kind of thought I had him, and then he immediately, he kind of sat back and went, well, but if you have unlimited clean power coming into that city, it doesn't really matter. </s>

<s>[INST] I agree with you. There's uh it's actually really difficult when you have to understand the physical world enough to uh project onto it. Well, I lied about the last question uh [/INST] because </s><s>[INST] I just thought of audio and my favorite topic, which is the movie [/INST] her. Do </s><s>[INST] you think? Well, there's part of Spotify or not? Well have, I don't know if you've seen the movie her? [/INST] Absolutely. Uh </s><s>[INST] uh their audio is the primary form of interaction and the connection with another entity that you can actually have a relationship with. You fall in love with based on voice alone, audio alone, how far do you think that's possible First of all, based on audio alone to fall in love with somebody somebody or Well, yeah, let's go with somebody. Just have a relationship based on audio alone. And second question to that, can we create an artificial intelligence system that allows one to fall in love with it and hurt him with you. [/INST] So there's my personal personal answer. Uh speaking for me as a person. The answer is quite unequivocally yes. On on both. I think what we just said about podcasts and the feeling of being in the middle of a conversation if you could have an assistant where and we we just said that feels like a very personal settings. So if you walk around with these headphones and this thing, you're speaking with this thing all over the time that feels like it's in your brain. I think it's, it's gonna be much easier to fall in love with something that would be on your screen, then that's entirely possible. And then from the you can probably answer this better than me, but from the concept of if it's going to be possible to build a machine that they can achieve that, I think whether you whether you think of it as uh if you can fake it, the philosophical zombie that assimilates it enough or it somehow actually is. I think there's it's only a question if you if you ask me about time, I had to be an answer, but if you say a given some have infinite time. Absolutely. I think it's just atoms and arrangement of information. </s><s>[INST] Well, I personally think that love is a lot simpler than people think. So we started with true romance and ended in love. I don't see a better place to end. Beautiful Gustav. Thanks so much for talking [/INST] today. Thank you so much. It was a lot of fun. </s><s>[INST] It was fun. [/INST] Yeah. </s>

<s>[INST] put it in perspective. I'm not sure a lot of people understand the deep human side or even the military strategy side of this war. There's a lot of experts outside of the situation there commenting on it with certainty and that kind of hurts me because I feel like there's a lot of uncertainty. There's so much propaganda, it's very difficult to know what is true. Um Yeah, so, so my whole hope was to travel to Ukraine to travel to Russia, to talk to soldiers, to talk to leaders, to talk to real people that have lost homes, that have lost family members that who this war has divided, who this war changed completely how they see the world. Uh whether they have love or hate in their heart to understand their stories. Um, I've learned a lot on the human side of things by having talked to a lot of people there, but it has been on the Ukrainian side, for me, currently traveling to the Russian side is more difficult. Let me ask you about your now friend, can we go as far as to say his friend in a Sabu Hector Monsegur what's the what's what's the story? What's your long story with him? Can you tell me about? What is law? Sec who is Sabu and who's anonymous? What is anonymous? Where's the right place to start? That story? [/INST] Probably anonymous, anonymous is a was a decent still is, I guess a decentralized organization. Uh they call themselves headless. But once you look into them a little ways and they're not really headless. Um the power struggle comes with whoever has hacking ability. Um that might be your good hacker or you have a giant bottom that used for d does. Um So so you're gonna wield more power if you can control where it goes anonymous started doing their like hacktivism stuff in 2010 or so. Um The word hack was in the media all the time then. Um and then right around then there was a federal contractor named H. B. Gary Federal. The Ceo is Aaron Barr and Aaron Barr said he was gonna come out and be anonymous is anonymous. He's gonna come out and talk at black hat or def con or one of those and say you know who they are, He figured it out. So he figured it out by based on you know when people were online when people in IRC when tweets came out it was there was no scientific proof behind it or anything. So he's just gonna falsely name people that were that were in anonymous. So anonymous went on the attack. They went and hacked in hp. Hp A. Federal and they turned his life upside down. They took over his twitter account and all that stuff. Um pretty quickly. So </s><s>[INST] I have very mixed feelings about all of this. [/INST] Okay I </s><s>[INST] get like part of me admires the positive side of the activism. Is there no room for admiration there of the funk. You to the man. [/INST] Not at the time again there was a violation of 18 U. S. C. 10 30. So it was my job you know so at the time though in retrospect shore. But </s><s>[INST] what was the philosophy of the activism was what the philosophically were they at least expressing it for the good of humanity or no [/INST] they outwardly said that they were going to go after people that they thought were corrupt. So they were judge and jury on corruption. They were to go after it once you get inside and realized what they were doing they were going after people that they had an opportunity to go after. Um So maybe someone had a zero day and then they searched for servers running that zero day. And then from there let's find a target. I mean one time they went after a toilet paper company, I still don't understand what that toilet paper company did but it was an opportunity to make a splash. </s><s>[INST] Is there someone for the joke for the lulls. [/INST] It developed into that. So I think the hacktivism and the anonymous stuff wasn't so much for the locals. Um But from that H. B. Gary federal hack. Then there were six guys that worked well together and they formed a crew. A hacking crew and they kind of split off into their own private channels. And that was low Sekar or laughing at your security was their motto. </s><s>[INST] So that's L. U. L. Z. S. E. C. Lulls sec. [/INST] Of course it is. </s><s>[INST] SEK and who founded that organization. [/INST] So Kayla and Sabu were the hackers of the group and so they really did all the work on H. B. Gary. So yeah they're online names, their their their nicks. Um And so you know they they that's all they knew each other </s><s>[INST] as you [/INST] know, they talked as those names um And they worked well together and so they formed a hacking crew and that's when they started the at first they didn't name it. This was the 50 days of lulls where they would just release major major breaches. Um And it stirred up the media. I mean they put hacking in on in the media every day. Uh They had 400 or 500,000 twitter followers. Um You know, and it was kind of interesting. Um But then they started swinging at the beehive and they took out some FBI affiliated sites. Uh and then they started fuck FBI Fridays where every every friday they would release something and we waited it for bated breath. I mean they had a hook line and sinker pissed. We were waiting to see what was going to be dropped every friday. It was, it's a little embarrassing looking back on it now. </s><s>[INST] And this is in the early 2010s. [/INST] Yeah this was 2010, around there can </s>

<s>[INST] that. Yeah, that was really, really, really refreshing to hear. So this is me speaking. But there's a sense when companies take on these issues publicly from a ceo position and anywhere else that it does seem to optimize for virtue signaling versus solving a particular problem because to solve a particular problem, you really have to really put in, you have to hire a huge number. You basically have to create a company with a company to take on a particular thing. But if you allow yourself to internally care about a particular issue, you're basically pacifying some number of employees. Like making sure slack doesn't get out of hand and then you're doing this kind of from my perspective, especially on issues I care about fake virtue signaling basically trying to understand what will make me look the best, what would make the company look the best in this particular aspect. And it it just seems very shallow and it's optimizing for the wrong thing, not for the solving of the problems but for the making yourself look like the good guy and trying to leverage that to say I'm the good guy in all situations and it's just it's it's it's the wrong thing. And perhaps from your perspective as a ceo as a leader, it's also creating division, unnecessary division within people. Like they get, yeah, there's something about us, we get extremely argumentative about certain topics. They really bring out the emotion. And I think that probably as you were saying that emotion is even probably okay maybe productive when that emotion has to do with the mission of the company. Like you really care about those disagreements versus like something that has nothing to nothing to do with a particular with with increasing economic freedom uh using crypto. Yeah, it's fascinating but it was so refreshing because it's rare. Why do you think that's a rare? So you the city you're mentioning we could I mean there's a bunch of cities but you know SAn Francisco is one such city when, when, when that culture and it's sad because SAn Francisco is also the Bay Area is also the hub historically of some of the greatest innovation in human history so that there's that tension. How did that culture emerge there where like the innovation was done by people that are very mission driven. You get a bunch of smart people together to solve a difficult problem. They get maybe sometimes too much blinders on but they try to balance that because it requires that focus to solve an actual problem. And yet that's also the place where this culture emerge. It's a fascinating human dynamic. I don't know, somebody will one day tell the history of of Silicon Valley not just the innovation but the social dynamics that occurred there anyway. Why do you think that's so rare? [/INST] Well because people don't wanna get attacked it's like super you don't wanna get canceled right, it's super uncomfortable. You know, nobody wants to be called a racist or whatever whatever you know people want to say on twitter so um Yeah. Yeah I definitely got attacked. I mean and I knew it, I knew it would be controversial. The only reason I did it frankly was that um I was kind of at my wit's end. I was like well like I said earlier like the job the ceo job sucks like either I don't want to do it or they have to go and I'm gonna make the company to something that I want and You know I spent um I'd spent eight or 90 years of my life at that point kind of building this thing. I was like well I could go start another company but it takes a long time to get momentum with these things. And you know Coinbase is a very rare thing that happened in the world. I feel very passionate about it. So um yeah I'm not gonna go like I need to make this the company that I want to work at. And what was really interesting was that there was such a huge outpouring of support that so I knew that it would be controversial and I would get attacked and predictably, you know, there was some um some journalists and you know, new york times and all these people who kind of like went and started writing hit pieces on on the company after shortly thereafter. And they basically just called people who left the company and like you know can get quotes on whatever they want and then they'll write a story. So mainstream media, I lost a lot of trust in mainstream media frankly after that. And of course it's kind of become obvious since then that um most mainstream media is like hyper politicized at this point. It's basically either super left or super right. And it's not really that focused on um truth. So that's that's kind of unfortunate because I think journalism is actually like really important in society so that that whole thing got eroded in the U. S. Luckily there's sort of new media people like you. Um And a whole bunch of people did </s><s>[INST] That blog post help that statement. The 95 people that remained. Is this still something you struggle with? Because it's also culture the broader tech space. [/INST] Okay so that was an interesting thing which was that. So the 95% of people stayed. I got a huge outpouring of support from people who said thank God you finally spoke up and said something because frankly it was making not a very fun place to work either. And I realized that there is I think there was I think is the same taleb has this blog post about the tyranny of the 1% or something like that. But there's basically a relatively small group 15% or something like that that is really upset about something. It's not the majority of company it's like 5%. There's another 15% or something that are sympathetic to the cause they're they're actually somewhat suggestible. They will go along with whatever because it sounds reasonable. You know these are like real issues they're talking about. It's not not to say that it's not real and they'll kind of get swept up in it. But there's an 80% of the company that basically doesn't agree or just wants to get their work done without all this drama and or distraction and they're afraid to speak up because if they speak up they're afraid of being again called a racist like fired, you know, ostracized amongst their peers. And so it did require um it to get to a bad enough place for me to finally say, you know what I I just I feel like I have to do this lived through the short term attacks of the press, which ultimately was very freeing for me because now I don't really care and now I can actually just build the company that I want to build without like caring about that. So and then what was cool was a lot of really great people reached out to the queen base to after that and we're like, I, you know, I'm an early engineer at google or whatever and like this culture has gotten kind of messed up and like I want to work at a company that's willing to stand for that. And so we've gotten a lot of good people come over basically what I realized and by the way, our diversity numbers and all that stuff, like people told me when I was drafting this post are like, don't post this, You're like people underrepresented groups will never want to work at this company again. And I was like, I don't think that's true. Like I talked to like R. E. R. G. Groups and they're not telling me they care about this stuff that much. They're telling me they just want to like be respected at work and do good work and contribute. So my gut was telling me that that advice was wrong and like I can tell you a year a year after doing it. Like our diversity numbers are basically either the same or better in every category. So that turned out to be false. Um Look I I hate to be like I'm like I'm you know polarizing on in either dimension here. Like I just want to get good work done and build good stuff with technology. So You know um I think companies should just have like reasonable policies like you want to get rid of bias in hiring you want to attract great people from all different backgrounds. Like you know, we have pledged 1%. We put 1% of the company equity into a foundation. Like I hope we're able to do good stuff with that. That's you know give back in some way. But like the main the main message I guess for me is like The core the core mission, the core work that we're doing on economic freedom and just all of our products are that is like the main value that we're contributing in the world. Like let's just do that more and hopefully we can get from 89 million verified users to a billion or whatever and then um I just think that's how we'll have the biggest impact. </s>

<s>[INST] So one of the interesting ideas of that system is that plays against itself, right? But there's no human in the loop there. So like you're saying it could have by itself created an alien intelligence. How [/INST] towards towards a goal, imagine your sentencing, you're judging your sentencing people or you're setting policy or you're you know, you're making medical decisions and you can't explain, you can't get anybody to understand what you're doing or why. So it's it's it's an interesting dilemma for the applications of AI do we hold A. I. Two? This accountability that says, you know, humans have to be humans have to be able when you take responsibility, you know, for for the decision. In other words, can you explain why you would do the thing, will you will you get up and speak to other humans and convince them that this was a smart decision is the Ai enabling you to do that. Can you get behind the logic that was made there? </s><s>[INST] Do you think sorry to linger on this point? Because it's a it's a fascinating one. That's a great goal for Ai Do you think it's achievable in many cases? Okay, there's two possible worlds that we have in the future. One is where aI systems do like medical diagnosis or things like that or drive a car without ever explaining to you why it fails when it does, that's one possible world and we're okay with it or the other where we are not okay with it and we really hold back the technology from getting too good before it's able to explain which of those worlds are more likely do you think and which are concerning to you or not? [/INST] I think the reality is is going to be a mix. You know, I'm not sure I have a problem with that. And I think there are tasks that perfectly fine with machines show a certain level of performance and that level of performance is already better already better than humans. So for example, I don't know that I take driverless cars, driverless cars learn how to be more effective drive drivers than humans but can't explain what they're doing. But bottom line, statistically speaking there, You know, 10 times safer than humans. I don't know that. I care. I think when we have these edge cases, when something bad happens and we want to decide who's liable for that thing and who made that mistake and what do we do about that? And I think in those educations are interesting cases. Um, and now do we go to designers of the Ai and the I says, I don't know if that's what it learned to do. And he says, well you didn't train it properly. You know, you you were you were negligent in the training data that you gave that machine, like how do we drive down and reliable? So I think those are, I think those are interesting questions. </s><s>[INST] So the optimization problem there, sorry, is to create an ac system is able to explain the lawyers away. [/INST] There you go. There you go. Um, I think that uh, I think it's gonna be interesting. I mean, I think this is where technology and social discourse are going to get like deeply intertwined and how we start thinking about problems, decisions and problems like that. I think in other cases it becomes more obvious where, you know, it's like, like why did you decide to give that person, you know, a longer sentence or or deny them parole again? Policy decisions or why did you pick that treatment? Like that treatment ended up killing that guy? Like why was that a reasonable choice to make. So, so and people are going to demand explanations now. There's a reality though here. And the reality is that it's not, I'm not sure humans are making reasonable choices when they do these things. They are using statistical hunches, biases or even systematically using statistical averages to make. Cause I mean that's what happened. My dad, if you saw the talk, I gave about that. But you know, I mean they decided that my father was brain dead. He had had went into cardiac harassed and it took two took a long time for the ambulance to get there and wasn't not resuscitated right away and so forth. And they came and told me he was brain dead and why was he brain dead? Because essentially they gave me a purely statistical argument Under these conditions with these four features, 98% chance he's brain dead. And I said, but can you just tell me not inductive Lee but productively go there and tell me his brain style functioning is the way for you to do that. And and and they're the protocol in response was no, this is how we make this decision. I said this is adequate for me. I understand the statistics and I don't know, you know, There's a 2% chance. He's a lot like I just don't know the specifics. I need the specifics of this case and I want the deductive logical argument about why you actually know he's branded so I wouldn't sign that do not resuscitate. And I don't know, it was like they went through lots of procedures a big long story. But the bottom was fascinating story by the way, but how I reasoned and how the doctors reason through this whole process. But I don't know somewhere around 24 hours later or something. He was sitting up in bed with 00 brain damage </s><s>[INST] and what lessons do you draw from that story that experience [/INST] that the data that they're you that the data that's being used to make statistical inferences doesn't adequately reflect the phenomenon. So in other words you're getting shipped wrong, sorry, you're getting stuff wrong because your your model is not robust enough and you might be better off not using statistical inference and statistical averages in certain cases when, you know, the model is insufficient and that you should be raising and about the specific case more logically and more deductive lee and hold yourself responsible to hold yourself accountable to doing that. </s>

<s>[INST] 10% of Sun-like stars have Jupiters around them, as far as we can tell. When you say Jupiter, [/INST] which aspect of Jupiter? In terms of its mass and its major axis. So anything beyond about half an AU, so half the distance of the Earth and the Sun, and something of order of a tenth of a Jupiter mass, so that's the mass of Saturn, up to, say, 10 Jupiter masses, which is basically where you start to get to brown dwarfs, those types of objects appear to be somewhat unusual. Most solar systems do not have Jupiters, which is really interesting because Jupiter, again, like the Moon, seems to have been a pivotal character in the story of the development of our solar system, perhaps especially having a large influence of the development of the late heavy bombardment and the rate of asteroid impacts that we receive and things like this. Anyway, to come back to 1625, this Jupiter-like planet had a hint of something in the data. But what I mean by that is when we looked at the transit, we got the familiar decrease in light that we always see when a planet tries in front of the star, but we saw something extra. Just on the edges, we saw some extra dips around the outside. It was right at the hairy edge of detectability. We didn't believe it, because I think one of the challenges of looking for something for 10 years is that you become your own greatest skeptic. No matter what you're shown, you're always thinking, it's like falling in love so many times and it's not working out. You convince yourself it's never going to happen, not for me. This just isn't going to happen. I saw that and I didn't really believe it because I didn't dare let myself believe it. But being a good scientist, we knew we had an obligation to publish it, to talk about the result and to follow it up and to try and resolve what was going on. We asked for Hubble space telescope time, which was awarded in that case. We were one of those lucky 20 that got telescope time. We stared at it for about 40 hours continuously. To provide some context, the dip that we saw in the Kepler data correspond to a Neptune-sized moon around a Jupiter-sized planet, which was another reason why I was skeptical. We didn't have that in the solar system. That seems so strange. Then when we got the Hubble data, it seemed to confirm exactly that. There was two really striking pieces of evidence in the data that suggested this moon was there. Another was a fairly clear second dip in light, pretty clearly resolved by Hubble. It was about a five-sigma detection. On top of that, we could see the planet didn't transit when it should have done. It actually transited earlier than we expected it to by about 20 minutes or so. That's a hallmark of a gravitational interaction between the planet and the moon. We actually expected that. You can also expect that if the moon transits after the planet, then the planet should come in earlier than expected because the center of mass lives between the two of them on a balancing arm between them. We saw that as well. The phase signature matched up. The mass of the moon was measured to be Neptune mass, and the size of the moon was measured to be Neptune radius. Everything just really lined up. We spent months and months trying to kill it. This is my strategy for anything interesting. We just try to write the kitchen sinker and say, we must be tricked by something. We tried looking at the centroid motion of the telescope, at the different wavelength channels that have been observed, the pixel-level information. No matter what we did, we just couldn't get rid of it. We submitted it to Science. I think at the time, Science, which is one of the top journals, said to us, would you mind calling your paper Discovery of an ExoMoon? I had to push back. We said, no, we're not calling it that. Even despite everything we've done, we're not calling it a Discovery. We're calling it evidence for an ExoMoon because for me, I'd want to see this repeat two times, three times, four times before I really would bet my house that this is the real deal. I do worry, as I said, that perhaps that's my own self-skepticism going too far. I think it was the right decision. Since that paper came out, there has been continuous interest in this object. Another team independently analyzed that star and recovered, actually, pretty much exactly the same resource as us, the same dip, the same wobble of the planet. A third team looked at it and they actually got something different. They saw the dip was diminished compared to what we saw. They saw a little hint of a dip, but not as pronounced as what we saw, and they saw the wobble as well. There's been a little bit of tension about analyzing the reduction of the Hubble data. The only way in my mind to resolve this is just to look again. We actually did propose to Hubble straight after that. We said, look, if our model is right, if the Moon is there, it came in late last time. It transited after the planet. Because of the orbit, we can calculate that it should transit before the planet next time. If it's not there, if it doesn't transit before, and even if we see a dip afterwards, we know that's not our Moon. It's obviously some instrumental effect with the data. We had a causal prediction as to where the Moon should be. I was really excited about that, but we didn't get the telescope time. Unfortunately, if you go further into the future, we no longer have the predictive capability because it's like predicting the weather. You might be able to predict the weather next week to some level of accuracy, but predicting the weather next year becomes incredibly hard. The uncertainties just grow and compound as you go forward into the future more and more. </s>

<s>[INST] So how much knowledge is there do you think? So? It's you said it's possible [/INST] there's a tremendous amount of detailed knowledge in the world there. You know, you can imagine, you know, effectively infinite number of unique situations and unique configurations of these things. But the knowledge that you need, what I refer to as like the frameworks for you need for interpreting them. I don't think, I think that's those are finite. </s><s>[INST] You think the frameworks are more important than the bulk of the not so like framing. [/INST] Because what the frameworks do is they give you now the ability to interpret and reason and to interpret and reason to interpret and reason over the specifics in ways that other humans would understand. </s><s>[INST] What about the specifics, [/INST] you know, you require the specifics by reading and by talking to </s><s>[INST] other people. So mostly actually just even if you can focus on even the beginning the common sense stuff, the stuff that doesn't even require reading or it almost requires playing around with the world or something. Just being able to sort of manipulate objects, drink water and so on all, does that every time we try to do that kind of thing in robotics or ai it seems to be like an onion, you seem to realize how much knowledge is really required to perform even some of these basic tasks. Do you have that sense as well? And so how do we get all those details? Are they written down somewhere idea, they have to be learned through experience. [/INST] So I think when like if you're talking about sort of the physics, the basic physics around us, for example, acquiring information about acquiring how that works um Yeah I think I think there's a combination of things going, I think there's a combination of things going on. I think there is like a fundamental pattern matching, like what we're talking about before you see enough examples enough data about something, you start assuming that and with similar input, I'm gonna predict similar outputs. You don't can't necessarily explain it at all. Um You may learn very quickly that when you let something go it falls to the ground. </s><s>[INST] That's that's just such a [/INST] can't necessarily explain that, </s><s>[INST] but that's such a deep idea that if you let something go like the idea of gravity, [/INST] I mean people are letting things go and counting on them falling well before they understood gravity, </s><s>[INST] but that seems to be uh that's exactly what I mean, is before you take a physics class or uh or study anything about Newton, just the idea of the stuff falls to the ground and you'll be able to generalize that all kinds of stuff falls to the ground. It just seems like a non if without encoding it like hard coding it in. It seems like a difficult thing to pick up. It seems like you have to have a lot of different knowledge to be able to integrate that into the framework into everything else. So both know that stuff falls to the ground and start to reason about socio political discourse. So both like the very basic and the high level reasoning decision making. I guess the question is how hard is this problem? And sorry to linger in it because again, and we'll get to it for sure. As Watson with jeopardy did is take on a problem that's much more constrained but has the same hugeness of scale, at least from the outsider's perspective. So I'm asking the general life question of to be able to be an intelligent being and recently in the world about both gravity and politics. How hard is that problem? [/INST] So, I think it's solvable. Okay, </s><s>[INST] now, beautiful. So what [/INST] about </s><s>[INST] what about time travel? Okay, I'm not, I'm not, I'm not as convinced. Not as convinced yet. [/INST] No, I I think it is, I think it is solvable. I mean, I think that it's a first of all, it's about getting machines to learn, learning is fundamental and I think we're already in a place that we understand for example how machines can learn in various ways right now, our learning are learning stuff is sort of primitive in that we haven't sort of taught machines to learn the frameworks, we don't communicate our frameworks because of our shared in some cases we do, but um we don't annotate if you will all the data in the world with the frameworks that are inherent or underlying our understanding instead we just operate with the data. So if we want to be able to reason over the data in similar terms in the common frameworks, we need to be able to teach the computer or at least we need to program the computer to acquire to have access to and acquire learn the frameworks as well and connect the frameworks to the data. I think this, I think this can be done, I think we can start, I think machine learning for example with enough examples can start to learn these basic dynamics, will they relate the necessary to gravity? Not unless they can also acquire those theories as well and put the experiential knowledge and connected back to the theoretical knowledge. I think if we think in terms of these class of architectures that are are designed to both learn the specifics find the patterns but also acquire the frameworks and connect the data to the frameworks. If we think in terms of robust architecture is like this, I think there is a path towards getting there </s>

<s>[INST] Yeah, I'm really glad you're talking about it because it's probably important to understand. I'm also hopeful that as people get educated about how much their data when collected unencrypted but in general can be used to harm them. I mean it's almost like an education is I feel like if you know it's a double edged sword because I feel like people become fearful too easily and that actually has a very negative effect on the quality of life in some sense you want to have tools that allow you to live freely as opposed to live in fear. If you live in fear it's not a good way to live. So it's a it's a balance. Um [/INST] it's a free society versus a fierce society. People are, it's all about the trade offs you make in your daily life like living more privately with more freedom is less convenient. You trade freedom and privacy for convenience and comfort and speed. Absolutely. It's an engineering decision and everything that you do. Um, in the West we in advanced democracies, we have not necessarily personally seen the results of that trade off because we've we live in these free societies that have these checks and balances and freedoms. But as soon as you step into an authoritarian state and you make those trade offs, your life, you know, immediately becomes more more restrictive. And what people are worried about is that even in advanced economies, market democracies, etcetera, the people are worried that they might not survive the great social digital transformation. Um, you know, look at what the NSA is capable of doing. I mean for now not that big of a problem because we still have free speech. Um, but it's deeply concerning what Snowden revealed. And it's a nice reminder that we need to be focused on on privacy and encryption and on helping users become more, more sovereign regardless of where you live. It's kind of like a crutch to live in a free society. Like, you know, it's almost like a free lunch in a way. Um, you're not going to be sent to a prison camp because of the color of your skin or your beliefs or what you say about the government. Um, and you're very lucky again, most people do live in a society where you you can be persecuted for those things. And I feel like especially in America we we forget that we're distanced from that really strong reality, you know, </s><s>[INST] on the topic of Snowden. And then, and I say, what should we be thinking about? Because that feels like already an outdated set of conversations because of the information we've gotten from the past. It feels like everything's gotten quiet now in terms of how much you actually know about the [/INST] hugely important. I think the two lessons from Snowden or a the patriot act and the war on terror and mass surveillance are not necessary for our democracy and for our freedoms. Um this was a false choice. We never had to sacrifice them to be safer. Um and and we've seen that government has spent hundreds and hundreds of millions of dollars on these like surveillance programs that you can read about it and amounted to very little except for tremendous bureaucratic waste and you know, you know, erosion of our freedoms. Um, but at the same time we, we need to practice more privacy and the dramatic increase in the usage of signal for example has been really, really great to see. It's fantastic that tens of millions of people are downloading signal and using it. You should try to be on boarding more and more of your conversations on to signal. For example, where governments can't see what you're saying. Maybe they can see the metadata, maybe they can see that you sent your phone number, sent a message to someone else's phone number at this time. They can't see what's inside. So using encryption in your life is very very important. That's a good starting point I would say that's kind of step a </s><s>[INST] the ideas of democracy, the ideas of the balance of power. Um The all the ideas that we were talking about the constructs more inventions. I wonder if there's other inventions that will allow us to sort of not engage, not give governments or any centralized institutions so much power. Like why why do citizens have to use signal? Why? Because it's an effort you have to be because you have to like understand exactly why. So that's a nice little solution for a particular set of problems. But like there's a million other ways that data I'm sure is being collected constantly. If we don't create a system that prevents the establishments of the centralist powers, then we'll always have this problem. [/INST] Yeah. I think we can keep it simple for the purposes of this conversation. You have politics, information and money. Those are the three things I would encourage us to focus on in politics. Yes, someone invented democracy. I mean whether it was the Greeks. Um the west Africans are many others around the world around the same time invented this idea that we should be ruled by rules and not by rulers. Right? Um and that has evolved dramatically right? And now and then you have information, information also used to be highly centralized, right? You know think about how rich you had to be to gain access to a library before the printing press or you know how much money you had to have or how close to the king or the feudal lord you had to be to be able to have that ability. But now you know the majority of the world, billions of people have access to all information in their pocket and they can set up an account on social media and get the word out. So not only politics but information has been dramatically decentralized. Um and I would say that encrypted messaging is kind of a corollary to that second innovation and as much as now people are like more effortlessly like signal is a lot easier to use than PGP for example, they're more easily able to practice privacy when it comes to having private messages globally. Um these are all good things and we need to keep pushing and I think money is like honestly maybe the most important piece and that's why I spend so much time thinking about Bitcoin. </s>

<s>[INST] one key little aspect that's deeply important to me and we'll go in that topic. Next is uh the World War Two mentality wasn't just about, you know, breaking all the rules to get the job done. There was a togetherness to it. There's so I would if I were president right now it seems quite elementary to unite the country because we're facing a crisis, it's easy to make the virus the enemy. And it's very surprising to me that the division has increased as opposed to decrease. Yeah. Well that's that's that's heartbreak. [/INST] Yeah. Well look, I mean it's been said by others that this is the first time in the country's history that we have a president who does not even pretend to, you know, want want to unite the country, right? Uh you know, I mean, I mean, I mean Lincoln who fought a civil war, you know, you know said he wanted to unite the country, right? Uh you know, and and I do I do worry enormously about what happens if the results of this election are contested. You know, and you know, will there be violence as a result of that? And will we have a clear path of succession? And you know, look, I mean, you know, this is all we're going to find out. The answers to this in two months. And if none of that happens, maybe I'll look foolish. But I am willing to go on the record and say I am terrified about that. </s><s>[INST] You have been reading the rise and fall of the 3rd Reich it. So if I can this this is like one little voice uh to put out there that I think november will be a really critical month for people to breathe and put love out there. Do not you know, anger in those in that context, no matter who wins, no matter what is said, will destroy our country, may destroy our country, may destroy the world because of the power of the country. So it's really important to be patient, loving, empathetic. Like one of the things that troubles me is that even people on the left are unable to have a love and respect for people who voted for trump. They can't imagine that there's good people that could vote for the opposite side and that. [/INST] So I know there are because I know some of them, right? I mean, you know, it's still, you know, maybe it baffles me, but you know, I I know such people, </s><s>[INST] let me ask you this. It's also heartbreaking to me on the topic of cancel culture. So in the machine learning community, I've seen it a little bit that there's um aggressive attacking of people who are trying to have a nuanced conversation about things. And it's troubling because it feels like nuanced conversation is the only way to talk about difficult topics. And when there's a thought police and speech police on any nuance conversation that everybody has to like in uh Animal Farm chant that racism is bad and sexism is bad, which is things that everybody believes and they can't possibly say anything nuanced. It feels like it goes against any kind of progress for my kind of shallow perspective. But you've written a little bit about cancel culture. Did you have thoughts that? Well, [/INST] look, I mean, I mean, I mean to say that I am opposed to, you know, the this trend of of cancelations or of you know shouting people down rather than engaging them that would be a massive understatement, right? And I feel like, you know, I have put my money where my mouth is, you know, not as much as some people have, but you know, I've tried to do something. I mean I have defended you know, uh some unpopular people and unpopular, you know, ideas on my blog, I've, you know, tried to defend, you know, norms of uh of of of open discourse of you know, reasoning with our opponents, even when I've been shouted down for that on social media, you know, called a racist called a sexist all of those things and which by the way, I should say, you know, I would be perfectly happy to, you know, so you know, if we had time to say, you know, you know, 10,000 times, you know, my hatred of racism, of sexism, of homophobia, right? But what I don't want to do is to cede to uh some particular political faction, the right to define exactly what is meant by those terms to say. Well then you have to agree with all of these other extremely contentious positions or else you are a misogynist or else you are a racist, right? I say that Well, no, you know, you know, don't like don't I or you know, don't people like me also get a say in the discussion about, you know, what is racism about what is going to be the most effective to combat racism, right? And you know, this this this um cancelation mentality I think is spectacularly ineffective at its own professed goal of, you know, combating racism and sexism, </s><s>[INST] what's the positive way out. So I try to I don't know if you see what I do on twitter but on twitter, I'm mostly on in my whole, in my life. I've actually who I am to the core is like I really focus on the positive and I try to put love out there in the world and still I get attacked and I [/INST] look at that and I wonder like you too, I didn't know like I </s><s>[INST] haven't actually said anything [/INST] difficult </s><s>[INST] and nuanced. You talk about somebody like steven [/INST] pinker </s><s>[INST] who I'm actually don't know the full range of things that he's attacked for. But he tries to say difficult, [/INST] he tries to be thoughtful about </s>

<s>[INST] Yes. So maybe maybe I don't know is the honest answer for everybody around the table, but the biggest question for which the, I don't know is the right answer is uh, what's the meaning of this whole thing? What's the meaning of life. No, you're not allowed to say, I don't [/INST] know. </s><s>[INST] You can, I'll be just like your dad and say, let me just give my two cents, [/INST] take it for whatever it's worth. Take it or leave it, it's probably worth nothing piddle on the ground. Um, I </s><s>[INST] mean, what, what? Why are we here? It's just busily creating all these kinds of things, worrying about things, having kids. [/INST] I my purpose, at least right now, is to wake up and try to bring light, love to the world, light, love to myself and have integrity. That's my purpose. Um the ultimate purpose of life. That I guess that's my ultimate purpose of life. I don't know what happens when I die. Ayahuasca gave me some sense that there's more to be known. I'm sure there are other things in life that would give me that. And I'm and I'm looking I'm looking for it. I'm a seeker. Like, I'm I'm always looking for the next something to give me hope in something more? Even if so, I could just not bullshit my kids when they ask me that question and be like, you know what, I really don't know, I wanna not no more. That makes sense. I don't want to, like, I want to see things that make me confused that make me question what I already knew. Like I and like, when I meet an atheist who comes up to me and they're like, Atheism, Atheism? Atheism, it's just as laughable to me, is when I meet the mormon who comes up and they're like, mormonism, mormonism, mormonism. I'm like, how do you how do anyone, how do you guys know that? Like, like, and you know, </s><s>[INST] so you feel like you're doing some through all your travels to all the people you meet, you feel like you're still keeping your eyes open and your heart open to sort of, discover, discover something new, like the ayahuasca experience that there might be, there might be deeper truths out there. [/INST] Yeah. And I want to find him and I want to surround myself with people who are just looking for it. I'm not I'm not interested in people who are just looking to point fingers at each like, life is so short I'm looking for. It's one of the reasons that I want to meet with you is I was like, wow, Lex really seems like he's on a journey to find truth and that humility for me, the same thing with rick. It drew me to rick. It was like, I really, I I see that and identify with it and that's what I'm looking for. There's the final song on our record, our new record that's coming out. The chorus goes, um and this is like, this is my best answer to to what to what you're asking um of course goes, take it easy on me. I need some lullaby, they tell me heaven's just a lie. Well, I'm not surprised. Tell me that, you know? No, you don't Yeah, you're just like me. Can we just hope for the best? Take it easy. That's it for me. It's like, I'm gonna place from like, I don't know, tell me, you know, I'm not gonna believe you. Maybe you do. I'm not gonna believe it, but like, just just be easier on each other and like try to find truth wherever it may lie. But above all know that we don't know Jack shit. </s><s>[INST] I think that's a mic drop moment, dan. Thank you so much. You're an incredible human. I love that you share with the world the darkness of your mind, of your life, experience, in the in the beautiful light that you've shown to the world. So it's a huge honor and thank you for spending your valuable time. Good luck on the tour. [/INST] Thanks man. Thanks for having me. </s><s>[INST] Thanks for listening to this conversation with dan Reynolds to support this podcast. Please check out our sponsors in the description and now let me leave you with some words from Aldous Huxley after silence. That which comes nearest to expressing the inexpressible is music. Thank you for listening and hope to see you next time [/INST] </s>

<s>[INST] That's one of the difficult things. When I think about Hitler, I think Hitler Stalin, I don't know if World War One quite has the same intensity of controversial leaders, but one of the sad things from a historian perspective is how few interviews Hitler has given or Stalin has given and that's such a difficult thing because it's obvious that talking to donald trump that talking tradition, ping talking to Putin is really valuable from a historical perspective to understand. But then you think about the momentary impact of such a conversation and you think, well, depending on how the conversation goes, you could steer or flame, what does it feed the flame of war or conflict or um abuses of power and things like this. And that's I think the tension between the journalist and the historian because when journalists interviewed dictators, for example, one of the things that strikes me is there often very critical of the dictator, they're they're they're like um they're basically attacking them in front of their face as opposed to trying to understand. Because what I perceive they're doing is they're signaling to uh the other journalists that they're on the right side of history kind of thing. Um but that's not very productive and it's also why the dictators and leaders often don't do those interviews. Uh it's not productive to understanding who the human being is to understand, you have to empathize. Um because few people, I think few leaders do something from a place of malevolence. I think they really do think they're doing good and not even for themselves, not even for selfish reasons. I think they're doing great for the they're doing the right thing for their country or for whoever the group they're leading and to understand that you have to and by the way, a large percent of the country often supports them, I bet if you pull legitimately pull people in North Korea, they will believe that their leader is doing the right thing for their country. Um And so to understand that you have to empathize. So that's the tension of the journalist I think and the historian because obviously the historian doesn't doesn't care. They really want they care obviously deeply, but they know that history requires deep understanding of the human being in the full context. Uh yeah, it's a tough decision to make. Well [/INST] I think it's both for journalists and historians, the challenge is not to be too close to your subject, right? Um and you know, not to be um overly influenced and used by them, right, you know, when you're talking to a living subject, which historians do, you know, um to um you know, it's it's a matter of making sure that you triangulate their story with with the rest of the record, right? Um and that may paint a different picture of of the person than um and will prevent you as a journalist or a historian from kind of, you know, just telling someone else's story. And and so and historians also have the benefit of going back, you know, 30, 40 years and finding all the other stories and figuring out, you know, uh playing two truths and a lie, you know, which parts are, you know, which parts are accurate, which are which are not. And journalists do that work in a day to day basis. But historians, um you know, we get a little more time to think about what we're doing. </s><s>[INST] Well, I I personally also think it's deeply disrespectful to the populace to people to um censor and ignore a person that's supported by a very large number of people like that. You oh, I personally feel like you owe the citizens of this country a deep empathy and understanding of the leaders they support, even if you disagree with what they say. I mean, that's the the to me, I'm much more worried about the resentment of the censorship, that it's to having a good conversation with donald trump is ultimately valuable because he I think especially in this case, I agree with you that donald trump is not a singular person. He is a he represents a set of feelings that a large number of people have and whatever those feelings are, you can try to figure out by talking to people, but also talking to the man and then seeing the interplay there. What does this really represent in this period in history, in this slice of the world? Um yeah, ultimately understanding, I think leads to compassion and love and unity, which is how this whole thing progresses. The tension between the different sides is useful to um have a good conversation but ultimately coming up with the right answer and progressing towards that answer is is how you make progress. Do you think a pure democracy can work? So we have this representative democracy with these contentious elections and so on. When we started civilization on MARS, which becomes more and more realistic, technologically we can have a more direct access to be able to vote on issues and vote for ideas. Do you think it can work? I [/INST] don't think we have to go to MArs to do it. Right. Um I think um the answer is not, you know, to flip a switch and turn on something called pure democracy. Um uh when people are not ready for it, when their incentive structures are not sort of structured for it. But you can, you know, experiment with more democratic forms of governance one after another, right? Whether it's um you know, sort of experimenting with technology to find new ways of sort of getting greater rates of participation in democracy. Um I think that we see some experiments in sort of more complicated systems of voting um that in fact might actually be more reflective of people's choices than simply picking one candidate, right, sort of ranked choice voting or run offs other kinds of things. Um You know, I think that we can think more creatively about something like participatory budgeting right, in which, you know, we put all this money into the government um and then um you know, we we you know, should as a as a people that are more democratic ways of of sort of how we spend it. And I think the most urgent in some level is a more democratic form of foreign policy making, right? The foreign policy making, decision making about the military, about foreign policy um is is very ways insulated from from popular participation in in modern american history. And I think you know, there uh technology is not the </s>

<s>[INST] Do you have an intuition about why is the FDA trying to get 75 years To release the fighter data? They're trying to request that we will not be released for 75 years. And then maybe the broader version of that question is, do you think people should have sort of, uh, full transparency and immediate access to the data Immediate, You know, on the scale of weeks, not years, [/INST] I think the relations with with regulators there have been always very transparent. And there are a lot of, uh, laws that, uh, they are forcing, uh, regulators to and companies to put out their their interactions And what exactly was discussed now to go into specific details of some discussions? I don't know. What is the reason that FDA wants to take the time, and I'm sure they have very good reasons. </s><s>[INST] Well, let me just say my side of it. It doesn't look like a good reason. It looks like maybe it's because I come from the Soviet Union. Now, this is not you saying this. This is me saying this, um is there seems to be a bureaucracy that gets in the way of transparency. That's always the challenge with government. So government is very good at setting rules and making sure there's oversight of companies and people and so on. But they create they slow things down, which is a feature and a bug, And in this case they slowed down so much. I think the reason they said at 75 years is because they set a rate of being able to only review 500 pages of data a day or something like that. And it's a very kind of bureaucratic thing, or in reality, you could just show the data and it's not like something is being hidden. But in the battle to win people's trust, to inspire them with science, it feels like transparency is one of the most beautiful things. One of the most powerful things that the FDA has FDA has the potential to be one of the great institutions of our country, and this is one example that it feels to me like a failure from your perspective. You're saying I'm sure they have a good reason so to you. The FDA is this black box that you submit things to once they approve. You know that those are the rules. It's approved. That's it. [/INST] But this is not a black books. We know very well. What is the process. Everybody knows very well what are the processes, the review process. Also it is very detailed. They have Scientists are very, very high caliber. Not every regulator in the world, but the Europeans, the bridge, the FDA. Clearly they have very, very high caliber of science that they are going into a lot of details. And also basically everything for a study is really released by law in the specification of the product. That is a very detailed document. But it is issue and has basically the essence of everything was discussed. I don't know about specific documents have take them time to release, But clearly this is not a black box type of process. </s><s>[INST] A lot of this stuff is how do you effectively communicate to the world about the incredible science that's been done about the processes that were followed? [/INST] And I agree with you, </s><s>[INST] and sometimes it's just in eloquence in communication. It's not that there is a failure of process. It's in eloquence, communication in silence, silence in the moment when clearly a lot of people are bothered and have questions. This is when you speak out and you explain exactly why, as as opposed to letting the sort of distrust build up and linger, because the result is there's a very large percentage of the population that just, um I mean, it divides people. And science suffers, I think. And also the effectiveness of solutions suffers, like the vaccine and so on. Yeah, I asked a few folks, I know if they had challenging questions for you, [/INST] I'm sure many of them answer your called. </s><s>[INST] Uh, yeah, you know, many friendly folks out there, by the way. I'm sweating. Not because this is a difficult conversation. It is. But it's also hot in here for the record. So one of the folks is Mr Jordan Peterson. I don't know if you know who that is. He's a psychologist and intellectual and author. He suggested to me that I raised the concern that there is a close working relationship between fighter, FDA and CDC. So we we talked about F D a. Do you worry that this affects both positive and negative. Uh, fighter's chances of getting drugs approved. The fact that there's people you know that worked at the FDA that not work a fighter fighter, f d A. That there's a kind of pipeline. Does this worry you that it affects your ability to do great, unbiased work? [/INST] I have zero doubts that this is not affecting at all. Their ability to be unbiased and regulate and in order to for the system also reinforces that by creating significant time barriers if someone moves from an industry the f d a, she won't be able to deal with topics for a period of time and then for even an enhanced period of time with topics that are related with the company he or she may come from. I think this, uh, regulators. They are really very strict, rightly so. If anything, I feel sometimes that maybe they should be a little bit more open minded particular when it comes to new technologies, rather than trying to judge and implement the same framework of evaluation of new technologies to all they are always as regulators in the conservative side. But always always, they are unbiased, and they are trying the best. And it's not only one or two people. They have processes To make sure that there are self checks and balances within the agencies, both in CDC and in the FDA, difficult decisions they bring external experts that they should express easy decisions, their internal experts that they are debating a lot, and if there are disagreements, they elevate them. So I think it's we are lucky to have good regulators. I think I agree with what you said before. As with all governmental agencies, there is bureaucracy, and the bureaucracy needs to be addressed and by saying bureaucracy is not relaxing the the bar, the bar needs to remain high. But uh, being, uh, focusing on what matters rather than on the on the detail. </s>

<s>[INST] The following is a conversation with Stephen [/INST] Kotkin, his second time in the podcast, Stephen is </s><s>[INST] one of the greatest [/INST] Historians of all time specializing in 20th and 20 </s><s>[INST] 1st Century History of Russia [/INST] and eastern europe, and he has written what </s><s>[INST] is widely considered to be the definitive biography of [/INST] Stalin in three volumes, 2 </s><s>[INST] of which have been [/INST] Published and the 3rd focused </s><s>[INST] on World War Two [/INST] and the years after he is in the midst of writing. Now, </s><s>[INST] this conversation includes a response [/INST] to my previous </s><s>[INST] podcast episode with Oliver [/INST] Stone that was focused on Vladimir Putin and the war in Ukraine </s><s>[INST] steven provides a hard hitting criticism of Putin [/INST] and the Russian invasion of Ukraine wade and contextualized deeply in the complex geopolitics and history of our world, all with an intensity and rigor, but also wit and humor. That makes </s><s>[INST] Steven one of my favorite [/INST] human beings. Please also allow </s><s>[INST] me to mention [/INST] something that has been apparent and has weighed heavy on my heart </s><s>[INST] and mind [/INST] this conversation with Stephen Kotkin makes </s><s>[INST] it more dangerous for [/INST] me to travel in Russia. The previous conversation </s><s>[INST] with Oliver Stone [/INST] makes it more </s><s>[INST] dangerous for me to travel in Ukraine. [/INST] This makes me sad, but it is the way of the world. I will nevertheless travel to both Ukraine and Russia. I need to once again see with my own eyes the land of my ancestors where they suffered but flourished and eventually gave birth. The silly old me. I need to hear directly the pain, anger and hope for both Ukrainians and Russians, I won't give details to my travel plans in terms of location and timing but the trip is very soon whatever happens, I'm truly grateful for every day I'm alive and I hope to spend each such day adding a bit of love to the world. I love you all and now a quick few second mention of each sponsor. Check them out in the description. It's the best way to support this podcast. We got lambda for hardware for deep learning and we got scale for data, data annotation for deep learning, then we also have a threat of greens for performance, Express VPN for privacy and ROCA for style, choose wisely my friends and now onto the full it reads 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 lambda computers, workstations, laptops, servers, cloud compute all for deep learning. Great both for individual researchers and huge companies. Lambda has created easy plug and play access to very powerful computation. I actually have one of their newly released laptops that I've been using for machine learning. Both the training and the influence side of machine learning. I've been thinking of doing a video on this laptop because I think it's the coolest thing ever. Honestly, it's already comes with a ban to all configured for tensorflow and pytorch all the things you need for machine learning already pre installed. I think they also have Windows machines. But this one is Linux which is the best operating system and the os of champions if I may say so anyway, I've been thinking of doing a video on it just to give people some insight into the machines that are part of my life because they do make my life easier. But they also mean a lot to me, I don't know, I spent so many hours behind computers that in a small way or maybe a big way, they do bring a lot of joy to my heart, especially when those computers are doing machine learning, which is the thing I'm deeply passionate about. Anyway, check out lambda at lambda labs dot com slash flex. This episode is also brought to you by scale the machine learning assisted data labeling, platform scale rapid works with any use case or task including image, video, text, annotation and classification three D data and it supports 20 plus languages. I've said this before. I'll say it again and again and again, I think in most cases in most real world applications, the particular neural network architecture that you use a particular model, the particular pipeline doesn't matter nearly as much as the quality of the data that's used for labeling for training the machine learning systems. The neural networks, there are cases actually where there's breakthrough performance on the algorithm side, but they're rare. That's actually why open a eyes Dolly too. So interesting because ultimately the architecture innovation is what provided the improvement, but actually I don't know how much data improvement there is too. But in any case in most real world application data is everything like 99% of applications. So if you want to have real world impact, make sure your annotation is done well is done at scale, but not just quantity, it's also quality. So go to scale dot com slash lex today, you can get your first batch of data labeled up to 50 bucks for free. Again, that's scale dot com slash lex. This show is brought to you by athletic greens and it's a G one drink, which is an all in one daily drink to support better health and peak performance. It replaced the multivitamin for me and went far beyond that, 75 vitamins and minerals. It's the first thing I drink every day. I drink it multiple times a day often, especially when I'm doing crazy workouts like I will be Tomorrow and I did two days ago. So running about 12 to 15 miles after I returned home sort of exhausted hard because it's austin in the summer Or almost summer, but it's, you know, you're talking about 90°, 100° weather, a pop of the threat of greens in the fridge or the freezer actually take a quick shower pop out of the shower and then it's just nice and chill and it's delicious and it's refreshing and it when I take it I just feel better about my life about my health, about everything in this world. It ensures that I have the nutritional basis for both the diet and the physical and mental pursuits that I take on anyway. Uh they'll give you a one month supply of fish oil as well when you sign up at athletic greens dot com slash lex fish oil is one of the only other supplements I take. Actually. It's really the only supplement. So I have also the electrolytes fish oil and a flood of greens and given all that I have all my bases covered. So athletic greens dot com slash lex. Mhm. This show is also brought to you by Express V. P. M. I don't know why I love Express VPN so much. I've loved him for many, many years, way before I had a podcast or any of that. Um it was just a simple button and it was a kind of liberating statement privacy in this world of the internet where everybody is watching you, where the big companies are watching you, they're tracing you, they're tracking you all that kind of stuff. You need protection and that's what I mean. Some of that is just psychologically but also technically I just press the button and I feel more protected and I in fact am more protected because SB still track your data even if you use sort of incognito mode on chrome to browse all the shady websites you do, you can also change location to watch different shows that are geographically restricted. Most importantly for me, it just works. It works fast in terms of both bandwidth. In terms of software popping up works any operating system like Linux, all of your mobile devices as well. You can go to express VPN dot com slash legs pod to get an extra three months free and we together, my friend will be using the same software to press that big sexy button and put the cloak of uh, privacy protection around us. That's express VPN dot com slash flex pod. This show is also brought to you by Roca, the makers of sexy glasses and sunglasses that I love wearing for the design and feel and innovation on material optics and grip Rocca was started by two all american swimmers from stanford, one of whom I've met. He's a really awesome dude here in Austin. They have a location where they do some of the design. I think they do manufacture here too. I don't know the point is all the people I met there are awesome and the vision of the company, the mission of the company is beautiful. It's, they're obsessed with performance, how the thing feels that it's lightweight, you can exercise in any weather conditions, but you also want the thing to look sexy and stylish, which it does, especially like the sunglasses with the minimalist sleek design and I wear them when I run. I wear them when I go out. That means dress shirts also suits all that kind of stuff. Or t shirt. If you know me, you know that I don't have much variety in fashion, but I stick to the old true standards. A black shirt and jeans, suit and tie, black suit and tie. And maybe if I want to dress down, it'll be a black dress shirt with dress pants. The variety is overwhelming. See there's three outfits. What else do you need in life? Anyway, it holds up in all conditions, including Austin summer weather, check them out for both prescription glasses and sunglasses at roca dot com And enter code lex to save 20% on your first order. That's rocket dot com. And enter code lex. This is the lex Friedman podcast and now Dear friends! Here's Stephen Kotkin. Yeah, </s>

<s>[INST] So you you you phrased a few concept really eloquently. So let me try to uh As a few directions. This goes. So 1 1st on the way we write software today, it's not common that we allow it to self modify. [/INST] But we do have that ability. Now </s><s>[INST] we have the ability, it's just not common. It's not just common. So so your your thought is that that is a serious worry if there becomes uh [/INST] it's self modifying code is available now. </s><s>[INST] So there's there's different types of self modification, right? There's a personalization, you know, your email app, your gmail is uh self modifying to you after you log in or whatever you can think of it that way but ultimately central. All the information is centralized but you're thinking of ideas where you're completely so this is a unique entity operating under selective pressures and it changes [/INST] you just if you think about the fact that our immune systems, I don't know what's coming at them next, but they have a small set of spanning components and if it's if it's a sufficiently expressive system in that any shape or binding region can be approximated with with the lego that is present. Um then you can have confidence that you don't need to know what's coming at you because the combinatorics um are sufficient to reach any configuration needed. </s><s>[INST] Uh Oh, that's a beautiful thing. Well, terrifying thing to worry about because it's so within our reach. Sure. [/INST] Whatever I suggest these things, I do always have a concern as to whether or not I will bring them into being by talking about them. </s><s>[INST] So uh there's this thing from open ai so uh next next week to talk to the founder of open ai ah this idea that they're text generation, the new uh new stuff they have for generating text is they didn't want to bring it, they didn't want to release it because they're worried about [/INST] the I'm delighted to hear that, but they're going to end up releasing. </s><s>[INST] Yes. So that's the thing is I think, talking about it. Um well, at least from my end, I'm more a proponent of technology preventing techno uh so further innovation, preventing the detrimental effects of innovation. Well, [/INST] we're in a we're sort of tumbling down a hill at accelerating speed. So whether or not we're proponents or it doesn't really it may not matter. </s><s>[INST] But not. [/INST] Well, I do feel that there are people who have held things back and uh you know, died poorer than they might have otherwise been. We don't even know their names. I don't think that we should discount the idea that having the smartest people showing off how smart they are by what they've developed. Maybe a terminal process. I'm very mindful in particular of a beautiful letter that Edward Teller of all people wrote to Leo Szilard, where's Dillard was trying to learn how to control the use of atomic weaponry at the end of World War Two. And tell her rather strangely because many of us view him as a monster um showed some very advanced moral thinking, talking about the slim chance we have for survival and that the only hope is to make war unthinkable. I do think that not enough of us feel in our gut what it is we are playing with when we are working on technical problems and I would recommend anyone who hasn't seen it. A movie called The Bridge Over the Bridge on the River Kwai about I believe captured british POWs who just in a desire to do a bridge well, end up over collaborating with their japanese captors. </s><s>[INST] Well, now you're making me uh, question the unrestricted open discussion of ideas in ai [/INST] I'm not saying, I know the answer. I'm just saying that I could make a decent case for either or need to talk about this and to become technologically focused on containing it or need to stop talking about this and try to hope that the relatively small number of highly adept individuals who are looking at these problems is small enough that we should in fact be talking about how to contain them. </s><s>[INST] Well, the way ideas, the way innovation happens, what new ideas develop. Newton with calculus, whether if he was silent, the idea would be, would emerge elsewhere in the case of Newton of course. But uh, you know, with the case of ai, how small is the set of individuals out of which such ideas would arise? [/INST] Uh, well, the, the idea is that the researchers we know and those that we don't know, who may live in countries that don't wish us to know what what level they're currently at our very disciplined in keeping these things to themselves, of course I will point out that there's a religious school in Corolla that developed something very close to the calculus, certainly in terms of infinite series in um, and I guess religious prayer uh, and uh, and rhyme and prose. So, you know, it's not that Newton had any ability to hold that back. And I don't really believe that we have an ability to hold it back. I do think that we could change the proportion of the time we spend worrying about the effects of what if we are successful rather than simply trying to succeed and hope that we'll be able to contain things later. </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] with them, and suddenly they've taken over the space. And I kinda believe that those people, on a different day, could actually do high-effort disagreement. It's just that they're in a certain kind of mood, and a lot of us, just like you said, with a primitive mind, could get into that mood, And it's, I believe it's actually the job of the technology, the platform, to incentivize those folks to be like, are you sure this is the best you can do? Like if you really wanna talk shit about this idea, like do better. Like, and then we need to create incentives where you get likes for high effort disagreement. Because currently you get likes for like something that's slightly funny and is a little bit like mockery. Like, yeah, basically signals to some kind of echo chamber that this person is a horrible person, is a hypocrite, is evil, whatever. That feels like it's solvable with technology. [/INST] Cause I think in our private lives, none of us want that. I wonder if it's making me think that I wanna like, because a much easier way for me to do it just for my world would be to say something like, you know, here's this axis, this is part of what I like about the latter, is it is it's a language that we can use like, specifically what we're talking about is High rung disagreement good, low rung disagreement bad. Right, and so it gives us like a language for that. And so what I would say is I would, you know, you know, I would have my, you know, readers understand this axis, and then I would specifically say something like, please do the, do it but why a favor. And upvote regardless of what they're saying horizontally, right, regardless of what their actual view is. Upvote high rungness? They can be tearing me apart. They can be saying great. They can be praising me, whatever. Up-road high-rungness and down-low-rungness. And if enough people are doing that, suddenly there's all this incentive to try to say, no, I need to calm my emotion down here and not get personal because I'm gonna get voted </s><s>[INST] into oblivion by these people. I think a lot of people would be very good at that. And not only would they be good at that, they would want that, that task of saying, I know I completely disagree with this person, but this was a high-effort, high-rung disagreement. [/INST] And gets everyone thinking about that other axis too. You're not just looking at where do you stand horizontally? You're saying well how did you get there and how are you, are you treating ideas like machines? </s><s>[INST] Are you treating them like little babies? And there should be some kind of labeling on personal attacks versus idea disagreement. Sometimes people throw in both a little bit. And it's like no, there should be a disincentive [/INST] at personal attacks versus idea attacks a little bit. Well, one metric is a respectful disagreement. Just say someone else's Twitter. And I see, you put out a thought. And I see someone say, I don't see it that way. Here's where I think you went wrong, and they're just explaining. I'm thinking that if Lex reads that, he's going to be interested. He's going to want to post more stuff, right? He's going to like that. If I see someone being like, wow, this really shows the kind of person that you become. It shows something. I'm thinking that person is making Lex want to be on Twitter less. It's making him, and so what is that doing. What that person is actually doing is they're putting, is they're actually, they're chilling discussion because they're making it unpleasant to... They're making it scary to say what you think. And the first person isn't at all. The first person is making you want to say more stuff. So, and those are both disagreed. Those are people who both disagree with you. </s><s>[INST] Exactly, exactly. I want to, great disagreeing with friends in meet space is like you're, they disagree with you They could be even yelling at you. Honestly. They could even have some shit talk or it's like personal attacks [/INST] It is still feels good is because you know them well and you know that that shit talk because I guess your friends should talk all the time playing us playing a sport or a game and again it's it's because they know each other well enough to know that this is Fun we're having fun, and obviously. I love you like exactly. You know and and that's that's important online It's a lot harder </s><s>[INST] yeah, that Obviously, I love you that underlies a lot of human interaction. Seems to be easily lost online. I've seen some people on Twitter and elsewhere just behave their worst. And it's like, I know that's not who you are. [/INST] Like, why are you, who is this human? I know someone personally who is one of the best people. Yeah. I'm just, I love this guy. Like, one of the best, like fun, funny, nicest dudes. And he, if you looked at this Twitter only, maybe you'd think he's a culture worrier, or an awful culture worrier. And biased, and just, stoking anger. And it comes out of a good place. And I'm not gonna give any other info about specific, but it comes out- I think you're describing a lot of people this. It comes out of a good place because he really cares about what he, but it's just, I can't square the two. Once you know someone like that, you can realize, okay, apply that to everyone. Cause a lot of these people are lovely people. just bring, even just back in the before social media. </s><s>[INST] You ever had a friend who like- [/INST] I think you're describing a lot of people. Was just like, they had this dickishness on text or email that they didn't have in person. And you're like, wow, like, email you is like kind of a dick. And it's like, it just, certain people have a different </s>

<s>[INST] on the ai front, if we could just link on effort for a second. Uh so your friends with you often talk with you a mosque history, uh did a lot of interesting things together. Um He has a a set of fears about the future of artificial intelligence. A. G I do you have a sense we've already talked about the things we should be worried about with a I do have a sense of the shape of his fears in particular about ai of the which subset of what we've talked about, whether it's creating, you know, it's that direction of creating sort of these giant competition systems that are not explainable, they're not intelligible intelligence, or is it um is it the and then like as a branch of that, is that the manipulation by big corporations of that or individual evil people to use that for destruction or the unintentional consequences? Do you have a sense of where his thinking is on this [/INST] from my many conversations with Dylan? Yeah, I certainly have a model of how how how he thinks. It's actually very much like the way I think also I'll elaborate a little bit. I just want to push back on when you said evil people, I I don't think it's very helpful contact concept evil people. Sometimes people do very very bad things, but they usually do it because they think it's a good thing because somehow other people have told them that that was a good thing or given them incorrect information or or whatever, right? Um uh I have to believe in the fundamental goodness of humanity. That if we educate people well and they find out how things really are, people generally wanted to do good and be good. </s><s>[INST] Hence the value alignment. Of [/INST] course it's it's </s><s>[INST] about information about knowledge and then once we have that we'll uh we'll likely be able to uh do good in a way that's aligned with everybody else who [/INST] thinks Yeah. And it's not just the individual people we have to align. So we don't just want people to be educated to know the way things actually are and treat each other well. But we also need to align other nonhuman entities. We talked about corporations, there has to be institutions so that what they do is actually good for the country they're in and we should align to make sure that what countries do is actually good for, you know, the species as a whole etcetera. Coming back to L. A. On my my my uh understanding of how Ellen sees this is really quite similar to my own, which is one of the reasons I like him so much and enjoy talking with him so much. I think he's quite different from most people in that he thinks much more than most people about the really big picture. Not just what's going to happen in the next election cycle, but Millennia millions and billions of years from now, right? And if you when you look in this more cosmic perspective, it's so obvious. So we're gazing out into this universe that as far as we can tell is mostly dead, with with life being uh almost imperceptibly tiny perturbation. Right? And and he sees this enormous opportunity for our universe to come alive for us to become an interplanetary species mars is obviously just first stop on this cosmic journey. And precisely because he thinks more long term, it's much more clear to him than to most people that what we do with this Russian roulette thing. We keep playing with our nukes is a really poor strategy. Really reckless strategy and also that that we're just building these ever more powerful ai systems that we don't understand. It's also it's a really reckless strategy. I feel Ellen is very much a humanist in the sense that he wants an awesome future for humanity. He wants it to be us that control the machines rather than the machines that control us. You know, And why shouldn't we insist on that they were building them after All right. Why should we build things that just make us into some little cog in the machinery that has no further say in the matter right? It's not my idea of inspiring future either. </s><s>[INST] Yeah. The if if you think on the cosmic scale, in terms of both time and space so much is put into [/INST] perspective whenever I have a bad day, that's what I think about it immediately makes you feel better. What it makes </s><s>[INST] me sad that for us, individual humans, at least for now the right ends too quickly, we don't get experience the cosmic [/INST] scale. Yeah. I mean I think of our universe sometimes as an organism that has only begun to wake up a tiny bit just like when you're in the very first little glimmers of consciousness you have in the morning when you start coming around with the coffee before the coffee even before you get out of bed before you can open your eyes start start to wake up a little bit, you know there's something here, you know uh that's very much how I think of but we are you know those all those Galaxies out there, you know, I think they're really beautiful, but why are they beautiful? They're beautiful because conscious entities are actually observing them, experiencing them through our telescopes. If I, you know, I define consciousness as subjective experience, whether it be colors or emotions or sounds. So beauty is an experience, meaning is an experience purposes and experience. If there was no conscious experience of observing these Galaxies, they wouldn't be beautiful if we do something dumb with advanced ai in the future here and earth originating life goes extinct and that was it for this. If there is nothing else with telescopes in our universe then it's kind of game over for me, beauty and meaning and purpose in the whole universe. And I think that would be just such an opportunity lost frankly. And I think okay, when Ellen points this out, he gets very unfairly maligned in the media for all the dumb media bias reasons we talked about right. They want to print precisely the things about Ellen out of context that are really click baby, like he has gotten so much flack for this summoning the demon statement Yeah, I happen to know exactly the context cause I was in the front row when he gave that talk. He was at MIT. You'll be pleased to know is the aero astro anniversary They had Buzz Aldrin there from the moon landing, whole house crazy auditorium packed with MIT students and he had this amazing Q and A. It might have gone for an hour and they talked about rockets and mars and everything at the very end. This one student was actually hit my class asked before about Ai. Ellen makes this one comment and they take this out of context print that goes viral or is it like with </s>

<s>[INST] Me Ask you about the famine of the 30s. [/INST] Do </s><s>[INST] you think in the Ukraine? [/INST] Yeah. Fun, fun, fun. </s><s>[INST] Similar. A lot of the things you mentioned in the last few sentences kind of echo to that part of human history. [/INST] The door, </s><s>[INST] Do You? No one [/INST] knows about. </s><s>[INST] Well now I've just spent four weeks in Ukraine, there's different parts of the world that still, even if they don't know. [/INST] Yeah, Dutch knew in some sense they had a famine at the end of World War Two. And part of the reason the dutch farmers are so unbelievably efficient and productive is that the dutch swore at the end of World War Two that that was not going to happen again and then they had to scrape land out of the ocean because Holland, that's quite a country, it shouldn't even exist. The fact that it's the world's number two exporter, you know, that is the world's number two exporter of agricultural products, Holland, it's like, I don't think it's as big as massachusetts, This little tiny place, it shouldn't even exist and they want to put here's this, here's the plan, let's put 30% of the farmers out of business. Well, the broader ecosystem of agricultural production in Holland is 6% of their GDP now, these centralizing politicians think, tell me if I'm stupid about this, take an industry, You knock it back by Fiat by 30% now, it runs on like a 3% profit margin. Now you're gonna kill 30% of it. How are you not going to bring the whole thing down, the whole farming ecosystem down? How are you not gonna impoverish the transport systems? How are you not gonna demolish the grocery stores? You can't take something like that and pare it back by fiat by 30% and not kill it. I I can't see how you can do that. I mean look what we did with the covid lockdowns, we broke the supply chains, tried buying something lately, you can and wait and aren't the chinese threatening Taiwan at the moment? What are we gonna do without chips? So I don't know what these people are thinking and then I think okay, what are they thinking? Well the Deloitte people are thinking, aren't we smart and shouldn't we be hired by our corporate employers? It's like okay, too bad about the poor. Um what are the uh environmentalist thinking? We love the planet, it's like, do you, we love the poor, do you? Okay let's pit the planet against the poor, Who wins the planet? Okay, you don't love the poor that much, Do you love the planet or do you hate capitalism, let's put those two things against each other, Oh well it turns out we actually hate capitalism. How can we tell? Because you're willing to break it And you know what's gonna happen? So what's gonna happen in Sri Lanka with these 20 million people who now have nothing to eat? Are they gonna eat all the animals? Are they gonna burn all the firewood? They're stockpiling firewood in Germany. It's like, so is your environmental, globalist utopia, I'm gonna kill the poor and destroy the planet and that's okay because we'll wipe out capitalism. It's like, okay, </s><s>[INST] yeah, the dragon and the fear of the dragon drives ideologies, some of which can build a better world, some of which can destroy that world. [/INST] Now, what do you think of that theory about, about trustworthiness? If the dragon that you're facing turns you into a terrified tyrant, you're not the man for the job. Is that a good theory? </s><s>[INST] It's an interesting theory. Let me use that theory, It's a challenge. Because what, what does terror look like? Let me uh table the turns, turn the tables on you, you are terrified, afraid, concerned about the dragon of something we can call communism Marxism [/INST] by terrified of it. </s><s>[INST] Your theories had two components. [/INST] I'm not paralyzed </s><s>[INST] at a dragon, [/INST] I'm not paralyzed and I don't want to be a tyrant. </s><s>[INST] The tyrant part I think is missing with you. Uh you are very concerned. The intensity of your feeling, uh does not give much space, actually at least in your public persona for sitting quietly with the dragon and sitting in a couple of beers and thinking about this thing. Uh, the intensity of your anger, concern about certain things you're seeing in society, is that going to drive you off the path that ultimately takes us to a better world? [/INST] That's a good question. I mean, I don't, I'm trying to get that right. So we've kind of come to a cultural conclusion about the nazis. Do you get to be angry about the nazis? Seems the answer to that is yes. </s><s>[INST] Well, actually let me push back here. Um, I also don't trust people who are angry about the nazis because [/INST] I mean, the actual nazis. </s><s>[INST] Well, I there's a lot, as, you know, there's a lot of people in the world um, that uh, use actual nazis to mean a [/INST] lot one </s><s>[INST] of them is very important to [/INST] me. For example, It's not magical. Super nazi as it turns out. </s><s>[INST] I think they actually sort of steel men, all their perspectives. I think a lot of people that call you a nazi mean it. [/INST] So, so, </s><s>[INST] but [/INST] like there's </s><s>[INST] an important thing there because I went to the front in Ukraine and a lot of the people uh, that lost their home or their kind of uh, that got to interact a lot with Russian soldiers. Ukrainian people interact with Russian soldiers. Uh, they reported that the Russian soldiers really believe they're saving the people of Ukraine in these local villages from the nazis? [/INST] So </s>

<s>[INST] that term, closed [/INST] cooling change? I imagine that people use it when they describe how they get meat into a supermarket. Right, If you break the cooling chain and starts to saw you in trouble and you have to throw it away. I think it's such a beautiful way to put it. Calling </s><s>[INST] a city a closed social change or something like that. I mean, that's right. I mean, the locality of is [/INST] really what it basically means. You wake up and acclimatized room, you go to work and acclimatized car, you work in your shop and acclimatize supermarket. And in between you have very short distance which you run from your car to the supermarket. But you have to make sure that your your temperature does not approach the temperature of the environment. So the crucial thing is the wet bulb temperature. The temperature is what you get when you take a wet clothes And you put it around your thermometer and then you'll move it very quickly through the air. So you get the evaporation heat and uh as soon as you can no longer cool your body temperature via operation to a temperature below something like I think 35° you die. And which means if the outside world is dry, you can still cool yourself down by sweating. But if it has a certain degree of humidity or if it goes over a certain temperature, then sweating will not save you. And this means even if you're healthy, fit individual within a few hours, even if you try to be in the shade and so on, you'll die unless you have some climate sizing equipment and this itself. If you as long as you maintain civilization and you have energy supply and you have foot tracks coming to your home, that acclimatized everything is fine. But what if you lose a large scale open agriculture at the same time. So basically we run into food insecurity because climate becomes very irregular or whether it becomes very irregular and you have a lot of extreme weather events, so you need to roll most of your, your foot maybe indoor or you need to import your foot from certain regions and maybe you're not able to maintain the civilization throughout the planet to get the infrastructure to get the foot to your home. </s><s>[INST] But there could be so there could be significant impacts in the sense that people begin to suffer. That could be wars over resources and so on. But ultimately, do you, do you not have a, not a faith, but what do you make of the capacity of technology, technological innovation to help us prevent some of the worst damages that this condition can create. So as an example, as a almost out, their example is the work of SpaceX and Elon musk is doing of trying to also consider our propagation throughout the universe in deep space to colonize other planets. That's one technological stuff. [/INST] But of course what the masses trying on MArs is not to save us from global warming because MArs looks much worse than earth will look like after the first outcomes of global warming imaginable, Right? Yeah, essentially not habitable, </s><s>[INST] It's exceptionally harsh environment. Yes, but what he is doing what a lot of people throughout history since the industrial revolution are doing are just doing a lot of different technological innovation with some kind of target and what ends up happening is totally unexpected. New things come up. So trying to trying to reform or trying to colonize mars extremely harsh environment might give us totally new ideas of how to uh expand or increase the power of this closed cooling circuit that that empowers the community. So like do you It seems like there's a little bit of a race between our open ended technological innovation of this ah communal operating system that we have and our general tendency to want to overuse resources and uh thereby destroy ourselves. You don't think technology can win that race. [/INST] I think the probability is relatively law given that our technology is for the US is stagnating since the 1970s, roughly in terms of technology. Most of the things that we do are the result of incremental processes. </s><s>[INST] What about intel? What about moore's law? [/INST] It's basically it's very incremental the things that we're doing so after the invention of the microprocessor was a major thing. Right? Uh The miniaturization of transistors was really major. But the things that we did afterwards largely we're not that innovative, gradual changes of uh scaling things into from Gpu. S into from Cpus and Gpus and things like that. But I don't think that there are Basically there's not many things if you take a person that died in the 70s and was at the top of their game. They would not need to read that many books to be current again. But </s><s>[INST] it's all about books, who cares about books, the there might be things that are beyond books, might be a [/INST] papers or </s>

<s>[INST] up. We'll sort of push back on that if you just look at Iran, I would draw different. So I agree with you mostly, but I would also draw a different distinction when the atrocities happening too, your own people versus there's a war Ukraine is a sovereign independent nation and there's not a war between two nations. It feels like it's easier for journalists to somehow reveal the truth and that when the atrocity is happening within the soviet union, for some reason, that's easier to hide. That's easier for journalists to deceive themselves and easier for the authoritarian leader to hide the and so that's, that's the dark. I mean, that's why people maybe maybe you can educate me on this, but this, this is why I think people don't talk about um, hot um, or and other atrocities, the greatly forward because it's inside the country versus the holocaust that's part of a war. Why, Why is that that we, uh, there were two almost like, uh, afraid too polite to what is it that we don't want to cover the atrocities [/INST] because side </s><s>[INST] the country like it's their business. So we don't want to touch it. That what what is it? I [/INST] think it's that what we refer to as the news is in the business of selling narratives, right? And the narrative of the holocaust is a very powerful one, which is if you let hatred of a subgroup in a population get out of control, this is the ultimate consequence. And this is something that we all have to be scared of and do everything in our power to avoid in the future for any out group. Whereas what's the narrative of the holiday more sometimes governments kill their own citizens. There's nothing you could do about it. There's nothing we I mean, they wouldn't have let us send food, they wouldn't like the newspapers even Russia weren't acknowledging it. Like, what's this? Like, this is some issues I had with regard to trying to advocate for the north korean people. The reporters would be like, well what can I do as an american? It's a very natural question and I'm like, I don't know, I like all I know is how to speak to what is happening. But in terms of next steps, I don't have a good answer for you. So that is where the news kind of does break down if there isn't a story or a call to action? The kind of, you're kind of almost like having a movie with a cliffhanger and there's no sequel. It's like, what am I supposed to do here? Like this is not scratching that itch. Which for me as a consumer of news, you know, Lehman is like, okay, here's the story. There was a bad guy and the cop shot him or they took him to jail and now the bad guys caught beginning middle end here. It's just like mao did this, A lot of people were executed and starved. Isn't that awful? Well, and now still in power now, Richard Nixon is raising a toast to him. Like that story is just like, how am I supposed to feel about this? </s><s>[INST] Yeah. It feels like when there's tanks and there's war and this military conflict then um, it's more actionable. You can cover it. You know, it did seem like Nazi Germany. I don't know if holocaust was the thing that made it most covetable. I think it was that this is a threat to the entire civilization, [/INST] this </s><s>[INST] is that's what makes it comfortable and if the holocaust was happening just inside the country, inside of Germany or even if it didn't expand beyond Poland. Yeah, [/INST] it would be like a footnote. It was in many ways a footnote. Like many of the early steps toward it was like they didn't cover it's just like all right there being oppressive towards their own people, okay. </s><s>[INST] Especially given some of the uh maybe if you negotiate certain peace treaties with the soviet union and with german like your to the basic, the pacifist imperative, oh boy, [/INST] sorry, santa. </s><s>[INST] So we say every time you masturbate, no, after you're done, you know, I'm sorry. Alright, alright now, see I hate it when you don't Yes. And because it leaves me in a hole, I dug for myself um and I sit there in the hole in my sadness. How long have you been writing this book? I mean [/INST] two years </s><s>[INST] mentally. It was like two years since you spent with time with it? What now? [/INST] Almost three, Yeah. </s><s>[INST] And I suppose it stages you much longer, like you said your family. So in many ways this is a book you've been writing your whole life. [/INST] I think that's fair that all my work has been leading to this. </s><s>[INST] Yeah, [/INST] it's certainly the most, in my opinion, the most important thing I've done. What stands </s><s>[INST] out to you about Baltimore, what moments what what aspects of human nature stand out to you? I [/INST] don't know, I think that story is I don't want to say story, but I mean like that incident is I mean, I was familiar with it before, you know what I mean? So I kind of knew about it, you know, in part thanks to kind of the north korean work and coming from Ukraine. Um the thing that was also kind of insane about it is that they were taking all this grain and not using it even to feed the Russian people, they were selling it for export for hard currency. Um </s><s>[INST] I [/INST] think what the takeaway there and I think again this is something westerners and especially americans don't appreciate, they think that evil often has like a logic to it, right? And it's like why would like, because it makes no sense to them, Like why would they kill their own people? Uh therefore it probably didn't happen right there. That there's that thing they really think like, okay, they can understand, you know, country Congress, country B and slaughters a bunch of people country B as a means of conquest. Like that kind of makes sense to them. They know that thing, but like why are you starving all these people? Like what are you gaining out of it? That doesn't make sense to them. And because it doesn't make sense, there's kind of like, well it's probably more the story that I'm hearing and a lot of times there's not it's just like evil for the sake of power. Um and we don't really have that certainly anywhere near that scale and never have um certainly, you know, since it's since America has been a thing, I mean it's it's it's and the fact that this is like the thirties, you know what I mean? This isn't that long ago, but I think also the narrative in some ways is how, </s>

<s>[INST] But do you think it's useful to have a term like the I. D. W. To capture some set of people, some set of ideas or maybe principles that capture what I think the I. D. W. Okay you can say that it's not supposed to mean it doesn't exist. It doesn't mean anything but to the public to me. Okay I'll just speak to me, it represented something uh it represented, I think it's just like this to you. It's my in my first attempt to interview the great eric Weinstein, I said that I spoke about you, but I E. W in general is trying to point out the elephant in the room or that the emperor has no clothes, the set of people that do that in their own way, [/INST] if there are multiple elephants in the room. The point is, is that the I. D. W. Is more interested in seeing the totality of elephants and trying to figure out how do we move forward? As opposed to say, I can spot the other guy's elephant in the room, but I can't see my own and, you know, in large measure, we didn't represent an institutional base and therefore it wasn't maximally important that we look at our own hypocrisy because we weren't on the institutional spectrum. </s><s>[INST] This is where friendship comes into play with the different figures that are loosely associated with the I. D. W. Is you are somehow uh responsible for, you know, the exactly thing that you said, Did you hear what? I don't know, I forget the dame. Oh what Sam Harris said about the stuff. Uh that that kind of thing is [/INST] why chuckled </s><s>[INST] lovingly or chocolate. Like I [/INST] was angry at some people who had said things that cause Sam to say what Sam said about turning his imaginary club membership into the I. D. W. People said very silly things and you know, I think that there is just this confusion that um integrity means calling out your friends in front of the world and you know, I've been pretty clear about this uh try to choose my friends carefully and if you would like to recuse me because I'm not a source of reliable information, people that I know and love the most um maybe that's reasonable for you. Maybe you prefer somebody who was willing to throw a friend under the bus at the first sign of trouble by all means uh exit my feed. You don't have to subscribe to me. If that's if that's your concept of integrity, you're barking up the wrong tree. What I will say is that I knew these people well enough to know that they're all flawed. Thank you for the call back. And uh but the issue is that um I love people who are flawed and I love people who have to earn a living, even if you call them a grifter. And I love people who ah you know like the fact that donald trump didn't get us into new wars, even if you call them all right, I love the fact that um some people believe in structural oppression and want to fight it even if they're not woke because they don't believe that structural oppression is hiding everywhere. I care and love different people in different ways. And I just I think that the overarching thing like that we're not getting at is that we were sold a bill of goods that you can go through life, like and Eliza program with pre programmed responses. Well, that's what about ISM? It's both sides ISm It's all right. It's the loony left campus madness. You know, It's like, okay, why don't you just empty the entire goddamn magazine all of those pre recorded snips now that you've done all of that now, we can have a conversation, </s><s>[INST] your son put it really well, which is we should in all things resist labels, [/INST] but we can't deal without labels. We have two general lease, but we also have to keep in mind that just in the way in science you deal with an effective theory that isn't a fundamental one in science. Most of our theories we consider to be effective theories if I generalize about, about europe, about women, about uh, you know, christians, those things have to be understood to mean something and not to have their definitions extend so broadly that they mean nothing at all, nor, um, that they're so rigid that their claims that clearly won't bear scrutiny. Let's what do you really want to talk about? That's always my question to you, that always gets </s><s>[INST] me. That's a good thing. Maybe you are the therapist, [/INST] but like you and I could talk about people love up until now at least people have loved listening to the two of us in conversation. And my feeling is that we're not talking about neural nets, we're not talking about geometric unity and we're not talking about where distributed computing might go. And I don't think that we're really focused on some of the most exciting things we could do to transform education were still caught in this world of other people that we don't belong, I don't belong in the world as it's been created. I'm trying to build a new world and I'm astounded that the people with the independent means to help build that world are so demotivated that they don't want to build new structures and the people who do want to build new structures seem to be wild at </s><s>[INST] wild eyed. What do you mean by wild eyed? They're not, they're not, [/INST] I guarantee you that I will get some message in my DMS and says, hey eric, you know, I'm a third year chemistry student at uh, you know South Dakota State and I've got a great idea. I just need funding. I want to build, they </s>

<s>[INST] and tell me what does it look like? There's a, like I could see everything twice. [/INST] It's a double image. It's a double image. That is a special crystal that has two different indices of refraction. So light emerging, which is unpolarized from that black ink comes out and it splits into two different directions. And it could split even more if I made the crystal </s><s>[INST] give you my more expensive crystal, but that's all I have. [/INST] What is the crystal with this kind of property called? It's called calcite. This is crystal, it's called birefringent crystal. Bi means two, refringent means refracting. So this is a special type of material </s><s>[INST] that separates light based on its polarization. Pretty clean by signal. Yeah. [/INST] It's cleanly too, I'm seeing too very cleanly. Yeah, yeah, it's very crisp, right. So that's yours to keep with every time you host me. Now take the polarizer underneath your left hand, put it on top of the crystal and kind of move it back and forth. </s><s>[INST] Wow. This is incredible. You can switch as you rotate, you switch from one signal to the other. [/INST] So it's one of the refractions to the other. Whoa. So that is now you're analyzing the polarization, you're confirming the light comes out of the crystal, two different types of polarization. And effectively what we do is we have those two things if you like, but working in the microwave. So our detect, well it's where this the cosmic photons are brightest in the microwave regime and the electromagnetic spectrum. And we're coupling that to a refracting telescope, but your eyes are refracting telescopes. So you are a polarimeter right now. The human eye can actually slightly detect polarization, but otherwise it mainly detects its intensity of light and the color, that's what we call color </s><s>[INST] and intensity, brightness. Whoa. So you're devising an instrument that's very precisely measuring that polarization. [/INST] Exactly, exactly. And doing so in the microwave region with detectors not made of biological human retina cells, but of superconductors and things called ballometers. And this has to be done at temperatures close to absolute zero under vacuum conditions </s><s>[INST] one billionth of the pressure we feel here at sea level. So why is it that this kind of device could win a Nobel Prize? [/INST] So when the CMB was discovered, it was discovered serendipitously. There were two radio astronomers working at the time at Bell Laboratories. Now, why would Bell Laboratories be employing radio astronomers? Bell Laboratories was kind of like Apple or it was like a think tank or it was Google. Let's say it was like Google. Google has like Google X, it has this thing and that thing, right? So they were working there, but imagine if Google was employing radio astronomers, like they were actively recruiting. Why would they do that? Well, it turns out that was the beginning in the 1960s was the first commercial satellite launch for communication. And so Bell Labs, which would later become the telephone, part of AT&T and the early telephone company, later invent the first cell phone the year I was born. And they would take that 1946 and they would take that telescope technology that radio astronomers had developed and they would use that to see if they could improve the signal to noise of the satellites that they were seeing. And they found they couldn't. They found that they could not improve the signal-to-noise ratio of the first telecommunication satellite. It was like the equivalent to one kilobit per second momentum. Then they were bouncing signals from the West coast up to the satellite, bouncing it down, landing it in New Jersey of all places, in northern New Jersey, homeville New Jersey. And these rainforest hunters couldn't get rid of the signal. So they said, well, New Jersey's not far from New York. Let's see if the signal's coming from New York. No, not coming from New York. Let's see if it changes with the year maybe it's coming from the galaxy, which was also discovered there </s><s>[INST] by Jansky in 1930 something. So not being able to reduce the signal or increase the signal-to-noise ratio, the noise... It was noise. [/INST] You couldn't do it... noise. They knew the signal was right. They couldn't get rid of the noise. And there was excess noise over the model that had not only been predicted by them, but had been measured by a previous guy, a guy by the name of Edward Ohm. He measured the same signal, found that there was this hiss of static, of radio static that he could not get rid of that had a value of about three Kelvin. So you can translate. Remember I said, if you take a radio telescope and you have pointed at an object that's hot, the radio telescopes detector will get to the same temperature as the object. It's a principle of radio thermodynamics. So it's a really interesting thing. It's a thermometer. You can stick it into Jupiter from here on earth. It's amazing. They were, and so we in radio astronomy characterize our signal not by its intensity, but by its temperature. So he found this guy, Edward Ohm, oh, there's a three Kelvin signal. I can't get rid of it. It must be, I did my era analysis wrong and I would give him an F if he was one of my first year students. But he's just attributed to lack of understanding these other guys, Penzias and Wilson, who are also radio astronomers. They said, no, let's build another experiment, put that inside of our telescope and do what's called calibration, inject a known source of signal every second that has a temperature of about four Kelvin, because the signal that they were trying to get rid of is about three Kelvin. And you want to have it as close as possible to the pernicious signal as possible. They did that once a second. So they got billions of measurements, millions of measurements over the course of several months, years, and even by the end, millions of measurements for sure. And they found they couldn't get rid of it either, but they measured it was exactly 2.7, two, six, five, you know, degrees Kelvin. </s>

<s>[INST] History doesn't matter. You're exploring ancient history and drawing deep wisdom from it and at the same time saying we need to forget all of it. We need to put that behind us. [/INST] Absolutely. We need to forget it and we need to move forward, </s><s>[INST] There's so much wisdom to draw from history, even the 20th century. Look at this communism without the lessons of history of the 20th century, communism sounds like a great idea except that some of the worst atrocities conducted by Stalin and mao that killed 500 plus million people, not just killed, tortured, starvation. Where people, the cannibalism, they ate each other, they ate their Children. There's, there's just dark people. People should read some books on this on the holiday more in 1930's [/INST] with that </s><s>[INST] lesson we would and now it's becoming more popular Marxism and communism [/INST] disagreeing that that happened. I'm disagreeing that we need to harp on the things that happened because the truth is I'm giving a fact 50% today of, let's say you don't call black people do right. Black people's deaths today is abortion today right now like that. It's not racism that's too wide of a term. It's genocide and population control that boy black people are in today in America that is promoted by the music and the media that black people make that jewish record labels get paid off of our media companies, record labels, media company also. So let's give it a wider, you </s><s>[INST] know, I agree with martin Luther king. I have a dream to [/INST] that one day. You </s><s>[INST] would not be judged by the color of your skin or your race, black or jew. But by the content of your character, all the assholes that fucked you over in the music industry, Fuck artists over in the music industry are individuals. They're not jews. Can you, can you [/INST] say they are? They are jewish. </s><s>[INST] It doesn't their human with opportunities and they took those opportunities. I don't care [/INST] if they're jewish. You feel like I should release that pain and separate it. </s><s>[INST] Yes. [/INST] Okay. So that, okay, so if you're saying I should release that pain and separate it, then I'm telling you, you should release your pain and separating and we could get to this the list of how you are being with engineering opportunities. </s><s>[INST] That's 100%. I see what you're doing that exactly. You're doing the pain. I'm gonna let it go. Engineering challenges. I get it. One of the problems you highlight is people get sucked over in the, in the music industry and get sucked over in the media, get sucked over all over the place they [/INST] created. There was a, there was a jewish trainer that brought me to the hospital and put in press that I went to the hospital. I got, I know friends that off of exhaustion, a jewish doctor they diagnosed because they were right, diagnosed me with bipolar disorder and shot me with medication and put me on medication then put it in the press and every time even if I wore the wrong color hat that a *** is not supposed to wear, right? Then they immediately say he's off of his ship. He's off his meds, he's off his rocker and it's literally used as a scarlet letter control mechanism for the people understand the kids, the colleges, the high schools, What do you think they put me right now? They put me as the prophet, not the leader. It doesn't have to be the leader, right? Because we, we need, we need a more intelligent person to be the leader, but at least right. They put me as the prophet. They put me as the only person That would say this. And I'm just saying that was four Jewish members that controlled my voice because for the fact that 90% of black people in entertainment, from sports to music to acting are in some way tied into Jewish business people, meaning that in some way just like if if rom is sitting next to Obama or Jared sitting next to trump, there's a jewish person right there controlling the country, the jewish controlling that, who gets the best video or not controlling what the media says about me, </s><s>[INST] not jewish, but [/INST] they are though. That's the only thing. It just so happens that they are, it's just </s><s>[INST] saying that [/INST] doesn't mean that I hate them. That just means that they are, </s><s>[INST] but it's a, it's a dog whistle to let me, let me just say as I would love to add more love to the world. I would love you to do that as a person with a big voice with a big powerful voice that a lot of people look up to. And when you say jewish media, it's funny how this world works that way. When you say jewish media or jews are controlling the voice of black artists, black people, black artists. When you say [/INST] that you </s><s>[INST] can say it, there's a large number of people that are hurting and have anger and even have hate in their heart. When they, when they hear jewish media, they start that hate starts being directed towards the jewish people. Do you acknowledge that? That's do you understand, can you feel the hate in the world? That's when that uh that comes to the surface when you say stuff like that. [/INST] Okay, I I feel that when we go into therapy, my dad was a therapist and obviously I've got some therapy skills myself, a lot of people. My music is healing these type of spot like existences or healing the color palettes that use our healing and we can use healing words. Right? What I really feel there, I feel that there's no accountability and no responsibility on jewish people in media to at least start with owning up with the facts of what's dealt with and tell me if I say the facts out loud to the point of ari emanuel writing a letter in the financial times, trying to take food out of my Children's mouth, telling people that they're not allowed to work with me, even chris uh, como or pierce morrigan. Getting me to apologize and separate jewish business people to from the families of the jewish business people, which I did update. I did that that already happened and </s>

<s>[INST] It's the psychology question because there's something really pleasant about, you know, pointing out that the emperor has no clothes when everybody like uh you know, thinking outside the box and coming up with the true answer where everybody else is diluted, There's something, I mean, I have that for science, right. You want to prove the entire scientific community wrong. That's the whole, [/INST] that's right. And of course historically, lone geniuses have come out right sometimes. Yes. But often people who think they're alone genius and much more often turned out not to. Um, so you have to judge each case on its merits. The mere fact that you're a maverick, the mere fact that you you're going against the current tide doesn't make you right. You want to show you're right by looking at the evidence. </s><s>[INST] So because you focus so much on on religion and disassembled a lot of ideas there and I just, I was wondering if if you have ideas about conspiracy theory groups, because it's such a prevalent, even reaching into uh presidential politics and so on. It seems like it's a very large communities that believe different kinds of conspiracy theories. Is there some connection there to your thinking on religion? And I'm curious, [/INST] it's a matter, it's an obviously difficult thing. I don't understand why people believe things that are clearly nonsense like Well flat earth and also the conspiracy about not landing on the moon or um, that the United States engineered 9-11, that that kind of thing. Um, </s><s>[INST] so it's not clearly nonsense. It's extremely unlikely. [/INST] Okay, it's extremely unlikely that religion is a bit different because it's passed down from generation to generation. So many of the people who are religious got it from their parents who got it from their parents who got it from their parents and Childhood indoctrination is a very powerful force, but these things like the 9-11 conspiracy theory, the Kennedy assassination conspiracy theory, the man on the Moon conspiracy theory, these are not childhood indoctrination, these are um presumably dreamed up by somebody who then tells somebody else who then wants to believe it. And I don't know why people are so eager to fall in line with some to some person that they happen to read or meat who spin some yarn. I can kind of understand why they believe what their parents and teachers told them when they were very tiny and not capable of critical thinking for themselves. So I sort of get why the great religions of the world like Catholicism and Islam, go on persisting. It's because of childhood indoctrination, but that's not true of flat earth is um and sure enough, flat earth is um is a very minority cult </s><s>[INST] way larger than I ever realized. [/INST] Well, yes, I know, </s><s>[INST] but so that's a really clean idea, you've articulated in your new book and then, and I'll go and God and then got delusion is the early indoctrination. That's really interesting. You can get away with a lot of out there ideas in terms of religious texts if uh the age at which you convey those ideas at first as a young age. So indoctrination is sort of an essential element of propagation of religion. Uh so let me ask on the morality side in the books that I mentioned, God delusion and I'll go and God you describe that human beings don't need religion to be moral. So from an engineering perspective, we want to engineer morality into ai systems. So in general, where do you think morals come from in humans? [/INST] A very complicated and interesting question. It's clear to me that the moral standards, the moral values of our civilization changes as the decades go by, certainly as the centuries go by, even as the decades go by and We in the 21st century are quite clearly labeled 21st century people. In terms of our moral values, there's a spread. I mean, some of us are a little bit more ruthless, some of us more conservative, some of us more more liberal and so on. But we all subscribe to pretty much the same views when you compare us with, Say 18th century, 17th century people, even 19th century 20th century people. Um, so we are much less racist, were much less sexist and so on than we used to be. Some, some people are still racist and some are still sexist. But the spread has shifted that the Gaussian distribution has moved and moves steadily as the centuries go by. And that is the most powerful uh influence. I can see on our moral values and that doesn't have anything to do with religion. I mean, the the religion of the story of the morals of the old testament, uh, Bronze Age models, models are deplorable. Um, and um, they are to be understood in terms of the people in the desert who made them up at the time. And so, human sacrifice. Um, uh, an eye for an eye and a tooth for a tooth. Petty revenge killing people for breaking the sabbath, all that kind of thing. Um, inconceivable. </s><s>[INST] No. So at some point, religious texts may have in part reflected that Gaussian distribution at that [/INST] time. They did. I'm sure they always </s><s>[INST] reflect that and then now, but the sort of almost like the meme, as you describe it of ideas moves much faster than religious text to the new religion, [/INST] basing your morals on, on religious texts, which are written millennia ago, um, is not a great way to proceed. I think that's pretty clear. So, um, not only should we not get our morals from such text, but we don't, we quite clearly don't. Um, if we did, then we'd we'd be discriminating against women and we'd be, we'd be racist, we'd be killing homosexuals and so on. Um, so, so we, we we don't, and we shouldn't. Now, of course it's possible to By the, to use your 21st century standards of morality. And you can look at the Bible and you can cherry pick particular verses which conform to our modern morality. And you'll find that jesus says a pretty nice things, which is great. But you're using your 21st century morality to decide which versus to pick which versus to reject. And so why not cut out the middleman of the bible and go straight to the 21st century morality, which is where that comes from. It's a much more complicated question. Why is it that morality, moral values change as the centuries go by? The undoubtedly do. And it's a very interesting question to ask why It's a it's another example of cultural evolution, justice, technology progresses. So moral values progress for probably very different reasons. </s>

<s>[INST] an awesome [/INST] okay, standard candles is what astronomers like to say that I don't like that term because there aren't any standard candles. But there are standardized herbal candles. And by looking at these California, you calibrate able standardized herbal calibrate, able you look at enough of them in nearby Galaxies whose distances, you know, independently. And what you can tell is that, you know, this is something that a colleague of mine, Mark phillips did who was on Schmidt's team and arguably one of them was one of the people who deserved the nobel prize. But he showed that the intrinsically more powerful Type one A's uh decline in brightness and it turns out rise and brightness as well more slowly than the less luminous one A's. And so if you calibrate this by measuring a whole bunch of nearby ones and then you look at a distant one. Instead of saying, Well, it's a 100 watt type one, a supernova. They're much more powerful than that by the way. Plus or minus 50 you can say, no, it's it's 100 and 12 plus or minus 15 or it's or it's 84 plus or minus 17. It tells you where it is in the power scale and it greatly decreases the uncertainties. And that's what makes these things, cosmological e useful. I showed that if you spread the light out into a spectrum, you can tell spectroscopic lee that these things are different as well. And in 1991 I happen to study two of the extreme peculiar ones, the low luminosity ones and the high luminosity one's 1991 B. G. In 1991 T. This showed that not all the one S are the same. And indeed at the time of 1991 I was a little bit skeptical that we could use Type one A's because of this diversity that I was observing. But in 1993 mark phillips wrote a paper that showed this correlation between the light curve the brightness versus time and the peak luminosity and once </s><s>[INST] is enough information to calibrate, [/INST] then they become calibrate able. And that was a game changer. </s><s>[INST] How many Type one As are out there to use for data [/INST] Now there are thousands of them. Thousands of time. The high Z team had 16. And the supernova cosmology project had 40. But the 16 were better measured than the 40. And so our statistical uncertainties were comparable. If you look at the two papers that were </s><s>[INST] published, does that make you feel that there's these gigantic explosions just sprinkled out there? [/INST] Well, I certainly don't want one to be very nearby and it would have to be within something like 10 light years to be an existential </s><s>[INST] threat. So they can happen in our galaxy. Yeah. You know, so that we would be okay [/INST] Uh in most cases we'd be okay because our galaxy is 100,000 light years across. And you need one of these things to be within about 10 light years to be an existential threat. </s><s>[INST] And it gives birth to a bunch of other uh stars I guess. [/INST] Yeah, gives birth to expanding gasses that are chemically enriched. And those expanding gasses mixed with other chemically enriched expanding gasses or primordial clouds of hydrogen and helium. I mean this is uh in a sense that the greatest story ever told, right? I try to I teach this introductory astronomy course set at Berkeley and I tell him there's only five or six things that I want them to really understand and remember and I'm gonna come to their death bed and I'm going to ask them about this and if they get it wrong, I will retroactively fake with their whole career. Will have been shot that they don't observe a total solar eclipse. And yet they had the opportunity to do so I will retroactively fail them. But one of them is, you know, where did we come from? Where did the elements in our DNA come from? The carbon in ourselves? The oxygen that we breathe, The calcium in our bones, the iron in our red blood cells, those elements, the phosphorus in our DNA. They all came from stars from nuclear reactions in stars and they were ejected into the cosmos. And in some cases like iron made during the explosions and those gasses drifted out mixed with other clouds, made a new star or a star cluster? Some of whose members then evolved and exploded, thus enriching the gasses in the galaxy progressively more with time until finally 4.5 billion years ago from one of these chemically enriched clouds, our solar system formed with a rocky earth like planet. And somewhere somehow these self replicating evolving molecules, bacteria formed and evolved through Para mi je and amoebas and slugs and and apes and and us and here we are sentient beings that can ask these questions about our very origins and with our intellect and with the machines we make come to a reasonable understanding of our origins. What a beautiful story. I mean, if that does not put you at least in awe if not in love with science and its power of deduction, I don't know what? Well, right. It's one of the greatest stories, if not the greatest story. Obviously that's you know, personality dependent and all that. It's it's a subjective opinion, but it's perhaps the greatest story over ever told. I mean, you could link it to the Big Bang and go even farther right to make an even more complete story but as as a subset that's even in some ways a greater story than than even the existence of the universe in some ways because you could end up you could just imagine some really boring universe that never leads to sentient creatures such as ourselves. </s>

<s>[INST] and in the process choose a better fate for ourselves. How difficult is the process of knowing, understanding what is the righteous action, of knowing what it means to be a good man or a good woman? [/INST] Well, the truth has consequences. So don't seek out the truth unless you're willing to abide by what you find. So a lot of people want to mold their journey in accordance with a predetermined pursuit that they already have. And so when they approach religion, they approach it like another product. There was an article that was actually written by a rabbi, I've spoken about this in several sermons. It was called the Allure of Narcissistic Spirituality. The Allure of Narcissistic Spirituality, where he talks about how religion becomes just another product of your own self-adoration and worship to where you only approach religion to the extent that it gives you more happiness in the worldly sense. You only approach of it what is therapeutic. So it becomes just as secular in its nature as any other practice of meditation or whatever it may be, or some other product. And it kind of mentions how he took that from a person that is praying in a temple and a guy walks into the temple and bumps into him and then he curses the guy out. So he didn't see his behavior towards that person as part of his trajectory of worship. He just saw his being godly as the worship that he was engaged in. The truth has consequences. The truth has circumstances that are required of you, actions that are required of you that may be somewhat inconvenient. So you have to be willing to engage in a sincere pursuit of truth and look for truth for what it is and not simply look for comfort and convenience. And when you engage in that journey of wanting to know, you have to engage it thoroughly and sincerely and try your best to remove any bias. I think that's what makes the religion of Islam such a phenomenon for people, that with all the Islamophobia and the bigotry towards it, it's still the fastest growing religion in the United States and the fastest growing religion in the world. And no, that's not all birth rate. Yeah, we have a lot of kids, but many people, you met someone just before we started this interview, many people in fact in a post-9 11 world saw what they saw of Islam in the media. And they actually went and checked out copies of the Quran and started to read about the religion and in their sincere pursuit of truth, ended up embracing a religion that they believed was the greatest source of destruction in the world. And now it's the greatest source of peace for them in their own existence, in their own lives. And so you have to be willing to engage in a sincere pursuit of wanting to know and then be willing to engage in sincere commitment after you know, otherwise the heart rusts. And so there's a process in the Quran talks about this, of making the heart like fertile soil towards truth. So you have a sincere pursuits, but then at some point if you come to know and then you ignore what you come to know, then the heart rusts and it becomes harder to recognize it the second time around and the third time around, and so, when people come to me and they say, you know, I'm looking for something. I'm looking for, I'm looking for God, I'm looking for my purpose, the first thing I tell them as I say, listen, what you need to do is, if you're really looking for God and you believe in God, and there are often people that say, I believe in God, but I don't know where to go with this, right? I know that there's something greater in Islam. We call that the fitra, a natural disposition towards the belief in the existence of God, but where do I go from here? You know, what do I do now? And I say, the first thing you need to do is you need to sincerely say, oh God, guide me to the truth. Call upon God, sincerely say, I'm calling upon you alone and I'm asking you to guide me to the truth. Show me what it is, right? And that's the heart function. Then you need to actually investigate and try to suspend bias, right? Investigate the world's religions, investigate the claims to truth, investigate, use rational inquiry to the extent that the heart becomes satisfied. And suspend bias and you'll be surprised. And so for a lot of people, they come to me and they say, you know, this about Islam? I'm like, look, if you're just gonna talk to me about what you've seen of Islam in the media, if you were serious about it, you know, if you're serious about it, then you're not simply going to be satisfied with the highly edited images and distorted facts that come towards you about this religion, right. What are you looking for, right? Are you looking for a scapegoat? Islam poses a threat to many people, right? Are you looking for a scapegoat? Are you looking for the big, bad, scary, foreign enemy? Or are you looking at a religion that one fourth of the world adheres to? And if one fourth of us were bad, the world would not exist, right? So are you looking towards this religion that one fourth of the world adheres to? Are you going to read about the prophet Muhammad, peace be upon him? Or are you going to read the Quran yourself? Are you going to investigate for yourself what it is that this faith has to offer and find in it a great sense of wisdom, a great sense of beauty, a great sense of truth. And I think that for a lot of people, they find that Islam has such a beautiful combination of the intellectual proofs as well as the spiritual experiences that often combine what people seek in the Western and the Eastern religion. So I had an interesting two weeks. Two weeks in a row, this was August, two weeks in a row. I had someone who converted to Islam that started off as a Methodist, went from being a Methodist to being a Buddhist to being a Muslim. So two weeks in a row, I had a Methodist turned Buddhist turned Muslim. Great journey. Yeah, I called my Methodist friends. I have a lot of Methodist pastors in the city that I work with. And I said, what's going on here, man? Sending people on to this interesting journey of Buddhism and then Islam. But both of them had a very similar story, which is that they had sought in Buddhism, for example, some of the meditative practices that are found, that really Western religion, which has been dominated by capitalism and dominated by very material things and can be very unfulfilling, they found that in some of the Eastern philosophies and the meditative practices. And then they came to Islam and it combines their belief in sort of the Abrahamic way. It merged their belief in one God and the prophets like Abraham and Moses and Jesus, peace be upon them all, with a deep tradition of meditative practices, of consciousness, of connection to God on a regular basis. And they found that to be very fulfilling both intellectually and spiritually. And so I was like, that's interesting. Two people in two weeks that went through that journey. So I think Islam is very wholesome, comprehensive when people actually approach it with humility. </s>

<s>[INST] Yeah. This is the problem with saying I'm an individual. I'm not going to bother you. You don't bother me. That's just like that's not actionable? Because to be to make it actionable, you have to think the why why, why, why why you have to do the steps beyond I think, what does that actually mean? That means understanding how even my very existence, uh, like hurts others because you have to understand that like I'm not, you're not just sitting alone in a room. You're, you're using like public transit, using the police force. You're using firefighters, you're using that like you're using a lot of resources that are publicly shared and some of those resources are, are unfairly distributed. Uh, like we've agreed that we're going to pay taxes and those taxes are gonna go towards building some kind of infrastructure. So that's already towards social. That's so you're not a real, you're, you're not a real sort of, I talked to Michael malice, like anarchists, right saying like basically full just leave me the funk alone and I'm going to collaborate whatever the hell I want. We're not, that's not the american society as it stands. Currently, we've agreed that there's going to be certain social institutions we pay into. And uh, some of the sort of discussions about race and all those kinds of things ah, is about those institutions being, uh, institutionally unfair. This race or gender, all those kinds of things. Listen, I, you know, I have a bunch of criticisms of the way that conversation carries itself out. But the thing is, was valuable is to actually listen and empathize. And that's not even often talked about would uh leave me the funk alone mindset because you're, it doesn't have, it doesn't have that little component which I think could be fundamental to the function of a society which is like social like it's, what is it the Obama you didn't build it or you didn't build it alone or whatever however that goes. But basically we wouldn't be, we wouldn't be able to accomplish anything as individuals without the help of others and to be able to then start to think okay so what is, what, what is my duty? What is my responsibility to other human beings to be respectful to be loving to help them as part of this functioning society that starts that's actually a lot of work to start to think about that because then I have to like think okay Ryan what's his life like as a business owner during Covid, What's that like? And then he has uh there's employees that run the gym, What's that like what's that stress like or about the fighting and the injury and so on. What's that Like that empathy takes a lot of like [/INST] compute </s><s>[INST] cycles and [/INST] also a lot of energy right? </s><s>[INST] But I have to go through that computation if I want to be an individual that's like doesn't hurt you [/INST] if I may I guess like to come back to Muhammad Ali, one of the things he said is service to others is the rent is the rent that you pay for your, you know, is the price you pay for your rent here on earth. And now one of the things that I think that I see as a result of the internet all the time is people talking about global giant problems, social problems that are society wide that are massive, like truly massive and frankly beyond the beyond the power of any of us to solve that certainly on an individual level. So I have, you know, I've discussed things with friends, like my father's an environmental attorney, like uh you know, has been for a long time and has been an engineer for a long time and uh you know, so I'm not, I barely know anything, but I'm reading a little bit of various things, but climate change, oh my God, I'm so concerned about climate change. What am I supposed to do about climate change? I'll tell you what I can do is I cannot litter, I can try to conserve energy where I can, I can do whatever I want. What can I personally do about some giant social problem that is that I didn't start and I was out of my control, I'm like, well I can be decent to the people around me, I can mention, I can demonstrate empathy and I can demonstrate consideration for the people in my circle and to the extent that I can, to people outside of my circle, but yelling at the trees over things that over problems that are borderline cosmic um doesn't seem very productive. It just makes me feel like I'm cool and important because I'm talking about something well hundreds of years from now, the water will rise. Maybe it will, maybe it won't, I can't, it's completely over my head and I know nothing but focusing on the problems that we can actually solve. It comes back to the same thing. I want to win a fight. I would love to win a fight. Uh I can't control that. What I can do is I can control each individual step that I take around the ring and trying to make the next correct move. I can't look, no, it gets people's uh you know, they get all excited, you know, I'm trying to keep my language and check, but they get all excited thinking about, you know, problems that are like superman couldn't solve these problems, like you could be that powerful and you can't make all of the bad things go away, but you can absolutely change yourself. And I think a lot of the lessons that you know, like the good lessons from religion that happened, the good lessons from the great men and women throughout history that were that were inspired by that talk about change, starting with within and again, treating the people around you decently and feeding the people round to decently doesn't even necessarily mean the golden rule do unto others as you would like them to do to you. I go, well, maybe what I would like and what this person would like aren't the same thing. Well, how am I going to get to the bottom of that? Because I could be attempting to be decent to this person and by my standards, I'm being decent. Maybe I'm, maybe I'm missing the mark by there's, well, I can't possibly if I just interacted with you. Like it's like someone talking about some nonsense microaggression. So let me get this straight. I've never met you before. You never met me before and you're interpreting some minor comment that, that I've made in the least charitable way possible. I'm not saying that, that you couldn't be annoyed, but your expectation for that level of consideration is you're gonna be, you're gonna be disappointed a lot. Now if you if you're someone that's in your life on a consistent basis and they're like, hey, I really don't appreciate what you're saying or what you're doing here, Do you realize that this is how I'm, this is how I'm perceiving you go home, man. I'm so sorry. Of course I would hear what you have to say. But I guess trying to recognize that, you know, my I guess my job is to treat others with dignity in general. But that level of the level of specificity that that that that requires increases as it gets closer to you and I have as a person, I have a very finite amount of resources, financially, intellectually emotionally, physically if I chuck you know, .001% of it in every single different direction. What am I doing? It's like people I cared deeply about Tibet and like why aren't you over there? Go build a house man, get on a plane, go build a house, oh, you don't want to do that. So really what you want to do is post on facebook and and and accept high fives for how much of a good guy you are. I got an idea, go help somebody in your neighborhood, go b, go play, go play with some kids, go be a friend to someone that doesn't have a friend, read a book, try to educate yourself. And so I guess to, to come back, it's all of these problems aren't solvable on a grand scale, but it's almost like by attempting to address them in our personal lives, we do better. But rather than a giant airing of the grievances on a, on a consistent basis. Not that that isn't, you know, sometimes necessary and valuable, but after you air your grievances, you know, hey, how about we, we sort this out, what's the next step And, and I guess again when we're trying to address it on a giant social level, it just seems unmanageable to me. Even if you have the best of intentions. </s>

<s>[INST] literally about the duration that your body is carrying the load. [/INST] Yeah, that's a big part of it because you have to you're using the resource of the diaphragm for stabilization. And so it's also responsible for respiration and all this other stuff. So even when you're not squatting, you've got to be handling those loads </s><s>[INST] just holding that way. It's fascinating. It's like it's fascinated the human body can do that can maintain that structure, just everything. Working together that the biology, the skeletal structure, the musculature on top of that can hold the weight. It's fascinating to watch [/INST] everything is very intent fel about positioning and how you're creating pressure and all that sort of stuff, especially for me. So when I mentioned that half a dozen people have squatted it and half a dozen people have dead lifted it. You understand those people all way, 380 to £440 I wait to 65 to 2 85 depending on the where I was between the two. So there's that as well, right? So big, big difference and uh over the course that I did a lot of other feats of strength that fit in that capacity and we can skip over those, but that was hugely invested as far as you know what I put into being able to accomplish that because it's over the top, which means the other stuff had to shift and I had to learn some, there's so many things that came into place to pull that off. And so yeah, last March two days before the world shut down. I did it, it was supposed to be at the largest equipment exhibition in the world, down in SAn Diego as an event and that got shut down a week beforehand obviously. So we moved to, let's do it in my gym and invite people And that was on a Saturday and Thursday or Friday, they limited it to 25 people for gatherings. I did it on saturday and then monday everything shut down. So it was kind of surreal for timing wise. Right? And so if I hadn't done it, it would have never got done like because I had pushed to the limit, I couldn't come back and do it. It was at the total limitation of my capabilities. So I'm pretty, I'm pretty proud of it in the last piece was every one of these feats along the way. I collaborated with the charity that I believed in. And there was a lot of those tied in my life story, which we probably will get into. Um so it was three fold. So that inspiration piece, inspiration, motivation, walking the walk and showing like just these methodologies that a guy that had to learn to walk again can do something like this with no back pain if you, if you there is a way and the third one is to provide awareness and recognition around a lot of uh, key charity. So, </s><s>[INST] so your heart was in this journey, but also your mind, which is your like a scholar of strength, a scientist of strength and engineer of strength for reps do £1000 of squats and dead lift. Let's first talk through the actual day you did it, What does it take to lift that much for reps? [/INST] The day of is really easy. The lift itself other than a few seconds is really easy and not challenging. People always ask me, what was it like, how beat up were you after that? And the dead lift and the simple fact is it was easy, the work to get, there was horrendous. So, </s><s>[INST] so even the psychology of the day, you weren't, there was not a fear, there was not a nervousness, there's not a doubt in your mind, [/INST] there was certainly doubts on that day. Um, from some training history. So there was some major breaks to my confidence in the couple months leading up where I had issues with passing out under the bar. So completely losing consciousness. And this was on weight less than £1,000 even. So that was like all this build up in me going, what if what if it, I think I have this resolved. But what if I get up there and I can't even do a rep, How embarrassing will this be that I've been talking about this and planning for this for so long. But outside of that, I knew I could do it. In fact, I wanted to do even more. Even up to the second rep training is about, you know, working into a fatigue state. So you're building amount of fatigue in your system. And then when you let off of it, that's when you get a compensation and that's how you stare stop training. This is period ization. But leading into a big event, you're accumulating this massive amount of fatigue. And so I was performing at a level that I could do it. And so I knew I was going to be able to on me because then you then you give yourself that window to be able to recover and super compensate and be able to do a little bit more. So like that first rep, when I didn't strength wise, I went, I could do this for five reps. Like it went through my head. I'm like feeling, I mean it was easy and it was fast and it felt like amazing and I'm like, I'm gonna crush this and then set rep too, the realization kicked in is like, oh this is for reps with £1000 on your back and you're fatiguing just like and then the 3rd 1 was every last thing I could muster to just finish, I mean, I just barely got it done because it's the strength is like there, but like that capacity to be able to manage all those resources for that amount of time, because not just leg strength when we're talking about this stuff. So </s>

<s>[INST] But it's hard. So when that it's hard to find a person that has that, I mean a lot of stuff you said is pretty profound, but having that person who has empathy and accountability. So basically that's ultimately what great friendship is, which is people that love, you have empathy for your book can also call you out on your bullshit. [/INST] She's a Lebron James like figure. And the reason I say that is I've seen and met so many people, I've seen the distribution on the scale of friendship and empathy. </s><s>[INST] She's the Lebron James of friendship, [/INST] She's a goat. Well what's so funny is like, you know, we have a dinner around poker and it's taken on a life of its own mostly because of her because these guys look to her and I'm like, whoa, </s><s>[INST] she's [/INST] thinking like </s><s>[INST] her [/INST] registers are already full, she's thinking of all kinds of crap with me, um but </s><s>[INST] but [/INST] it's a, it's a, it's a very innate skill and it's paired with, you know, it's but it's not just an emotional thing, meaning she's the person that I make all my decisions with these decisions we're making together as a team. I've never understood that, you know, there's an african proverb, like, go fast, go alone, go far, go together. And like, since since I was born, I was by myself and I had to cope and I didn't have a good toolkit to use into the world and in these last five or six years she's helped me and at first my toolkit was literally like sticks, you know, and then I found a way to, you know, she helped me sharpen a little rock and that became a little knife, but even that was crap, and then she showed me fire and then I forged a knife and then, and that's what it feels like we're now this toolkit is like most average people and I feel humbled to be average because I was here down here on the ground, so it's made all these things more reasonable. So I see what comes from having deep, profound friendships and love to help you through these critical moments. I have another friend who um who I would say just completely unabashedly loves me, this guy rob Goldberg, he doesn't hold me accountable that much, which I love. Like I could say I killed a homeless person. He's like, they probably deserved it, you know, whereas that would be like, that was not </s><s>[INST] good what you just did. [/INST] So, but I have both. I mean I have not every day, you know, rob, I don't talk to that often, but to have two people I had zero, I think most people unfortunately have zero. Um so I think like what what he needs is somebody to just listen. You don't have to put a label on these things and you just have to try to guide in these very unique moments where you can just like deescalate what is going on in your mind and I suspect what's going on in his mind again, to play armchair quarterback, I don't know is that he is in a moment where he just feels lower than low and we all do it. We've all had these moments where we don't know how to get attention and if you didn't grow up in a healthy environment, you may go through a negative way to get attention and it's not to excuse it, but it's to understand it, </s><s>[INST] that's so profound. The feeling less than and at those low points going externally to find it and maybe creating conflict and scandal to get that attention. [/INST] The way that my doctor explained it to me is you have to think about yourself Worth like a knot, It's inside of a very complicated set of knots. So it's like a some people don't have these knots, it's just presented to you on a platter. But for some of us, because of the way we grow up, it's covered in all these knots. So the whole goal is to loosen those knots and it happens slowly. It happens unpredictably and it takes a long time. And so while you're doing that, you are going to have moments where when you feel less than you're not prepared to look inside and say actually here's how I feel about myself. It's pretty cool. I'm happy with where I'm at. </s><s>[INST] I have to ask on the topic of friendship, you do an amazing podcast called All in podcast. People should stop listening to this and go listen to that. You just did your 100th episode. Um I mean it's one of my favorite podcasts, incredible for the, the technical and the human psychological wisdom that you guys constantly give and in the way you analyze the world, but also just the chemistry between the between you. You're clearly there's there's a tension and there's a camaraderie that's all all laid out on on the table. So I don't know the two Davids that well, but I have met Jason. What do you love about him? [/INST] I mean, I'll give you a little psychological breakdown of all three of these guys. Um just my opinion and I love you guys um </s><s>[INST] would they agree with your psychological breakdown there? [/INST] I don't know, you know, I think that what I would say about Jaeckel is he is unbelievably loyal um to no end and you know, he's like any of those movies where which are about like the mafia or whatever, where like, you know, something bad is going wrong and you need somebody to show up. That's so </s><s>[INST] if you killed the said proverbial homeless person, he would be right there to help [/INST] the body. But he's the one that he'll defend you in every way, shape or form, even if it's not doesn't make sense in that moment, he doesn't see that is an action of whether it will solve the problem. He sees that as an act of devotion to you, your friend and that's an incredible gift that he gives us. The other side of it is that, you know, Jaekle needs to learn how to trust that other people love him back as much as he loves us and that's where he makes mistakes because he assumes that he's not as lovable as the rest of us, but he's infinitely more lovable than he understands. He's I mean you have to see lex like he is unbelievably funny. I mean I cannot tell you how funny this guy is um next level, funny </s>

<s>[INST] Yeah, I mean, okay, so many things you said are just brilliant or the experiment, experiential blindness, but also from my perspective, like I preach and I tried to practice empathy a lot and something about the way you've explained it makes me almost see it as a kind of exercise that we should all do like to train like to add experiences to the brain to expand its capacity to predict more effectively. So, so like what like what I do is kind of like a method acting thing, which is I imagine what the life of a person is like. Yeah, I just think this is something you see with black lives matter and police officers, it feels like they're both ah not both, but I have because of martial arts and so on. I have a lot of friends score cops, they don't necessarily um have empathy or visualize the experience of the other. Certainly currently unfortunately people aren't doing that police officers, they're not imagining they're not empathizing or putting themselves in the shoes of a police officer to realize how difficult that job is, how dangerous it is, how difficult it is to maintain calm and under so much uncertainty, all those kind of things, [/INST] you know but there's more, there's even that's all that's true, but I think that there's even more, there's even more to be said there. I mean like from a predicting brain standpoint, there's even more that can be said there. So I don't know if you want to go down that path or you on empathy, but I will also say that one of the things that I was most gratified by, I still am receiving, you know, it's been three more than 3.5 years since how emotions are made came out and I'm still receiving daily emails from people, right? So that's gratifying, but one of the most gratifying emails I received was from police officer in texas who told me that he thought that how motions are made um contained information that would be really helpful to resolving some of these difficulties. And he hadn't even read my op ed piece about when is a gun? Not a gun. And you know, like using what we know about the science of perception from predict from a prediction standpoint. Like the brain is a predictor to understand a little differently what might be happening in these circumstances. So there's there's a real what's hard about, it's hard to talk about because everyone gets mad at you when you talk about this, like, you know, and um there is a way to understand this which has profound empathy for the suffering of people of color and that definitely is in line with black lives matter at the same time as understanding the really difficult situation that police officers find themselves in. And I'm not talking about this Bad Apple or that bad Apple. I'm not talking about police officers who are necessarily shooting people in the back as they run away. I'm talking about the cases of really good well meaning cops who have the kind of predicting brain that everybody else has. They're in a really difficult situation that I think both they and the people who are harmed don't realize. I think the the way that these situations are constructed. I think it's just there's a lot to be said there, I guess is what I want. </s><s>[INST] Is there something we can try to say in a sense, like what I'm from the perspective of the predictive brain, just a fascinating perspective to take on this. You know, the all the protests are going on, there seems to be a concept of a police officer being built. [/INST] No, I think that I think that concept is there, </s><s>[INST] but it's it's gaining strength, so it's being re um [/INST] I mean, yeah, </s><s>[INST] yeah, for sure, [/INST] but I think, yeah, for sure. I think that that's right. I think that there's um there's a shift in the stereotype of what I would say is a stereotype. There's a stereotype of a black man in this country that's always in movies and television. Not always, but like, largely um uh that many people watch, I mean, you know, you think you're watching at 10:00 drama and all you're doing is like kicking back and relaxing, but actually you're having certain predictions reinforced and others not. And what's happening, What's happening now with police is the same thing, um that there are certain stereotypes of a police officer that are being abandoned and other stereotypes that are being reinforced by by what you see happening. All I'll say is that if you remember, I mean, there's a lot to say about this really, that, you know, regardless of whether it makes people mad or not. I mean, I just the science is what it is. Um just remember what I said, the brain is makes predictions about internal changes in the body first and then motor, it starts to prepare motor action and then it makes a prediction about what you will see and hear and feel based on those actions. Okay, so it's also the case that we didn't talk about is that sensory sampling, like your brain's ability to sample what's out there is yoked to your heart rate, it's yoked to your heart beats, There are certain phases of the heartbeat where it's easier for you to see what's happening in the world than at others. And so if your heart rate goes through the roof, you will be less let you will be more likely to just go with your prediction and not correct based on what you what's out there, because you're actually literally not seeing as well or you will see things that aren't there basically. </s>

<s>[INST] that really throws a wrench into the whole nature versus nurture because you usually associate electricity with the with the nurture and the hardware with the nature and there's just this weird integrated mess that propagated generations. [/INST] Yeah, it's much more fluid. It's much more complex. Um You can you can imagine what's what's happening here is just just imagine the evolution of of of of an animal like this that that multi skills goes back to this multi scale competency. Right? Imagine that you have to you have an animal that um that where it's it's tissues have some degree of multi scale competency. So for example if the like like we saw in the tadpole, you know if you put an eye on its tail they can still see out of that. I write that. You know, there's all this incredible plasticity. So if you have an animal and it comes up for selection and the fitness is quite good evolution doesn't know whether the fitness is good because the genome was awesome or because the genome was kind of junky but but the competency made up for it right? And things kind of ended up good. So what that means is that the more competency you have, the harder it is for selection to pick the best genomes it hides information. Right? And so that means that uh so so what happens you know evolution starts basically starts although start all the hard work is being done to increase the competency because it's harder and harder to see the genomes. And so I think in plan area what happened is that there's this runaway phenomenon where all the effort went into the algorithm such that we know you got a crappy genome. We can't keep we can't clean up the genome. We can't keep track of it. So what what what's gonna happen is what survives are the algorithms that can create a great worm no matter what the genome is. So everything went into the algorithm and which which of course then reduces the pressure on keeping you know keeping a clean genome. So this idea of right and and two and different animals have this in different two different levels. But this idea of putting energy into an algorithm that does not over train on priors right? It can't assume. I mean I think biology is this way in general evolution doesn't take the past too seriously because it makes these basically problem solving machines as opposed to like exactly what you know to to deal with exactly what happened last time. </s><s>[INST] Yeah problem solving versus memory recall. It's a little memory but a lot of problem solving I [/INST] think so yeah. In many cases </s><s>[INST] problem solving. I mean it's incredible that those kinds of systems are able to be constructed, especially how much they contrast with where we build problem solving systems in the Ai world. Um back to Zeno bots. I'm not sure if we ever described housing robots are built. But you have a paper titled biological robots perspectives on an emerging interdisciplinary field. And the beginning you you mentioned that the words in robots is like controversial. You guys get in trouble for using robots or what do people not like? The words in robots? Are you trying to be provocative with the words in robots versus biological robots? I don't know. This. Is there some drama that we should be aware of? [/INST] There's a little bit of drama. I think. I think the drama is basically related to people um having very fixed ideas about what terms mean. And I think in many cases these ideas are completely out of date with with where science is now and for sure they're they're out of date with what's going to be. I mean these these these concepts are not going to survive the next couple of decades. So if you ask a person and including um you know, a lot of people in biology who kind of want to keep a sharp distinction between biologicals and robots, right? See what's the robot? Well, a robot, it comes out of a factory, it's made by humans. It is boring, It is meaning that you can predict everything it's going to do, it's made of metal and certain other inorganic materials, living organisms are magical. They arise. Right? And so so these these distinctions. I think these these distinctions, I think we're we're never good, but they're going to be completely useless going forward. And so part of there's a couple of papers that that's one paper, there's another one that josh vanguard. And I wrote where we really attack the terminology and we say these binary categories are based on very um non essential kind of surface uh limitations of technology and imagination that were true before. But they've got to go. And so and so we call them. So so Zeno, for whether it's the frog that that these guys are made of. But we think it's an example of of of of a bio about technology. Because ultimately if we if we under once we understand how to uh communicate and manipulate the inputs to these cells, we will be able to get them to build whatever we want them to build. And that's robotics, right? It's it's the rational construction of machines that have useful purposes. I I absolutely think that this is a robotics platform, whereas some biologists don't. But </s><s>[INST] it's built in a way that all the different components of doing their own computation. So in a way that we've been talking about. So you're trying to do top down control that biological systems [/INST] And in the future, all of this will will will merge together because of course, at some point we're gonna throw in synthetic biology circuits, right? New, new, you know, new transcription circuits to get them to do new things. Of course we'll throw some of that. But we specifically stayed away from all of that because in the first few papers and there's some more coming down the pike that are, I think going to be pretty pretty dynamite um that we want to show what the native cells are made of. Because what happens is, you know, if you engineer the heck out of them, right. If we were to put put in new, you know, new transcription factors and some new metabolic machinery and whatever people say, well, okay, you engineered this and you made it do whatever and fine. I wanted to show uh and and and the whole team uh wanted to show the plasticity and the intelligence in the biology. What does it do that surprising before you even start manipulating the hardware in that way? </s>

<s>[INST] And now here's my conversation with Jeremy Howard, What's the first program you ever written? [/INST] This program I wrote that I remember would be at high school. Um I did an assignment where I decided to Try to find out if there were some better musical scales in the normal 12 12 Interval scale. So I wrote a program on my Commodore 64 in basic that search through other scale sizes to see if he could find one where there were more accurate harmonies, </s><s>[INST] like mid tone. [/INST] Like you want an actual exactly 3-2 ratio. Where else with the 12 Interval scale, it's not exactly 3-2 for example. So that in the Commonwealth tempered as they say in the </s><s>[INST] Basic on the Commodore 64. Where was the interest in music from? Or is it just [/INST] take music all my life? So I played saxophone and clarinet and piano and guitar and drums and whatever. So </s><s>[INST] how does that threat go through your life? Where's music today? [/INST] It's not where I wish it was. I for various reasons, couldn't really keep it going, particularly because I had a lot of problems with IRC with my fingers. And so I had to kind of cut back anything that used hands and fingers. I hope one day I'll be able to get back to it health wise. </s><s>[INST] So there's a love for music underlying [/INST] it all. Yeah. </s><s>[INST] What's your favorite instrument? [/INST] Saxophone? Sax, baritone saxophone, Well, probably bass saxophone, but they're awkward. </s><s>[INST] Well, I'm I always love it when music is coupled with programming. There's something about a brain that utilizes those that emerges with creative ideas. So you've used and studied quite a few programming languages. Can you given an overview of what you've used? What are the pros and cons of each? [/INST] Well, my favorite programming environment almost certainly was Microsoft access back in like the earliest days. So that visual basic for applications, which is not a good programming language but the programming environment fantastic. It's like the ability to create user interfaces and tie data and actions to them and create reports and all that as I've never seen anything as good. There's things nowadays like air table which are like small subsets of that which people love for good reason but unfortunately nobody's ever achieved anything like that. </s><s>[INST] What is that? If you could pause on that for a second is it uh database [/INST] database program that Microsoft produced part of office and that kind of withered. You know basically it lets you in a totally graphical way create tables and relationships and queries and tie them to forms and set up event handlers and calculations and it was very complete, powerful system designed for not massive scalable things but for late useful little applications that I loved. </s><s>[INST] So what's the connection between Excel and access [/INST] very close. So access kind of was the relation or database equivalent if you like. So people still do a lot of that stuff that should be an access in Excel because they know what Excel is great as well. So um but it's just not as rich a programming model is feb combined with a relational database. I've always loved relational databases but today programming on top of relational databases just a lot more of a headache. You know you generally either need to kind of you know you need something that connects that runs some kind of database server unless you use sequel light, which has its own issues then you can often, if you want to get a nice programming model, you'll need to create an at an O RM on top and then I don't know there's all these pieces tie together and it's just a lot more awkward than it should be. There are people that are trying to make it easier. So that in particular I think of Sharp Don Syme who him and his team have done a great job of making something like a database appear in the type system. So you actually get like tab completion for fields and tables and stuff like that. Anyway, so that was kind of anyway, so like that whole veba office thing I guess was a starting point which is still a mess. I got into standard Visual Basic. </s><s>[INST] That's interesting just to pause on that for a second. It's interesting that you're connecting programming languages too. The ease of management of data. [/INST] Yeah. </s><s>[INST] So in your use of programming languages, you always had a love and a connection with data. [/INST] I've always been interested in doing useful things for myself and for others, which generally means getting some data and doing something with it and putting it out there again. So that's been my interest throughout. So I also did a lot of stuff with apple script back in the early days. Um, so it's kind of nice being able to okay, the computer and computers to talk to each other and to do things for you and I think that one night the programming language I most loved then would have been Delphi which was object pascal created by Anderson Ellsberg, who previously did turbo pascal and then went on to create dot net and then went on to create typescript. Delphi was amazing because it was like a compiled fast language that was as easy to use this. Visual Basic </s><s>[INST] Delphi, what is it similar to in in more modern languages? [/INST] Visual Basic </s><s>[INST] Visual Basic [/INST] but a compiled fast version. So I'm not sure there's anything quite like it anymore. If you took like C Sharp or java and got rid of the virtual machine and replaced it with something you could compile. A small, tight binary. I feel like it's where Swift could get to with the new Swift UI and the cross platform development going on. Like that's one of my dreams. Is that well, hopefully get back to where Delphi was. There is actually a free pascal project nowadays called Lazarus which is also attempting to recreate Delphi. So they're making good progress. </s>

<s>[INST] It's super nice. Get yours at thera body dot com slash lex. This show is also brought to you by athletic greens and it's a G one drink, I drink it first thing in the morning, I drink it twice a day. It replaced the multivitamin for me. It does a lot of stuff you can check out the vitamins and minerals that got and they keep innovating on the thing too. So they're staying ahead of the science. I should also mention that it's delicious. It's kind of like um [/INST] a </s><s>[INST] reminder to me that I have my life together when everything else is falling [/INST] apart </s><s>[INST] when nothing is working mentally or physically it's just it's just giant chaos. I'm not getting sleep. The diet, it's a nightmare and it's just you know I'm putting my life [/INST] through </s><s>[INST] a a grinder source at times driven by the passion, the passionate pursuit of different curiosities that I have. I just kinda Alice in wonderland. I dive in and hang out with the rabbits but without the L. S. D. And so given all that, The one place I can return to that reminds me that I have my life together at least nutritionally is a flight of queens twice a day and I even travel with it. They have travel packs. It's super easy. They'll give you one month supply of fish oil when you sign up at athletic greens dot com slash [/INST] lex join </s><s>[INST] me brothers and sisters in this nutritional pursuit of a stable healthy life. The show is also brought to you by inside Tracker service. I used to track biological data. They have a bunch of plans, most of which include blood tests that collect data about your body. The blood is a beautiful thing. It has both the current stage of your body and the history of the body. But they also use DNA data, fitness tracker data, all of that using machine learning algorithms to help you plan your life out. The life was falling apart. Maybe like relationships and all that kind of stuff. They can't help you. This is just about your body but maybe in the future we'll be able to collect more and more data from not just the stuff below the neck but the stuff above the neck too meaning the brain getting not just the neuronal signals but the the cognitive stuff. So the high level the things you're worried about maybe would be able to look in to uh the young king shadow of your mind, the unconscious, the subconscious mind and find their large scale data that reveals to you how you can solve that [/INST] puzzle </s><s>[INST] sort of do what psychiatry has always hoped to do but do so systematically. I mean we're probably really really far away from that because I think human biology is super complicated but the human mind is orders of magnitude more complicated. [/INST] But </s><s>[INST] Let's focus on the human biology part and that's what you need. Inside track of four. You can go to inside tracker dot com slash flex for a limited time to get special savings. This episode is also brought to you by eight sleep and its pod pro mattress, it controls temperature with an app. It's back with sensors and it can cool down to as low as 55° and east side of the bed separately. Now the first part of that 55° feels like heaven. Honestly it's uh 100° plus here in Austin I've been running outside sometimes in the afternoon in that heat. Really test the mind really, really test the mind, but I enjoy it. It's fine. It's just, it's just rough mentally, physically it's good. But mentally it's rough, which is fine. It's a good test for the mind. Not when I return [/INST] take a </s><s>[INST] shower, it's so beautifully refreshing. Even in an air conditioned room to lay down on a chilled bed and then with a little bit of a warm blanket, it's just heaven whether we're talking about a power nap or a full night's sleep, it's heaven. You can get your pod pro cover in Usa Canada and the U. K. If you go to sleep dot com slash lex. This show is also brought to you by express VPN. I use them to protect my privacy on the internet. I know you go to all kinds of shady websites, I probably go to them as well. There's no shame in it. We're in this together, life is short. Why not enjoy it? This is bad country after all. But when you do so you should take precautions, use a good VPN and I think the best VPN, my favorite VPN, the one I've used for many, many years religiously before any of this podcast stuff has always been expressed. VPN had still has a big sexy button that when you press, it just works and it works super fast. I mean that's, I guess what you want from VPN. The connection is super fast. The, the interface is intuitive, It works on any device, any operating system including my favorite os, which is Linux. I use most my machines use Bantu matt, M A T E. I just love the interface and then based on the Bond to which is W N B A, it's probably my favorite Linux. I used to use Sushi a lot. Um, Elsie's gentoo. There's a lot. I mean I've used a lot of distributions. And how did this discussion about? Uh, VPN lead me to a discussion of, I don't know. The point is you can go to express VPN dot com slash like spot to get an extra three months free. This selects Friedman podcast to support it. Please check out our sponsors in the description and now your friends, here's joe Rogan Charles. Bukowski said something in a poem called Style [/INST] about </s>

<s>[INST] Earth is a book right? Uh Probably there has to be an ending. I mean there's going to be an end to Earth and it could end in all kinds of ways. It can end soon. You can end later. What do you think of the possible stories? [/INST] We'll definitely there seems to be, yeah, you're sort of </s><s>[INST] it's [/INST] pretty incredible that these self replicating systems will basically arise from the dynamics and then they perpetuate themselves and become more complex and eventually become conscious and build a society. And I kind of feel like in some sense it's kind of like a deterministic wave that, you know, that kind of just like happens on any, you know, any sufficiently well arranged system like Earth. And so I kind of feel like there's a certain sense of inevitability in it. Um and it's really beautiful </s><s>[INST] and it ends somehow. Right? So it's a it's a chemically a diverse environment where complex dynamical systems can evolve and become more more further and further complex. But then there's a certain um what is it? There's certain terminating conditions. [/INST] Yeah, I don't know what the terminating conditions are, but definitely there's a trend line of something and we're part of that story and like where does that, where does it go? So, you know, we're famously described often as a biological boot loader for ai and that's because humans, I mean, you know, we're an incredible biological system and we're capable of computation and uh you know, and love and so on. Um but we're extremely inefficient as well. Like we're talking to each other through audio. It's just kind of embarrassing honestly that we're manipulating like seven symbols serially. We're using vocal cords. It's all happening over like multiple seconds. It's just like kind of embarrassing when you step down to the frequencies at which computers operate or are able to cooperate on. And so basically it does seem like um synthetic intelligences are kind of like the next stage of development and um I don't know where it leads to like at some point I suspect the universe is some kind of a puzzle. And these synthetic a eyes will uncover that puzzle and solve it. And </s><s>[INST] then what happens after right? Like what? Because if you just like fast forward earth many billions of years it's like it's quiet and then it's like normal you see like city lights and stuff like that. And then what happens at like at the end like is it like a pro is it or is it like a calming is it explosion? Is it like [/INST] Earth? Like open like </s><s>[INST] a giant because you said emit roasters will start admitting like like a giant number of like satellites? [/INST] Yes. It's some kind of a crazy explosion and we're living we're like we're stepping through a explosion and we're like living day to day and it doesn't look like it but it's actually if you I saw a very cool animation of Earth and life on Earth and basically nothing happens for a long time. And then the last like two seconds like basically cities and everything and in the lower orbit just gets cluttered and just the whole thing happened in the last two seconds and you're like this is exploding statement explosion. </s><s>[INST] Yeah if you play it at normal speed is it'll just look like an explosion. [/INST] It's a firecracker. We're living in a firecracker </s><s>[INST] where it's going to start emitting all kinds of interesting things and then the explosion doesn't, it might actually look like a little explosion with with lights and fire and energy emitted all that kind of stuff. But when you look inside the details of the explosion there's actual complexity happening where there's like yeah human life or some kind of life [/INST] we hope it's another destructive firecracker. It's kind of like a constructive firecracker. Alright </s><s>[INST] so given that [/INST] I think is </s><s>[INST] hilarious, it [/INST] is a really interesting to think about like what the puzzle of the universe is that the creator of the universe. Give us a message. Like for example in the book contact um Carl Sagan, there's a message for humanity for any civilization in the digits In the expansion of Pi in base 11 eventually which is kind of interesting thought maybe maybe we're supposed to be giving a message to our creator, maybe we're supposed to somehow create some kind of a quantum mechanical system that alerts them to our intelligent presence here because if you think about it from their perspective, it's just say like quantum field theory massive like cellular automaton like thing. And like how do you even notice that we exist? You might not even be able to pick us up in that simulation. And so how do you how do you prove that you exist, that you're intelligent and that you're part of the universe? So </s><s>[INST] this is like a touring test for intelligence from earth. [/INST] Like the </s><s>[INST] creator is uh I mean maybe this is like trying to complete the next word in the sentence. This is a complicated way of that. Like Earth is just is basically sending a message back. [/INST] Yeah, the puzzle is basically like alerting the creator that we exist or maybe the puzzle is just to just break out of the system and just you know, stick it to the creator in some way basically like if you're playing a video game, you can um you can somehow find an exploit and find a way to execute on the host machine any arbitrary code. There's some uh for example, I believe someone got Mario game of Mario to play pong just by uh exploiting it and then um creating uh basically writing writing code and being able to execute arbitrary code in the game. And so maybe we should be, maybe that's the puzzle is that we should be um find a way to exploit it. So so I think like some of these synthetic ads will eventually find the universe to be some kind of a puzzle and then solve it in some way. And that's kind of like the endgame somehow. </s>

<s>[INST] So is it is it correct to think of mass broadly as a kind of storage of energy? Yes You mentioned it's environmentally friendly. So Nuclear fusion is a source of energy. It's cheap clean safe So easy access to fuel and virtually unlimited supply no production of greenhouse gases little radioactive waste produced allegedly [/INST] Can you sort of elaborate why it's cheap clean and safe? Yes Mm-hmm. I'll start with the easiest one cheap It is not cheap yet because it hasn't been made at a commercial scale Ryan flies when you're having fun </s><s>[INST] Yes, Ryan flies when you're having yeah [/INST] But yes, not yet, but talk about actually we'll come back to that because it this is Cheaper or a more technically correct term that it's economic that it's economically interesting is is really the primary Challenge actually a fusion at this point </s><s>[INST] But I think we can get back to that. So what were the other ones you said so cheap we're actually when we're talking about cheap We're thinking like asymptotically like take it forward. Yeah several hundred years That's sort of because of how much availability there is of resources to use of the fuel you have the fuel [/INST] Yeah, we should separate those two the fuel will all the fuel is already cheap. It's basically free, right? Now what I mean by basically free, so if if we were to be using fusion fuel sources to power Your and it's like that's all we had was fusion power plants around and we were doing it the fuel cost per person or something Like 10 cents a year. It's like it's free. Okay This is why it's hard to in some ways I think it's hard to understand fusion because people see this and go oh if the fuel is free This means that energy source is free because we're used to energy sources like this So we, you know, we spend resources and drill to get gas or oil, or we chop wood or we make coal, we find coal or these things, right? So fusion, this is what makes fusion. And it's also, um, it's not an intermittent renewable energy source, like wind and solar. It's just like, but this is, this makes it hard to understand. So if you're saying the fuel is free, why isn't the, like, why isn't the energy source free and it's because of the necessary technologies, which must be applied to basically recreate the conditions which are in stars in the center of stars, in fact. So there's only one natural place in the universe that fusion re fusion energy occurs that's in the center of stars. So that's going to bring a price to it, depending on the cost and, sorry, the size and complexity, uh, of the technology that's needed to recreate those things. </s><s>[INST] And we'll talk about the details of the technologies and which we'll talk We'll talk about the details of the technologies and which parts might be expensive today [/INST] and which parts might be expensive in too many years. Today. Exactly. It will have a revolution, I'm certain of it. So about clean, so clean is at its heart, what it does is converts, it basically converts hydrogen into, it's heavier forms of hydrogen, the most predominant one that we use on Earth and converts it into helium and some other products, but primarily helium is the product that's left behind. So helium, safe, inert, gas, you know. In fact, that's actually what our sun is doing, it's eventually going to extinguish itself because it'll just make so much helium that it doesn't do that. So in that sense, clean because there's no, there's no emissions of carbon or pollutants that come directly from the combustion of the fuel itself. </s><s>[INST] And safe. Safe, yeah. We talk about very high temperature. [/INST] Yeah, yeah, yeah. So this is also the counterintuitive thing. So I told you temperatures which like 50 million degrees or it actually tends to be more like about a hundred million degrees is really what we aim for. So how can a hundred million degrees be safe? And it's safe because it is, this is so much hotter than anything on Earth where everything on Earth is at around 300 Kelvin, you know, it's around a few tens of degrees Celsius. And what this means is that in order to get a medium to those temperatures, you have to completely isolate it from anything to do with terrestrial environment. It can have no contact like with anything on Earth basically. So this means what we, this is the technology that I just described is it fundamentally what it does is it takes this fuel and it isolates it from any terrestrial conditions so that it has no idea it's on Earth. It's not touching any object that's at room temperature. Including the walls of the containment. Even the, including the walls of the containment building or containment designs or even air or anything like this. So it's that part that makes it safe in this and there's actually another aspect to it, but that fundamental part makes it so safe. And in the main lines approach to fusion is also that it's very hot where there's very, very few particles in at any time in the thing that would be the power plant. That actually the more correct way to do it is you say, there's very few particles per unit volume. So in a cubic centimeter and a cubic meter or something like that so we can do this. So right now we're, although we don't think of air really as there's atoms floating around us and there's a density. Because if I wave my hand, I can feel the air pushing against my face. That means we're in a fluid or a gas, which is around us. That has a particular number of atoms per cubic meter. So this actually turns out to be 10 to the 25th. So this is one with 25 zeros behind it per cubic meter. So we can figure out like cubic meters about like this, the volume of this table, like the whole volume of this table. Okay, very good. So like fusion, there's a few of those. So fusion, like the mainstream one of fusion, like what we're working on at MIT will have 100,000 times less particles per unit volume than that. So this is very interesting because it's extraordinarily hot, 100 million degrees, </s>

<s>[INST] So the same kind of design, but now using the superconducting magnets. [/INST] Yeah, and if in fact, if you look at, it's like it's, if you just expand the size of it, they're like, they look almost identical to each other because it's based on the, and actually that comes for a reason by the way, is that it also looks like a bigger version of the Tokamak that we ran at MIT for 20 years, where we established the scientific benefits in fact, of these higher magnetic fields. So that's the pathway that, so we say, so what does this mean? The context is different because it was made, because it's primarily being made by a private sector company spun out of MIT because the way that it raised money and the purpose of the entity which is there is to make commercial fusion power plants, not just to make a scientific experiment. This is actually why we have a partnership, right? Is that our purpose at MIT is not to commercialize directly, but boy, do we want to advance the technology and the science that comes along this and that's the reason we're sort of doing it together. </s><s>[INST] So it's MIT and Commonwealth fusion systems. So what's interesting to say about financing and this seems like from a scientific perspective, maybe not an interesting topic, but it's perhaps an extremely interesting topic. I mean, you can just look at the tension between SpaceX and NASA, for example. It's just clear that there's different financing mechanisms can actually significantly accelerate [/INST] the development of science and engineering. It's great that you brought that up. We use several historic analogs and one of them is around SpaceX, which is an appropriate one because space, you know, putting things into orbit has a minimum size to it and integrated technological complexity and budget and things like this. So, you know, our point when we were like talking about starting like a fusion commercialization, you know, company, people look at you like, isn't this still really just a science experiment, you know? But one of the things that we pointed to was SpaceX to say, well, tell me like 25 years ago, how many people would have voted that, you know, the leading entity on the planet to put things into orbit is a private company. People would have thought you were not so, right? It's like, and what is interesting about SpaceX is that it proved it's more than actually just financing. It's really the purpose of the organization. So the purpose of a, and I'm not against public finance or anything like that, but the purpose of a public entity like NASA correctly, you know, speaks to the political, because the cost comes from the political, you know, assembly that is there and I guess from us eventually as well too, but its purpose wasn't about like making a commercial product. It's about fundamental discovery and so forth, which is all, which is all really great. It's like, why did SpaceX, it's interesting, because why did SpaceX succeed so well is because the idea was, it's like the focus that comes in the idea that you're going to relentlessly like reduce cost and increase efficiency is a drive that comes from the commercial aspect of it, right? And this also then changes the people in the teams which are doing as well too. And in fact, trickles throughout the whole thing because the purpose isn't, while you're advancing things, like it's really good that we can put things in orbit a lot less, more cheaply, like it advances science, which is an interesting synergy, right? You know, it's the same thing that we think is going to happen in fusion, that namely, this is a bootstrap effect that actually, that when you start to push yourself to think about near term commercialization, it like allows the science to get in hand faster, which then allows the commercialization to go faster and up we go. By the way, we've seen this also in another, again, you have to watch out with analogies because they only can go so far, but like biotech is another one. Like you look at the human genome project, which was, it's sort of like, to me that's like mapping the human genome is like that we can make net energy from fusion. Like it's one of those, like in your drawer that you go, this is a significant achievement by humanity, right, in the century. And there's the human genome project, fully government funded, it's gonna take 20, 25 years because we basically know the technology, we're just gonna be really diligent, keep going da, da, da, da. And then all of a sudden what comes along? Disruptive technology, right? You can sequence, you know, shotgun sequencing and computer, you know, recognition patterns. And basically, oh, I can do this a hundred times faster. I'm like, wow, right? So that's really the, you know, to me that the story about why we started, why we launched Commonwealth Fusion Systems was more than just about another source of funding, which it is a different source of funding because it comes, it's also a different purpose, </s>

<s>[INST] How do we how do we fight that? So like a neighboring concept of that is conspiracy theories which is [/INST] I don't think they're neighboring at all. </s><s>[INST] Well, let me, let me give you a sort of naive perspective. Maybe you can educate man this from my perspective, conspiracy theories are these constructs of ideas that go deeper and deeper and deeper into creating worlds where there's uh powerful pedophiles controlling things like these very sophisticated models of the world that you know in part might be true but in large part I would say are are figments of imagination that become really useful constructs and self reinforcing, self reinforcing for them feeding like empowering the trolls to attack the powerful, the conventionally powerful. [/INST] I don't think that that's a function of conspiracy theories. Now let's talk about conspiracy theories because one of my quotes is you take one red pill, not the whole bottle, this concept that everything in life is at the function of a small cadre of individuals would be for many people reassuring because as bad as it looks, you know, they whoever they are, usually the jews aren't going to let it get that bad that they will pull back or the black pill is that they aren't intentionally trying to destroy everything and there's nothing we can do and we're doomed. And there's an amazing book where Arthur Herman called the idea of decline of Western history, It's one of my top 10 books Where he goes through every 20 years, how there's a different population that say it's in the world, here's the proof and very often the proof is something that is kind of self fulfilling, where there's no it's not falsify a ble and we both have to think of ways to falsify their claims from earlier. So it is a big danger. It's a big danger online because very quickly if someone who you thought was good, but now it's bad on one aspect, well they're controlled opposition or they've been uh taken over or they've been kind of appropriated by the bad people, Whoever those bad people would be um I don't know that I have a good answer for this. I don't think it's as pervasive as people think </s><s>[INST] the number of people who believe conspiracy [/INST] there, right? I mean, and also, conspiracy theory is a term used to dismiss ideas that have some currency. The constitutional convention was a conspiracy. The founding fathers got together secretly under swore to secrecy in philadelphia said, we're throwing out the article. Confederation were making your government, right? Yeah, and Luther martin left, and he told everyone this is a conspiracy and they're like, yeah, whatever, Luther martin. So, and Jeffrey Epstein was a conspiracy, harvey Weinstein was a conspiracy. Bill Cosby conspiracy. They all knew they didn't care uh communist infiltration in America. There's a great book by Eugene Lyons called the Red Decade. They all knew every atrocity that was done under stalinism was excused in the west and if you don't believe it, so you've got this crazy anti Russian conspiracy. So it's a term that is weaponized in a negative sense, but that does not at all imply that it does not have very negative real life consequences because it's kind of a cult of one, right? Like I'm at home on my computer, I bought into this ideology. Anyone who doesn't agree with me, they're blind, they're oblivious mom and dad, my friends, you don't get it. We were warned about people like you and I think there's a very heavy correlation. I'm not a psychiatrist of course between that in certain types of mild mental illness. Like, you know, some kind of paranoid schizophrenia, things like that. Because after a certain point, if everything is a function, this conspiracy, it's it's there's no randomness or beauty in life. </s><s>[INST] Yeah, I mean, I don't know if you can say anything interesting about it and in the way of advice of how to take a step into conspiracy theory world without completely going like diving deep, because it seems like that's what happens. People can't look at Jeffrey Epstein, [/INST] I can tell you what the device that has, </s><s>[INST] seriously and rigorously without going, because you can look at Jeffrey Epstein and say there's a deeper thing. You can always go deeper. It's like Jeffrey Epstein was just a tool of uh the lizard people and the lizard people are they say satanists say, uh, in this case, and somehow, recently, very popular pedophiles somehow always involved. I'm not understanding any of that. And I legitimately, I say this both humorously and seriously, I need to look into it. And I guess the bigger question, I'm asking, how does the serious human being, uh, somebody with a position at a respectable university. Like, look at a conspiracy theory and look into it. When I look at somebody like Jeffrey Epstein who had a role at M I. T. [/INST] Yeah, </s><s>[INST] and I and I think I'm not happy, personally, I didn't I wasn't there when Jeffrey Epstein was there, I'm not happy with the behavior of people now about Jeffrey Epstein about the bureaucracy and the everybody's trying to keep quiet hoping it blows over without really looking into any like looking in a deep philosophical way of like how do we let this human being be among us? Can I [/INST] give you a better example? That is kind of conspiratorial, the Speaker of the House, the longest serving Republican Speaker of the House, Dennis Hastert was a pedophile, he went to jail. The democrats don't throw this in the republicans faces every five minutes, not even democratic activists. I find that very, very odd and not what I would predict now, I'm not saying there's some kind of conspiracy, but when it comes to things like sexual predation, which is something that I'm very, very concerned about. I'm an uncle now, my sister just had her second kid recently is adorable. Um it's something that I don't understand. It feels as if there's a lot of people who want this to all go away now. I think it's also because we don't have the vocabulary and framework to discuss it because when you start talking about things like Children in these kind of issues, we want to believe it's all crap because it's for those of us who aren't in this kind of mindset, the idea that this happens to kids and happens frequently is something so horrible that we it's just like, I don't even want to hear it and that does these Children and adult survivors and enormous disservice. So I don't know, they have any particular insight on this, </s>

<s>[INST] this is the opposite of a pandemic is you want in terms of ideas, you want to minimize barriers that prevent the spread. You want to maximize the spread of impact. So like you wanted to to grow when you're doing in technological development is so that you do hold up, that rate holds up and that's all that's almost like uh like an operational challenge of like how you run a company, how you run a group of people is that anyone invention has a ripple that's unstoppable and that ripple effect then has its own ripple effects and so on. And that continues. Like moore's law is fascinating, like on a psychological level, on a human level because it's not exponential, it's it's just a consistent set of like what you call like s curves, which is like, it's constantly like breakthrough innovations nonstop. [/INST] That's a good point. Like it might not actually be an example of exponential because of something which grows in proportion to itself, but instead it's almost like a benchmark that was set out that everybody's been pressured to meet. And it's like all these innovations in micro inventions along the way rather than some consistent sit back and just let the lily pad grow across the lake phenomenon. </s><s>[INST] And it's also there's a human psychological level for sure of like the four minute mile. Like there's something about like saying that, look, there is uh you know, moore's law. It's a law. So like it's uh it's certainly unachievable thing. You know, we've achieved it for the last decade, for the last two decades, the last three decades, you just keep going. Uh, and it somehow makes it happen. It makes people, I'm continuously surprised in this world how few people do the best work in the world. Like in that particular, whatever that field is, it's very often that like the genius, I mean you could argue the community matters, but it's certainly like I've been in groups of engineers were like, one person is clearly like doing an incredible amount of work and just is the genius. And it's fascinating to see basically it's kind of the steve jobs idea is maybe the whole point is uh, to create an atmosphere where the genius can discover themselves. Like, like have the opportunity to do the best work of their life. And yeah, and that the exponential is just milking that it's like rippling the idea that it's possible and that idea that it's possible finds the right people for the four minute mile and the idea that it's possible finds the right runners to run it and then explodes the number of people who can run faster than four minutes. It's kinda interesting too. I don't know, basically the positive way to see that is most of us are way more intelligent, have way more potential than we ever realized. I guess. That's kind of depressing. But I mean like the ceiling for most of us is much higher than we ever realized. [/INST] That is true, a good book to read if you want that senses peak, which essentially talks about peak performance in a lot of different ways like chess, London cabdrivers, how many pushups people can do short term memory tasks. Um and if there's one, it's meant to be like a concrete manifesto about deliberate practice and such, but the one sensation you come out with is wow, no matter how good people are at something, they can get better and way better than we think they could. I don't know if that's actually related to exponential growth, but I do think it's a true phenomenon. </s><s>[INST] That's interesting. Yeah, I mean there's certainly no law of exponential growth and human innovation. Well, I don't know [/INST] what kind of there is like, there's I think it's really interesting to see when innovations in one field allow for innovations in another. Like the advent of computing seems like a prerequisite for the advent of chaos theory. You have this truth about physics in the world that in theory could be known, you could find Lorenzo's equations without computers. But in practice it was just never going to be analyzed that way unless you were doing like a bunch of simulations and that you could computational ec these models. So it's like physics allowed for computers, computers allowed for better physics and wash rinse and repeat that self proportionality. That's exponential. So I think I wouldn't, I don't think it's too far to say that that's a law of some kind. </s><s>[INST] Yeah, a fundamental law of the universe, is that uh these descendants of apes well exponentially improve their technology and one day take be taken over by the G. I. That's something that's built in the simulator, that'll make the video game fun. Whoever created this thing. Uh, I mean, since you're wearing a SpaceX shortly, let me ask. [/INST] I didn't realize that. I apologize. It's on us. That's on top of that. So, </s><s>[INST] Crew Dragon, The 1st crewed mission out into space since the the special though. And just by first time ever by a commercial company. I mean, it's an incredible accomplishment I think, but it's also just an incredible, it inspires imagination amongst people that this is the first step in a long like vibrant journey of humans into space. Oh yeah. So what are your, how do you feel is this is it's just exciting [/INST] to you? Yeah, it is. I think it's great the idea of seeing it basically done by smaller entities instead of by governments. I mean, it's a heavy collaboration between SpaceX and Nasa in this case, but moving in the direction of not necessarily requiring an entire country and its government to make it happen, but that you can have something closer to a single company doing it. We're not there yet because it's not like they're unilaterally saying like we're disputing people up into space. Um it's just a sign that we're able to do more powerful things with smaller groups of people. I find that inspiring innovate quickly. I hope we see people land on mars in my lifetime. I think we will. I think so. I mean I think there's a ton of challenges there, right? Like radiation being kind of the biggest one. And I think there's a ton of people who look at that and say why why would you want to do that? Let's let the robots do the science for us. But I think there's enough people who are like genuinely inspired about broadening like the worlds that we've touched. Um Or people who think about things like backing up the light of consciousness with like super long term visions of terra forming. Like as long as there's </s>

<s>[INST] So you think it's possible, like I was going to ask this again, it may be a very shallow view, but it feels like this country is more divided than it has been in recent history. Perhaps the social media and all those kinds of things are merely revealing the division as opposed to creating the division. But is it possible to have a leader that unites in the same way that FDR did without? Well, we're living through a pandemic. This is already so like I was going to say without suffering, but there this is economic suffering. A huge number of people have lost their job. Is it possible to have? Uh is there one of hunger? Is is there a possibility to have an FDR style leader who unites? [/INST] Yes, I think that is what President biden is trying. I'm not saying, I'm not saying he'll he'll succeed, but I think that's what he's trying to do. The way you do this is you do not allow yourself to be captured by your opponents in Congress or somewhere else. FDR had a lot of opponents in Congress. He had a lot of opponents in politics, Governors and others who didn't like him. Herbert Hoover was still around and still accusing FDR of being, you know, conspiracists and all these other things. So, um you don't allow yourself to be captured by the leaders of the other side. You go over their heads to the people and so today the way to do this is to explain to people and empathize with the suffering and dislocation and difficulties they're dealing with and show that you're trying to help them. Not an easy solution, not a simple statement. But here are some things we can all do together. That's why I think infrastructure makes a lot of sense. It's what FDR invested into. Right. FDR built Hoover Dam, Hoover Dam turned the lights on for young Lyndon johnson who grew up outside of Austin. Right. FDR was the one who invested in road construction. That was then continued by Dwight Eisenhower by a Republican with the Interstate Highway system. Right. FDR invested through the W. P. A. And building thousands of schools in our country, planting trees. That's the kind of work that can bring people together. You don't have to be a democrat or Republican to say, you know what, we'd be a lot better off in my community if we had better infrastructure today, I want to be a part that maybe I can get a job doing that. Maybe my company can benefit from that. You bring people together and that way it becomes a common mission, even if we have different ideological positions. </s><s>[INST] Yeah, it's funny. I have uh, when I first heard joe biden many many years ago, I think he ran for president against Obama and I before I heard him speak, I really liked him, but once I heard him speak, I stopped, I started like him less and less and it speaks to something interesting where it's hard to put into words what why you connect with people the empathy that you mentioned. FDR you have like these bad, pardon the french motherfucker's like teddy Roosevelt that connect with you. There's something just powerful and with joe biden, I can't I want to really like him and there's something not quite there where it feels like he doesn't quite know my pain [/INST] even though he </s><s>[INST] on paper is exactly you know, he knows the pain of the people and there's something not connecting and it's it's hard to explain. It's hard to put into words. And uh it makes me not uh as an engineer and scientist and makes me not feel good about like presidencies because it makes me feel like it's more art than science. [/INST] It is an art. And I think it's exactly an art for the reasons you laid out, its aesthetic, it's about feeling, it's about emotion. All the things that we can't engineer. We've tried for centuries to engineer emotion we're never gonna do. Don't try and I'm a parent of teenagers, don't even try to explain emotion. Um But you hit on the key point of the key challenge for biden. He's got to find the right words. It's not finding the words to bullshit people, it's finding the words to help express. We've all felt empowered and felt good when someone uses words that put into words what we're feeling. </s><s>[INST] Yeah [/INST] that's what he needs. That's the job of a leader </s><s>[INST] and there's certain words, I haven't heard many politicians use those words, but there's certain words that like make you forget that, that you're for immigration or against immigration, make you forget whether you're four wars and against wars, make you forget about like the bickering and somehow like inspire you. Like elevate you to believe in the greatness that this country could [/INST] be um, </s><s>[INST] in that same way. Like the reason I moved to Austin, it's funny to say is like, I just heard words from people, from friends where they're excited by the possibility of the future here. I wasn't thinking like what's the right thing to do? What's like strategic because I want to launch your business. Uh, there's a lot of arguments for san Francisco or maybe staying in boston in my case. But there's this excitement that that was beyond reason. That was emotional. That that that's that's what it seems like. That's what builds, that's what great leaders do. But that's what builds countries. That's what Bill grades great businesses. [/INST] That's right. And it's what people say about Austin for example all the time, a talented people who come here like yourself and here's the interesting thing no one person creates, that the words emerge and part of what FDR understood, you've got to find the words out there and use them. You don't have to be the creator of them, right? Just as the great painter doesn't invent the painting. They're taking things from others. </s>

<s>[INST] And now here's my conversation with Erik Brynjolfsson. You posted a quote on twitter by Albert Bartlett saying that the greatest shortcoming of the human race is our inability to understand the exponential function. Why would you say the exponential growth is important to understand? [/INST] Yeah, that quote, I remember posting that, it's actually a reprise of something Andy Mcafee and I said in the second machine age but I posted it in early March when Covid was really just begin to take off and I was really scared. There were actually only a couple dozen cases maybe less at that time, but they were doubling every like two or three days and you know, I can see, oh my God, this is going to be a catastrophe and it's going to happen soon. But nobody was taking it very seriously or not, a lot of people are taking it very seriously. In fact, I remember I did my last um in person conference that week, I was flying back from las Vegas and I was the only person on the plane wearing a mask and the flight attendant came over to me, she looked very concerned. She kind of put her hands on my shoulder was touching me all over, which I wasn't thrilled about and she goes, you know, do you have some kind of anxiety disorder? Are you okay? And I was like no because of Covid and this is early March, early March. But you know, I was worried because I knew I could see or I suspected I guess that that that doubling would continue and it did and pretty soon we had thousands of times more cases. Most of the time when I use that quote I try to you know, it's motivated by more optimistic things like moore's law and the wonders of having more computer power. But in either case it can be very counterintuitive. I mean if you if you walk for 10 minutes you get about 10 times as far away as if you walk for one minute, you know that's the way our physical world works, that's the way our brains are wired. Um but if something doubles for 10 times as long as you don't get 10 times as much you get 1000 times as much. And after 20 it's a billion. After 30 it's a No. So after 20 it's a million. After 30 It's a billion. And pretty soon after that it just gets to these numbers that you can barely grasp our world is becoming more and more exponential, mainly because of digital technologies. So more and more often our intuitions are out of whack and and that can be good in the case of things creating wonders, but it can be dangerous in the case of viruses and other things. </s><s>[INST] Do you think it generally applies because there are spaces where it does apply and where it doesn't how are we supposed to build an intuition about in which aspects of our society does exponential growth apply [/INST] well. You know you can learn the math but the truth is our brains I think tend to be learned more from experiences so we just start seeing it more and more often. So hang around Silicon Valley, hanging around AI and computer researchers. I see this kind of exponential growth a lot more frequently and I'm getting used to it but I still make mistakes. I still underestimate some of the progress in Just talking to someone about gpt three and how rapidly natural language has improved. But I think that as the world becomes more exponential will all start experiencing it more frequently. The danger is that we may make some mistakes in the meantime using our old kind of caveman intuitions about how </s><s>[INST] the world works. Well, the weird thing is that those kind of looks linear in the moment. Like the everything, you know, it's hard to feel. It's hard to Richard like introspect and really acknowledge how much has changed in just a couple of years or five years or 10 years with the internet if we just look investments of AI or even just social media, all the various technologies that go into the digital umbrella. [/INST] Yeah, </s><s>[INST] it feels pretty calm and normal and gradual and [/INST] a lot of stuff, you know I think there are parts of the world, most of the world that is not exponential you know um the way humans learn the way organizations change the way our whole institutions adapt and evolve. Those don't improve an exponential basis. And that leads to a mismatch oftentimes between these exponentially improving technologies or let's say changing technologies because some of them are exponentially more dangerous and our intuitions and our human skills and our institutions that that just don't change very fast at all. Um and that mismatch I think is at the root of a lot of the problems in our society, the growing you know inequality and uh other other dysfunctions in our political and economic systems. </s><s>[INST] So one guy that talks about exponential functions a lot of musk uh he seems to internalize this kind of way of exponential thinking. He calls the first principles thinking sort of kind of going to the basics asking the question like what were the assumptions of the past? How can how can we throw them out the window, how can we do this 10 x. Much more efficiently and constantly practicing that process And also using that kind of thinking to estimate sort of uh when you know create deadlines and estimate when you'll be able to deliver on some of these technologies now, it often gets him in trouble because he overestimates like he uh he doesn't meet the initial estimates of the deadlines but he seems to deliver late but deliver and which is kind of interesting like what are your thoughts about this [/INST] whole? I think we can all learn from Milan. I think going to first principles, I talked about two ways of getting more of a grip on the exponential function and one of them just comes from first principles. You know if you understand the math of it you can see what's going to happen. And even if it seems counter intuitive that a couple of dozen of covid cases can become thousands or tens or hundreds of thousands of them in a in a month. Um It makes sense once you just do the math. Um And I think Ellen tries to that a lot you know in paris I think also benefits from hanging out in Silicon valley and he's experienced it in a lot of different applications. So you know it's not as much of a shock to him anymore but that's uh that's something we can all learn from uh in my own life. I remember one of my first experiences really seeing it was when I was a grad student in my my adviser asked me to plot the growth of computer power in the U. S. Economy in different industries. And they're all these you know exponentially growing curves and I was like holy sh it look at this each in each industry, it was just taking off and you know you have to be a rocket scientist to extend that and say, wow, this means that this was in the late eighties and early nineties that you know, if it goes anything like that, we're going to have orders of magnitude more computer power than we did at that time. And of course we do </s>

<s>[INST] the following is a conversation with Grant Sanderson his second time in the podcast. He's known to millions of people as the mind behind three blue one Brown, a Youtube channel where he educates and inspires the world with the beauty and power of mathematics. Quick summary of the sponsors dollar shave club doordash and cash app, click the sponsor links in the description to get a discount and to support this podcast, especially for the two new sponsors dollar shave club [/INST] and doordash. </s>

<s>[INST] Australia. So it's not human created noise. [/INST] Yeah. Which is always the worry because actually the same observatory, the Parkes Observatory uh detected a couple of years ago, some signal and then they realized that it comes back at lunch lunchtime and they said, okay, what could it be? And then they figured out that it must be the microwave open in the observatory because someone was opening it before it finished and it was creating this radio signal that they detected with the telescope every lunchtime. Uh So just a cautionary remark. But the reason I think it's human made without getting to the technical details is because of this very short window by which we were transmitting radio signals out of the lifetime of the earth. You know, As I said, 100 years out of 4.5 billion years that the earth existed. So what's the chance that another civilization between civilization of ours is transmitting radio signals exactly the time that we are looking with our radio telescopes 10 to the -7. You know, so, and the other, the other argument I have that is, is that they detected it in a very narrow band of frequencies. And that makes it, and not, it cannot be through natural processes, very narrow band. Just like some radio transmissions that we produce. Um but if it were to come from the habitable zone, from a transmitter on the surface of Proxima B, this is the planet that orbits Proxima centauri. Then I calculated that the frequency would drift through the Doppler effect. Just like when you hear a siren on the street, you know, when the car approaches you, it has a different pitch than when it goes receives away from you. That's the Doppler effect. And when the planet orbits the star Proxima centauri, you would see or detect a different frequency when the planet approaches us as compared to when it receives. So there should be a frequency drift just because of the motion of the planet. And I calculated that it must be much bigger than than observed. So it cannot just be a transmitter sitting on the planet and sending in our direction a radio single unless they want to cancel the Doppler effect, but then they need to know about us because in a different direction, it will not be canceled only in our direction. They can cancel it perfectly. So there is this direction of Proxima centauri. But I have a problem imagining a transmitter on the surface of a planet in the habitable zone meeting. Uh but my main issue is really with the likelihood given what we know about ourselves </s><s>[INST] right in terms of the duration of the civil Copernican principle. Uh so nevertheless this particular signal is likely to be a human interference or perhaps, but uh do you find a Proxima B interesting or the more general question is, do you think we humans will venture out into outside our solar system and potentially colonize other habitable [/INST] planets? Actually, I am involved in a project whose goal is to develop the technology that would allow us to leave the solar system and visit the nearest stars and that is called the star shot. Uh in 2015, May 2015, an entrepreneur from Silicon Valley, Yuri, Milner, came to my office at Harvard and said, would you be interested in leading a project that would do that in our lifetime because as we discussed before to traverse those distances, you know, with existing rockets would take tens of thousands of years and you know, that's too long. You know, for example, to get to Proxima centauri with the kind of spacecrafts that we already sent like new horizons or Voyager one, Voyager two, You need, you you needed to send them when the first humans left Africa, so that they would arrive there now and you know, that that's a long time to wait. So you already wanted to do it within our lifetime, 10, 20 years meaning it has to move at a fraction of the speed of light. So can we send a spacecraft that would be moving at a fraction of the speed of light And I said, let me look into that for six months. Um, and with my students and postdocs, we arrived to the conclusion that the only technology that can do that is the Lightsail technology where he explained, you basically produce a very powerful laser beam on earth. So you can collect sunlight with photovoltaic cells or whatever and then convert it into uh, stall the energy and then produce a very powerful laser beam that is 100 gigawatt uh, and focus it on a sale in space. That is roughly the size of a person, a couple of meters or a few meters that weighs only a gram or a few grams. Very thin. And through the math, you can show that you can propel such a sale. If you shine on it for a few minutes, it will traverse the distance that is five times the distance to the moon and it will get to 1/5 of the speed of light. </s><s>[INST] Sounds crazy, but I've talked to a bunch of people and they're like, I know it sounds crazy but it's actually it will [/INST] work. This is </s><s>[INST] one of those is beautiful. I mean this is, this is science. [/INST] And the point is, people didn't get excited about space since the Polo uh, era and it's about time for us to go into space. A couple of months ago, I was asked to participate in a debate organized by IBM and Bloomberg news. And the discussion centered on the question is the space race between the us and china good for humanity and all the other debaters. We're worried about the military threats, and I just couldn't understand what they're talking about because military threats come from hovering above the surface of the earth, right? And we live on a two dimensional surface. We live on the surface of the Earth. But space is all about the third dimension getting far from Erika. So if you go to mars or you go to a star, another star, there is no military threat. What are we talking about? Space is all about? You know, feeling that, you know, we are one civilization in fact not fighting each other, just going far and having aspirations for something that goes beyond military threats. So why would we be worried that the space race will lead? </s>

<s>[INST] Can can you describe what your view of simply manipulation in its early days? Can you describe expert systems and where do you think they hit a wall or a set of challenges? Sure. [/INST] So I mean first I just want to clarify, I'm not endorsing expert systems per say you've been kind of contrasting them. There is a contrast but that's not the thing that I'm endorsing so expert systems trying to capture things like medical knowledge with a large set of rules. So if the patient has this symptom and this other symptom then it is likely that they have this disease? Um so there are logical rules and they were simple manipulating rules of just the sort that I'm talking about. Um and the </s><s>[INST] bank code, a set of knowledge that the experts and put in [/INST] and very explicitly so so you'd have somebody interview an expert and then Try to turn that stuff into rules. And at some level I'm arguing for rules. But the difference is those guys did in the 80s was almost entirely rules. Almost entirely handwritten with no machine learning. What a lot of people are doing now is almost entirely one species of machine learning with no rules. And what I'm counseling is actually a hybrid. I'm saying that both of these things have their advantage. So if you're talking about perceptual classification, how do I recognize a bottle? Deep learning is the best tool we've got right now. If you're talking about making inferences about what a bottle does something closer to the expert systems is probably still um the best available alternative and probably we want something that is better able to handle quantitative and statistical information than those classical systems typically were. So we need new technologies that are going to draw some of the strengths of both the expert systems and the deep learning but are going to find new ways to synthesize them. </s><s>[INST] How hard do you think it is to add knowledge at the low level. So mine human intellects to add extra information to symbol manipulating systems [/INST] and some domains. It's not that hard, but it's often really hard partly because a lot of the things that are important people wouldn't bother to tell you. So if you pay someone on amazon mechanical turk to tell you stuff about bottles, they probably won't even bother to tell you some of the basic level stuff that's just so obvious to a human being and yet so hard to capture in machines. You know, they're going to tell you more exotic things and like they're all well and good, but they're not getting to the root of the problem. So untutored humans aren't very good at knowing and why should they be what kind of knowledge the computer system developers actually need. I don't think that that's an irremediable problem. I think it's historically been a problem. People have had crowdsourcing efforts and they don't work that well, there's one at MIT, we're recording this at MIT called virtual home where and we talk about this in the book, find the exact example there, but um people were asked to do things like describe an exercise routine and the things that that people describe it are very low level and don't really capture what's going on. So they're like go to the room with the television and the and the weights, turn on the television press or press the remote to turn on the television lift weight, put weight down, it's like very micro level and it's not telling you what an exercise routine is really about, which is like I want to fit a certain number of exercises in a certain time period. I want to emphasize these muscles. You want some kind of abstract description. The fact that you happen to press the remote control in this room when you watch this television isn't really the essence of the exercise routine. But if you just ask people like what did they do, then they give you this fine grain. And so it takes a level of expertise um about how the AI works in order to craft the right kind of knowledge that there's </s><s>[INST] this ocean of knowledge that we all operate on? Some of them may not even be conscious or at least we're not able to communicated effectively. [/INST] Yeah, most of it, we would recognize if somebody said it if it was true or not, but we wouldn't think to say that it's true or not. </s><s>[INST] It's a really interesting uh mathematical property. This ocean has the property that every piece of knowledge in it. We would recognize it as true if we were told, but we're unlikely to retrieve it uh in the reverse. So that that interesting property, I would say there's a huge ocean of that knowledge. What's your intuition? Is it accessible to AI system somehow. Can we? [/INST] I mean most of it is not, I'll give you an asterisk on this in a second, but most of it is not ever been encoded in machine interpret herbal form. And so I mean, if you say accessible, there's two meanings of that. One is like, could you build it into a machine? Yes. The other is like, is there some database that we could go, you know, um, download and sticking towards the first thing? You know, </s><s>[INST] could could we is what's [/INST] interesting. We could, I think it hasn't been done right. You know, the closest and this is the asteroid is the CYC psych system. Try to do this. A lot of magicians work for Doug Lennon for 30 years on this project. I think they stuck too closely to logic, didn't represent enough about probabilities, tried to hand coded their various issues and it hasn't been that successful. That is the closest existing system to trying to encode this. </s>

<s>[INST] Yeah, I mean, okay, the superset part is just, I mean, there's so much brilliant stuff here. That definitely is incredible. We'll talk about that. First of all, how's the typing implemented differently in Python versus Mojo? So this heterogeneous flexibility, you said, is definitely implemented. [/INST] First of all, how is it definitely implemented? Yeah. So I'm not a full expert in the whole backstory on types in Python. So I'll give you that. I can give you my understanding. My understanding is basically, like many dynamic languages, the ecosystem went through a phase where people went from writing scripts to writing large scale, huge code bases in Python, and at scale, it kind of helps to have types. People want to be able to reason about interfaces. What do you expect to string or an int? These basic things, right? And so what the Python community started doing is it started saying, okay, let's have tools on the side, checker tools. Right? To go and enforce some variants, check for bugs, try to identify things. These are called static analysis tools generally, and so these tools run over your code and try to look for bugs. What ended up happening is there's so many of these things, so many different weird patterns and different approaches on specifying the types and different things going on that the Python community realize and recognize, hey, hey, hey, there's a thing here. And so what they started to do is they started to standardize the syntax for adding types to Python. Now, one of the challenges that they had is if they're coming from kind of this fragmented world where there's lots of different tools, they have different trade-offs and interpretations and the types mean different things. And so, if you look at types in Python, according to the Python spec, the types are ignored, right? So, according to the Python spec, you can write pretty much anything in a type position, okay? And technically, you can write any expression, okay. Now, that's beautiful because you can extend it. You can do cool things. build your own tools, you can build your own house, linter or something like that, right? But it's also a problem because any existing Python program may be using different tools and they have different interpretations. And so if you adopt somebody's package into your ecosystem, try around the tool you prefer, it may throw out tons of weird errors and warnings and problems just because it's incompatible with how these things work. Also because they're added late and they're not checked by the Python interpreter, it's always kind of more of a hint than it is a requirement. Also the CPython implementation can't use them for performance and so it's really- </s><s>[INST] That's a big one, right? So you can't utilize for the compilation, [/INST] for the just in time compilation. Okay. Exactly. And this all comes back to the design principle of it's, they're kind of hints, they're kind of the definitions a little bit murky. It's unclear exactly the interpretation in a bunch of cases. And so because of that, you can't actually, even if you want to, it's really difficult to use them to say like, it is going to be an int and if it's not, it's a problem, right? A lot of code would break if you did that. So in Mojo, right. So you can still use those kinds of type annotations, it's fine, but in Mojo if you declare a type and you use it, then it means it is going to be that type and the compiler helps you check that enforce it and it's safe. </s><s>[INST] And it's not, it's not a best effort hint kind of a thing. So if you try to shove a string type thing into an integer- You get an error. And you get another. [/INST] From the compiler at compile time. You get an error. </s><s>[INST] And you get another. Nice. [/INST] Okay, what kind of basic types are there? Yeah, so Mojo is pretty hardcore in terms of what it tries to do in the language, which is the philosophy there is that we, again, if you look at Python, Python's a beautiful language because it's so extensible. And so all of the different things in Python, like for loops and plus, and all these things can be accessed through these underbar and bar methods. Okay, so you have to say, okay, if I make something that is super fast, I can go all the way down to the metal. Why do I need to have integers built into the language? And so what Mojo does is it says, okay, well, we can have this notion of structs. So you have classes in Python, now you can have structs. Classes are dynamic, structs are static. Cool, we can get high performance, we can write C++ kind of code with structs if you want. These things mix and work beautifully together. But what that means is that you can go and implement strings and ints and floats and arrays and all that kind of stuff in the language, right? And so that's really cool because, you know, to me as a idealizing compiler language type of person, what I wanna do is I wanna get magic out of the compiler and put it in the libraries. Because if somebody can, you know, if we can build an integer that's beautiful and it has an amazing API and it does all the things you'd expect an integer to do, but you don't like it, maybe you want a big integer, maybe you wanna like sideways integer, I don't know, like what all the space of integers are, then you can do that and it's not a second-class citizen. And so if you look at certain other languages like C++, one I also love and use a lot, int is hard-coded in the language, but complex is not. And so it's kind of weird that, you know, you have this STD complex class, but you have int. And complex tries to look like a natural numeric type and things like this, but integers in floating point have these like special promotion rules and other things like that, they're magic and they're hacked into the compiler. And because of that, you can't actually make something </s>

<s>[INST] So if you look back, you probably spent 10s of thousands of hours on the map, spilled sweat blood, even tears maybe maybe a few times. So technically or philosophically how would you do any of those hours differently Just looking back at the tens of thousands of hours. [/INST] I would be more probably in my older age, I probably would have been more relaxed in my training and probably would have won another cycle if I could do it over again. Um, in 96, I really thought that when Gable retired that I would be the next guy in line and I was wrong. And that was immature of me </s><s>[INST] in terms of the coach, [/INST] in terms of the coach. Yes. And I knew that gable was close. I mean, I didn't know when, but it just so happens, you know, 97 was his record breaking year and then he retired, but I didn't know how close he was, but I knew that he had, you know, he went down with a bad hip injury and, and so you know, you're just, you're, you're not gonna, </s><s>[INST] so what is, what is the relaxed tom brands looks like you're saying you would, you would have been a [/INST] little more relaxed more like where you know what, I was pretty damn good and I was getting better every day, but maybe doing a little bit different, a little bit smarter and terry actually did that going through 2000, he had to do it and he would have been in in the, you know, the funny farm, let alone, uh, you know, the physical farm, whatever you want to say mentally and physically beat up. But um, he had to learn to less is more type approach and how it came around was, is, you know, you work hard at feeling good, you work hard in your recovery. So even when you're not wrestling hard in that wrestling room and looking for the toughest partner to go, you're still working hard in your recovery and massage could be that stretching could be that, um, things like that that are more fluffy </s><s>[INST] and that's something you weren't as good at. [/INST] Never, never, there's not a place for it with young people because in my opinion, there's so much development have happened. I mean, when, when you need to learn wrestling, you need to be wrestling and as you get older, um, your body won't do it anymore. And so to learn wrestling, it's more of a, probably a relaxed approach. </s><s>[INST] So if you had to choose between two athletes Who would dominate competition, one who drills 100,000 reps of a specific take down specific technique Or one that spends that time live wrestling [/INST] both. Um, it's the same. And I like to live wrestling, I was always wanted and I've wrestled, bring the warm up into the live wrestle, let's go. Uh, but where I got really, really good was a repetition and I was disciplined enough to know that the things that you hate to do in this sport are the things that make you the very best and that is a rare ingredient as I've gotten older and you spend a lot of time communicating that to younger athletes. </s><s>[INST] So the thing, if you feel yourself hating something, that's probably the thing you should be doing. [/INST] Yes. As a matter of fact, I had a strength coach when I was really young, he was just a rick and guy that when he wore white, like he was almost like a nurse, nurse's clothes, he wore all white from head to toe and he was in Cheyenne Wyoming and his first name was walt and he talked terri and I hate the bar away from you on that last rep when you're dead and whether it's a curl, you hate it up and then you do the negative and you hate it down and you hate that bench up and you hate it, you look at the bar and you hate it away from you. So you know, I learned that I was young, I was young and um I remember being born, my mom's sister lived out there and we were dropped off to stay out there with our cousins and I was born a little bit and they always treated us really good, but this was like the the single most um bright spot in a, in a weightlifting like enlightenment, even though I lifted weights, but I never knew the psychology behind lifting weights, it's just to look good and so you can flex and look in the mirror or is it for performance? And this guy was about performance. </s><s>[INST] And you said repetition, Do you mean technique? [/INST] I'm talking repetition, technique, technique, technique, drill drill drill, hit, hit, dry finish, hit dr finished. </s><s>[INST] So you believe in that. You believe [/INST] in that whole heartedly. </s><s>[INST] So I mean, [/INST] I believe that you have to do it on your own. I don't believe in the coach taking you to the promised land. </s><s>[INST] So in the guys today or in yourself, how often do you see people that grow the belief of doing 10,000 20,000 reps? [/INST] I think it's rare. I think it's very rare and I think it's especially rare. I mean you can talk about that as a coach, but it's especially rare to bring a guy to that understanding, but you never stop trying, you're always trying to reach him. I mean, we didn't have a good performance out there tonight, but you know what? You don't stop communicating. There's a lot of programs out there that put their head down when things aren't going their way and then as things start going their way, then they rise with the tide. There was no difference in the demeanor that of our corner and we talk about that's a philosophy. And so you're reaching your guys that way. Um so go back to your point or your question, you know, do you believe in the, in the 10,000 reps. And yes I do. And </s>

<s>[INST] so when you say ancient lakes an impact craters the simple question so impact crater is a crater created by a giant rock hitting the planet [/INST] and yes the big rock that can be metal or rock or it can be a comment as well mostly ice </s><s>[INST] so is that good for life for bad for life foreboding life in book is destroying them both [/INST] it's actually both interestingly enough the building blocks of life the bricks the stuff we are made of carbonate region oxygen and nitrogen and phosphorus the where included on our planet they will be built in just because our planet is made of this kind of rocks asteroids and comets coming together but what we call a Christian so they will be Austin when an asteroid cubs there is a lot of destruction going on but at the same time those rocks they bring with them those breaks of life and the creates lots of energy N. eve the environment around is favorable you might possibly be have some sitting going on that's one of the aspect of what we call been spared you which used to the fact that comets and asteroids have the building blocks of life and better than them and that given favorable conditions they might be able to see that's this is a theory </s><s>[INST] what percentage of you when you're looking up at the stars and wondering about this stuff thinks that panspermia has is what happened on Mars or are on earth which is the building blocks of life came from elsewhere [/INST] well that's you know that's the thing pence is a vector potential vector which means that he actually distribute the stuff of life left and right but it doesn't explain the origin of life it does it's not the environment itself it's just promotes maybe and we still have to prove this but what we know is that the stuff we are made of is very abundant all over the place including in interstellar medium so it's all over it's all over the idea is that maybe just waits to have the proper environment and we know what it needs here on earth it needs water it needs energy shelter a nutrient </s><s>[INST] so you're fundamentally interested in the origin of life and the big leaps that in evolutionary history that could be like an origin of something origin of your curry at sea origin of photosynthesis origin of whatever I just think if we're civilization here on earth only survive another few hundred years I think I'll be a good idea to take a big gun and just shoot life out there like a life gun basically tragically passed by me as a good backup solution so one way is to actually copy our brains an actual humans some complex information and send it out there another way to preserve life is just the like send the basic building blocks cinnamon you bacteria bunch of whatever the rugged organisms on earth just send a bunch of the lease on the building blocks it they they are actual organism so what what is that initial cut or do or do we want to because you said building blocks everywhere [/INST] yeah the bricks of live the carbon nitrogen the tow truck of the they where produced by the death of previous stars so this is how they were produced and stars like our sun I started to form ten billion years ago that doesn't mean that the the sun is the only kind of start that produce you know life for animals life but actually was produced in ten billion years ago that what you're talking about is is a little different right now there are many many efforts to do the type of thing you're talking about which she used to put our DNA on what whatever kind of substrate and preserve it involves either indifference place on earth or on the moon some people are already thinking about putting the NFL on the moon as far as brands concerned and it's drawing towards transhumanism which she is the hence ment of we are through a I and machine learning of course having backups is a good thing for me I would say that taking care of our planets and going back to a place where we are in the Calabria with our environment would be also maybe the best backup possible inclusion do it's sayings right now we are like teenagers who is enough brain to create cool tools but we don't have enough brain to understand yet the consequences of what we're doing N. right now we're paying for this so the question is whether we are going to be able to move forward and learn from the mistakes we're making to become a mature civilization you probably heard of the Drake equation that would be the L. at the very end the duration </s><s>[INST] which version of intelligence of the station [/INST] exactly and and or I'd least the length of time a civilization remains detectable it can disappear from the radar screen literally for a number of reasons the first one is destroy itself for being destroyed by external events or you can become so in tune and sat with the universe and sweat vents the disappears because emails really in the background and it's not visible anymore there are some wild theories they're saying that an exposition might be so advanced that you cannot distinguish them from physical prostheses N. </s><s>[INST] A. [/INST] this was an example doesn't say that this is the case but some people say imagine that in fact all the doctor matter that we we see wait wait we theorized about is in fact some sort of a biological process so you can think about the number of thing personally I believe that what you talk about about preserving our information is kind of what life does we we need to look at ourselves as the different of what the legal sale that started off was in this is what tells you not about the origin of life but in fact the nature of life which is a lot more interesting to me </s>

<s>[INST] to undermine that, it affects everything else. We need to have our scientific mind about us, about these foundational ideas. But I guess my sense of hope comes from observing the immune system respond to wokeism. There seems to be a pro-liberalism immune system. And not only that, so like there's intellectuals, there's people that are willing to do the fight. You talk about courage, being courageous. And there is a hunger for that, such that those ideas can become viral and they take over. So I just don't see a mechanism by which wokeism accelerates exponentially and takes over, like it's expand. It feels like as it expands, the immune system responds. The immune system of liberalism, of basically a country, at least in the United States, that's still ultimately at the core of the individual values the freedom of speech, just freedoms in general, the freedom of an individual. [/INST] But that's the battle, which is stronger. So to me it is like a virus in an immune system. And I totally agree, I see the same story happening. And I'm sitting here rooting for the immune system. Are you still worried? Well, here's the thing. So a liberal democracy is always gonna be vulnerable to a movement like this, right? And there will be more. Because it's not a totalitarian dictatorship. Because if you can socially pressure people to not say what they're thinking, you can suddenly start to just take over, right? You can break the liberalism of the liberal democracy quite easily and suddenly a lot of things are illiberal. On the other hand, the same vulnerability, the same system that's vulnerable to that, also is hard to truly conquer. Because now the Maoists, right, similar kind of vibe. They were saying that science is evil and that the intellectuals are, it's all this big conspiracy. But they could murder you. And they had the hard cudgel in their hand, right? And the hard cudgel is scary. And you can conquer a country with the hard cudgel. But you can't use that in the U.S. So what they have is a soft cudgel, which can have the same effect initially. You can scare people into shutting up. You can't maybe imprison them and murder them. But if you can socially ostracize them and get them fired, that basically is gonna have the same effect. So the soft cudgel can have the same effect for a while, but the thing is, it's a little bit of a house of cards because it relies on fear. And as soon as that fear goes away, the whole thing falls apart, right? The soft cudgel requires people to be so scared of getting canceled or getting whatever. And as soon as some people start, you know, Toby Lutka of Shopify, I always like think about, you know, he just said, you know what, I'm not scared of this soft cudgel, and spoke up and said, we're not political at this company and we're not a family, we're a team and we're gonna do this. And, you know what, like they're thriving. </s><s>[INST] He will be on this podcast, he seems like a fascinating human. He's amazing. [/INST] He spoke up, he's saying we're not deficit moving. He's amazing. He spoke up, he's saying we're not deficit moving. He's one of the smartest and kindest dudes, but he's also, he has courage at a time when it's hard. But here's the thing is that it's different than that you need so much less courage against a soft cudgel than you'd do. The Iranians, throwing their hejabs into the fire. Those people's courage just blows away any courage we have here, because they might get executed. That's the thing, is that you can actually have courage right now, and it's, so don't worry about it. </s><s>[INST] Oh man, the irony of that. And you talk about, so two things to fight this, there's two things, awareness and courage. [/INST] What's the awareness piece? The awareness piece is under, first just know understanding the stakes, like getting your heads out of the sand and being like, technology's blowing up exponentially. Our society's trust is devolving, we're kind of falling apart in some important ways. We're losing our grip on some stability at the worst time. That's the first point, just the big picture. And then also awareness of, I think this vertical axis, or whatever your version of it is, this concept of how do I really form my beliefs? Where do they actually come from? Are they someone else's beliefs? Am I following a checklist? How about my values? I used to identify with the blue party or the red party, but now they've changed and I suddenly am okay with that. Is that because my values changed with it or am I actually anchored to the party, not to any principle? Asking yourself these questions. Looking for where do I feel disgusted by fellow human beings? Maybe I'm being a crazy tribal person without realizing it. How about the people around me? Am I being bullied by some echo chamber without realizing it? Am I the bully somewhere? So that's the first, I think just to kind of do a self audit. And I think that just some awareness like that and just self audit about these things can go a long way. But if you keep it to yourself, it's almost useless because if you don't have, awareness without courage does very little. So courage is when you take that awareness and you actually export it out into the world and it starts affecting other people. And so courage can happen on multiple levels. It can happen by first of all, just stop saying stuff you don't believe. If you're being pressured by kind of a ideology or a movement to say stuff that you don't actually believe, just stop, just stay in your ground and don't say anything. That's courage, that's one first step. Start speaking out in small groups, start actually speaking your mind, see what happens. The sky doesn't usually fall. Actually, people usually respect you for it, like not every group, but you'd be surprised. And then eventually, maybe start speaking out in bigger groups, start going public, go public with it, and you don't need everyone doing this. Some people will lose their jobs for it. I'm not talking to those people. Most people won't lose their jobs, but they have the same fear as if they would, right? And it's like, what, are you gonna get criticized or are you gonna get a bunch of people, angry Twitter people will criticize you? Like, yeah, it's not pleasant, but actually that's a little bit like our primitive minds fear that really, back when it was programmed, that kind of ostracism or criticism will leave you out of the tribe and you'll die today. It's kind of a delusional fear. It's not actually that scary. And the people who have realized that </s>

<s>[INST] uh uh what's his name? Chris Latner, who's a google uh oh he's not google anymore sci fi. He's legit. He's one of the most legit engineers. I talked about. I talked with him again on this podcast and whether he gives me a private advice a lot and you said for this podcast, I should like interview like I should widen the range of people because that gives you much more freedom to do stuff like so his idea which I think I agree with chris is that you go to the extremes, you just like cover every extreme base and then it gives you freedom to then go to the more nuanced conversations. It's kind of I think there's a safe place for that. There's certainly a hunger for that nuanced conversation. I think amongst people were like on social media you get canceled for anything slightly tense that there is a hunger to go full [/INST] you go so far to the opposite side. It's like demystifies it a little bit. Yeah, there is a person behind all of these things </s><s>[INST] And that's the cool thing about podcasting, like 3, 4 hour conversations that that it's very different than a Clickbait journalism take the opposite that there's a hunger for that. There's a willingness for that. [/INST] Especially now, I mean, how many people do you even see face to face anymore? Right? Like this, You know, it's like not that many people, like in my day today, aside from my own family, but like I said across </s><s>[INST] it's sad, but it's also beautiful. Like, I've gotten a chance to like, like our conversation now, there's somebody I guarantee you there's somebody in Russia listening to this now, like jogging. There's somebody who is just smoke some weed, sit back on the couch and just like enjoying, like, I guarantee you that will write in the comments right now, that yes, I'm in ST Petersburg, I'm in Moscow and whatever and were in their head and dave have a friendship with us and I'm the same way I'm a huge fan of podcasting. It's a beautiful thing. I mean, it's a it's a weird one way human connection. Like before I went on, Joe Rogan, Uh and still I'm just a huge fan of his, so, it was like, we had been friends with Joe Rogan for 10 years. But one way [/INST] from this way from the, from the ST Petersburg way </s><s>[INST] at the same place, but it's a real friendship uh I mean now it's like two way but it's still surreal. It's uh and that's the magic of podcasting. I'm not sure what to make of it. That voice. It's not even the video part. It's the audio. That's magical. That I don't know what to do with it, but it's, people listen to 34 hours. [/INST] We evolved over millions of years, right? To be very fine tuned things like that, right? Um, expressions as well? Of course. Right? But uh, you know, back back in the day on the, you know, on the savannah, he had to be very tuned to, you know, whether you have a good relationship with the, with the rest of your tribe or a very bad relationship, right? Because if you have a very bad relationship, you're probably going to be left behind and eaten by the lions. But </s><s>[INST] it's weird that the tribe is different now. Like you could have a connect one way connection with joe Rogan as opposed to the tribe of your physical vicinity. [/INST] But that's, but that's why I like, you know, it works with the podcasting, but it's the opposite of what happens on twitter, right? Because all those nuances are removed, right? You're not connecting with the person because you don't hear the voice, you are connecting with like an abstraction, right? It's like some, some stream of tweets, right? And it's very easy two assigned to them and you kind of like evil intent or dehumanize them, which is, it's much harder to do when it's a real voice, right? Because thank you realize it's a real person behind the Voice. </s><s>[INST] Let me uh, try this out on you. I sometimes ask about the meaning of life. Do you, your, your father now, uh, engineer, You're building up a company to ever zoom out and think like, what the hell is this whole thing for? Like why why are we descended into vapes even on this planet? What's, what's the meaning of it all? [/INST] That's a pretty big question. I think I don't allow myself to think about it too often. Or maybe like life doesn't allow me to think about it too often. Um, but in some ways, I guess the meaning of life is kind of, uh, contributing to this kind of weird thing we call humanity, right? Like it's in a way I can think of humanity is like a living and evolving organism, right? That like we all contributing as far away, but just by existing by having our own unique set of desires and drives, right? Um, and maybe that means like creating something great and it's bringing up kids who, you know, are unique and different and seeing like, you know, taking joy in what they do. Um, but I mean, to me that's pretty much it, I mean if you're not a religious person, right? Which I guess I'm not, um, that's, that's the meaning of life. It's in the living and then the creation and the creation. </s>

<s>[INST] does seem to have a kind of direction it is taking us, that's somehow perhaps is defined by the environment itself, it feels like we're headed or something like we're playing out a script that was just like a single cell defines the entire organism. It feels like from the origin of Earth self, it's playing out a kind of script, you can't really go any other way. I [/INST] mean, so this is very controversial and I don't know the answer, but people have, people have argued that this is called, you know, sort of rewinding the tape of life, right? And and some people have argued, I think, I think, I think Conway Morris maybe has argued that it is that there's a deep attractor, for example, to human to the human um kind of structure and that and that if you were to rewind it again, you basically get more or less the same thing. And then other people have argued that no, it's, it's incredibly sensitive to frozen accidents and then once certain stochastic decisions are made downstream, everything is gonna be different. I don't know, I don't know, you know, we're we're very bad at predicting attractors in the space of complex systems, generally speaking, right, we don't know, so may, so maybe evolution on Earth has these deep attractors that no matter what has happened, pretty much would likely to end up there are maybe not, I don't know what's </s><s>[INST] A really difficult idea to imagine that if you ran earth a million times 500,000 times you would get Hitler [/INST] like we </s><s>[INST] don't like to think like that we think like because at least maybe in America you like to think that individual decisions can change the world and if individual decisions can change the world, then surely any perturbation results in a totally different trajectory. But maybe there's a in this competency hierarchy. It's a self correcting system that's just ultimately, there's a bunch of chaos that ultimately is leading towards something like a super intelligent artificial intelligence system. The Answers 42. I mean there might be a kind of imperative for life that is headed to and we're too focused on our day to day life of getting coffee and snacks and having sex and getting a promotion at work, not to see the big imperative of life on earth that is headed towards something. [/INST] Yeah, maybe, maybe I don't, I don't, it's it's it's difficult. I think I think one of the things that's important about chi America by engineering technologies, all of those things are that we have to start developing a better science of predicting the cognitive goals of of composite system. So we're just not very good at it, right? We we don't know uh if if if if I create a composite system and this could be internet of things or swarm robotics or a cellular cellular swarm or whatever, what is the emergent intelligence of this thing first of all, what level is it gonna be at? And if it has goal directed capacity, what are the goals going to be like? We are just not very good at predicting that yet. And I think that uh it's it's um it's a it's a existential level uh need for us to be able to, because we're building these things all the time, right? We're building, we're building both physical structures like swarm robotics and we're building uh social financial structures and so on. We with very little ability to predict what sort of autonomous goals that system is going to have of which we are now and so, Right. So, so learning, learning to predict and control those things is gonna be critical. So, in fact, so if you're right and there is some kind of a tractor to evolution, it would be nice to know what that is and then to make a rational decision of whether we're gonna go along or we're going to pop out of it or to try to pop out of it because there's no guarantee. I mean, that's that's that's the other, you know, kind of important thing. A lot of people, I get a lot of complaints from people email me and say, you know what you're doing, uh it isn't natural, you know, and I'll say, look natural, That would be nice if if some he was making sure that natural was was was matched up to our values, But no one's doing that by, you know, evolution optimizes for biomass, That's it. Nobody's optimizing, it's not optimizing for your happiness. That's I don't think it necessarily, it's optimizing for for for intelligence or fairness or any of that stuff. </s><s>[INST] I'm going to find that person that emailed you, beat them up, take their place, um steal everything they own and say now we're this is natural. [/INST] This is natural. Yeah, exactly. Because because it comes from it comes from a from an old world view where you could assume that whatever is natural that that's probably for the best. And I think we're long out of that garden of Eden kind of view. So I think we can do better. We I think we and we have to write natural just isn't great for for a lot of a lot of life forms. </s><s>[INST] What are some cool synthetic organisms that you you think about? You dream about when you think about embodied mind, what do you imagine? What do you hope to build? [/INST] Yeah. On a practical level, what I really hope to do is to gain enough of an understanding of the embodied intelligence of the organs and tissues such that we can achieve a radically different regenerative medicine so that we can say basically. And I think about it as um, you know, in terms of like, okay, can you, what's the what's the uh what's the goal kind of uh and and end game for this whole thing to me, the end game is something that you would call an anatomical compiler. So the idea is you would sit down in front of the computer and you would draw the body or the organ that you wanted, not not molecular details, but like this is what I want. I want a six legged, uh, you know, frog with a propeller on top or I want, I want a heart that looks like this or I want a leg that looks like this. And what it would do if we knew what we were doing is put out, convert that anatomical description into a set of stimuli that would have to be given to cells to convince them to build exactly that thing, right, I probably won't live to see it, but I think it's achievable. And I think that if if we can have that, then that is basically the solution to all of medicine except for infectious disease. So birth defects, right, traumatic injury, cancer, aging, degenerate disease. If we knew how to tell cells what to build all of those things go away. So those things go away and the positive feedback spiral of economic costs where all of the advances are increasingly more heroic and expensive interventions of a sinking ship when you're like 90 and and and and so on. Right, All of that goes away because basically, instead of trying to fix you up as you, as you degrade you, you you progressively regenerate, you know, you you apply the regenerative medicine early before things degrade. So I think that that will have massive economic impacts over what we're trying to do now, which is not at all, you know, sustainable and uh and that that's what I hope. I hope that I hope that we get so, so to me, yes, the nanobots will be doing useful things, cleaning up the environment, cleaning out, you know, your, you know, your joints and all that kind of stuff. But more important than that, I think we can use these uh synthetic systems to try to understand to to to to develop a science of detecting and manipulating the goals of collective intelligences, of cells specifically for regenerative medicine. And then sort of beyond that if we, you know, sort of think further beyond that, what I hope is that kind of like what you said, all of this drives a reconsideration of how we formulate um ethical norms because this old school. So, so so in the olden days, what you could do </s>

<s>[INST] So this is almost like a little glimpse into the early history of [/INST] earth. Okay, </s><s>[INST] cool. So what are the chances that volcano on earth destroys all of human civilization? Maybe I wanted to sneak in that question. [/INST] A volcano on earth? Um </s><s>[INST] Do you think about that kind of stuff when you just study volcanoes elsewhere? Because then it kind of humbling to see something so powerful and so hot, so unpleasant for humans and then you realize we're sitting on many of them here, [/INST] Right? Yeah. Yellowstone is a classic example. I don't know what the chances are of that happening. My intuition would be that the chances of that are lower than the chances of us getting wiped out by some other means that the tire, you know that maybe it'll happen eventually. There will be one of these massive volcanoes on earth, but we'll probably be gone by then by some other means not to sound bleak, but </s><s>[INST] that's very comforting. Okay, can we talk about Europa is there? Um, so maybe, can you talk about the intuition, the hope that people have about life beyond europe maybe also. What are the things we know about it? What are things to you that are interesting about that particular moon of jupiter? [/INST] Sure, Europa is from many perspectives, one of the really interesting places in the solar system among the solar system moons. So there are a few, there has, there's a lot of interest in looking for or understanding the potential for life to evolve in the subsurface oceans. I think it's fairly widely accepted that the chances of life evolving on the surfaces of really anything in the solar system is very low. Um, the radiation environment is too harsh. Um, and they're just not liquids on the surface of most of these things and it's, I can honestly accepted that liquids are required for life. Um, and so the subsurface oceans in addition to maybe titan's atmosphere, the subsurface oceans of the icy satellites are one of the most plausible places in the solar system for life to evolve. Um, Europa and Enceladus are interesting because for many of the big satellites, so Ganymede and Callisto, also, satellites of jupiter also are thought to have subsurface oceans. But um they are so they have these ice shells and then there's an ocean underneath the ice shell. But on those moons around Ganymede, we think that there's another ice shell underneath. And then there's rock. And the reason that that is a problem for life is that your ocean is probably just pure water because it's trapped between two big shells of ice. Uh so Europa doesn't have this ice shell at the bottom of the ocean, we think. And so the water and rock are in direct interaction. And so that means that you can basically dissolve a lot of material out of the rock. You potentially have this hydrothermal activity that's injecting energy and nutrients for life to survive. And so this rock water interface is considered really important for the potential habitability. </s><s>[INST] Mhm. As a small aside, you kind of said that it's economically assume that uh like water is required for life, is it possible to have life uh like in the volcano, remember people are uh like in that National Geographic Program or something kind of hypothesizing that you can really have life anywhere. So as long as there's a source of heat source of energy. Do you think it's possible to have life in a volcano, like no water, [/INST] I think anything's possible. I think it's so water, it doesn't have to be water. That sort of you can tell as you identified, I phrase that really carefully. It's economically accepted that because we recognize that, you know, scientists recognize that we have no idea what broad range of life could be out there and all we really have is our biases of life as we know it. But for life as we know, it is very helpful to have or even necessary to have some kind of liquid and preferably a polar solvent that can actually dissolve molecules, something like water. So the case of liquid methane on titan is less ideal from that perspective, but you know, liquid magma. If it stays liquid long enough for life to evolve, you have a heat source, you have a liquid, you have nutrients in theory that checks your three classic astrobiology boxes. Um </s><s>[INST] That'd be fascinating to be fascinating. If it's possible to detect it easily, how would we detect if there's life on Europa is um is it possible to do in a non contact way from a distance, the telescopes and so on. Or do we need to send robots and do some drilling? [/INST] I think realistically you need to do the drilling um There's so Europa also has these long tectonic features on its surface where it's thought that um there's potential for water from the ocean to be somehow making its way up onto the surface. And you could imagine some out there scenario where there's bacteria in the ocean, it's somehow working its way up through the ice shell, it's spilling out on the surface. It's being killed by the radiation. But your instrument could detect some spectroscopic signature of that dead bacterium, but that's, you know, that's many ifs and assumptions. </s><s>[INST] That's a hope, because then you don't have to do that much drilling. You can collect from the surface, [/INST] right or skeleton. I'm even remotely </s><s>[INST] remotely. Yeah, that's sad that there's this single cell civilization living underneath all that ice, trying, trying trying to get up, trying to get out. [/INST] So, Enceladus gives you a slightly better chance of that because Enceladus is a is a moon of Saturn and its broadly similar to europe. In some ways, it's an icy satellite, has a subsurface ocean that's probably in touch with the rocky interior, but it has these massive geysers at its south pole where it's spewing out material that appears to be originating all the way from the ocean. And so in that case you could potentially fly through that plume and scoop up that material and hope that at the velocities you'd be scooping it up, You're not destroying any signature of the life you're looking for. Um But let's say that you have some ingenuity and can come up with a way to do that. You know, it potentially gives you a more direct opportunity at least to try to measure those bacteria directly. </s>

<s>[INST] I mean, you're you're avoiding the word, the use of the word consciousness for example, but the experience is referring to the subjective experience. So it's it's the actual technical use of the word consciousness of of [/INST] an objective experience. And even that word, there's certain ways that like, like sort of like if you're talking about access consciousness or narrative self awareness, which is an aspect of like you can wrap a definition around that we can talk meaningfully about it. But so often around psychedelics, it's used in this much more, you know, in terms of ultimately explaining phenomenal consciousness itself. The so called hard problem, you know, uh relating to that question, and psychedelics really haven't spoken to that. And that's why it's hard because like it's hard to imagine anything. But I think what I was getting is the psychedelics have done this by the reason I was getting into the biology versus mind psychology divide, is that just to kind of set up the fact that I think all of our experience is related to these biological events, so whether they be naturally occurring neurotransmitters like serotonin and dopamine and norepinephrine, et cetera. And and a whole other sort of biological activity and kind of another layer up that we could talk about network activity, communication amongst brain areas like this is always going on. Even if I just prompt you to think about a loved one, You know, like there's something happening biologically. Okay, so that's always another side of the coin. So another way to put that is all of our subjective experience outside of drugs, it's all a controlled hallucination in a sense, like this is completely constructed our our experience of reality is completely a simulation. So I think I think we're on solid ground to say that that's our best guess. And that's a pretty reasonable thing to to say scientifically </s><s>[INST] take all the rich complexity of the world emerges from just some biology and some chemicals. [/INST] So and you know that that definition implied causation it comes from. And so that's that's what we know. At least there's a solid correlation there. And so then we don't dig we delve deep into the philosophy of like idealism or materialism and things like this, which I'm not an expert in. But I know we're getting into that territory. You don't even necessarily have to go, they're like you at least go to the level of like OK, we know there's there seems to be this one on one correspondence and that seems pretty solid. Like you can't prove a negative and you can't, you know, it's fun in that category of like you could come up with an experience that maybe doesn't have a biological correlate. But then you're talking about there's also the limits of the sciences that a false negative, but I think our best guess and a very decent assumption is that every psychological event has a biological correlate. So with that said, you know, the idea that you can throw alter that biology in a pretty trivial manner. I mean you could take like a relatively small number of these molecules throw them into the nervous system and then have a 60 year old person who has you name it. I mean that has hiked To the top of Everest and that speaks five languages and that has been married and has kids and grandkids and has, you know, you know, like being at the top and say this fundamentally changed who I am as a person and the, and what I think life is about like that's, that's the thing about psychedelics that just floors me and it never fails. I mean sometimes you get bogged down by the paperwork and running studies and all the, I don't know all of the Bs that can come with being in academia and everything. And then you and sometimes you get some duds sessions where it's not the full, all the magic isn't happening. And it's, you know, more or less it's or it's either a dud or somewhere. And I don't mean to dismiss them. But you know, it's it's not like these magnificent sort of reports, but sometimes you get the full monty report from one of these people and you're like, oh yeah, that's why we're doing this, whether it's like therapeutically or just to understand the mind and you're like, you're still floored. Like how is that possible. How did we slightly alter sarah too energetic new york transmission And say and this person is now saying that they're they're they're making fundamental differences in the priorities of their life after 60 years. </s><s>[INST] It also just fills you with all of the possibility of experiences were yet to have uncovered if if just a few chemicals can change so much. It's like man, what if this could be up to, I mean like because we're just like took a little, it's like lighting a match or something in the darkness and you can see there's a lot more there but you don't know how much more [/INST] and that's and then like where is that going to go with? Like, I mean I'm always like aware of the fact that like we always as humans and as scientists think that we figured out 99% and we're working on that 1st 1% and we gotta keep reminding ourselves, it's hard to do. Like we figured out like not even 1% like were we know nothing. And so like I can't, I can speculate I might sound like a fool, but like what are drugs, Even the concept of drugs like 10 years, 50 years, 100 years, 1000 years if we if we're surviving like you know, molecules that go to a specific area of the brain in combination with technology in combination with the magnetic stimulation. In combination with the, you know, like targeted pharmacology of like oh like this subset of serotonin two A receptors in the classroom, you know, at this time in this particular sequence in combination with this other thing like this baseball cap you wear that like has you know, you know has has one of the is doing some of these things, we can only do with these like giant like pieces of equipment now, like where it's going to go is going to be endless. And it becomes easy to combined with in virtual reality where the virtuality is going to move from being something out here to being more in there. And then we're getting like we talked about before, we're already in a virtual reality in terms of human perception and cognition, models of the of the universe being all representations and you know sort of color not existing and just are representations of E. M um wavelengths etc, et cetera, you know, sound being vibrations and all of this. And so as the external VR and the internal VR come closer to each other like this is what I think about in terms of the future of drugs, like all of this stuff sort of combines and and like where that goes is just it's it's unthinkable. Like we're probably gonna you know, again it might sound like a fool and this may not happen, but I think it's possible, you know, to go completely offline like where most of people's experiences maybe going into these internal worlds and I mean maybe you through through some through a combination of these techniques, you create experiences where someone could live 1000 years in terms of maybe they're living a regular lifespan, but over the next two seconds you're living 1000 years worth of experience </s>

<s>[INST] What is testing looked like. What are we talking about here? Like what's what's a loop of test like a from start to finish? What is a loop of testing? Yeah, [/INST] I mean, I think there's a whole philosophy to testing, there's the unit tests and you can do that on a hardware, you can do that in a small piece of code. You write one function, you should write a test that checks that functions input outputs. You should also write an integration test at the other extreme of of running the whole system together. You know where that that try to turn on all the different functions that you think are correct. It's much harder to write the specifications for a system level test, especially if that system is as complicated as a humanoid robot. But the philosophy is sort of the same. I'm the real robot. Um it's no different, but on a real robot, it's impossible to run the same experiment twice. So if you if you see a failure, you hope you caught something in the logs that tell you what happened, but you'd probably never be able to run exactly that experiment again. And right now, I think our philosophy is just yeah, basically monte Carlo estimation is just run as many experiments as we can maybe try to set up the environment to uh to make the things we are worried about happen as often as possible. But really we're relying on somewhat random search in order to test maybe that's all we'll ever be able to. But I think uh because there's an argument that the things that will get you are the things that are really nuanced in the world and they'll be very hard to for instance, put back in a simulation. </s><s>[INST] Yeah, I guess the edge cases. What what was the hardest thing like so you said, walking over rough terrain like that just taking footsteps. I mean people, it's so dramatic and painful in a certain kind of way to watch these videos from the drc of robots following. Yeah, I just so heartbreaking. I don't know. Maybe it's because for me at least we anthropomorphize the robot. Um of course is one of the funny for some reason like humans falling is funny uh for I don't it's some dark reason I'm not sure why it is so but it's also like tragic and painful and uh, so speaking of which, I mean, what, what made the robots fall and fail uh, in your view. [/INST] So I can tell you exactly what happened. And we, I contributed, one of those are team contributed to one of those spectacular falls. Um, every one of those falls, the has a complicated story. I mean at one time the power effectively went out on the robot because it had been sitting at the door waiting for a green light to be able to proceed and its batteries, you know, and therefore it just fell backwards and smashed his head on the ground. And it was hilarious, but it wasn't because of bad software, right? Um, but for ours, so the hardest part of the challenge, the hardest task in my view, was getting out of the polaris was actually relatively easy to drive the polaris. We can tell the story started to </s><s>[INST] interrupt the story of the car. People should watch this video. I mean, the thing you've come up with is just brilliant. But anyway, sorry, what's [/INST] uh, yeah, we, we kind of joke, we call it the big robot little car problem because somehow the race organizers decided to give us a £400 humanoid. And they also provided the vehicle, which is a little polaris and the robot didn't really fit in the car. So you couldn't drive the car with your feet under the steering column. We actually had to straddle the main column of the uh and have basically one ft in the passenger seat, one ft in the driver's seat and then drive with our left hand. But the hard part was we had to then park the car, get out of the car. Uh it didn't have a door that was okay, but it's just uh getting up from crouched from sitting when you're in this very constrained environment. </s><s>[INST] Uh First of all, I remember after watching those videos, I was much more cognizant of how hard is it it is for me to get in and out of the car and out of the car, especially like it's actually really difficult control problem. Yeah, and I'm very cognizant of it when I'm like [/INST] injured for whatever </s><s>[INST] reason. Yeah. So how did you, how [/INST] did you approach? So we had uh, you know, you think of um Nasa's operations and they have these checklists, you know, pre launch checklist and they're like, we weren't far off from that. We had this big checklist. And on the first day of the competition, we're running down our checklist. And one of the things we had to do, we had to turn off the controller, the piece of software that was running that would drive the left foot of the robot in order to accelerate on the gas. And then we turned on our balancing controller and the nerves jitters On the first day of the competition, someone forgot to check that box and turned that controller off. So we used a lot of motion planning to figure out a sort of configuration of the robot that we get up and and over. We relied heavily on our balancing controller and, and basically there was when the robot was in one of its most precarious, you know, sort of configurations trying to sneak it's big leg out of the, out of the side, the other controller that thought it was still driving, told it's left foot to go like this and and that wasn't good. Um but but it turned disastrous for us because what happened was A little bit of push here actually if we have videos of us, you know, running into the robot with a 10-foot pole and it kind of will recover. But this is a case where there's no space to recover. So a lot of our secondary balancing mechanisms about like take a step to recover, they were all disabled because we were in the car and there's no place to step. So we're relying on our just lowest level reflexes and even then I think just hitting the foot on the seat on the, on the floor, we probably could have recovered from it. But the thing that was bad that happened is when we did that and we just a little bit the tailbone of our robot hat was only a little off the seat, it hit the seat and the other foot came off the ground just a little bit and nothing in our plans had ever told us what to do if your butts on the seat and your feet are in the </s>

<s>[INST] Sorry, spike timing dependent plasticity. Yeah, that's just a [/INST] STD. It's a particular learning rule that uses spike timing to figure out how to determine how to update the Synapses. So it's kind of like if the synapse fires into the neuron before the neuron fires, then it strengthen the synapse. And if the synapse fires into the neurons shortly after the neuron fired, then it becomes the synapse. Something along this line. I'm 90% sure it's right. So if I said something wrong here don't don't get too angry, </s><s>[INST] but you sounded brilliant while saying it. But the timing, that's one thing that's missing. The temporal dynamics is not captured. I think that's like a fundamental property of the brain is the timing of the of the signals [/INST] were recorded neural networks. </s><s>[INST] But you think of that as I mean, that's a very crew simplified uh what's that called? There's a clock, I guess to uh recurrent neural networks. It this seems like the brain is the general of the continuous version of that. The generalization where all possible timings are possible And then within those timings is contained some information you think recurrent neural networks, there are currents in recurrent neural networks can capture the same kind of phenomena as the timing that seems to be important for the brain in the in the firing of neurons in the brain. [/INST] I mean, I think I think recurrent recurrent neural networks are amazing and they can do I think they can do anything. We would want them to if you want a system to do right now. Recurrent neural networks have been superseded by transformers but maybe one day they'll make a comeback. Maybe it'll be back. We'll see. </s><s>[INST] Let me uh a small change and say, do you think they'll be back? So, so much of the breakthroughs recently that we'll talk about on uh natural language processing on language modeling has been with transformers that don't emphasize recurrence. Do you think recurrence will make a comeback? [/INST] Well, some kind of recurrence I think very likely recurrent neural networks for process as there typically thought of for processing sequences? I think it's also possible. </s><s>[INST] What is to you? A recurrent neural network And generally speaking, I guess. What is the recurrent neural network? [/INST] You have a neural network which maintains a high dimensional hidden state. And then when an observation arrives it updates its higher dimensional hidden state through its connections in some way. </s><s>[INST] So, do you think, you know that's what like expert systems did? Right, symbolic. Ai the knowledge based growing a knowledge base is maintaining a hidden state which is its knowledge base and it's growing it by some question process. Do you think of it more generally in that way? Or is it simply is it the more constrained form of of a hidden state with certain kind of gating units that we think of as today with L S D M S and that, [/INST] I mean the hidden state is technically what you described there. The hidden state that goes inside the LSD em or they are running or something like this. But then what should be contained? You know, if you want to make the expert system analogy, I'm not, you could say that the knowledge story in the connections and then the short term processing is done in the in the hidden state. </s><s>[INST] Yes, could you say that? So I sort of do you think there's a future of building large scale knowledge bases within the neural networks? Definitely. So we're gonna pause in that confidence because I want to explore that. Let me zoom back out and ask, mm back to the history of image. Net neural networks have been around for many decades. As you mentioned, what do you think were the key ideas that led to their success, that image in that moment and beyond The success in the past 10 years. [/INST] Okay, so the question is to make sure I didn't miss anything, the key ideas that led to the success of deep learning over the past 10 years. </s><s>[INST] Exactly. Even though the fundamental thing behind deep learning has been around for much longer. [/INST] So, the key idea about Deep learning, or rather, the key fact about deplaning before deep Learning started to be successful is that it was underestimated people who worked in machine learning simply didn't think that new neurons could do much. People didn't believe that large neural networks could be trained. People thought that well, there was lots of, there was a lot of debate going on in machine learning about what are the right methods and so on, and people were arguing because there were no, there were no, there was no way to get hard facts and by that, I mean, there were no benchmarks which were truly hard, that if you do really well in them and you can say, look, here is my system, that's when you switch from, that's when this field becomes a little bit more of an engineering field. So, in terms of deep learning to answer the question directly, the ideas were all there. The thing that was missing was a lot of supervised data and a lot of compute, once you have a lot of civil rights data and a lot of compute, then there is a third thing which is needed as well. And that is conviction, conviction that if you take the right stuff, it already exists and apply and mixed with a lot of data and a lot of compute that it will in fact work. And so that was the missing piece. It was you had the you need the data, he needed to compute, which showed up in terms of gpu s and you needed the conviction to realize that you need to mix them together. </s>

<s>[INST] that Marcus is [/INST] wrong. So, first point correlation studies consistently show a link, they almost all do, but it's not big equivalent to a correlation coefficient around 0.0.1 typically. Um that's the first point. The second point um is that um the the correlation is actually much larger than for eating potatoes. So that famous line wasn't about social media use, that was about digital media use. That included watching netflix doing homework on everything. And so what they did is they looked at all screen use and then they said this is correlated with Self reports of depression, anxiety and like you know .03 it's tiny. Um And but they said that clearly in the paper but the media has reported as social media is point oh three or tiny and that's just not true. What I found digging into it. You don't know this until you look at the more than 100 studies in the google doc. Once you dig in, what you see is okay you see a tiny correlation. What happens if we zoom in on just social media? It always gets bigger. Often a lot bigger. Two or three times bigger. Um What happens if we zoom in on girls and social media? It always gets bigger. Often a lot bigger. And so um what I think we can conclude in fact what one of the authors of the potato studies herself concludes amy or been says I have a quote from here. She reviewed a lot of studies and she herself said that quote the associations between social media use and well being therefore range from about R equals 10.15 to R equals 0.1. Oh. Um so that's the range we're talking about and that's for boys and girls together. Um and a lot of research, including hers and mine show that girls it's higher. So for girls we're talking about correlations around .152.2 I believe Jean Twenge and I found it's about .2 or .22. Now this might sound like an arcane social science debate, but people have to understand public health correlations are almost never above 0.2. So the correlation of childhood exposure to lead an adult I. Q. Very serious problem. That's point oh nine, like the world's messy and our measurements are messy. And so if you find a consistent correlation of 90.15, like you would never let your kid do that thing. That actually is dangerous. And it can explain when you multiply it over 10s of millions of kids spending years of their lives, you actually can explain the mental health epidemic just from social media use </s><s>[INST] well. And then there's questions by the way, uh this is really good to learn because I quit potatoes and it had [/INST] no uh </s><s>[INST] it's a rush and that was a big sacrifice. Um They're quite literal actually because I'm mostly eating keto these days. But that's that's that's funny that they're actually literally called the potato studies okay. But given this and there's a lot of fascinating data here. There's also a discussion of how to how to fix it. What are the aspects? Yeah. That if fixed would start to reverse some of these trends. So if we just linger on the side of the Mark Zuckerberg statements. So first of all, do you think Mark is aware of some of these studies? So if you if you put yourself in the shoes of Mark Zuckerberg and the executives that facebook and twitter, how can you try to understand the studies like the google docs you put together to try to make decisions that fix things? Is there a stable science now that you can start to investigate? And and also maybe if you can comment on the depth of data that's available because ultimately this is something you argue that the data should be more transparent, should be provided. But currently if it's not, all you have is maybe some leaks of internal data. Um and we could talk about the potential you have to be very sort of objective about the potential bias and those kinds of leaks you want to. It would be nice to have a non leaked data like like [/INST] yeah, it'd be nice to be able to actually have academic researchers able to access in de individuated de identified form. Um the actual data on what kids are doing and how their mood changes and and you know, when people commit suicide, what was happening before, it would be great to know that we have no idea. </s><s>[INST] So what how do we begin to fix social media would you say? [/INST] Okay, so here's the most important thing to understand in the social sciences? You know, we say, is social media harmful to kids. That's a broad question, you can't answer that directly. You have to have much more specific questions. You have to operationalize it and have a theory of how it's harming kids. And so almost all of the research is done on what's called the dose response model. That is everybody including the most researchers are thinking about this. Like let's treat this like sugar. Um, you know, because the data usually shows a little bit of social media use isn't correlated with harm, but a lot is so, you know, I think that like sugar and if kids have a lot of sugar, then it's bad. So how much is okay. Um, but social media is not like sugar at all. It's not a dose response thing. It's a complete rewiring of childhood. So We evolved as a species in which kids play in mixed age groups, they learn the skills of adulthood. They're always playing and working and learning and doing errands. That's normal childhood. That's how you develop your brain. That's you become a mature adult until the 1990s in the 1990s, we dropped all that we said it's too dangerous if we let you outside, you'll be kidnapped. So we completely, we began rewiring childhood in the 90s before social media and that's a big part of the story. I'm a big fan of lenore Skenazy who wrote the book, free range kids. If there are any parents listening to this please by Eleanor's book, free range kids and then go to let grow dot org. It's a nonprofit that lenore and I started with Peter Gray and, and Daniel Shiffman to help change the laws and the norms around letting kids out to play. They need free play. So that's the big picture. They need free play. Uh, and we started stopping that in the nineties that we reduced it and then gen Z kids point in 1996 they're the first people in history to get on social media before puberty. Um, millennials didn't get until they were in college, but gen z, they get it because you can lie, you just lie about your age. Um, they, so they really began to get on around 2000 and 2010 and boom, two years later they're depressed. It's not because they eat too much sugar necessarily. It's because even normal social interactions that kids had in the early two thousands largely. Well they decline because now everything is through the phone and that's what I'm trying to get across that. It's not just a dose response thing. It's imagine imagine one middle school where everyone has an instagram account and it's constant drama. Everyone's constantly checking and posting and worrying and imagine going through puberty that way versus imagine there was a policy, no phones in school, you have to check them in a locker, no one can have an instagram account, all the parents are on board, parents only let their kids have instagram because the kid says everyone else has it and thats we're stuck in a social dilemma. We're stuck in a trap. So what's the solution? Keep kids off until they're done with puberty. There's a new study actually by Amy or been and Andy Schablitsky showing that the damage is greatest For girls between 11 and 13, so there is no way to make it safe for preteens or even 13, 14 year olds we've gotta kids should simply not be allowed on these business models Where you're the product, they should not be allowed until you're 16. We need to raise the Agent enforce it, that's the biggest thing. </s>

<s>[INST] Well, I think it can actually, it's funny with the two books you can actually get a pretty deep understanding if you read and also think deeply about it. It allows you to approach a thing from First Principles a lot, a lot of times if you're a quote unquote expert, you get um get carried away by the momentum of what the field has been thinking about versus like stepping back, alright, what is really going on that the challenge is to pick the right to books, [/INST] so that usually what I'll try to find somebody who knows the topic pretty well and have them recommend or a couple of people and have them recommend books. So a couple years ago I knew nothing about Bitcoin, I was at a conference and uh a couple of people who you've had on your show actually were there and I asked them, give me your top three books on Bitcoin. And so then I went, I read like nine books on Bitcoin and so if you're nine books on Bitcoin, you at least know enough to get by. Uh and so that so I can actually explain what Bitcoin is and why it works or why it doesn't work in some cases and and what's happening in the markets that way. So that that's, you know, very, very helpful. </s><s>[INST] Well, Putin is an example, that's a difficult one to find the right books on, I think the news are, is the one I read where was the most objective [/INST] when I read, I think about Putin was one called Strong Man. It was it was very highly critical of Putin but it gave like a good background on him. </s><s>[INST] Yeah, so I'm very skeptical sort of things that are very uh they're critical of Putin because it feels like there's activism injected into the history, like the way the rise and fall of the Third Reich is written about Hitler, I like because there's almost not a criticism of Hitler, it's a description of Hitler which is very um it's easier to do about a historical figure which with William shire with the Rise and Fall of the Third Reich is impressive because he lived through it, but it's very tough to find objective descriptions about the history of the man in a country of Putin. Zelensky of any difficult trump is the same and I feel [/INST] like that's the hero villain archetype and it's like either somebody's completely a hero or completely a villain and the truth is pretty much no one is completely a hero or completely a villain. People, in fact, I'm not sure that I love descriptions of people as heroes or villains generally. I think that people tend to do heroic things or do villainous things in the same way that I'm not sure. I love descriptions of people as a genius. My dad used to say that when I was growing up, he used to say they didn't believe that they were geniuses, he said he believed that there were people with a genius for something because people, you know, yes there are people who are very high I. Q. And we call them geniuses, but does that mean that they're good at eQ stuff. Not necessarily but there are people who are geniuses at eq stuff in other words. It would be more specific to say that somebody is a genius at engineering than to say just broad spectrum their genius. And that does avoid the problem of thinking that they're good at something that they're not good at, right. It's a little more specific. </s><s>[INST] So because you read a lot of books that there, can you look back and it's always a tough question because so many, it's like your favorite song. But are there books that have been influential in your life that impact on your thinking? Or maybe once you go back to that, um, that still carry inside for you, [/INST] The Federalist papers, a big one in terms of sort of how american politics works. The 1st, 2nd book that I thought was really great because it was written for teenagers essentially is one called Economics in one lesson by Henry Hazlitt, like 100 and 50 pages, I recommend it to everybody sort of 15 and up. It's it's easier than say thomas Sowell's Basic Economics is four or 500 pages and </s><s>[INST] it's looking like. [/INST] Um and uh and then uh in terms of there's there's a great book by Karl Truman called Rise and Triumph for the Modern Self, which I think is the best book in the last 10 years that's been sort of impactful on some of the thoughts. I've been having the key ideas that we've shifted the nature of how identity is done in the west from how it was historically done that basically for nearly all of human history. The way that we identify as human beings is as a mix of our biological drives and then how that interacts with the social institutions around us. And so when you're a child, you're a bunch of unfettered biological drives. And it's your parents job to civilize you and civilize you literally means bring you into civilization, right? You learn the rules of the road. You learn how to integrate into institutions that already exist and are designed to shape you. And it's how you interact with those institutions that makes you you it's not just a set of biological drives. And then in the modern world, we've really driven toward the idea that what we are is how we feel on the inside without reference to the outside world. And it's the job of the outside world to celebrate and reflect what we think about ourselves on the inside. And so what that means is that we are driven now toward fighting institutions because institutions are in positions so everything around us societal institutions. These are these are things that are cramping our style. They're making us not feel the way that we want to feel. And if we just destroy those things, then we'll be freer and more liberated. It's a it's a I think much deeper model of how to think about why our social politics particular moving in a particular direction, is that a ground shift has happened and how people think about themselves? And and this has had some some some what kind of shocking effects in terms of social politics. </s>

<s>[INST] I tried to uh tried to deeply empathize with a lot of experiences of other people and like one of the things I love like the smell of paper books and books in general and early on this is like five years ago, I just gave away all my books and I said, you know, I'm really going to try to fall in love with the books in the same way I did before, but now with the Kindle or not a Kindle, paperwhite, whatever the I e book reader, the reader and um I'm still not there, but I've been kind of trying to follow up with that experience and the same way I try to think like teenagers are really into Tiktok now, like making these short videos, I try to consider the possibility that their existence will be much happier one than I've had because of this kind of interaction. It's for my sort of skeptical perspective, it's like the attention span is so short, they don't really deeply think or deeply experienced things. They construct uh a social layer that they present to the world and they work on creating this social layer, like the presentation to the world much more than really sitting alone with their thoughts and the sadness is and their hopes and dreams and fears and like working on the project that is there their own like actual person that exists in this physical world as opposed to work on the project of a particular social platform. But they show, but like perhaps that project, like who cares who you are in the physical space, maybe what you are, is what your instagram shows, that's the more important project to work on. Well, what's reality is reality [/INST] perception is reality, right? So how other people perceive this constructed thing, That's their reality of you. But is it your reality like that? I mean like we said earlier, it's what, what you want, how you want people to see you, it's very rarely in line with how you really are or how you see yourself. And I mean I can remember being like a 13 year old kid and like when you go through a bunch of, you know, weird 13 year old kid shit, like sitting in my room like turning a red light on and listening to like a sad record and like you know, trying to figure out what's going on inside. Sometimes you like it sometimes you don't like it. But I feel like those experiences are lost on kids constantly connected to a phone and like, you know, I don't know what the remedy for those situations is nowadays. Like, I don't know, do they make a Tiktok video, Do they blog about it? Do they, you know, make a video or </s><s>[INST] nobody blogs anymore bro? [/INST] Whatever man or a video? A story about this is what happened to me and blah blah blah blah blah. Does that actually help them work it out or does it just create more noise and more static on how to get to the root of the problem and learn about themselves. </s><s>[INST] I don't know what future social networks are exactly. I do know on a shallow of it does feel good when somebody clicks like on something. I think that is more of a drug than an actual deep, long lasting fulfilling happiness. But perhaps there's a way to make a social network that does lead to long lasting happiness that's somehow detached from the physical meat space. I don't know, but it feels like you want to give that a chance. [/INST] Do you think when people are liking things on social media, do you think there's just a group of people, an overwhelming majority of people that are gonna like, whatever you put out there, they're clicking like and then there's another section of people that just constantly scroll and like scroll and like and scrolling. Like, like do you think when you get a like on content you put out that that like perhaps came from someone who normally doesn't like your content, but like, you've just changed their mind on something like you you've turned them around on it. I tend to think that when I get likes on social media, those are just the people that like all my ship no matter what I say. Like they probably don't even read it. Like I could, you know, put the most preposterous thing up there and you're still gonna get a handful of the same exact likes </s><s>[INST] that's interesting. But I I kind of the way she likes, you're kind of you said multiple things, I think in one sense, you see social media is like a battleground of ideas and like, is a kind of indicator like the best possible, like, is an indicator of like, of the of you winning over somebody on an idea and they really appreciated idea that's the best possible. Like to me a like, is just two strangers smiling at each other. Like, like a moment of like, like I got you bro. Yeah, I [/INST] got you bro. Yeah, </s><s>[INST] yeah, like this ball, like yeah, we're in this fucking thing together, this whole thing doesn't make any sense, but we're in this together and yeah, it's possible for likes to be that I I don't think the actual clicking of a like, I think social media at its best might be that where it's like, I got you bro, in a large scale as opposed to kind of this weird uh crazy pool of dopamine where everyone is just obsessed with there's likes and likes and and then the division drives like more of this, like weird, anxious engagement, I think that's just the dark version of it in the early days of social media, [/INST] I think you called it a battleground of ideas, but I think social media is nothing but a battleground of fragile egos, </s>

<s>[INST] And so you're trying to design a representation that will support an arbitrary set of tasks in a particular sort of class of problem. [/INST] Yeah. And and also it turns out, and that's again a surprise that Elliot found was that those tests don't have to be very related. You know, you can learn to do better vision by learning language or better language by learning about DNA structure. No, somehow the world </s><s>[INST] it rhymes the world rhymes, even if it's very uh, very disparate fields. Um, I mean on that small topic, let me ask you because you've also on the competition? You're assigned side. Yeah. You worked on both language and vision. What's what's the connection between the two? Uh what's more maybe there's a bunch of ways to ask this, but what's more difficult to build from an engineering perspective and evolutionary perspective? The human language system or the human vision system or the equivalent of in the ai space language and vision or is it the best is the multi task idea that you're speaking to that they need to be deeply integrated? [/INST] Yeah, absolutely. The latter learning both at the same time. I think it's fascinating direction in the in the future. So we have data sets where there is visual component as well as verbal descriptions for instance. And and that way you can learn a deeper representation and more useful representation for both. But it's still an interesting question of um which one is easier eventually, I mean recognizing objects or even understanding sentences that's relatively possible. But when it becomes where the challenges are is to understand the world, like the visual world of three D what are the objects doing and predicting what will happen. Uh the relationships, that's what makes vision difficult and language obviously it's what's the me what is being said, what the meaning is and the meeting doesn't stop at who did what to whom? There are goals and plans and themes and eventually you have to understand the entire human society and history in order to understand the sentence very much fully. There are plenty of examples of of those kind of short sentences when you bring in all the world knowledge to understand it. Uh and that's the big challenge. Now we are far from that, but even just bringing in the visual world uh together with the sentence, we'll give you already a lot deeper understanding of what's happening. And I think that that's where we're going very soon. I mean we've we've had Image net for a long time and now we have all these tax collections but having both together uh and then learning a semantic understanding of what is happening. I think that that will be the next step in the next few years. </s><s>[INST] He's starting to see that with all the work with transformers was the community, the community started to dip their toe into this idea, the idea of having uh language models that are now doing stuff with images with vision and then connecting the two. I mean right now it's like these little explorations were literally dipping the toe in, but like maybe at some point we'll just like dive into the pool and it'll just be all seen as the same thing. I I do still wonder what's more fundamental or their vision is um whether we don't think about vision correctly. Maybe the fact because we're humans and we see things as beautiful and so on that. And because we have cameras, that taking pixels is a two D image that we don't sufficiently think about vision is language, you know maybe maybe chomsky is right all along that vision is fundamental to uh sorry that language is fundamental to everything to even cognition to even consciousness they the base layers all language not necessarily like english but some weird abstract representation. Uh linguistic representation. [/INST] Yeah well earlier we talked about the social structures and that may be what's underlying the language that's the more fundamental but language has been added on top of that </s><s>[INST] language emerges from the social interaction [/INST] problem. Yeah that's a very good yes. Um we are visual animals, there are a lot of the brain is dedicated to vision and and also when we think about various abstract concepts uh usually reduce that division uh and images and that's you know we go to the whiteboard you draw pictures of very abstract concepts. So we tend to tend to resort to that quite a bit and that's a fundamental representations probably possible that it predated. Um you know language even I mean animals a lot of they don't talk but they certainly do have vision. Uh and and language is interesting development in um from for investigation from eating, you develop an organ that actually can produce sound to manipulate them. Maybe that was an accident. Maybe that was something that was available and and then allowed us to do the communication or maybe it was gestures. Sign language could have been the original proto language, we don't quite know but there the language is more fundamental than the medium in which it's uh communicated. And I think that it comes from those representations um now in in current world they are so strongly integrated. It's really hard to say which one is fundamental. You look at the brain structures and even visual cortex which supposed to be very much just vision. Well, if you are thinking of semantic concept, you're thinking of language. Visual cortex lights up. It's still useful even for language computations. So there are common structures underlying them. So utilize what you need and when you are understanding a scene understanding relationships. Well that's not so far from understanding relationships between words and concepts. So I think that that's how they are integrated. </s>

<s>[INST] Now we just need to do the same for thomas, vehicles and AI systems in general. So again, if you get cash app from the app store, google play and use the code lex podcast, You get $10 in cash up. Will also donate $10 to first an organization that is helping to advance robotics and stem education for young people around the world. And now here's my conversation with Daphne koller. So you co founded Coursera made a huge impact in the global education of AI and after five years in august 2016 wrote a blog post saying that you're stepping away and wrote, quote, it is time for me to turn to another critical challenge, the development of machine learning and its applications to improving human health. So let me ask too far out philosophical questions. One do you think we'll one day find cures for all major diseases known today and to do you think we'll one day figure out a way to extend the human lifespan, perhaps the point of immortality. [/INST] So one day is a very long time. And I don't like to make predictions of the type, we will never be able to do X. Because I think that's a uh, you know, that smacks of hubris assumes that never in the in the entire eternity of human existence, will we be able to solve a problem? That being said, curing disease is very hard because oftentimes by the time you discover the disease, a lot of damage has already been done. And so to assume that we would be able to cure disease at that stage assumes that we would come up with ways of basically regenerating entire parts of the human body in the way that actually returns it to its original state and that's a very challenging problem. We have cured very few diseases. We've been able to provide treatment for an increasingly large number, but the number of things that you could actually define to be cures is actually not that large. Um, so I think that there's a lot of work that would need to happen before one could legitimately say that we have cured even a reasonable number of far less all diseases </s><s>[INST] On the scale of 0-100. Where are we in understanding the fundamental mechanisms of all major diseases? What's your sense? So from the computer science perspective that you've entered the world of health, how far along are we? [/INST] I think it depends on which disease. I mean, there are ones where I would say we're maybe not quite at 100 because biology is really complicated and there's always new things that we uncover that people didn't even realize existed. Um so, but I would say there's diseases where we might be in the seventies or eighties. Um and then there's diseases in which I would say Probably the majority where we're really close to zero </s><s>[INST] with Alzheimer's and schizophrenia and Type two diabetes fall closer to zero or to the 80. [/INST] I think Alzheimer's is Probably closer to zero than 80. There are hypotheses, but I don't think those hypotheses have as of yet been sufficiently validated that we believe them to be true. And there is an increasing number of people who believe that the traditional hypotheses might not really explain what's going on. I would also say that Alzheimer's And schizophrenia even type two diabetes are not really one disease. There are almost certainly a heterogeneous collection of mechanisms that manifest in clinically similar ways. So in the same way that we now understand that breast cancer is really not one disease. It is multitude of uh cellular mechanisms, all of which ultimately translate to uncontrolled proliferation, but it's not one disease the same is almost undoubtedly true for those other diseases as well. And that understanding that needs to proceed any understanding of the specific mechanisms of any of those other diseases now in schizophrenia, I would say we're almost certainly closer to zero than to anything else. Um type two diabetes is a bit of a mix. There are clear mechanisms that are implicated that I think have been validated that have to do with insulin resistance and such. But there's almost certainly there as well, many mechanisms that we have not yet understood. </s><s>[INST] You've also thought and worked a little bit on the longevity side. Do you see the disease and longevity as overlapping completely, partially or not at all as efforts. [/INST] Those mechanisms are certainly overlapping. There's um a well known phenomenon that says that for most diseases other than childhood diseases, the um risk um forgetting for contracting that disease increases exponentially year on year, every year from the time you're about 40. So obviously there's a connection between those two things. Um I that's not to say that there are identical, there's clearly aging that happens that is not really associated with any specific disease. Um and there's also diseases and mechanisms of disease that are not specifically related to aging. So I think overlap is where we're </s><s>[INST] at. Okay, it is a little unfortunate that would get older and it seems that there is some correlation with the fact that the the occurrence of diseases or the fact that we get [/INST] older and </s><s>[INST] both are quite sad. [/INST] I mean there's processes that happen as cells age that I think are contributing to disease. Some of those have to do with DNA damage that accumulates the cells divide where the repair mechanisms don't fully correct for those. Um there are accumulations of proteins that are misfolded and potentially aggregate and those to contribute to disease and contribute to inflammation. There is a there is a multitude of mechanisms that have been uncovered that are sort of wear and tear at the cellular level that contribute to disease processes that and I'm sure there's many that we don't yet understand </s>