Datasets:

ianiket23

/

podcast_llama_chat_format-5k

like 0

<s>[INST] It's gonna, the worry doesn't accomplish anything. [/INST] How much do physicists think about possibility? Well, they think about it in terms of probability more often, but probability just describes, and again, this is a place where I might be out of my depth and need to talk to somebody to debunk this, but the- You can do therapy with a physicist. Yeah, but probability, it seems, just describes a pattern of actuality that we've observed, right? I mean, there's certain things we observe, and those are the actual things that have happened. And we have this additional story about probability. I mean, we have the frequency with which things happen, have happened in the past. I can flip a fair coin and know, I know in the abstract that I have a belief that in the limit, those flips, those tosses should converge on 50% heads and 50% tails. I know I have a story as to why it's not gonna be exactly 50% within any arbitrary timeframe. But in reality, all we ever have are the observed tosses, right? And then we have an additional story that, oh, it came up heads, but it could have come up tails. Why do we think about that last toss? And what are we claiming is true about the physics of things </s><s>[INST] if we say it could have been otherwise? I think we're claiming that probability is true, that it just allows us to have a nice model about the world. [/INST] It gives us hope about the world, about the world. It seems that possibility has to be somewhere to be effective. It's a little bit like what's happening with the laws. There's something metaphysically interesting about the laws of nature, too, because so the laws of nature impose their work on the world, right? We see their evidence, but they're not reducible to any specific set of instances, right? So there's some structure there, but the structure isn't just a matter of the actual things. We have the actual billiard balls that are banging into each other. All of that actuality can be explained by what actual things are actually doing, But then we have this notion that in addition to that, we have the laws of nature that are making, they're explaining this, but how are the laws of nature an additional thing? In addition to just the actual things that are actually effect-causingy, and if they are an additional thing, how are they effectives if they're not among </s><s>[INST] the actual things that are just actually banging around? [/INST] Yeah. </s><s>[INST] To some degree. For that possibility has to be hiding somewhere for the laws on nature to be- [/INST] To be possible. For anything to be possible, </s><s>[INST] It has to be, it has to have- It's a closet somewhere, I'm sure, [/INST] where all the possibility goes. </s><s>[INST] It has to be attached to something, so. You don't think many worlds is that? Yeah, or- [/INST] Because many worlds still exists. Yeah, or- Because many worlds still exists. Well, because we're in this strand of that multiverse. Yeah. Right, so it's still, you have just a local instance of what is actual. Yeah. And then if it proliferates elsewhere where you can't be affected by it, many worlds has- </s><s>[INST] Or as well. Yeah, yeah. Many worlds has- Or as well. You can't really connect with the other. [/INST] Yeah. Yeah. Yeah. And so many worlds are just a statement of basically everything that can happen, happens somewhere, right? Yeah. Yeah. And that's, I mean, maybe that's not an entirely kosher formulation of it, but it seems pretty close. So, but there's whatever happens, right? In fact, there's, you know, relativistically, there's a, you know, the Einstein's original notion of a block universe seems to suggest this. And it's been a while since I've been in a conversation with a physicist where I've gotten a chance to ask about the standing of this concept in physics currently. I don't hear it discussed much, but the idea of a block universe is that, you know, space-time exists as a totality and our sense that we are traveling through space-time where there's a real difference between the past and the future, that that's an illusion of just our, you know, the weird slice we're taking of this larger object. But on some level, it's like, you know, you're reading a novel, the last page of the novel exists just as much as the first page. We, when you're in the middle of it, and they're just, you know, if that's, if we're living in anything like that, then there's no such thing as possibility. I would, it would seem there's just what is actual. So as a matter of our experience, moment to moment, I think it's totally compatible with that being true, that there is only what is actual. And that sounds to the naive ear, that sounds like it would be depressing and disempowering and confining, but it's anything but. It's actually, it's a circumstance of pure discovery. Like you have no idea what's gonna happen next, right? You don't know who you're gonna be tomorrow. You're only by tendency, seeming to resemble yourself from yesterday. And there's way more freedom in all of that than it seems true to many people. And yet the basic insight is that you're not, you're not, the real freedom is the recognition that you're not in control of anything. Everything is just happening, </s><s>[INST] including your thoughts and intentions and moves. [/INST] So life is a process of continuous discovery. You're part of the universe. Yeah, you are just this, I mean, it's the miracle that the universe is illuminated to itself, as itself, where you sit. And you're continually discovering what your life is. And then you have this layer at which you're telling yourself a story that you already know what your life is. And you know exactly who you should be and what's about to happen, or you're struggling to form a confident opinion about all of that. And yet there is this fundamental mystery to everything, </s>

<s>[INST] Did you bite on that idea? [/INST] No, because I wanted to be to do text first because I'm a journalist. So I was fascinated by just texting. </s><s>[INST] So you thought so the emotional um that interaction that the woman had like, do you think you could feel emotion from just text? [/INST] Yeah, I saw something in just this pure texting and also thought that we should first start start building for people who really need it versus people have google glass, you know what I mean? And I felt like the early adopters of google glass might not be overlapping with people who are really lonely and might need some someone to talk to. Um but then we really just focused on the tech itself, we just thought what if we just, we didn't have a product idea in the moment and we thought what if we just look into um building the best conversational constructors, so to say Use the best tech available at the time. And that was before the first paper about deep learning applied to dialogues, which happened in 2015 in august 15, which google published, </s><s>[INST] did you follow the work of Love No prize and like all the sort of non machine learning chatbots, [/INST] what really struck me was that you know, there was a lot of talk about machine learning and deep learning, like big data was a really big thing, everyone is saying, you know, the business will, big data 2012, the biggest gaggle competitions were you know, um important, but that was really the kind of upheaval people started talking about machine learning a lot. Um but it was only about images or something else and it was never about conversation as soon as I looked into the conversational attack, it was all about something really weird and very outdated and very marginal and felt very hobbyist, it was all about Lord Turner Prize which was won by a guy who built a chapel to talk like a Ukrainian teenager that it was just a gimmick and somehow people picked up those gimmicks and then you know, the most famous chat about at the time was Eliza from 1980s, which was really bizarre or smarter child and aim </s><s>[INST] The funny thing is that what it felt at the time not to be that popular and it still doesn't seem to be that popular. Like people talk about the touring test people like talking about it philosophically, journalists like writing about it, but it's a technical problem, like people don't seem to really want to solve the open dialogue, like they are not obsessed with it. Even folks are like you know in boston, the Alexa team even they're not as obsessed with it as I thought they might be. [/INST] Why not? What do you think? </s><s>[INST] So? You know what you felt like you felt with that woman when she felt something by reading the text, I feel the same thing. There's something here, what you felt, I feel like Alexa folks and just the machine learning world doesn't feel that that there's something here because they see as a technical problem is not that interesting for some reason. Um it could be argued that maybe isn't as a purely sort of natural language processing problem, it's not the right problem to focus on because there's too much subjectivity that that thing that the woman felt like crying, like if if you're a benchmarking crew includes a woman crying, that doesn't feel like a good benchmark test, but to me there's something there that you could have a huge impact but I don't think the machine learning world likes that. The human emotion, the subjectivity of it, the fuzziness, the fact that was maybe a single word, you can make somebody feel something deeply. What is that? It doesn't feel right to them. So I don't know, I don't I don't know why that is, that's why I'm excited um when I discovered your work, it feels wrong to say that it's not like I'm giving myself props for for Googling and for becoming a for uh for I guess mutual friend introducing us, but I'm so glad that you exist in what you're working on. But I have the same kind of if we could just backtrack for a second because I have the same kind of feeling that there's something here. Um in fact, I've been working on a few things. Mm hmm. That are kind of crazy and very different from your work. I think I think there I think they're too crazy. But the [/INST] what I have to know. </s><s>[INST] All right, well, we'll talk about it more. I I feel like it's harder to talk about things that have failed and our failing while your failure. Like it's easier for you because you're already successful on some measures. [/INST] Tell it to my board. </s><s>[INST] Well, you're you're I think I think you've demonstrated success and a lot of benchmarks easier for you to talk about failures for me, I'm in the the bottom currently of the of the success [/INST] way to home. No. </s><s>[INST] So it's hard for me to know, but there's something there, there's something there and I think you're you're exploring that and you're discovering that Yeah, it's been so it's been surprising to me, but I uh you've mentioned this idea that you you thought it wasn't enough to start a company or start efforts based on it feels like there's something here Mhm like uh what did you mean by that? Like you should be focused on creating a should have a product in mind. Is that what you meant? [/INST] It just took us a while to discover the product because it all started with a hunch of like um of me and my mentor and just sitting around and he was like well this that's it, there's that's the you know the Holy Grail is there, there's like there's something extremely powerful and conversations And there's no one who's working on machine conversation from the right angle. So to say, I feel like that's </s>

<s>[INST] failure is not a sign that the initial pursuit was worthless. Failure is just part of this kind of this whole exploration thing. And we should fund more and more of this exploration. The variety of the exploration. [/INST] I think it was Linus Pauling or somebody from, you know, that generation of scientists and a good way to have good ideas is to have a lot of ideas. So that's I think that's true. If you are conservative in your thinking, if you worry about proposing something that was going to fail and or what if, you know, like I there's no science police that's going to come and arrest you for proposing the wrong thing. And you know, it's also just like why would you, what would you do science if you're afraid of, you know, taking that step, it would be so much better to propose things that are plausible. They're interesting. And then for a fraction of them to be wrong than to just kind of, you know, make incremental progress all your life. Right. </s><s>[INST] Speaking of wild ideas, let me ask you about the thing we mentioned previously, which is this Interstellar object and more and more, could it be space junk from a distant alien civilization. [/INST] You can't immediately discount that by saying absolutely cannot anything, can be space junk. I mean, from that point of view, can any of the kuiper belt objects we see could be space space junk, anything on the night sky can in principle be space junk. </s><s>[INST] And kuiper belt would catch into stellar objects potentially and like force them into an orbit if they're like small [/INST] enough, not the kuiper belt itself, but you can imagine like jupiter family comments being captured, uh, you know, so you can actually capture things. It's even easier to do this very early in the solar system, like early in the solar system's life while it's still in a cluster of stars. Um, it's unavoidable that you capture debris, whether it be natural debris or unnatural debris or debris of some kind from other stars that it's like a daycare center, right? Like everybody passes their infections onto other kids. Um, you know, or more and more. There's been a lot of discussion about it and there's been a lot of interest in this over. Like, is it is it aliens or is it not? But let's like, if you just kind of look at the facts, like what we know about it is it's kind of like a weird shape and it also accelerated, right? Like that's the two, the two interesting uh, things about it, there are um, there are puzzles about it and perhaps the most uh daring resolution to this puzzle is that it's not aliens or it's not like Iraq, it's actually a piece of hydrogen ice. So this is a friend of mine, you know, Darryl Seligman Greg Laughlin came up with this idea where that in giant molecular clouds that are just clouds of hydrogen helium gas that live in uh live throughout the galaxy at their cores. You can condense ice to become the hydrogen, you know, icebergs if you will. And then uh that explains many of the aspects of uh in fact, I think that explains all of the normal mystery how it becomes elongated because basically the hydrogen I sublimate and kind of like a bar of soap that, you know, slowly kind of elongates as you uh as you strip away the the surface layers, how it was able to accelerate because of a jet that is produced from, you know, the hydrogen coming off of it. But you can't see it because it's hydrogen gas, like all of this stuff kind of falls together nicely. I'm intrigued by that idea truly because it's like if that's true, that's a new type of astrophysical object </s><s>[INST] and it would be produced by what's the monster that produced initially that kind of object? [/INST] So this giant molecular molecular clouds, they're everywhere. I mean they are. The fact that they exist is not </s><s>[INST] are they rogue clouds? Are they part of like an orange [/INST] cloud so loud? Yeah, they're </s><s>[INST] just floating about [/INST] Yeah, so if you go like a lot of people imagine the galaxy as being a, you know, a bunch of stars, right? And they're just orbiting, right? But the truth is if you fly between stars that you run into clouds, uh they </s><s>[INST] don't have any large object that creates orbits. They're just floating about. Just floating. But why are they floating together? Are they just float together for a time and not? [/INST] Well. So these are these eventually become the nurseries of stars. So as they as they cool, they contract and uh you know, then collapse into stars or into groups of stars. But some of them the starless uh molecular clouds. According to the calculations that Daryl and Greg did can can create these like icicles of hydrogen. I </s><s>[INST] wonder why they would be flying so fast. It seemed to be moving pretty fast [/INST] at a </s><s>[INST] more more [/INST] that's just because of their acceleration due to due to the sun. If you stop, it's like take something really far away, let it go. And the sun is here by the time it comes close to the sun, right? It's good moving pretty fast. So that's an attractive explanation. I think not so much because it's cool, but it makes a clear prediction right? Of when vera Rubin Observatory comes online next year or so. We will discover many, many more of these objects, Right? And they have um so I like, I like theories that are falsify a ble and not just testable, but falsify ability. It's good to have a falsified herbal theory where you can say that's not true uh aliens is one that's fundamentally difficult to say, no, that's not alien. The </s>

<s>[INST] That's another coincidence. So yes, yes, you could say the oil was one of the catalysts for absolute power, but the 20th century saw quite a few countries um have dictators with power unlike anything else in human history. Yes, that's weird to [/INST] precisely and you know, you can name them from the beginning of the century with people like I don't know, Lenin or Stalin of course, Hitler </s><s>[INST] even mao [/INST] of course you can name them and probably as I would say, is the last of them is Khomeini in that century, that you would see this strong man with a sense of even a artificial or real or a sense of so called charisma and with this total power over the regime that they create in the some of them do Nasser, he didn't have much of another resources in Egypt, but he was also one of these strongman. Okay, in the 20th century loved by some hated by others. So it necessarily does not tie up to uh to resource economic resources underground, but in the Iranian case, unfortunately it did And it was uh it was more than it created more than one issue for Iran. It's created a strong state which is the Pahlavi state from 1921 onward, because in 1921, at the end of the First World War, Iran was in it almost a state of total bankruptcy. And uh the british had a desire to try to bring Iran to the system that they created in the Middle East, in the post war era. The mandate system, Palestine Iraq and then of course, french mandate of Lebanon and Syria all of this and Iran was separate because Iran was an independent country. It wasn't part of the Ottoman Empire that collapsed. So they had to somehow handle it and what they tried to do, didn't work as a result, partly domestic, partly international issues brought about a regime which is headed by the founder of the Pahlavi dynasty, Reza Shah. Okay. First military officer called Reza Khan, actually a military officer of the Kazakh forces and the Cossack forces was the force that was created in the 19th century model of the Russian Cossacks. When the ruler in the 19th century visited Russia as in a royal tour. And the desire showed the great uh Kazakh forces is that I like this and he created one for himself with Russian officers actually. So the Russian officers served in Iran from Iran 1880s up to the revolution of 1917, the collapse of the regime, </s><s>[INST] So many revolutions, [/INST] so many revolutions and razor sharp was an officer in that Reza khan was an officer in that force and he created a new monarchy for reasons that we need to go to and discord the Pahlavi regime. Pahlavi regime was a modernizing regime. Okay, that brought a compass in effect, fulfilled many of the ambitions of the constitution, many of the aspirations of the constitutional revolution, better communication, but uh secular education, um centralized states and centralized army, um better contact with the outside world, greater urbanization, that's what modern state is all about. And in that regard, in a sense, for the 1st 20 years up to the Second World War was successful despite and more significant of all, it managed to keep the european powers, which was always interfering in the local affairs of Iran in an arm length, so they were there in an arm length, but they were also respecting the power of the state power of the Pahlavi state. During the 2nd 2nd World War. The same phenomenon as earlier interference led to the occupation of Iran by the allied forces. The british from the south, the Russians from the north, the Red Army, they took over Iran. And of course, they said </s><s>[INST] World War, [/INST] Yes, from 1941 up to 1945. And of course, when the when the Red Army refused to uh withdraw from Iranian Azerbaijan and with some thought of possible annexation of that province, there was a big issue in the post war Iran. </s><s>[INST] So after 1945, [/INST] Yes, - 1946, there was a big </s><s>[INST] soviet union. Getting greedy. [/INST] Yes, but eventually they agreed eventually, Stalin agreed to live uh the Azerbaijan province in the hope that it would get some concessions from Iran which in the oil of the Caspian era area, which didn't work. And it's a different story altogether. But what happened is that in the post war era between 1944 45 1953 is a period of greater uh democratization was that Reza Shah's dictatorship basically disappeared. And this is where you see political parties free press, a lot of chaotic really, as as democracies often are so </s><s>[INST] something like, was it, was it officially democracy? [/INST] Yes, it was a democracy. </s><s>[INST] Elections, there [/INST] were elections, yes, of course, yes, of course. And they were very diverse political tendencies. Came to the picture including the two, the party of Iran, which is the Communist Party of Iran. This Communist party of Iran is probably the biggest Communist party of the whole of the Middle East and one of the biggest in the world actually at that time, did </s><s>[INST] the soviet union have a significant influence on the [/INST] course, basically following orders from the Soviets, although they deny it, but the reality, that's the case. But what happened, they were seen by the americans during the Cold War as a as a threat. And Iran was going through a period of demanding nationalization of his old resources. That's a very important episode with whom you might have heard about his name. Dr Mohammad Mosaddegh, who was the prime minister and the national charismatic leader from 1951 to 1953. Prior to that, he was a famous parliament area. But this period was the prime minister of Iran and he nationalized the Iranian oil industry and the british didn't like it at all and eventually resulted in the famous coup which at least partly was supported by the funding and by the moral support of the british and the americans, particularly by the americans. It was always seen as one of the earliest and the most successful CIA operations during the Cold War, </s>

<s>[INST] You decided there you're not going [/INST] on you. I just know I was gonna I didn't know what I could do. I talk to a lawyer. I mean I just didn't I didn't know what I could do. But the best in Miami said what? He told me. So I had to go </s><s>[INST] and you went to brazil. Did you have a conversation with anybody at the cartel? I mean that's such an interesting moment that tests the man's character to not snitch. And did you have a conversation with anybody Pablo with about it? [/INST] Like? </s><s>[INST] So it's just understood. [/INST] I just didn't couldn't do it. </s><s>[INST] But how many men like you? Are [/INST] there not many? I had all my friends testified against me. 11 friends and every one of them put your finger up. Roger did it. And I was facing life continuing criminal enterprise. </s><s>[INST] You're still, you couldn't do [/INST] it. I just couldn't do it. </s><s>[INST] Do you ever get respect from the cartels for that? From the time [/INST] I got back and stuff. They owe me money and I can't get it. So </s><s>[INST] Well that's about money. I just need about human beings. [/INST] Oh, I think so. I'm not going back down there and I've been welcomed. I have my uh, my contact. And when I was in brazil, I was trying to get this money. They will be $3.5 million. So I called up there and he was going to pay me, oh, I got 600,000 today and I'll get you some more tomorrow. And then the next week I called, hey got great news. Great news, barry seal has been killed. So, Oh no. And I went back to the hotel, we was up in the northern part of brazil and where was it muddy? Uh yeah. And uh, so I went back, I told Marie and Miriam and uh, and they cried and I cried, I really cried. </s><s>[INST] How, how is that great news from the cartels? Well [/INST] now there's no case against me and him and them, </s><s>[INST] do you know who killed him? Yes, [/INST] I'll tell you about that story. On the first load I did. I landed in a banana plantation and it was raining and it was a muddy strip clay and they put the 300 kg of cocaine and then the ugliest man you can imagine named Ronaldo got in there with a Mac 10 and uh, he would make sure I took it to Louisiana. So </s><s>[INST] this is many years before. [/INST] Yeah, a couple of years before. So anyway, he, uh, uh, we took off and the mud got up in the wheel well, so so thick until the wheels wouldn't come up. Well, I'm going to 100 miles an hour instead of 300 mph wheel coming down. Well, I can't go back there if I do, I'm gonna be in the same situation until the sun dries it out in a few days. And so, but in beliefs I had a runway that we've been used for $10,000 used to refuel. So I told the guy, listen, we got to land in police to refuel. No, no, no, He put them back to him and I'll shoot you go ahead, fool, you're gonna die too. So it was in the term. So </s><s>[INST] he wasn't just ugly. He was also [/INST] he was a bad bad killer. So uh he's the one to actually kill Barry, The one that went up on the first load with me. And uh Ronaldo and he's been doing like </s><s>[INST] he's just a killer. Yeah. [/INST] You're doing life in Louisiana. </s><s>[INST] I wonder who uh is it known who made that decision? [/INST] Uh The younger Ochoa brother. I understand Fabio Which one paid for the hit? I don't know that, but that's what I've heard. And it's probably sounds about right. He's done in jessup Georgia Doing a long, long time. I think he's about to get out. He's been in 30 years or whatever </s><s>[INST] the movie american made. Yeah. What do you think that movie got right? What did he get wrong? [/INST] Almost everything wrong. Hit was disgustingly wrong. </s><s>[INST] Ok. Which parts can you, can you? Uh [/INST] Well, one media library, it's about barry seal and it just didn't even it was nothing. And whoever wrote it had no idea who barry seal was. They sit in the rocking chair and just try to think of what was some baby passion drug dealer doing. And it's just like God just you just don't have any idea of the spirit of the man. </s><s>[INST] So they wanted to try to tell a fun story without actually uh studying the [/INST] story. They didn't know where. They just had no idea. And barry was such a nice person. Such a really nice gentleman person. </s><s>[INST] They talk to you or no you know the people that made them [/INST] all uh and uh I see all these people tell them about Barry never met him. They tell them all about it. I think that's just ridiculous. Yeah and uh for one thing and for his character coming out of your houses and all that that was just like ugly. And then Down in Colombia putting a gun to his head, gonna take his sunglasses and then put $25,000 million dollars worth of cocaine on his plane And then they're gonna bet $100 you don't have enough room to take off. That's just insane. I mean just just the whole thing and then he's talking to the D. E. A. Agents when he's coming up. You don't know what frequently they own how you got five planes and they all split when the D. A. Comes out. These are just somebody just fantasy. </s><s>[INST] But those are like those are details of the man details of the story. Is there some big profound things they missed about just this whole period. But that's something that's really important to you that was missed. [/INST] Yes. They just try to sensationalized on little things that people remember and it's just not true. It's just it was just like a business deal and and and and good people and good airplanes and good flying and um it was like a good watch. It was made, it just clicked and it just went on and they missed all that. They tried to make it sound like it's something very ugly. Do </s>

<s>[INST] Maybe there's an intermediate place to I did my research on twitter by research, I mean scrolling through your twitter feed, you mentioned that you were going at some point to an animal law conference. So I have to ask, do you think there's something that we can learn from animal rights that guides our thinking about robots? [/INST] So I think there is so much to learn from that. I'm actually writing a book on it right now, That's what I'm going to this conference. So I'm writing a book that looks at the history of animal domestication and how we've used animals for work for weaponry for companionship and you know, one of the things the books the book tries to do is move away from this um fallacy that I talked about of comparing robots and humans because I don't think that's the right analogy. Um, but I do think that on a social level, even on a social level, there's so much that we can learn from looking at that history, because throughout history we've treated most animals like tools like products and then some of them we've treated differently. And we're starting to see people treat robots in really similar ways. So I think it's a really helpful predictor to how we're going to interact with the robots. </s><s>[INST] Do you think we'll look back at this time, like 100 years from now and see, uh, what we do to animals as like, similar the way we view like the holocaust, uh, with World War Two. [/INST] That's a great question. I mean, I hope so, I am not convinced that we will, but I often wonder, you know, what are my grandkids going to view as abhorrent that my generation did that they would never do? And I'm like, well, what's the big deal? You know, it's it's a fun question to ask yourself, </s><s>[INST] it always seems that there's atrocities that we discover later. So, things that at the time people didn't see as, uh, you know, you look at everything from uh slavery, uh, to any kind of abuse throughout history to the kind of insane wars that were happening to the way war was carried out and rape and the kind of violence that was happening during war and uh, that we now, you know, we see as atrocities, but at the time perhaps didn't as much. And so now I have this intuition that I have this worry maybe I'm you're going to probably criticize me, but I do anthropomorphize robots. I have, I don't see a fundamental philosophical philosophical difference between a robot and a human being. Uh, in terms of once the capabilities are matched. So the fact that we're really far away doesn't, um, in terms of capabilities and then that from, from natural language processing, understanding generation to just reasoning and all that stuff. I think once you saw that, I see the there's a very gray area and I don't feel comfortable with the kind of abuse that people throw robots subtle, but I can see it becoming, I can see basically a civil rights movement for robots in the future. Do you think you put it in the form of a question? Do you think robots should have some kinds of rights? [/INST] Well, it's interesting because I came at this originally from your perspective, I was like, you know what? There's no fundamental difference between technology and like human consciousness. Like we can probably recreate anything. We just don't know how yet. And so there's no reason not to give machines the same rights that we have once, like you say they're kind of on an equivalent level. But I realized that that is kind of a far future question. I still think we should talk about because I think it's really interesting. But I realized that it's actually, we might need to ask the robot rights question even sooner than that while the machines are still, you know, quote unquote. Really? Yeah, dumb and not on our level because of the way that we perceive them. And I think one of the lessons we learned from looking at the history of animal rights and one of the reasons we may not get to a place in 100 years where we view it as wrong to eat or otherwise, you know, use animals for our own purposes is because historically we've always protected those things that we relate to the most. So one example is whales. No one gave a ship about the whales. AM I allowed to swear? </s><s>[INST] Yeah, [/INST] No one gave a shout about the whales until someone recorded them singing. And suddenly people were like, Oh, this is a beautiful creature. And now we need to save the whales. And that started the whole save the whales movement in the 70s. So I'm as much as I and I think a lot of people want to believe that we care about consistent biological criteria. That's not historically how we formed our alliances, </s><s>[INST] Why do we, why do we believe that all humans are created equal killing of a human being, no matter who the human being is. That's what I meant by equality is bad. And then because I'm connecting that to robots. And I'm wondering whether mortality, so the killing act is what makes something that's the fundamental first, right? So I'm, I am currently allowed to take a shotgun and shoot a Roomba. I think I'm not sure, but I'm pretty sure it's not considered murder, right? Uh, or even shutting them off. So that's, that's where the line appears to be right. Is its mortality a critical thing here. [/INST] I think here again, like the animal analogy is really useful because you're also allowed to shoot your dog, but people won't be happy about it. So we give, we do give animals certain protections from like, you know, you're not allowed to torture your dog and set it on fire at least in most States and countries, you know, um, but you're still allowed to treat it like a piece of property in a lot of other ways. And so we draw these arbitrary lines all the time. And you know, there's a lot of philosophical thought on why viewing humans is something unique. Um, is not, is just species is, um, and not, you know, based on any criteria that would actually justify making a difference between us and other species. </s>

<s>[INST] we're looking for what its polarization is. And we'll go there, let me just ask, are you serious about the per cubic millimeter of 420 is the number? Centimeter. But cubic centimeter, 420 is the number. I wonder if Elon knows this and if he doesn't, he will truly enjoy this. This is great. Yeah, it's true. Oh, okay, funding security, excellent. So, I mean, this takes us to this story [/INST] of heartbreak, of triumph. </s><s>[INST] That's true. Of that you described in losing the Nobel Prize. So describe what polarization is that you mentioned. Can you describe what bicep one and bicep two are? Bicep three, perhaps the instruments that can detect this kind of polarization, what are the challenges, the origin story, the whole thing. [/INST] Yeah, so well, the origin story goes back again to like a father-son rivalry. It really does. My father won all these prizes, awards, et cetera, but he never won a Nobel Prize. And some parents in America, they compete with their kids. Oh, I was a football player in high school, I'll show you and whatever, wrestling, whatever. And some of us could be healthy too. But with me and my dad, it wasn't super healthy. We would compete and he was much more of a pure mathematician and I was an experimental physicist. So we had both different ideas in what was worth prioritizing our time. But I knew for sure he didn't win the Nobel Prize. And I knew I could kind of out deal him. So I feel pretty venal and kind of minuscule </s><s>[INST] kind of character-wise, saying that. The only reason you could outdo him is because the Fields Medal is given every four years. [/INST] And only if you're under 40, which he wasn't. So he's working under much more limited conditions. That's right, so even if I had, which spoiler alert, the book's called Losing the Nobel Prize, so I didn't do it. But I wanted to do something big and I wanted to do something that would really just unequivocally be realized as in a discovery for the ages, as in fact it was when we made </s><s>[INST] the premature announcement that we had been successful. So you were, from the beginning, reaching for the big questions. That's all I could do. [/INST] So as an experimenter, you were swinging for the fences. That's all I wanted to do. I felt like if it's worth spending perhaps the rest of my life on as a scientist, it better be damn well, better be interesting to me to carry me through, to give me the, you know, I always say passion is great when people say, oh, follow your passion. But it's not enough. Passion's like the spark that ignites the rocket, </s><s>[INST] but that's not enough to get the rocket into space. So then you swung for the fences with bicep one. [/INST] What is this? So bicep one was born out of kind of interesting circumstances. So I had gone to a Stanford University for a postdoc. So an academic coming here games. Stanford. Stanford University. Yeah, it's this small little school. It's not like that technical college in Massachusetts that you're affiliated with, but as I went there, I was working for a new assistant professor. She had gotten there only a year before I got there and she had her own priorities, the things that she wanted to do. But I kept thinking in my spare time that I wanted to do something completely different. She was studying galaxies at high redshift and I wanted to study the origin of the universe using this type of technology. And I realized courtesy of a good friend of mine who's now at Johns Hopkins, Mark Hemenkowski, that we didn't need this enormous Hubble telescope. We didn't need a 30 meter diameter telescope. We needed a tiny refracting telescope, no bigger than my head, less than a foot across. And that telescope would have the same power as a Hubble telescope, size telescope could have. Because the signals that we're looking for are enormous in wavelength on the sky. They're enormously long, large area signals on the sky. And if we could measure that, it would be prove effectively as close as you to get to proof. There could be things that mimic it but that we discovered the inflationary epoch. Inflation being the signal originally conceived of by Alan Dooth to explain why the universe had the large-scale features that it does, namely that it has so called flat geometry. So there's no way to make a triangle in space in our universe that has three interior angles that do not sum to 180 degrees. You can do that with spacecraft, you can do that with stars, you can do that laser beams, you can do that with three different galaxies. All those galaxies, no matter how far you go, have this geometry, it's remarkable. But it's also unstable, it's very unlikely, it's very seemingly finely tuned. And that was one of the motivations that Guth had to kind of conceive of this new idea called inflation 1979 when he was a postdoc also at Stanford, Slack. And he was trying to get a permanent job, I was trying to make my name for myself. And so I realized I could do this, but I was also being paid by this professor at Stanford to do a job for her. And I was kind of a crappy employee, to be honest with you. And then one day she couldn't take it anymore because I was like sketching notebooks and planning his experiments and I just, I wasn't, no. </s><s>[INST] If you had big ideas in your mind, you were planning big experiments. And that was difficult to work with on a small scale for like a postdoc type of situation. We have to, you know, publish basic papers, deliver on some basic deadlines for a project, [/INST] all those kinds of things. And support your advisors paying, she was paying me. And so one day I came in and actually involved another friend of mine, an astronomer named Jill Tarter, one of the pioneers in the SETI science business of detecting extraterrestrials, which I assume you'd never like to talk about aliens. So I'm sure we won't get into aliens. But Jill was visiting Stanford and I was like, I really want to meet her. Can you introduce me? And she said, no. In fact, you're fired. My boss. So I was like, this is possibly the best thing that could ever happen to me. I didn't know where it would lead or what would happen to it. But getting fired from this ultra prestigious university turned out to be the path. I mean, literally, it brings me here today in that because of that, I ended up working for another person in Caltech, which is in Pasadena. And she, my original boss Sarah Church, she got me the job with her former advisor, a man by the name Andrew Lang. And Andrew was like, he was like this, I don't know, like, he's like Steve Jobs or Elon, you know, charismatic, handsome, persuasive, idea man. Not the guy always in the lab doing everything, but understood where things are going decades from now. And he had been involved in an experiment that actually measured the universe was flat, very close to flat, along with a preceding experiment done at Princeton by Lyman Page and other collaborators. So the shape of the universe is flat. The geometry of the universe is flat. How did he do that experiment? So he used the cosmic microwave background. And so what I said is you have to look for triangles in the universe. So you can measure triangles on Earth. You can actually, it's hard to show that the Earth is curved, but you can show the Earth is curved using triangles, mountaintops, etc. If you have an accurate enough protractor. Allegedly. </s>

<s>[INST] It's very susceptible to adversarial [/INST] attacks, essentially, potentially. Yes. So in general, the problem with these models is Unity models is that they're very good at generating possible text but that's just that's just not enough. Right? Um you need uh I think 11 avenue that would be very interesting to make progress is to make it possible uh to write programs over the latent space that these models of Britain, that you would rely on these uh self supervised models to generate a sort of flag pool of knowledge and concepts and common sense. And then you will be able to write explicit reasoning programs over it. Because the current problem with deputy strings that you it can be quite difficult to get it to do what you want to do if you want to turn history into products, you need to put constraints on it, you need to um force it to a base it and rules. So you need a way to program it explicitly. </s><s>[INST] Yeah. So if you look at its ability to program synthesis it generates like you said something that's plausible. [/INST] Yeah. So if you if you try to make it generic programs it will perform well uh for any program that has seen it in its training data. But because program space is not interpretive, right? Um uh it's not gonna be able to generalize to problems it hasn't seen before. </s><s>[INST] No, that's currently do you think mm sort of and absurd. But I think useful. Um I guess intuition builder is uh You know the GTT three has 175 billion parameters. Human brain has a 100 Has bought 1000 times that or or more in terms of number of synapses. Do you think? Obviously very different kinds of things. But there is some degree of similarity do you think? What do you think GPT will look like when it has 100 trillion parameters? You think our conversation might be in nature different like because you've criticized GPT three very effectively now, do you think? [/INST] No, I don't think so. So the beginning with the bottleneck with scanning of GPT three GPT models, genetic potential summer models is not going to be the size of the model. How long it takes to train it? The bottleneck is going to be the training data because open your eyes already. Training ship industry on a Kroll of basically the entire web. Right? And that's a lot of data. So you can imagine training on more data than that like google could trained on more data than that but it would still be only incrementally more data and I don't recall exactly how much more data. GPT three with strain on compared GPT two but it's probably at less like hundreds maybe even thousands X. Don't have the exact number. You're not going to be able to train the model on 100 more data than what you already what you're already doing. </s><s>[INST] So that's that's brilliant. So it's not you know it's easier to think of computers a bottleneck and then arguing that we can remove the bottom like [/INST] but we can remove the compute bottle like I don't think it's a big problem if you look at the at the pace at which we've improve the efficiency of deep learning models in the past a few years. I'm not worried about train time bottlenecks and model size politics. Uh The bottleneck in the case of this generative transforming models is absolutely the train data. </s><s>[INST] What about the quality of the data? [/INST] So so yeah so the quality of the data is an interesting point. The thing is if you're going to want to use these models in real products um then you you want to feed them data that's as high quality as factual I would say as unbiased as possible that you know there's there's not really such a thing as m biased data in the first place, but you probably don't want to train it unready for instance. Sounds like sounds like a bad plan. So from my personal experience working with uh large scale deep learning models. So at some point I was working on a model at Google that's trained on uh X 350 million labeled images. It's image classification model. That's a lot of images. That's like probably most publicly available images on the web at the time. And it was very noisy dataset because the labels were not originally annotated by hand by humans, they were automatically derived from like tags on social media are just keywords in the same page as the image was fall and so on. So it was very noisy. And it turned out that she could easily get a better model. Uh Not just by train, like if you train on more of the noisy data, you get an incrementally better model. But you you you you very quickly heat diminishing returns. On the other hand, if you train on smaller data set with higher quality and rotations quality, that uh annotations that actually uh made by humans, you get better modeled. And it also takes less time to train it. </s><s>[INST] Yeah. That's fascinating. It's the self supervised learning. There's a way to get better doing the automated labeling? [/INST] Yeah. So you can enrich refine your levels in an automatic way. That's correct. </s>

<s>[INST] it's just an interesting like it feels gutsy to insert silence. You know, [/INST] that's what makes it, you know, it's like the greatest speakers of all time are like and I told you </s><s>[INST] right, [/INST] you would know like you're like, oh </s><s>[INST] yeah, what is that? Yeah, that's so interesting to do that just at the right time and then Pain, Right man, this is it's a brilliant song. Did you know it was a good song when you when you wrote it out of the thousands of songs even, [/INST] you know, I it's always the same thing for me, which is like all listen if I want to listen to the song and I want to listen to it a lot of times then those are the songs we put out and I and I only want to listen to the songs that make me feel something whether or not it's like our single that did the very worst of all our singles was the song that I wanted to listen to the least. But it made the most sense as a single which was all the wrong reason to choose it, right? It was this, it was I bet My Life is the single off our second album. And that song was originally written, it was just a guitar and a vocal and it was very just quiet and laid back and we were like, well let's try to dial it up, let's try to produce it. And we over produced that song. We self produced it as a band and we overproduced and that song, I mean it's it did good, you know, in terms of a song, but for us it did not do good um compared to other songs and I really look back at that and learned a lesson from that. It's like I don't want to listen to the song that's a sign already, You don't wanna listen to your own song, it's probably not a good song. Yeah. </s><s>[INST] Um You said your dad um elsewhere and today just said that your dad early on was a kind of the early rick Rubin. So when you were starting out, he was um he gave you feedback. He listened um what did you learn about music about life from your dad? [/INST] My dad is a really quiet farm, grew up on a farm. Very humble. Um I think he starts every sentence by saying </s><s>[INST] this is [/INST] just my two cents. Pretty much. You know I mean? It's like, like take it or leave it like, you know what I mean? Is that that kind of a sense? Like, there's humility and everything and it's real for him, it's not like false humility. He really, I really feel like when he's saying things, he really is like, maybe this isn't any worth to you son and he means it, but here it is and it's always gold. And I'm like, wow, dad, that's incredible. You know? </s><s>[INST] So what in those early days of you? Like, so you were like 12 or something like that? Like, starting to write 12. I [/INST] Wasn't showing my music to anyone. I started writing when I was 12 and I probably wrote for at least, let's say six months or something. And I had written probably, I don't like a lot of songs during </s><s>[INST] what was the topic by the way, Love? [/INST] It was all sad. No, it was the first song I ever wrote went, it was like a bluesy thing. It was like, there was my voice and it was like by himself? No other one around and he stood all alone. When would he be found? Did he want company or was he fine on his own? Everyone needs a friend. So why was he all alone? You know what it was like, but I was like a 12 year old with I just felt like depressed for the first time and I was, and I just was like, yeah, right. It really was like my sense of the blues at that time. For sure, like bad version of the blues but it was like 12 year old kid with a bunch of acne and like I just like, I hated going to school. I felt like that. I just had not found myself </s><s>[INST] a great song by the way. [/INST] I wanted to keep </s><s>[INST] listening, I forgot I was, [/INST] I don't know about that. But um yeah, </s><s>[INST] What was your dad at which point did you begin to share it with your dad? A [/INST] lot of the songs that I wrote in the beginning were very much like bobby Mcferrin like that because we are are mike was in a part of the house where I couldn't bring it over the piano and the only instrument I played at the time was the piano </s><s>[INST] so I [/INST] would do everything with my voice. But then I started teaching myself the guitar in those in the beginning, like six month period, just watching my brothers play in their garage bands in the, in the basement and then I started to write songs a little bit more like any vibes like stack my voice like 2030 times and like, and you meet like jarrah, which is who my dad would listen to a lot, john john Michael Jarre, this incredible synth genius. But anyway, so I finally got my like gall up enough to show it to my dad one day after work and I got very little of my dad because there were nine kids and he worked from eight AM till six PM, we'll come home very tired and here's nine kids that are like dad, you know, and you're the young when you're not, you're just gonna miss. I was in the middle kind of too. So it's even, you know, middle child thing. But I sat them down, I was like, hey dad, I just want to like, can I show you a song? And he's like, oh you know, he didn't know I was writing anything and I showed it to him and he listened and he took it off and he really looked at me and was like, that was really good. It was like, I really, I thought and this when you said this, it made me feel this, he was like and that did it. I probably would have given up music. Like I look back that was a very pivotal moment for me. I was like in a place where I was like, is this good, bad? I don't know, maybe it's so embarrassing and terrible. And I was already writing lyrics that were a little like overly metaphorical to hide that I was dealing with faith crisis because I thought okay, I'm gonna show this to dad, I don't want my dad to know, I'm like questioning the truthfulness of joseph smith. I'm not gonna be like, it's joseph smith a real profit is mormonism true. I don't really know like you know what? I was like writing way overly metaphorical, but because my dad really validated it and he was a no bullshit person. So I knew when my dad said that I was like, you know what? At least my dad really actually thinks this is cool and I really trusted my dad's taste and and I thought everything he listened to was cool. So I was like wow, I keep doing this and I just showed it to my dad for years and years and still to this day I send every song to my dad </s>

<s>[INST] mean? Like a definitive, [/INST] well they took it away and gave me a bag of weed instead and I cried my eyes out for </s><s>[INST] days and days and days, you know, [/INST] and then you know as a, and my dad said we're going to exchange it back in a little bit. So you keep the little gun, you know, the one that you shoot the ducks with. So I'm like, okay, I'm keeping the gun. So sometimes it's going to come back. But if they exchanged the gun as well for some sugar or something, I was so pissed. I was like, I didn't want to eat for days after that. I'm like, I don't want your food keeping my Nintendo. Um, that was extremely traumatic. Um, but you know, I was happy that that was my only traumatic experience. You know, my dad had to actually go to trial novel with a bunch of 20 year old. He was 20 when he went to Chernobyl and that was right after the explosion. No one knew anything. The whole crew, he went with all of them are dead now. I think there was this one guy still, wow, that was still alive for this last few years. I think he died a few years ago now. My dad somehow luckily got back earlier than everyone else, but just the fact that that was the, and I was always like, well how did they send you? I was only, I was just born, you know, you had a newborn talk about paternity leave. They're like, but that's who they took because they didn't know whether you would be able to have kids when you come back. So they took the ones with kim so him with some guys want to And I just think, you know me. And when I was 20, I was so sheltered from any problems would serve in life. And then my dad um His 21st birthday at the reactor, You work three hours a day, you sleep the rest. And yeah, so I played with a lot of toys from Chernobyl. What are your </s><s>[INST] memories of Chernobyl in general? Like bigger context? You know, because of that HBO show is the world's attention turned to it once again. Like what are your thoughts about your novel? The Russia screw that one up. Like, you know, there's probably a lot of lessons about our modern times with data about coronavirus and all that kind of stuff. It seems like there's a lot of misinformation, there's a lot of people kind of trying to hide whether they screwed something up or not. As it's very understandable. It's very human, very wrong probably. But obviously Russia was probably trying to hide that. They screwed things up. Like what are your thoughts about that time? Personal and general. [/INST] I mean, I was born when the explosion happened. So actually a few months after. So of course, I don't remember anything apart from the fact that my dad would bring me tiny toys plus like plastic things that would just go crazy haywire when you put the bigger thanks to it. My mom was like just nuclear about that. Um it was like what do you bring age? I'll do that. She was a nuclear, very nice, well done was uh, but yeah, but the tv show was just phenomenal. Yeah, definitely. First of all, it's an incredible how, um, that was made, not by the Russians but someone else, but capturing so well everything about the, in, about, about our country. Um, it felt a lot more genuine than most of the movies and tv shows that are made now in Russia, just so much more genuine. And most of my friends in Russia were just complete all about the, with the show, but I think that good of a job, they did a phenomenal, but the apartments, </s><s>[INST] there's something just [/INST] design. I mean Russians can't do that, you know, but you, you, you see everything and it's like, wow, that's exactly how it was. </s><s>[INST] So I don't know that show, I don't know what to think about that because it's british accents, british actors of a person, I forgot who created the show. I'm not, but I remember reading about him and he's not, he doesn't even feel like, like there's no Russia in his history. [/INST] No, he did like super bad or some like, or like, uh, I don't know whatever that thing about the bachelor party in Vegas, uh, number four and five or something, we're the ones that he </s><s>[INST] worked, but he, it made me feel really sad for some reason that if a person obviously a genius could go in and just study and just be uh extreme attention to detail that can do a good job. It made me think like why don't other people do a good job with this? Like about Russia? Like there's so little about Russia, there's so few good films about the Russian side of World War Two. Uh I mean there's so much interesting evil and not and beautiful Moments in the history of the 20th century in Russia. That feels like there's not many good films on from the Russians. You would expect something from the Russians. [/INST] Well they keep making this propaganda movies now unfortunately, trainable was such a perfect tv show I think capturing really well, it's not about like given the set design, which was phenomenal, but um just capturing all the problems that exist now with the country and like um focusing on the right things. Like if you build the whole country on a lie, that's what's going to happen and that's just this very a simple kind of thing. </s><s>[INST] Yeah. And did you have your dad talked about it to you like his thoughts on the experience. [/INST] He never talks. It's this kind of Russian man that just my husband was american and he asked him a few times like you know, Igor, how did you, but why did you say yes or like why did you decide to go? You could have said no, not go to your novel, why would like a person to Yeah, that's what you do. You cannot say no. It's just, it's like a Russian way. It's the Russian don't talk that much there. Downsides and upsides for that. </s>

<s>[INST] don't think there's a better way to end a discussion of the meaning of life, whatever the heck the meeting is. Go all in as that poem says monopolies. Thank you so much for talking today. [/INST] Thanks. I look forward to next time. </s><s>[INST] Thanks for listening to this conversation with Manila's kelly's and thank you to our sponsors Graham early, which is a service for checking spelling, grammar, sentence structure and readability. I thought of greens, the all in one drink that I start every day with to cover all my nutritional bases. Cash up the app. I used to send money to friends. Please check out these sponsors in the description to get a discount and to support this podcast. If you enjoy this thing, subscribe on youtube, review five stars on apple podcast. Follow on Spotify, support on Patreon or connect with me on twitter at lex Friedman and now let me leave you with some words from Douglas Adams in his book, Hitchhiker's guide to the galaxy on the planet earth. Man had always assumed that he was more intelligent than dolphins because he had achieved so much the wheel new york wars and so on. Whilst all the dolphins had ever done was muck about in the water having a good time. But conversely, the dolphins had always believed that they were far more intelligent than man for precisely the same reasons. Thank you for listening. I hope to see you next time. [/INST] </s>

<s>[INST] It's funny because it's also it's a funny game because it's connected through centuries of play. Just some of the most interesting people in the history of the world have played this game and have struggled with whatever have projected their struggles onto the chessboard thought there and the nations have fought over the chessboard. The soviet, Union University, United States bobby Fischer represented the United States. [/INST] Yeah, </s><s>[INST] I got uh before I lose track of it when we were talking about the Godfather, you were in american gangster, great film. Uh you said it's one of your favorites to what you were in it with Denzel Washington. What makes that movie meaningful to you, What what what was it like making that movie? That was a great, great America. [/INST] That was a great american film. It was so many things in that film being a part of that film was probably a blessing and a treasure because even if even if I wasn't a part of it, uh this court's sets great filmmaking and and to me a really cool, great story. Um the thing that I love about it the most really is the process of it, you know, which part, I wouldn't have known the process if I wasn't part of it. So as a film. Joyous, it was great feeling like, but even the process of making it was like high level education for me on multiple levels. I'm working with Ridley scott, which is and this is a bold statement if I say this here because I got a lot of friends that's gonna probably, but he's probably the best living director because watching him allow me to understand a principle that I've coined to him and I know people use it yet core, multi vision. Mhm. He seems to have the capacity to see eight Things at one time. I heard on Robin Hood, he had 18 cameras, I wasn't there for that. And you think he keeps </s><s>[INST] them all in his mind. Just see I [/INST] seen him do it when he went to the monitors with the video playback guy. I've seen him bring everything back to a point, but nothing was the same on the frame, he was already </s><s>[INST] there [/INST] and he knew if he had what it was or not and he placed the cameras there and he saw it like, in his own way. And I peeped it, you know, my peep this. And I said, yeah. And I just, you know, humbly asks him, he was like, he was gracious enough to speak to me and talk to me. Uh and and confirmed of what I thought I saw. He confirmed it, he confirmed it and I was able to utilize it as I'm a filmmaker now and I'm I c I could at least see three or four things. I can't see eight yet. I'll be there though. Um but I could definitely like, even right now, just so I could go like this in the room. Okay, I got it now. I got like how to make this right here, which is just us all sitting, How do I make this look boom. Mhm. Come on on him. There's a story, there is a story there and I might just took off his hanging watch or is hanging wristband. Yeah. You know, because there's something else there </s><s>[INST] to be dead. We don't know. [/INST] So, so he has this. And even though this is the scene, </s><s>[INST] you're keeping that in mind all of this in mind. What about like, can you give an inkling of other parts of the process? Like the editing? Like what is another [/INST] thing? Another thing Pedro, I don't pronounce patrol last night, right? He's a cool guy, had a chance to play rugby with him. He was on, it was on my team. Yeah, well we were both teams. But page will the editor who you know added many great films. Once again he has, I will call the ciphering power a good editor is a decipher almost like breaking the enigma because he's dealing with thousands or we'll call it a film with millions of feet of film, lisa million feet of film. That's a lot of film with four feature. He's dealing with that. But he's dealing with multiple cameras. So it is like it's like two cameras. He got an A. B. And he could just go back. No, he may have six cameras and he has to go back and deal with that process and you know what he knows how to tell the story again. And he proved it on american gangster as me being a witness because it's so much information even when they, when the brothers all start getting their little business and then he put one of the Bronx, he just captured every neighborhood within one minute and you knew what would happen. You know, you knew it all. You know you saw the whole rise to fame as you watch the palmer in scarface Who does it in two minutes but it's only one character. So you see him go to the bank, he drops the money off. You see him by the lion, you see him gets his wife or the tiger, You see him get his wife, you see all that. Then it ends on the big shot of him in the big house with all the T. V. Screens and you've seen him go through it right? But in american gangster you're going to tell that story of rising. But you also got to include these five brothers. </s><s>[INST] Yeah that's all in the edit man but [/INST] also all in the director knowing that as well. </s><s>[INST] You got to keep track. You gotta keep thinking about them because that was a story right there. [/INST] Yeah. Well I was hearing it. I don't know if they were taking pictures of them or yeah I have a little </s>

<s>[INST] okay. I love this. I love every aspect. I love everything you're, you're talking about a lot of people believe because vaccines started being deployed currently that we are no longer in need of a solution. We're no longer in need of uh slowing the spread of the virus. Uh, to me, as I understand, it seems like this is the most important time to have something like a rapid testing solution. Can you kind of break that apart? What's the role of rapid testing currently in the next, You know, what is it? 3, 4 months maybe is [/INST] even more this the vaccine rollout isn't going to be as peachy as everyone is hoping. You know, and I hate to be the deputy downer here. But um, there's a lot of unknowns with this vaccine. You've already mentioned one, which is, there's a lot of people who just don't want to get the vaccine. Uh, you know, I hope that that might change as things move forward and people see their neighbors getting in their family, getting it and it's safe and all. We don't know how effective the vaccine is going to be after two or three months. We've only measured it in the first two or three months, which is a massive problem, which we can go into biologically because there's reasons to Very good reasons to believe that the efficacy could fall way down after two or 3 months. We don't know if it's going to stop transmission and if it doesn't stop transmission, then we're not, then there's herd immunity is much, much more difficult to get because that's all based on transmission blockade. And uh, and frankly we don't know how easily we're going to be able to roll it out. Some of the vaccines needed really significant cold chains have very short half lives outside of that cold chain. We need to organize massive uh numbers of people to be able to distribute these most hospitals today are saying that they're not equipped to hire the right people to be even administering enough of these vaccines. And then a lot of the hospitals are frustrated because they're getting much low smaller allocations than they were expecting. So I think right now like you say right now is the best time Besides three or 4 or five or six months ago right now is the best time to get these rapid house out. And we need to I mean the country has the capacity to build them. We have we're shipping them overseas right now. We just need to flip a switch, get the FDA to recognize that there's more important things than diagnostic medicine which is the effectiveness of the public health program. When we're dealing with a pandemic. They need to authorized uses public health tools or you know frankly the president could uh you know there's a lot of other ways to get these tests to not have to go through the normal FDA authorization program but maybe have the NIH and the C. D. C. Give a stamp of approval. Uh and if we could we could get these out tomorrow and that's where that article came from. You know how we can stop the spread of this virus by christmas. We could you know now it's getting late and so we have to keep updating that timeframe. Maybe putting christmas in the title was and should have said how we can stop the spread of this virus in a month. It would be a little bit more timeless but but we could do it you know we really could do it. And that's the most frustrating part here is that we're just choosing not to as a country we're choosing to bankrupt our society because some people at the FDA and other places just can't seem to get their head around the fact that this is a public health problem not a bunch of medical problems. </s><s>[INST] Is there a way to change that policy wise? So this is this is a much bigger thing that you're speaking to which I love in terms of the uh M. I. T. Uh engineering approach to public health. Is there a way to push this? Is this is this a political thing? Like we're some Andrew yang type characters need to like start screaming about it. Is that uh more of an Elon musk thing [/INST] where people just need to build </s><s>[INST] it and then on on twitter start talking crap to politicians. We're not doing it. What what what what what what are the ideas here? [/INST] I think it's a little both. I think it's political on the one hand and I've certainly been talking to Congress a lot. Talking to senators. Are they receptive? Oh yeah. I mean that's the crazy thing. Everyone but the FDA is receptive. I mean it's it's astounding. I mean I advise, you know, informally I advised the president and the president elect's teams. I talked to Congress, I talked to senators, governors, you know, and then all the way down to the mayors of towns and things. And I have, I mean months ago I held a roundtable discussion with Mayor Garcetti is the mayor of L. A. And I brought all the all the companies who make these things. This was in like july or august or something. I brought all the companies to the table and said, okay, how can we get these out? And unfortunately it went nowhere because the FDA won't authorize them as public health tools. Um the nice thing is that this is one of the nice and frustrating things. This is one of the few bipartisan things that I know of and like you said, it's it's a real solution lockdowns are in a solution there. There a of emergency band aid to a catastrophe that's currently happening. They're not a solution and they're definitely not a public health solution. If we're taking a more holistic view of public health, which includes people's well being, includes their psychological well being, their financial well being. You know, just stopping a virus if it means that all those other things get thrown under the bus is not a public health solution. It's a it's a it's a myopic are very tunnel vision approach to a viral virus that's spreading. This is a simple solution with essentially no downfall. You know, there is no nothing bad about this. It's just giving people a result. And it's bipartisan, you know, the most conservative and the most liberal people, everyone just wants to know their status. You know, nobody wants to have to wait in line for four hours to find out their status on monday uh a week later on saturday. You know, it just doesn't make any sense. It's a useless test at that point and everyone recognizes that. </s>

<s>[INST] Yeah, on the book point I've read um Animal Farm by George Orwell a ridiculous number of times. So for me, like that book, I don't know if it's a good book in general, but for me it connects deeply somehow. Uh it somehow connects. So I was born in the soviet Union. So it connects to me to the entire the history of the soviet Union and to World War Two into the love and hatred and suffering that went on there and the uh the corrupting nature of power and greed. And just somehow I just that that that book has taught me more about life than like anything else, even though it's just like a silly like childlike book about pigs, Like I don't know why it just connects and inspires the same. There's a few um yeah, there's a few technical books two and algorithms that just you returned to often. I'm I'm with you. Uh Yeah, there's I don't and I've been losing that because of the internet. I've been like going on, I've been going to archive and blog posts and get hub and the new thing and of uh you lose your ability to really master an idea, [/INST] wow. Exactly. Right. </s><s>[INST] What's a fond memory from childhood when baby Ross Todrick? [/INST] Well, I guess I just said that at least my current life begins began when I got to admit if I have to go further than that. </s><s>[INST] Yeah. What was was there life before I met you? [/INST] Oh, absolutely. But but let me actually tell you what happened when I first got to MIT because that I think might be relevant here. But uh you know, I I had taken a computer engineering degree at michigan, I enjoyed it immensely, learned a bunch of stuff. I was I liked computers, I've liked to like programming. Um but when I did get to mitt and started working with sebastian song, theoretical physicist, computational neuroscientist. Um the culture here was just different, It demanded more of me, certainly mathematically, and in the critical thinking and I remember the day that I uh I borrowed one of the books from my advisor's office and walked down to the Charles river and was like, I'm getting my butt kicked, you know? Um and I think that's going to happen to everybody who's doing this kind of stuff right? I think, yeah, I expected you to ask me the meaning of life, you know, I think that the um somehow I think that's that's got to be part of it, this </s><s>[INST] doing hard things. [/INST] Yeah. Did </s><s>[INST] you did you consider quitting at any point? Did you consider this isn't for me? [/INST] No, never. That I mean, I was it was working hard, but I was loving it right? There's I think there's this magical thing where you you know, I'm lucky to surround myself with people that basically almost every day I'll I'll see something, I'll be told something or something that I realized, wow, I don't understand that. And if I could just understand that there's there's something else to learn that if I could just learn that thing, I would connect another piece of the puzzle and you know, I think that is just such an important aspect and being willing to, I understand what you can and can't do and and loving the journey of going and learning those other things. I think that's the best part. </s><s>[INST] I don't think there's a better way to end us. I've, you've been an inspiration to me since I showed up at MIT. Your work has been an inspiration to the world. This conversation was amazing. I can't wait to see what you do next with robotics home robots. I hope to see your work in my home one day. So thanks so much for talking. Today has been awesome. Thanks for listening to this conversation with Ross Todrick and thank you to our sponsors magic spoon cereal. Better help and express VPN. Please consider supporting this podcast by going to magic spoon dot com slash lex and using collects at checkout. Going to better help dot com slash lex and signing up at express VPN dot com slash lex pod, click the links by the stuff, Get the discount. It really is the best way to support this podcast. If you enjoy this thing. Subscribe on youtube, review five stars on Apple podcast supporter on Patreon or connect with me on twitter at lex Friedman spelled somehow without the e just F R I D M a M and now let me leave you with some words from Neil degrasse Tyson talking about robots and space and the emphasis we humans put on human based space exploration, robots are important. If I don my pure scientists. Hat, I would say just send robots, I'll stay down here and get the data. But nobody's ever given a parade for a robot. Nobody's ever named a high school after a robot. So when I done my public educator hat have to recognize the elements of exploration that excite people. It's not only the discoveries and the beautiful photos that come down from the heavens, it's the vicarious participation in discovery itself. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] And shove it up the tube. [/INST] Got it. Almost enough, yeah. If I was running the lanyard, which is the thing that makes it go boom, it's really easy, it's a long rope. You hook it on and you put your right hand on your hip and on your left and you hold it there and you just stare at your sergeant like this and you just wait for him to yell fire. And he points at you when he does it, and when you do it, you turn your whole body with it. And when you do that, it alleviates the, a misfire essentially, because if you just pull it, sometimes that's not enough. You gotta really give it your whole body into it. And so he would train me on how to do things differently so that I could do them effectively. </s><s>[INST] And I wasn't a ship pump. [/INST] A what? So ship pump is a term that we use in Canada to call somebody useless. A ship pump is a useless soldier who is just, you're there and that's the ship pump. And so we all just deal with it, </s><s>[INST] but somehow they're still there. Yeah. What were we talking about? The lanyard? [/INST] Okay. Yeah. We were talking about the artillery guns. So those things though, what you would find fascinating is just how they break down when you have to take one of those apart. I think your mind would really find it fascinating how a breach comes apart all the way down to like ball bearing size. And there's a way to just make that gun completely ineffective and all you have to do when you're on the charge side, there's a magazine that's a long linear magazine and it holds like 15 little rounds. If you just take that thing out, </s><s>[INST] nothing's not a fighter. How many people does it take to move that? [/INST] Like how easy it is to move that thing? </s><s>[INST] To move a triple seven? A triple seven, I like it. That's what they're called, M triple seven. A lot of the terminology cross over the same in English and French? No. [/INST] Okay. That's what they're called, M triple seven. I mean, M triple seven does. Because it's an obvious, howitzer I'm sure has a separate word, but like if you're running it, you're running it in French. So like when I'd be running, when I'm doing the charge bags and I'm loading everything and I'm getting that ready and that's my position that day, I'm also controlling the breach. So like how it opens, how it closes when it locks. And so, but you have to yell that as you do it. So you're yelling like, Me lib, coulas, au vais. Like you have to yell all these things, you have to learn them though. And so for a long time, it was a little frustrating. </s><s>[INST] It won't lie. It was really exciting. I took a lot of French, but I forgot all of it. But I think it's a beautiful, romantic language. [/INST] It's a good language. If it's from Paris, if it's from Quebec, it's a. </s><s>[INST] Yeah, yeah, that's true. It's a good language to fall in love with. [/INST] Not as good as Russian, but English is eh, all right. I mean, I mean, Russian really, </s><s>[INST] is that like a love language? [/INST] It is to me. I mean, because you're Russian, but like if somebody walked up to me and was like, hey, Kelsey, I like you. </s><s>[INST] I'd be like, ah, God, he's gonna put me in a camp. That's because you don't understand love in Kelsey. I don't. We'll talk about that, okay. How many people does it take to move them triple seven? [/INST] We'll talk about that. Okay, it depends. If you're moving it by ground, you're moving it on a truck. And when you're moving it on a truck, you're hooking the back of it onto, you're hooking the front of the barrel onto one of those big transport looking trucks that has those cargo tents that's got soldiers in it. You don't want to ever move an M triple seven by that way if you don't have to. </s><s>[INST] The barrel's worth a million dollars. Wow, okay, so this is like a serious piece of equipment. You don't want to move them. [/INST] Okay. You don't want to move them. When we got to Kandahar, we were there for a couple days. we got flown out to the fog we were gonna be at. Forward observation base. Kandahar is the safe space or was the major base in Afghanistan that we were at. There's things like Tim Hortons there. There's Canada House. There's a British side, an American side, a Canadian side. And that's where you see all the different countries in the world kinda come together. You would see Italians, you would see Germans, you would see French, you would see all these different uniforms and you never know who to salute </s><s>[INST] because you don't know what each thing means. [/INST] It doesn't feel like a war zone. No. No, there's a boardwalk. There's hockey there like floor hockey because Canada had to have that. There's a Tim Hortons, a subway, a Pizza Hut, a PX. I think there's a restaurant there somewhere, but I never I didn't get to go. You know, stuff like that. There's gyms. You can run around it. You feel fairly safe. You always have a weapon on you, but you can, you know, live your life. When you get out to the fob, the guns are already there. So those M triple sevens get lifted by a Chinook. Normally they're going by air. They go by Chinook because they're heavy as hell. And Chinooks can hook them under the bottom and they fly them and then they'll drop them down. They have wheels on them, but you don't need them if you're going to leave it in place. </s>

<s>[INST] No it's probably well I hope it keeps us around. Do you by the way? Think about Ai and the existential threats. Like speaking of gods are you is this whole technological world. We talked about social networks and this increasing power of technology around us, We ourselves are becoming less human because we keep becoming we we keep relying on technology more and more so we're becoming kinds of cyborgs. But also there's a future that's quite possible where the technology becomes smarter and more powerful than us humans and you know, starts having a life of its own in ways that perhaps we don't imagine as human beings. I don't just mean like two legged robots walking around and being humans but smarter. I mean like an intelligent life that's Uh huh That's beyond and fundamentally different than our human life. It's infinite. It's [/INST] uh creating new </s><s>[INST] species. Yeah. Yeah a new a new kind of species, not even just a new species. Talk about systems but like it lives in the space of information. It lives uh in a different time scale in a different scale of all sorts spatial scale. It uh operate like we spoke about individuals, it doesn't operate in the sense of a single individual like embodied, it's not embodied. So it's not like a thing that walks around and it like it looks at stuff it consumes the world. It's able to do much larger scale sensing of the environment around it. All that kind of stuff. [/INST] I can barely even tried to kill. I can barely conceive of what that would be like. You scared? </s><s>[INST] Are you excited? Yeah. [/INST] I don't define it, scared or excited. I feel like I try intended to find them like the same way. I'm like, I guess I'm </s><s>[INST] kind of before karaoke. [/INST] Well, that's actually kind of my happy place. It's not so much everyone else's, you know, it's everyone else is probably, you know, heading for the door at that point. But, you know, it's </s><s>[INST] while you're doing it or leading or leading up to [/INST] the karaoke. Well, it depends whether or not whether or not they know it's me. If they know it's me, that's before I start. If they have they're like, who's that guy? Then they're like halfway through the song. They're already what's thrown their beer. </s><s>[INST] What categories a song or a particular song we're talking about in terms of like your happy place, [/INST] man. Are you kidding me? I mean, obviously bohemian rhapsody. I mean, there's no question because Yeah, because I don't have to sing it here. It's that's like, remember, can I be can be Yeah, of course, isn't here, No. Yeah. Yeah. Yeah. All right. If you like </s><s>[INST] it here know that I never torn, I've uh have torn feelings about the human wraps because I like the beginning part, the sadness. I like the solo heartbreak, but the second part I understand [/INST] it, it </s><s>[INST] gets, it gets ridiculous. It's so ridiculous. Everyone's it for [/INST] me. But it's more about flexing on people. I think if you can actually hit that, hit that, you know, the false shadow. </s><s>[INST] Yeah. So it's, it's, it's not okay, so you appreciate it. Not for the musical beauty and complexity of the song. You just like to [/INST] flex because like for all, you know, like what's the purpose of of anything except for just to let everyone know that you think you're cool </s><s>[INST] and there's no better way of doing that, that karaoke. So I'm not sure why [/INST] about captive audience. </s><s>[INST] Yeah, exactly. About fear and excitement of artificial intelligence. [/INST] I mean, you know me, I don't know anything about, just basically, I don't, I don't understand the implications of any of this. I would just say that like graphically altering what it means to be human in such an unbelievably short period of time just seems like such a crazy thing. And also it's not like we're, I can't remember who said this to me recently. I mean, you know, I can't remember. So this is definitely not my idea, but uh, we're not even going, hey, would you like to opt in everyone. Everyone is being opted in, you know, and particularly you want to talk about like large scale robotics, a large scale ai like the world is changing. People in Senegal are opting in right now without realizing it. It's not even like, and again, I don't mean to pick on Senegal's justice, whatever country comes up to mind, but that's in the developing world. But basically, uh, you know, recognizing that this huge shift is coming, we have no idea. This is a decent idea. And also something else have always been considered is uh, you know, you think about most of the really awful, awful, awful things that have done in history, large scale slavery holiday, You name it. It didn't people say that it came from this motivation and that motivation, maybe it did. Maybe it didn't fundamentally the issue, at least in my mind and I'm not a historian power differential. If you, if you and I can't contest, we don't contend it's not like you we fight and you might win or we fight even you'll win comfortably. It's, you are so unbelievably powerful compared to me that there's nothing I can do to stop you. That seems like a recipe for something really, really not great happening. Because if you think about like, uh, you know, european countries encountering each other and I'm just speculating, I don't know anything about history, but let's say countries that can contend with one another vs countries that can't let's say an alien species, alien race shows up. You know right now we don't want that. I think Stephen Hawking said that it makes it makes perfect sense to me. We don't want that. If you can come here, we better hope you're nice because what are we gonna do, what we're gonna hope that you invade the water planet like they did and uh you know, one of the uh Lord of the war of the worlds. So I guess what I'm trying to get across is like shocking levels of power, differential between groups makes the makes the world ripe for horrific abuse in the event that someone decides to do it. It's like I like to imagine an adult hitting a child, like hitting, hitting a child, no one in their right mind would ever go like that's a great idea because it's such a, it's so grossly imbalanced like this is wrong, but but it's also on the table only because of the gross imbalance. So I guess to come back, it's like whether we create ai and it's on some crazy level of its own or it's I'm in charge of it or I just, it seems like we're creating, you mentioned like game theory and nuclear war, what prevented nuclear war, I mean presumably mutually assured destruction, I mean hopefully also humanity and and the humanity and the reasonable, you know, cooler heads prevailing and going, hey, I can, I can understand the veil of ignorance and I um I don't go, oh yeah, let me kill those guys because I can't go, this is wrong period and in concept this is not an action I should take, but it's also nice and easy to keep me honest if I know that I can't get you without being got myself. But what happens when I can get anyone anything and I'm more or less untouchable? Like that seems to me to be like, like various times in colonial history, You know what I mean? And what happened? We </s>

<s>[INST] one of the miracles to me. Perhaps the layman again, I was born in the soviet union. Uh so I have echoes, [/INST] at least in my family history of World War </s><s>[INST] two and the cold [/INST] War. </s><s>[INST] Do you have a sense of why human civilization has not destroyed itself through nuclear war? A nuclear deterrence? And thinking about the future, does this technology has a role to play here? And what is the long term future of nuclear deterrence look like? [/INST] Yeah, it's you know, this is one of those hard, hard questions. And I should note that Lockheed Martin is you know, both proud and privileged to play a part in multiple legs of our nuclear and strategic deterrent uh systems like the trident, uh submarine launched ballistic missiles. You know, you talk about, is there still a possibility that the human race could destroy itself? I'd say that possibility is real. But interestingly, um in some sense, I think the strategic deterrence Have prevented the kinds of, you know, incredibly destructive world wars that we saw in the first half of the 20th century. Now, things have gotten more complicated since that time and since the Cold War, it is more of a multi polar great powers world today. Uh just to give you an example back then, you know, there were, you know, in the in the Cold War time frame, just a handful of nations that had ballistic missile capability By last count. And this is a few years old. There's over 70 nations today that have that similar kinds of numbers in terms of space based capabilities. So, so the world has gotten more complex and more challenging. And the threats I think have proliferated in ways that we didn't expect. The nation today is in the middle of a recapitalization of our strategic deterrent. I look at that as one of the most important things that our nation can do. </s><s>[INST] What is involved in deterrence. Is it is it being ready to attack or is it the defensive systems that catch attacks? [/INST] A little bit of both? And so it's a complicated game theoretical kind of program. But ultimately, um we are trying to prevent the use of any of these weapons. And the theory behind prevention is that even if an adversary uses a weapon against you, you have the capability to essentially strike back and do harm to them. That's unacceptable. And so that will deter them from, you know, making use of these weapons systems. Um the deterrence calculus has changed of course with uh, you know, more nations now having these kinds of weapons. But I think, you know, from my perspective, it's very important uh to maintain a strategic deterrent, you have to have systems that you will know, you know, will work when they are required to work. You know, that they have to be adaptable to a variety of different scenarios in today's world. And so that's what this recapitalization of systems that were built over previous decades, making sure that they are appropriate, not just for today, but for the decades to come. So the other thing I'd really like to note is strategic deterrence has a very different um uh character today. Uh you know, we used to think of weapons of mass destruction in terms of nuclear, chemical, biological and today we have a cyber threat. Um We've seen examples of the use of cyber weaponry. And uh if you think about the possibilities of using cyber capabilities, an adversary attacking the US to take out things like critical infrastructure, electrical grids, water systems, um those are scenarios that are strategic in nature to the survival of a nation as well. So that is the kind of world that we live in today. Um and you know, part of my hope on this is one that we can also develop technical or technological systems perhaps enabled by ai and autonomy that will allow us to contain and to fight back against these kinds of uh new threats that were not conceived when we first develop their strategic deterrence. </s><s>[INST] Yeah, I know that luck is involved in cyber. I saw you mentioned that uh it's an incredibly change nuclear almost seems easier than cyber because there's so many attacks, like there's so many ways that cyber can evolve in such an uncertain future. But talking about engineering with the mission, I mean, uh in this case that your engineering systems that basically save the world [/INST] well, like, like I said, we were privileged to do to work on some very challenging problems for for very critical customers here in the US and with our allies abroad as well. </s><s>[INST] Lockheed builds both military and non military systems and perhaps the future. Lockheed maybe more and non military applications. If you talk about space and beyond. I say that as a preface to a difficult question. So President Eisenhower, in 1961 in his farewell address, talked about the military industrial complex and that it shouldn't grow beyond what is needed. So what are your thoughts on those words, on the military industrial complex and the concern of growth of their developments beyond what may be needed? [/INST] That what where it may be needed is a critical phrase of course. And I think it is worth pointing out, as you noted that Lockheed martin, we're in a number of commercial businesses from energy to space to commercial aircraft. And so I wouldn't and I wouldn't neglect the importance of those parts of our business as well. I think the world is dynamic and uh, you know, there was a time, it doesn't seem that long ago to me was I was a graduate student here at MIT and we were talking about the peace dividend at the end of the Cold War. If you look at expenditure on military systems as a fraction of GDP were far below peak levels of the past. And uh to me at least it looks like a time where you're seeing global threats changing in a way that would warrant relevant investments in defense, defensive capabilities. Um the other thing to note, mhm, for military and defensive systems, it's it's not quite a free market, right? We don't sell to people on the street and that warrants a very close partnership between, say, the customers and the people that design build uh and maintain these systems because of the very unique nature, the the very difficult requirements, the very uh great importance on safety and on uh operating the way they are intended every time. And so that does create. And it's frankly, it's one of Lockheed martin's great strengths is that we have this expertise built up over many years in partnership with our customers to be able to design and build these systems that meet these very unique mission needs. </s>

<s>[INST] the following is a conversation with George shots. He's the founder of comma ai Machine learning based vehicle automation company. He is most certainly an outspoken personality in the field of AI and technology in general, he first gained recognition for being the first person to carrier unlock an iphone and since then he's done quite a few interesting things at the intersection of hardware and software. This is the artificial intelligence podcast. If you enjoy it, subscribe on youtube, give it five stars on itunes supported on Patreon or simply connect with me on twitter. A lex Friedman spelled F R I D M A N and I'd like to give a special thank you to jennifer from Canada for her support of the podcast on Patreon. Merci Beaucoup jennifer, She's been a friend and an engineering colleague for many years since I was in grad school. Your support means a lot and inspires me to keep this series going. And now here's my conversation with George Hotz. [/INST] I think </s><s>[INST] we're living in a simulation. [/INST] Yes, but it may be unfalsifiable. </s><s>[INST] What do you mean by unfalsifiable? [/INST] So if the simulation is designed in such a way that they did like a formal proof to show that no information can get in and out. And if their hardware is designed for the anything in the simulation to always keep the hardware and spec, it may be impossible to prove whether we're in a simulation or not. </s><s>[INST] So they've designed it such as a closed system you can't get outside the system. Well, [/INST] maybe it's one of three worlds were either in a simulation which can be exploited. We're in a simulation which not only can't be exploited, but like the same things too about VMS um, a really well designed VM. You can't even detect if you're in a VM or not. </s><s>[INST] That's brilliant. So where it's Yeah. So the simulation is running on a virtual machine, [/INST] but in reality all VMS have wasted the fact. </s><s>[INST] That's the point. I mean, is it uh, you've done quite a bit of hacking yourself and so you should know that uh really any complicated system will have ways in and out. [/INST] So this isn't necessarily true going forward. I spent my time away from comma, I learned a cock dependent. We typed like it's a language writing math proofs and if you write code that compiles in a language like that. It is correct. By definition. The the types check. It's correct. So it's possible that the simulation is written in a language like this, in which case, </s><s>[INST] Yeah, but that that can't be sufficiently expressive language like that. We can it can be Okay. All right. So the [/INST] simulation doesn't have to be turing complete if it has a scheduled end date looks like it does actually with entropy. </s><s>[INST] I mean, I don't think that a simulation that results in uh something as complicated as the universe would would have a formal proof of correctness. Right? Uh, it's possible. Of course. [/INST] We have no idea how good their tooling is and we have no idea how complicated the universe computer really is. It may be quite simple. </s><s>[INST] It's just very large. Right? [/INST] It's very it's definitely very large, </s><s>[INST] but the fundamental rules might be super simple. [/INST] Conway's game of life kind of stuff. </s><s>[INST] Right? So if you could hack so imagine stimulation that is hackable. If you could hack it, what would you change about? Like how would you approach hacking a simulation? [/INST] The reason I gave that talk, </s><s>[INST] by the way, I'm not familiar with the talks you gave. I just read that you talked about escaping the simulation or something like that. So maybe you can tell me a little bit about the theme and the message there too. [/INST] It wasn't a very practical talk about how to actually escape the simulation. It was more about a way of restructuring an US versus them narrative. If we continue on the path, we're going with technology, I think we're in big trouble like as a species and not just as a species, but even as me, as an individual member of the species. So if we could change rhetoric to be more like to think upwards, I like to think about that we're in a simulation and how we could get out already would be on the right path what you actually do once you do that. While I assume I would have acquired way more intelligence in the process of doing that. So I'll just ask that. </s><s>[INST] So the thinking upwards, what kind of ideas, what kind of breakthrough ideas do you think? Thinking in that way could inspire? And what did you say upwards upwards into space? Are you thinking, sort of, exploration in all forms [/INST] these space narrative uh that held for the modernist generation doesn't hold as well for the post modern generation. </s><s>[INST] What's the space narrative? We're talking about the same space, the three dimensional space, [/INST] like, literally like building like Elon musk, like we're gonna build rockets, we're going to go to mars, we're going to colonize the universe. </s><s>[INST] And the narrative you're referring to was born in the soviet union. You're referring to the race to space race to Space Explorer. [/INST] That was a great modernist narrative. It doesn't seem to hold the same weight in today's culture. I'm hoping for good postmodern narratives that replace it. </s><s>[INST] So, think, let's think. So, you work a lot with ai so ai is one formulation of that narrative. There could be also I don't know how much you do in VR and they are. That's another I know less about it. But every time I play with it in our research is fascinating that virtual world, are you are you interested in the virtual world? I [/INST] would like to move to virtual reality </s><s>[INST] uh in terms of your work [/INST] or I would like to physically move there. The apartment I can rent in the cloud is way better than the apartment I can rent in the real world? </s>

<s>[INST] is there anecdotal stuff like with steve jobs? I think their stories right, in your exploration of the is there something a little bit more than just stories? Is there like a little bit more of a solid data points, even if they're just experiential like anecdotes? Is there something that you draw inspiration from? Like in your intuition, because we'll talk about your trying to construct studies that are more rigorous around these questions? But is there something you draw inspiration from from the past from the 80s and the 90s and Silicon Valley that kind of space? Or is it just like you have a sense based on everything you've learned and these kind of loose stories that there's something worth digging at. [/INST] I am influenced by the gosh, the the just incredible number of, of anecdotes surrounding these. I mean, um uh Carrie Mullis, he he invented pcr I mean absolutely revolutionized biological sciences. He says he wouldn't have won the Nobel prize for him and said he wouldn't have come up with that, had he not had psychedelic experiences. Um you know, now he's an interesting character. People should read his autobiography because you could point to other things he was into, but I think that speaks to the casting your nets wide and this mental flex more of these general these general mechanisms where sometimes if you cast your nets really wide and it's going to depend on the person and their influences, but sometimes you come up with false positives, you know, um you know, you connect the dots where maybe you shouldn't have connected those dots, but I think that can be constrained and so much of our not only a personal psychological suffering but our our limitations um academically and in terms of technology are because of the self imposed limitations and and heuristics, these entrance ways of thinking, you know, like, you know, those examples throughout the history of science where someone has come up with a rat, the paradigm Kuhn's paradigm shifts, it's like, here's something completely different, you know, this doesn't make sense by any of the previous models and like, we need more of those, you know, and then you need the right balance between that because so many of the, you know, novel crazy ideas are just bunk and you you need, that's what science is about separating them from from the valid paradigm shifting ideas. But we need more paradigm shifting ideas, like in a big way. And I think we could, I think you could argue that we've because of the structure of academia and science in modern times, it heavily biases against those </s><s>[INST] right? There's all kinds of mechanisms in our human nature that resists paradigm shift quite sort of obviously so and uh psychedelics, there could be a lot of other tools, but it seems like psychedelics could be one set of tools that encourage paradigm shifting thinking. So like the first principle is kind of thinking, so it's a kind of uh you're at the forefront of research here, There's just kind of anecdotal stories, there's uh early studies, there's a sense that we don't understand very much, but there's a lot of depth here. How do we get from there to where Ellen and I can regularly, like I wake up every morning, I have deep work sessions where it's well understood uh like what dose to take, Like if I want to explore something where it's all legal, where it's all understood and safe, all that kind of stuff. How do we get from where we are today to they're not speaking in terms of legality in the sense like policy making all that like laws and stuff meaning like how do we scientifically understand this stuff well enough to get to a place where I can just take it safely in order to expand my uh thinking like this kind of first principles thinking, which I'm in my personal life currently doing? Like how do I have revolutionized particular? Several things like it seems like the only tools I have right now. It's just just but my mind going doing the first principles like, wait, wait, wait, okay. Why has this been done this way? Can we do completely differently? It seems like I'm still tethered to the prior that I bring to the table and I keep trying to untether myself. Maybe there's tools that can systematically help me on to other. [/INST] Yeah, well we need experiments, you know, and that's that's tied to kind of the policy level stuff. Um, and I should be clear. I would never encourage anyone to do anything um illicitly. But yeah, you know, uh in the future we could see these these, you know, compounds used for the for for technical and scientific innovation. What we need are studies that are digging into that right now. Most of what the funding, which is largely fun from philanthropy, um, not from the government. Um, largely what it's for is treatment of mental disorders like addiction and depression, et cetera. Um, but we need studies, you know, one of the early initial stabs on this question decades ago was they took some architects and engineers and said, what what problems have you been working on? Where you've been stuck for months like working on this damn thing and you're not getting anywhere like your heads butting up against the wall. It's like come in here taken. I think it was 100 micrograms of LSD so not a big session and a little bit different model where they were actually working. It was a moderate enough dose where they could work on the problem during the session. I think probably I'm an empiricist. So I'd I'd like to see all the studies done. But the first thing I would do is like a really high dose session where you're not necessarily in front of your computer. You know what you can't really do on a really high dose. And </s>

<s>[INST] to push back, Is it possible that the crazier the person, the less likely they are and in a way where we're safe, meaning like this is the kind of proposition I've had, I had the discussion with my dad is a physicist about this, where he thinks that uh uh like if you have a graph like evil people can't also be geniuses. So his, this is his defense why evil people will not get control of nuclear weapons because to be truly evil, but evil meaning sort of, you can argue that not even the evil of Hitler we're talking about because Hitler had a kind of view of Germany and all those kinds of, there's like he probably deluded himself and the people around him to think that he's actually doing good for the world is similar with Stalin and so on. By evil. I mean more like almost like terrorists where they want to destroy themselves and of the world, like those people will never be able to be actually skilled enough to do to deliver that kind of mass scale destruction. So the hope is that It's very unlikely that the kind of evil that would lead to extinction of humans or mass destruction is so unlikely that we're able to last way longer than 700, years. [/INST] That's free. It's very unlikely in that sense. I accept the argument, but that's why you need to let the clock tick. It's also the best argument for bureaucracy To negotiate a bureaucracy, it actually select against pure evil because you need to build alliances. So bureaucracy in that regard is great, right? It keeps out the worst apples. But look, put it this way, could you imagine 35 years from now the Osama bin laden of the future has nukes are very bad bioweapons. It seems to me you can Yeah, and Osama was pretty evil and actually even he failed, right? But nonetheless, That's what the seven or 800 years is there for. </s><s>[INST] And it might be destructive technology that don't have such a high cost of production or such a high learning curve. Make cyber attacks or artificial intelligence, all those kinds of things. [/INST] Yeah, I mean, let me ask you a question, let's say you could as an act of will By spending $1 million dollars obliterate any city on earth and everyone in it dies and you'll get caught uh and you'll be sentenced to death. But you can make it happen just by willing it, how many months does it take before that happens. </s><s>[INST] So the obvious answer is like very soon. There's probably a good answer for that because you can consider how many millionaires there are. You can look at that, right? I have a sense that there's just People that have $1 million. I mean there's a certain amount, but have $1 million dollars have other interests that will outweigh the uh the interest of destroying entire city? Like there's a particular, you know, like maybe that's a hope that's why [/INST] we should be nice to the wealthy too, right? Yeah. </s><s>[INST] Yeah. All that trash talking is Bill Gates. We just stop that because uh that doesn't inspire the other future. Bill Gates is to be nice to the world. [/INST] That's </s><s>[INST] true. But your senses the cheaper guest to destroy the world, the more likely it becomes. [/INST] Now when I say destroy the world, there's a trick in there. I don't think literally every human will die, but it would set back civilization by an extraordinary degree. It's then just hard to predict what comes next. But a catastrophe where everyone dies that probably has to be something more like an asteroid or supernova. And those are purely exogenous for the time being at </s><s>[INST] least. So I immigrated to this country and I was born in the soviet union in Russia. And uh [/INST] which one? Which is an important question? Well, when you were born in the soviet union, </s><s>[INST] right, Yes. I was born in the soviet union. The rest of the details. But I grew up in Moscow Russia. But I came to this country and this country even back there, but it's always symbolized to me a place of opportunity where everybody could build like uh build the most incredible things, especially in the engineering side of things just invent and build and scale and have a huge impact on the world? And that's been to me the, that's my version of the american ideal of the american dream. Uh Do you think the american dream is still there? Uh Do you think, what do you think of that notion itself from an economics perspective? From a human perspective? Is it still alive? And how do you think about it? The american dream? [/INST] The american dream is mostly still there. If you look at which groups are the highest earners? It is individuals from India and individuals from Iran, which is a fairly new development. Great for them. Not necessarily easy. Both. You could call persons of color may have faced discrimination also on the grounds of religion. Uh yet they've done it. That's amazing. It says great things about America. Now, if you look at native born americans, the story is trickier. People think intergenerational intergenerational mobility has declined a lot recently, but it has not for native born americans For about I think 40 years, it's been fairly constant, which is sort of good. But compared to much earlier times it was much higher in the past. I'm not sure we can replicate that because look, go to the beginning of the 20th century, very few americans finish high school or even have much wealth. There's not much credential ism there aren't that many credentials. So there's more upward mobility across the generations </s><s>[INST] than today. [/INST] And it's a good thing that we had it. I'm not sure we should blame the modern world for not being able to reproduce that. But look, the general issue of who gets into Harvard or Cornell, is there an injustice? Should we fix that? Is there too little opportunity for the bottom say half of americans? Absolutely. It's a disgrace how this country has evolved in that way. And in that sense, the american dream is clearly ailing, but it has had problems from the beginning for blacks, for women from any other groups. </s>

<s>[INST] in. So it did uh through the evolutionary process [/INST] of what they wanted, they would have called it that back then or Yeah, I mean whether they said they didn't have that is pre enlightenment, They just say this is here and and the directive is to try to live in alignment with that. </s><s>[INST] Well then I want to ask who wrote the original code. Yeah, So question. [/INST] So armstrong lays out this good argument and where it gets really interesting is that she emphasizes that all this was considered inevitable, right? So the whole notion and this is like rich and jewish tradition in particular and also an Islamic tradition we can't comprehend and understand what's going on here, right? And so the best we can do to approximate understanding live in alignment as we like act as if this is true. Do these rituals have these actions or whatever post enlightenment? A lot of that got once we learned about enlightenment, we grew these suspicions around religion that are very much of the modern era. Right? So like the the Karen armstrong, like uh Sam Harris's critique, religion makes no sense, right? The critiques based on, well this is you're making the ascent of propositions that you think are true for which you do not have evidence that they are true. So like that's an enlightenment thing, right? This is not the context and this is not the religion is the Rutherford model of the atom, like it's not actually maybe what is underneath happening, but this model explains why your chemical equations work. And so this is like the way religion was you you there is a god will call it this, this is how it works, We do this ritual, we act in this way, it aligns with it just like the model of the atom predicted why you know in A. And C. L. Is going to become salt. This predicts that you're going to feel and live in alignment, right? This beautiful sophisticated theory which actually matches how a lot of great theologians have you thought about it. Um but then when you come forward in time, yeah, maybe it's evolution. I mean, this is like what Peterson hints at, right? Like he's basically is not big. He doesn't like to get super pinned down on this, but I'm just kind of seems where </s><s>[INST] he was almost like searching for the words. [/INST] He focuses more like young and other people. But I mean, I know he's very union, but but that same type of analysis, I think roughly speaking like Armstrong is sort of a it's kind of like a peter Sony in analysis, but she's looking more at the deep history of religion than uh but yeah, he throws in an evolutionary </s><s>[INST] and I wonder what home it finds. I wonder what the new home is. If religion dissipates what the new home for these kinds of natural inclinations are. Uh yeah, well there's technology, whether [/INST] and if it's evolution, I mean, this is Francis Collins book also. He's like, well that's a religious, that could be a very religious notion. I don't think this stuff is interesting. Not a very religious person, but I'm I'm thinking it's not a bad idea. Maybe. Maybe what replaces honestly, like maybe what replaces religion is a return to religion, but in this sort of more sophisticated. I mean if you went back. Yeah, I mean, it's the issue with like a lot of the recent critiques, I think is it's a it's a straw man could critique in a complicated way, right? Because the whole way these the way this works. I mean, the theologians, if you're reading paul Tillich, if you're reading Heschel, if you're reading these people, they're they're thinking very sophisticatedly about religion in terms of this, it's ineffable and we're just these things and this is this deep, connects us to these things in a way that puts life in the line, man, we can't really explain what's going on because we, our brains can't handle it right. For the average person though, this notion of live as if it's kind of how religions work live as if this is true, it's like an os for getting in alignment with, because through a cultural evolution like you behave in this way, do these rich and live as if this is true, um, gives you the what the goal you're looking for. But that's a complicated thing live as if this is true, because if you, especially if you're not a theologian to say, uh, yeah, this is not true in an enlightenment sense, but I'm living as if it kind of takes the heat out of it. But of course it's what people are doing, because, you know, highly religious people still do bad things where if you really were no, there's absolutely a hell, and I'm definitely gonna go to it if I do this bad thing, you would never have, you know, no one would ever murder anyone if they were evangelical christian. Right? So, so it's like what? This is kind of a tangent that I'm I'm on shaky ground here, but it's something I've been interested off and on a lot </s><s>[INST] was as fast. I mean, I think we're in some sense searching for because it is, it does make for a good operating system. We're searching for a good live as if X is true and we're searching for a new X and maybe artificial intelligence will be the very, the new gods that were so desperately looking [/INST] For. Or it'll just spit out 42 </s>

<s>[INST] Lennox. Yeah, but it's funny that from my distant perception, I felt that, you know, it was open source without actually knowing it, but what you're really saying, it was just uh freely licensed, so it's freely licensed, so it felt open sources because universities are not trying to make money so there it felt open source in the sense that you can get access if you want it, right [/INST] and a very, very, very large number of universities had the license and they were able to talk to all the other universities who had the license and so technically not open, technically belonging to A T and T pragmatically pretty open. </s><s>[INST] And so there's a ripple effect that all the faculty and the students then they all grew up and then uh they went throughout the world and uh permeate in that kind of way. So what kind of features do you think made for a good operating system? If you take the lessons of UNIX, you said that, you know, make it easy for programmers like that seems to be an important one, but also UNIX turned out to be exceptionally robust and efficient. Right. So is that an accident when you focus on the programmer or is that a natural outcome? [/INST] I think part of the reason for efficiency was that it began on extremely modest hardware. Very, very, very tiny. And so you couldn't get carried away. You couldn't do a lot of complicated things. Yeah, because you just didn't have the resources, either processor speed or memory. And so that enforced a certain minimum al Itty of mechanisms and maybe a search for generalizations so that you would find one mechanism that served for a lot of different things rather than having lots of different special cases. I think the file system and UNIX is a good example of that file system interface and its fundamental form is extremely straightforward and that means that you can write code very, very effectively for the file system and then one of those ideas? And one of those generalizations is that g that file system interface works for all kinds of other things as well. And so in particular, the idea of reading and writing to devices is the same as reading and writing to a disk that has a file system and then that gets carried further in other parts of the world. Processes become in effect files in a file system. Um and the Plan nine operating system which came along, I guess in the late 80s or something like that, uh took a lot of those ideas from the original UNIX and tried to push the generalization even further. So that in plan nine, a lot of different resources are file systems, they all share that interface. So that would be one example. Uh We're finding the right model of how to do something means that an awful lot of things become simpler and it means therefore that more people can do useful, interesting things with them without him to think as hard about it. </s><s>[INST] So, you said you're not a very good programmer, you're you're the most modest human being. Okay, But you'll continue saying that I understand how this works, but you do radiate a sort of love for programming. So let me ask, uh do you think programming is more an art or science creativity or kind of rigor? [/INST] I think it's some of each, it's some combination, um some of the art is figuring out what it is it do you really want to do? What should that program be? What what would make a good program? And that's some understanding of what the task is, what the people who might use this program want. And I think that's that's art in many respects. The science part is trying to figure out how to do it well. And some of that is a real computer sciences stuff. Like what algorithms should we use at some point? Mostly in the sense of being careful to use algorithms that will actually work properly scale, properly avoiding quadratic algorithms when a linear algorithm should be the right thing, that kind of more formal view of it. Um Same thing for data structures. But also it's I think an engineering field as well and engineer is not quite the same as science because engineering, you're working with constraints, you have to um figure out not only what is a good algorithm for this kind of thing, but what's the most appropriate algorithm given the amount of time we have to compute the amount of time we have to program what's likely to happen in the future with maintenance, who's going to pick this up in the future, all of those kind of things that if you're an engineer you get to worry about. Whereas if you think of yourself as a scientist? Well, you can maybe push them over the horizon in a way and if you're an artist, what's that? </s><s>[INST] So just on your own personal level, what's your process? Like a writing program? Say a small and large sort of tinkering my stuff. Do you just start coding right away and just kind of evolved iterative lee with a loose notion or do you plan on a sheet of paper first and then kind of design in this, what they teach you in the kind of uh software engineering courses in undergrad or something like that. What's your process? Like? [/INST] It's certainly much more the informal, incremental first, I don't write big programs at this point, it's been a long time since I wrote a program that was more than that. I call it a few 100 or more lines, something like that. Many of the programs are right or experiments for either something I'm curious about or often for something that I want to talk about in a class and so those necessarily tend to be relatively small. Um a lot of the kind of code I write these days tends to be for sort of exploratory data analysis where I've got some collection of data and I want to try and figure out what on earth is going on in it and for that, those programs tend to be very small. Sometimes you're not even programming, you're just using existing tools, like counting things or sometimes you're writing och scripts because two or three lines will tell you something about a piece of data and then when it gets bigger, well then I will probably write something in python um because that scales better up to call it a few 100 lines or something like that. And it's been a long time since I wrote programs that were much more than that. </s>

<s>[INST] Yeah. Especially when they see like, I don't know what you look like, but I look tormented when I'm working very hard. Like it means Like it's easy to worry for my well-being. It's not like I'm happy go lucky, but I'm happy underneath it. [/INST] My working too hard is like on a plane every other day or every day getting up at six working out and then going into like two in the morning or one in the morning and then going to sleep and then getting up at six working out getting on a plane going to another place. Like that's what my working is just a lot of travel in mind. If I didn't drink on planes, I don't think anyone would probably worry about me at all. They'd be like, no, you're doing great. </s><s>[INST] But the working out is there. So I got to ask you, because you and I seem to have a similar relationship with running. I like this idea of slow treadmill. I like running slow. Yeah. You know, like a 10 minute mile or something like this. I'll just run forever. Just listen to an audio book, listen to brown noise. Think. I love it. What's brown noise? It's actually brownian noise, but short brown noise. It's kind of like white noise, but deeper. So it's just noise like that. Oh, wow. It kind of sounds like a waterfall. And I'll just listen to it and something happens to me. I think there's, you can ask Kuberman about this. I don't, but apparently there's some science that kind of focuses the mind and so on. [/INST] It's funny because I think sometimes people don't get about running as they go, They get on and they put it on like a six right away on like a treadmill and they go, I can't do this for fucking 30 minutes. But you can if you build yourself up to your six and you play games. I play games with myself a lot. Like I'll play games where I go. Um, and I can do this. I can do this. I can do this almost not all day long, but I can do this a lot longer. Like I did it for two hours the other day before my workout or no hour and a half before my workout where I started at 3.5 walking. And then I, and then I get my jog up to like a five and then I'm like 5.5. Then I go six. And then I go, and once I'm at a six, my body's really loose. And so then I go, all right, bring it down to a 3.5. And then I go punch it to a 7.5 for a quarter of a mile. And then let's walk at a four, let's jog at a five. I can do that. I love, they're called a fartlets, I think. And I love those like where it's like, it's, Regiment and running and sprinting at certain levels. I love that and I love also when I work out to listen to music but put on foreign language cooking shows on Netflix Can you explain that they just put it on mute? You don't need to hear it for some reason. They're sexier the way they're shot. They're sexier. Yeah, and it's like Street food Asia, and they're just watching them make street food in Asia. There's one called broth. It's called broth the nation of broth and they're just making broths and you're like Fuck I want some broth. </s><s>[INST] So this is South America. This is Asia South America Asia [/INST] They do one on pizzas. I've watched this one on pizzas. I've watched it. There's like four episodes. I've watched every episode so many times that my trainer goes, God, that's that fucking, I could watch that again. I love watching foreign language cooking shows on mute when I work out. </s><s>[INST] While blasting music. While blasting hip hop. See Darren. All right. Well, I usually run outside, but I do the same thing. [/INST] Oh, I can't. I don't mind hiking. And I like, I do, like, you know what, my fun thing, the fun thing I would do, and this is a, this is ripped off totally from Cam Haines, is I like to go, there's a great hike called Fryman Canyon out in the valley where I live. And I'd be like, all right, I'm going to run to Fryman Canyon. I'm going to jog to Fryman Canyon. I'm going to hike Fryman Canyon. And then I'm going to jog back. And then I wonder how long that is. don't think about it. Just know that that's your thing. Just know that that's your thing. And then all of a sudden you're like, shit, that was eight miles. You're like, that's a fucking beast. The hike doesn't even feel like anything. The hike, once you do the jog, there's a hard part there. The jog home is a fucking cakewalk. I had the best jog when I was in Serbia. I had the best jog. I think it was in Hyde Park. I think the name of the park's Hyde Park. It was, get this, it was 80% downhill. Wow. So this jog, You started the park and it was like, and I'll do it like this for you. You went like, down hell like this, down hell like this, down hell like this. And then it was like a little steep incline to get to the beginning of it. So it was like a little like nice, like lower back pain. You're like, okay, okay. And then the jog was perfect. And you did it four times. It was four miles. I loved it. My very first day, I did it. A butterfly got in front of me. It's like six in the morning. So yeah, six in the morning. The butterfly got in front of me. And it ran the whole first mile in front of me. And I just, it was like so surreal. It would disappear and then it would show back up in front of me. You sure it was real? Definitely real. And then the next day, and so I go, I'm on the right path. I'm on the right path. The next day I go for a jog, six in the morning, and it rained. And as I'm doing the steep uphill incline, a tree collapsed in front of me. Just went, and I went, whoa, a tree fell in the woods and I was here to see it. Shut the fuck up. I was like, that's crazy and it didn't hit me. I'm on the right path and then I started getting overthinking it like the next day I saw condom and I was like, this is a good place to do it. I was like, people fucked here last night. But, but yeah, that was one of the best jogs I've ever had. I could do that. I could run that park every single day and no one jogged that park in Serbia. </s>

<s>[INST] And in some sense, those stories are platforms and uh the kinds some of which itself is creating, right? Platforms in which we define the future. So, last question, what do you get philosophical, maybe bigger than you have a Microsoft? What do you think The next 2030 plus years looks like for computing for technology, for devices, do you have crazy ideas about the future of the world. [/INST] Yeah, look, I think we you know, we're entering this time where we've got we have technology that is progressing at the fastest rate that it ever has and you've got you got some really big social problems like society, scale problems that we have to we have to tackle and so you know, I think we're going to rise to the challenge and like figure out how to intersect like all of the power of this technology with all of the big challenges that are facing us, whether it's uh you know global warming, whether it's like the biggest remainder of the population boom is in uh africa for the next 50 years or so. And like global warming is going to make it increasingly difficult to feed the global population in particular. Like in this place where you're going to have like the biggest population boom um I think we you know like a i is gonna uh like if we push it in the right direction, like you can do like incredible things to empower all of us to achieve our full potential and to um you know like live better lives but like that also means focus on like some super important things like how can you apply it to health care to make sure that uh you know like our quality and cost of and and sort of ubiquity of health coverage is is better and better over time. Like that's more and more important every day is like in the in the United States and like the rest of the industrialized world, western europe china, japan Korea, like you've got this population bubble of like aging, working, you know, working age folks who are, you know, at some point over the next 2030 years, they're going to be largely retired and like you're going to have more retired people and working age people and then like you've got, you know, sort of natural questions about who's gonna take care of all the old folks and who's going to do all the work. And the answer is to like all of these sorts of questions like where you're sort of running into, you know, like constraints of the, you know, the world and of society has always been like what tech is gonna help us get around this. You know, like when I was when I was a kid in the seventies and eighties, like we talked all the time about like uh like population boom, population boom, like we're gonna uh we're not gonna be able to like feed the planet. And like we were like right in the middle of the green revolution where like </s><s>[INST] this this [/INST] massive technology driven uh increase in crop productivity like worldwide and like some of that was like taking some of the things that we knew in the west and like getting them distributed to the, you know to the to the developing world and like part of it were things like um you know, just smarter biology like helping us increase and like we don't talk about like, yep overpopulation anymore because like we can more or less we sort of figured out how to feed the world, like that's a that's a technology story. Um and so like I'm super super hopeful about the future and in the ways where we will be able to apply technology to solve some of these super challenging problems, like I've I've like one of the things that I I'm trying to spend my time doing right now is trying to get everybody else to be hopeful as well because you know, back to Harari, like we we are the stories that we tell, like if we, you know, if we get overly pessimistic right now about like the the potential future of technology, like we, you </s><s>[INST] know, like [/INST] we we may fail to fail to get all of the things in place that we need to like have our best possible future </s><s>[INST] and that kind of hopeful optimism. I'm glad that you have it because you're leading large groups of engineers that are actually defining that are writing that story that are helping build that future, which is super exciting and uh I agree with everything you said except I do hope clip he comes [/INST] back, we </s><s>[INST] miss them, I speak for the people so Callan, thank you so much for talking [/INST] today, thank you so much for having me. It was </s><s>[INST] a pleasure. [/INST] </s>

<s>[INST] right? That could be a hoax. But other things might not be. I mean, this is the point. I mean, this is why it's nice to remove some of the stigma about this topic because it's all just data and uh, and anomalous events are such that there is going to be, they're going to be rare in terms of how much data they represent. But we have to consider the full range of data to discover the things that actually represents something that's, um, if we pull at it, we'll discover something that's extraterrestrial or something deep about the phenomena on earth that we don't yet understand. Right? [/INST] Well, if it only stimulates people for instance to think, okay, well what happens if we could move like that with momentum list movement and, and it stimulates young individuals to go into the sciences too. Ask those questions. That to me is fascinating. I mean, after I've been openly talking about this in the last year, especially, I've had a number of, uh, students from top schools who aren't my students come to me and say if I can help, let me, how can I help? I never had thought about this before, But you opened you and others, not just you and others have opened my mind to thinking about this matter. </s><s>[INST] Yeah, that's why it's actually funny that Elon musk doesn't think too much about this. Uh, these kinds of propulsion systems that could defy the laws of physics as we currently understand them. To me, it's a powerful way to think what, what is possible. It's, uh, it's inspiring. Even if some of the data doesn't represent, uh, extraterrestrial vehicles. I think the, the observation itself, it's like something you mentioned, which is, uh, you know, hypothesizing imagining these things. Considering the possibility of these things, I think opens up your mind in a way that ultimately can create the technology. First, you have to believe that technology is possible before you can create it [/INST] in my own lab. You know, we always look for as, as I've said before, what is inevitable and you know, saying inevitably this is the kind of data we need. But if we need that kind of data, the instrument we want isn't, doesn't exist. Okay, so I imagine the perfect instrument, I can't make it and you back into something which is practical. And then you, in a sense, reverse engineer the future of what it is that you want to make. And I've started and sold like at least half a dozen or more companies using that basic premise. And so it was always something that didn't exist today, but we imagined what we wanted. And at the time many people said it couldn't be done. I mean, for instance, all the gene therapy that's done today with retroviruses came from a group meeting in David Baltimore's lab, I was a postdoc with him and one of the other postdocs, I wasn't able to make retroviruses in a way that he wanted to and I realized I had a cell line that would allow us to make retroviruses in two days rather than two months. And so he and I then worked together to make that system. And now all gene therapy with retroviruses is done using this basic approach around the whole world because something couldn't be done and we wanted to do it better and we imagined the future. And so that's I think what the whole Ufo phenomenon is doing for people, It's like, well, let's imagine a future where these kinds of technologies are. But also let's imagine a future where we don't blow ourselves up. Right? So if these things are there, they managed to not blow themselves up. So it means that at least one other civilization got past the inflection point. </s><s>[INST] So, if some of the encounters are actually representing alien civilizations visiting us, why do you think they're doing So, you suggested that perhaps it's this study, understand their own past. Right. Right. What what what are some of the motivations do you think? And again from from our perspective us as humans, what motivations would we have when we approach other civilizations we might discover in the future. [/INST] Well, I think one motivation might be to steer us away from the precipice, right? Or on the assumption that, you know, even if we make it past the precipice, at least we're not a bunch of psychopaths, you know, running around. So maybe there's a little bit of motivation there to make sure that you're the neighbor that's growing up next to you is not unruly. Um you know, but I mean maybe it's sort of a moral imperative like what we have with, you know, creating uh national parks where animals can continue to live out their lives in a natural way. Um I don't know. I mean that would be, I mean, the problem is we're imagining from a anthropomorphic viewpoint, what an alien might think. And as I've said before, alien means alien, right? I mean not Hollywood aliens, but the whole different way of thinking and a whole different level of experience. And let's say wisdom, hopefully uh that we could only hope to understand now. But if we ever get out there, if we ever make it past our current problems, uh and even if we don't have faster than light travel. And even if we're only using ram scoops or light sails to get where we want to go And it takes us 10,000 years to get somewhere or to spread out, um we might encounter such things and we're just going to stomp all over it like we did in colonial south America or africa or all the rest on our current path, likely, you know? And and so what are we going to learn? </s>

<s>[INST] If you were managing your money, you were done. You were finished. [/INST] You're saying this kind of stuff naturally emergencyable to states. So my point is what I presented as the strongest criticism of anarchism are inevitably descriptions of status quo. What you're describing is already the event. I am a big insurance company, I don't want to pay you, I call Washington, either I pay you and Washington gives me a subsidy. So what you're describing is an inevitable aspect of having a government. Yes. So what I'm describing is the inevitable evolution of anarchy into a government. I just think that the- Markets don't consolidate into Monopoly. That's the leftist propaganda myth. Not markets where you have substitute products, but this is the problem. The problem is force has no substitute. That is, force is not a product you can have. So, this is my fundamental issue about turning…completing police forces. Force is not a product. The service- It's not a service. It's not a service and it's not a… Security is not a service? Well, security in the context of a legal system is... But this is the point, the legal system, the laws, are not a service or product. They are a different type of human institution. Science is not a product or service. It's a different type of human institution. You can create markets and some you cannot. Law is not marketable system. It's not a service. For the service. It's not a service and it's not a product. Security is not a sad. Can I ask a question quickly? Any other field other than law that you think you can't create markets? No science. Science is not marketable. The science itself is not marketable. Well, sure. And the same method because law is not marketable. Law is the system that allows markets to happen. Right? You need a system of law whether it's private law in a in a in a particular narrow context or whether it's broader law. Law is the is the is the context in which markets arise. So one of the reasons we transact is we know that there's a certain contract between us, explicit or implicit, that is protected by a certain law, whether it's protected by a private agency or private agency, the government doesn't matter, but there's a certain contract that is protectable, right? By a system. Theoretically. Yes. So law is the context in which markets arise. Sure. You don't create a market because there's nothing above it, in a sense. It is the context that allows markets to be created. Once you market it, markets fall apart. So you think that law could be a market? And it already is a market. And we see it, for example, eBay. If I am buying something from your own, I won't even know his name. I don't know. Maybe he's in another country. And he screws me out of the money. I don't have acts. I can't sue you. Or if I sue you in England, it's good luck with that. You're not going to argue that I'm going to sue you. What happens in this case, which has already been solved by the market, eBay and PayPal, which has access to your bank account, they act as the private arbiter. They're going to get it wrong a lot. Not even a question. Just like Yaron's not going to argue that the government right now gets it wrong a lot. That's not even a question. The point is, at the very least, I'm going to get my resolution faster, cheaper, and more effectively. So the issue with having any kind of government, anything, and Yaron's not going to disagree with this, is at the very least, it's going to be expensive, inefficient, and cause conflict. Yeah, but I think what it allows is exactly- We don't even know what the Supreme Court's going to judge. Again, you're moving us to today's environment, which I'm trying to guess, right? I'm moving us to reality. No, but reality doesn't have to be what it is. I mean, go back and try and guess. I'm moving us to reality. That's the most anti-Ran quote for this. No. No, in a sense of the politics, the political reality. I know. But the quote by itself is great. </s><s>[INST] I know. Myself is great. I know. [/INST] I know. I know. You'd love to. He agrees with Donald Hoffman. It turns out I agree with Hoffman. He's an elf. It's not an inch. So it's, it's, where were we? So I believe that because we have a certain system of government, right, it allows for these private innovations to come about that facilitate certain issues in a much more efficient way than the government would deal with it. But it's only because we have a particular system that has defined property rights that has a clear view of what property rights are. It has a clear view of what transaction meaning, what the, what contract law is. And eBay has a bunch of stuff that you sign, whether you read it or not. Sure. Of course. All of that is defined first. And then there are massive innovations at the, at the level of particular transactions, the level of an eBay that facilitate increased efficiency, and that's great. But the fact is none of that gets developed, none of that gets created in a world in which I might be living under the different definition of property rights. eBay might be living on a separate definition of property rights. You might have a third definition of property rights. And there's no mechanism by which we can actually operationalize that because we all have a different system. There is a, we already have that. Let's change the example I just used. What happens if a Chinese person who has different definition of private rights, kills an American in Brazil? Again, in a smaller community, what happens is lots of violence. No, but I'm talking about it right now. A Chinese person has- Right now, the only reason that it doesn't lead to violence is because people are afraid of even more violence and it affects many people, large numbers of people who don't want to go to war. In a state where the states were small, in those little states, there was war all the time for exactly those reasons. Because the cost was lower, because it was more personal, because I knew maybe the person who was killed over there, and I went to my king and he encouraged him to go to war. You know why there was war? Violence is constant. You know why there was war? Because there had been no Ayn Rand. ideas lead to good societies, which leads to good people, which leads to good behavior, good interrelationships. So now that we have Ayn Rand, all this stuff in the past is irrelevant because if they studied her works, Rand was on Donahue again, you could watch the clip, and he asks her, she goes, he goes, you're saying that if we were more selfish and acted more self-interest, there'd be less war, less Hitler, and she said there wouldn't be any. Right? If you were more selfish, there wouldn't be any Hitless. Right? Who do you regard as the overwhelming authority if I am buying a product from you as a incumbent in England via eBay? Who is the governing authority? The governing authority is the legal systems in England and the United States, which have to be synchronized pretty well. Right. Right. But what I'm saying is... It's why eBay... Why do they have to be... Why eBay doesn't function in certain countries, because there is no legal system... Right. But what I'm saying is... ... It's to why eBay... ... why they're... My point is, why do those legal systems have to be a function, specifically of geography, as opposed to, why can't I, sitting here, I could sit here, you're not, let me finish my point. I can sit here and be a British diplomat, right? And as a British diplomat, I'm going to be treated differently under American law than you are as an American citizen, as you are. Why can't you have that same process? Sure we're geographically proximate, but I'm a citizen of this company and you're a citizen of that company. Why would that be different in your opinion? Let me finish my point. If it's England and the United States, it's probably not going to matter that much, right? But if it's Iran and the United States, then the fact that we're sitting next to each other makes a huge difference. Oh, I... Massive difference. And the fact is that, and I think would be the first technologist, and this is why she was so opposed to anarchy. It's not... That's not why. Sure. It's because of Rothbard. It has nothing to do with... Nothing. It has nothing to do with Rothbard's... Nothing. Nothing. How do you know? Nothing. How would you know? Because argument against anarchy is an intellectual one, not a personality based one... </s>

<s>[INST] They have very specific questions like, what is that, the country by country kind of specific questions or what The [/INST] thing that they're all trying to do that, I think is the right. I don't have to give them a really basic piece of advice because they're already doing it. Like they're trying to find a vocation, they they're really interested in. What I mean by that is it's like a career where they find meaning, where the work is almost like superfluous because they just they would do it for free and they're passionate about and they really find meaning in the work. And and and then it becomes a little bit all consuming. So scientists do that in their own way. I think international development humanitarian workers, people who are doctors and nurses, like we all do our careers for other reasons, right? But but they they find like meaning in their career. And so the thing, so I don't have to tell them whatever you do find meaning, um and try to make it a vocation something that you would do for free, amongst all of these many, many, many options. Uh that's what I would tell that, but that's what I would tell high school students and young people in college, </s><s>[INST] sometimes it's hard to find a thing and hold on to it. [/INST] Well, that's the other thing. It took me a long time. So I actually started off as an accountant, I was an accountant with Deloitte and Touche for a few years, so I I did </s><s>[INST] not. Did [/INST] you wake up in the morning </s><s>[INST] excited? I [/INST] was miserable. I got, I found it by accident which is another different story, but I landed in this job and a degree where I studied accounting and I was miserable, I was totally miserable and I hated it and I was becoming a miserable person um and so I eventually just quit and I did something new, but I was still, you know, but then I was working in the private sector and I actually just need trial and I actually had to try on like three or four or five careers before I found like this mixture of academia and activism and research and international development and what </s><s>[INST] did you know that this was love when you, when you found this kind of international development, that is the academic academic context to [/INST] the key lesson was just trial and error, which we all have to engage until until it feels right, </s><s>[INST] It's okay. Alright. Step one is trial and error, but until it feels right because like it often feels right, but not perfect. [/INST] Yeah, well, if that's true right enough, I mean, I was really intellectually engaged, like I just loved learning about it. I wanted to read more like it in some sense, like, like I was doing, I was an account but I was reading about like world history and international development in poor countries in my spare time. Right? And so it was like this hobby and I was like, wait a second. I could actually do that. Like just I could like researchers and even write the neck those books and that's kind of what I did like 25 years later. That didn't occur to me right away. I didn't even know it was possible. This is the other thing people do, People do their 9 to 5 job and then they find meeting and everything else they do, they're volunteering and their family and their hobbies and things and that was my social media and, and um, and that's a great path to like, I mean that's because not all of us can just have a vocation or you don't find it I think. And then you just circumscribed what you do in your work and then you go find um and that's not entirely true because everyone in my family does like their job and get a lot of fulfillment out of it. But um, but I think it's not, that's, that's a different path in some ways. </s><s>[INST] So it's good to take the leap and keep trying stuff even when you found like a little local local minima [/INST] Yeah, the hardest part was it got easy after a while it was was quitting. But but now I take this to a lot of, you know, and one of the people, I think one of the reasons I discovered your podcast or maybe Tyler Cowen, </s><s>[INST] Tyler [/INST] takes this approach to everything. He takes this approach to movie. And he's like walking to the movie theater after half an hour if you don't like the movie and um you know what kind of </s><s>[INST] person he probably is, I don't know, but now that you say this, he's probably somebody that goes to a restaurant. If, if the meals is not good, I could see him just walking away like paying for and just walking away [/INST] meal and go eat something better. That's exactly right. And I thought that was kind of crazy. And I never, I was the person, I would never just put a book down halfway and I would never um stop watching a movie. But then I, and I convinced my wife, we lived in new york when we were, when we, when we're single initially in three denominations when we were childless. Uh and we lived in new york, There's all this culture and theater and stuff and I just said let's go two more plays, but let's just walk out after the first act if we don't like it. And she thought that was a bit crazy. And I was like, no, no, here's the logic, Here's what Tyler says and then we started doing it and it was so freeing and glorious. We just go to take so many more chances on things and we would, and if we didn't like it, we were and we were walking out of stuff all the time. Um and so I think I did that without realizing that that's how I like I just kept quitting my jobs. Yeah. And trying to find something else that like some risk because </s>

<s>[INST] So that's a really compelling and interesting idea to have two. First question. So one on the ensemble part of everything coming together, you have these 1000 brains, how how do you know which one has done the best job of forming [/INST] the great question. Let me explain. There's a problem that's known in neuroscience called the sense of fusion problem. And so the idea is there something like the image comes from the eye, there's a picture on the retina and that gets projected to the neocortex. Oh, by now it's all spread out all over the place and it's kind of squirrely and distorted and pieces are all over the, you know, it doesn't look like a picture anymore. When does it all come back together again? Right. Or you might say well yes, but I also I also have sounds or touch is associated with a couple. So I'm seeing the cup and touching the cup. How do they get combined together again? So this is called the sensor fusion problem is if all these disparate parts have to be brought together into one model. Someplace that's the wrong idea. The right idea is that you got all these guys voting. There's auditory models of the cup, There's visual models, the cup, those tactile models of the cup. Um, there are one in division system, there might be ones that are more focused on black and white and unfortunately color, it doesn't really matter. There's just thousands and thousands of models of this cup and they vote, they don't actually come together in one spot. Just literally think of it this way. Imagine you have these columns are about the size of a little piece of spaghetti Okay, like a 2.5 millimeters tall and about a millimeter in mind they're not physical like but you can think of them that way and each one is trying to guess what this thing is we're touching now. They can they can do a pretty good job if they're allowed to move over touch so I can reach my hand into a black box and move my finger around an object. And if I touch enough pace is like okay I don't know what it is but often we don't do that often. I could just reach and grab something with my hands all at once and I get it. Or if I had to look through the world through a straw so I'm invoking one little column. I can only see a part of something. I have to move the straw around. But if I open my eyes to see the whole thing at once so what we think is going on. It's all these little pieces of spaghetti if you have all these little columns in the cortex or all trying to guess what it is that they're sensing um they'll do a better guest if they have time and can move over time. So if I move my eyes with my fingers. But if they don't they have a they have a poor guest it's a it's a probabilistic s of what they might be touching now imagine they can post their probability at the top of little piece of spaghetti. Each one of them says I think and it's not really a probability distribution. It's more like a set of possibilities in the brain. It doesn't work as a probability distribution works is more like what we call a union you could say. Uh and one common sense, I think it could be a coffee cup, soda can or water bottle. Another calm says, I think it could be a coffee cup or you know telephone or camera or whatever, right? Um and all these guys are saying what they think it might be and there's these long range connections in certain layers in the cortex. So there's some layers in some cell types in each column sending projections across the brain. And that's the voting occurs. And so there's a simple associative memory mechanism. We've we've described this in a recent paper and we've modeled this um that says they can all quickly settle on the only or the one best answer for all of them if there is a single best answer, they all vote and said yeah, it's gotta be the coffee cup. And at that point they all know it's a coffee cup and at that point everyone acts as if it's a coffee cup, then we know it's a coffee, even though I've only seen one little piece of this world, I know it's coffee cup I'm touching or I'm seeing whatever. And so you can think of all these columns are looking at different parts in different places, different sensory input, different locations. They're all different, but this layer that's doing the voting, um that's it solidifies, it's just like it crystallizes and says, oh, we all know what we're doing and so you don't bring these models together in one model, you just vote and there's a crystallization of the vote. </s><s>[INST] Great, that's uh at least a compelling way to think about about the way you form a model of the world. Now, you talk about a coffee cup, do you see this as far as I understand, you're proposing this as well? That this extends to much more than coffee cups? It [/INST] does, </s><s>[INST] or at least the physical world, it expands to the world of concepts. [/INST] It does. And well, the first, the primary face every evidence for that is that the regions of the Neocortex that are associated with language or high level thought or mathematics or things like that, they look like the regions of the Neocortex, that process, vision, hearing and touch, they don't look any different or they look only marginally different. Um and so one would say, well if vernon Mount Castle who proposed that all the, all the parts of the country is doing the same thing, If he's right then the parts are doing language or mathematics or physics are working on the same principle, they must be working on the principle of reference frames, so that's a little odd thought. Um hmm, but of course we had no we had no prior idea how these things happen, so let's let's go with that. Um and uh we, in our recent paper we talked a little bit about that, I've been working on it more since I have better ideas about it now, um I'm sitting here very confident that that's what's happening and I can give you some examples to help you think about that. Um it's not, we understand it completely, but I understand better than I've described it in any paper so far. So, but we did put that idea out there says okay this is it's a good place to start, you know, and the evidence would suggest it's how it's happening and then we can start tackling that problem one piece at a time. Like what does it mean to do? High level thought, what do you mean to do? Language, how would that fit into a reference frame </s>

<s>[INST] energy. And that's special relativity. And that ultimately is connected to the force of gravity, which is one of the forces that seems to, based on its strength, operate on a different scale [/INST] than some of the other forces. So, it operates at a scale that's very large. What happens there is just this curvature of space which causes the paths of objects to be deflected. That's what gravity does. It causes the paths of objects to be deflected. And this is an explanation for gravity, so to speak. And the surprise is that from 1915 until today, everything that we've measured about gravity precisely agrees with general relativity. And that it wasn't clear black holes were sort of a predict... Well, actually, the expansion of the universe was an early potential prediction, although Einstein tried to sort of patch up his equations to make it not cause the universe to expand. Because it was so obvious the universe wasn't expanding. And it turns out it was expanding. And he should have just trusted the equations. And that's a lesson for those of us interested in making fundamental theories of physics is, you should trust your theory and not try and patch it because of something that you think might be the case, </s><s>[INST] that might turn out not to be the case. Even if the theory says something crazy is happening, [/INST] Yeah, right. Like the universe is expanding, right? But then it took until the 1940s, probably even really until the 1960s, until people understood that black holes were a consequence of general relativity and so on. But the big surprise has been that so far, this theory of gravity has perfectly agreed with these collisions of black holes seen by their gravitational waves. You know, it all just works. So that's been kind of one pillar of the story of physics. It's mathematically complicated to work out the consequences of general relativity, but it's not, there's no, I mean, and some things are kind of squiggly and complicated. Like people believe, you know, energy is conserved. Okay, well, energy conservation doesn't really work in general relativity in the same way as it ordinarily does. And it's all a big mathematical story of how you actually nail down something that is definitive that you can talk about it and not specific to the, you know, reference frames you're operating in and so on and so on. But fundamentally, general relativity is a straight shot in the sense that you have this </s><s>[INST] theory, you work out its consequences. And that theory is useful in terms of basic science and trying to understand the way black holes work, the way the creation of galaxies work, sort of all these kind of cosmological things, understanding what happened, like you said, at the Big Bang, like all those kinds of, well, not at the Big Bang, actually, right? But the... [/INST] Well, features of the expansion of the universe. Yes. I mean, and there are lots of details where we don't quite know how it's working. You know, is there, you know, where's the dark matter? Is there dark energy, you know, etc, etc, etc. But fundamentally, the testable features of general relativity, it all works very beautifully. And it's, in a sense, it is mathematically sophisticated, but it is not conceptually hard to understand in some sense. </s><s>[INST] Okay, so that's general relativity. And what's its friendly neighbor, [/INST] like you said, quantum mechanics, quantum mechanics, quantum mechanics. Right. So quantum mechanics, the sort of the way that that originated was, one question was, is the world continuous, or is it discrete? You know, in ancient Greek times, people have been debating this. People debated it in, you know, throughout history as light kept made of waves as it continuous, as it discreet, as it made of particles, corpuscles, whatever. You know, what had become clear in the 1800s is that atoms, that, you know, materials are made of discrete atoms. You know, when you take some water, the water is not a continuous fluid, even though it seems like a continuous fluid to us at our scale. But if you say, let's look at it smaller and smaller, and smaller, and smaller scale, eventually, Eventually you get down to these molecules and then atoms. It's made of discrete things. The question is sort of how important is this discreteness, just what's discrete, what's </s><s>[INST] not discrete, is energy discrete, is what's discrete, what's not. And so- [/INST] Does it have mass, those kinds of questions? Yeah, yeah, right. Well, there's a question, I mean, for example, is mass discrete, is an interesting question, which is now something we can address. But what happened in the coming up to the 1920s, there was this kind of mathematical theory developed that could explain certain kinds of discreteness, particularly in features of atoms and so on. And what developed was this mathematical theory that was the theory of quantum mechanics, theory of wave functions, Schrodinger's equation, things like this. It's a mathematical theory that allows you to calculate lots of features of the microscopic world, lots of things about how atoms work, etc., etc., etc. Now the calculations all work just great. The question of what does it really mean is a complicated question. Now I mean, to just explain a little bit historically, the early calculations of things like atoms worked great in the 1920s, 1930s, and so on. There was always a problem, there were in quantum field theory, which is a theory of in quantum mechanics, you're dealing with a certain number of atoms, a certain number of electrons, and you fix the number of electrons. You say I'm dealing with a two electron thing. In quantum field theory, you allow for particles being created and destroyed. So you can emit a photon that didn't exist before, you can absorb a photon, things like that. That's a more complicated, mathematically complicated theory, and it had all kinds of mathematical issues and all kinds of infinities that cropped up, and it was finally figured out more or less how to get rid of those. But there were only certain ways of doing the calculations, and those didn't work for atomic nuclei, among other things. And that led to a lot of development up until the 1960s of alternative ideas for how one could understand what was happening in atomic nuclei, et cetera, et cetera, et cetera. Second result, in the end, the kind of most, quote, obvious mathematical structure of quantum field theory seems to work, although it's mathematically difficult to deal with. But you can calculate all kinds of things. You can calculate to a dozen decimal places, certain things. You can measure them. It all works. </s>

<s>[INST] And so maybe we use maybe we'll use a lot of terms that are synonymous. So uh something is plastic, something is malleable changing. Livewire. The name of the book is like, [/INST] so I'll tell you exactly right, but I'll tell you why I chose Livewire instead of plasticity. So I use the term plasticity in the book. But um but sparingly because that was a term coined by William James over 100 years ago and and he was of course very impressed with plastic manufacturing that you could molting in shape and then hold that. But that's not what's actually happening in the brain. It's constantly rewiring your entire life. You never hit an endpoint. The whole point is for it to keep changing. So even in the, you know, a few minutes of conversation that we've been having your brain is changing. My brain is changing. Um next time I see your face. So I will remember, oh yeah, like that time lex and I sat together and we did these things. I </s><s>[INST] wonder if your brain will have like a lex thing going on for the next few months, like you'll stay there until you get rid of it because it was useful for now. [/INST] I'll probably never get rid of it, let's say for some circumstances and I don't see each other for the next 35 years when I run into you, I'll be like, oh </s><s>[INST] yeah, that looks familiar. Yeah, [/INST] yeah, yeah. We sat down for a podcast back when they were podcast exactly </s><s>[INST] back when we lived outside virtual reality. [/INST] Exactly. So </s><s>[INST] you chose livewire. Exactly, [/INST] Exactly. Because plastic implies, I mean it's the term that's used in the field and so that's why we need to use it still for a while, but it implies something gets mold in the shape and then holds that shape forever. But in fact the whole system is completely changing </s><s>[INST] then then back to uh how malleable is the human brain at each stage of life. So what just at a high level is it valuable? [/INST] Yes. And plasticity diminishes. But one of the things that I I felt like I was able to put together for myself after reading thousands of papers on this issue is that different parts of the brain have different plasticity uh windows. So for example with the visual cortex that cement itself into place pretty quickly over the course of a few years. And I argue that's because of the stability of the data. In other words, what you're getting in from the world, you've got a certain number of angles, colors, shapes, you know, it's essentially the world is visually stable. So that hardens around that data as opposed to let's say the somatosensory cortex, which is the part that's taking information from your body or the motor cortex right next to it, which is what drives your body. The fact is bodies are always changing. You get taller over time, you get fatter thinner over time you you might break a leg and have to limp for a while, stuff like that. So because the data there is always changing and by the way you might get on a bicycle, you might get a surfboard, things like that. Um because the data is always changing, that stays more malleable. Um And when you look through the brain you find that it appears to be this, you know how stable the data is, determines how fast something hardens into place. But the point is different parts of the brain hardened into place at different times. </s><s>[INST] Do you think it's possible that uh depending on how much data you get in a different sensors that it stays more malleable longer. So like you know, if you look at different cultures and experience like if you keep your eyes closed or maybe your blind? I don't know. But let's say you keep your eyes closed for your entire life. Uh then then the visual cortex might be much less malleable. The reason I bring that up is like, you know, well maybe we'll talk about brain. Computer interface is a little bit and down the line. But you know, like is this is the malleability a genetic thing or is it more about the data? Like I said that comes in? [/INST] Uh so the malleability itself is a genetic thing. The big trick that mother nature discovered with humans is make a system that's really flexible As opposed to most other creatures to different degrees. So if you take an alligator, it's born, its brain does the same thing every generation. If you compare an alligator 100,000 years ago to an alligator. Now they're essentially the same. Um We on the other hand, as humans drop into a world with a half baked brain and what we requires to absorb the culture around us and the language and the beliefs and the customs and so on. That's what um mother nature has done with us. And it's been a tremendously successful trick. We've taken over the whole planet as a result of this. </s><s>[INST] So that's an interesting point. I mean it's just a Lingard it. That I mean this is a nice feature, like if you were to design a thing to survive in this world. Do you put it at age zero already equipped to deal with the world and like hard coded way or do you put it, do you make it valuable and just throw it and take the risk that you're maybe going to die but you're going to learn a lot in the process and if you don't die you'll learn a hell of a lot to be able to survive in the environment. [/INST] So this is the experiment that mother nature ran and and it turns out that for better, worse we've won I mean, you know, we put other animals in zoos and we Yeah, that's what I might do better. Okay, fair enough. That's true. And maybe what the trick mother nature did is just the stepping stone to today. I but </s>

<s>[INST] So the goal of this kind of therapy is in the uncoupling for that to be permanent to separate. [/INST] So they can recount the event and they can describe it without it triggering the same somatic experience of terror and dread. Um Because terror. Those feelings can be debilitating Obviously </s><s>[INST] physiologically in rem sleep a similar process has happened. That's right, [/INST] thematically rem sleep is about experiencing or replaying intense emotions without experience the somatic, the physical component of the emotion. Either the acting out or the accelerated heart rate and agitation. Likewise with things like ketamine therapies, that's the idea is you're uncoupling the physical sensation from the mental events. </s><s>[INST] What is rem sleep and why is it so special? Maybe we can comment on that rapid eye movement sleep [/INST] Yet discovered in the 50s and the University of Chicago. It's intense brain activity, high levels of metabolic activity dreams in which people report a lot of the theory of mind. We're talking about Simon Baron Cohen theory of mind is was actually something that he developed for the diagnosis of autism. If you take kids most kids of age 567, you put them in front of a tv screen in the laboratory and you have them watch a video where a kid is playing with a ball or a doll. And then the kid puts it into a drawer, shuts the drawer and walks away. And another kid comes in and you asked the child who's observing this little movie, you say, what does this second child think? And they, a typical kid would say they want to play and they don't know where the ball or doll is or they they're upset or they're sad, they want the doll autistic Children tend to say the dolls in the drawer, the toys in the drawer. They tend to fixate. They can't get on the event. They can't get into the mind of that? They don't have a theory of mind dreams in Rem have a heavy theory of mind component. People are after me trying to get me, You can assign motive to other people I'm afraid. But it's because there's an expectation that doesn't tend to happen in slow wave sleep dreams. Now, all this of course, is by waking people up and asking them what they were dreaming about, which, from a standpoint of ai guy or a machine learning or neuroscientists kind of like, but it's the best we've got. But brain imaging in waking states while people view a movie and then brain imaging while people are sleeping supports the idea that that's basically what's going on. So Rem sleep is amazing and you're not going to get much of it during your about with Goggins, but you will afterward </s><s>[INST] why such to comment, Why won't I? So is it not possible to get into it real quick? [/INST] Only if you're very, very sleep deprived, but because you're going to be at high muscular output, that's going to bias you towards more slow wave sleep overall and your body and brain are smart, they will know they will know that your main goal is to recover So you can keep going so you can keep firing your muscular contractions and you can keep running so that you can I mean, it's amazing to think like why do we ever stop the unlike weight training where I can't do a £500 dead lift, I just can't Like a train for it. But I certainly can't do a £600 and I can't do that. What causes us to stop an endurance event is usually not a physical barrier, it's almost always a purely mental barrier. And that's a very interesting problem. I mean neuroscientists don't tend to think about those sorts of problems because it sounds so non neuro scientific, but that's fundamentally related to the question of, you know, what is pursuit, Why, what is the desire to push and to and to carry on? </s><s>[INST] Is there a neuro scientific answer for that question? You think? [/INST] I think the closest thing is this paper from uh, from jenalia farms, the howard Hughes campus showing that if you put uh animals into a simulated environment where you can measure their effort forces on while they're running and you can look at the, you can control the visual environment and you can create a scenario where the animal thinks that its output is futile, it thinks it knows it's running and it's actually running, but you change the frequency of the stripes going by in their visual world, such that they think they're not getting anywhere and eventually they quit. And the thing that determines whether or not they quit is a threshold level of epinephrine in the brain stem if you drop that level back down or you or you give the animals dopamine essentially, they keep going. If you take dopamine down, they they're like, this isn't worth it. It's helplessness. There just this isn't worth my time and energy. </s><s>[INST] But this is where the difference between humans and non human animals is interesting because it does feel like humans have an extra level of cognitive ability that might be relevant [/INST] here. Well, you can pull from different time references, so you're in that moment, you're going to need a kit of things to pull from. So you can think this is in honor of someone else that passed away and you will find a gas reserve. That's amazing right now, whether or not mice or like I remember my brother back in the other cage when I was a little mouse, you know, we don't know, but it's very likely that they don't do that, that they're so present there in the experience of there and then and now that they aren't able to extract from the past and they're not able to project into the future. Like how great it's going to feel when I get to the end of this really lame for VR corridor. I don't think they think about that </s>

<s>[INST] But the mediocrity is enforced there [/INST] correct very strictly and the homogenization pressures trying to climb the rankings by another three places and be a little closer to M. I. T. Though you'll never touch them. That to me is very harmful and you'd rather they be more like Chicago more like caltech or the elder caltech all the more like pick some model, be weird in it, you might fail, that's socially better. </s><s>[INST] Yeah but so the problem that might for example is the mediocrity is really enforced on the junior faculty. So like the people that are allowed to be weird or actually they just don't even ask for permissions anymore are more senior faculty and that's good of course, but you want the weird young people ah you know I find you know this podcast I like talking to protect people and I find the young faculty to be really boring. [/INST] They are, they're the most boring of faculty. </s><s>[INST] Their work is interesting technically technically but just the passion, [/INST] they are drudges </s><s>[INST] ca and it was some of them sneak by like you have like the max tag Mark young version of max check Mark, who knows how to play the role of boring and and fitting in and on the side he does the weird shit. Uh but they're not, they're far and few in between, which I'd love to figure out a way to shake up the system because [/INST] you look at M. I. T. S. Broad institute right and biomedical it's been a huge hit. I'm not privy to their internal doings. But I suspect they support weird more than the formal departments do at the junior level. </s><s>[INST] Yes, that's probably true. Yeah. I don't know what whatever they're doing is working, but we needed to figure it out because I think the best ideas still do come from the uh forget my apologies. But for the humanity side of things, I don't know anybody but the engineering and the science side, I think there's so many amazing ideas are still coming from universities. [/INST] It's not true that you don't know anything about the humanities. You're doing the humanities right now. We're talking about people, there are no numbers put on a blackboard, right? There's no hypothesis testing per se. You have however many subscribers to your podcast, all listening to you on the humanities, every whatever your frequency is, that </s><s>[INST] I'm not in the department of the humanity. That's why they have very different conversations. There's the number of emails I get about, listen, I I really deeply respect diversity and the and the full scope of what diversity means. And also the more narrow scope of different races and genders and so on. It's a really important topic, but there's a disproportionate number of emails I'm getting about meetings and discussions and that just kind of overwhelming. I don't get enough emails from people like a meeting about uh why are all your ideas bad? Let's let's, for example, let me call at M. I. T. Why don't we do more? Uh why don't we kick stanford's ask or google's ask more importantly, in Deep learning and machine learning and ai research. What C cell, for example, used to be a laboratory is a laboratory for artificial intelligence research. And why is that not the beacon of what? Of greatness in artificial intelligence? Let's have those meetings as well. [/INST] Diversity talk has oddly become this new mechanism for enforcing conformity. Yes, </s><s>[INST] exactly. And right. So it's almost like this conformity mechanism finds the hot new topic to use to enforce further conforming. Exactly. Ah boy, I still hope I'm an [/INST] optimistic humanities have innovated through podcasts, including yours and mine and they're alive and well, all the bad talk you hear about the humanities in universities, there's been this huge and run of innovation on the internet and it's amazing. You're </s><s>[INST] right, I never thought, I mean, this is humanity's [/INST] this podcast. I've been speaking prose all one's life and didn't know it. Right. </s><s>[INST] Uh Yeah, I am actually part of the humanities department at M I. T. Now, I didn't did not realize this and I will fully embrace it from this moment on, [/INST] look, you have this thing, the media lab, I'm sure you know about it, done some excellent things, done a lot of very bogus things, but you're out competing them. You're blowing them out of the water? Yeah, like you are them. </s><s>[INST] Yeah, I mean, and I'm talking to those folks and they they're trying to well, uh, just trying to figure it out, I mean, they had their issues with Jeffrey, Epstein and so on. But outside of that, there's uh actually gone through a shift with this particular podcast, for example, where at first it was seen as one of the very first, it was seen as a distraction second, it was a source of like, almost like a kind of jealousy, like the same kind of jealousy you feel when junior faculty outshines the senior faculty and now it's more like, okay, this is the thing, like we should do more of that. We should embrace this guy, we should embrace this thing. So there's a sense that podcasting and whatever this is and it does not do podcasting will drive some innovation with anonymity within different universities. There's a sense that things are changing. It's just that universities lag behind and my hope is that, you know, they catch up quickly. They, they they they innovate in some way that goes along with the innovations of the internet. [/INST] I think the internet will outrace them for a long time. Maybe forever. </s><s>[INST] Well, I mean, it's okay if they're as long as they keep them. [/INST] Yeah, and we're both in university. So we have multiple hats on here. We're speaking, we can complain about the university's, that's like complaining about the podcast, right? We see them, </s>

<s>[INST] Well, okay, let's lay out the full, there's George W Bush, there is Barack Obama, there's donald trump. There is uh biden if uh so they're all driving this van and these exits and they keep not taking the exits and then running out of gas? I do this all the time, thinking where am I gonna pull off? I'll go to to those empty. How could it have been done better? And what exactly uh how much suffering have all of the decisions along the way caused? What are the long term consequences? What are the biggest things that concern you about the decisions we've made in both invading Afghanistan and staying in Afghanistan as long as we have. [/INST] I mean, if we start at the end as you proposed, um you know, the horrific scenes of the airport, you know, that was just 11 dimension. Um I think in the weeks to come, I mean we're gonna see Afghanistan implode. Um There are lots of signs that malnutrition, hunger, starvation are going to claim tens of thousands, maybe hundreds thousands of lives this winter. And I think there is really nothing, there's no framework in place to force all that. </s><s>[INST] What is the government, what is currently the system? There was through all the Taliban. So there could be tens of thousands, hundreds of thousands of starved. Uh Either just almost the famine or starve to death. So this is economic implosion. This is political implosion. What what's the system they're like and what could be the one, you know, some inkling of [/INST] hope, The Taliban sitting control. That's unique when they were in power in the 1990s. From 1996001. They controlled some 85-90% of the country now. They own it all. Uh but they have no budget. The afghan banking system is frozen. </s><s>[INST] So the financial system is a mess [/INST] and it's frozen by the U. S. Because the U. S. Is trying to use that lever to exert pressure on the taliban. And so the ethical quandaries are of course legion. Right? Do you release that money to allow the taliban to shore up their rule? Right. The administration has said no, but the banks aren't working Uh if you're in California, you want to send $100 to your cousin so she can buy bread. You can't do that now. It's almost impossible. There are some informal networks, they're moving some stuff. But there are red lines. The taliban government is incapable fun really just of ruling. I mean they can destroy people on the street. They can force people in the mosque, they can shoot people, they can beat protesters, they can put out a newspaper, they can have their greatest diplomacy. It turns out they can't rule this country. So essentially the hospitals and the kind of health care infrastructure is being managed by Ngos that are international. Um but many people had to leave and and the taliban have impeded some of that work. They told adult women essentially to stay home. Right? So a big big part of the workforce isn't there? So I mean the supply chain is it is kind of crawling to a halt trade with Pakistan and its neighbors. I mean it's kind of a transit trade economy. Um it exports fruits, Pakistan has been closing the border because they're anxious about refugees. They want to exert pressure on the national community to recognize the Taliban because the Pakistan want the Taliban to succeed in power. Because I see that in Pakistan's national interest especially did lends its rivalry with with India. So the Pakistan, the Pakistani security institutions are playing a double game. Especially african people are being held hostage. And so the taliban are also saying, you know, if you don't recognize us, you're going to let tens of millions of afghan starve. </s><s>[INST] So to which degrees Taliban, like who are the Taliban, what do they stand for? What do they want? Obviously year by year this changes. So what is the nature of this organization? Can they be a legitimate, peaceful, kind respectful government sort of hold enough power or or are they fundamentally not capable [/INST] of doing so, I mean, the briefest answer would be that they are a clerical slash military organization. Um, they have this is kind of a imperfect metaphor. But years ago, a german scholar, he's the term caravan to describe them and that has some attractive elements because different people who joined the taliban for different purposes at different times, but today and people tell us, you know, scholars who know more about them than I said. Listen, the Taliban is this kind of hodgepodge of different actors and people and competing interests and I think so we have a lot of scholars say listen there there it's poly centric, it's got people in this city and that city and so on. I think actually I was always very skeptical. How do they know this? I mean this is an organization that doesn't, I want you to know um where the money comes from and so on. But I would say now that we have a clear picture of what has happened. I'd say they already astoundingly well organized clerical military organization that has a a very cohesive and enduring ideology, which is quite idiosyncratic. If we zoom out and continue the conversation we're having about Islam and how we think about radicalism and who's going to what um people throw different terms around to describe the taliban. Some use the term that links it to A kind of school of thought born in the 19th century in India, the Deobandi School. But if you look at their teachings, it's very clear now. I think that these labels, it's like saying, you know, you're an MIT guy. Well what does that mean? I mean it is home to you dozens of different potentially kinds of intellectual orientations. Right? I mean attaching the name of the school doesn't quite capture, I mean </s>

<s>[INST] start to wonder like what what kind of person do you want to be? So all the dreams you had, all the promises you made to yourself and to others, all the ambitions you had that haven't come yet, realized somehow that all becomes really intensely like visceral as, as the struggle is happening. And then when all of that is allowed to pass from your mind, you have this clear appreciation of what you really love in life, which is just like just living just the moment, the like take a step at a time. It's I think what meditation does and it's most effective, it's just that pain is and as a catalyst for the meditative process. I think for me, for me, I don't know um magnus said there's no meaning to life, do you guys agree or no, why are we here? [/INST] I do not know why we're here, but I do know that having some kind of meaning that I give my own life makes it a lot more motivating every day. So I just try to focus on finding meaning within my own life even if I know it's just self imposed </s><s>[INST] and then chess is a part of that, [/INST] chess is a part of it, maybe it was more so when I was younger because it was easier to just feel like I want to improve as a person and to use chess to kind of measure some kind of self improvement and now it's more different than that and I think I need to once again find what that you know northern stars basically I need to have a why for why I'm doing things and then you I feel like I could do very hard things, </s><s>[INST] what role does love play in the human condition, Alex and Andrea [/INST] Andrea start this one since I took the last. Sure and yeah just to add my answer for the last one I also kind of think well life is meaningless but I like the stoic idea where that's something that you live to revolt against but for the second question the </s><s>[INST] revolt against the fundamental meaninglessness [/INST] of life. Like </s><s>[INST] yeah [/INST] it was what does love play? What role does love play </s><s>[INST] in the human condition [/INST] the way I see it, love is a reason you want to share experiences with other people. That's how I see it like the people you really love, you want to share the things you're going through with them um </s><s>[INST] Yeah, [/INST] exactly, that's my simple take on love. My take on it. Is </s><s>[INST] that [/INST] part of what it is to be human is to be somebody who feels things emotionally. And love is one of the most intense feelings you can have. Um obviously there's the opposite of that and there's things like hate, but I think the love you feel for people like your parents and your friends and romantic love in that moment is much more intense than in other situations. Um and I think it's also just very unique to humans and that's what I appreciate </s><s>[INST] about the meaning of life. Maybe that's what the stoics are searching for. Andrea Alex, thank you so much for this and thank you for an amazing conversation. Thank you for creating, keep creating and thank you for putting knowledge and love out there in the world, [/INST] thank you for having us lex and we're both big fans of your podcast, so this was really exciting for us. </s><s>[INST] Thanks for listening to this conversation with Alexandra and Andrea bowties. To support this podcast. We check out our sponsors in the description and now let me leave you with some words from bobby Fischer Chess is life. [/INST] Thank </s><s>[INST] you for listening and hope to see you next time [/INST] </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] So yeah, so the way it comes into being is by you accepting those notions and then you see there uh these three divine concepts and you see them [/INST] realized another divine is a loaded concept in our world because we are outside of this card and be a still scarred from breaking free of it. But the idea is basically, we need to have a civilization that acts as an intentional agent like an insect state and we are not actually a tribal species. We are state building species. And what what enabled state building is basic. The formation of religious states and other forms of rule based administration in which the individual doesn't matter as much as the rule or the higher goal. We got there by the question, what's the optimal form of governance? So I don't think that castle Catholicism is the optimal form of governance because it's obviously on the way out. Right? So it is for the present type of society that we are in a religious um institutions don't seem to be optimal to organize that. So what we discovered right now that we live in in the west is democracy and democracy is the rule of oligarchs that are the people that currently own the means of production, That is administered not by the oligarchs themselves because they there's too much disruption, right? We have so much innovation that we have in every generation means of production, that we invent and corporations dive usually after 30 years or so and something other takes the leading role in our societies. So it's administered by institutions and these institutions themselves are not elected, but they provide continuity and they are led by electable politicians. And this makes it possible that you can adapt to change without having to kill people. Right? So you can tell, for instance of a change and governments if people think that the current government is too corrupt or it's not up to date. You can just elect new people. Or if a journalist finds out something inconvenient about the institution and the institution is uh has no plan B like in Russia, the journalist has to die. This is what when you run society by the deep state. So ideally you have a administration layer that you can change if something bad happens right? So you will have a continuity in the whole thing. And this is the system that we came up in the west and the way it's set up in the U. S. Is largely a result of low level models. Mostly just 2nd 3rd order consequences that people are modeling in the design of these institutions. It's relatively young society that doesn't really take care of the downstream effects of many of the decisions that are being made. And I suspect that ai can help us this in a way. If you can fix the incentives the society of the US as a society of teachers, it's basically cheating. So indistinguishable from innovation and we want to encourage innovation. </s><s>[INST] Can you elaborate on what you mean by cheating? [/INST] It's basically people do things that they know are wrong, it's acceptable to do things that you know are wrong in this society to a certain degree. You can, for instance, uh suggests some non sustainable business models and implement them </s><s>[INST] right, but you're always pushing the boundaries. I mean you're you're. [/INST] Yes this is seen as a good thing, largely. </s><s>[INST] Yes. [/INST] And this is different from other societies. So for instance, social mobility is an aspect of the social mobility is the result of individual innovation that would not be sustainable at scale for everybody else. Normally you should not go up, you should go deep, right? We need bakers and I need you are very good bakers. But in a society that innovates maybe you can replace all the bakers with a really good machine, right? And that's not a bad thing and it's a thing that made the U. S. Was successful, right? But it also means that the U. S. Is not optimizing for sustainability but for innovation. </s><s>[INST] And so it's not obvious as the evolutionary processes enrolling, it's not obvious that that long term would be better. [/INST] It has side effects. So basically if you cheat, you will have a certain layer of toxic sludge that covers everything that is a result of teaching </s><s>[INST] and we have to unroll this evolutionary process to figure out if these side effects are so damaging, that the system is horrible or if the benefits actually outweigh the the negative effects. How do we get to the system of government is best. That was from I'm trying to trace back the last like five minutes. [/INST] I suspect that we can find a way back to ai by thinking about the way in which our brain has to organize itself in some sense, our brain is a society of neurons and our mind is a society of behaviors and they need to be organizing themselves into a structure that implements regulation and government is social regulation. We often see government as the manifestation of power, local interests, but it's actually a platform for negotiating the conditions of human survival and this platform emerges over the current needs and possibilities and the trajectory that we have. So given the present state, there are only so many options on how we can move into the next stage without completely disrupting everything. And we mostly agree that it's a bad idea to disrupt everything because it would endanger our food supply for mobile and the entire infrastructure and fabric of society. So we do try to find natural transitions and they're not that many natural transitions available at any given point. </s><s>[INST] What do you have a natural transition? [/INST] So we try to not to have revolutions if </s>

<s>[INST] is a qualified [/INST] member to be on the Supreme Court. I wish that biden had not done what he did. He could have just appointed a black woman </s><s>[INST] by [/INST] saying that he was limiting his considerations to black women and what are black women as a percentage of </s><s>[INST] all [/INST] potential appointees to the Supreme Court. 3% </s><s>[INST] four [/INST] 1%. I don't know. We could look the number up the by saying that he puts an asterisk on the appointment but it's worse than that because she will live down the asterisk of if a person is inclined to </s><s>[INST] do that, [/INST] she will have the opportunity to show through her performance exactly what </s><s>[INST] kind of jury she is just [/INST] as justice Clarence thomas has shown through his performance that he was qualified and more than </s><s>[INST] qualified to be on the [/INST] United States Supreme Court. </s><s>[INST] What I disliked was the [/INST] pandering, </s><s>[INST] he was [/INST] seeking votes from black </s><s>[INST] people by [/INST] pandering </s><s>[INST] to us [/INST] and he's treating us like Children. Why should I care what color the person is, who's on the United States Supreme </s><s>[INST] Court. What I should care about [/INST] is what kind of opinions are going to write when they're on the United Do </s><s>[INST] I suppose [/INST] that being a black woman means that you're going to write different kinds of opinions than others? Well perhaps perhaps uh that kind of identity politics at the highest level of american legal establishment is something that rubs me very much the wrong way. What I should care about is the nature and the future of the law. I'm actually struck by this because the court is conservative, It has six conservative </s><s>[INST] members on it and [/INST] It has three liberal members on it. Um and uh if I were and I'm not a liberal democrat. The highest concern that I would have about an appointment to the Supreme Court is is this a </s><s>[INST] person who is [/INST] going to be effective in advocating my liberal views within the highest council of american law. Now, the fact that that person </s><s>[INST] is a woman or [/INST] as a black person is way down the list of the things that I would think are important to the kinds of opinions that they're going to write. So I mean, I think uh joe biden this is just a piece of a larger political strategy </s><s>[INST] to cobble [/INST] together a coalition that will be successful at the polls and </s><s>[INST] sustaining democrats. [/INST] Jim </s><s>[INST] Crow two point [/INST] oh, this whole characterization of the conflict in the states about election security and voting rights is </s><s>[INST] another part of that strategy. He [/INST] is pandering to black voters. He is trying to frighten us thinking that if the republicans win our rights will be taken away. Um, and I I I think it is a infantilized ation of african american politics. I think black people are not to be as concerned about the color of the skin, of a person who is serving in government as they are about the content of their </s><s>[INST] character and [/INST] the focus of their, of their political and ideological orientation which for me would be center or even center right, but that's me and </s><s>[INST] should not have a [/INST] significant impact. </s><s>[INST] Nevertheless, he said she can overcome the asterix, [/INST] but to me it was deeply disrespectful that </s><s>[INST] um anyone would give an extra abstract stuff to overcome. He [/INST] didn't have to say it. All, he had to do was do it. If he wanted to put a black woman on the court that he could just go ahead and </s><s>[INST] done it. The reason, he [/INST] said it is because he wanted black people to vote for him by saying it and I'm saying that treats us like we're </s><s>[INST] Children. Uh you know, it's not a political statement, I just thought as a leader that was [/INST] not </s><s>[INST] um those, those kind of disgusting. [/INST] Um let me ask you about </s><s>[INST] thomas. So you mentioned [/INST] him, he's </s><s>[INST] a colleague and somebody who was an influence what [/INST] in the space of </s><s>[INST] ideas. So what [/INST] broadly, </s><s>[INST] what impact has he had on your ideas? [/INST] And um </s><s>[INST] how do you think he shaped the [/INST] landscape of ideas in our </s><s>[INST] culture in general? [/INST] I think Thomas Soul, he's in his 90s now, he's been around for a long time. He's </s><s>[INST] still got it, he's still going at [/INST] it, he's still going at the </s><s>[INST] books continue to come out. I [/INST] think he's a great man. </s><s>[INST] Um I [/INST] think thomas </s><s>[INST] soul, regardless [/INST] of his race, </s><s>[INST] he's black [/INST] is one of the 100, The most significant economists of the 20th century. He has chosen as his subject, a substantial part of his subject, subject to investigate The deep causes and consequences of racial disparity of one kind or another. He's written fundamental books about that. </s><s>[INST] Uh many of them. [/INST] He's a social philosopher, he is a economic historian, he is a </s><s>[INST] combatant [/INST] in the conflict of ideas around how to think about society and this beyond racial differences. Although race has been a big part of what he's written about, he's </s><s>[INST] been critical [/INST] of affirmative action and he didn't just stand back and wag his finger, </s><s>[INST] he got busy looking [/INST] at the consequences of affirmative action in societies all around the world. And he's written books about that. He's been critical of the narrative about civil rights and </s><s>[INST] racial inequality. [/INST] He believes in small </s><s>[INST] government, he doesn't [/INST] think uh that efforts to redistribute income have proved to be the solution to the problem of racial disparity. Tom has not been honored by the committee </s><s>[INST] that hands out [/INST] nobel recognition in economic science and probably won't be because he's </s><s>[INST] controversial. And I [/INST] reckon that that committee would be loath to encourage the blowback that they would be sure to receive if they were to take a controversial and politically uh focus and expressive </s><s>[INST] black [/INST] conservative and and honor in that way. So, I think another reason is that tom as a methodology method, a logical matter </s><s>[INST] is [/INST] not especially quantitative, he pays attention to data, but he doesn't do statistical analysis and he doesn't do modeling. So, from a methodological point of view, he's not a cutting edge uh kind of uh mathematically sophisticated, kind of quantitatively and </s>

<s>[INST] And so don't look at the price of Bitcoin and all that kind of stuff. Just pick a specific time specific day that you just by and you just keep buying that's probably a good investment advice across any kind of assets. [/INST] Like if you don't believe in Bitcoin and just want to, let's say you just want to the s. p. 500, You shouldn't try to time the market of the S&P 500 either, right? You should just every two weeks you should just buy something over a 20-year period. You're gonna end up buying it at all kinds of different prices. But you can get kind of a blended average and the more important thing is the compounding and the time in the market then, did you buy it at, you know, 2% higher or lower than where you bought? It doesn't really matter. </s><s>[INST] And buying off and makes you, I guess resistant, robust to the to the volatility of the market or volatility. The Bitcoin price and so on. That said, uh, you know, Bitcoin price is volatile. And you know, again, the argument, I've heard it's like everything that's going to be a lot more valuable in the future. Like if you look at the history like companies like Apple like Tesla's now, I mean, but let's look at companies that have now stabilized, right? Apple is a good example. It's like volatile in the beginning. And so the argument for Bitcoin is like yeah this is the early stages because it's going to be a lot more valuable right now it's volatile and this is why you have to have these kinds of strategies to write out the volatility. Of course everything that goes to zero is also volatile. Like the early days are volatile. Uh Do you see like this volatility is like a feature or a bug or is this just like a way of life? [/INST] So Amazon is the one that I know the numbers on in terms of the early volatility uh every year since it has gone public it's had a double-digit drawdown in that year. Uh the average is over 30 And one time I drew down over 95%. Sounds a lot like Bitcoin like oh I was just crazy But it's one of the best performing stocks in the last 20 years. If not the best performing stock. And so volatility is not positive or negative, it's positive or negative compared to the position you're in. So if you're long and its volatile to the upside, its positive, if you're long holding something and its volatile to the downside. You see it as a negative. It's all about perspective with that said um Another way that I look at this is every asset priced in Bitcoin is down significantly. So over the last 135 years the dollar priced in Bitcoin has crashed 99%. If you denominated stocks it's down like 80% 85%. If you didn't nominate gold if you denominated bonds, if you just go down the line, real estate etcetera it's all down massively against Bitcoin. Now you could argue that that's because Bitcoin is appreciating in us dollar terms or you could actually argue that the world is re pricing this assets doing price discovery on this asset. And it's essentially comparing it's saying hey Bitcoin versus the stock or Bitcoin versus this ounce of gold or Bitcoin verse you know this dollar which is more valuable and it continues to move up in the rankings in terms of the value that the world ascribes to this. Something is based on lindy effect. Just the longer it persists, the more likely it is to survive. Some of that's based on like the underlying fundamentals of how much computing power, the usage transaction volume, things like that. But some of it also is that as more and more people wake up to the fact that it's a finite supply asset that has a place in the world and demand increases. People just naturally compete ascribe more value to it. And so the volatility I think all comes back to like what do you price your life in for majority people that's dollars so we look at the U. S. Dollar price. You get all this volatility. The beauty of this is that 60%. That doesn't move regardless of price upward or downward and movement. Those people aren't looking at the day to day price. What they basically said is I've acquired X. Amount of Bitcoin and I'm just gonna hold it for years And every time somebody has done that right, if you bought Bitcoin at any point in the last 12 years and you held it till today you are up in us dollar terms. Now If we had this conversation 18 months ago, I couldn't say that. So it's all about not only the acquisition price if you will, It's also one of you looking at it right because there was a point in 2017 you could have said the same thing but in 18 you couldn't and so I tend to think a lot about humans are really really bad at short term uh decision making. Because we're so emotional especially when something has a </s><s>[INST] price tied to it. So it's in terms of our strategies and decision making which should be long term and have like a regular almost think like an algorithm that in that in that kind of way. So I think you've tweeted that you believe that Bitcoin has a chance of reaching one million. I don't know what it is currently. I think it's 5 16 sixties which is incredible. Mm [/INST] hmm I think I remember </s><s>[INST] when it was at least in the double [/INST] digits I think I remember </s><s>[INST] was in the signal digits of a dollar. [/INST] So the fact that is cross 50's </s>

<s>[INST] You mentioned again, a lot of beautiful poetic things, you mentioned grace, you mentioned sin, you mentioned incarnation. Is there a philosophical pragmatic way to start talking about the pillars of Christianity. What are the defining things that make Christianity to you and and broadly speaking to those that follow the religion, [/INST] you know, in a way, what we're doing so far is a necessary, proper duty? Because we're talking about God, um what makes Christianity distinctive of course, is the claim of the incarnation. So we come up out of Judaism, we come up out of this great monotheistic tradition and you know, the bible itself and all the great commentaries within Judaism, I think would agree with this basic theistic stuff that I've been talking about taking most of my manganese, for example. Now what makes Christianity distinct? This supremely weird claim that God becomes one of us, God becomes a creature, but without ceasing to be God and without overwhelming the integrity of the creature, he becomes what we see in the burning bush, that principle which obtains across the board. So the closer God comes to me, the more radiant I become right, but take that now to the end degree would be what we mean by the incarnation, the incarnation of the son of God becoming a creature in such a way as to make humanity radiant and beautiful. That's the pillar of Christianity, It's the incarnation, you know. Um, and what follows from that is the redemption of of all of reality. So not just of human beings, but in becoming creature God divine eyes is the world. You know, the greek fathers always said God became human that humans might become God and that's a good way to sum up, I think the essence of Christianity? </s><s>[INST] Why is this such an important thing. So it's a distinctive thing, but why is it so important philosophically to what it means to be a christian? Like, what impact did that have on our world? On human civilization, On human nature, on our morals of why live what to live for? The meaning of it all? Like, why is incarnation so important? [/INST] I think it's it's massively important because it's it's the Divine ization principle that God wants to divine eyes his creation and sort of in this concentrated point of jesus of Nazareth. But then we talk about the mystical body of jesus. So that goes right back to paul, as we're grafted onto christ, we talk about that as the Church, we become like cells and molecules in an organism, that's the Church, it's not an organization, that's a that's a d formation of ecclesial ology, The Church is this organism that begins with jesus, and then he's drawing all of humanity, but ultimately, all of nature, all of creation to himself. When the Son of man has lifted up, he will draw all things to himself, that idea of the gathering in of a scattered creation. So in that way it's at the heart of it, then there's all kinds of things. If God becomes human, that means there's a dignity to humanity, which goes beyond anything any humanist of any stripe has ever said, write ancient, medieval, modern contemporary Christianity is the greatest humanism imaginable God became one of us in order to demonize us. The goal of my life is not just to be a good person, not just to be, you know, materially successful, not just to be a member of society. The goal of my life is to become a participant in the divine nature. And so there, I don't think there is a humanism greater than that, even conceivably. So that's where I think humanism is profoundly influenced by the incarnation. Uh, just our notion of God is non competitive to us. That's so important because I think it's so many systems from mythology on word, you have these competitive understandings of God. When jesus says to his disciples the night before he dies, I no longer call you servants but friends. It's an extraordinary moment because every God right who's ever been served well that's, that's the best we can hope for is is the servant of God. You know, I've tried to obey you Lord, I'll try to do what you want. But when jesus says, I no longer call you servants or slaves, he would have said in the greek there, you know. Um, but friends, I don't know, I can't imagine anything greater than that becoming God's friend. </s><s>[INST] That's a call to become one with, with God, it's possible to become, become one with God. Now I should mention, you're one of the greatest religious communicators I've ever experienced that. A lot of, a huge number of people are fans of yours. You've done a lot of great conversations. You've done Reddit Amas, which is a very unique, bold brave thing. And on one of them somebody asked, um, what's the most challenging of the seven deadly sins? So first, what are the seven deadly sins? What do they have to do with Christianity? How essential, how crucial they are to the religion? And what's the most challenging in our modern day? [/INST] Yeah. To name him pride, Envy, Anger, Sloth, Avarice, Gluttony & Lust are the seven deadly sins? Capital sins sometimes of couple it there. The head sins from which things tend to flow. The most fundamental is pride. Probably most people today, if you talk about vice or you talk about deadly sin, they would think about lust. But the classical authors, including Dante who does this pictorially there, that's the least of the deadly sense is lost because it's the one that's most sort of dependent upon the body and its and its passions and so on. The most important pride. Pride is the deadliest of deadly sins. And it's very simple to see why pride is the Augustine calls it in calvados and say I'm caved in around myself like a black hole right to get into the scientific, but the black hole to me is a great symbol. You know that it's so heavy that draws everything including light, nothing can escape from it. See that's the center that we're all sinners. We're like black holes that we draw everything into ourselves. So as a sinner and you know, I'll confess I'm a sinner, the temptation is okay, this is the Bishop Baron moment and I'm gonna I'm drawing you now into my you know world and so on. What that does is it kills us off and it makes it it darkens life and it makes it small and and heavy and awful. It's like but see compared to the to the contrasting thing is when you're lost in a moment, you're not concerned about the impression I'm making, you're not concerned about drawing the world into yourself. You're not concerned about this monkey on my back. That's always telling me, you know, look good and sound right, but you're lost in something, you're just you're just talking you know, to a friend and the two of you together discovering something true or or beautiful. You're lost in a movie or you're lost in a book. Those are the best moments in life. Those are the best. These are the least prideful moments, right? That's when I the light comes out. I I become radiant because I'm overcoming this tendency to fall in on myself. Um Dante is so good because the way he pictures um satan in the divine comedy and you know, he's at the center of the earth. So like like a black hole that way he's at the center of gravity is at the heaviest place and there's not fire where he is, but ice, which is much, much better image that your frozen in place and you're stuck. And he's got wings, right? And they used to be angel wings because he's an angel, but now they're like bat wings for Dante and they're flapping. And all they're doing is making the world around him colder because he's ice, he's stuck in his own icy nous. And then he's beating his wings over the ice and making everyone else colder. It's a great image. And then he has this cool too. He has three faces, satan because he's the simulacrum of the trinity. So every center thinks he's God. So I pretend I'm God. So he's got the three faces and from all six eyes he weeps Also from all three miles. He's chewing a sinner, he's got cassius, Brutus and judas in the three miles, you know the three traders. But I thought it's just a great image of all of us sinners is we're stuck, it's heavy, it's cold. Were chewing on our past resentments were weeping in our sadness and we're making the world around us colder. It's beautiful. It's a great, So that's Pride. That's an image of pride because satan that's his great sin, Pride, which is why he needed Michael, right? Mickael who is like God. So that the great challenge to him, which we need all the time is someone to say wait a minute, wait a minute, you're not God. But the minute we say I'm God black hole. I know cave in on myself, I suck everything into myself and I turn into Dante satan. So that's a great image. That's pride, that's the most fundamental, that's the Uber capital sin. It's all the other ones flow from that in a way. </s>

<s>[INST] That's fascinating. You put it that way. It's actually, so I work in a building autonomous vehicles and when you look at what may be compared Tesla to most other automakers. Uh, the psych, the whatever the heartbeat for Tesla is literally days now in terms of, they can, um, over the air deploy software updates to all their vehicles, which is markedly different than every other automaker, which takes years to update a piece of software. And so, and that's reflected in everything. That's, um, the final product that's reflected in really how slowly they adapt to the times [/INST] and to be clear. I'm not saying being a hummingbird is the goal either. It's like, you want a heartbeat that's like so fast. It's like, you're, you're, you know, you're just freaking out. But like it is a measure of health. You should have a healthy heartbeat. It's up to for people listening to decide what that means. But it has to be healthy. It has to be reasonable because otherwise you just get frustrated because like, that's how you build software, you make mistakes, you roll it out, you live with it. You see what it feels like and say, oh God, that was a terrible idea. Oh my gosh, this could be even better if we did. Why? Right? You turn the crank and then the more you do that, the faster you get ahead of your competitor is ultimately because you're its rate of change, right? Delta v. Right? How fast are you moving? Well within a year, you're gonna be miles away by the time they catch up with you, right? Like that's the way it works. And plus users, like I as a software development, I love software. That's constantly changing because I don't understand people get super piste off when like, oh, they changed the software on me. How dare they? I'm like, yes, changed the software. Change it all the time. Man, That's, that's what makes this stuff great is that it can be changed so rapidly and become something that that is greater than it is now. Now granted, there's some changes that suck. I admit I've seen it many times. But in general, it's like, that's what makes software cool. Right. Is that it is so malleable, like fighting. That is like weird to me because it's like, well you're fighting the essence of the thing that you're building. Like that doesn't make sense. You want to really embrace that. Not, not to be a hummingbird, but like embrace it to a healthy cycle of your heartbeat. Right? </s><s>[INST] So you talk about that people really don't change. [/INST] It's </s><s>[INST] true. That's why I probably, a lot of the stuff you write about in your blog probably will remain true. [/INST] There's a flip side of the coin, People don't change. So investing in understanding people is like learning UNIX in 1970 because, And nothing has changed, right? Like all those things you've learned about, people will still be valid 30, 40 years from now. Whereas if you learn the latest Javascript framework, that's going to be good for like two years. Right. </s><s>[INST] Exactly. So, but if you look at the future of programming? So there's a people component, but there's also the technology itself. Do you what do you see as the future of programming, will it change significantly or as as far as you can tell, uh people are ultimately programming and so it will not, it's not something that you foresee changing in any fundamental way. [/INST] Well, you gotta go look back on sort of the basics of programming. And one thing that always shocked me is like source control. Like I didn't learn anything about source control on the ground. I graduated college in 1992, but I remember hearing from people like as late as the 1998, like even maybe today they're not learning source control. And to me, it's like, well how can you not learn source control? That is so fundamental to working with other programmers working away. You don't lose your work, like just just basics off the bed, literal Bedrock. Software development is source control. Now you compare today like get up right, like Microsoft project Hope, which I think was incredibly smart acquisition, move on their part. Now they have anybody who wants like reasonable source controls and go see them and get hub. It's all set up for you, right? There's tons of walk through tons of tutorials. So from the concept of like has programming advanced from ST 1999 it's like, well hell we have git hub. I mean, my God, Yes. Right? Like it's it's massively advanced over over what it was now as to whether programming is significantly different. I'm gonna say no, but I think the baseline of like what we view is like fundamentals will continue to go up and actually get better, like source control. That's one of the fundamentals that has gotten, I mean Hundreds of orders of magnitude better than it was 10, 20 years ago. So those are the fundamentals. </s><s>[INST] Let me introduce to things that maybe you can comment on. So one is mobile phones. So that could fundamentally transform what um what programming is or maybe not. Maybe you can comment on that. And the other one is artificial intelligence which promises to in some ways to do some of the programming for you is one way to think about it. So it's [/INST] really what a programmer is, </s><s>[INST] is uh using the intelligence that's inside your skull to to do something useful. Uh The hope with artificial intelligence is that it does some of the useful parts for you where you don't have to think about it. So, do you see Smartphones, the fact that everybody has one and they are getting more and more powerful as potentially changing programming. And do you see a i is potentially changing [/INST] Problem. Okay, so that's good. So smartphones have definitely changed, I mean, since, you know, I guess 2010 is when they really started getting super popular. I mean in the last eight years, the world has literally changed, right? Like everybody carries a computer around and that's normal. I mean that is such a huge change in society. I think we're still dealing with a lot of the positive negative ramifications of that, right? Like everybody's connected all the time. Everybody's on the computer all the time. That was my dream world as a geek, right? But it's like be careful what you ask for, right? Like wow now everybody has a computer. It's not quite the utopia that we thought it would be right, computers can be used for a lot of stuff that's not necessarily great. Um So to me that's the central focus of the smartphone is just that it puts a computer in front of everyone granted a small touch screen smallish touchscreen computer. But as for programming, like I don't know, I don't think that I've kind of over time come to subscribe to the UNIX view of the world when it comes to programming. It's like you want to teach these basic command line things and that is just what program is going to be for I think a long long time. I don't think there's any magical like visual programming that's going to happen. Um I just I don't know I've over time have become a believer in that UNIX philosophy of just you know they kind of had to write with UNIX that's going to be the way it is for a long long time and we'll continue to like I said raise the baseline the tools get better, it'll get simpler, but it's still fundamentally command line tools, you know, fancy I. D. S. That's kind of it for the foreseeable future. I'm not seeing any visual programming stuff on the horizon because you can't think like what do you do on a smartphone that will be directly analogous to programming? Like, I'm trying to think right, like, and there's really not much. </s>

<s>[INST] I promise you, you'll improve. Yeah, and I guess when you have the plan, have a plan that carries across many training sessions. So, I just remember, I know this is perhaps dumb, but I saw in my own game early on, a lot of growth by self-identifying a problem and coming up by myself with a solution by watching in that case Marcel Garcia. I just thought my butterfly guard was very weak. And so I thought, okay, what's the solution here? I thought maybe this X-guard thing, double X-guard. Okay, so I watched a bunch of video, let me try to work on this. And then all I did, just this is self, but when I could get time by myself, meaning like not instructor guided classes, but in training, I would just, everything I would put myself into butterfly and X-guard. That's good. Just let go, like don't progress, sweep and figure out a way to get swept, to get right back to it, back to it and everything. It was annoying probably to train with me because that's all I did and that's all I thought about. Right, but you learned quickly. Yeah, I learned it's the most progress I've ever made. Now, you could say that X-guard wasn't the right solution for me, that maybe that wasn't the weakest point for me to work on. If I were to look back now, it's still to this day, sadly, the obvious weakest point for me is escapes from much worse positions. That should be worked on. That should have been worked on from the very beginning. That's still, today, if I were to say, what's the weakest thing that I should work on, absolutely, is even with one day a week is escapes. But yeah, a lot of that has to do with just caring, like focusing on the one thing over and over and over and over across training sessions. Now, I'd also, I would write down on a sheet of paper the number of times I would get an X-guard sweep and I would set a rule that I have to get whatever it was, like 500 sweeps a week. So I have to, and then like, the closer you get to the end of the week, [/INST] the more you like just pick up a small white pick up. 500 in a week? Yeah, something like that. </s><s>[INST] Your training pot just must suck, bro. No, no, you start with good ones and then you get more and more desperate. You start like finding the kid, right, that you can just sweep over and over. But like that number, for me, the number is, for some reason, like I set a goal to pull off a technique. It enforced, like we're staying with this for a while. This is a journey we're doing. And then for some reason, for me, that helped me focus the study to understand the deep complexities of this thing, that at least for me, other people, like nobody at the gym was doing X-Guard or anything of that. So you have to kind of figure everything out yourself. I'm sure there's better ways to do that, but at least that focus helps from a hobbyist perspective. What's the day, what's the perfect day in the life of John Donner? If we're talking about a basic non-ADCC, now you're, I'm really grateful that you sit down with me on a Sunday, late at night, but it all starts again for you tomorrow. So three training sessions a day. What time do you wake up? Do you do like a mantra in the morning? Do you listen to like some Zen music? What do you eat in the morning? [/INST] What's the perfect day look like? When you say a small animal, to the gods. I usually, when you say a perfect day, what I think you really mean is an average day. Perfectly productive average day. Yeah. So let's take Monday morning for you watching this video. We're filming this late on a Sunday night. So after this, I'll drive home. We just had ADCC. It was two weeks ago. It was one of the longest training camps. It was the longest training camp I've ever run because of the fact we had to go through </s><s>[INST] three different matches for Gordon Ryan leading up to it. When you say- Sacrifice a small animal? Yeah. [/INST] Productive- So immediately after ADCC, I cut the training down for the competitive athletes to one session per day for the first week after ADCC to give their bodies a bit of a break. I still have to teach two classes in addition to that, two recreational classes. So my teaching schedule went down to three classes per day. After one week of relative break, we go back to two competition classes per day plus two recreational classes, plus an MMA class four. Gary Tonin and his friends. The first class requires me to get up around 6 a.m. to drive. I'm still a student driver, so I'm not very good at driving. So I have to spend a little extra time to get to the destination on time. </s><s>[INST] Just for the record, John pulled in a red Lamborghini with a, no. [/INST] You're the worst liar I've ever met. My day typically starts pretty early. I don't eat in the morning. I just get up and go to work. And I teach through the day. My last class finishes usually around 8 p.m. During that time, I coached jiu-jitsu. I try to find time for one Instagram post per day, which usually describes some basic theme of jiu-jitsu in most cases, unless we've just had a competition, in which case I'll talk about upcoming competitions or what happens after a competition. But most of them just express a simple jiu-jitsu theme. I try to do a short workout for myself. And then I go home. At the end of the day, I always start by asking myself, what do my students need from me tomorrow? Based on what I've seen today, what do the recreational students need and what do the competitive students need? This is always done in the light of what are the upcoming competitions. </s>

<s>[INST] So you don't think of quantum mechanics as useful uh for understanding the nature of [/INST] reality. </s><s>[INST] So in your thinking the world might as well be deterministic. [/INST] The world is a deterministic. And as far as the new no one firing is concerned. It's Communistic to first approximation. </s><s>[INST] What about free will? [/INST] Free will is also a nice exercise. Free will is an illusion that we ai people are going to solve. </s><s>[INST] So what do you think once we saw that that solution will look like once we put it in [/INST] the page look like, first of all, it will look like a machine, a machine that act as though it had free will. It communicates with other machines as though they have free will. And you wouldn't be able to tell the difference between a machine that does in machine that doesn't have free will. </s><s>[INST] So the illusion it propagates the illusion of free will amongst the other machines [/INST] and faking it is having it. Okay, that's what two in tests are about. Faking intelligence is intelligent because it's not easy to fake. It's very hard to think and you can only affect if you have it. </s><s>[INST] That's such a beautiful statement. Yeah. Yeah. You could yeah. Yeah. You can take it if you don't have it. Yeah. So uh let's begin at the beginning with probability. Both philosophically mathematically. What does it mean to say? The probability of something happening is 50%. What is probability? [/INST] It's a degree of uncertainty that an agent has. And by the world </s><s>[INST] you're still expressing some knowledge in that statement, of [/INST] course Is a problem. It is 90%. It's absolutely a different kind of knowledge. And if it is 10 </s><s>[INST] but it's still not solid knowledge, [/INST] it's solid knowledge by If you tell me that 90 shoo ins smoking will Um give you lung cancer in five years versus 10%. It's a piece of useful knowledge. </s><s>[INST] So the statistical view of the universe. Why is it useful? So we're swimming in complete uncertainty. [/INST] Most of everything that allows you to predict things with a certain probability and computing those probabilities are very useful. That's the whole idea of prediction. And you need prediction to be able to survive. If you cannot predict the future then you're just crossing the street will be extremely fearful. </s><s>[INST] And so you've done a lot of work in causation. And so let's let's think about correlation. [/INST] I started with probability. </s><s>[INST] You started with probability, you've invented the Beijing networks and so you know, we'll dance back and forth between these levels of uncertainty. But what is correlation? What is it? So probability of something happening is something. But then there's a bunch of things happening and uh sometimes they happen together sometimes not their independent or not. So how do you think about correlation of things? [/INST] Coalition of kids? When two things vary together over a very long time is one way of measuring it or when you have a bunch of variables that they were very aggressively. Um then we call, we have a coalition here and usually when we think about coalition, we really think cause a things cannot be called unless there is a reason for them to vary together. Why should they vary together? If they don't see each other, Why should they vary together? </s><s>[INST] So underlying it somewhere is causation. [/INST] Yes. Hidden in our intuition, he's a notion of causation because we cannot grasp any other logic except authorization. </s><s>[INST] And how does conditional probability differ from causation? So what is conditional probability, [/INST] conditional probability. How things vary when one of them stays the same? Now, staying the same means that I have chosen to look only at those incidents where the guy has the same value as previously. It's my choice as an experimenter. So things that are not correlated before could become correlated like for instance if I have two coins which are uncorrelated, Okay. And I choose only those flipping experiments in which a bell rings and bell rings when at least one of them is a tale. Okay. Then suddenly I see correlation between the two coins because I only looked at the cases where the bell rang. You see it's my design with my ignorance essentially with my audacity to ignore certain incidents, I suddenly create a coalition where it doesn't exist physically. </s><s>[INST] Right? So that's you just outlined one of the flaws of observing the world and trying to infer something fundamental about the world from looking at the correlation. [/INST] I don't look at it. The law of the world works like that, which but the flows comes if we try to impose um causal logic on coalition. It doesn't work too well, </s><s>[INST] I mean, but that's exactly what we do. That's what that has been. The majority of science is your [/INST] majority of naive science statisticians know it decisions know it. If you condition on a third variable then you can destroy or create coalitions among two other variables. They know it. It's in the data. All right. There's nothing surprising. That's why they all dismissed the Simpson paradox. Ah We know it, we don't know anything about it. </s><s>[INST] Well there's there's disciplines like psychology where all the variables are hard to get to account for. And so oftentimes there's a leap between correlation to causation. You're you're [/INST] a leap. Who is trying to get position from coalition? </s><s>[INST] Not you're not proving causation but you're sort of uh discussing it implying sort of hypothesizing with all the ability [/INST] which disciplinary have in mind. I'll tell you if they are absolute. Is there an outdated or they're about to get outdated? Oh tell me which one? </s><s>[INST] Uh psychology? You [/INST] know what? S. E. M. No </s>

<s>[INST] regret. So I guess I'm uh, this is for you, the listener. I'm coming out of the closet here a little bit, the fact that I enjoy the madness I live in. So please do not criticize me, embrace me. I I understand the sacrifices I'm making. I enjoy sleeping on the floor when I'm passionate programming all night and just pass out on on the carpet. I I love this life. Okay, so it's it's uh, but it's definitely something I think about that there's a balance of strike uh where [/INST] I just want you to have as much of it though </s><s>[INST] of life, See quality of life is important. [/INST] I should have said I want you to have as much high quality life. And if high quality of life means I spent five decades on this planet. But yet in that time I am thrilled every day. I'm turned on every day by what I do. And I reveled in this thing called my life's work. I think that that is a 50 Year journey of absolute delight and fulfillment that you should take. </s><s>[INST] I think about my death all the time. I meditate on death. I'm okay to die today. So to me, longevity is not, it's not, it's not a significant goal. I'm so happy to be alive. I don't even think it would suck to die. uh today I'm I'm as afraid of it today as I will be in 50 years. I don't want to die as much today as I will in 50 years. There's uh there's of course all these experiences I would like to have, but I'm everything is already amazing. It's like that leg of movie. So I don't know. So I, to me, I just want to keep doing this and there's, there's of course things that could affect, you know, like you mentioned dementia and these deterioration of the mind or the body that can significantly affect the quality of life. And so you want to uh [/INST] you're aware of that and you know, that's the price you pay for the entry of into this magical, you know, kingdom that you are experiencing, which is a lovely thing. You know, I feel privileged to to I can't believe the life that I live. It's incredible. And just like you, I don't I do I think about mortality a great deal. I think a lot about death, but I don't worry about death. I probably with the exception of the potential pain that comes before it that some people, many people can suffer that may be concerns me. But I actually think about mortality as a tool as I use it as a lens through which I can then retrospect and by placing myself at the point of future mortality, I can then use it as a retrospective lens to focus and ask the following question, is there anything I feel I would regret and therefore change in the life that I currently have now. I that's the way I meditate and use mortality as a question is to try and course correct and focus my life. I worry not about dying, but I like to think about death as a way to prioritize my life if that makes I don't know if that makes sense. </s><s>[INST] It's total sense to decide how do you want to live today? So that in the future you do not regret the way you live today [/INST] and place yourself in the future at your point of mortality is one way to I think as an exercise to retrospectively look back and not lose out on informed choices that you could otherwise lose lose out on if you weren't thinking about mortality. </s><s>[INST] Yeah, it clarifies your thinking uh is there, So I mentioned I sleep on the floor, take naps and power naps and it's just kind of madness. Is there uh weirdness is to your own sleep schedule. As a scientist that does incredible work, has a lot of things going on, has has to lead, research has to write, research has to be a science communicator also have a social life, all those kinds of things. Is there certain patterns to your own sleep that you regret or you um are you participate in uh that you find you enjoy? Um like is is there some like personal stuff quirks or things you're proud of that you do in terms of your sleep schedule? [/INST] The funny thing about being a sleep researcher is that it doesn't make you immune to the ravages of a difficult night of sleep. And I have battled my own periods of insomnia in my life too. Mhm. And I think I've been fortunate in ways because I know how sleep works and I know how to combat insomnia. I know how to get it under control because insomnia in many ways is a condition where all of a sudden your sleep controls you rather than you control your sleep. Yeah, that's a beautiful way to put it. Yeah. And I know when I'm starting to lose control and it's starting to take control, I understand how to regain, but I've it doesn't happen our overnight, it takes a long time. </s><s>[INST] So you've struggled with insomnia. Yeah. My life [/INST] I have not, not all of my life, I would say I probably had three or four really severe bouts and all of them usually triggered by you know, emotional circumstances by stress, </s><s>[INST] um stress that's connected to actual events in life or stress. That's unexplainable, [/INST] Little externally triggered. Yeah, it's sort of what we would call reactive stress. Um and so that that that sort of point number one about the idiosyncrasies. The point number two is that when you are having a difficult night of sleep as a sleep researcher, you basically have become the woody allen neurotic of the sleep world because at that moment, you know, I'm trying to fall asleep and I'm not and I'm starting to think, okay, my dorsal lateral prefrontal cortex is not shutting down. My nor adrenaline is not ramping down. My sympathetic nervous system is not giving away to my parents at that point, you are dead in the water for the next two hours and nothing is bringing you back. So there is some irony in that too. I would say for myself though, I if there's something I'm not proud of, it has been at times railing against my Krone type. So your Krone type is essentially are you a morning type, evening type or somewhere in between. And there were times because society is desperately biased towards the morning types. You know, this notion of the early bird catches the worm maybe that's true. But I'll also tell you that the second mouse gets the cheese. Yeah. So I think the issue is a good line around, you know, is firstly people don't really understand Krone type because I'll have some people when I'm sort of out in the public, they'll say look, I struggle with terrible insomnia. And I ask them, is it problems falling asleep or staying asleep? And they'll say falling asleep. And then I'll say, look, if you are on a desert island with nothing to wake up for no responsibilities, what time would you normally go to bed and what time would you wake up? And they would say I probably like to go to bed about midnight and wake up maybe eight in the morning. And then I'd say, so what time do you now go to bed? And they would say, well I've got to be up for work early. So I get into bed at 10 and say, well you don't have insomnia. You have a mismatch between your biological krone type and your current sleep schedule and when you align those two and I was fighting that for some time to I'm probably mostly right in the middle, I am desperately vanilla. Unfortunately many aspects of life, but this included, I'm neither a strong morning type nor a strong evening type, so ideally I'd probably like to go to bed around, you know 11, 10 30 11, probably somewhere between 10 30 11 and wake up, you know, I naturally wake up usually most days before my alarm at um 704 um And it's 704 because why not be idiosyncratic in terms of sitting and I love it. And so </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] publicly, but it's a hard problem. And uh, you know, for me, I've gotten a chance to interact with people that take on hard problems and solve them and they're rare what Tesla has done with their data engine. So I thought tom was driving cannot be solved without collecting a huge amount of data and organizing while not just collecting but organizing it. And exactly what Tesla is doing now is what I thought it would be like, I couldn't see car companies doing that, including Tesla and now that they're doing that, it's like, okay, so it's possible to take on this huge effort seriously to me tell the operation is another huge effort like that. It's like taking seriously what happens when it fails. What's the in the case of Waymo for for the consumer like ride sharing, what's the customer experience? Like there's a bunch of videos online now where people are like the car fails and it pulls off to the side and you call that customer service and you're basically sitting there for a long time and there's confusion and then there's a rescue that comes and they started, I mean just the whole experience is a mess that has a ripple effect to how you trust in the in the entirety experience. But like actually taking on the problem of that failure case and revolutionizing that experience both for trucking and for ridesharing. That's an amazing opportunity there because that feels like it would change everything if you can reliably know when failures happen, which they will, you have a clear plan that doesn't significantly affect the efficiency of the whole process. That that could be the game changer. And if tell the operations part of that, it could be just like you're saying it could be tell the operation or it could be like a fleet of rescuers that can come in which is a similar idea but tell the operation obviously that allows you to to just have a network of monitors, people monitoring this giant fleet of trucks and taking over when needed. It's a beautiful vision of the future where there's millions of robots and only thousands of humans monitoring those millions of robots that seems like that seems like a perfect dance of allowing humans to do what they do best and allowing robots to do what they do best. [/INST] Yeah. So I mean, I think there are, and we just applied for an NSF, we didn't get anybody's watching, but with some folks from Wisconsin who do telly operation, right? And you know, some of this is used for like rovers and you know, I mean really, you know, high stakes difficult problems. But one of the things we wanted to study were these minds in these Rio tinto mines in Australia where they remotely pilot the trucks and there's some autonomy I guess and then, but it's overseen by um, a remote operator and they, you know, it's a, it's a it's a near Perth it's quite remote and um, they retrained the truck drivers to be the remote operators, right? Um, there's autonomy and in the port of Rotterdam and places like that where their jobs there and so there, I think, you know, maybe we'll get to this later. But you know, there's a real policy question about sort of who's going to lose and what we do about it. And, you know, whether or not there are opportunities there that, you know, maybe we need to put our thumb on the scale a little bit too to make sure that, you know, there there's some give back to the community that's that's taking the hit, you know? Um So for instance if there were tally operation centers, you know, maybe they go in these communities that we disproportionately source truck drivers from today now. I mean what does that mean? It may not be the cheapest place to do it if they don't have great connectivity and it may not be where the upper level managers want to be and you know, places like that, you know the issues like that. Right? So um I do think it's an interesting question, you know, both from sort of a practical uh scenario situation of how it's gonna work, but also from a policy perspective, </s><s>[INST] so there's platoons, there's tell the operation and this is taking care of some of the highway driving that we're talking about. Is there other ideas? Like um is there are other ideas scenarios that you have for autonomous strokes? [/INST] Yeah, so I mean the most obvious one actually is just you know, uh facility to facility right? The sort of, you know um It can't go everywhere. But a lot of logistics facilities are very close to interstates and they're and they're on big commercial roads without you know, bikes and parked cars and all that stuff. And some of the jobs that I think are really first on the chopping block are these L. T. L. That less than truckload what's called line haul, right? So these are the drivers who go from terminal to terminal with those full trailers. Um And those facilities are often located strategically to avoid congestion right? Um And to be in big you know industrial facilities. So you could imagine that being you know the first place you see a Waymo self driving, you know truck roll out might be you know um sort of direct facility to facility for ups or Fedex or less than </s><s>[INST] truck. Okay and the idea there is fully driverless so potentially not even a driver in the truck it's just going from facility to facility empty zero [/INST] occupancy. Yeah and those because that labor is expensive you know they don't keep those drivers out overnight. Those drivers do do a run back and forth typically or in a team go back and forth in in one day. </s>

<s>[INST] Yeah, but so I know it's painful to have explicit decisions but there is underlying [/INST] explicit decisions which is some of the most beautiful fundamental philosophy </s><s>[INST] that we have before us which is personal growth. If I want to watch videos from which I can learn, what does that mean? So if I have a checkbox that wants to emphasize and learning there's still an algorithm with explicit decisions in it that would promote learning. What does that mean for me, like for example, I've watched a documentary on Flat Earth Theory. I guess it was very like I learned a lot. I'm really glad I watched it. It was a friend recommended to me not because I don't have such an allergic reaction to crazy people as my fellow colleagues do. But it was very, it was very eye opening and for others it might not be from others that they might just get turned off from. That same with republican democrat and what it's a non trivial problem. And first of all, if it's done well I don't think it's something that wouldn't happen that uh that youtube wouldn't be promoting or twitter wouldn't be, it's just a really difficult problem how to reduce how to give people control. [/INST] Well it's mostly an interface design problem the way I see it you want to create technology that's like a mentor or coach or an assistant so that it's not your boss, right, you are in control of it, you are telling it what to do for you and if you feel like it's manipulating you, it's not actually, it's not actually doing what you want. You should be able to switch to a different algorithm, you know, </s><s>[INST] so that fine tune control and you kind of learn, you're trusting the human collaboration and that's how I see autonomous vehicles to is giving as much information as possible and you learn that dance yourself. Yeah, adobe don't refuse adobe [/INST] products for like </s><s>[INST] yeah, they're trying to see if they can inject youtube into their interface, but basically allow you to show you all these videos that because everybody is confused about what to do with features. So basically teach people by linking to in that way it's an assistant that shows uses videos as a basic element of information. Okay, so what practically should people do to try to um to try to fight against abuses of these algorithms or algorithms that manipulate us? [/INST] Honestly, it's a very vertical problem because the starfish, there is very little public awareness. I was his issues very few people would think there's anything wrong with their news feed algorithm even though there is actually something wrong already, which is that it's trying to maximize engagement most of the time, which has a very negative side effects. Right? Um, so ideally so the very first thing is to uh stop trying to purely maximize engagement. Try to propagate contents based on popularity, right? Instead take into account the goals and the profiles of each user. So you will you will be one example is for instance when I look at topic recommendations on twitter's like they have this news tab with switch recommendations, it's always the worst garbage because it's it's content that appeals to the the smallest commanding minister to all twitter users because they're trying to optimize a purely trying to obtain its popularity. The purely trying to optimize engagement, but that's not what I want. So they should put me in control of some setting. Uh so that I define was the objective function. Um the twitter is going to be following to show me this content. So and honestly, so this is all about interface design and we are not, it's not realistic to give you this council of a bunch of knobs that define algorithm instead we should purely put them in charge of defining the objective function. Thanks, let the user tell us what they want to achieve, how they want to sell those um to impact their lives. So do you think </s><s>[INST] it is that or do they provide individual article by article reward structure where you give a signal? I'm glad I saw this and I'm glad I didn't [/INST] so like a Spotify type a feedback mechanism. It works to some extent. I'm kind of skeptical about it because the only way the algorithm, the algorithm will attempt to relate um your choices with the choices of everyone else, which might, you know, if you have an average profile that works fine. I'm sure Spotify accommodations work fine. If you just like mainstream stuff, if you don't it can be a it's not often one or two elections will </s><s>[INST] be uh in an efficient search for the for the part of the Spotify world that represents [/INST] you. So it's it's a tough problem. But I do notice that even even a feedback system like what Spotify has does not give me control over what the algorithm is trying to optimize her. </s><s>[INST] Well, public awareness, which is what we're doing now, is a good place to start. Do you have concerns about long term existential threats of artificial intelligence? [/INST] Well, as as I was saying, our world is increasingly made of information. Ai algorithms are increasingly going to be our interface to this world of information and somebody will be in control of the algorithms and that puts us in any kind of a bad situation. Right? Uh It has risks, it has risks coming from potentially large companies wanting to optimize their their own goals? Maybe profit? Maybe something else also from governments who might want to use these uh these algorithms as a means of control of the entire population. Do you think there's </s><s>[INST] an existential threat that could arise from [/INST] that? So kind of existential threats? So maybe you're referring to the singularity narrative where robots to stake over. </s>

<s>[INST] So they turn away. And where does the contempt come in? [/INST] All right, all right. So contempt is criticism on steroids. This is what John Gottman calls sulfuric acid for love. Nothing will erode a relationship quicker than contempt. Contempt is when you are looking at your partner from a superior position. So you are eye rolling, you are name calling, there's a mockery, mocking even physical mockery, imitating them, imitating their voice. Contempt is meant to just take the legs out from your partner, make them feel pathetic, ridiculous. And it can be abusive, but most people have engaged in contempt at some point in their relationship, lower level would be sort of the eye rolling, </s><s>[INST] but that is the biggest predictor of a split. If you allow yourself to think, yeah, that mockery or contempt just a little bit, it's like this weird slippery slope. Sure is. And the opposite is true, where I just look at a person and think, wow, isn't that the most wonderful creature I've ever seen in my life? Just think that. And you notice the little details about who they are. That's why I just observe them the way you observe a weird peacock at a zoo or something like that. [/INST] A little detail. </s><s>[INST] Intention is powerful, isn't it? Yeah, and it changes. You start to notice beautiful things and then let the things that annoy you. Yes. [/INST] You're exactly right. You're touching on some really important things. So in relationships, we actually know that wearing rose-colored glasses is important, it's healthy, we need it. And it's a choice you're making, right? So there is a saying that getting married is just choosing one person's faults over another. And the reality is that we may become infatuated with somebody else as human beings. Love is an emotion, attraction is an emotion. And as you go through life, even if you're in a committed relationship, you might see beauty in another. And that person who is novel might seem attractive to you. But if you can remember that they too have a set of problems that you would be marrying, it really helps you to see the beauty in your partner again and recognize all of their incredible strengths and all the ways we meld with a person and become our own family. Almost become, I mean, our lives intertwine </s><s>[INST] and we grow those oak trees, some really important. So by the way, it's a line I read somewhere that when you're wearing rose-colored glasses, all the red flags looks just like flags. I think it's a good line. So you think that humans are fundamentally, all of us are fundamentally flawed or have flaws, they're unique flaws. And they're basically relationships, [/INST] it's just a way to figure out how the two can fit together. Right, and we're different. So no matter what, we're going to have differences. We are raised differently than our partner. We have different stories, different experiences that shaped our value systems, especially when it comes to the big ones like parenting, love, money, these principles that are based in our history. We're gonna have differences. So is this a set of differences you can accept from somebody and work with? Do the benefits and do their strengths, do they make it worth it? </s><s>[INST] Or are they deal breaker differences? Tricky question, but in the couples you've worked with, is there like the feminine and the masculine, is there different dynamics that come into play, like dominant, submissive? Is it like a dance where it just changes from minute to minute? Is there dynamics that you observe that both limit and enable successful relationships? [/INST] Yes, so there are, if we're talking about masculine, feminine, then how also are we could get into, are we talking about actual gender, identified gender, or are we just talking about these traits? Because like I said, I stonewall, which is typically in couples, something that is more associated with straight men. But that's my style of coping when I get overwhelmed. That is not tied to any sort of success or non-success of a relationship. But what we do know is that gay couples, so lesbians and gay men, tend to be gentler with one another when they are having conflict discussions. I, so that's actually been identified in the research and it's something I've witnessed and it's just fascinating. So with my straight couples, I'll be going through one of these, if we're processing the conflict that occurred, I'll be going through the sheet and it's very, very structured because you don't want couples doing more damage when they're there with you. You want them practicing skills that protect them from criticism, that protect them from contempt. And when I'm working with a straight couple, I am like a referee or sometimes I'll relate it to being like a ski coach and keeping people on a funny hill and you tell them, you let them make like two turns and then you stop them and you meet up again because you don't want them to veer off. With straight couples, you are doing very short turns before you need to kind of intervene and re-scaffold. I had a lesbian couple recently and they were so lovely with each other. They skipped like seven steps to the advanced final portion where they were already coming up with solutions and suggesting things that they might be able to do differently next time to make it better for their partner. They were asking each other questions about how their partner felt with no agenda, no attempt to sort of be like, well, do you think you're feeling that way because, which straight couples do all the time, you just see this humility and openness. </s><s>[INST] It's lovely. Yeah, it's lovely. But I wonder if maybe watching too many Hollywood films if some of the drama, some of the tension [/INST] is required for a passionate lifelong romance. No, it's not. And that's great news. So we actually know that the closer you feel to your partner. You've talked a lot about beauty and you can ignite that beauty, that interest, right? So when you're falling in love, it's usually that a person is sort of a mystery to you and you're uncovering these layers that you find really appealing. There are continual layers that you can uncover with your partner over time. I don't think we realize that. I think we get complacent and we think we've had every conversation imaginable. What else are they gonna do to surprise me? But we don't know the questions to be asking. One of my favorite questions, I like turning these conversations kind of into a quiz because I get bored easily. So rather than just asking an open-ended question, there's a way you can do this with your partner where it's sort of like the dating game. Like, what is my as of yet fondest but unrealized life dream? And see if your partner knows. You might not even know. They might know you better than you know yourself. That in and of itself is a beautiful reminder of the relationship and how special it is. But then also when they say it or when you realize or have to think critically, like what is my husband's as of yet unrealized but fondest life dream? </s>

<s>[INST] products. So you're saying not fundamentally like the idea but the execution of the actual craft factor for the [/INST] construction, the actual product is amazing then um there's customers and that every business has ultimately a customer and that customer if they are in fact delighted by that product. That's the magic because you need a team to build the product and then you need customers to use the product and really those three vectors are undeniable now you can have great teams that build a bad product doesn't happen too often um where you have customers who don't like the product. But generally speaking, a great team will build a great product or a good product and iterate and then eventually delight customers. And so most people say the team is the most important. But um, there's a lot of smart people out there and let's assume that you can have, you can raise money for your idea or you have money or you can just convince people to do it for free. If you make a great product and it connects with users, that's the magic. You look at clubhouse. It's actually a really well designed product. Uh, and that product is connecting with customers. And if you were to talk to the customers or look at the product, you would see a well constructed product and a delighted customer. And you can tell the delighted customer by just the amount of time they use it. That's called engagement. It's a fancy word for how much they use it and Snapchat when that was going around and they were trying to raise money. They had a fraction of the number of users, but the top, maybe third. We're opening the app every hour. Yeah. And that nobody had ever seen that before. People were using facebook, you know, a couple of times a day. The top users, but nobody had ever seen people using it every day for 100 days in a row, every hour. And I was like, what's going on here? It's like, oh, the ephemeral messaging and then the streaks they had created, these streaks between people where, you know every day and then people would be like on vacation, like I just have to open my streak and keep my streak with lex that we chatted every day going. And so they had this like addictive nature to it and that's why clubhouse was able to garner so much investment is the number of hours people were using it every month. I was just unbelievably off the charts. </s><s>[INST] Some of that is execution, but some of it's the weird magic of the [/INST] product market </s><s>[INST] fit. Yeah. So there's something, I mean, clubhouse, there's uh, it's still a mystery to me because I also use discord voice. There's an intimacy to voice [/INST] that you have people. Yeah, </s><s>[INST] it's well, but like the video gets in the way actually in a weird way there's a privacy when you just use voice. [/INST] People are not taking showers now lex. I </s><s>[INST] mean, this is, we're in a pandemic [/INST] and people just roll out of bed in </s><s>[INST] the hair. Nobody's getting, [/INST] nobody cares good, nobody's getting haircuts. People are wearing gym clothes. I mean zoom is just </s><s>[INST] horrific to be [/INST] on Zoom for five hours a day. It is </s><s>[INST] exhausting. Well, it doesn't make me wonder what, what, once we emerge from the pandemic or their product market fit? How that evolves with clubhouse and all those kinds of things? [/INST] Yeah, clubhouse is a beneficiary of the pandemic for sure. When do you think the panda, when do you think Deaths will be under, let's say 200 a day and we'll have 200 million people on the other side of this because that's kind of what it takes, right? You gotta get 250, million people on the other side in America. </s><s>[INST] I haven't, you know, I personally stopped deeply thinking about this because I've been frustrated for so long that you checked out. I almost checked out because it uh, psychologically allows me to carry on because I thought for many months now that testing needs to be done at scale and it still hasn't gotten done. It has. So we gave up basically untested gave up because we're and we're all sitting there waiting for vaccine to come along. Uh, and the distribution of the vaccine is not, you know, it's struggling from the same kind of things that the testing is going to take quite a bit of time. So it does, if everything goes great, meaning there's not a second strand of the virus that's going to create a second major wave that I am cynical enough to think that it won't be until mid summer that we started opening back up. And [/INST] Yeah, I think it's gonna be May June, I'm a little bit earlier than you. I've been tracking it's like 1.5 million shots in arms a day. I think this vaccine has been undersold. I mean, it's a miracle, not one person who was in the trials died, who took it and only one went to the hospital and they weren't even put on a ventilator. So, and the hospitalizations are plummeting and we're at 10% now in the United States at the pace. We're going at 1.5 a day. I think the johnson johnson one comes out next month. It will be three million a day, maybe 2.5. And we already have 100 million people who have likely had it. So I've been doing the math. I think we're like 60 days away, February March sometime in April. I think anybody's gonna be able to get a shot and the number of deaths is going to go below 200 a day. And once that happens, I think people have had enough of this. They're just gonna go YOLO. </s>

<s>[INST] So how does having a four Kelvin source, how does the calibration work? [/INST] It could be larger. Imagine like you're trying to calibrate the microphone. Like you could do it with like a really loud sound, but the gain would start to compress. So there are amplifiers downstream from the detector in every experiment that I've ever worked on. And they only have a linear region over a very small region and you want to keep it as linear as possible. That means you want, if you're trying to get rid of it, you're trying to compare like a voice and you're trying to compare that to a jet engine. It's not as, it's not going to be as easy on the amplifiers as getting, you know, a slightly last gong or something, you know. </s><s>[INST] So the idea of the noise is present in both? [/INST] There's noise present in both. And you get, you measure what they did is they made a separate measurement just of the calibration system, which they measured exactly very well. Four kelvin is the temperature of liquid Helium. That's a temperature that's not going to change. And certainly not going to change over time scale, one second. And so they could compare unknown signal, known signal, unknown signal, known signal, like a scale, like a balance. So another way to think about it is like this. You've seen these Libra kind of balances, where you put two weights in a pan. Right? What happens if you put like a one ounce weight on one side in a 20 kilogram, you don't get any measurement, right? But you do get kind of a of measurement if they're close in weight. </s><s>[INST] That's why they use four Kelvin. Got it. Just to linger on the fact that there's a romantic element to the fact that you're arriving at the same temperature. That's kind of fascinating and you measuring stuff in terms of... You're measuring signal in terms of temperature at the source. Yeah. So you get to... I mean there's something about temperature that's intimate. Yeah. [/INST] It's cool. Yeah. Especially since all life is basically conversion of energy and trying to control entropy, which is then related to thermodynamics exactly in that way. And this is a very crucial kind of thing to do in science because they weren't looking for the signal. They found it accidentally, these two scientists, Penzias and Wilson. And I like to think that those kinds of discoveries are the purest in science. Like when you see something, Isaac Asimov once said, like the most important reaction as a scientist is not Eureka, which means in Greek, as you know, I have found it. No. He said, no. That's weird. Like that's a much better reaction or that's freaking cool. That's a scientist. Not like, oh, I found one. Because surprise. Yeah. Yeah. Because if you find what you're going to find, that's what leads us susceptible to confirmation </s><s>[INST] bias, which is deadly inside, you know, as close to deadly as possible. Yeah. Yeah. [/INST] So how does that take us to something that's potentially worthy of a Nobel prize? So Penzias and Wilson weren't looking for a signal. They ended up discovering the heat left over from the fusion of helium from hydrogen, etc. And that was a serendipitous discovery. They won the Nobel Prize in 1978. It was the first one ever awarded in cosmology. My reasoning is what if you could explain not only how the elements got formed, but how the whole universe got formed and kill off every other model of science. So if that weren't enough, every scientist, you know, worth his or her salt had told me and Andrew Lang and our colleagues, this is a slam dunk, no ball prize. If you could do it, because it was really explaining, again, the stakes of this science is different than like superfluidity, plasma physics. When you talk about the origin of the universe, it ties into everything. It ties into philosophy, theology. You realize if Paul Steinhardt is correct, that the Bible can't be correct. In other words, if the Bible is correct, now isn't falsified, if you like, if you believe it. I never use the Bible as a science book, obviously. But the Bible speaks of a singular beginning. What if you knew for sure the universe was not singular? It would be more like the cosmology of Akhenaten and Egyptians than the biblical Torah, Old Testament, if you will, narrative. So in my mind, the stakes could not be higher. And again, it's not an effect because we need plasma physics, we need every type of physics except maybe biophysics. We literally use every branch of physics, thermodynamics, superconductivity, quantum mechanics, all that goes into our understanding of the instrument. And even further, if you want to understand the theory that predicts the signal that we purport to measure. So I rationalize that if Penzias and Wilson won the Nobel Prize for this, if Halcyn Taylor won the Nobel Prize for indirectly detecting gravitational waves, this is decades before LIGO, by me detecting gravitational waves indirectly, detecting how the universe began, detecting the origin of the input initial conditions for the Big Bang nucleosynthesis, which won the Nobel Prize in 1983. These are like five Nobel Prizes, you know, potentially. For that reason, it seemed as close as you could possibly get to being a slam dunk to outdo what my father did to do, you know, really this impossible. And at that time, Lex, you know, again, I'm, you know, it sounds weird because people like, oh, you wouldn't, you know, you don't really, you know, you still want the Nobel Prize. You're still like reading. Look, you wrote another book of it. And I always joke, I'm like, well, if you want to see if I'm a hypocrite, just get them to give me the Nobel Prize in literature, you know, and if I accept it, then I'm a hypocrite. </s>

<s>[INST] to, to make it more efficient to make judgments. So the racism makes it more efficient. It, [/INST] uh, it efficiently, uh, moves people from society to the streets. Uh, and that's, uh, and a lot of innocent people get caught up in that. </s><s>[INST] Well, let me ask in terms of the innocence. So you've gotten a lot of people who are innocent? Are you different? Uh, I guess I guess revealed their innocence, demonstrated their innocence. What's that process? Like what's it like emotionally psychologically, what's it like legally to fight the system in uh through the process of revealing sort of the innocence of a human being. [/INST] You emotionally and psychologically it can be taxing. I follow a model of what's called empathic representation and that is I get to know my clients and their family, I get to know their strivings, their aspirations, their fears, their sorrows. So that certainly uh Mhm Sometimes can do psychic injury on one if you you know, you get really invested and really sad and and or happy and it uh it does become emotionally taxing. But the idea of someone sitting in jail for 20 years, completely innocent of the crime. Can you imagine sitting there every day for 20 years doing that? You factually did not do the thing that you were convicted of by a jury of your peers? It's got to be the most incredible thing in the world. What but the people who do it and the people who make it and come out on the other side as productive citizens are folks who say they have come to an inner peace in their own minds. And they say these bars aren't going to define me uh that my my humanity is uh is there and it's it's immutable And they are not bitter, which is amazing. I I would tend to think that I'm not that good of a person, I would be bitter for every day of 20 years if I were in jail for something. But you know, but people tell me that you know, that they can't survive like that one cannot survive like that. And you have to come to terms with it. And uh and the people who might have exonerated, I mean they come out, most of them uh come out and and they just uh really just take on life with of them and and vigor without bitterness. And it's it's a beautiful thing to see. </s><s>[INST] Do you think it's possible to eradicate racism from the judicial system? [/INST] I do. I think as I think that race insinuates itself in all aspects of our lives and just the judicial system is not immune from that. So to the extent we began to eradicate dangerous and deleterious race thinking from society generally, then it will be eradicated from the criminal justice system. I think we've got a lot of work to do and I think it'll be a while, but but I think it's it's doable. I mean, you know, uh the country, so historians will look back 300 years from now and take note of the incredible journey of uh diaspora Africans in the in the U. S. An incredible journey from uh you know slavery uh to the the heights of politics and business and judiciary of the academy and so forth and not a lot of time and actually not a lot of time. And if we can have that sort of movement historically. Uh, let's think about what the next 175 years will look like. I'm not saying it's going to be short, but I'm saying that if we keep at it, uh, keep getting to know each other a little better. Keep enforcing laws that prohibit the sort of race based discrimination that people have experienced and provide as a society opportunities for people to thrive in this world. Then I think we can, we can see a better world and if we see a better world, we'll see a better judicial system. </s>

<s>[INST] So when you're like, uh, you know, many minutes into the match and you're slowly moving as you sometimes do tying about catching your breath, you're not thinking about anything, you're trying to let go of thinking, [/INST] I'm trying to like to save Everything to defy, like nothing goes to waste. It's, you know, every move unnecessary is just gonna make some more tired or it's going to take something out of you. Like, you know, I try to calculate every single move I make, save as much energy as I can so I can fully, you know, be focused 100% in the fight with no way. Especially energy wise. </s><s>[INST] And that's instinctual like uh minimizing the amount of moves you're not like explicitly thinking, should I do this or not? It's just just don't move unless it's absolutely required. [/INST] Yeah, because fight this you cannot really, there's not really time to think much, you know, it's like it's your instinct are playing. It's like it's you know, you already have your you know, your your weapons, let's say, you know you the things that you do, it is just you wait for the perfect moment. The beauty of it is, you know, is this the right moment to everything if you feel one second too late doesn't work or you get messy. So it's you know, you're trying to catch that moment, that's his, you know, and for that you have to be fully focused on what you're doing because one second is you out, it won't work </s><s>[INST] but you're you're not exactly known as somebody that moves super quickly. So the [/INST] so </s><s>[INST] the moment it's not about how quickly you move, it's about the right moment. Moment. [/INST] Yeah, it's not like it's speed, it's not like you have to move the speed of light. It's the move itself at that precise moment. It doesn't have to be super fast because your opponent is not moving super fast, you know? So it is a combination of moving between you and him. </s><s>[INST] I mean the same thing happens in judo and the movement can be really small. [/INST] Yeah, just Judaism is a bit more explosive, you know, it's it's moving slightly faster so it didn't know it does require a bit more explosiveness in judo, but </s><s>[INST] even just the right timing for an off balance. Just a little [/INST] tough. Yeah, it's not that that, you know, moving the speed is not going to count that much. Yeah, it's the timing that you initiate that move. You </s><s>[INST] see that with foot sweeps there's nothing more beautiful than not like olympic level athletes going at it in the olympics? And a and it's just and you see one man's life flash before his eyes and realize like I'm supposed to be the top three person in the world that I just find they don't they have this look on their face like, I don't know what just happened. It's beautiful to see. And you don't see that, I guess you see that in boxing knockouts and stuff like that, you don't know what the hell just happened. [/INST] Is that precise moment of movement that you get caught? Like is that one split second? That's it. Do </s><s>[INST] you get that in jujitsu at all because judo has because of the explosiveness because of the point scoring system that incentivizes these giant throws um has these moments where everything just turns on a single moment, you have that [/INST] Not really because then his points. Yes you get like you know two points. So it's because I think regarding the submission is not just one precise movement that changed everything. I think judo is to take down that counts as a submission. Like Ippon fight over judicial don't have that. So you you will score points. But I think in terms of submission you need to get to uh you know dominant position first and then the submission will come slowly. It's </s><s>[INST] a process. Yeah. Okay, let's go back to that guy with with his mind. So actually in the weeks leading up to it in the days and the hours and the minutes. Is there some fear in you leading up to this? [/INST] I mean I'm not gonna say you know that I'm fearless because everybody fears something. You know the fear is there but it's like how much you let that control you? I think I was a lot more confident than fearful for sure. Walk into that fight Like I was pretty confident that I could beat him. Where </s><s>[INST] is the source of that confidence? [/INST] My beliefs don't on me. Okay, I can take the </s><s>[INST] word that you can take anyone in the world. But is there a specific strategic like you know, talking to Donna her, he believes that there's no such thing as confidence. Like or rather the way you get confidence is through data like that You have proven yourself effective uh in previous situations. But with you don't you don't have much data. It was a very the first time you faced. It was a very tough. That was also one of the greatest matches of all time. Was very tough. So doesn't that creep in like that doubt? Because you know, you don't have enough data to be confident based on [/INST] uh Yeah, I mean, okay, if I never had fought before, you know, somebody walked into a fight with someone like that, then would I be that confidence? I mean, probably no. You know, so that history or you know what we've been doing or had been achieving this gives you confidence. If that was my first fight ever, I wouldn't probably wouldn't be that long. </s><s>[INST] But the time off, [/INST] it doesn't matter. </s><s>[INST] Doesn't matter. [/INST] Doesn't matter. You </s><s>[INST] don't have the fear or the actual physical experience, the psychological experience of being rusty of being out of [/INST] the </s>

<s>[INST] is do you do you think about the concept of burnout? Because so I personally never experienced burnout in the way that folks talk about, which is like, it's not just the up and down. It's like you don't want to do anything ever again. It's like, it's for some people, it's like physical, like to the hospital kind of thing. [/INST] Yeah. So I do worry about it. So when I used to do student writing like writing about students, a student advice. It came up a lot with students at elite schools and I used to call it deep procrastination. But it was a real, really vivid, very replicate herbal syndrome where they stop being able to do schoolwork. Yeah. Like this is, do the professor gives you an extension and the professor gives an incomplete and says you got, you were going to fail the course. You have to hand this in. They can't do it right. It's like it's a complete stop on the ability to actually do work. And I used to counsel students, you have that issue and often it was a combination of this is my the best analysis is you have just the physical and cognitive difficulties of their usual under a very hard load right there. Doing too many majors to an extracurricular is just, you know, really pushing themselves and the motivation is not sufficiently intrinsic. So if you have a motivational center that's not completely on board. So a lot of these kids like what I'm doing with my kids, they would be, you know, their whole town was shrewd enough fireworks that they got in there. Everyone's hope that they were going there. Uh and that they're in three majors, don't wanna let people down, but they're not really interested in being a doctor or whatever. So your, your motivation is not in the right place. The motivational psychologists would say the locus of control was more towards the extrinsic end of the spectrum and you have hardship and you could just fritz out the whole system and so I would always be very worried about that. So I think about that a lot. I do a lot of Multiphase or multi scale seasonality. So I'll go hard on something for a while and then for a few weeks ago, easy, I'll have semesters that are hard and semesters that are easier. I'll take the summer really low. So on multiple scales and in the day I'll go really hard on something, but then have a hard cut off at five. So like every scale, it's all about rest and recovery because I really want to avoid that and I do burnout? I burnt out pretty recently. I get minor burnt out. I got a paper a couple papers that was trying to work through for a deadline a few weeks ago and I wasn't sleeping well and um there's some other things going on and it just, it knocks out and I get sick usually is how I know I pushed myself too far and so I kind of pulled it back and I'm doing this book launch then after this book launch and pulling it back again. So I like I seasonality for rest and recovery, I think it's crucial and at every scale daily, monthly, you know, and then at the annual scale, like an easy summer for example, I think it's like a great idea if that's possible. </s><s>[INST] Okay, you just made me realize that that's exactly what I do because I feel like I'm not even close to burnout or anything even though I'm, I'm in chaos, I feel the right exact ways the seasonality is the, not even the seasonality, but like you always have multiple seasons operating, it's like you said like because when you have a lot of cool ship going on, you, there's always at least one thing that's a source of joy that there's always a reason, I suppose the fundamental thing and I've known people that suffer from depression to the fundamental problem with like the experience of depression and burnout is like why do like life is meaningless? And I always have an answer of like why, why today could be cool [/INST] and you have to contrive it right? If you don't have it, you have to contrive it. I think it's really important. Like okay, well this is going bad. So now is the time to start thinking about. I mean look, I started a podcast during the pandemic is like, this is going pretty bad. But you know what, This could be something really interesting. </s><s>[INST] Deep questions with colony apart. Uh do it all in that voice. I love the podcast by the way. But yeah, I think David Foster Wallace said uh the key to life is to be unbearable. Uh I've always kind of taken that to heart which is like, you should be able to maybe artificially generate anything. Like uh find something in your environment, in your surroundings that's a source of joy. Like everything is fun. [/INST] Yeah. Did you read the pale king? It goes deep on board? Um it means it's like uncomfortable. It's like an uncomfortable meditation on boredom. Like the characters in that are just driven to the extremes of, I just bought three books on board. Um the other day. Uh so now I'm really interested in this topic because I was anxious about my book launch happening this week. I was like, okay, I need something else. So I have this idea for a might do as an article first, but as a book like okay, I need something cool to be thinking about because I was worried about like I don't have a lot going to work the pandemic, what's going to happen, I don't know if it's going to get to. So this is exactly what we're talking about. So I went and I bought a bunch of books and I'm beginning like a whole uh sort of intellectual exploration. </s>

<s>[INST] course, most people don't [/INST] Write prior to 98. It took the family after 98. The hospital can do it, funeral home can do it or the family can do it. So a lot more people haven't filed after if they've died. </s><s>[INST] But it's still there's a lot of people probably [/INST] People don't because that death benefits only like $219. Okay nobody's thinking about that ship. So I started to apply for Social Security benefits, nope Numbers dormant. So they want you to come in for a physical interview here I am. You know 32, you're not going to pass as a 65 year old. So. No. So the next idea I had was I wonder if you could file income tax returns on these people </s><s>[INST] turns [/INST] out you can all day long. So I started doing that and I started to steal once I got ramped up because you test everything. You know you're testing to make sure you've got to figure out what the deposit instrument is and everything else. And once you get all that lined out, I started to steal $160,000 a week every week for 10 months out of the year </s><s>[INST] by paying taxes [/INST] by filing fake. </s><s>[INST] Yeah filing fake tax insurance. So [/INST] you find a business. And the way the system worked is the I. R. S. Will issue a refund on somebody before they are able to verify that that person works for an employer still works like that today. Alright, so </s><s>[INST] and you're keeping the amounts relatively low. [/INST] $30,000. </s><s>[INST] All right [/INST] amounts are very low. But </s><s>[INST] you're still able to achieve scale because this large index [/INST] and I was manual and later on a couple of buddies of mine went automated with it. </s><s>[INST] What you would go doing this by hand. So there's no code involved? [/INST] All manual. I'd file a return once every six minutes Work 10 hours a day. three days a week. So </s><s>[INST] clicking on, typing fast and quick [/INST] Return every six minutes. That's changing I. P. That's changing address. Everything else will return every six minutes for three days a week. 4th day I would take a road trip plot out a map of ATMs. And then the next two days cash out bam bam bam bam bam. Alright come back home, rinse and repeat. Um It turns out that a backpack. I don't see any sitting around here but a backpack will hold 100 and $50,000 of twenties is what it will hold. So I put 100 50 k. and 20s in a backpack. I had a spare bedroom had come in, toss the back back in the bedroom. </s><s>[INST] This is very very important information. And the fact that you know it is is also very first we started with the volume of cold that weighs a ton. And now a backpack holds $150,000 of 20. And then you can multiply that by five for hundreds. Yeah [/INST] it's 20 most of the time is 20. It's coming out of a tm. Right each. 20 ways Graham </s><s>[INST] Each. 20 g. So [/INST] it's actually go by weight which is what federal authorities do when they get a pile of cash. They just weigh it. </s><s>[INST] They just they just wait, [/INST] 150 K. is 7.5 keys of cash. </s><s>[INST] 15, that's pretty light. [/INST] That's sad. </s><s>[INST] Did you get big backpack? Go do a good run with David Goggins with it. I like it. But the fact that, you know, this is great. So, wait. Uh, where, where does that come in with a backpack? [/INST] So, what happens is I didn't know how to launder money. All right, So, you know, I'm throwing cash in in the spare bedroom one day. You open up the bedroom and you're like, I gotta do something with those backpacks. And that's when you start learning how to launder money. You know, cash based businesses, things like that. I had a production company, had a couple of detailing company. I was thinking about going to the food trucks, things like that in charleston. </s><s>[INST] Actually. Can you pause on that to take a tangent there? How does money laundering work? I mean, at that time. And what years are we talking about? [/INST] This is uh by the time the tax return schemes go into play, we're talking 2000 to 2003 is one tax return start. And </s><s>[INST] so, what, at that time? And what you're aware of now, how it evolved, How does monday money laundering work? [/INST] You know, it's not that much different. It's really not. You you get a cash based business start laundering the money or putting the money through that saying that transactions are legal. You then start deposited into bank accounts from the bank accounts. My thing was is have bank accounts. The United States Mexico Canada and then finally bounced over to Estonia was the final destination of all this stuff. And the idea is to try to move them to so many places that by the end of the day it looks legal and you can't trace it all if you're ever caught which you ultimately are. But so the cash based businesses, you know </s><s>[INST] when you say sorry to interrupt the cash based businesses, so you have money that needs to be moved to other people. Uh So how does that work? What's what's the business service and you're giving them money? [/INST] Right. So you you do the Ozark thing if you want to do that, so you can gamble cash out something like that. So for trips to whatever casinos you've got, you've got your production company or your detailed company. So how many cars you cleaning today? How many companies have you got to do that? Alright, Whatever that company is, it's gotta be cash based. Somebody's paying you in cash is what you're doing. You have to have enough of those cash based businesses where it doesn't look funny. All right, because if you're a detailed company make $100,000 a month, that's a problem. Okay, so then you start depositing into that. Well because of the Patriot act as a suspicious activity report. SARS Came in at $2500 instead of the 10K. That it used to be. So all of a sudden you've got multiple bank accounts that you've got to set up. All right, fortunately what you also had is you had a bunch of prepaid debit cards that were coming into play at the same time. So a combination of bank accounts, prepaid debits that had a ch abilities attached to those as well. And you start running them all together. Then once it's out of the United States, you don't have to worry as much. You can start funneling that into uh fewer bank accounts until finally, you've got the one main account that's over at bank politico and Estonia at that point. That's what you've got. Um </s>

<s>[INST] it's so cool. So there's these like big variables that you're aware of and you're trying to optimize over the space of variables. You get to start to play with that when you're looking for performance, [/INST] it's almost like moving from checkers to chess, you have like or maybe even like connect for us or something like that, where it goes from just kind of like, well one ft in front of the other and when I get to the next stage station, I'll just eat whatever, looks good, drink whatever, you know, quenches my thirst and then move on to the next one to like, well, which one of these food products is actually going to make me move a little faster the next aid station or you know, which one of these pacing strategies is going to get me to the finish line faster than the other one and that sort of stuff. So uh, it gets more complicated, more interesting. And uh in my opinion anyway, also there, I mean there's a breaking point with that too because like I said, there's an endless number of variables you could account for and there's a distance gets longer, that list gets longer too. So you find yourself in this position where where you have to at some point say, okay, I've accounted for everything I can reasonably account for. Now. I need to be in a mental space where when something happens that I wasn't able to account for. I'm able to respond to it with the right decision and keep going and not dwell on it. Because that's another thing, I mean, you're running slow enough when you're doing 100 miles where if you make a mistake, you can sit there and just fixate on that mistake and say, why did I do that? That cost me 10 minutes, blah, blah blah. When in reality, what you need to do is that happened everyone else and you're gonna have a situation like that at some point, mine happened. Now I need to figure out how I can move forward at the fastest sustainable pace and not think about what happened back there. And that's where I think it gets really interesting. </s><s>[INST] What would you say it takes to set a world record in the 100 miler? [/INST] First of all, I think you probably have to focus on that specific event. Um, I mean there's the interesting about ultra running where maybe deviates a bit from just other endurance sports is, there's such a wide range. I mean, we talked about a little bit, when I talked with the SAn, Diego 100 versus kind of flat rentable stuff. So </s><s>[INST] can you maybe paint a picture of what are, there's a huge range of different kinds of ultra marathon events? What are like the big ones in your mind? So marathon would go the distance for a marathon. There's a 50 K, what are different kind of, there's 100 mile that in your mind, like kind of these islands where people gather off. [/INST] Yeah, so there's a few that really stand out, I would say the three biggest ultramarathons right now, even from a historic, maybe not necessarily historical standpoint, but Uh, in modern day, ultra running is going to be the Western States 100. That's the biggest, most competitive 100 miler. It's on the trail side of things in the United States. Then there's ultra trail mont blanc, which is probably the most competitive 100 miler on the planet right now in previous years. It's been debatable as weather. Western States are ultra trail mont blanc's more competitive. I think in the most recent few years, you're just seeing a lot more like Of the bulk of international talent on the trail side of the sport heading over that way and then you have the road running side of things where the comrades marathon, which is technically 56 miles, but they called the comrades marathon, uh, is going to generally be the most competitive ultra marathon. The weird thing is the distance thing, right? Because most people think of endurance sports, they're thinking about precise distances like, five km, 10 km all that stuff. And then then you get into the ultra running world and it's like sometimes it's the event, so like the Western </s><s>[INST] itself is much more important than the distance. [/INST] Yeah, so the Western States, 100 is actually 100.2 miles, which isn't that big of a deviation when you think about it, especially when you figure like tangents, they're going to probably account for more than 0.2 miles on 100 mile race. But the ultra trail mont blanc, you know, that's listed as 100 miles, but it's actually think like 104 105 miles. So, You know, it's more, there's different cultures too. So the United States is definitely more motivated, I think to try to get as close to the exact distance. You're gonna hear maybe a little more grumbling. If someone says I signed up for this 100 mile and it turned out to be 103 miles versus like over in europe, they don't really care too much about the distance. They're more interested in, like a specific route or a loop </s><s>[INST] is consistency important in terms of the exact length of the, of the roots. So like you can compare performances from previous years or are they a little bit more flexible? Like they redefine the trail from year to year? [/INST] Yeah, I mean, it's definitely hard to compare. I mean, there's the events that, um, take, for example, um, I would say the best ultra marathoner in the world today on the men's side is Jim Walmsley. The reason I think Jim Williams is the best, is because he is the most versatile and not only the most versatile, but he's arguably the best at almost everything up to 100 miles. So there's a race called the Angeles crest 100 miler. The trail has drastically changed from when they originally had that event and it's a different time of year, so much much warmer on that course and jim is not the kind of guy who would, uh, sit back and say like I can't chase that record, but I think Angela crest when he looks at the segments and the pacing for that one, he's like that one is maybe not even the same event anymore. So you have that, you have some that are a little more controlled and a little more kind of like preserved I guess you would say, but I think it gets really rare on the trail side. I mean comrades is going to be very comparable from one year to the next because that's a road race and that's where you get, you maybe get like a split in the sport from people who really want that kind of like, I want to compare myself to someone who ran this course in 1970 versus like someone just says, I want to be competitive today and you know, maybe the weather is going to be 30 degrees different from one year to the next on this course. But if I beat everyone on this day, then I'm the champion of that big named race, like Ultra trail mont blanc or western states 100 my legacy will be cemented because I won that big race and it doesn't matter when or how the course was or what the time even was to some degree </s>

<s>[INST] and a business preference. Conversations in an unregulated way. Can we kind of return to proof of work and proof of stake? There's just so many topics I want to talk to you about, so I'll jump around a little bit, but at the Bitcoin conference, Jack Dorsey spoke. I believe he said, Bitcoin changes everything. I think you made a video for Jack trying to explain different ideas to him describing the difference between proof of work and proof of stake because we've talked about, what do you hope Jack Dorsey comes to understand [/INST] about the difference between proof of work and proof of stake? Well, I hope he understands it's just a resource. That's the entire point of the video I was trying to make is like, dude, you're like in this cult where you think the only way to be secure is proof of work. And somehow proof of stake is less secure than proof of work. I don't even know how you put those inequalities there because you're talking about apples and oranges. You're making different trade-offs and there's different assumptions about the nature of the people involved, but the mechanics are the same. And so it's really more of a question of what type of system do you prefer? Do you want mercenaries guarding Rome or do you want Roman citizens guarding Rome? And as the Romans learn, it's better to have citizens usually doing that. And that's the only point I was trying to make to Dorsey. I don't think he watched it or particularly cared, but it was more of a video for everyone. And to start that dialogue of realizing that the real game is not is proof of stake better than proof of work, it's how do we go from one to N and what should N be? You just mentioned that semantical addressable web going back to IPFS and these other concepts. Well, how do you pay for the enormous burden of storing that much data? You can create a consensus protocol for it. There actually is one. It's called Permacoin. It came out in 2014-15. Andrew Miller wrote it and a few other authors. I think John Katz may have been an author as well, but basically it was just a throwaway proof of work style algorithm that only works if you have large amounts of data. So it's like your miners are like a hard drive effectively. Proof of storage, I think you call it. This type of stuff. And there's been since then many iterations and evolutions of that type of protocol. So what if you throw that into your resource back? Now you have a capacity in your system for storing huge amounts of information. That's incentivized by the way the system works, and you can balance that with a proof of stake system. And you can balance that with, let's say you have proof of useful computation. We may have a paper on that, who knows, coming soon. And what if you have a proof of useful computation where maybe you can do Wokiyah or something. Who knows. With something like that, okay, well now you have three resources inside your system and those three things keep your system secure, they keep each other balanced, and they just so happen to create the world's largest supercomputer that's programmable, and it just so happens to create the world's largest database that's programmable, in addition to having a shareholder style model for ownership inside of it to kind of balance these things out so people care about the appreciation of value inside the system. So that was my point to Jack, is you're a business guy, why are you betting all your eggs? And one crazy model that's a cult, step away and realize that that does something. It's a tool, but saws aren't the only tool in the toolbox. There's hammers and screwdrivers and other things. Go to end resources and let's have a real conversation about what would a world computer or a world infrastructure that's useful for your business domain, in his case, Twitter, require? And what type of resources would you need for such a thing? </s><s>[INST] Proof of storage, I think you call it. In this case, Square, more importantly. Currently, if you look at Square and Cash App, they support Bitcoin. He is kind of all in on the proof of work idea. Not all in, but currently kind of, that's the one supported idea. [/INST] I guess there's an adjusted tip in proof of work. </s><s>[INST] I love you so much, Charles. Thank you, appreciate this. But I'm not gonna run with that, even though I'm tempted to, but looking forward, do you hope Cardano [/INST] becomes part of Cash App? I mean, he's a business guy, or at least I'd hope he is, and it's not about what I want or what he wants, it's about what markets want. When you run a publicly traded company, you have fiduciary obligation to your shareholders to maximize the utility, the sustainability and value of your company. And so if he's running a company that makes money off of these things, it makes absolutely no sense to be a maximalist. You want transaction volume, that's how you make your damn money. Coinbase was the same way, they were very maximalist in the beginning. Very quickly they started realizing, hey, we're losing a lot of money. If we wanna IPO, we kind of need to be a bit more diverse. Eric Voorhees was also a maximalist way back today. Now look at Eric, he's got ShapeShift and all these other pieces of infrastructure. He's a lot more friendly with us altis. So Jack will make that decision, his people will make that decision, I think, based on market dynamics, transaction volume and value to the user. And if the concern is actually legitimately security, then the only question I'd ask their team is, can you please provide me a definition of one? Doing POW is more secure than proof of stake as a tweet is not really a proof, okay? You need to actually come out and sit down and say, what is your security model? What do you care about? What do you value? What's the problems you're concerned about a proof of stake? And they never really get there. And that's why I call this maximally like a religion, because it's just like saying, the angels descended from the heavens. And it's like, well, how do you know? Because the Bible said so, or this doctrine said so. It's like, well, that's your evidence. Somebody wrote something down. Can you please give me a little bit more? They say, no, you're challenging the word of God. In this case, you're challenging the word of Satoshi. And all I ask for is just, what is the burden of proof? We wrote the papers, we have security models, we went through the peer review process. God, that was not easy. We wrote formal specifications. In some cases, we formalize those specifications with Isabel, for God's sakes, which is not easy to do. And then we implemented it. And it's running in production with a million users at a $50 billion market cap. I mean, at what point do you start saying, well, maybe there's something there, you know? And they say, no, there's nothing there and it's not secure, it can't be secure. And he said, okay, then why do you believe what you believe? </s>

<s>[INST] Well the thing that's really important to me and I wonder if it's possible? Well, I hope it's possible, pretty sure it's possible is for me, even though I know how it works to make sure there's sufficient randomness in the [/INST] process. </s><s>[INST] Uh Probably because it would be a machine learning based that I'm surprised that I don't I'm surprised by certain reactions. Uh surprised by certain communication, maybe that's in the form of a question. Were you surprised by certain things, Cosmo did like certain interactions? [/INST] Yeah, we made it intentionally like uh so that there would be some surprises and like a decent amount of variability and how he'd respond in certain circumstances. And so in the end, like it's um this is this isn't generally i this is a giant like spectrum and library of like primer tries kind of emotional responses and an emotional engine that would like kind of map your current state of the game, your emotions, the world that people were playing with you all so forth to what's happening. Um But we could make it feel spontaneous by creating enough diversity uh and randomness. Uh but still within the bounds of what felt felt like very realistic um to make that work. And what's really neat is that we could get statistics on how much of that space we were saturating um and then add more animations and more diversity in the places that would get hit more often so that you stay ahead of the um you know the curve and maximize the chance that it stays feeling alive. Um and so, but then when you combine it like the permutations and kind of like the combinations of emotions stitched together sometimes surprised us because you see them in isolation, but when you actually see them and you see them live, you know, relative to some event that happened in the game or what not. Like it was kind of cool to see the combination of the two and uh not too different in other robotics applications where like you get so used to thinking about like the modules of the system and how things progressed to a tech stack that the real magic is when all the pieces come together and you start getting the right emergent behavior um in a way that's easy to lose when you just kind of go too deep into any one piece of it. </s><s>[INST] Yeah, when the system is sufficiently complex, there is something like emergent behavior and that's where the magic is as a human being can still appreciate the beauty of that magic of the final [/INST] at the system level. </s><s>[INST] First of all, thank you for humoring me on this, it's really really fascinating. I think a lot of people love this. I love to just one last thing [/INST] on the butter robot </s><s>[INST] problems in terms of speech Cosmo is able to communicate so much would just movement and face. Do you think speech it's too much of a degree of freedom? Like speech a feature or a bug of deep uh interaction, emotional interaction [/INST] for a product. It's too deep right now, it's just not really. Uh You would immediately break the fiction because the state of the art is just not good enough. Um And uh and that's on top of just narrowing down the demographic where like the way you speak to an adult versus away speak to a child is very different. Um yet a dog is able to appeal to everybody. Um and so right now there is no speech system that is like rich enough and and subtly really realistic enough to feel appropriate. Um And so we're very very quickly kind of like moved away from it. Now speech understanding is a different matter where understanding intent that's a really valuable input. Um but giving it back requires like a you know way way higher bar um given kind of where today's uh world is. And so uh that realization that you can do surprisingly much with either no speech or kind of tonal like the way you know while we R. Two D. Two and kind of other characters are able to um it's quite powerful and it generalizes across cultures and across ages. Really. Really well I think we're gonna be in that world for a little while where it's still very much an unsolved problem on how to like make something it touches on the uncanny valley things. So if you have legs and you're a big humanoid looking thing, you have very different expectations in a much narrower degree of what's gonna be acceptable by society. Then if you're uh you know robot like uh cause more wall and you can or some other form where you can kind of like reinvent the character. Speech has that same property where speeches so well understood. Um in terms of expectations by humans that you have far less flexibility on how to deviate from that and and lean into your strengths and avoid weaknesses. </s><s>[INST] But I wonder if there is obviously there's certain kinds of speech that uh activates the uncanny valley and breaks the illusion faster. So I guess my intuition is we will solve certain we would be able to create some speech based personalities sooner than others. So for example I could I could think of a robot that doesn't know english and is learning english right? Those kinds of person [/INST] action where you're like uh you're intentionally kind of like getting a toddler level of speech. So that that's exactly right. So you can have like uh tie it into the experience where uh it is a more limited character or you embrace the lack of emotions or the lack of sorry dynamic range in the speech kind of capabilities, emotions as like part of the character itself. And you've seen that in like kind of fictional characters as well. Um but that's why this podcast works. Yeah, like, and you've got to have that with like um you know, I guess like data and some of the other. Yeah, like but yeah, so you have to and that becomes a constraint that lets you meet the </s>

<s>[INST] Well that's great. That's I mean she's grown to be able to communicate, To understand, to self reflect, to understand where she is. I've people in my life who I love her bipolar. It's a beautiful ride. It [/INST] is right. Yeah, it's yeah, it's the highs and the lows are like, they're so but yeah, like because I like, I feel like a protector and for me, I just want to be a rock, right? And that's part of the whole cereal thing. If she wants to eat cereal, don't make a wrong for anything. She wants to do. </s><s>[INST] What have you learned from life from the song? The gambler by Kenny Rogers. You gotta know when to hold em, know when to fold em, know when to walk away. No one to run. You never count your money when you're sitting at the table, there'll be plenty of time for counting when the dealing is done is that do you live by those words? [/INST] The first part of it for sure. </s><s>[INST] Do what do they even mean? Because you [/INST] got no when hold No. So basically it's like, all right. You know, in life like you know what let's let's use a whatever the market, for example, you bought a stock, right? Or you bought Bitcoin and you're like, that's gonna go to the moon, right? It's like, okay, well maybe things have changed. New scenario, new circumstances, new situation. Are you going down with the ship, right? Or you gonna play the hand down? Are you going to fold it? Whether it's a relationship, You know, you're you're you're with this woman. You're like, all right. I think it's time to fold this one. I think, you know, I don't think that we're gonna be able to make this this this hand work right now. Yeah, </s><s>[INST] maybe every gambler knows that the secret to surviving is knowing what to throw away, knowing what to keep. Cause every hand's a winner and every hand's a loser. That's like a stoic philosophy and the best thing you can hope for is to die in your sleep. Every hand's a winner and every hand's a loser. What does that mean? [/INST] I like that one. I like for me that's like the difference between victim and responsible. Like the way that I think about it, right? You can be a victim of circumstance or you can be responsible for everything in your life, Right? So an event happens, the event itself is neither good or bad until you assign it value, Right? So like an event happens and it can be traumatic, it can be, you know, painful, but you know how you respond to it is ultimately going to be up to you. Like you actually do have a choice. </s><s>[INST] The fact that you, Daniel took my commentary about the gambler seriously shows once more that you're a beautiful human being. Thank you. Thank you so much for being who you are for inspiring millions of people about poker, about how to live life. And thank you for giving me your valuable time today. This is amazing. Thanks for [/INST] talking. It's great to have the conversation. </s><s>[INST] Thanks for listening to this conversation with Daniel Negreanu to support this podcast. Please check out our sponsors in the description and now let me leave you with some words from Doyle Bronson poker is war. People pretend it is a game. Thank you for listening and hope to see you next time [/INST] </s>

<s>[INST] and [/INST] A $100 that he has to lay out for workers hire the workers and he puts them all together and he has an output and let's say the output is 100 units of something and one of the prices and that's his revenue. And when he when he takes his product and sells it and gets the revenue, let's say the revenue is it doesn't really matter, it's 120 for lack of a better word. 220 Sorry, And he takes 100 of it and replaces the tools, equipment and raw materials. He used up another 100 to hire the workers for the next shift and the other 20 is his prophet. And he puts that aside now along comes a technological breakthrough, a machine, a new machine and the new machine is so effective, You can get the same out the same number of units of output with half the workers. So you don't need to spend 100 on workers, you only need to spend 50, you can do it with half the workers. And so the capitalist goes to the workers by the way, this happens every day and he says to half of them, you're fired, don't come back monday morning, I don't need you, it's nothing personal. I just I got a machine. Why does he do that? Because of the 50 he now no longer has to spend on labor because they'll need half of them. He keeps everything else is the same. The machine, everything else is just to make the math easy. So he he keeps as his own profit. The 50 that before he paid for those workers, </s><s>[INST] right? [/INST] Because when he sells it for 220, that 50 don't have to give to the next job because he has a new machine. So that's what he does. The technology leads, he's happy, He's become more profitable. He's got an extra 50, which is why he buys the machine. The workers are screwed. Half of them just lost their job, have to go home to their husband and wife. Tell them I don't have a job anymore. I didn't do anything wrong. The guy was nice enough to say there was nothing wrong with me. But he doesn't need. I mean, so I'm I'm completely screwed here. I don't know what I'm gonna do about the debts. We have the house on mortgage, my Children's education or whatever else he's got going for himself right now. Now, the point there was of course, an alternative path. The alternative path would have been to keep all the workers pay them exactly the same that you did before for half a day's work. He would have got the same output, same revenue, same profit as before. But the gain of the technology would have been a half a day of freedom every day of the lives of these workers. The majority of workers would have been really helped by this technology, but instead they were screwed. So that one guy, the employer could make a big bundle of more money. You want to support a system like this? </s><s>[INST] Well, [/INST] uh, to go </s><s>[INST] back to Hagel the good and the bad. So you just listed the bad and you also first listed the good, the technological innovation of this kind of system. The question is the alternative whatever. As we try to sneak up to ideas of what the alternative might look like, What are the good and the bad of the alternative. So you just kind of as a opposite in the contract by contrast, showed that. Well, a nice alternative as you work less, get paid the same. You have more leisure time opportunity to to pursue other [/INST] other </s><s>[INST] interests, the creative interests, family flourish as a human being basically strengthen and embolden the basic humanity that's under all of us. Yes, But then what cost does that have on the um, the deadline fueled competition fueled machine of technological innovation. That is the positive side of capitalism [/INST] slows it down. </s><s>[INST] It slows it down. And the question is, which is more important for the flourishing of humanity. [/INST] I love, I agree with that. And I'd love there to be a democratic mechanism. So let's let's discuss it. Let's debate it and then let's decide what mixture because it's not either or the math problem I gave you is either or we could mix it, you could have a third less of a working day instead of a half less and then the other part would be extra profit for our employer etcetera. So let's have a democratic discussion of what is the mix between the positive and we have no such thing. All of this is decided by one side in this debate, which not only we know what they do, they always choose the one that maximizes their profit because that's what they were told to do in business school where I've taught, right. Um So we not only is it an undemocratic decision, but it's lopsided to boot so we don't have the opportunity, but I would love for us to be good. Hegelian Marxist and say let's take a look at the plus and the minus and make the best decision that we can we'll make mistakes but we'll all make them together. It won't be one of us making a dictatorial decision. You know, Marx developed the notion of the dictatorship of the proletariat, not as a notion of how government, it's not, I'm sorry not Marx lenin did that. Not as a notion of how the government works, but as a notion of what the practical reality is the dictatorship of these key decisions is not made by some sitting council. It's made by each little capitalist in his her relationships with the workers in the workplace. Which is why Marx focused his analysis on that point. And by the way, I can sketch for you right now. So it doesn't lurk in the background. What the alternative is, it goes right back to what I said earlier. The workers themselves, the collection of employees together, appropriate their own surplus and decide democratically what to do with it. Which includes the decision of whether or not to buy a machine and whether or not to use the machine and the savings it might allow to be handled by more leisure for themselves or as a fund for new developments in technology or new products or whatever they want. And, you know, this this is an old idea in human marks loved that. Towards the end of his life. He he started reading extensively in anthropology and one of the reasons he did that toward the end of his life was because he kept discovering that in this society and that including here in the United States, that there were examples of people who organized their production in precisely this way as a collective democratic community in which everybody had an equal voice. So we all together decide democratically what to produce, how to produce, where to produce and what to do with the output we all helped to produce. So let's do it in, you know, in this country where democracy is a value. Nearly everybody subscribes two think about it this way, the stunning contradiction that there is a place in our society where democracy has never been allowed to enter the workplace in the workplace. A tiny group of people unaccountable to the rest of her, the the employer, whether that's an individual, a family, a partnership, or a corporate board of directors, tiny group of people controls economically, a vast mass of employees. Those employees don't elect, Those people have no nothing. There is no accountability. It is the most undemocratic arrangement imaginable. And this society insists on calling itself democratic when it has organized the minor matter of producing everything in a in a way that is the direct, its autocratic, </s>

<s>[INST] This is the LexVietman podcast, support it. Please check out our sponsors in the description. And now to your friends, here's Robin Hanson. You are working on a book about, quote, grabby aliens. This is a technical term, like the big bang. [/INST] So what are grabby aliens? Grabby aliens expand fast into the universe and they change stuff. That's the key concept. So if they were out there, we would notice. That's the key idea. So the question is, where are the grabby aliens? So Fermi's question is, where are the aliens? And we could vary that in two terms, right? Where are the quiet, hard to see aliens and where are the big loud grabby aliens? So it's actually hard to say where all the quiet ones are, right? There could be a lot of them out there cause they're not doing much. They're not making a big difference in the world, but the grabby aliens by definition are the ones you would see. We don't know exactly what they do with where they went but the idea is they're in some sort of competitive world where each part of them is trying to grab more stuff and do something with it. And almost surely whatever is the most competitive thing to do with all the stuff they grab, isn't to leave it alone the way it started, right? So we humans, when we go around the earth and use stuff, we change it. We would turn a forest into a farmland, turn a harbor into a city. So the idea is aliens would do something with it. And so we're not exactly sure what it would look like, but it would look different. So somewhere in the sky, we would see big spheres of different activity where things had been changed because they had been there. </s><s>[INST] Expanding spheres. Right. So as you expand, you aggressively interact and change the environment. And so the word grabby versus loud, you're using them sometimes synonymously, sometimes not. Grabby to me is a little bit more aggressive. What does it mean to be loud? What does it mean to be grabby? What's the difference? And loud in what ways? A visual, is it sound? Is it some other physical phenomena like gravitational waves? What are you using this kind of in a broad philosophical sense? Or there's a specific thing that it means to be loud [/INST] in this universe of ours. My co-authors and I put together a paper with a particular mathematical model. And so we use the term grabby aliens to describe that more particular model. And the idea is it's a more particular model of the general concept of loud. So loud would just be the general idea </s><s>[INST] that they would be really obvious. So grabby is the technical term. Is it in the title of the paper? [/INST] It's in the body. The title is actually about loud and quiet. So the idea is there's, you want to distinguish your particular model of things from the general category of things everybody else might talk about. </s><s>[INST] So that's how we distinguish. So the idea paper title is, if loud aliens explain human earlyness, quiet aliens are also rare. If life on earth, God, this is such a good abstract. If life on earth had to achieve and hard steps to reach humanity's level, then the chance of this event rose as time to the end to power. So we'll talk about power, we'll talk about linear increase. So what is the technical definition of grabby? How do you envision grabbyness? And why are, in contrast with humans, why aren't humans grabby? So like, where's that line? Is it well-definable? [/INST] What is grabby and what is non-grabby? We have a mathematical model of the distribution of advanced civilizations, i.e. aliens in space and time. That model has three parameters and we can set each one of those parameters from data and therefore we claim this is actually what we know about where they are in space-time. So the key idea is they appear at some point in space-time and then after some short delay, they start expanding and they expand at some speed. And the speed is one of those parameters. That's one of the three and the other two parameters are about how they appear in time, that is they appear at random places and they appear in time according to a power law and that power law has two parameters and we can fit each of those parameters to data. And so then we can say, now we know. We know the distribution of advanced civilizations in space and time. So we are right now a new civilization and we have not yet started to expand, but plausibly we would start to do that within say 10 million years of the current moment. That's plenty of time. And 10 million years is a really short duration in the history of the universe. So we are at the moment, a sort of random sample of the kind of times at which an advanced civilization might appear because we may or may not become grabby, but if we do, we'll do it soon. And so our current date is a sample and that gives us one of the other parameters. The second parameter is the constant in front of the power law </s><s>[INST] and that's arrived from our current date. So power law, what is the N in the power law? That's the more complicated thing to explain. [/INST] Right, that's the more complicated thing to explain. Advanced life appeared by going through a sequence of hard steps. So starting with very simple life and here we are at the end of this process at pretty advanced life. And so we had to go through some intermediate steps such as sexual selection, photosynthesis, multi-cellular animals and the idea is that each of those steps was hard. Evolution just took a long time searching in a big space of possibilities to find each of those steps. And the challenge was to achieve all of those steps by a deadline of when the planets would no longer host a simple life. And so Earth has been really lucky compared to all the other billions of planets out there and that we managed to achieve all these steps in the short time of the five billion years that Earth can support simple life. </s><s>[INST] So not all steps, but a lot of them because we don't know how many steps there are before you start the expansion. So these are all the steps from the birth of life [/INST] to the initiation of major expansion of them. Right, so we're pretty sure that it would happen really soon so that it couldn't be the same sort of a hard step as the last ones in terms of taking a long time. So when we look at the history of Earth, we look at the durations of the major things that have happened that suggest that there's roughly say six hard steps that happened, say between three and 12 and that we have just achieved the last one that would take a long time. Which is? Well, we don't know, but whatever it is, </s><s>[INST] we've just achieved the last one. Are we talking about humans or aliens here? So let's talk about some of these steps. So Earth is really special in some way. We don't exactly know the level of specialness. We don't really know which steps were the hardest or not because we just have a sample of one. But you're saying that there's three to 12 steps that we have to go through to get to where we are that are hard steps, hard to find by something that took a long time and is unlikely. There's a lot of ways to fail. [/INST] There's a lot more ways to fail than to succeed. So let's talk about some of these steps. The first step would be sort of the very simplest form of life of any sort. And then we don't know whether that first sort is the first sort that we see in the historical record or not, but then some other steps are say the development of photosynthesis, the development of sexual reproduction. There's the development of eukaryote cells, which are certain kind of complicated cell that seems to have only appeared once. And then there's multicellularity that is multiple cells coming together to large organisms like us. And in this statistical model of trying to fit all these steps into a finite window, the model actually predicts that these steps could be of varying difficulties, that is they could each take different amounts of time on average, but if you're lucky enough that they all appear at a very short time, then the durations between them will be roughly equal. And the time remaining leftover in the rest of the window will also be the same length. So we at the moment have roughly a billion years left on earth until simple life like us would no longer be possible. Life appeared roughly 400 million years after the very first time when life was possible at the very beginning. So those two numbers right there </s><s>[INST] give you the rough estimate of six hard steps. Just to build up an intuition here. So we're trying to create a simple mathematical model of how life emerges and expands in the universe. And there's a section in this paper, how many hard steps, question mark. Right. The two most plausibly diagnostic earth durations seem to be the one remaining after now before earth becomes uninhabitable for complex life. So you estimate how long earth lasts, how many hard steps, there's windows for doing different hard steps. And you can sort of like queuing theory and mathematically estimate of like the solution or the passing of the hard steps or the taking of the hard steps. Sort of like coldly mathematical look if life, pre expansionary life requires N number of steps? What is the probability of taking those steps on an earth that lasts a billion years or two billion years or five billion years or 10 billion years. When you say solving for e using the observed durations of 1.1 and 0.4 then gives e values of 3.9 and 12.5 range 5.7 to 26 suggesting a middle estimate of at least six. That's where you said six hard steps just to get to where we are. Right. [/INST] We started at the bottom now we're here and that took six steps on average. The key point is on average these things on any one random planet would take trillions or trillions of years, just a really long time. We're really lucky that they all happened really fast in a short time before our window closed and the chance of that happening in that short window goes as that time period to the power of the number of steps. That was where the power we talked about before came from. That means in the history of the universe we should overall roughly expect advanced life to appear as a power law in time so that very early on there was very little chance of anything appearing and then later on as things appear other things are appearing somewhat closer to them in time because they're all going as this power law. </s><s>[INST] What is time? Time is a power law. [/INST] Can we for people who are not math inclined can you describe what a power law is? Say the function x is linear and x squared is quadratic so it's the power of two. If we make x to the three that's cubic or the power of three and so x to the sixth is the power of six and so we'd say life appears in the universe on a planet like Earth in that proportion to the time that it's been, you know, ready for life to appear and that </s><s>[INST] over the universe in general it'll appear at roughly a power law like that. What is the x, what is n? Is it the number of hard steps? Yes, the number of hard steps. So that's the idea. Okay, so it's like if you're gambling and you're doubling up every time this is the probability you just keep winning. So it gets very unlikely very quickly and so we're the result of this unlikely chain of successes. [/INST] So that's the idea. It's actually a lot like cancer. So the dominant model of cancer in an organism like each of us is that we have all these cells and in order to become cancerous a single cell has to go through a number of mutations and these are very unlikely mutations and so any one cell is very unlikely to have any have all these mutations happen by the time your life spans over but we have enough cells in our body that the chance of any one cell producing cancer by the end of your life is actually pretty high, more like 40%. And so the chance of cancer appearing in the life of your lifetime also goes as a power law, this power of the number of mutations that's required for anyone selling your body </s><s>[INST] to become cancerous. [/INST] This is the longer you live, the likely you are to have cancer cells. And the power is also roughly six. That is, the chance of you getting cancer is roughly the power of six of the time you've been since you were born. </s><s>[INST] It is perhaps not lost on people that you're comparing power laws of the survival or the [/INST] arrival of the human species to cancerous cells. The same mathematical model, but of course we might have a different value assumption about the two outcomes. </s><s>[INST] But of course, from the point of view of cancer, some are similar. From the point of view of cancer, it's a win-win, we both get to thrive, I suppose. It is interesting to take the point of view of all kinds of life forms on Earth, viruses of bacteria. They have a very different view. It's like the Instagram channel, Nature is Metal. The ethic under which nature operates doesn't often coincide, correlate with human morals. [/INST] It seems cold and machine-like in the selection process that it performs. I am an analyst, I'm a scholar, an intellectual, and I feel I should carefully distinguish predicting what's likely to happen and then evaluating or judging what I think would be better to happen. And it's a little dangerous to mix those up too closely because then we can have wishful thinking. And so I try typically to just analyze what seems likely to happen regardless of whether I like it or whether we do anything about it. And then once you see a rough picture of what's likely to happen, if we do nothing, then we can ask, well, what might we prefer? And ask, where could the levers be to move it at least a little toward what we might prefer, and that's a useful... But often, doing that just analysis of what's likely to happen if we do nothing offends many people. they find that dehumanizing or cold or metal, as you say, to just say, well, this is what's likely to happen. And it's not your favorite, sorry, but maybe we can do something, </s><s>[INST] but maybe we can't do that much. Your favorite, sorry, but. This is very interesting that the cold analysis, whether it's geopolitics, whether it's medicine, whether it's economics, sometimes misses some very specific aspect of human condition. Like for example, when you look at a doctor and the act of a doctor helping a single patient, if you do the analysis of that doctor's time and cost of the medicine or the surgery or the transportation of the patient, this is the Paul Farmer question. Is it worth spending 10, 20, $30,000 on this one patient? When you look at all the people that are suffering in the world, that money could be spent so much better. And yet, there's something about human nature that wants to help the person in front of you, and that is actually the right thing to do, despite the analysis. And sometimes when you do the analysis, you, there's something about the human mind that allows you to not take that leap that irrational leap to act in this way, that the analysis explains it away. Well, it's like, for example, the US government, the DOT, Department of Transportation, puts a value of, I think, $9 million on a human life. And the moment you put that number on a human life, you can start thinking, well, okay, I can start making decisions about this or that, and with a sort of cold economic perspective, and then you might lose, you might deviate from a deeper truth of what it means to be human somehow. So you have to dance, because then if you put too much weight on the anecdotal evidence on these kinds of human emotions, then you're going to lose, you could also probably more likely deviate from truth. But there's something about that cold analysis. Like I've been listening to a lot of people coldly analyze wars. War in Yemen, war in Syria, Israel, Palestine, war in Ukraine, and there's something lost when you do a cold analysis of why something happened. When you talk about energy, talking about sort of conflict, competition over resources, when you talk about geopolitics, sort of models of geopolitics of why a certain war happened, you lose something about the suffering that happens. I don't know. It's an interesting thing because you're both, you're exceptionally good at models in all domains, literally, but also there's a humanity to you. So it's an interesting dance. I don't know if you can comment on that dance. [/INST] Sure, it's definitely true as you say, that for many people, if you are accurate in your judgment of say, for a medical patient, right? What's the chance that this treatment might help? And what's the cost? And compare those to each other. And you might say, this looks like a lot of cost for a small medical gain. And at that point, knowing that fact that might take the air out of your sales, you might not be willing to do the thing that maybe you feel is right anyway, which is still to pay for it. And then somebody knowing that might want to keep that news from you, not tell you about the low chance of success or the high cost in order to save you this tension, this awkward moment where you might fail to do what they and you think is right. But I think the higher calling, the higher standard to hold you to, which many people can be held to, is to say, I will look at things accurately. I will know the truth. And then I will also do the right thing with it. I will be at peace with my judgment about what the right thing is in terms of the truth. I don't need to be lied to in order to figure out what the right thing to do is. And I think if you do think you need to be lied to in order to figure out what the right thing to do is you're at a great disadvantage because then people will be lying to you, you will be lying to yourself and you won't be as effective </s><s>[INST] at achieving whatever good you were trying to achieve. but getting the data, getting the facts is step one, not the final step. Absolutely. So it's a, I would say having a good model, getting the good data is step one and it's a burden because you can't just use that data to arrive at sort of the easy, convenient thing. You have to really deeply think about what is the right thing. You can't use the, so the dark aspect of data, of models is you can use it to excuse the way actions that are unethical. [/INST] You can use data to basically excuse the way anything. But not looking at data lets you excuse yourself to pretend and think that you're doing good when you're not. </s><s>[INST] Exactly. But it is a burden. It doesn't excuse you from still being human and deeply thinking about what is right. That very kind of gray area, that very subjective area. That's part of the human condition. But let us return for time to aliens. So you started to define sort of the model, the parameters of grabbiness. Right. Or the, as we approach grabbiness. [/INST] So what happens? So again, there was three parameters. Yes. There's the speed at which they expand. There's the rate at which they appear in time. And that rate has a constant and a power. So we've talked about the history of life on Earth suggests that power is around six, but maybe three to 12. We can say that constant comes from our current date, sort of sets the overall rate. And the speed, which is the last parameter, comes from the fact that when we look in the sky, we don't see them. So the model predicts very strongly that if they were expanding slowly, say 1% of the speed of light, our sky would be full of vast spheres that were full of activity. That is, at a random time when a civilization is first appearing, if it looks out into its sky, it would see many other grabby alien civilizations in the sky, and they would be much bigger than the full moon. They'd be huge spheres in the sky. And they would be visibly different. We don't see them. </s><s>[INST] Can we pause for a second? Okay. There's a bunch of hard steps that Earth had to pass to arrive at this place we are currently, which we're starting to launch rockets out into space. We're kind of starting to expand. A bit. Right. Very slowly, okay. But this is like the birth. If you look at the entirety of the history of Earth, [/INST] we're now at this precipice of expansion. We could. We might not choose to, but if we do, </s><s>[INST] we will do it in the next 10 million years. 10 million, wow. Time flies when you're having fun. [/INST] 10 million's a short time on the cosmological scale. So that is, it might be only a thousand. But the point is, even if it's up to 10 million, that hardly makes any difference to the model. So I might as well give you 10 million. </s><s>[INST] This makes me feel, I was so stressed about planning what I'm gonna do today. And now- Right, you got plenty of time. Plenty of time. Just need to be generating some offspring quickly here. Okay. So, and there's this moment. There's 10 million year gap or window when we start expanding. And you're saying, okay, so this is an interesting moment where there's a bunch of other alien civilizations that might, at some history of the universe, arrived at this moment where here, they passed all the hard steps. There's a model for how likely it is that that happens. And then they start expanding. And you think of an expansion as almost like a sphere. Right. That's when you say speed, we're talking about the speed of the radius growth. Exactly. The surface, how fast the surface is. How fast, okay. And so you're saying that there is some speed for that expansion, average speed. And then we can play with that parameter. And if that speed is super slow, then maybe that explains why we haven't seen anything. If it's super fast, [/INST] Well, it would be as the slow would create the puzzle. It's slow predicts we would see them, but we don't see them. Okay. And so the way to explain that is that they're fast. So the idea is if they're moving really fast, </s><s>[INST] then we don't see them until they're almost here. And, okay, this is counterintuitive. All right, hold on a second. So I think this works best when I say a bunch of dumb things. Okay. And then, you elucidate the full complexity and the beauty of the dumbness. Okay, so there's the spheres out there in the universe that are made visible because they're sort of using a lot of energy. So, they're generally in a lot of light stuff, but they're changing things. [/INST] And change would be visible. Like, they're changing the way off. it would take apart stars, rearrange them, restructure galaxies. </s><s>[INST] They would do big, big, huge stuff, big, big, huge stuff. Okay, if they're expanding slowly, we would see a lot of them because the universe is old, [/INST] is old enough to where we would see all these things. We're assuming we're just typical, maybe at the 50th percentile of them. So like half of them have appeared so far, the other half will still appear later. And the math of our best estimate is that they appear roughly once per million galaxies, and we would meet them in roughly a billion years </s><s>[INST] if we expand it out to meet them. So we're looking at a grab the aliens model 3D sim, right? What's this, that's the actual name of the video. What, by the time we get to 13.8 billion years, the fun begins. Okay, so this is, we're watching a three dimensional sphere rotating, I presume that's the universe, and then grab the aliens are expanding and filling that universe with all kinds of fun. Pretty soon, it's all full. It's full. So that's how the grab the aliens come in contact, first of all, with other aliens, and then with us humans. The following is a simulation of the grab the aliens model of alien civilizations. Civilizations are born that expand outwards at constant speed. A spherical region of space is shown. By the time we get to 13.8 billion years, this sphere will be about 3000 times as wide as the distance from the Milky Way to Andromeda. Okay, this is fun. It's huge. Okay, it's huge. All right, so why don't we see, we're one little tiny, tiny, tiny, tiny dot in that giant, giant sphere. [/INST] Why don't we see any of the grab the aliens? Depends on how fast they expand. So you could see that if they expanded at the speed of light, you wouldn't see them until they were here. So like out there, if somebody is destroying the universe with a vacuum decay, there's this doomsday scenario where somebody somewhere could change the vacuum of the universe and that would expand at the speed of light and basically destroy everything it hit. But you'd never see that until I got here cause it's expanding at the speed of light. If you're expanding really slow, then you see it from a long way off. So the fact we don't see anything in the sky tells us they're expanding fast, say over a third the speed of light. And that's really, really fast. But that's what you have to believe if we look out and you don't see anything. Now you might say, well, maybe I just don't want to believe this whole model. Why should I believe this whole model at all? And our best evidence why you should believe this model is our early date. We are right now and almost 14 million years into the universe on a planet around a star that's roughly 5 billion years old, but the average star out there will last roughly 5 trillion years, that is a thousand times longer. And remember that power law, it says that the chance of advanced life appearing on a planet goes as the power of sixth of the time. So if a planet lasts a thousand times longer, then the chance of it appearing on that planet, if everything would stay empty at least is a 1000 to the sixth power or 10 to the 18. So, enormous, overwhelming chance that if the universe would just stay set and empty and waiting for advanced life to appear, when it would appear would be way at the end of all these planet lifetimes. That is the long planets near the end of the lifetime, trillions of years into the future. But we're really early compared to that. And our explanation is, at the moment, as you saw in the video, the universe is filling up in roughly a billion years. It'll all be full. And at that point, it's too late for advanced life to show up. So, you had to show up now before that deadline. </s><s>[INST] Okay. Can we break that apart a little bit? Okay. Or linger on some of the things you said. So, with the power law, the things we've done on Earth, the model you have says that it's [/INST] very unlikely, like we're lucky SOBs. Is that mathematically correct to say? We're crazy early, that is. When early means like... </s><s>[INST] In the history of the universe. In the history of the... Okay. So, given this model, how do we make sense of that? If we're super... Can we just be the lucky ones? [/INST] Well, 10 to the 18 lucky, you know, how lucky do you feel? So, you know, that's pretty lucky, right? You know, 10 to the 18 is a billion billion. </s><s>[INST] So, then, if you were just being honest and humble, that that means... What does that mean? [/INST] It means one of the assumptions that calculated this crazy early must be wrong. That's what it means. So, the key assumption we suggest is that the universe would stay empty. So, most life would appear like a thousand times longer later than now if everything would stay empty waiting for it to appear. What is non-empty? So, the gravity aliens are filling the universe right now, roughly at the moment, they've filled half of the universe and they've changed it. And when they fill everything, it's too late for stuff like us to appear. But wait, hold on a second. </s><s>[INST] That's how... Did anyone help us get lucky? [/INST] If it's so difficult, what... How do... So, it's like cancer, right? There's all these cells, each of which randomly does or doesn't get cancer, and eventually some cell gets cancer and, you know, we were one of those. </s><s>[INST] But hold on a second. Okay. But we got it early. [/INST] Early compared to the prediction with an assumption that's wrong. That's... So, that's how we do a lot of, you know, theoretical analysis. </s><s>[INST] You have a model that makes a prediction that's wrong, then that helps you reject that model. Okay. Let's try to understand exactly where the wrong is, so the assumption is that the universe is empty. Stays empty. [/INST] Stays empty. And waits until this advanced life appears in trillions of years. That is, if the universe would just stay empty, if there was just, you know, nobody else out there, then when you should expect advanced life to appear, if you're the only one in the universe, when should you expect to appear? </s><s>[INST] you should expect to appear trillions of years in the future, you know? Yeah, I see. Right, right. So this is a very sort of nuanced mathematical assumption. I don't think we can intuit it cleanly with words. But if you assume that you're just waiting, the universe stays empty and you're waiting for one life civilization to pop up, then it's gonna, it should happen very late, much later than now. And if you look at Earth, the way things happen on Earth, it happened much, much, much, much, much earlier than it was supposed to, according to this model, if you take the initial assumption, therefore, you can say while the initial assumption of the universe staying empty is very unlikely. [/INST] Right, right, right. And the other alternative theory is the universe is filling up and will fill up soon. And so we are typical for the origin data, things that can appear before </s><s>[INST] the deadline before the okay it's filling up so why don't we see anything if it's filling up because they're expanding really fast close to the speed of light exactly so we will only see it when it's here almost here okay uh what are the ways in which we might see a quickly expanding this is both exciting and terrifying it is terrifying it's like watching a truck [/INST] like driving at you at 100 miles an hour and uh right so we would see spheres in the sky at least one sphere in the sky growing very rapidly and like very rapidly right yes very </s><s>[INST] rapidly though we're not so there's there's you know different because we were just talking about [/INST] 10 million years this would be you might see it 10 million years in advance coming i mean you You still might have a long warning. Or the universe is 14 billion years old, the typical origin times of these things are spread over several billion years. So the chance of one originating at a, you know, very close to you in time is very low. So they still might take millions of years from the time you see it, from the time it gets here. You want a million years a year to be terrified this past sphere coming at you. </s><s>[INST] This past sphere... But coming at you very fast. So if they're a traveling [/INST] close to the speed of light, but they're coming from a long way away. So remember the rate at which they appear is one per million galaxies. Right. So they're, they're roughly a hundred galaxies away. </s><s>[INST] I see. So the Delta between the speed of light and their actual travel speed is very [/INST] important, right? </s><s>[INST] So if they're going at say half the speed of light, we'll have a long time then. Yeah. But what if they're traveling exactly at a speed of light? [/INST] Then we see them like, then we wouldn't have much warning, but that's less likely. Well, we can't exclude it. </s><s>[INST] And they could also be somehow traveling fast in the speed of light. [/INST] We can't I think we can't exclude, because if they could go faster than the speed of light, then they would just already be everywhere. So you know, in a universe where you can travel fast on the speed of light, you can go backwards in space time. So anytime you appeared anywhere in space time, you could just fill up everything. Yeah. And so anybody in the future, whoever appeared, they would have been here by now. </s><s>[INST] Can you exclude the possibility that those kinds of aliens aren't already here?" [/INST] Well, we should have a different discussion of that. </s><s>[INST] Okay, so let's actually leave that discussion aside. and understand the grabby alien expansion which is beautiful and fascinating. Okay so there's these giant expanding spheres of alien civilizations. Now when those spheres collide mathematically it's very likely that we're not the first collision of grabby of alien civilizations. I suppose is one way to say it. So there's like the first time the spheres touch each other recognize each other, right. They meet. They recognize each other first before they meet. They see each other coming. They see each other coming and then so there's a bunch of them there's a combinatorial thing where they start seeing each other coming and then there's a third neighbor it's like what the hell and then there's a fourth one. Okay so what is that you think look like. What lessons from human nature, that's the only data we have but can you drop [/INST] So, what can you do? So the story of the history of the universe here is what I would call a living cosmology. So, what I'm excited about in part by this model is that it lets us tell a story of cosmology where there are actors who have agendas. So most ancients peoples, they had cosmologies, stories they told about where the universe came from and where it's going and what's happening out there. And there are stories they like to have agents and actors, gods or something out there doing things. our favorite cosmology is dead, kind of boring. We're the only activity we know about or see, and everything else just looks dead and empty. But this is now telling us, no, that's not quite right. At the moment, the universe is filling up, and in a few billion years, it'll be all full. </s><s>[INST] And from then on, the history of the universe will be the universe full of aliens, aliens. Yeah, so that's a really good reminder, a really good way to think about cosmologies. We're surrounded by a vast darkness, and we don't know what's going on in that darkness until the light from whatever generate lights arrives here. So we kind of, yeah, we look up at the sky, okay, they're stars, oh, they're pretty, but you don't think about the giant expanding spheres [/INST] of alien! Right, because you don't see them, but now our date because you don't see them, but now, our date. Looking at the clock, if you're clever, the clock tells you. So I like the analogy with the Ancient Greeks. You might think that an Ancient Greek, you know, staring at the universe couldn't possibly tell how far away the sun was, or how far away the moon is, or how big the Earth is. That all you can see is just big things in the sky. You can't tell it, but they were clever enough actually to be able to figure out the size of the Earth and the distance to the Moon and the sun and the size of the moon and sun. That is, they could figure those things out, actually, by being clever enough, and so similarly we can actually figure out where are the aliens out there in space-time, by being clever about the few things we can see, one of which is our current date. And, so now that you have this living cosmology, we can tell the story that the universe starts out empty, and then at some point things like us appear very primitive, and then some of those stop being quiet and expand. And then for a few billion years they expand, and then they meet each other and then for the next hundred billion years they commune with each other...as the usual models of cosmology say that in roughly a hundred- hundred and 50 billion years the expansion of the universe will happen so much that all you'll have is left is some galaxy clusters and they that are sort of disconnected from each other. But before then for the next hundred million years...hundred billion years excuse me...um...they will interact. There will be this community of all the grabby alien civilizations and each one of them will hear about and even meet thousands of others. And we might hope to join them someday and become part of that community. That's an interesting thing to aspire to. </s><s>[INST] Yes, interesting is an interesting word. Is the universe of alien civilizations defined by war as much or more than war-defined human history? [/INST] I would say it's defined by competition and then the question is how much competition implies war. So up until recently, competition defined life on Earth. Competition between species and organisms and among humans, competitions among individuals and communities, and that competition often took the form of war in the last 10,000 years. Yes. Many people now are hoping or even expecting to sort of suppress and end competition in human affairs. They regulate business competition, they prevent military competition and that's a future I think a lot of people will like to continue and strengthen. People will like to have something close to world government or world governance or at least a world community and they will like to suppress war and many forms of business and personal competition over the coming centuries. And they may like that so much that they prevent interstellar colonization, which would become the end of that era that is interstellar colonization would just return severe competition to human or our descendant affairs. And many civilizations may prefer that and ours may prefer that. But if they choose to allow interstellar colonization, they will have chosen to allow competition to return with great force. That is, there's really not much of a way to centrally govern a rapidly expanding sphere of civilization. And so, I think one of the most solid things we can predict about gravity aliens is they have accepted competition, and they have internal competition, and therefore they have the potential for competition when they meet each other at the borders. But whether that's military competition is more of an open question. </s><s>[INST] So, military meaning physically destructive. Right. So, there's a lot to say there. So, one idea that you kind of proposed is progress might be maximized through competition, through some kind of healthy competition, some definition of healthy. So, like, constructive, not destructive competition. So, like, we would likely, gravity alien civilizations would be likely defined by competition because they can expand faster. Because competition allows [/INST] innovation and sort of the battle of ideas. The way I would take the logic is to say, you know, competition just happens if you can't coordinate to stop it. And you probably can't </s><s>[INST] coordinate to stop it in an expanding interstellar wave. So, competition is a fundamental force [/INST] in the universe. It has been so far, and it would be within an expanding gravity alien civilization, but we today have the chance, many people think and hope, of greatly controlling and limiting competition within our civilization for a while. And that's an interesting choice, whether to allow competition to sort of regain its full force or whether to </s><s>[INST] suppress and manage it. Well, one of the open questions that has been raised in the past less than 100 years is whether our desire to lessen the destructive nature of competition, or the destructive kind of competition, will be outpaced by the destructive power of our weapons. Sort of, if nuclear weapons and weapons of that kind become more destructive than our desire for peace, then all it takes is one asshole at the party to ruin the party. [/INST] It takes one asshole to make a delay, but not that much of a delay on the cosmological scales we're talking about. So, you could still party on. Even a vast nuclear war, if it happened here right now on Earth, could still party on, it would not kill all humans. It certainly wouldn't kill </s><s>[INST] all life, and so human civilization would return within 100,000 years. So, all the history of the history of atrocities, and if you look at the Black Plague, which is not human-caused atrocities or whatever. There are a lot of military atrocities in history. Absolutely. In the 20th century, those challenges to think about human nature, but the cosmic scale of time and space, they do not stop the human spirit, essentially. The humanity goes on. Through all the atrocities, [/INST] it goes on. Most likely. There are a lot of atrocities in history, most likely. So, even a nuclear war isn't enough to destroy us or to stop our potential from expanding, but we could institute a regime of global governance, that limited competition, including military and business competition of sorts, and that could prevent our expansion. </s><s>[INST] Of course, to play devil's advocate, global governance is centralized power. Power corrupts, and absolute power corrupts, absolutely. One of the aspects of competition that's been very productive is not letting any one person, any one country, any one center of power become absolutely powerful, because that's another lesson, is it seems to corrupt. There's something about ego in the human mind that seems to be corrupted by power. So, when you say global [/INST] governance, that terrifies me more than the possibility of war. I think people will be less terrified than you are right now, and let me try to paint the picture from their point of view. This isn't my point of view, but I think it's going to be a widely shared point of view. This is two devil's advocates arguing, two devils. So, for the last half century and into the continuing future, we actually have had a strong elite global community that shares a lot of values and beliefs, and has created a lot of convergence in global policy. So, if you look at electromagnetic spectrum, or medical experiments, or pandemic policy, or nuclear power energy, or regulating airplanes, or just in a wide range of area. In fact, the world has very similar regulations and rules everywhere, and it's not a coincidence because they are part of a world community where people get together at places like Davos, etc., where world elites want to be respected by other world elites, and they have a convergence of opinion, and that produces something like global governance, but without a global center. This is sort of what human mobs or communities have done for a long time. That is, humans can coordinate together on shared behavior without a center by having gossip and reputation within a community of elites, and that is what we have been doing and are likely to do a lot more of. So, for example, one of the things that's happening, say, with the war in Ukraine is that this world community of elites has decided that they disapprove of the Russian invasion and they are coordinating to pull resources together from all around the world in order to oppose it, and they are proud of that, sharing that opinion and their feel that they are morally justified in their stance there. And that's the kind of event that actually brings world elite communities together, where they come together and they push a particular policy and position that they share and that they achieve successes and the same sort of passion animates global elites with respect to say global warming. Or global poverty and other sorts of things and they are in fact making progress on those sorts of things through shared global community of elites. And in some sense they are slowly walking toward global governance, slowly strengthening various world institutions of governance. But cautiously, carefully watching out for the possibility of a single power that might corrupt it, I think a lot of people </s><s>[INST] over the coming centuries will look at that history and like it. It's an interesting thought, and thank you for playing that devil's advocate there, but I think the elites too easily lose touch of the morals that the best of human nature and power corrupts. [/INST] Sure, but if their view is the one that determines what happens, their view may still end up </s><s>[INST] there even if you or I might criticize it from that point of view. From a perspective of minimizing human suffering, elites can use topics of the war in Ukraine and climate change and all of those things to sell an idea to the world and with this regard to the amount of suffering it causes, their actual actions. So like you can tell all kinds of narratives, that's the way propaganda works, Hitler really sold the idea that everything Germany is doing is either it's the victim is defending itself against the cruelty of the world and is actually trying to bring out about a better world. So every power center thinks they're doing good. And so this is the positive of competition, of having multiple power centers, this kind of gathering of elites makes me very, very, very nervous, the dinners, the meetings in the closed rooms. I don't know. [/INST] But remember, we talked about separating our cold analysis of what's likely or possible from what we prefer. And so this isn't exactly enough time for that. We might say, I would recommend we don't go this route of a strong world governance. And because I would say it'll preclude this possibility of becoming Rabbi aliens, of filling the nearest million galaxies for the next billion years with vast amounts of activity and interest and value of life out there, that's the thing we would lose by deciding that we wouldn't expand, that we would stay here and keep our comfortable shared governance. </s><s>[INST] Wait, you think that global governance makes it more likely or less likely that we expand out into the universe? [/INST] Less. So okay. This is the key point. </s><s>[INST] Great. Right. So screw the elites. [/INST] Wait, do we want to expand? So again, I want to separate my neutral analysis from my evaluation and say, first of all, I have an analysis that tells us this is a key choice that we will face and that it's key choice other aliens have faced out there. And it could be that only one in 10 or only one in 100 civilizations chooses to expand and the rest of them stay quiet. And that's how it goes out there. And we face that choice too, and it'll happen sometime in the next 10 million years, maybe the next thousand. But the key thing to notice from our point of view is that even though you might like our global governance, you might like the fact that we've come together and we no longer have massive wars and we no longer have destructive competition and that we could continue that, the cost of continuing that would be to prevent interstellar colonization. Because once you allow interstellar colonization, then you've lost control of those colonies and whatever they change in to, they could come back here and compete with you back here as a result of having lost control. And I think if people value that global governance and the global community and regulation and </s><s>[INST] all the things it can do enough, they would then want to prevent interstellar colonization. I want to have a conversation with those people. I believe that both for humanity, for the good of humanity, for what I believe is good in humanity, and for expansion, exploration, innovation, distributing the centers of power is very beneficial. So this whole meeting of elites, and I've been very fortunate to meet quite a large number of elites. They make me nervous, because it's easy to lose touch of reality. I'm nervous about that in myself, to make sure that you never lose touch as you get sort of older, wiser, you know, how you generally get like disrespectful of kids, kids these days. [/INST] No, the kids are, they have cultures. Okay, but I think you should hear a stronger case for their position. So I'm gonna play for the elites. Yes, well, for the limiting of expansion and for the regulation of behavior. </s><s>[INST] So, yes, well, for the- Okay, can I link on that? Sure. So you're saying those two are connected. So the human civilization and alien civilizations come to a crossroads. They have to decide, do we want to expand or not? And connected to that, do we want to give a lot of power to a central elite? Do we want to distribute the power centers, which is naturally connected to the expansion? [/INST] When you expand, you distribute the power. Sure. If, say over the next thousand years, we fill up the solar system, right? We go out from earth and we colonize Mars and we change a lot of things. Within a solar system, still everything is within reach. That is, if there's a rebellious colony around Neptune, you can throw rocks at it and smash it and then teach them discipline, okay? A central- How did that work for the bird? A central control over the solar system is feasible. Yes. But once you let it escape the solar system, it's no longer feasible. But if you have a solar system that doesn't have a central control, maybe broken into a thousand different political units in the solar system, then any one part of that that allows interstellar colonization, and it happens, that is interstellar colonization happens when only one party chooses to do it and is able to do it. And that's what it is there for. So we can just say in a world of competition, if interstellar colonization is possible, It will happen, and then competition will continue, and that will sort of ensure the </s><s>[INST] continuation of competition into the indefinite future. How did that work for the Great Center? Essential control. And competition, we don't know, but competition can take violent forms [/INST] and conductive forms. And the case I was going to make is that I think one of the things that most scares people about competition is not just that it creates Holocaust and death on massive scales, is that it's likely to change who we are and what we value. </s><s>[INST] Yes. So this is the other thing with power. As we grow, as human civilization grows, becomes [/INST] multiplanetary, multi-solar system potentially, how does that change us, do you think? I think the more you think about it, the more you realize it can change us a lot. So, first of all- This is pretty dark, by the way. Well, it's just honest. Right. Well, I'm trying to agree there, but I think the first thing you should say, if you look at history, just human history over the last 10,000 years, if you really understood what people were like a long time ago, you'd realize they were really quite different. Ancient cultures created people who were really quite different. Most historical fiction lies to you about that. It often offers you modern characters in an ancient world, but if you actually study history you will see just how different they were and how differently they thought and they've changed a lot many times and they've changed a lot across time. So I think the most obvious prediction about the future is even if you only have the mechanisms of change we've seen in the past, you should still expect a lot of change in the future. But we have a lot bigger mechanisms for change in the future than we had in the past. So I have this book called The Age of M, Work, Love, and Life, and Robots Rule the Earth, and it's about what happens if brain emulations become possible. So a brain emulation is where you take an actual human brain and you scan it and find spatial and chemical detail to create a computer simulation of that brain. And then those computer simulations of brains are basically citizens in a new world. They work and they vote and they fall in love and they get mad and they lie to each other, and this is a whole new world. And my book is about analyzing how that world is different than our world – basically using competition as my key lever of analysis, that is, if that world remains competitive that I can figure out how they change in that world, what they do differently than we do, and it's very different. And it's different in ways that are shocking sometimes to many people in ways some people don't like. I think it's an okay world, but I have to admit it's quite different. And that's just one technology. If we add, you know, dozens more technologies, changes into the future, you know, we should just expect it's possible to become very different than who we are. In the space of all possible minds, our minds are a particular architecture, a particular structure, a particular set of habits— And they are only one piece in a vast space of possibilities. The space of possible minds is really huge. </s><s>[INST] So let's linger on the space of possible minds for a moment just to sort of humble ourselves how peculiar our peculiarities are. like the fact that we like a particular kind of sex and the fact that we eat food through one hole and poop through another hole. And that seems to be a fundamental aspect of life. It's very important to us. And that life is finite in a certain kind of way. We have a meat vehicle. So death is very important to us. I wonder which aspects are fundamental or would be common throughout human history and also throughout, sorry, throughout history of life on Earth and throughout other kinds of lives. Like what is really useful? You mentioned competition, [/INST] seems to be a one fundamental thing. I've tried to do analysis of where our distant descendants might go in terms of what are robust features we could predict about our descendants. So again, I have this analysis of sort of the next generation, so the next era after ours. If you think of human history as having three eras so far, right? There was the forager era, the farmer era and the industry era. Then my attempt in age of M is to analyze the next era after that. And it's very different, but of course there could be more and more errors after that. So, you know, analyzing a particular scenario and thinking it through is one way to try to see how different the future could be, but that doesn't give you some sort of like sense of what's typical. But I have tried to analyze what's typical. And so I have two predictions, I think I can make pretty solidly. One thing is that we know at the moment that humans discount the future rapidly. So we discount the future in terms of caring about consequences, roughly a factor of two per generation. And there's a solid evolutionary analysis why sexual creatures would do that. Because basically your descendants only share half of your genes </s><s>[INST] and your descendants are a generation away. So- [/INST] So we only care about our grandchildren. You know, basically that's a factor of four, later. Yeah. Because you know, it's later. So this actually explains typical interest rates in the economy, that is interest rates are greatly influenced by our discount rates. And we basically discount the future by a factor of two per generation. But that's a side effect of the way our preferences evolved as sexually selected creatures. We should expect that in the longer run creatures will evolve who don't discount the future. they will care about the long run and they will therefore not neglect the wrong. So for example, for things like global warming or things like that, at the moment many commenters are sad that basically ordinary people don't seem to care much, market prices don't seem to care much and more ordinary people, it doesn't really impact them much because humans don't care much about the long-term future. But, and futureists find it hard to motivate people and to engage people about the long-term future because they just don't care that much. But that's a side effect of this particular way that our preferences evolved about the future. And so in the future, they will neglect the future less. And that's an interesting thing that we can predict robustly. Eventually, maybe as few centuries, maybe longer, </s><s>[INST] eventually our descendants will care about the future. Can you speak to the intuition behind that? [/INST] Is it useful to think more about the future? Right, if evolution rewards creatures for having many descendants, then if you have decisions that influence how many descendants you have, then that would be good if you made those decisions. But in order to do that, you'll have to care about them. You'll have to care about that future. </s><s>[INST] To push back, that's if you're trying to maximize the number of descendants. But the nice thing about not caring too much about the long-term future is you're more likely to take big risks or you're less risk-averse. And it's possible that both evolution and just life in the universe rewards the risk-takers in the universe. [/INST] Well, we actually have analysis of the ideal risk preferences too. So there's a literature on ideal preferences that evolutions should promote. And for example, there's a literature on competing investment funds and what the managers of those funds should care about in terms of risk, various kinds of risks, and in terms of discount. So managers of investment funds should basically have logarithmic risk, i.e. in shared risk, in correlated risk, but be very risk neutral with respect to uncorrelated risk. So that's a feature that's predicted to happen about individual personal choices in biology and also for investment funds. So that's other things, that's also something we can say about the long run. What correlated and uncorrelated risk? If there's something that would affect all of your descendants, then if you take that risk, you might have more descendants, but you might have zero, and that's just really bad to have zero descendants. But an uncorrelated risk would be a risk that some of your descendants would suffer, but others wouldn't. And then you have a portfolio of descendants and so that portfolio ensures you against problems with any one of them. </s><s>[INST] Oh, I like the idea of portfolio descendants and we'll talk about portfolios with your idea that you briefly mentioned, will return there with E.M., the age of E.M., work, love, and life when robots rule the Earth. E.M., by the way, is emulated minds. [/INST] So this, one of the... </s><s>[INST] M is short for emulations. M is short for emulations, and it's kind of an idea of how we might create artificial minds, [/INST] artificial copies of minds, or human-like intelligences. I have another dramatic prediction I can make about long-term processes. Yes. Which is, at the moment, we reproduce as a result of a hodgepodge of preferences that aren't very well-integrated, but in our ancestral environment, induce us to reproduce. So we have preferences over being sleepy, and hungry, and thirsty, and wanting to have sex, and wanting to be excitement, et cetera, right? Yeah. And so, in our ancestral environment, the packages of preferences that we evolved to have did induce us to have more descendants, And that's why we're here. But those packages of preferences are not a robust way to promote having more descendants. They were tied to our ancestral environment, which is no longer true. So that's one of the reasons we are now having a big fertility decline, because in our current environment, our ancestral preferences are not inducing us to have a lot of kids, which is, from evolution's point of view, a big mistake. We can predict that in the longer run, there will arise creatures who just abstractly know that what they want is more descendants. That's a very robust way to have more descendants, is to have that as your direct preference. </s><s>[INST] First of all, your thinking is so clear, I love it. So mathematical, and thank you for thinking so clear with me and bearing with my interruptions and going on the tangents when we go there. So you're just clearly saying that successful long-term civilizations will prefer to have [/INST] descendants, more descendants. Not just prefer, consciously and abstractly prefer. That is, it won't be the indirect consequence of other preference. It will just be the thing they know they want. There'll be a president, in the future, that says, we must have more sex. </s><s>[INST] We must have more descendants and do whatever it takes to do that. We must go to the Moon and do the other things. Not because they're easy, but because they're hard, but instead of the Moon, let's have lots of sex. But there's a lot of ways to have descendants, right? [/INST] Right, right. So that's the whole point. When the world gets more complicated and there are many possible strategies, it's having that as your abstract preference that will force you to think through those possibilities </s><s>[INST] and pick the one that's most effective. So just to clarify, descendants doesn't necessarily mean the narrow definition of descendants, meaning humans having sex and then having babies. Exactly. So artificial intelligence systems that in whom you instill some capability of cognition and perhaps even consciousness, you can also create through genetics and biology clones of yourself or slightly modified clones, thousands of them. Right. So all kinds of descendants. It could be descendants in the space of ideas too, but somehow we no longer exist in this meat vehicle. It's not just whatever the definition of a lifeform is, you have descendants of those [/INST] lifeforms. Yes, yes and they will be thoughtful about that. They will have thought about what counts as a descendant, and that'll be important to them to have the right concept. So the they there is very interesting included. They are, but the key thing is we're making predictions that I think are somewhat robust about what our distant descendants will be like. Another thing I think that you would automatically accept is they will almost entirely be artificial. And I think that would be the obvious prediction about any aliens we would meet. That is, they would long sense have given up, you know, reproducing biologically. </s><s>[INST] Well, it's all, it's like organic or something. It's all... [/INST] Reel and it's portable. It might be squishy and made out of hydrocarbons, but it would be artificial in the sense of made-in factories with designs on CAD things, right? Factories with scale economy. So the factories we have made on Earth today have much larger scale economies than the factories in our cells. So the factories in our cells are, there are marvels, but they don't achieve very many scale economies. They're tiny little factories. </s><s>[INST] But they're all factories. Yes. [/INST] Factors on top of factories, so everything. </s><s>[INST] The factories that are designed is different than sort of the factories that have evolved. I think the nature of the word design is very interesting. Yep. To uncover there. But let me, in terms of aliens, let me, go, let me analyze your Twitter like it's Shakespeare. Okay. There's a tweet that says, define hello, in quotes, alien civilizations as one that might, in the next million years, identify humans as intelligent and civilized, travel to Earth, and say hello by making their presence and advanced abilities known to us. The next 15 polls, this is a Twitter thread, the next 15 polls ask about such hello aliens. And what these polls ask is your Twitter followers, what they think those aliens would be like, certain particular qualities. So poll number one is, what percent of hello aliens evolved from biological species with two main genders? The popular vote is above 80%. So most of them have two genders. What do you think about that? I'll ask you about some of these, because they're so interesting. It's such an interesting question. It is a fun set of questions. I like fun set of questions. So the genders as we look through evolutionary history, what's the usefulness of that, [/INST] as opposed to having just one or like millions? So there's a question in evolution of life on Earth. There are very few species that have more than two genders. There are some, but they aren't very many. But there's an enormous number of species that do have two genders, much more than one. And so there's a literature on why did multiple genders evolve, and then sort of what's the point of having males and females versus haemaphrodites. So most plants are haemaphrodites. That is, they would mate male, female, but each plant can be either role. And then most animals have chosen to split into males and females. And then they're differentiating the two genders. And there's an interesting set of questions about why that happens. </s><s>[INST] Because you can do selection. You basically have one gender competes for the affection of other, and there's sexual partnership that creates the offspring. So there's sexual selection. It's nice to have... To a party, it's nice to have dance partners, and then each one gets choose based on certain characteristics. And that's an efficient mechanism for adapting to the environment, [/INST] being successfully adopted to the environment. It does look like there's an advantage. If you have males, then the males can take higher variance. And so there can be stronger selection among the males in terms of weeding out genetic mutations because the males have a higher variance </s><s>[INST] in their mating success. Sure, okay. Question number two. What percent of hello aliens evolved from land animals as opposed to plants or ocean slash air organisms? By the way, I did recently see that there's only 10% of species on Earth or in the ocean. So there's a lot more variety on land. There is. It's interesting. So why is that? I don't even, I can't even name to it exactly why that would be. Maybe survival on land is harder [/INST] and so you get a lot on land. The story that I understand is it's about small niches. So speciation can be promoted by having multiple different species. So in the ocean, species are larger. That is, there are more creatures in each species because the ocean environments don't vary as much. So if you're good in one place, you're good in many other places. But on land, and especially in rivers, rivers contain an enormous percentage of the kinds of species on land, you see, because they vary so much from place to place. And so a species can be good in one place and then other species can't really compete because they came from a different place where things are different. So it's a remarkable fact actually that speciation promotes evolution in the long run. That is, more evolution has happened on land because there have been more species on land because each species has been smaller. And that's actually a warning about something or something called rot that I've thought a lot about which is one of the problems with even a world government which is large systems of software today just consistently rot and decay with time and have to be replaced. And that plausibly also is a problem for other large systems including biological systems, legal systems, regulatory systems. And it seems like large species actually don't evolve effectively as small ones do. And that's an important thing to notice about that. And that's actually different from ordinary sort of evolution in economies on Earth in the last few centuries, say. On Earth, the more technical evolution and economic growth happens in larger, integrated cities and nations. But in biology, it's the other way around. More evolution happened </s><s>[INST] in the fragmented species. Yeah, it's such a nuanced discussion because you can also push back in terms of nations and at least companies. It's like large companies seem to evolve less effectively. There is something that, you know, they have more resources, they don't even have better resilience. And when you look at the scale of decades and centuries, [/INST] it seems like a lot of large companies die. But still large economies do better, like large cities grow better than small cities, large integrated economies like the United States </s><s>[INST] of the European Union do better than small fragmented ones. So that's a very interesting long discussion. But so most people, and obviously votes on Twitter, represent the [/INST] absolute objective truth of things. But an interesting question about oceans is that, okay, remember, I told you about how most planets would last for trillions of years and be later, right? So people have tried to explain why life appeared on Earth by saying, oh, all those planets are going to be unqualified for life because of various problems. That is, they're around smaller stars, which last longer. And smaller stars have some things like more solar flares, maybe more tidal locking. But almost all of these problems with longer-lived planets aren't problems for ocean worlds. And a large fraction of planets out there are ocean worlds. So if life can appear on an ocean world, then that pretty much ensures that these planets that last a very long time could have advanced life because there's a huge fraction of ocean </s><s>[INST] worlds. So that's actually an open question. So when you say, sorry, when you say life appeared, you're kind of saying life and intelligent life. So that's an open question, is land, and that's, I suppose, the question behind the Twitter poll, which is a grabby alien civilization that comes to say hello, what's the chance that they first began their early steps, the difficult steps they took on land? What do you think? 80%? Most people on Twitter think [/INST] it's very likely on land. What do you think? I think people are discounting ocean worlds too much. That is, I think people tend to assume that whatever we did must be the only way it's </s><s>[INST] possible. And I think people aren't giving enough credit for other possible paths, but dolphins, water world, by the way, people criticize that movie. I love that movie. Kevin Costner can do me no wrong. Okay. Next question. What percent of hello aliens once had a nuclear war with greater than 10 nukes fired in anger? So not in the incompetence and as an accident, intentional firing of nukes and less than 20% was the most popular vote. And that just seems wrong to me. Like I wonder what, so most people think once you get nukes, we're not going to fire them. [/INST] They believe in the power of the game you're running. I think they're assuming that if you had a nuclear war, then that would just end civilization for good. I think that's the thinking. That's the main thing. And I think that's just wrong. I think you could rise again after a nuclear war. It might take 10,000 years or 100,000 years, but it could rise again. </s><s>[INST] What do you think about mutually assured destruction as a force to prevent people from firing nuclear weapons? That's a question that a new, to a terrifying degree, [/INST] has been raised now, and what's going on. Clearly, it has had an effect. The question is just how strong an effect for how long. Clearly, we have not gone wild with nuclear war, and clearly the devastation that you would get if you initiated nuclear war is part of the reasons people have been reluctant to start a war. The question is just how reliably will that ensure </s><s>[INST] the absence of a war? The night is still young. This has been 70 years or whatever it's been. [/INST] What do you think? Do you think we'll see nuclear war in the century? Yeah, in the century. I don't know, in the century, but it's the sort of thing that's likely to </s><s>[INST] happen eventually. That's a very loose statement. Okay, I understand. Now, this is where I pull you out of your mathematical model and ask a human question. Do you think this particular human? [/INST] I think we've been lucky that it hasn't happened so far. </s><s>[INST] But what is the nature of nuclear war? Let's think about this. There is dictators. There's democracies. Miscommunication. How do wars start? World War I, World War II. [/INST] The biggest datum here is that we've had an enormous decline in major war over the last century. That has to be taken into account now. The problem is, war is a process that has a very long tail. That is, there are rare, very large wars. The average war is much worse than the median war because of this long tail. That makes it hard to identify trends over time. The median war has clearly gone way down in the last century, the median rate of war. But it could be that's because the tail has gotten thicker. In fact, the average war is just as bad, but most wars are going to be big wars. That's the thing we're not so sure about. </s><s>[INST] There's no strong data on wars because of the destructive nature of the weapons, [/INST] kill hundreds of millions of people. There's no data on this. But we can start intuiting. But we can see the power law. We can do a power law fit to the rate of wars, and it's a power law with a thick tail. It's one of those things that you should expect most of the damage to be in the few biggest ones. That's also true for pandemics and a few other things. For pandemics, most of the damage is in the few biggest ones. The median pandemic so far is less than the average that you should expect in the future. </s><s>[INST] That fitting of data is very questionable because everything you said is correct. The question is, what can we infer about the future of civilization threatening pandemics or nuclear war from studying the history of the 20th century? You can't just fit it to the data, the rate of wars and the destructive nature. That's not how nuclear war will happen. Nuclear war happens with two assholes or idiots that have access to a button. [/INST] Small wars happen that way too. </s><s>[INST] No, I understand that, but it's very important. Small wars aside, it's very important to understand the dynamics, the human dynamics and the geopolitics of the way nuclear war happens in order to predict how we can minimize the chance of... [/INST] It is a common and useful intellectual strategy to take something that could be really big but is often very small and fit the distribution of the data. Small things, which you have, a lot of them, and then ask, do I believe the big things are really that different? I see. Sometimes it's reasonable to say, like say with tornadoes or even pandemics or something, the underlying process might not be that different. </s><s>[INST] But that's behind some of the small ones. It might not be. The fact that mutual assured destruction seems to work to some degree shows you that to some degree it's different than the small wars. So it's a really important question to understand. Are humans capable? One human. How many humans on earth? If I give them a button now, say you pressing this button will kill everyone on earth. Everyone, right? How many humans will press that button? I want to know those numbers like day to day, minute to minute. How many people have that much irresponsibility, evil, incompetence, ignorance, whatever word you want to assign? There's a lot of dynamics to the psychology that leads you to press that button. But how many? My intuition is the number, the more destructive that press of a button, the fewer humans you find. And that number gets very close to zero very quickly. Especially people have access to such a button. But that's perhaps a hope that a reality. Unfortunately, we don't have good data on this. Which is like how destructive [/INST] are humans willing to be? So I think part of this just has to think about asking what your time scales you're looking at, right? So if you say, if you look at the history of war, we've had a lot of wars pretty consistently over many centuries. So if I ask, if you ask, will we have a nuclear war in the next 50 years? I might say, well, probably not. If I say 500 or 5,000 years, like if the same sort of risks are underlying and they just continue, then you have to add that up over time and think the risk is getting a lot larger the longer a timescale we're </s><s>[INST] looking at. But okay, let's generalize nuclear war. Because what I was more referring to is something that kills more than 20% of humans on Earth and injures or makes the other 80% suffer horribly, survive but suffer. That's what I was referring to. So when you look at 500 years from now, there might not be nuclear war, there might be something else that kind of has that destructive effect. And I don't know, these feel like novel questions in the history of humanity. I just don't know. I think since nuclear weapons, this has been engineering pandemics, for example, robotics, so nanobots. It just seems like a real new possibility that we have to contend with and [/INST] we don't have good models. From my perspective. So if you look on, say, the last 1,000 years or 10,000 years, we could say we've seen a certain rate at which people are willing to make big destruction in terms of war. Yes. Okay. And if you're willing to project that data forward, that I think if you want to ask over periods of thousands or tens of thousands of years, you would have a reasonable data set. So the key question is what's changed lately? Yes. Okay. And so a big question of which I've given a lot of thought to, what are the major changes that seem to have happened in culture and human attitudes over the last few centuries? And what's our best explanation for those so that we can project them forward into the future? And I have a story about that, which is the story that we have been drifting back toward forager attitudes in the last few centuries as we get rich. So the idea is we spent a million years being a forager, and that was a very sort of standard lifestyle that we know a lot about foragers who live in small bands. They make decisions cooperatively. They share food. They don't have much property, et cetera, a thousand and humans like that. And then 10,000 years ago, farming became possible, but it was only possible because we were plastic enough to really change our culture. Farming styles and cultures are very different. They have slavery. They have war. They have property. They have inequality. They have kings. They stay in one place instead of wandering. They don't have as much diversity of experience or food. They have more disease. Farming life is just very different, but humans were able to sort of introduce conformity and religion and all sorts of things to become just a very different kind of creature as farmers. Farmers are just really different than foragers in terms of their values and their lives. But the pressures that made foragers into farmers were part mediated by poverty. Farmers are poor. And if they deviated from the farming norms that people around them supported, they were quite at risk of starving to death. And then in the last few centuries, we've gotten rich. And as we've gotten rich, the social pressures that turned forgers into farmers have become less persuasive to us. So for example, a farming young woman who was told, if you have a child out of wedlock, you and your child may starve. That was a credible threat. She would see actual examples around her to make that a believable threat. Today, if you say to a young woman, you shouldn't have a child out of wedlock. She will see other young woman around her doing okay that way. We're all rich enough to be able to afford that sort of a thing. And therefore she's more inclined often to go with her inclinations or sort of more natural inclinations about such things rather than to be pressured to follow the official farming norms of that you shouldn't do that sort of thing. And all through our lives, we have been drifting back toward forager attitudes because we've been getting rich. And so aside from at work, which is an exception, but elsewhere, I think this explains trends toward less slavery, more democracy, less religion, less fertility, more promiscuity, more travel, more art, more leisure, fewer work hours. All of these trends are basically explained by becoming more forager like. And much science fiction celebrates this Star Trek or the culture novels. People like this image that we are moving toward this world where basically like foragers were peaceful, we share, we make decisions collectively, we have a lot of free time, </s><s>[INST] we are into art. So forager, you know, forager is a word and it has, it's a loaded word because it's connected to the actual, what life was actually like at that time. As you mentioned, we sometimes don't do a good job of telling accurately what life was like back then. But you're saying if it's not exactly like foragers, it rhymes in some fundamental way. You also said peaceful. Is it obvious that a forager with a nuclear weapon would be peaceful? [/INST] I don't know if that's 100% obvious. So we know, again, we know a fair bit about what foragers lives were like. The main sort of violence they had would be sexual jealousy. They were relatively promiscuous and so there would be a lot of jealousy. But they did not have organized wars with each other. That is, they were at peace with their neighboring forager bands. They didn't have property in land or even in people. They didn't really have marriage. And so they were, in fact, peaceful. When you think about large-scale wars, they don't start large scale wars. They didn't have coordinated large-scale wars. In the ways chimpanzees do, our chimpanzees do have wars between one tribe of chimpanzees and others, but human foragers do not. Farmers return to that, of course, the more chimpanzee-like styles. </s><s>[INST] Well, that's a hopeful message. If we could return real quick to the Hello Aliens Twitter thread, one of them is really interesting about language. What percent of Hello Aliens would be able to talk to us in our language? This is the question of communication. It actually gets to the nature of language. [/INST] It also gets to the nature of how advanced you expect them to be. So I think some people see that we have advanced over the last thousands of years and we aren't reaching any sort of limit, and so they tend to assume it could go on forever. And I actually tend to think that within, say, 10 million years, we will sort of max out on technology. We will sort of learn everything that's feasible to know for the most part. And then obstacles to understanding would more be about sort of cultural differences, like ways in which different places had just chosen to do things differently. And so then the question is, is it even possible to communicate across some cultural differences? And I might think, I could imagine some maybe advanced aliens who just become so weird and different from each other, they can't communicate with each other, but we're probably pretty simple compared to them. </s><s>[INST] So I would think, sure, if they wanted to, they could communicate with us. So it's the simplicity of the recipient. I tend to, just to push back, let's explore the possibility where that's not the case. Can we communicate with ants? [/INST] I find that this idea that we're not very good at communicating in general. </s><s>[INST] Oh, you're saying, all right, I see. [/INST] You're saying once you get orders of magnitude better at communicating. Once they had maxed out on all communication technology in general, and they just understood in general how to communicate with lots of things, and had done that for millions of </s><s>[INST] years. But you have to be able to, this is so interesting, as somebody who cares a lot about empathy and imagining how other people feel, communication requires empathy, meaning you have to truly understand how the other person, the other organism sees the world. It's like a four-dimensional species, talking a two-dimensional species. [/INST] It's not as trivial as, to me at least, as it might have foreseen. So let me reverse my position a little, because I'll say, well, the Hello Aliens question really combines two different scenarios that we're slipping over. So one scenario would be that the Hello Aliens would be like grabby aliens. They would be just fully advanced. They would have been expanding for millions of years. They would have a very advanced civilization. And then they would finally be arriving here after a billion years, perhaps, of expanding, in which case they're going to be crazy advanced at some and maximal level. But the Hello Aliens, about aliens we might meet soon, which might be sort of UFO aliens, </s><s>[INST] and UFO aliens probably are not grabby aliens. How do you get here if you're not a grabby alien? [/INST] Well, they would have to be able to travel, but they would not be expansive. </s><s>[INST] So the road trip doesn't count as grabby. [/INST] So we're talking about expanding the colony, the comfortable colony. The question is, if UFOs, some of them are aliens, what kind of aliens would they be? This is sort of the key question you have to ask in order to try to interpret that scenario. But the key fact we would know is that they are here right now, but the universe around us is not full of an alien civilization. So that says right off the bat that they chose not to allow massive expansion of a grabby civilization. </s><s>[INST] Is it possible that they chose it, but we just don't see them yet? [/INST] These are the stragglers, the journeymen. So the timing coincidence is almost surely, if they are here now, they are much older than us. They are many millions of years older than us. And so they could have filled a galaxy in that last millions of years if they had wanted to. That is, they couldn't just be right at the edge. They're very unlikely. Most likely they would have been around waiting for us for a long time. They could have come here anytime in the last millions of years and they just chosen... They've been waiting around for this, or they just chose to come recently, but the timing It would be crazy unlikely that they just happened to be able to get here, say, in the last 100 years. </s><s>[INST] They would no doubt have been able to get here far earlier than that. They couldn't just be right at the table. Again, we don't know. So, this is a friend's like UFO sightings on Earth. We don't know if this kind of increase in sightings have anything to do with action [/INST] visitation. I'm just talking about like the timing, like they arose at some point in space time, right? And it's very unlikely that that was just at a point that they could just barely get here recently. </s><s>[INST] Almost surely they could have gotten here much earlier. Throughout the stretch of several billion years that Earth existed, they could have [/INST] been here often. Exactly. </s><s>[INST] So, they could have therefore filled the galaxy a long time ago if they had wanted to. Let's push back on that. Well, the question to me is isn't it possible that the expansion of a civilization is much harder than the travel. The sphere of the reachable is different than the sphere of the colonized. So isn't it possible that the sphere of places where the stragglers go, the different people that journey out, the explorers, is much, much larger and grows much faster than the civilization? So in which case they would visit us. There's a lot of visitors, the grad students of the civilization. They're like exploring, they're collecting the data, but then we're not yet going to see them. And by yet, I mean across millions of years. [/INST] The time delay between when the first thing might arrive and then when colonists could arrive in mass and do a mass amount of work is cosmologically short. In human history, of course, sure there might be a century between that, but a century is just a tiny amount of time on the scales </s><s>[INST] we're talking about. So this is a computer science and colony optimization. It's true for ants. So it's like when the first ant shows up, it's likely, and if there's anything of value, it's likely the [/INST] other ants will follow quickly. Yeah, relatively short. It's also true that traveling over very long distances, probably one of the main ways to make that feasible is that you land somewhere, you colonize a bit, you create new resources, then allow you to go farther. Many short hops, as opposed to a giant long journey. Exactly. Those hops require that you are able to start a colonization of sorts along those hops, right? You have to be able to stop somewhere, make it </s><s>[INST] into a way station such that you can then support you moving farther. So what do you think of, there's been a lot of UFO sightings. What do you think about those UFO sightings? And what do you think if any of them are of extraterrestrial origin and we don't see giant civilizations out [/INST] in the sky, how do you make sense of that then? I want to do some clearing of throats, which is people like to do on this topic, right? They want to make sure you understand they're saying this and not that, right? So I would say the analysis needs both a prior and a likelihood. So the prior is, what are the scenarios that are at all plausible in terms of what we know about the universe? And then the likelihood is the particular actual sightings, like how hard are those to explain through various means? I will establish myself as somewhat of an expert on the prior. I would say my studies and the things I've studied make me an expert and I should stand up and have an opinion on that and explain, be able to explain it. The likelihood, however, is not my area of expertise. That is, I'm not a, you know, pilot. I don't do atmospherics studies of things. I haven't studied in detail, the various kinds of atmospheric phenomena or whatever that might be used to explain the particular sightings. I can just say from my amateur stance, the sightings look damn puzzling. They do not look easy to dismiss. The attempts I've seen to easily dismiss them seem to me to fail. It seems like these are pretty puzzling, weird stuff that deserve an expert's attention in terms of considering, asking what the likelihood is. So analogy I would make is a murder trial. Okay. On average, if we say, what's the chance any one person murdered another person as a prior probability, maybe one in a thousand people get murdered. Maybe each person has 1000 people around them who could plausibly have done it. So the prior probability of a murder is one in a million, but we allow murder trials because often evidence is sufficient to overcome on one in a million prior because the evidence is often strong enough. Right. My guess, rough guess for the UFOs as aliens, scenario, at least some of them is the prior is roughly one in a thousand, much higher than the usual murder trial. Plenty high enough that strong physical evidence could put you over the top to it's more likely than not. But I'm not an expert on that physical evidence and I'm going to leave that part to someone else. I'm going to say the prior is pretty high. This isn't a crazy scenario. So then I can elaborate on where my prior comes from. What scenario could make most sense of this data? Higher than the usual. My scenario, to make sense, has two main parts. First is panspermia siblings. So panspermia is the hypothesized process by which life might have arrived on Earth from elsewhere. And a plausible time for that, I mean, it would have had to happen very early in Earth's history because we see life early in history. And a plausible time could have been during the stellar nursery where the sun was born with many other stars in the same close proximity, with lots of rocks flying around, able to move things from one place to another. If a rock with life on it from some rock planet with life came into that stellar nursery, it plausibly could have seeded many planets in that stellar nursery, all at the same time. They're all born at the same time, in the same place, pretty close to each other. Lots of rocks flying around. So a panspermia scenario would then create siblings, i.e. there would be, say, a few thousand other planets out there. So after the nursery forms, it drips, it separates, they drift apart. And so out there in the galaxy, there would now be a bunch of other stars all formed at the same time, and we can actually spot them in terms of their spectrum. And they would have then started on the same path of life as we did with that life being seeded, but they would move at different rates. And most likely, most of them would never, you know, reach an advanced level before the deadline, but maybe one other did. And maybe it did before us. So if they did, they could know all this and they could go searching for their siblings. That is, they could look in the sky for the other stars with the spectrum that matches the spectrum that came from this nursery. They could identify their sibling stars in the galaxy, the thousand of them. And those would be of special interest to them, because they would think, well, life might be on those. And they could go looking </s><s>[INST] for them. It's such a brilliant mathematical, philosophical, physical, biological idea of panspermia siblings because we all kind of started a similar time in this local pocket [/INST] of the universe. And so that changes a lot of the math. So that would create this correlation between when advanced life might appear, no longer just random independent spaces in space-time, there'd be this cluster perhaps. </s><s>[INST] And that allows interaction between non-grabby alien civilizations like kind of primitive alien civilizations like us with others. And they might be a little bit ahead. [/INST] That's so fascinating. A little bit to the cluster. They would probably be a lot ahead. So the puzzle is, if they happen before us, they probably happen hundreds of millions of years before us. </s><s>[INST] But less than a billion. [/INST] Less than a billion, but still plenty of time, that they could've become grabby and filled the galaxy and gone beyond. So there'd be plenty. So the fact is, they chose not to become grabby. That would have to be the interpretation. If we have panspermia siblings... sensitive firms. </s><s>[INST] Plenty of time to become grabby you said. So they should be fine. [/INST] Yes. They have plenty of time, and they chose not to. </s><s>[INST] Are we sure about this? 100 million years is enough. [/INST] A hundred million. So I told you before that I said within 10 million years, our descendants will become grabby or not. And they'll have that choice, okay. And so they clearly more than 10 million years earlier than us, so they chose not to. But still go on vacation, look around, just not grabby. If they chose not to expand, that's going to have to be a rule they set to not allow any part of themselves to do it. Like if they let any little ship fly away with the ability to create a colony, the game's over. Then they have prevented, then the universe becomes grabby from their origin with this one colony, right? So in order to prevent their civilization being grabby, they have to have a rule they enforce pretty strongly that no part of them can ever </s><s>[INST] try to do that. Through a global authoritarian regime or through something that's internal [/INST] to them, meaning it's part of the nature of life that it doesn't want. As like a political officer </s><s>[INST] in the brain or whatever. Yes, there's something in human nature that prevents you from, or like like alien nature, that as you get more advanced, you become lazier and lazier in terms of exploration [/INST] and expansion. Right. So I would say they would have to have enforced a rule against expanding, and that rule would probably make them reluctant to let people leave very far. They, you know, any one vacation trip far away could risk an expansion from this vacation trip. So they would probably have a pretty tight lid on just allowing any travel out from their origin in order to enforce this rule. Interesting. But then we also know, well, they would have chosen to come here. So clearly they made an exception from their general rule to say, okay, but an </s><s>[INST] expedition to earth, that should be allowed. It could be intentional exception or incompetent [/INST] exception. But if incompetent, then they couldn't maintain this over 100 million years, this policy of not allowing any expansion. So we have to see, they have successfully, they not just had a policy to try, they succeeded over 100 million years in preventing the expansion. That's a substantial </s><s>[INST] competence. Let me think about this. So you don't think there could be a barrier in 100 million years. You don't think there could be a barrier to like technological barrier to becoming [/INST] expansionary. Imagine the Europeans have tried to prevent anybody from leaving Europe to go to the New World and imagine how what it would have taken to make that happen over a hundred million years. Yeah, it's impossible. They would have to have very strict, you know, guards at the borders. I don't know. </s><s>[INST] Saying no you can't go. I don't know. But just just to clarify, you're not suggesting that's actually possible. I am suggesting it's possible. I don't know how you keep my silly human brain. Maybe it's a brain that values freedom, but I don't know how you can keep, no matter how much force, no matter how much censorship or control or so on. I just don't know how you can keep people from [/INST] exploring into the mysterious, into the end. You're thinking of people. We're talking aliens. Remember there's a vast space of different possible social creatures they could have evolved from, different cultures they could be in, different kinds of threats. I mean, there are many things, as you talked about, that most of us would feel very reluctant to do. This isn't one of those, but. </s><s>[INST] Okay, so how, if the UFO sightings represent alien visitors, how the heck [/INST] are they getting here under the panspermia siblings? So panspermia siblings is one part of the scenario, which is that's where they came from. And from that we can conclude they had this rule against expansion and they've successfully enforced that. That also creates a plausible agenda for why they would be here. That is to enforce that rule on us. That is, if we go out and expanding, then we have defeated the purpose of this rule they set up. Interesting. Right? So they would be here to convince us to not expand. Convince in quotes. Right, through various mechanisms. So obviously one thing we conclude is they didn't just destroy us. That would have been completely possible, right? So the fact that they're here, and we are not destroyed, means that they chose not to destroy us. They have some degree of empathy or you know, whatever their morals are that would make them reluctant to just destroy us. They would </s><s>[INST] rather persuade us. To destroy their brethren. And so they may have been- there's a difference in arrival and observation. They may have been observing for a very long time. Exactly. And they arrive to try to, not to try. I don't to ensure that we don't become grabby. [/INST] In the meantime, exactly. Which is because we can see that they did not, they must have enforced a rule against that and they are therefore here to, that's a plausible interpretation why they would risk this expedition when they clearly don't risk very many expeditions over this long period to allow this one exception because otherwise if they don't, we may become grabby and they could have just destroyed us </s><s>[INST] but they didn't. And they're closely monitoring the technological advancing civilization. Like what nuclear weapons is one thing that, all right, cool. That might have less to do with nuclear weapons and more of a nuclear energy. Maybe they're monitoring fusion closely. [/INST] Like how clever are these apes getting? So no doubt they have a button that if we get too uppity or risky, they can push the button and ensure that we don't expand but they'd rather do it some other way. So now that explains why they're here and why they aren't out there. But there's another thing that we need to explain. There's another key data we need to explain about UFOs if we're going to have a hypothesis that explains them. And this is something many people have noticed which is they had two extreme options. They could have chosen and didn't chose, they could have either just remained completely invisible that's one thing they could have done. The other thing they could do is just show up and land on the White House lawn, as they say, and shake hands, make themselves really obvious. They could have done either of those, and they didn't do either of those. That's the next thing you need to explain about UFOs as aliens. Why would they take this intermediate approach hanging out near the edge of visibility with somewhat impressive mechanisms, but not walking up and introducing selves, </s><s>[INST] nor just being completely invisible? There's a lot of questions there. [/INST] So, one, do you think it's obvious where the White House is, or the White House lawn? Well, it's obvious where there are concentrations of humans that you could go up and introduce. </s><s>[INST] But is humans the most interesting thing about Earth? Yeah. [/INST] Are you sure about this? Because if they're worried about an expansion, then they worried about a civilization that could be capable of expansion. Obviously, humans are the civilization on Earth. That's by far the closest to being able to expand. </s><s>[INST] I just don't know if aliens obviously see humans, like the individual humans, [/INST] like the organ of the meat vehicles, as the center of focus for observing a life on a planet. They're supposed to be really smart in advance. This shouldn't be that hard for that. </s><s>[INST] But I think we're actually the dumb ones, because we think humans are the important things, [/INST] but it could be our ideas. It could be something about our technologies. That's mediated with us. That's correlated with us. </s><s>[INST] No, we make it seem like it's mediated by us humans. But the focus for alien civilizations might be the AI systems or the technologies themselves. That might be the organism. Okay. Okay. [/INST] Human is the food, the source of the organism that's under observation versus the what they wanted to have close contact with was something that was closely near humans, then they would be contacting those and we would just incident on all you see, but we would still see. </s><s>[INST] But don't you think they... Isn't it possible, taking their perspective, isn't it possible that they would want to interact with some fundamental aspect that they're interested in without interfering with it? And that's actually a very... [/INST] No matter how advanced you are, it's very difficult to do, I think. But that's puzzling. So, I mean, the prototypical UFO observation is a shiny, big object in the sky that has very rapid acceleration and no apparent surfaces for using air to manipulate at speed. And the question is, why that? Again, if they just... For example, if they just wanted to talk to our computer systems, they could move some sort of little probe that connects to a wire and reads and sends bits there. They don't need a shiny </s><s>[INST] thing flying in the sky, puzzling. But don't you think they are or would be looking for the right way to communicate, the right language to communicate? Everything you just said, looking at the computer systems, I mean, that's not a trivial thing. Coming up with a signal that us humans would not freak out too much about, but also understand, might not be that trivial. [/INST] Well, so not freak out apart is another interesting constraint. So again, I said, the two obvious strategies are just to remain completely invisible and watch, which would be quite feasible or to just directly interact. That's come out and be really very direct, right? I mean, there's big things that you can see around. There's big cities, there's aircraft carriers, there's lots of... If you want to just find a big thing and come right up to it and like tap it on the shoulder or whatever, that would be quite feasible and they're not doing that. So my hypothesis is that one of the other questions there was, do they have a status hierarchy? And I think most animals on earth who are social animals have status hierarchy and they would reasonably presume that we have a status hierarchy. And take me to your leader. Well, I would say their strategy is to be impressive and sort of get us to see them at the top of our status hierarchy. That's how, for example, we domesticate dogs, right? We convince dogs we're the leader of their pattern, right? And we domesticate many animals that way, but as we just swap in to the top of their status hierarchy and we say, we're your top status animal, so you should do what we say, you should follow our lead. So the idea that would be, they are going to get us to do what they want by being top status. All through history, kings and emperors, et cetera, have tried to impress their citizens and other people by having the bigger palace, the bigger parade, the bigger crown and diamonds, right, whatever, maybe building a bigger pyramid, et cetera. It's a very well-established trend, to just be high status by being more impressive than the rest. </s><s>[INST] To push back when there's an order of several orders of magnitude of power differential, asymmetry of power, I feel like that status hierarchy no longer applies. It's like mimetic [/INST] theory. It's like... Most emperors are several orders of magnitude more powerful than anyone, </s><s>[INST] a member of their empire, a member of their empire. Let's increase that even more. So if I'm interacting with ants, I no longer feel like I need to establish my power with ants. I actually want to lessen... I want to lower myself to the ants. I want to become the lowest possible ant so that they would welcome me. So I'm less concerned about them worshipping me. I'm I'm more concerned about them welcoming me into it. [/INST] It is important that you be non-threatening and that you be local. So I think, for example, if the aliens had done something really big in the sky, you know, a hundred light years away, that would be there, not here. And that could seem threatening. So I think their strategy to be the high status would have to be to be visible, but to be here and non-threatening. </s><s>[INST] I just don't know if it's obvious how to do that. Like take your own perspective. You see a planet with, with relatively intelligent, like complex structures being formed, like, yeah, life forms. You could see this under in Titan or something like that. The moon, you know, Europa. You start to see not just primitive bacterial life, but multicellular life. And it seems to form some very complicated cellular colonies or structures that they're dynamic. There's a lot of stuff going on. Some gigantic cellular automata type of construct. How do you make yourself known to them in an impressive fashion without destroying it? Like we know how to destroy potentially. Right. [/INST] So if you go touch stuff, you're likely to hurt it, right? There's a good risk of hurting something by getting too close and touching it and interacting, right? </s><s>[INST] Yeah, like landing on a White House lawn. Right, right. [/INST] So the claim is that their current strategy of hanging out at the periphery of our vision and just being very clearly physically impressive with very clear physically impressive abilities is at least a plausible strategy they might use to impress us and convince us sort of, we're at the top of their status hierarchy. And I would say if they, if they came closer, not only would they risk hurting us in ways that they couldn't really understand, but more plausibly, they would reveal things about themselves we would hate. So if you look at how we treat other civilizations on earth and other people, we are generally interested in foreigners and people from other plants land and we were generally interested in their varying cult customs, et cetera, until we find out that they do something that violates our moral norms and then we hate them and these are aliens for God's sakes, right? They there's just going to be something about them that we hate. They eat babies, who knows what it is? Well, something they don't think is offensive, but that they think we might find, and so they would be risking a lot by revealing a lot about themselves. a lot about themselves. We would find something we hated. </s><s>[INST] Interesting. But do you resonate at all with mimetic theory where like we only feel this way about things that are very close to us? So aliens are sufficiently different to where we'll be like fascinated, terrified or fascinated, but not like- [/INST] Right, but if they want to be at the top of our status hierarchy to get us to follow them, they can't be too distant. They have to be close enough that we would see them that way. </s><s>[INST] But pretend to be close enough and not reveal much that mystery that old Clint Eastwood, [/INST] cowboy, save less. The point is, we're clever enough that we can figure out their agenda. That is just from the fact that we're here. If we see that they're here, we can figure out, oh, they want us not to expand. And look, they are this huge power and they're very impressive. And a lot of us don't want to expand. So that could easily tip us over the edge toward we already wanted to not expand. We already wanted to be able to regulate and have a central community. And here are these very advanced smart aliens who have survived for a hundred million years and they're telling us not to </s><s>[INST] expand either. This is brilliant. I love this so much. Returning to panspermia siblings, just to clarify one thing. In that framework, who originated, who planted it? Would it be a grabby alien civilization that planted the [/INST] siblings or no? The simple scenario is that life started on some other planet billions of years ago and it went through part of the stages of evolution to advance life, but not all the way to advance life. And then some rock hit it, grabbed a piece of it on the rock and that rock drifted for maybe in a million years until it happened upon the stellar nursery where it then seeded many stars. </s><s>[INST] And something about that life without being super advanced, it was nevertheless resilient [/INST] to the harsh conditions of space. There's some graphs that I've been impressed by that show sort of the level of genetic information in various kinds of life on the history of earth. And basically we are now more complex than the earlier life, but the earlier life was still pretty damn complex. And so if you actually project this log graph in history, it looks like it was many billions of years ago when you get down to zero. So like plausibly you could say there was just a lot of evolution that had to happen before to get to the simplest life we've ever seen in history of life on earth was still pretty damn complicated. And so that's always been this puzzle. How could life get to this enormously complicated level in the short period it seems to at the beginning of earth history? So it's only 300 million years at most when it appeared, and then it was really complicated at that point. So panspermia allows you to explain that complex by saying, well, it's been another 5 billion years on another planet going through lots of earlier stages where it was working </s><s>[INST] its way up to the level of complexity you see at the beginning of earth. We'll try to talk about other ideas of the origin of life, but let me return to UFO sightings. Is there other explanations that are possible outside of panspermia's siblings that can explain no grabby aliens in the sky and yet alien arrival on earth? [/INST] Well, the other categories of explanations that most people will use is, well, first of all, just mistakes like, you know, you're confusing something ordinary for something mysterious, right? Or some sort of secret organization like our government is secretly messing with us and trying to do a, you know, a false flag ops or whatever, right? You know, they're trying to convince the Russians or the Chinese that there might be aliens and scare them into not attacking or something, right? Because if you know the history of World War II, say the US government did all these big fake operations where they were faking a lot of big things in order to mess with people. So that's a possibility. The government's been lying and, you know, faking things and paying people to lie about what they saw, etc. That's a plausible set of explanations for the range of sightings seen. And another explanation people offer is some other hidden organization on earth or some, you know, secret organization somewhere that has much more advanced capabilities than anybody's given a credit for. For some reason, it's been keeping secret. I mean, they all sound somewhat implausible, but again, we're looking for maybe, you know, one in a thousand sort of priors. The question is, you know, could they be in that level of plausibility? </s><s>[INST] Can we just linger on this? So you first of all, you've written, talked about, thought about so many different topics. You're an incredible mind. And I just thank you for sitting down today. I'm almost like at a loss of which place we explore. But let me on this topic, ask about conspiracy theories, because you've written about institutions and authorities [/INST] today. This is a bit of a therapy session, but what do we make of conspiracy theories? The phrase itself is pushing you in a direction, right? So clearly in history, we've had many large coordinated keepings of secrets, right? Say the Manhattan Project, right? And there was what? Hundreds of thousands of people working on that over many years, but they kept it a secret, right? Clearly many large military operations have kept things secrets over, you know, even decades with many thousands of people involved. So clearly it's possible to keep something secret over time periods, you know, but the more people you involve and the more time you are assuming and the more, the less centralized an organization or the less discipline they have, the harder it gets to believe. But we're just trying to calibrate basically in our minds, which kind of secrets can be kept by which groups </s><s>[INST] over what time periods for what purposes, right? Let me, I don't have enough data, so I'm somebody I, you know, I hang out with people and I love people. I love all things really. And I just, I think that most people, even the assholes have the capacity to be good and they're beautiful and I enjoy them. So the kind of data my brain, whatever the chemistry of my brain is that sees the beautiful in some things is maybe collecting a subset of data that doesn't allow me to intuit the competence that humans are able to achieve in constructing a conspiracy theory. So for example, one thing that people often talk about is like intelligence agencies, this like broad thing. They say the CIA, the FSB, the different, the British intelligence. I've fortunate or unfortunate enough never gotten the chance that I know of to talk to any member of those intelligence agencies nor like take a peek behind the curtain or the first curtain. I don't know how many levels of curtains there are. And so I don't, I can't intuit, but my interactions as government, I was funded with DOD and DARPA and I've interacted, been to the Pentagon, like with all due respect to my friends, lovely friends in government and there are a lot of incredible people, but there is a very giant bureaucracy that sometimes suffocates the ingenuity of the human spirit is one way I can put it. Meaning they are, I just, it's difficult for me to imagine extreme competence at a scale of hundreds or thousands of human beings. Now that doesn't mean that's my very anecdotal data of the situation. And so I try to build up my intuition about centralized system of government, how much conspiracy is possible, how much the intelligence agencies or some other source can generate sufficiently robust propaganda that controls the populace. If you look at World War II, as you mentioned, there've been extremely powerful propaganda machines on the Nazi, on the side of Nazi Germany, on the side of the Soviet Union, on the side of the United States and all these different mechanisms. Sometimes they control the free press through social pressures. Sometimes they control the press through the threat of violence, as you do in authoritarian regimes. Sometimes it's like deliberately the dictator like writing the news, the headlines and literally announcing it. And something about human psychology forces you to embrace the narrative and believe the narrative and at scale that becomes reality when the initial spark was just a propaganda thought in a single individual's mind. So I can't necessarily intuit of what's possible, but I'm skeptical of the power of human institutions to construct conspiracy theories that cause suffering at scale, especially in this modern age when information is becoming more and more accessible by the populace. Anyway, that's, I don't know if you can elucidate for a suffering [/INST] scale, but of course, say during wartime, the people who are managing the various conspiracies like D-Day or Manhattan Project, they thought that their conspiracy was avoiding harm rather than causing harm. So if you can get a lot of people to think that supporting the conspiracy is helpful, then a lot more might do that. And there's just a lot of things that people just don't want to see. So if you can make your conspiracy the sort of thing that people wouldn't want to talk about anyway, even if they knew about it, you're, you know, most of the way there. So I have learned many over the years, many things that most ordinary people should be interested in, but somehow don't know, even though the data has been very widespread. So, you know, I have this book, The Elephant in the Brain, and one of the chapters is there on medicine. And basically, most people seem ignorant of the very basic fact that when we do randomized trials where we give some people more medicine than others, the people who get more medicine are not healthier. Just overall in general, just like induce somebody to get more medicine because you just give them more budget to buy medicine. Not a specific medicine, just the whole category. And you would think that would be something most people should know about medicine. You might even think that would be a conspiracy theory to think that would be hidden, but in fact, most people never learned that fact. </s><s>[INST] So just to clarify, just a general high-level statement, the more medicine you take, the [/INST] less healthy you are. Randomized experiments, don't find that fact. Do not find that more medicine makes you more They're just no connections. In randomized experiments, there's no relationship between more medicine... So it's not a negative... </s><s>[INST] Right. In randomized experiments. So it's not a negative relationship, but it's just no relationship. Right. And so the conspiracy theories would say that the businesses that sell you medicine don't want you to know that fact. And then you're saying that there's also part of this is that people just don't wanna know. [/INST] They just don't wanna know. And so they don't learn this. So, you know, I've lived in Washington to an area for several decades now, reading The Washington Post regularly. Every week there was a special, you know, section on health and medicine. It never was mentioned in that section of the paper in all the 20 years I read that. </s><s>[INST] So do you think there is some truth to this caricatured blue pill, red pill, where most [/INST] people don't want to know the truth, not most people. There are many things about which people don't want to know certain kinds of truths. That is bad looking truths, truths that, discouraging truths that sort of take away the justification for things they feel passionate about. </s><s>[INST] Do you think that's a bad aspect of human nature? That's something we should try to [/INST] overcome? Well, as we discussed, my first priority is to just tell people about it, to do the analysis and the cold facts of what's actually happening, and then to try to be careful about how we can improve. So our book, The Elephant in the Brain, co-authored with Kevin Simler, is about hidden motives in everyday life. And our first priority there is just to explain to you what are the things that you are not looking at, that you ever are reluctant to look at. And many people try to take that book as a self-help book where they are trying to improve themselves and make sure they look at more things, and that often goes badly because it's harder to actually do that than you think. </s><s>[INST] And so we at least want you to know that this truth is available if you want to learn about it. It's the Nietzsche if you gaze long to the abyss. The abyss gazes in to you. Let's talk about this elephant in the brain, amazing book. The elephant in the room is quote, an important issue that people are reluctant to acknowledge or address a social taboo. The elephant in the brain is an important but unacknowledged feature of how our mind works and introspective taboo. You describe selfishness and self-deception as the core or some of the core elephants, some of the elephants, elephant offspring in the brain, selfishness and self-deception. All right, can you explain? Can you explain why these are the taboos in our brain that we don't want to acknowledge to ourselves? [/INST] Your conscious mind, the one that's listening to me that I'm talking to at the moment, you like to think of yourself as the president or king of your mind, ruling over all that you see issuing commands that immediately obeyed. You are instead better understood as the press secretary of your brain. You don't make decisions, you justify them to an audience. That's what your conscious mind is for. You watch what you're doing and you try to come up with stories that explain what you're doing so that you can avoid accusations of violating norms. Humans, compared to most other animals, have norms and this allows us to manage larger groups with our morals and norms about what we should or shouldn't be doing. This is so important to us that we needed to be constantly watching what we're doing in order to make sure we had a good story to avoid norm violation, so many norms are about motives, so if I hit you on purpose, that's a big violation. If I hit you accidentally, that's okay, I need to be able to explain why it was an accident </s><s>[INST] and not on purpose. You watch what you're doing, it was an accident and not an accident. So where does that need come from for your own self-preservation? [/INST] Right, so humans have norms and we have the norm that if we see anybody violating a norm, we need to tell other people and then coordinate to make them stop and punish them for violating. So such benefits are strong enough and severe enough that we each want to avoid being successfully accused of violating norms. So for example, hitting someone on purpose is a big clear norm violation. If we do it consistently, we may be thrown out of the group and that would mean we would die. That's right. Okay, so we need to be able to convince people we are not going around hitting people on purpose. If somebody happens to be at the other end of our fist and their face connects, that was an accident and we need to be able to explain that. And similarly for many other norms humans have, we are serious about these norms and we don't want people to violate the way we find them violating, we're going to accuse them. But many norms have a motive component and so we are trying to explain ourselves and make sure we have a good motive story about everything we do which is why we're constantly trying to explain what we're doing and that's what your conscious mind is doing. It is trying to make sure you've got a good motive story for everything you're doing and that's why you don't know why you really do things. </s><s>[INST] What you know is what the good story is about why you've been doing things. that's the self-deception. And you're saying that there is a machine, the actual dictator is selfish. And then you're just the press secretary who's desperately doesn't want to get fired and is justifying all of the decisions of the dictator. And that's the self-deception. [/INST] Right now, most people actually are willing to believe that this is true in the abstract. So our book has been classified as psychology, and it was reviewed by psychologists. And the basic way that psychology referees and reviewers responded to say, this is well-known, most people </s><s>[INST] accept that there's a fair bit of self-deception. But they don't want to accept it about themselves. [/INST] Well they don't want to accept it about the particular topics that we talk about. So people accept the idea in the abstract that they might be self-deceived or that they might not be honest about various things. But that hasn't penetrated into the literatures where people are explaining particular things like why we go to school, why we go to the doctor, why we vote, etc. So our book is mainly about ten areas of life and explaining about in each area what our actual motives there are and </s><s>[INST] You know people who study those things have not admitted that hidden motives are explaining those particular areas They haven't taken the leap from theoretical psychology to actual public policy exactly and economics and all that kind of stuff well, let me just linger on this and Bring up my old friends Zingman Freud and Carl Jung. So how vast is this? Landscape of the unconscious mind the power and the scope of the dictator is is it only dark there? [/INST] Is it some light? Is there some love the vast majority of what's happening in your head? you're unaware of so in a literal sense the unconscious the Aspects of your mind that you're not conscious of is the overwhelming majority that but that's just true in a literal engineering sense Your mind is doing lots of low-level things and you just can't be consciously aware of all that low-level stuff </s><s>[INST] But there's plenty of room there for lots of things. You're not aware, but can we try to shine a light at the things? We're unaware of Specifically now against staying with the philosophical psychology side for a moment, you know, can you shine the light in the Jungian shadow? Can you what what's going on there? What is this machine like like what what level of thoughts are happening there? Is it something that could we can even interpret if we somehow could visualize it? Is it something that's human interpretable? Or is it just a kind of chaos of like monitoring different systems in the body making sure you're happy making sure you're Fed all those kind of basic forces that form abstractions on top of each other and they're not [/INST] Introspective at all. They're we humans are social creatures plausibly being social is the main reason we have these unusually large brains therefore most of our brain is devoted to being social and So the things we are very obsessed with and constantly paying attention to are how do I look to others? </s><s>[INST] What would others think of me if they knew these various things they might learn about me So that's close to being fundamental thought or it needs to be human is caring [/INST] What others think right to to be trying to present a story that would be okay for what other things but we're very </s><s>[INST] Constantly thinking what do other people think so let me ask you this question then about you Robin Hanson who? Many places Sometimes for fun sometimes as a basic statement of principle likes to disagree. What would what would the majority of people think? So, how do you explain How are you self deceiving yourself in this task and how are you being self? How's your like? Why is the dictator manipulating you inside your head to be so critical like there's norms Why do you want to stand out? [/INST] In this way, why do you want to challenge the norms in this way almost by definition? I can't tell you what I'm deceiving myself about but the more practical strategy That's quite feasible is to ask about what are typical things that most people to seize themselves about and then to own up to those particular things sure What's a good one? So for example, I can very much acknowledge that I would like to be well thought of Yes, that I would be seeking attention and glory and Praise. Yes from my intellectual work and that that would be a major agenda driving my intellectual attempts So, you know if there were topics that other people would find less interesting I might be less interested in those for that reason for example, I might want to find topics where other people are interested and I might want to Go for the glory of finding a big insight rather than a small one What's a good one? And maybe one that was especially surprising That's also of course consistent with some more ideal concept of what an intellectual should be but most intellectuals are relatively risk-averse They are in some local intellectual tradition and they are adding to that and they are staying Conforming to this sort of usual assumptions and usual accepted beliefs and practices of a particular area So that they can be accepted in that area and you know, treat it as part of the community is part of the community. But you might think, for the purpose of the larger intellectual project of understanding the world better, people should be less eager to just add a little bit to some tradition and they should be looking for what's neglected between the major traditions and major questions. They should be looking for assumptions maybe we're making that are wrong, they should be looking at ways, things that are very surprising. You would've thought a prior and likely that once you are convinced of it find that to be very important and a big update, right? So you could say that one motivation I might have is less motivated to be sort of comfortably accepted into some particular intellectual community and more willing to just go for these more fundamental long shots that should be very important if you could find them. </s><s>[INST] Which would, if you can find them, would get you appreciated across a larger number of people across the longer time span of history. So like maybe the small local community will say, you suck, you must conform, but the larger community will see the brilliance of you breaking out of the cage of the small conformity into a larger cage. There's always a bigger cage and then you'll be remembered by more. Also that explains your choice of colorful shirt that looks great in a black background, so you definitely stand out. [/INST] Now of course, you could say, well, you could get all this attention by making false claims of dramatic improvement and then wouldn't that be much easier than actually working through all the details? Why not? To make true claims, right? </s><s>[INST] True claims, right. Let me ask the press secretary, why not? So of course, you spoke several times about how much you value truth and the pursuit of truth. That's a very nice narrative. Right. Hitler and Stalin also talked about the value of truth. Do you worry when you introspect as broadly as all humans might, that it becomes a drug, this being a martyr, being the person who points out that the emperor wears no clothes, even when the emperor is obviously dressed, just to be the person who points out that the emperor is wearing no clothes. Do you think about that? [/INST] Yeah. So I think the standards you hold yourself to are dependent on the audience you have in mind. So if you think of your audience as relatively easily fooled or relatively gullible, then you won't bother to generate more complicated, deep arguments and structures and evidence to persuade somebody who has higher standards because why bother? You can get away with something much easier. And of course, if you are say a salesperson, you know, you make money on sales, then you don't need to convince the top few percent of the most sharp customers. You can just go for the bottom 60% of the most gullible customers and make plenty of sales. Right. So I think intellectuals have to vary. One of the main ways intellectuals varies in who is their audience in their mind. Who are they trying to impress? Is it the people down the hall? Is it the people who are reading their Twitter feed? Is it their parents? Is it their high school teacher? Right. Or is it Einstein and Freud and Socrates? Right. So I think those of us who are especially arrogant, especially think that we're really big shot or have a chance at being a really big shot, we were naturally going to pick the big shot audience that we can. We're going to be trying to impress Socrates and Einstein. Shot audience. Is that why you hang out with Tyler Coen and trash? Sure. I mean, try to convince him and stuff. Right. You know, and you might think, you know, from the point of view of just making money or having sex or other sorts of things, this is misdirected energy. Right. Right. Trying to impress the very most highest quality minds. That's such a small sample and they can't do that much for you anyway. Yeah. So I might well have had more, you know, ordinary success in life, be more popular, invited to more priorities, make more money if I had targeted a lower tier set of intellectuals with the standards they have. But for some reason, I decided early on that Einstein was my audience or people like him and I was going to impress them. </s><s>[INST] Yeah. I mean, you pick your set of motivations, you know, convincing and pressing Tyler Coen is not going to help you get laid. Trust me, I tried. All right. What are some notable sort of effects of the elephant in the brain in everyday life? So you mentioned when we tried to apply that to economics, to public policy. So when we think about medicine, education, all those kinds of things. Right. So what are some things that... [/INST] Well, the key thing is medicine is much less useful health-wise than you think. So, you know, if you were focused on your health, you would care a lot less about it. And if you were focused on other people's health, you would also care a lot less about it. But if medicine is, as we suggest, more about showing that you care and let other people showing that they care about you then a lot of priority on medicine can make sense. So that was our very earliest discussion in the podcast. You're talking about, you know, should you give people a lot of medicine when it's not very effective? And then, the answer then is, well, if that's the way that you show that you care about them and you really want them to know you care, then maybe that's what you need to do if you can't find a cheaper, more effective substitute. </s><s>[INST] So if we actually just pause on that for a little bit, how do we start to untangle the [/INST] full set of self-deception happening in the space of medicine? So we have a method that we use in our book that is what I recommend for people to use in all these sorts of topics. The straightforward method is first, don't look at yourself. Look at other people. Look at broad patterns of behavior in other people and then ask what are the various theories we could have to explain these patterns of behavior? And then just do the simple matching, which theory better matches the behavior they have. And the last step is to assume that's true of you too. Don't assume you're an exception. If you happen to be an exception, that won't go so well. But nevertheless, on average, you aren't very well positioned to judge if you're an exception. </s><s>[INST] So look at what other people do, explain what other people do and assume that's you too. In the case of medicine, there's several parties to consider. So there's the individual person that's receiving the medicine. There's the doctors that are prescribing the medicine. There's drug companies that are selling drugs. There are governments that have regulations that are lobbyists. So you can build up a network of categories of humans in this, and they each play their role. So how do you introspect, the sort of analyze the system at a system scale versus at the individual scale. [/INST] So, it turns out that in general, it's usually much easier to explain producer behavior than consumer behavior. That is, the drug companies or the doctors have relatively clear incentives to give the customers whatever they want. And some of these say governments in democratic countries have the incentive to give the voters what they want. So, that focuses your attention on the patient and the voter in this equation and saying, what do they want? They would be driving the rest of the system. Whatever they want, the other parties are willing to give them in order to get paid. So, now we're looking for puzzles in patient and voter behavior. </s><s>[INST] What are they choosing and why do they choose that? And how much exactly? And then we can explain that potentially, again, returning to the producer by the producer [/INST] being incentivized to manipulate the decision-making processes of the voter and the consumer. Now, in almost every industry, producers are in general happy to lie and exaggerate in order to get more customers. This is true of auto repair as much as human body repair and medicine. So, the differences between these industries can't be explained by the willingness of the producers to give customers what they want or to do various things that we have to, again, go to the customers. </s><s>[INST] Why are customers treating body repair different than auto repair? Yeah, and that potentially requires a lot of thinking, a lot of data collection and potentially looking at historical data too because things don't just happen overnight, [/INST] over time there's trends. In principle it does, but actually it's a lot, actually easier than you might think. I think the biggest limitation is just the willingness to consider alternative hypotheses. So, many of the patterns that you need to rely on are actually pretty obvious, simple patterns. You just have to notice them and ask yourself, how can I explain those? Often you don't need to look at the most subtle, most difficult statistical evidence that might be out there. </s><s>[INST] The simplest patterns are often enough. All right, so there's a fundamental statement about self-deception in the book. There's the application of that, like we just did in medicine. Can you steel man the argument that many of the foundational ideas in the book go wrong? Meaning, there's two that you just made, which is, it can be a lot simpler than it looks. Can you steel man the case that it's, case by case, it's always super complicated, like it's a complex system, it's very difficult to have a simple model about, it's very difficult in retrospect. And the other one is that the human brain isn't not just about self-deception, that there's a lot of, there's a lot of motivation to play, and we are able to really introspect our own mind, and like what's on the surface of the conscious is actually quite a good representation of what's going on in the brain, and you're not deceiving yourself. You're able to actually arrive to deeply think about where your mind stands and what you think about the world. [/INST] And it's less about impressing people and more about being a free thinking individual. So when a child tries to explain why they don't have their homework assignment, they are sometimes inclined to say, the dog ate my homework. They almost never say the dragon ate my homework. The reason is, the dragon is a completely implausible explanation. Almost always when we make excuses for things, we choose things that are at least in some degree plausible. It could perhaps have happened. That's an obstacle for any explanation of a hidden motive or a hidden feature of human behavior. If people are pretending one thing while really doing another, they're usually going to pick as a pretense something that's somewhat plausible. That's going to be an obstacle to proving that hypothesis if you are focused on sort of the local data that a person would typically have if they were challenged. So if you're just looking at one kid and his lack of homework, maybe you can't tell whether his dog ate his homework or not. If you happen to know he doesn't have a dog, you might have more confidence, right? You will need to have a wider range of evidence than a typical person would when they're encountering that actual excuse in order to see past the excuse. That will just be a general feature of it. So in order, if I say, you know, there's this usual story about where we go to the doctor and then there's this other explanation, you know, it'll be true that you'll have to look at wider data in order to see that because, you know, people don't usually offer excuses unless in the local context of their excuse, they can get away with it. That is, it's hard to tell, right? So in the case of medicine, I have to point you to sort of larger sets of data. But in many areas of academia, including health economics, the researchers there also want to support the usual points of view. And so they will have selection effects in their publications and their analysis whereby they, if they're getting a result too much contrary to the usual point of view everybody wants to have, they will file drawer that paper or redo the analysis until they get an answer that's more to people's liking. So that means in the health economics literature, there are plenty of people who will claim that in fact we have evidence that medicine is effective. And when I respond, I will have to point you to our most reliable evidence and ask you to consider the possibility that the literature is biased in that when the, when the evidence isn't as reliable, when they have more degrees of freedom in order to get the answer they want, they do tend to get the answer they want. But when we get to the kind of evidence that's much harder to mess with, that's where the, that's where we will see the truth be more revealed. So with respect to medicine, we have millions of papers published in medicine over the years, most of which give the impression that medicine is useful. a small literature on randomized experiments of the aggregate effects of medicine where there's, you know, maybe a few half dozen or so papers where it would be the hardest to hide it because it's such a straightforward experiment done in a straightforward way that, you know, it's hard to manipulate. And that's where I will point you to, to show you that there's relatively little correlation between health and medicine. But even then, people could try to save the phenomenon and say, well, it's not hidden motifs. It's just ignorance. They could say, for example, you know, medicine is complicated. Most people don't know the literature, therefore they can be excused for, for ignorance. They are just ignorantly assuming that medicine is effective. It's not that they have some other motive that they're trying to achieve. And then I will have to do, you know, as with the conspiracy theory analysis I'm saying, well, Like, how long has this misperception been going on? How consistently has it happened around the world and across time? And I would have to say, look, you know, if we're talking about, say, a recent new product like Segway scooters or something, I could say not so many people have seen them or used them. Maybe they could be confused about their value. If we're talking about a product that's been around for thousands of years, used in roughly the same way all across the world, and we see the same pattern over and over again, this sort of ignorance mistake just doesn't work </s><s>[INST] so well. It also is a question of how much of the self-deception is prevalent versus foundational? Because there's a kind of implied thing where it's foundational to human nature versus just a common pitfall. This is a question I have. So, like, maybe human progress is made by people who don't fall into the self-deception. It's a dissir aspect of human nature, but then [/INST] you escape it easily if you're motivated. The motivational hypotheses about these self-deceptions are in terms of how it makes you look to the people around you. Again, the press secretary. So the story would be most people want to look good to the people around them. Therefore, most people present themselves in ways that help them look good to the people around them. That's sufficient to say there would be a lot of it. It doesn't need to be 100%, right? There's enough variety in people and in circumstances that sometimes taking a contrarian strategy can be in the interest of some minority of the people. So I might, for example, say that that's a strategy I've taken. I've decided that being contrarian on these things could be winning for me and that there's a room for a small number of people like me who have these sort of messages who can then get more attention, even if there's not room for most people to do that. And that can be explaining sort of the variety, right? Similarly, you might say, look, just look at most obvious things. Most people would like to look good, right? In the sense of physically, just you look good right now. You're wearing a nice suit, you have a haircut, you shaved, right? So, and we got my own hair, by the way. Okay. Well, Ben, all the more impressive. That's a counter argument for your client. So clearly, if we look at most people in their physical appearance, clearly most people are trying to look somewhat nice, right? They shower, they shave, they comb their hair. But we certainly see some people around who are not trying to look so nice, right? Is that a big challenge, the hypothesis that people want to look nice? Not that much, right? We can see in those particular the people's context, more particular reasons why they've chosen to be an exception to the more general rule. </s><s>[INST] So the general rule does reveal something foundational, generally. Right. That's the way things work. Let me ask you, you wrote a blog post about the accuracy of authorities since we were talking about this, especially in medicine. Just looking around us, especially during this time of the pandemic, there's been a growing distrust of authorities, of institutions, even an institution of science itself. What are the pros and cons of authorities, would you say? So what's nice about authorities? What's nice about institutions? [/INST] And what are their pitfalls? One standard function of authority is as something you can defer to, respectively, without needing to seem too submissive or ignorant or gullible. That is, when you're asking, what should I act on or what belief should I act on? You might be worried if I chose something too contrarian, too weird, too speculative, that would make me look bad, so I would just choose something very conservative. So maybe an authority lets you choose something a little less conservative because the authority is your authorization. The authority will let you do it, and somebody says, why did you do that thing? And they say, the authority authorized it. The authority tells me, I should do this. </s><s>[INST] Why aren't you doing it? So, the authority is often pushing for the conservative... [/INST] Well, no, so for example, we just think about- in a pandemic, even, right? You could just think, I'll just stay home and close all the doors, or I'll just ignore You could just think of some very simple strategy that might be defensible if there were no authorities. But authorities might be able to, no more than that, they might be able to look at some evidence, draw a more context-dependent conclusion, declare it as the authority's opinion, and then other people might follow that, and that could be better than doing nothing. </s><s>[INST] So you mentioned WHO, the world's most beloved organization. So, you know, this is me speaking in general, WHO and CDC has been kind of, depending on degrees and details, just not behaving as I would have imagined in the best possible evolution of human civilization, authorities should act. They seem to have failed in some fundamental way in terms of leadership in a difficult time for our society. [/INST] Can you say what are the pros and cons of this particular authority? So, again, if there were no authorities whatsoever, no accepted authorities, then people would sort of have to sort of randomly pick different local authorities who would conflict with each other, and then they'd be fighting each other about that, or just not believe anybody and just do some initial default action that you would always do without responding to context. So the potential gain of an authority is that they could no more than just basic ignorance, and if people followed them, they could both be more informed than ignorance and all doing the same thing, so they're each protected from being accused or complained about. That's the idea of an authority. That would be the good idea. What's the con? How does that go wrong? The con is that if you think of yourself as the authority and asking, what's my best strategy as an authority, it's unfortunately not to be maximally informative. So you might think the ideal authority would not just tell you more than ignorance. It would tell you as much as possible. It would give you as much detail as you could possibly listen to and manage to assimilate, and it would update that as frequently as possible or as frequently as you were able to listen and assimilate. And that would be the maximally informative authority. The problem is there's a conflict between being an authority or being seen as an authority and being maximally informative. That was the point of my blog post that you're pointing out to here. That is, if you look at it from their point of view, they won't long remain the perceived authority if they are too incautious about how they use that authority. And one of the ways to be incautious </s><s>[INST] would be to be too informative. Okay, that's still in the protocol for me. Because you're talking about the tensions that are very data-driven and very honest. And I would hope that authorities struggle with that. How much information to provide to people to maximize outcomes. Now, I'm generally somebody that believes more information is better because I trust in the intelligence of people. But I'd like to mention a bigger con on authorities, which is the human question. This comes back to global government and so on. Is that, you know, there's humans that sit in chairs during meetings in those authorities. They have different titles. It's for humans form hierarchies. And sometimes those titles get to your head a little bit. And you start to want to think, how do I preserve my control over this authority? As opposed to thinking through like, what is the mission of the authority? What is the mission of WHO and the other such organization? And how do I maximize the implementation of that mission? You start to think, well, I kind of like sitting in this big chair at the head of the table. I'd like to sit there for another few years, or better yet, I want to be remembered as the person who in a time of crisis was at the head of this authority and did a lot of good things. So you stop trying to do good under what good means given the mission of the authority. And you start to try to carve a narrative, to manipulate the narrative. First, in the meeting room, everybody around you, just a small little story you tell yourself. Then you interns, the managers, throw out the whole hierarchy of the company. Okay, once everybody in the company or in the organization believes this narrative, now you start to control the release of information, not because you're trying to maximize outcomes, but because you're trying to maximize the effectiveness of the narrative that you are truly a great representative of this authority in human history. And I just feel like those human forces, whenever you have an authority, it starts getting to people's heads. One of the most, me as a scientist, one of the most disappointing things to see during the pandemic is the use of authority from colleagues of mine to roll their eyes, to dismiss other human beings, just because they got a PhD, just because they're an assistant associate full faculty, just because they are deputy head of ex-organization, NIH, whatever the heck the organization is, just because they got an award of some kind. And at a conference, they won a best paper award seven years ago, and then somebody shook their hand and gave them a medal, and maybe it was a president. And it's been 20, 30 years that people have been patting them on the back saying how special they are, especially when they're controlling money and getting sucked up from other scientists who really want the money in a self-deception kind of way. They don't actually really care about your performance. And all of that gets to your head, and no longer are you the authority that's trying to do good and less than the suffering in the world, you become an authority that just wants to maximize, self-preserve yourself [/INST] in a sitting on a throne of power. So this is core to sort of what it is to be an economist. I'm a professor of economics. There you go, with the authority again. No, so it's about saying. Just joking, yes. We often have a situation where we see a world of behavior, and then we see ways in which particular behaviors are not sort of maximally socially useful. And we have a variety of reactions to that. So one kind of reaction is to sort of morally blame each individual for not doing the maximally socially useful thing. </s><s>[INST] The authority again, no. [/INST] Under perhaps the idea that people could be identified and shamed for that and maybe induced into doing the better thing if only enough people were calling them out on it, right? But another way to think about it is to think that people sit in institutions with certain stable institutional structures and that institutions create particular incentives for individuals and that individuals are typically doing whatever is in their local interest </s><s>[INST] in the context of that institution, [/INST] loving them out, and then, you know, perhaps to less blame individuals for winning their local institutional game and more blaming the world for having the wrong institution. So economists are often like wondering what are the institutions we could have instead of the ones we have and which of them might promote better behavior. And this is a common thing we do all across human behavior, is to think of, what are the institutions we're in, and what are the alternative variations we can imagine, and then to say which institutions would be most productive. I would agree with you, that our information institutions, that is, the institutions, by which we collect information and aggregate it and share it with people are especially broken in the sense of far from the ideal of what would be the most cost-effective way to collect and share information. But then the challenge is to try to produce better institutions. And as an academic, I'm aware that academia is particularly broken in the sense that we give people incentives to do research that's not very interesting or important because basically they're being impressive. And we actually care more about whether academics are impressive than whether they're interesting or useful. And I'm happy to go into detail with lots of different known institutions and their known institutional failings, ways in which those institutions produce incentives that are mistaken. And that was the point of the post we started with talking about the authorities if I need to be seen as an authority, that's at odds with my being informative and I might choose to be the authority instead of being informative because that's my institutional incentives. </s><s>[INST] And if I may, I'd like to given that beautiful picture of incentives and individuals that that you just painted. Let me just apologize for a couple of things. One, I often put too much blame on leaders of institutions versus the incentives that govern those institutions. And as a result of that, I've been, I believe too critical of Anthony Fauci, too emotional about my criticism of Anthony Fauci. And I like to apologize for that because I think there's deeper truth to think about. There's deeper incentives to think about. That said, I do sort of, I'm a romantic creature by nature. I romanticize Winston Churchill. And when I think about Nazi Germany, I think about Hitler more than I do about the individual people of Nazi Germany. You think about leaders, you think about individuals, not necessarily the parameters, the incentives to govern the system that, because it's harder. It's harder to think through deeply about the models from which those individuals arise, but that's the right thing to do so. But also I don't apologize for being emotional sometimes [/INST] and being- I'm happy to blame the individual leaders in the sense that, you know, I might say, well, you should be trying to reform these institutions if you're just there to like get promoted and look good at being at the top, but maybe I can blame you for your motives and your priorities in there. But I can understand why the people at the top would be the people who are selected for having the priority of primarily trying to get to the top. </s><s>[INST] I get that. Can I maybe ask you about particular universities? They've received, like science has received an increase in distrust overall as an institution, which breaks my heart because I think science is beautiful as a not maybe not as an institution, but as one of the things, one of the journeys that humans have taken on. The other one is university. I think university is actually a place, for me at least, in the way I see it, is a place of freedom of exploring ideas, scientific ideas, engineering ideas, more than a corporate, more than a company, more than a lot of domains in life. It's not just in its ideal, but in its implementation, a place where you can be a kid for your whole life and play with ideas. And I think with all the criticism that universities still not currently receive, I think they, I don't think that criticism is representative of universities. They focus on very anecdotal evidence of particular departments, particular people, but I still feel like there's a lot of place for freedom of thought, at least at MIT, at least in the fields I care about, in particular kind of science, particular kind of technical fields, mathematics, computer science, physics, engineering, so robotics, artificial intelligence. This is a place where you get to be a kid. Yet there is bureaucracy that's rising up. There's more rules, there's more meetings, and there's more administration, having PowerPoint presentations, which to me, you should be more of a renegade explorer of ideas and meetings destroy. They suffocate that radical thought that happens when you're an undergraduate student and you can do all kinds of wild things when you're a graduate student. Anyway, all that to say, you've thought about this aspect too. Is there something positive, insightful you could say about how we can make for better universities in the decades to come, this particular institution? [/INST] How can we improve them? I hear that centuries ago, many scientists and intellectuals were aristocrats. They had time and could, if they chose, choose to be intellectuals. That's a feature of the combination that they had some source of resources that allowed them leisure and that the kind of competition they were faced in among aristocrats allowed that sort of a self-indulgence or self-pursuit at least at some point in their lives. The analogous observation is that university professors often have sort of freedom and space to do a wide range of things, </s><s>[INST] and I am certainly enjoying that as a tenured professor. You're a really, sorry to interrupt, a really good representative of that, just the exploration you're doing, the depth of thought that most people are afraid to do the kind of broad thinking that you're doing, [/INST] which is great for that. The fact that that can happen is a combination of these two things analogously. One is that we have fierce competition to become a tenured professor, but then once you become tenured, we give you the freedom to do what you like, and that's a happenstance. It didn't have to be that way, and in many other walks of life, even though people have a lot of resources, et cetera, they don't have that kind of freedom set up. So I think we're kind of, I'm kind of lucky that tenure exists and that I'm enjoying it, but I can't be too enthusiastic about this unless I can approve of sort of the source of the resources that's paying for all this, right? So for the aristocrat, if you thought they stole it in war or something, you wouldn't be so pleased, whereas if you thought they had earned it or their ancestors had earned this money that they were spending as an aristocrat, then you could be more okay with that, right? So for universities, I have to ask, where are the main sources of resources that are going to the universities and are they getting their money's worth? Are they getting a good value for that payment, right? So first of all, there's students and the question is, are students getting good value for their education and you know, each person is getting value in the sense that they are identified shown to be a more capable person which is then worth more salary as an employee later, but there is a case for saying there's a big waste to the system because we aren't actually changing the students or educating them, we're more sorting them or labeling them and that's a very expensive process to produce that outcome and part of the expense is the you know freedom of from tenure I get. So I feel like I can't be too proud of that because it's basically a tax on all these young students to pay this enormous amount of money in order to be labeled as better whereas I feel like we should be able to find cheaper ways of doing that. The other main customer is researcher patrons like the unit the government or other foundations and then the question is are they getting their money worth out of the money they're paying for research to happen and my analysis is they don't actually care about the research progress they are mainly buying an affiliation with credentialed impressiveness on the part of the researchers they mainly pay money to researchers who are impressive and have high, you know, impressive affiliations and they don't really much </s><s>[INST] care what research project happens as a result, you know. Is that a cynical? So there's a deep truth to that cynical perspective, is there a less cynical perspective that they do care about the long-term investment into the [/INST] progress of science and and humanity? Well, they might personally care but they're stuck in an equilibrium wherein they basically most foundations like governments or research or like the Ford Foundation, the individuals there are rated based on the prestige they bring to that organization. Even if they might personally want to produce more intellectual progress, they're in a competitive game where they don't have tenure and they need to produce this prestige. Once they give grant money to prestigious people, that is the thing that shows that they have achieved prestige for the organization and that's what they need to do in order </s><s>[INST] to retain their position. You do hope that there's a correlation between prestige and actual competence? [/INST] Of course, there is a correlation. The question is just, could we do this better some other way? Yes. I think it's pretty clear we could. </s><s>[INST] What is harder to do is move the world to a new equilibrium where we do that instead. What are the components of the better ways to do it? Is it money, the sources of money and how the money is allocated to give the individual [/INST] researchers freedom? Years ago, I started studying this topic exactly because this was my issue and this was many decades ago now and I spent a long time and my best guess still is prediction markets, betting markets. If you as a research patron want to know the answer to a particular question like what's the mass of the electron neutrino, then what you can do is just subsidize a betting market in that question and that will induce more research into answering that question because the people who then answer that question can then make money in that betting market with the new information they gain. That's a robust way to induce more information on a topic. If you want to induce an accomplishment, you can create prizes. There's of course a long history of prizes to induce accomplishments. moved away from prizes, even though we once had used them a far more often than we did today. And there's a history to that. And for the customers who want to be affiliated with impressive academics, which is what most of the customers want, students, journalists, and patrons, I think there's a better way of doing that, which I just wrote about in my second most recent blog post. Can you explain? Sure. What we do today is we take sort of acceptance by other academics recently as our best indication of their deserved prestige. That is recent publications, recent job affiliation, institutional affiliations, recent invitations to speak, recent grants. We are today taking other impressive academics' recent choices to affiliate with them as our best guesstimate of their prestige. I would say we could do better by creating betting markets in what the distant future will judge to have been their deserved prestige looking back on them. I think most intellectuals, for example, think that if we looked back two centuries, say two intellectuals from two centuries ago, and tried to look in detail at their research and how it influenced future research and which path it was on, we could much more accurately judge their actual deserved prestige. That is who was actually on the right track, who actually helped, which will be different than what people at the time judged using the immediate indications at the time of which position they had or which publications they had or things like that. </s><s>[INST] In this way, if you think from the perspective of multiple centuries, you would higher prioritize true novelty, you would disregard the temporal proximity, like how recent the thing is, and you would think, what is the brave, the bold, the big, novel idea that this... And you would actually... [/INST] You would be able to rate that because you could see the path with which ideas took, which things had dead ends, which led to what other followings. You could, looking back centuries later, have a much better estimate of who actually had what long-term effects on intellectual progress. So my proposal is we actually pay people in several centuries to do this historical analysis. And we have prediction markets today where we buy and sell assets, which will later off pay off in terms of those final evaluations. And so now we will be inducing people today to make their best estimate of those things by actually looking at the details of people and setting the prices accordingly. So my proposal would be we rate people today on those prices today. So instead of looking at their list of publications or affiliations, you look at the actual price </s><s>[INST] of assets that represent people's best guess of what the future will say about them. That's brilliant. So this concept of idea futures, can you elaborate what this would entail? [/INST] I've been elaborating two versions of it here. So one is, if there's a particular question, say the mass of the electron neutrino, and what you as a patron want to do is get an answer to that question, then what you would do is subsidize a betting market in that question under the assumption that eventually we'll just know the answer and we can pay off the bets that way. And that is a plausible assumption for many kinds of concrete intellectual questions like </s><s>[INST] what's the mass of the electron neutrino? In this hypothetical world that you're constructing that may be a real world, do you mean literally financial? Yes, literal. [/INST] Very literal. Yes, literal. Very cash. Very direct and literal, yes. Well, crypto was funny. So the idea would be research labs would be for profit. They would have, as their expense, paying researchers to study things, and then their profit would come from using the insights the researchers gains to trade in these financial markets, just like hedge funds today make money by paying researchers to study firms and then making their profits by trading on those, that </s><s>[INST] insight in the ordinary financial markets. And the market would, if it's efficient, would be able to become better and better predicting the powerful ideas that the [/INST] individual is able to generate. The variance around the mass of the electron neutrino would decrease with time as we learned that value of that parameter better and any other parameters </s><s>[INST] that we wanted to estimate. You don't think those markets would also respond to recency of prestige [/INST] and all those kinds of things? They would respond, but the question is, if they might respond incorrectly, but if you think they're doing it incorrectly, you have a profit opportunity where you can go fix it. So we'd be inviting everybody to ask whether they can find any biases or errors in the current ways in which people are estimating these things from whatever clues they have. </s><s>[INST] There'll be a correction. There's a big incentive for the correction mechanism. In academia, [/INST] currently, it's the safe choice to go with the prestige and there's no... Even if you privately </s><s>[INST] think that the prestige is overrated. Even if you think strongly that it's overrated. Still, you don't have an incentive to defy that publicly. You're going to lose a lot unless you're a contrarian that writes brilliant blogs and then you could talk about it in the podcast. [/INST] Right. Initially, this was my initial concept of having these betting markets on these key parameters. What I then realized over time was that that's more what people pretend to care about. What they really mostly care about is just who's how good. That's what most of the system is built on is trying to rate people and rank them. I designed this other alternative based on historical evaluation centuries later just about who's how good because that's what I think most of the customers really care about. Customers. I like the word customers here. Humans. Every major area of life, which has specialists who get paid to do that thing, </s><s>[INST] must have some customers from elsewhere who are paying for it. Who are the customers for the mass of the neutrino? Yes, I understand a sense people [/INST] who are willing to pay for a thing. That's an important thing to understand about anything. Who are the customers? What's the product? Medicine, education, academia, military, etc. That's part of the hidden motives analysis. Often people have a thing they say about what the product is and who the customer is and maybe you need to dig a little deeper to find out what's really going </s><s>[INST] on. A lot deeper. You've written that you seek out quote viewquakes. You're able as an intelligent black box, word generating machine. You're able to generate a lot of sexy words. I like it. I love it. Viewquakes, which are insights which dramatically changed my world view, your world view. You write, I loved science fiction as a child, studied physics and artificial intelligence for a long time each, and now study economics and political science, all fields full of such insights. So let me ask, what are some viewquakes or a beautiful surprising idea to you from each of those fields, physics, AI, economics, political science? I know it's a tough question. Something [/INST] that springs to mind about physics, for example, that just is beautiful. I mean, right from the beginning, say special relativity was a big surprise. You know, most of us have a simple concept of time and it seems perfectly adequate for everything we've ever seen. And to have it explain to you that you need to sort of have a mixture concept of time and space where you put it into the space-time construct, how it looks different from different perspectives, that was quite a shock. And that was, you know, such a shock that it makes you think, what else do I know that, you know, isn't the way it seems? Certainly quantum mechanics is certainly another enormous shock in terms of from your point, you know, you have this idea that there's a space and then there's, you know, point particles at points and maybe fields in between. And quantum mechanics is just a whole different representation. It looks nothing like what you would have thought as sort of the basic representation of the physical world. And that was quite a surprise. What would you say </s><s>[INST] is the catalyst for the viewquake in theoretical physics in the 20th century? Where does that come from? So the interesting thing about Einstein, it seems like a lot of that came from like almost thought experiments. It wasn't almost experimentally driven. And with, actually, I don't know the full story of quantum mechanics. How much of it is experiment, like where, if you look at the full trace of idea generation there, of all the weird stuff that falls out of quantum mechanics, how much of that was the experimentalist? How much was it the theoreticians? But usually in theoretical physics, the theories lead the way. So maybe can you elucidate like [/INST] what is the catalyst for these? The remarkable thing about physics and about many other areas of academic intellectual life is that it just seems way overdetermined. That is, if it hadn't been for Einstein or if it hadn't been for Heisenberg, certainly within a half a century, somebody else would have come up with essentially the same things. Is that something you believe? Yeah. Yes. So I think when you look at sort of just the history of physics and the history of other areas, some areas like that there's just this enormous convergence. The different kind of evidence that was being collected was so redundant in the sense that so many different things revealed the same things that eventually you just kind of have to accept it because it just gets obvious. Yeah, so if you look at the details, of course, you know, Einstein did it for somebody else, and it's well worth celebrating Einstein for that. And, you know, we, by celebrating the particular people who did something first or came across something first, we are encouraging all the rest to move a little faster, to try to push us all a little faster, which is great, but I still think we would have gotten roughly to the same place within half-century. So sometimes people are special because of how much longer it would have taken. So some people say general relativity would have taken longer without Einstein than other things. I mean, Heisenberg quantum mechanics, I mean, there were several different formulations of quantum mechanics all around the same few years, means no one of them made that much of a difference. We would have had pretty much the same thing regardless of which of them did it exactly when. Nevertheless, I'm happy to celebrate them all. But this is a choice I make in my research. That is, when there's an area where there's lots of people working together, you know, who are, of course, sort of scoping each other and getting getting your results just before somebody else does. You ask, how much of a difference would I make there? You know, at most I could make something happen a few months before somebody else. And so I'm less worried about them missing things, so when I'm trying to help the world like doing research, I'm looking for neglected things, I'm looking for things that </s><s>[INST] nobody's doing it. If I didn't do it, nobody would do it. Nobody would do it... Or at least... In the next ten to twenty years. Same with general relativity. [/INST] The whole... You know, it might take another ten, twenty, thirty... Or at least for a long time. 20 years kind of thing. Same with the wood 50 years. So that's the place where you can have the biggest impact is finding the things that </s><s>[INST] nobody would do unless you did them. And then that's when you get the big view quake, the insight. So what about artificial intelligence? Would it be the EMs, the emulated minds? What idea, whether that struck you [/INST] in the shower one day, or are they, you just. Clearly the biggest view quake in artificial intelligence is the realization of just how complicated our human minds are. So most people who come to artificial intelligence from other fields or from relative ignorance, a very common phenomenon, which you must be familiar with is that they come up with some concept and then they think that must be it. Once we implement this new concept, we will have it, we will have full human level or higher artificial intelligence, right? And they're just not appreciating just how big the problem is, how long a row is, just how much is involved because that's actually hard to appreciate when we just think it seems really simple and studying artificial intelligence, going through many particular problems, looking at each problem, all the different things you need to be able to do to solve a problem like that, makes you realize all the things your minds are doing that you are not aware of. It's that vast subconscious that you're not aware, that's the biggest view cave from artificial intelligence by far. </s><s>[INST] For most people who study artificial intelligence, is it to see just how hard it is? I think that's a good point, but I think it's a very early view quake. It's when the Dunning-Kruger crashes hard. It's the first realization that humans are actually quite incredible, the human mind, the human body is quite incredible. There's a lot of different parts to it. It's already been so long for me that I've experienced that view quake that for me, I now experience the view quakes of, holy shit, this little thing is actually quite powerful, like neural networks. I'm amazed because you've become almost cynical after that first view quake of like, this is so hard, like evolution did some incredible work to create the human mind. But then you realize, just because you have, you've talked about a bunch of simple models, that simple things can actually be extremely powerful, that maybe emulating the human mind is extremely difficult, but you can go a long way with a large neural network. You can go a long way with a dumb solution. It's that Stuart Russell thing with the reinforcement learning, holy crap, you can go quite a long [/INST] way with a simple thing. </s><s>[INST] But we still have a very long road to go, but nevertheless. I can't, I refuse to sort of know the road, the road is full of surprises. So long is an interesting, like you said, with the six hard steps that humans have to take to arrive at where we are from the origin of life on earth. So it's long maybe in the statistical improbability of the steps that have to be taken, but in terms of how quickly those steps could be taken, I don't know if my intuition says it's, if it's hundreds of years away or if it's a couple of years away, I prefer to measure [/INST] long. Sure, pretty confidence at least a decade and mildly confidence at least three decades. </s><s>[INST] I can steal man in either direction. [/INST] I prefer to measure that journey in Elon Musk's, that's a new, we don't get Elon Musk very </s><s>[INST] often so that's a long time scale. For now, I don't know, maybe you can clone or maybe multiply or even know what Elon Musk, what that is. What is that? That's a good question. Exactly. Well, that's an excellent question. How does that fit into the models of three parameters that are required for becoming [/INST] a grabby alien civilization? That's the question of how much any individual makes in the long path of civilization over time. Yes. And that's the topic of historians and people to try to focus on individuals and how much of a difference they make. And certainly some individuals make a substantial difference in the modest term, right? Like you know, certainly without Hitler being Hitler in the role he took, European history would have taken a different path for a while there. But if we're looking over like many centuries longer term things, most individuals do fade </s><s>[INST] in their individual influence. So maybe- Even Einstein. Even Einstein. Even Einstein, no matter how sexy your hair is, you will also be forgotten in the long arc of history. So you said at least 10 years. [/INST] So let's talk a little bit about this AI point. </s><s>[INST] Even Einstein. Of how we achieve, how hard is the problem of solving intelligence by engineering artificial intelligence that achieves human level, human like qualities that we associate with intelligence. How hard is this? [/INST] What are the different trajectories that take us there? One way to think about it is in terms of the scope of the technology space you're talking about. So let's take the biggest possible scope, all of human technology, right? The entire human economy. So the entire economy is composed of many industries, each of which have many products with many different technologies supporting each one. At that scale, I think we can accept that most innovations are a small fraction of the total. That is usually have relatively gradual overall progress and that individual innovations that have a substantial effect that total are rare, and their total effect is still a small percentage of the total economy, right? There's very few individual innovations that made a substantial difference to the whole economy, right? What are we talking? Steam engine, shipping containers, you know, a few things. Hah, shipping containers deserves </s><s>[INST] to be up there with steam engines, honestly. Shipping containers deserves to be up there with steam. Can you say exactly shipping containers revolutionized shipping, shipping is very important? But placing that is shipping containers. So you're saying you wouldn't have some of the magic of the supply chain, all that without shipping containers. Made a big difference, absolutely. Interesting, that's something to look into. I we shouldn't we shouldn't take that tangent although I'm tempted to do but anyway, so there's a few just a few [/INST] Innovations right so at the scale of the whole economy, right now as you move down to a much smaller scale You will see individual innovations having a bigger effect, right? So if you look at I don't know lawnmowers or something I don't know about the innovations lawnmower But there are probably like steps where you just had a new kind of lawnmower and that made a big difference to mowing lawns Because you're focusing on a smaller part of the whole technology space, right? So And you know sometimes like military technology. There's a lot of military technologies a lot of small ones But every once in a while a particular military weapon like makes a big difference but still even so mostly overall they're making modest differences to a Something that's increasing relatively say like US military is the strongest in the world consistently for a while no one weapon in the last 70 years has like Made a big difference in terms of the overall prominence of the US military Right because that's just saying even though every once in a while even then recent Soviet hyper missiles or whatever. They are they aren't Changing the overall balance dramatically, right? So when we get to AI now that now I can frame the question How big is AI basically if so one way of thinking about AI is it's just all mental tasks then you ask what fraction of tasks are mental tasks and then I go a lot and then if I think of AI is like half of everything then I think well It's got to be composed of lots of parts where anyone innovation is only a small impact right now If you think no, no, no AI is like AGI and then you think AGI is a small thing Like there's only a small number of key innovations that will enable it. Now you're thinking there could be a bigger Chunk that you might find that would have a bigger impact. So the way I would ask you to frame these things in terms of the chunkiness of different areas of technology In part in terms of how big there is that if you take ten chunky areas and you add them together </s><s>[INST] The total is less chunky. Yeah, but don't you are you able until you solve the fundamental core? Parts of the problem to estimate the chunkiness of that problem [/INST] Well, if you have a history of prior chunkiness, that could be your best estimate for future chunkiness So for example, I mean even at the level of the world economy, right? We've had this what 10,000 years of civilization Well, that's only a short time. You might say oh that that doesn't predict future chunkiness But you know, it looks relatively steady and consistent We can say even in computer science. We've had, you know, 70 years of computer science We have enough data to look at chunkiness of computer science like when were there algorithms or approaches that made a big chunky difference and you know Versus and how large a fraction of those that was that and I'd say mostly in computer science </s><s>[INST] Most innovation has been relatively small chunks. The bigger chunks have been rare. Well, this is the interesting thing this is about AI and just algorithms in general is You know page rank so Google's right so Sometimes it's a simple algorithm that by itself is Not that useful but the scale in context and in a context that's scalable Like depending on the guy. Yeah, depending on the context is all of a sudden the powers revealed and there's something I guess that's the nature of chunkiness is That you get things that can reach a lot of people simply [/INST] Can be quite chunky. So one so one standard story about algorithms is to say algorithms have a fixed cost plus a Marginal cost and so In history when you had computers are very small you tried all the algorithms had low fixed costs and you look for the best of those But over time as computers got bigger you could afford to do larger fixed cost and try those and some of those had More effective algorithms in terms of their marginal cost and that in fact You know that it roughly explains the long-term history where in fact the rate of algorithmic algorithmic improvement is about the same as the rate of hardware improvement, which is a remarkable coincidence. But it would be explained by saying, well, there's all these better algorithms you can't try until you have a big enough computer to pay the fixed cost of doing some trials to find out if that algorithm actually saves you on the marginal cost. And so that's an explanation for this relatively continuous history. So we have a good story about why hardware is so continuous, right? And you might think, why would software be so continuous with the hardware? But if there's a distribution of algorithms in terms of their fixed costs, and it's saved spread out at a wide log-normal distribution, then we could be sort of marching through that log-normal distribution, trying out algorithms with larger fixed costs and finding the ones </s><s>[INST] that have lower marginal costs. So would you say AGI, human-level, AI, even EM, EM, emulated minds, is chunky? [/INST] Like a few breakthroughs can take this. So an EM is, by its nature, chunky in the sense that if you have an emulated brain and you're 25% effective at emulating it, that's crap. That's nothing. Okay. So you pretty much need to emulate a full human brain. Is that obvious? Is that obvious? I think it's pretty obvious. I'm talking about, so the key thing is, you're emulating various brain cells, and so you have to emulate the input-output pattern of those cells. So if you get that pattern somewhat close, but not close enough, then the whole system just doesn't have the overall behavior you're looking for, right? But it could have functionally, functionally, some of the power of the overall strategy. So there'd be some threshold. The point is when you get close enough, then it goes over the threshold. It's like taking a computer chip and deleting every one percent of the gates, right? </s><s>[INST] No, that's, that's very chunky. But hope is that the emulating the human brain, I mean the human brain itself is not. [/INST] Sure. Sure. So, it has a certain level of redundancy and a certain level of robustness. And so, there's some threshold when you get close to that level of redundancy and robustness, then it starts to work. But until you, you know, until you get to that level it's just going to be crap, right? It's going to be just a big thing that isn't working gross. So we can be pretty sure that emulations is a big chunk in an economic sense, right? At some point, you'll be able to make one that's actually effective and enable substituting for humans. And then that will be this huge economic product that people will try to buy crazy now. You'll bring a lot of out of people's lives, so they'll be willing to pay for it. But it could be that, you know, the first emulation costs a billion dollars each, right? And then we have them, but we can't really use them. They're too expensive. The cost slowly comes down, and now we have less of a chunky adoption, right? That as the cost comes down, then we use more and more of them in more and more contexts, and that's a more continuous curve. So it's only if the first emulations are relatively cheap that you get a more sudden disruption to society. And that could happen if sort of the algorithm is the last thing you figure out how to do </s><s>[INST] or something. What about robots that capture some magic in terms of social connection? Robots, like we have a robot dog on the carpet right there, robots that are able to capture some magic of human connection as they interact with humans, but are not emulating the brain. What about those? [/INST] How far away? We're thinking about chunkiness or distance now. </s><s>[INST] So if you ask how chunky is the task of making a, you know, emulatable robot or something, [/INST] which chunkiness and time correlated. Right. It's about how far away it is or how suddenly it would happen. Chunkiness is how suddenly and, you know, difficulty is just how far away it is. But it could be a continuous difficulty. It could just be far away, but we'll slowly, steadily get there. Or there could be these thresholds where we reach a threshold and suddenly we can do a </s><s>[INST] lot better. Yeah. That's a good, I mean, question for both. I tend to believe that all of it, not just the M, but AGI too is chunky and human level [/INST] intelligence embodied in robots is also chunky. My best guess is the history of computer science and chunkiness so far seems to be my rough best guess for the chunkiness of AGI. Yeah. It is chunky. It's modestly chunky. Not that chunky. Right. Our ability to use computers for too many things in the economy has been moving relatively steadily. Overall, in terms of our use of computers in society, they have been relatively steadily improving for 70 years. </s><s>[INST] No, but I would say that's our ability to use computers for too many things. Okay. Okay. I would have to really think about that because neural networks are quite surprising. [/INST] Sure, but every once in a while we have a new thing that's surprising. But if you stand back, you know, we see something like that every 10 years or so. Some new innovations are gradual. </s><s>[INST] That has a big effect. [/INST] So moderately chunky. Yeah. The history of the level of disruption we've seen in the past would be a rough estimate of the level of disruption in the future, unless the future is, we're going to hit a chunky territory, much chunkier than we've seen in the past. </s><s>[INST] Well, I do think there's, it's like, like Cooney and like revolution type. It seems like the data, especially on AI is difficult to reason with because it's so recent. It's such a recent field in the span around for 50 years, I mean, 50, 60, 70, 80 years being recent. Okay. [/INST] That's the in the span around for 50 years. Okay. </s><s>[INST] That's the, that's how I'm, it's enough time to see a lot of trends, a lot of a few trends, a few trends. I think the internet computing, there's really a lot of interesting stuff has happened over [/INST] the past 30 years that I think the possibility of revolutions is likely than it was in, in the- I think for the last 70 years, there would have always been a lot of things that looked like that had a potential for revolutions. So we can't reason well about this. I mean, I think we can reason well by looking at the past trends, I would say the past trend is roughly your best guess for the future future. </s><s>[INST] No, but if I look back at the, at the things that might have looked like revolutions in in the 70s and 80s and 90s, they are less like the revolutions that appear to be happening now or the capacity of revolution that appear to be there now. First of all, there's a lot of more money to be made. So there's a lot more incentive for markets to do a lot of kind of innovation, it seems like in the AI space. But then again, there's a history of winters and summers and so on. So maybe we're just like riding a nice wave right now. [/INST] One of the biggest issues is the difference between impressive demos and commercial value. Yes. So often through the history of AI, we saw very impressive demos that never really translated much into commercial value. </s><s>[INST] Somebody who works on and cares about autonomous and semi-autonomous vehicles, tell me about it. So, and there again, we return to the number of Elon Musk's per year generated. That's the M, coincidentally, same initials as the M, very suspicious, very suspicious. We're gonna have to look into that. All right, two more fields that I would like to force and twist your arm to look for viewquakes and for beautiful ideas, economics. What is a beautiful idea to you about economics? You've mentioned a lot of them. [/INST] Sure. So as you said before, there's gonna be the first viewcake most people encounter that makes the biggest difference on average in the world, because that's the only thing most people ever see is the first one. And so, with AI, the first one is just how big the problem is. But once you get past that, you'll find others. Certainly for economics, the first one is just the power of markets. You might've thought it was just really hard to figure out how to optimize in a big complicated space and markets just do a good first pass for an awful lot of stuff. And they're really quite robust and powerful. And that's just quite the viewquake, where you just say, you know, just let up, if you wanna get in the ballpark, just let a market handle it and step back. And that's true for a wide range of things. It's not true for everything, but it's a very good first approximation. Most people's intuitions for how they should limit markets are actually messing them up. They're that good in sense, right? Most people when you go, I don't know if we wanna trust that, </s><s>[INST] well, you should be trusting that. What about, what are markets? Like just a couple of words. [/INST] So the idea is if people want something, then let other companies form to try to supply that thing. Let those people pay for their cost of whatever they're making and try to offer that product to those people. Let many people, many such firms enter that industry and let the customers decide which ones they want. And if the firm goes out of business, let it go bankrupt and let other people invest in whichever ventures they wanna try to attract customers to their version of the product. And that just works for a wide range of products and services. </s><s>[INST] And through all of this, there's a free exchange of information too. There's a hope that there's no manipulation of information [/INST] and so on, that you're making these- Even when those things happen, still just the simple market solution is usually better than the things you'll try to do to fix it. Then the alternative. That's a view crank. It's surprising. It's not what you would initially thought. </s><s>[INST] That's one of the great, I guess, inventions [/INST] of human civilization that trust the markets. Now, another view cake that I learned in my research that's not all of economics, but something more specialized is the rationality of disagreement. That is basically people who are trying to believe what's true in a complicated situation would not actually disagree. And of course, humans disagree all the time. So it was quite the striking fact for me to learn in grad school that actually rational agents would not knowingly disagree. And so that makes disagreement more puzzling and it makes you less willing to disagree. Humans are to some degree rational and are able to- Their priorities are different than just figuring out the truth, </s><s>[INST] which might not be the same as being irrational. That's another tangent that could take an hour. In the space of human affairs, political science, what is a beautiful, foundational, interesting idea to you, [/INST] a view quake in the space of political science? The main thing that goes wrong in politics </s><s>[INST] is people not agreeing on what the best thing to do is. That's the wrong thing. [/INST] So that's what goes wrong. That is when you say, what's fundamentally behind most political failures? It's that people are ignorant of what the consequences of policy is. And that's surprising because it's actually feasible </s><s>[INST] to solve that problem, which we aren't solving. So it's a bug, not a feature, that there's an inability to arrive at a consensus. [/INST] So most political systems, if everybody looked to some authority, say, on a question and that authority told them the answer, then most political systems are capable of just doing that thing. But that is, and so it's the failure to have trustworthy authorities. That is sort of the underlying failure behind most political failure. We invade Iraq, say, when we don't have an authority to tell us that's a really stupid thing to do. And it is possible to create more informative, trustworthy authorities. That's a remarkable fact about the world of institutions </s><s>[INST] that we could do that, but we aren't. Yeah, so that's surprising. [/INST] We could and we aren't. Another big view, correct, about politics is from the Elf in the Brain that most people, when they're interacting with politics, they say they want to make the world better and to make their city better, their country better. And that's not their priority. What is it? They want to show loyalty to their allies. They want to show their people. They're on their side, yes. Are there various tribes they're in? That's their primary priority. </s><s>[INST] And they do accomplish that. What is it? They want to show their people they're on their side. Yeah and the tribes are usually color-coded conveniently enough. What would you say, it's the Churchill question democracies, the crappiest form of government, but it's the best one we got. What's the best form of government? For this, our seven billion human civilization and the maybe as we get farther and farther, you mentioned a lot of stuff that's fascinating about human history as we become more forager-like and looking out beyond what's the best form of government in the next 50, 100 years as we become a multi-planetary species. [/INST] So the key failing is that we have existing political institutions and related institutions like media institutions and other authority institutions and these institutions sit in the vast space of possible institutions. And the key failing, we're just not exploring that space. So, I have made my proposals in that space and I think I can identify many promising solutions. And many other people have made many other promising proposals in that space. But the key thing is we're just not pursuing those proposals. We're not trying them out on small scales. We're not doing tests. We're not exploring the space of these options. That is the key thing we're failing to do. And if we did that, I am confident we would find much better institutions than when we're using now, </s><s>[INST] but we would have to actually try. So there are a lot of those topics. I do hope we get a chance to talk again. You're a fascinating human being. So I'm skipping a lot of tangents on purpose that I would love to take. You're such a brilliant person. There's so many different topics. Let me take a stroll into the deep human psyche [/INST] of Robin Hanson himself. So first- May not be that deep. I might just be all on the surface. What you see, what you get, there might not be much hiding behind it. </s><s>[INST] Some of the first fun is on the surface and- [/INST] I actually think this is true of many of the most successful, most interesting people you see in the world. That is they have put so much effort into the surface that they've constructed. And that's where they put all their energy. So somebody might be a statesman or an actor or something else and people want to interview them and they want to say like, what are you behind the scenes? What do you do in your free time? And you know what? Those people don't have free time. They don't have another life behind the scenes. They put all their energy into that surface. The one we are the one we're fascinated by and they kind of have to make up the stuff behind the scenes to supply it for you, </s><s>[INST] but it's not really there. Well, there's several ways of phrasing this. So one of it is authenticity, which is if you become the thing you are on the surface, if the depths mirror the surface, then that's what authenticity is. You're not hiding something, you're not concealing something. To push back on the idea of actors, they actually have often a manufactured surface that they put on and they try on different masks, and the depths are very different from the surface. And that's actually what makes them very not interesting to interview. If you're an actor who actually lives the role that you play, so like, I don't know, a Clint Eastwood type character who clearly represents the cowboy, like at least rhymes or echoes the person you play on the surface, that's authenticity. [/INST] Some people are typecast and they have basically one persona they play in all of their movies and TV shows. And so those people probably is the actual persona that they are, or it has become that over time. Clint Eastwood would be one I think of Tom Hanks </s><s>[INST] as an ever, I think they just always play the same person. And you and I are just both surface players. You're the fun, brilliant thinker and I am the suit wearing idiot full of silly questions. All right, that said, let's put on your wise Sage hat and ask you what advice would you give to young people today in high school and college about life, about how to live a successful life in career [/INST] or just in general that they can be proud of? Most young people, when they actually ask you that question that they usually mean is how can I be successful by usual standards? I'm not very good at giving advice about that because that's not how I tried to live my life. So I would more flip it around and say, you live in a rich society, you will have a long life, you have many resources available to you. Whatever career you take, you'll have plenty of time to make progress on something else. Yes, it might be better if you find a way to combine your career and your interests in a way that gives you more time and energy but there are often big compromises there as well. So if you have a passion about some topic or some thing that you think just is worth pursuing, you can just do it. You don't need other people's approval and you can just start doing whatever it is you think if we're doing it might take you decades but decades are enough to make enormous progress </s><s>[INST] on most all interesting things. And don't worry about the commitment of it. I mean, that's a lot of what people worry about is, well, there's so many options. And if I choose a thing and I stick with it, [/INST] I sacrifice all the other paths I could have taken. But I mean, so I switched my career at the age of 34 with two kids age zero and two, went back to grad school in social science after being a research software engineer. So it's quite possible to change your mind later in life. How can you have an age of zero? Less than one. </s><s>[INST] Okay. Oh, you index was, I got it. [/INST] Okay. Right. And you know, like people also ask what to read and I say textbooks. And until you've read lots of textbooks or maybe review articles, I'm not so sure you should be reading, you know, blog posts and Twitter feeds and even podcasts. I would say at the beginning, read the read, you know, this is our best, humanity's best summary of how to learn things is crammed into textbooks. Yeah, especially the ones on like introduction to biology. Yeah, everything, introduction to everything. Just read all the algorithms, read as many textbooks as you can stomach. And then maybe if you want to know more about a subject, find review articles. </s><s>[INST] You don't need to read the latest stuff for most topics. Yeah. And actually textbooks often have the prettiest pictures. There you go. And depending on the field, if it's technical than doing the homework problems at the end, it's actually extremely, extremely useful. Extremely powerful way to understand something. If you allow it, you know, I actually think of like high school and college, which you kind of remind me of, people don't often think of it that way, but you'll almost not again, get an opportunity to spend the time with a fundamental subject and like all the basics and everybody's forcing you like, everybody wants you to do it. And like, you'll never get that chance again to sit there, even though it's outside of your interest, biology, like in high school, I took AP biology, AP chemistry. I'm thinking of subjects I never again really visited seriously. And it was so nice to be forced into anatomy and physiology, to be forced into that world, to stay with it, to look at the pretty pictures, do certain moments to actually for a moment, enjoy the beauty of these, of like how cell works and all those kinds of things. And you're, somehow that stays, like the ripples of that fascination, that stays with you, even if you never do those, even if you never utilize those learnings [/INST] in your actual work. That's all sorts of stuff. A common problem, at least of many young people I meet, is that they're like feeling idealistic and altruistic, but in a rush. So, you know, the usual human tradition that goes back, you know, hundreds of thousands of years, is that people's productivity rises with time and maybe peaks around the age of 40 or 50. The age of 40, 50 is when you will be having the highest income, you'll have the most contacts, you will sort of be wise about how the world works. Expect to have your biggest impact then. Before then, you can have impacts, but you're also mainly building up your resources and abilities. That's the usual human trajectory, expect that to be true of you too. Don't be in such a rush to like accomplish enormous things at the age of 18 or whatever. I mean, you might as well practice trying to do things, but that's mostly about learning how to do things by practicing. There's a lot of things you can't do </s><s>[INST] unless you just keep trying them. And when all else fails, try to maximize the number of offspring [/INST] however way you can. That's certainly something I've neglected. I would tell my younger version of myself, try to have more descendants. Yes, absolutely. </s><s>[INST] It matters more than I realized at the time. Both in terms of making copies of yourself in mutated form and just the joy of raising them. [/INST] Sure, sure. I mean, the meaning even, you know, so in the literature on the value people get out of life, there's a key distinction between happiness and meaning. So happiness is how do you feel right now about right now? And meaning is how do you feel about your whole life? And, you know, many things that produce happiness don't produce meaning as reliably. And if you have to choose between them, you'd rather have meaning. And meaning is more goes along with sacrificing happiness sometimes. And children are an example of that. You get a lot more meaning out of children, </s><s>[INST] even if they're a lot more work. What do you think kids, children are so magical, like raising kids? Because I would love to have kids. And whenever I work with robots, there's some of the same magic when there's an entity that comes to life. And in that case, I'm not trying to draw too many parallels, but there's some echo to it, which is when you program a robot, there's some aspect of your intellect that is now instilled in this other moving being that's kind of magical. Or why do you think that's magical? And you said happiness and meaning, as opposed to a short- Meaningful. [/INST] Why is it meaningful? It's over-determined. Like I can give you several different reasons, all of which is sufficient. And so the question is, we don't know which ones are the correct reasons, but- It's such a technical, it's over-determined. Look it up. So, you know, I meet a lot of people interested in the future, interested in thinking about the future. They're thinking about how can I influence the future? But, you know, overwhelmingly in history so far, the main way people have influenced the future is by having children, overwhelmingly. And that's just not an incidental fact. You are built for that. That is, you're the sequence of thousands of generations, each of which successfully had a descendant. And that affected who you are. You just have to expect, and it's true that who you are is built to be, you know, expected to have a child, to want to have a child to have, that be a natural and meaningful interaction for you. And it's just true. It's just one of those things you just should have expected. </s><s>[INST] And it's not a surprise. Such a technical, it's over. Well, to push back and sort of, in terms of influencing the future, as we get more and more technology, more and more of us are able to influence the future in all kinds of other ways. Right. [/INST] Being a teacher, educator. Even so though, still most of our influence in the future has probably happened being kids. Even though we've accumulated more ways, other ways to do it. </s><s>[INST] You mean at scale, I guess the depth of influence, like really how much of much effort, how much of yourself you really put another human being. Do you mean both the raising of a kid, [/INST] or do you mean raw genetic information? Well, both, but raw genetics </s><s>[INST] is probably more than half of it. More than half. More than half. [/INST] Even in this modern world, </s><s>[INST] more than half genetics. Let me ask some dark, difficult questions if I might. Let's take a stroll into that place that may or may not exist. According to you, what's the darkest place you've ever gone to in your mind, in your life? A dark time, a challenging time in your life that you had to overcome? [/INST] Probably just feeling strongly rejected. And so I've been, I'm apparently somewhat emotionally scarred by just being very rejection-averse, which must have happened </s><s>[INST] because some rejections were just very scarring. At a scale in what kinds of communities are there to the individual scale? [/INST] I mean, lots of different scales, yeah. All the many different scales, still that rejection stings. </s><s>[INST] Hold on a second, but you're a contrarian thinker. You challenge the norms. Why, if you were scarred by rejection, why welcome it in so many ways at a much larger scale, constantly with your ideas? [/INST] It could be that I'm just stupid or that I've just categorized them differently than I should or something. Most rejection that I've faced hasn't been because of my intellectual ideas, so. Oh, so the ones. The intellectual ideas haven't been the thing to risk the rejection. </s><s>[INST] Oh, so the ones, the things that challenge your mind, taking you to a dark place, the more psychological rejections, so. [/INST] Well, you just asked me what took me to a dark place. You didn't specify it as sort of an intellectual dark place, I guess. Yeah, it just meant like what? </s><s>[INST] So intellectual is disjoint, or at least at a more surface level [/INST] than something emotional. Yeah, I would just think there are times in your life when you're just in a dark place and that can have many different causes. Most intellectuals are still just people and most of the things that will affect them are the kinds of things that affect people. They aren't that different necessarily. I mean, that's gonna be true for, like, I presume most basketball players are still just people and if you ask them what was the worst part of their life, it's gonna be this kind of thing that was the worst part of life for most people. So rejection early in life? Yeah, I think it's not in grade school probably, but you know, yeah, sort of like, you know, being a young, nerdy guy and feeling, you know, not in much demand or interest or, you know, later on lots of different kinds of rejection. But yeah, but I think that's, you know, most of us like to pretend we don't that much need other people, we don't care what they think, you know, it's a common sort of stance if somebody reject you or something, I didn't care about them anyway, you know, but I think to be honest, people really do care. </s><s>[INST] Yeah, we do seek that connection, that love. What do you think is the role of love in the human condition? [/INST] Opacity, in part. That is, love is one of those things where we know at some level it's important to us, but it's not very clearly shown to us exactly how or why or in what ways. There are some kinds of things we want we can just clearly see that we want and why we want that right? We know when we're thirsty and we know why we are thirsty. We know what to do about being thirsty And we know when it's over that we're no longer thirsty and we love isn't like that. </s><s>[INST] It's like, what do we seek from this? We're drawn to it, but we do not understand why we're drawn exactly because it's not just affection because if it was just affection we don't seem to be drawn to pure affection, we don't seem to be drawn to somebody who is like a servant, we don't seem to be necessarily drawn to [/INST] somebody that satisfies all your needs or something like that. So it's clearly something we want or need but we're not exactly very clear about it and that isn't kind of important to it. So I've also noticed there are some kinds of things you can't imagine very well. So if you imagine a situation, there's some aspects of the situation that you can imagine it being bright or dim, you can imagine it being windy, or you can imagine it being hot or cold. But there's some aspects about your emotional stance in a situation that's actually just hard to imagine or even remember. It's hard to, like, you can often remember an emotion only when you're in a similar sort of emotion situation, and otherwise you just can't bring the emotion to your mind as a... and you can't even imagine it, right? So there's certain kinds of emotions you can have, and when you're in that emotion, you can know that you have it and you can have a name and it's associated, but later on, I tell you, you know, remember joy and it doesn't come to mind. You're not able to replay it. Right. And it's sort of a reason why we, one of the reasons that pushes us to re-consume it and reproduce it is that we can't re-imagine it. </s><s>[INST] Well, there's a, it's interesting, because there's a Daniel Kahneman type of thing of like reliving memories, Which is, I'm able to summon some aspect of that emotion again by thinking about that situation from which that emotion came. So, a certain song ya can listen to it and you can feel the same way you felt the first [/INST] time you remember that song associated with certain things. Right, but you need to remember that situation in some sort of complete package. You can't just take one part off of it and then if you get that whole package again, </s><s>[INST] if you remember the whole feeling, you can't just take one part off of it. I can't just take one part. It's some fundamental aspect of that whole experience that from which the feeling of growth. Actually, the feeling is probably different in some way, it can be more pleasant or less pleasant than the feeling you felt originally, in that it morphs over time every time you replay that memory. It is interesting. You're not able to replay the feeling perfectly. You don't remember the feeling. [/INST] You remember the facts of the events. There's a sense in which over time we expand our vocabulary as a community of language, And that allows us to have more feelings and know that we are feeling them. That is, you can have a feeling but not have a word for it and then you don't know how to categorize it or even what it is and whether it's the same as something else. But once you have a word for it you can sort of pull it together more easily. And so I think over time we are having a richer palette of feelings because we have more words for them. </s><s>[INST] What has been a painful loss in your life? Maybe somebody or something that's no longer in your life but played an important part of your life. Youth. That's a concept. No, it has to be. [/INST] No, it has to be. I was once younger. I had more health than I had vitality. </s><s>[INST] I was handsome or I've lost my health. Do you see that as a different person? Maybe you've lost that person. [/INST] Certainly. Yes, absolutely. I'm a different person than I was when I was younger and I'm not who, I don't even remember exactly what he was. I don't remember as many things from the past as many people do. So in some sense, I've just lost a lot of my history by not remembering it. But does that- And I'm not that person anymore. That person is gone and I don't have any of their abilities. </s><s>[INST] Is it a painful loss though? Yeah. Or is it a, why is it painful? Because you're wiser. I mean, there's so many things that are beneficial to getting older. [/INST] Yeah. Right, but I just was this person and I felt assured that I could continue to be that person. And you're no longer that person. And he's gone and I'm not him anymore. </s><s>[INST] He died without fanfare or a funeral. And the person you are today talking to me, that person will be changed to- Yes. Maybe in 20 years he won't be there anymore. And a future person. [/INST] Maybe in 20 years he won't be there anymore. But for M's this will be less of a problem. For M's they would be able to save an archived copy of themselves at each different age. </s><s>[INST] And they could turn it on periodically and go back and talk to it. So we play. You think some of that will be... So with emulated minds, with M's, there's a digital cloning that happens. And do you think that makes you less special if you're cloneable? Like, does that make you... the experience of life, the experience of a moment, the scarcity of that moment, the scarcity of that experience, isn't that a fundamental part of what makes that experience so delicious? [/INST] So rich of feeling? I think if you think of a song that lots of people listen to that are copies all over the world, </s><s>[INST] we're going to call that a more special song. Yeah, yeah. So there's a perspective on copying and cloning [/INST] where you're just scaling happiness versus degrading. I mean, each copy of a song is less special if there are many copies, but the song itself is more special if there are many copies. </s><s>[INST] In a mess, right, you're actually spreading the happiness even if it diminishes over a larger number of people at scale and that increases the overall happiness in the world. And then you're able to do that with multiple songs. [/INST] Is a person who has an identical twin more or less special? </s><s>[INST] Well, the problem with identical twins is, you know, [/INST] you is like just two with M's. But two is different than one, so. But I think an identical twin's life is richer for having this other identical twin, somebody who understands them better than anybody else can. From the point of view of an identical twin, I think they have a richer life for being part of this couple, each of which is very similar. Now if you said if we lose one of the identical twins, would the world miss it as much because you've got the other one and they're pretty similar. Maybe from the rest of the world's point of view, they suffer less of a loss when they lose one of the identical twins. But from the point of view of the identical twin themselves, their life is enriched by having a twin. </s><s>[INST] See, but the identical twin copping happens at the place of birth. that's different than copying after you've done some of the environment like the nurture at the [/INST] teenage or the in the 20s. Yes, that'll be an interesting thing for ems to find out all the different ways that can have different relationships to different people who have different degrees of similarity to them in time. Yeah. Yeah, man. But it seems like a rich space to explore and I </s><s>[INST] don't feel sorry for them. This sounds like interesting world to live in. And there could [/INST] be some ethical conundrums there and there. There will be many new choices to make that they don't make now. And then we discussed and I discussed that in the book, Age of Hymn, like say you have a lover and you make a copy of yourself, but the lover doesn't make a copy. </s><s>[INST] Well, now which one of you or are both still related to the lover? So should make now. So [/INST] we entitled to show up. Yes. So you'll have to make choices then when you split yourself, </s><s>[INST] which which of you inherit which unique things. Yeah. And of course, there'll be an equivalent increase in lawyers. Well, I guess you can clone the lawyers to help manage some of these negotiations of how to split property. The nature of owning, I mean, property is connected to individuals, [/INST] right? You only really need lawyers for this with an inefficient, awkward law that is not very transparent and able to do things. So, you know, for example, an operating system of a computer is a law for that computer. When the operating system is simple and clean, you don't need to hire a lawyer to make a key choice with the operator. You don't need a human in the loop. Just make a choice. Yeah. Right. So ideally we want a legal system that </s><s>[INST] makes the common choices easy and not require much overhead. And that's what this is making my rules. Yeah. Digitization of things further and further enables that. So the loss of a younger self, what about the loss of your life overall? Do you ponder your death, your [/INST] mortality? Are you afraid of it? I am a cryonics customer. That's what this little tag around my deck says. It says that if you find me in a medical situation, you should call these people to enable the cryonics transfer. So I am taking a long shot chance at living a much longer life. Can you explain what cryonics is? So when medical science gives up on me in this world, instead of burning me or letting worms eat me, they will freeze me or at least freeze my head. And there's damage that happens in the process of freezing the head, but once it's frozen, it won't change for a very long time. Chemically, it'll just be completely exactly the same. So future technology might be able to revive me. And in fact, I would be mainly counting on the brain emulation scenario, which doesn't require reviving my entire biological body. It means I would be in a computer simulation. And so that's, I think I've got at least a 5% shot at that. And that's immortality. Are you most likely </s><s>[INST] to say it won't happen, and therefore, I'm sad that it won't happen? Do you think immortality [/INST] is something that you would like to have? Well, I mean just like infinity, I mean, you can't know until forever, which means never, right? So all you can really, you know, the better choices at each moment do you want to keep going. So I would like at every moment </s><s>[INST] to have the option to keep going. You can't. The interesting thing about human experience is that the way you phrase it is exactly right. At every moment, I would like to keep going. But the thing that happens, leave them wanting more of whatever that phrase is. The thing that happens is over time, it's possible for certain experiences to become bland, and you become tired of them. And that actually makes life really unpleasant. Sorry, it makes that experience really unpleasant. And perhaps you can generalize that to life itself if you have a long enough horizon. [/INST] And so- </s><s>[INST] It might happen, but might as well wait and find out. [/INST] But then you're ending on suffering, you know? So in the world of brain amylations, I have more options. Now you can return yourself to life. I can make copies of myself, archive copies at various ages. And at a later age, I could decide that I'd rather replace myself with a new copy from a younger age. </s><s>[INST] So does a brain amylation still operate in physical space? So can we do, what do you think about like the metaverse and operating in virtual reality? So we can conjure up, not just emulate, not just your own brain and body, [/INST] but the entirety of the environment. Most brain amylations will in fact, most of their time in virtual reality. But they wouldn't think of it as virtual reality, they would just think of it as their usual reality. I mean, the thing to notice, I think in our world, most of us spend time, most time indoors. And indoors we are surrounded by walls covered with paint and floors covered with tile or rugs. Most of our environment is artificial. It's constructed to be convenient for us. It's not the natural world that was there before. A virtual reality is basically just like that. It is the environment that's comfortable and convenient for you. And, but if, if, when it's the right that environment for you, it's real for you, just like the room you're in right now most likely is very real for you. You're not focused on the fact that the paint is hiding the actual studs behind the wall and the actual wires and pipes and everything else. The fact that we're hiding that from you doesn't make it fake or unreal. </s><s>[INST] What are the chances that we're actually in the very kind of system that you're describing where the environment and the brain is being emulated and you're just replaying an experience when you were first did a podcast with Lex after, and now the person that originally launched this already did hundreds of podcasts with Lex, this is just the first time, and you like this time, because there's so much uncertainty. There's nerves, it could have gone any direction. [/INST] At the moment, we don't have the technical ability to create that an emulation, so we'd have to be postulating that in the future. We have that ability, and then they choose to evaluate </s><s>[INST] this moment now, postulating. Don't you think we could be in the simulation of that exact experience right now, we wouldn't be able to know? [/INST] So, one scenario would be, this never really happened. This only happens as a reconstruction later on. That's different than the scenario. This did happen the first time, and now it's happening again as a reconstruction. That second scenario is harder to put together because it requires this coincidence where between the two times, </s><s>[INST] we produce the ability to do it. No, but don't you think replay of memories, poor replay of memories is something that- That might be a possible thing in the future. You're saying it's harder than to conjure up things [/INST] from scratch. That might be a possible. It's certainly possible. So, the main way I would think about it is in terms of the demand for simulation versus other kinds of things. So, I've given this a lot of thought, because I first wrote about this long ago and Bostrom first wrote his papers about simulation argument, and I wrote about how to live in a simulation. So, the key issue is, the fraction of creatures in the universe that are really experiencing what you appear to be really experiencing relative to the fraction that are experiencing it in a simulation way, i.e. simulate it. So then the key parameter is at any one moment in time, creatures at that time, many of them, most of them are presumably really experiencing what they're experiencing, but some fraction of them are experiencing some past time where that past time is being remembered via their </s><s>[INST] simulation. [/INST] So to figure out this ratio, what we need to think about is basically two functions. One is how fast in time does the number of creatures grow? And then how fast in time does the interest in the past decline? Because at any one time, people will be simulating different periods in the past with different emphasis based on... I love the way you think so much. That's exactly right. So if the first function grows slower than the second one declines, then in fact, your </s><s>[INST] chances of being simulated are low at any one time. I love the way you think so much. [/INST] That's exactly right, yeah. So the key question is how fast does interest in the past decline relative to the rate at </s><s>[INST] which the population grows with time? Does this correlate to you? You earlier suggested that the interest in the future increases over time. Are those correlated, interest in the future versus interest in the past? [/INST] Why are we interested in the past? But the simple way to do it, as you know, like Google Ngrams has a way to type in a word and see how interest declines or rises over time, right? You can just type in a year and get the answer for that. If you type in a particular year, like 1900 or 1950, you can see with Google Ngram how interest in that year increased up until that date and decreased after it. And you can see that interest in a date declines faster than does the population grow with </s><s>[INST] time. [/INST] Brilliant. That is so interesting. </s><s>[INST] You can have the answer. That is so interesting. Wow! And that was your argument against, not against, to this particular aspect of the simulation. How much, um, past simulation there will be. We play of past memories. [/INST] We play of past memories. First of all, if we assume that, like, simulation of the past it's a small fraction of all the creatures at that moment, then it's about how fast? Now some people have argued plausibly that maybe most interest in the past falls with this fast function, but some unusual category of interest in the fast won't fall that fast quickly and then that eventually would dominate. </s><s>[INST] So that's a other hypothesis. Some category. So that very outlier specific kind of, yeah, okay, yeah, yeah, yeah, yeah, like really [/INST] popular kinds of memories, but like probably sex. And in a trillion years, there's some small research institute that tries to randomly select from all possible people in history or something to simulate. Yeah, yeah, yeah. So the question is how big is this research institute and how big is the future in a trillion years, right? And that's, that would be hard to say. But if we just look at the ordinary process by which people simulate recent errors. So if you look at, it's also true for movies and plays and video games, overwhelming they're interested in the recent past. There's very few video games where you play someone in the Roman empire, but even fewer where you play someone in the Egyptian empire. </s><s>[INST] Yeah, just different. It's just declined very quickly, but every once in a while that's brought back. But yeah, you're right. I mean, just if you look at the mass of entertainment, movies and games, it's focusing on the present recent past and maybe some, I mean, where does science fiction fit into this? It's sort of a, what is science fiction? I mean, it's a mix of the past and the present and some kind of manipulation of that to make [/INST] it more efficient for us to ask deep philosophical questions about a humanity, a humanity. The closest genre to science fiction is clearly fantasy, fantasy and science fiction and many bookstores and even Netflix or whatever categories, they're just lumped together. So clearly they have a similar function so that the function of fantasy is more transparent than the function of science fiction. So use that as your guide. What's fantasy for? It's just to take away the constraints of the ordinary world and imagine stories with much fewer constraints. Right? That's what fantasy is. </s><s>[INST] You are much less constrained. You are much less constrained. What's the purpose to remove constraints? Is it the escape from the harshness of the constraints of the real world or is it just remove constraints in order to explore some N getting deeper understanding of our world. What is it? I mean, why do people reach that? [/INST] I'm not a cheap fantasy reading kind of person. One story that it sounds plausible to me is that there are sort of these deep story structures that we love and we want to realize and then many details of the world getting their way. Fantasy takes all those obstacles out of the way and lets you tell the essential hero story or the essential love story, whatever essential story you want to tell. The reality and constraints are not in the way. And so science fiction can be thought of as like fantasy, except you're not willing to admit that it can't be true. So the future gives the excuse of saying, well, it could happen. And you accept some more reality constraints for the </s><s>[INST] illusion at least that maybe it could really happen. Maybe it could happen and that stimulates the imagination. The imagination is something really interesting about human beings. And it seems also to be an important part of creating really special things is to be able to first imagine them. With you and Nick Bostrom, where do you land on the simulation and all the mathematical ways of thinking it and just the thought experiment of it? Are we living in a simulation? [/INST] That was the just discussion we just had. That is, you should grant the possibility of being a simulation. You shouldn't be 100% confident that you're not. You should certainly grant a small probability. The question is, how large is that probability? </s><s>[INST] Oh, you're saying we would be misunderstood because I thought our discussion was about replaying things that already happened. [/INST] Right. But the whole question is, right now, is that what I am? Am I actually a replay from some distant future? </s><s>[INST] But it doesn't necessarily need to be a replay. It could be a totally new. You don't have to be an NPC. [/INST] Right. But clearly, I'm in a certain era with a certain kind of world around me. So either this </s><s>[INST] is a complete fantasy or it's a past of somebody else in the future. No. It could be a complete fantasy, though. [/INST] It could be, right? But then you have to talk about what's the fraction of complete fantasies. </s><s>[INST] I would say it's easy to generate a fantasy than to replay a memory, right? [/INST] Oh, but the fraction. We just look at the entire history of everything. Sure. We just say, but most things are real. Most things aren't fantasies. Therefore, the chance that my thing is real. So the simulation argument works stronger about sort of the past. We say, ah, but there's more future people than there are today. So you being in the past of the future makes you special relative to them, which makes you more likely to be in a simulation, right? If we're just taking the full count and saying in all creatures ever, what percentage are in simulations? Probably no more than 10%. </s><s>[INST] See, so what's the good argument for that? That most things are real. Yeah. Because it was Boston who says the other way, right? [/INST] Yeah. Because it was in a competitive world, in a world where people like have to work and have to get things done, then they have a limited budget for leisure. And so, you know, leisure things are less common than work things, like real things, right? That, that, that's just. </s><s>[INST] But if you look at the stretch of history in the universe, doesn't the ratio of leisure increase? [/INST] Isn't that what we, isn't that the for doing, isn't that the for? Now, we're looking at the fraction of leisure, which takes the form of something where the person doing the leisure doesn't realize it. Now there can be some fraction of that? That's much smaller, right? Yeah. Clue as four years or somebody is clueless in the process of supporting this, this leisure, right? It might not be the person leisurering somebody there, a supporting character or something, but still, that's got to be a pretty small fraction of leisure. </s><s>[INST] What you mentioned, the children, are one of the things that things that are a source of meaning, broadly speaking. Then let me ask the big question. What's the meaning of this whole thing? The Robin, meaning of life. What is the meaning of life? We talked about alien civilizations, but this is the one we got. Where are the aliens? Where are the human? Seem to be conscious, be able to introspect. What's, why are we here? [/INST] Why are we here? This is the thing I told you before about how we can predict that future creatures will be different from us. We, our preferences are this amalgam of various sorts of random sort of patched together preferences about thirst and sex and sleep and attention and all these sorts of things. So we don't understand that very well. It's not very transparent and it's a mess, right? That is the source of our motivation. That is how we were made and how we are induced to do things. But we can't summarize it very well and we don't even understand it very well. That's who we are. And often we find ourselves in a situation where we don't feel very motivated. We don't know why. In other situations we find ourselves very motivated and we don't know why either. And so that's the nature of being a human of the sort that we are, because even though we can think abstractly and reason abstractly, this package of motivations is just opaque and a mess. And that's what it means to be a human today and the motivation. We can't very well tell the meaning of our life. It is this mess that our descendants will be different. They will actually know exactly what they want. And it will be to have more descendants. That will be the meaning for that. </s><s>[INST] Our descendants will be different. Well, it's funny that you have the certainty. You have more certainty. You have more transparency about our descendants than you do about your own self. Right. So it's really interesting to think, because you mentioned this about love. that something that's fundamental about love is this opaqueness, that we're not able to really introspect what the heck it is, [/INST] or all the feelings, the complex feelings involved. </s><s>[INST] Right, and that's true about many of our motivations. And that's what it means to be human of the 20th and the 21st century variety. Why is that not a feature that we want, we'll choose to persist in civilization then? This opaqueness put another way mystery, maintaining a sense of mystery but ourselves and about those around us. Maybe that's a really nice thing to have. [/INST] Maybe, but this is the fundamental issue in analyzing the future. What will set the future? One theory about what will set the future is what do we want the future to be? So under that theory, we should sit and talk about what we want the future be, have some conferences, have some conventions, discussion things, vote on it maybe, and then hand out off to the implementation people to make the future the way we've decided it should be. Yeah. That's not the actual process that's changed the world over history, up to this point. It has not been the result of us deciding what we want and making it happen. In our individual lives, we can do that. We might decide what career we want or where we want to live, who we want to live with. In our individual lives, we often do slowly make our lives better, according to our plan and our things, but that's not the whole world. The whole world so far has mostly been a competitive world where things happen if anybody anywhere chooses to adopt them and they have an advantage, and then it spreads, and other people are forced to adopt it by competitor pressures. That's the kind of analysis I can use to predict the future, and I do use that to predict the future. </s><s>[INST] It doesn't tell us it'll be a future we like, it just tells us what it'll be. [/INST] It'll be one where we're trying to maximize the number of our descendants. </s><s>[INST] We know that abstractly, indirectly, and it's not opaque. With some probability that's non-zero, that will lead us to become grabby and expanding aggressively out into the cosmos until we meet other aliens. [/INST] The timing isn't clear. We might become grabby, and then this happens. These are beat-grabbiness and this are both the results of competition, but it's less clear which happens first. Does this future excite you or scare you? How do you feel about this whole thing? Well, again, I told you compared to sort of a dead cosmology, at least it's energizing and having a living story with real actors and characters and agendas, right? </s><s>[INST] Yeah, and that's one hell of a fun universe to live in. Robby, you're one of the most fascinating, fun people to talk to. Brilliant, humble, [/INST] systematic in your analysis. Hold on to my wallet here. What's he looking for? </s><s>[INST] I already stole your wallet long ago. I really, really appreciate you spending your valuable time with me. I hope we get a chance to talk many more times in the future. Thank you so much for sitting down. [/INST] Any more times in the future. Thank you so much for sitting down. Thank you. </s><s>[INST] Thanks for listening to this conversation with Robyn Hanson. To support this podcast, please check out our sponsors in the description. And now, let me leave you with some words from Ray Bradbury. We are an impossibility in an impossible universe. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] pretty but technically would be [/INST] alive. So I, you know, </s><s>[INST] philosophically, [/INST] could I object? It's borderline. Yeah, </s><s>[INST] but romantically [/INST] no romantic, they </s><s>[INST] need to carry the [/INST] duty. </s><s>[INST] Yes, yes, there's [/INST] a bit of a romance to the philosophy, </s><s>[INST] it's in there [/INST] and you also </s><s>[INST] uh and the book [/INST] with a universe that </s><s>[INST] creates new [/INST] universes. </s><s>[INST] Ah [/INST] so if this isn't the only </s><s>[INST] universe, do you think [/INST] that's in our future </s><s>[INST] that we might [/INST] launch new </s><s>[INST] universe, new offspring universes? It's very possible [/INST] multiverses a </s><s>[INST] controversial field because it's very [/INST] much hypothetical, but </s><s>[INST] with [/INST] this universe has been </s><s>[INST] created, the one we're in now and so [/INST] it's happened before. </s><s>[INST] It certainly could happen again. Some of them might be happening in [/INST] parallel I think, you know, if you look out billions of years trillions of years in the future of technological development. </s><s>[INST] Certainly possible. [/INST] We could, it's good to have a little baby universes, </s><s>[INST] grow [/INST] them like cabbage, get them out, </s><s>[INST] saute them and [/INST] make them have flavor. Ah yeah, </s><s>[INST] creates something delicious. [/INST] Well it sounds difficult, </s><s>[INST] but it's our human [/INST] duty to </s><s>[INST] try. As [/INST] you said chris, this is an incredible </s><s>[INST] conversation, You're [/INST] an incredible person, a scientist </s><s>[INST] explorer, [/INST] I can't wait to </s><s>[INST] see what you do in this world and I [/INST] um I hope to be there with you on mars. I would like to also um breathe my last </s><s>[INST] breath on that [/INST] sexy red planet. That's our neighbor podcast from mars at least space, I think space should be coming. Face is </s><s>[INST] pretty good. Space is pretty [/INST] good, but mars </s><s>[INST] next chris, thanks so much for talking to you. Thanks [/INST] for having me. It's really an honor and a pleasure to be here. Thanks thanks for listening to this </s><s>[INST] conversation with chris mason. To support this podcast. Please check out our sponsors in the description and now let me leave you some words from Stanislaw Lem [/INST] and Solaris. </s><s>[INST] Man has gone out [/INST] to explore other </s><s>[INST] worlds and other civilizations [/INST] without having </s><s>[INST] explored his own labyrinth of dark [/INST] passages and </s><s>[INST] secret chambers and without finding what [/INST] lies behind </s><s>[INST] doorways that he himself has [/INST] sealed. </s><s>[INST] Thank you for listening and hope to see you next [/INST] time </s>

<s>[INST] So my focus is on autonomous vehicles. Do you think this approach of third person watching is uh the autonomous driving is amenable to this kind of approach? [/INST] So for autonomous driving, I would say it's third person is slightly easier. And the reason I'm going to say it's slightly easier to do a third person is because the hard dynamics are very well understood. So the </s><s>[INST] easier than the first person you mean or I [/INST] think so I think the distinction between third person and first person is not a very important distinction for autonomous driving, they're very similar because the distinction is really about who turns the steering wheel and or maybe let me put it differently how to get from a point where you are now to a point let's say a couple of meters in front of you and that's a problem that's very well understood and that's the only distinction in 3rd and 1st person there, whereas with robot manipulation, interaction forces are very complex and it's still a very different thing um for autonomous driving, I think there's still the question imitation vs. RL So imitation gives you a lot more signal I think where imitation is lacking and needs some extra machinery is it doesn't and it's normal format, doesn't think about goals or objectives. And of course there are versions of imitation learning, inverse reinforcement, learning type, imitation, which also thinks about goals, I think then we're getting much closer but I think it's very hard to think of a fully reactive horror generalizing Well, if it really doesn't have a notion of objectives to generalize well to the kind of general that you would want, you want more than just that reactivity that you get from just behavioral cloning slash supervised learning. </s><s>[INST] So a lot of the work, whether self play or even imitation learning would benefit significantly from simulation from effective simulation and you're doing a lot of stuff in the physical world and in simulation, do you have hope for greater and greater power of simulation being boundless eventually to where most of what we need to operate in the physical world? What could be simulated to a degree that's directly transferable to the physical world? Are we still very far away from that? [/INST] So I think we could even rephrase that question in some sense, please. And so so the power of simulation, right? As simulators get better and better, of course, becomes stronger and we can learn more assimilation, but there's also another version which is where you said assimilated doesn't even have to be that precise as long as it's somewhat representative. And instead of trying to get one simulator that is sufficiently precise to learn and and transfer really well to the real world, I'm going to build many simulators. </s><s>[INST] Ensemble simulators, [/INST] ensemble of simulators, Not any single one of them is sufficiently representative of the real world, such that it would work if you train in there. But if you train in all of them, then there was something that's good in all of them, the real world will just be, you know, another one that's, you know, not identical to any one of them, but just another one of them. </s><s>[INST] Another sample from the distribution of simulators. [/INST] We do live in </s><s>[INST] A simulation. So this is just one [/INST] other one, I'm not sure about that. But yeah, </s><s>[INST] it's [/INST] definitely a very advanced simulator, if it is. </s><s>[INST] Yeah, it's pretty good one. I've talked to us to russell. It's something you think about a little bit too, of course you're like really trying to build these systems, but do you think about the future of ai a lot of people have concerned about safety. How do you think about ai safety as you build robots that are operating the physical world? What what is um yeah, how do you approach this problem in an engineering kind of way? In a systematic way. [/INST] So what a robot is doing things, you kind of have a few notions of safety to worry about. One is that Drobot is physically strong and of course could do a lot of damage. Um same for cars, which we can think of as robots do in some way and this could be completely unintentional. So it could be not the kind of long term ai safety concerns that okay, i is smarter than us and now what do we do? But it could be just very practical. Okay, this robot, if it makes a mistake, uh whether the result is going to be of course, simulation comes in a lot there to test in simulation. It's a difficult question. And I'm always wondering like I was wondering, let's say, you look at let's go back to drive because a lot of people know driving? Well of course, what do we do to test somebody for driving right to get a driver's license? What do they really do? I mean you fill out some test and then you drive and I mean it's suburban California, that driving test is just you drive around the blog, pull over, you need to do a stop sign successfully and then, you know, you pull over again and you pretty much done and you're like, okay, if a self driving car did that, would you trust it that it can drive? I'd be like, no, that's not enough for me to trust it. But somehow for humans we have figured out that somebody being able to do that is representative of them being able to do a lot of other things. And so I think somehow for humans we figured out representative tests of what it means. If you can do this where you can really do of course testing, you must, you must not want to be tested at all times. Self driving cars and robots could be tested more often. Probably you can have replicas that get testament are known to be identical because they use the same year old and so forth. But still I feel like we don't have this kind of unit tests or proper tests for robots. And I think there's something very interesting to be thought about their, especially as you update things, your software improves, you have a better self driving cars you updated. How do you know, it's indeed more capable on everything than what you had before that you didn't have any bad things creep into it. So I think that's a very interesting direction of research that there is no real solution yet. Except that somehow for humans we do because we say okay, you have a driving test you passed, you can go on the road now and you must have accents every like million or 10 million miles. Some something pretty phenomenal compared to that short test that is being done. </s>

<s>[INST] You [/INST] think it's a talent? No. Do you think it's do you think you have talent? What are you doing? </s><s>[INST] I [/INST] know what you're doing, not adding information, I know what you're doing. That's a good thing. It's a good thing. I </s><s>[INST] kept doing it and you kept filling the space. It's quite interesting. [/INST] Yeah, that is true </s><s>[INST] because you're yes ending yourself, which is great. The improv thing that was really impressive. [/INST] Can I ask you a question? Have you ever had a guest on that didn't add information? And then you had to keep doing it. </s><s>[INST] Yeah. Yeah. But it's part of the magic too. And sometimes I feel like uh they were actually giving me a gift of silence and I was stepping on it. Like for example I had a conversation with Jaco, you know Jack a willing and every question I would ask him in the beginning and I'm now better friends with him. It was the first time we met in that conversation and I would ask him these long questions of mumble and meander and so on and he would answer with yes or no and that's it. And then but he'd do it in a strong like viking like way and I kept I kept trying to go full like bobby lee style of create chaos and just keep talking and talking and so on. As opposed to I think he was inviting me more for the stoic type of silence. Short sentences, that kind of conversation. So I fucked that up I believe. But yeah, there's um, that not the adding information part, but the adding chemistry part or something. It's usually ego. We're where people don't realize there's a magic to be found between two humans. Like genuine. It's like a first date like that to truly listen to each other and to do the yes and thing and have fun with it when you have this energy on way too important for this conversation that the yeah, the information might be there, but the chemistry is not. So you have to remember that a lot of the podcasts I've done are like technical and so you could still say a lot of stuff about like what, what this project or whether it's physics or robotics or biology, you could say informational stuff. But the, the excitement, the magic is not there. But I often blame myself because like if I'm excited they'll be excited. I've learned this. So I'm learning, I'm not allowed to have like a board face which my, my face naturally looks bored. But on the inside I'm excited. It might be a Russian thing. I don't know, it's [/INST] not, can I tell you why you're not boring your face, </s><s>[INST] right? [/INST] Because you have crow's feet. </s><s>[INST] Oh, this thing. Yeah. [/INST] Yeah. And the reason why you have crow's feet is you smile a lot. </s><s>[INST] Yeah. [/INST] Yeah. You're very expressive. I know white dudes. I don't trust white dudes, right? With no crow's feet, Right? Because that means they don't, they're not accessing that part of their, you know, I mean face, </s><s>[INST] which is why I hate when, um, this is an L. A. Thing. Especially uh, women have talked to me about like Botox and they hate the, they hate not on me on themselves. And they hate because it's all wrinkles and stuff like that? And to me it's like, no, that's where the, that's the magic. [/INST] It really? </s><s>[INST] Yeah. So, okay. So the interesting thing about tiger belly. Uh huh Is there some weird like aesthetic to it? It's really unique. It's not just good. It's also unique. Like in the way that wes Anderson films are unique. Like life aquatic. I don't know if you know those films? [/INST] I love those. I mean, my favorite films. What </s><s>[INST] is that? What is that? It's not just the chemistry between you and koala. It's like, what is that? Can you, can you put a finger on it or is it just like, [/INST] well, it's, it's essentially who I am. I like. I that's what all my houses have looked like that. You know what I mean? Like I've always been a collector of designer toys, You know, I mean, I've always been a collector of um kind of weird artwork. Um Yeah, I've always been like that, You know, I I like weird wallpaper, like I'll get instead of like going to a wallpaper store. What I'll do is I'll get artwork that I like from an artist like and go get the, you know, get their approval and go to a place and make wallpaper out of their artwork. You know, I mean, you can like if I wanted a lex Friedman, your face on my wall, I would ask for your permission and I would probably put your face on a gigantic wall. Like I would do stuff like that, but I </s><s>[INST] wouldn't do that. [/INST] Yeah. </s><s>[INST] You know, [/INST] I think I will yeah, I think I would laugh. Yeah, I mean, but I would do </s><s>[INST] it big. [/INST] Yeah, yeah, yeah, Yeah. But my point is that um yeah, it's essentially who I am on the inside I guess in terms of like my you know, I don't know, but I don't really I've never I'm glad you said that because I never even thought about that. </s><s>[INST] Yeah, he's just, you [/INST] know, you just kind of do it like this, you know, because all your podcasts have this black ominous thing, you know, you're you're wearing a black suit. Your you have a specific thing too. It's like, but </s><s>[INST] I don't I don't really think people ask me like, why do you wear a suit. I really don't, I just feel good in it [/INST] and the reason why my podcast looks the way I do is because I feel comfortable in that environment and it, you know like you, I don't try to think too much about what I'm doing on tiger belly or even bad friends, right? Because when you start thinking about it and go, we should do this segment and I should, you know, do it this way or this podcast, does it this way. So what? You know, no, I just show up, I keep my mind open and I do the best I can. I add information like we talked about and I just keep talking right and I'm being, I try to be authentically myself like right now, you know, I had this fear when I was I was I shot in your bathroom man because I was so scared </s>

<s>[INST] Yeah, that's a beautiful, I mean that's, that is at the core where you work stands for. Is that a few people can have the power to transform society. Were just a few radical ideas with just a little bit of code uh change the [/INST] world to do it. </s><s>[INST] And that's empowering and that is the american way, that's why this country is, I believe the greatest country and that's, that's not over romanticize it too much. But I think some special things have already happened in this country and will continue to happen and that's and that [/INST] spirit can continue no matter you know who comes here, they can, they can adopt those folkways and that spirit </s><s>[INST] Brandon, I said, I can't tell you how much I was freaking out how much of an honor it is to talk to you. You're an incredible human being is one of my favorite conversations ever. Thank you so much for wasting all this time with me. I really appreciate [/INST] it. It seems like a breeze. My pleasure. </s><s>[INST] Thank you for listening to this conversation with Brendan Eich and thank you to our sponsors, Jordan's Harvard's show, sun basket meal delivery service, better help, online therapy and eight sleep self cooling mattress. Click the sponsor links to get a discount and to support this podcast and now let me leave you with some words from Jeff Atwood. Any app that can be written in javascript will eventually be written in javascript. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] I wonder what it takes to be the kind of leader that steps in and ask some difficult questions. So aliens is one UFO spacecraft, right. Another one who tortures another one. The CIA how much information is being collected about americans? I can see as a president being very uncomfortable asking that question because if the answer is a lot of information is being collected by americans, then you have to be the guy whose lives with that information for the rest of your life. You have to walk around, you're probably not going to reform. That system is very different. You have to, you probably have to be very picky about which things you reform. You don't have much time. It takes a lot of sort of effort to restructure things, but you nevertheless would have to be basically lying to, uh, to the, you know, to, to yourself, to others around you about the unethical things, depends of course what you're the ethical system is. I wonder what it takes to ask those hard questions. I wonder if how few of us are can be great leaders like that. And I wonder if our political system, the electoral system such that makes it likely that such leaders will come to power. [/INST] It's hard and you can't ask all the right questions. And there is a legal hazard if you know things at certain times. But I think you can back to your point on hiring, you can hire people who will do that in their domains and then you have to trust that when they think it's something that's a question you need to ask, they'll pass that on to you. Uh, this is why it's not a good idea to have loyalists because loyalists will shield you from things. It's a good idea to have people of integrity who you can rely on and who you think will ask those right questions and then pass that down through their organization. </s><s>[INST] What's inspiring to you? What's insightful to you about several of the presidency's throughout the recent decades. Is there somebody that stands out to you that's interesting and, and sort of in your study of how the office has changed? [/INST] Well, Bill Clinton is one of the most fascinating figures. Can </s><s>[INST] I I apologize. Bill Clinton just puts a smile on my face every time somebody mentions him at this point, I don't know why he gets charisma, I suppose. [/INST] Well and he's uh he's a unique individual, but he um he fascinates me because he's a figure of such enormous talent, an enormous appetite and such little self control and such extremes. Uh and I think it's not just that he tells us something about the presidency, tells us something about our society. You know, american society, this is not new to our time, is filled with enormous, enormous reservoirs of talent and creativity and those have a bright and a dark side and you see both with Bill Clinton in some ways he is the mirror of the best and worst of our society and maybe that's really what presidents are in the end, right? There are mirrors of our world that we get the government we deserve. We get the leaders we deserve. </s><s>[INST] I wish we embrace that a little bit more. You know, a lot of people criticize, you know, donald trump for certain human qualities that he has. A lot of people criticize Bill Clinton for certain human qualities. I wish we'd kind of embrace the chaos of that, you know, because he does, you're right in some sense, represent, I mean, he doesn't represent the greatest ideal of America, but the flawed aspect of human nature, what he represents. And that's the beautiful thing about America, the diversity of this land with the mix of it, the corruption of, of within capitalism, the beauty of capitalism, the innovation, all those kinds of things, the people that start from nothing and create everything the Elon musk to the world and the Bill gates and so on. But also the people Bernie madoffs and and and all is the Me Too movement showed the the multitude of creeps that apparently permeate the entirety of our system. So I don't know, there's something, um, there is some sense in which we put our president on a pedestal, which actually creates a fake human being. Like the standard would hold them to is forcing the fake politicians to come to power versus the authentic one, which is in some sense, the promise that donald trump is uh, like it's a, it's a definitive statement of authenticity. It's like this the opposite of the fake politician. It's whatever else you want to say a bottom is there's the chaos that's unlike anything else that came before. One thing and this particular maybe preference and quirk of mine, but I really admire. Maybe I'm romanticizing the past again, but I romanticized the presidents that were students of history. There were almost like king philosophers, you know, great, you know, that made speeches that uh, you know, reverberated through decades after. Right then we were kind of using the words of those presidents whether written by them or not. We tell the story of America and I don't know does even Obama has been an exceptionally good? As far as I know, I apologize if I'm incorrect on this. But from everything I've seen, he was a very deep scholar of history and I really admire that. Is that through the, through the history of the office of the presidency, Is that just your own preference or is that supposed to come with the job? Are you supposed to be a student of [/INST] history? I think, I mean I'm obviously biased as a historian, but I do think it comes with the job. Every president I've studied uh had a serious interest in history now. How they pursued that interest would vary. Obama was more bookish, more academic. Uh so was George W Bush in strange ways? George H W. Bush was less so, but George H. W. Bush loved to talk to people. So he would talk to historians, write Ronald Reagan uh loved movies and movies were an insight into history for him. He likes to watch movies about another time. It wasn't always the best of history, but he was interested in what is a fundamental historical question. How has, how has our society developed, how has it grown and changed over time and how has that changed, affected who we are today. That's the historical question. It's really interesting to me. I do a lot of work with business leaders and others to uh, you reach a certain point in any career and you become a historian because you realize that the formulas and the technical knowledge that you've gained got you to where you are. But now your decisions are about human nature. Your decisions are about social change. And they can't be answered technically they can only be answered by studying human beings. And what is history. It's studying the laboratory of human behavior </s>

<s>[INST] So the really nice thing, you're right. That convolution is just one of the things that's like, it's an innate feature of this program by the human expert, but [/INST] we need more of those. Not </s><s>[INST] so the but the nice feature is it feels like that requires coming up with that brilliant idea. Can get your touring award, but it requires less effort than encoding and something we'll talk about the expert system. So including a lot of knowledge by hand. So it feels like one, there's a huge amount of limitations which you clearly outlined with Deep learning. But the nice feature, Deep learning, whatever it is able to accomplish, it doesn't, it does a lot of stuff automatically without human intervention Well, [/INST] and that's part of why people love it, right? But I always think of this quote from Bertrand Russell, which is it has all the Advantages of theft over honest toil. It's really hard to program into a machine, a notion of causality or you know, even how a bottle works or what containers are Ernie Davis and I wrote a I don't know, 45 page academic paper trying just to understand what a container is, which I don't think anybody ever read the paper, but it's a very detailed analysis of all the things, not even all of some of the things you need to do in order to understand the container, it would be a whole lot nice and you know, I'm a co author on the paper, I made it a little bit better, but I already did the hard work for that particular paper and it took him like three months to get the logical statements correct and maybe that's not the right way to do it. Um It's a way to do it, but on that way of doing it, it's really hard work to do something as simple as understanding containers and nobody wants to do that. Hard work. Even Ernie didn't want to do that hard work. Everybody would rather just like feed their system in with a bunch of videos with a bunch of containers and have the systems infer how can paint containers work. It would be like so much less effort, Let the machine do the work. And so I understand the impulse, I understand why people want to do that. I just don't think that it works. I've never seen anybody build a system that in a robust way, can actually watch videos and predict exactly which containers would leak and which ones wouldn't or something like and I know someone's going to go out and do that since I said it and I look forward to seeing it. Um but getting these things to work robustly is really, really hard. So john Macoun, who was my colleague in N. Y. U. For many years, thinks that the hard work should go into defining an unsupervised learning algorithm that will watch videos use the next frame basically in order to tell it what's going on. And he thinks that's the Royal Road and he's willing to put in the work in devising that algorithm. Then he wants the machine to do the rest. And again, I understand the impulse, my intuition based on years of watching this stuff and making predictions 20 years ago that still hold even though there's a lot more computation so forth is that we actually have to do a different kind of hard work, which is more like building a design specification for what we want the system to do, doing a hard engineering work to figure out how we do things like what johN did for convolution in order to figure out how to encode complex knowledge into the system. The current systems don't have that much knowledge other than convolution, which is again this objects being in different places and having the same perception I guess I'll say same appearance. People don't want to do that work. They don't see how to naturally fit one with the other. </s><s>[INST] I think that's Yes, absolutely. But also on the expert system side there's a temptation to go too far the other way. So we're just having an expert sort of sit down and encode the description, the framework for what a container is and then having the system reason to the rest from my view. Like one really exciting possibilities of active learning where it's continuous interaction between a human and machine as the machine that there's kind of deep learning type extraction of information from data patterns and so on. But humans also guiding the learning procedures, guiding the the both the process and the framework of how the machine learns whatever the test [/INST] I was with you with almost everything you said, except the phrase Deep learning. Uh what I think you really want. There is a new form of machine learning. So let's remember. Deep learning is a particular way of doing machine learning. Most often it's done with supervised data for perceptual categories. There are other things you can do with Deep Learning, some of them quite technical. But the standard use of Deep learning is I have a lot of examples and I have labels for them. So here are pictures. This one is the Eiffel Tower, this one's the Sears Tower, this one is the Empire State building, this one's a cat, this one's a pig and so forth. You just get millions of examples, millions of labels. And deep learning is extremely good at that. Um It's better than any other solution that anybody has devised. But it is not good at representing abstract knowledge. It's not good at representing things like bottles contain liquid and you know have tops to them. And so it's not very good at learning or representing that kind of knowledge. It is an example of having a machine learned something but it's a machine that learns a particular kind of thing which is object classification. It's not a particularly good algorithm for learning about the abstractions that govern our world. There may be such a thing. Part of what we counsel in the book is maybe people should be working on devising such things. So one </s>

<s>[INST] Well, it's starting to change. I mean, I suppose 100 years ago it was minor. It's starting to [/INST] well, it depends on how you viewed so what people did 100 years ago still have effects on the world today. </s><s>[INST] Oh, as uh, I see as um as a civilization in the together. [/INST] Yeah. So it might be that the greatest impact of individuals is not at technological maturity or very far down, it might be earlier on, when there are different tracks, civilization could go down. Maybe the population is smaller things still haven't settled out if you can't interact effect that um that that that could be bigger than the direct effects that people have later on. </s><s>[INST] So part three of the argument says that so that leads us to a place where eventually somebody creates a simulation that I think you you had a conversation with Joe Rogan. I think there's some aspect here where you got stuck a little bit uh how does that lead to were likely living in a simulation. So this kind of probability argument If somebody eventually creating a simulation, why does that mean that we're now in a simulation? [/INST] What you get to if you accept alternative 3 1st is that would be more simulated people with our kinds of experiences than non simulated ones. Like if in and kind of if you look at the world as a whole, by the end of time I said we just counted up, that would be more simulated ones than non simulated ones, then there is an extra step to get from that if you assume that I suppose for the sake of the argument that that's true. Um how do you get from that to uh the statement we are probably in a simulation. Um so here you are introducing an index ical statement like it's uh that this person right now is in a simulation. There are all these other people, you know that are in simulations and some that are not in the simulation. Um but what probability should you have that you yourself is one of the simulated ones, </s><s>[INST] Right. And that [/INST] set up. So, so yeah, so I call it the bland principle of indifference, which is that in in cases like this when you have to, I guess sets of observers, um one of which is much larger than the other and you can't from any internal evidence, you have towel which said you belong to you uh sure. Design of probability that is proportional to the size Of these sets. So that if there are 10 times more simulated people with your kinds of experiences, you would be 10 times more likely to be one of those. </s><s>[INST] Is that as intuitive as it sounds? I mean that that seems kinda if you don't have enough information you should rationally just assign the same probability as as the the size of the [/INST] set. It seems it seems pretty steep um plausible to me. </s><s>[INST] Were the holes in this is it at the at the very beginning, the assumption that everything stretches sort of you have infinite time essentially [/INST] you don't need infinite time. </s><s>[INST] You should need what? How long does the time, [/INST] however long it takes I guess for a universe to produce an intelligent civilization that contains the technology to run some ancestor simulations. </s><s>[INST] When the first simulation is created that stretch of time just a little longer than they'll all start creating simulations kind of [/INST] like well I mean there might be different, it might if you think of there being a lot of different planets and uh some subset of them have life and then some subset of those get to intelligent life. And some of those maybe eventually start creating simulations. They might get started at quite different times. Like maybe on on some planet it takes a billion years longer before you get like monkeys or before you get even bacteria then on another planet? Uh so that this might happen kind of at different cosmological epochs. </s><s>[INST] Is there a connection here to the doomsday argument and that sampling their [/INST] of their is a connection um in that they both involved an application of anthropic reasoning that is reasoning about this kind of index ical propositions. But the assumption you need uh in the case of the simulation argument, um it's much weaker than to simulate the assumption you need to uh make the doomsday argument go through </s><s>[INST] what is the doomsday argument? And maybe you can speak to the anthropic reasoning in more general. [/INST] Yeah, that's that's a big and interesting topic in its own right and topics. But the doomsday argument is this really first discovered by Brandon carter, who was a theoretical physicist and then developed by um philosopher john Leslie. Um I think it might have been discovered initially in the 70's or 80s and less. They wrote this book I think in 96. And there are some other versions as well by Richard got to say physicist. But let's focus on the carter Leslie version where um it's an argument um that we have systematically underestimated the probability that humanity will go extinct soon. Uh Now I should say most people probably think at the end of the day there is something wrong with this doomsday argument that it doesn't really hold, it's like there's something wrong with it, but it's proved hard to say exactly what is wrong with it. And different people have different accounts. My own view is, it seems inconclusive, but um, and I can say what the argument is, that would be good. Yeah, so maybe it's easiest to explain via uh, analogy to um, sampling from earns. So imagine you have a big um, imagine you have two urns in front of you and they have balls in them that have numbers, uh, there's the tourist look the same, but inside one there 10 balls, paul, number 123 up to ball number 10 and then in the other earn you have a million balls numbered one to a million. And uh, somebody puts one of these urns in front of you and Ask you to guess what's the chance, it's the $10 and you say, well 50, 50, they you know, I can't tell which one it is. Um, but then you're allowed to reach in and pick a ball at random from the urn and that's supposed to find that it's ball # seven. So that's strong evidence for the 10 ball hypothesis. Like it's a lot more likely that you would get such a low numbered ball if they're on the 10 balls in the air, like it's in fact 10% done right. Um, then if there are a million balls, it would be very unlikely you would get number seven. So you perform a basin update And if your prior was 5050 that it was the temple and you become virtually Sergent after finding the random sample was seven that it only has 10 balls in it. So in the case of the Ernst, this is on controversial just elementary probability theory. The doomsday argument says that you should reason in a similar way with respect to different hypotheses about how many um, how many balls that will be in the urn of humanity. I said for how many humans that would have been by the time we go extinct. Um, so to simplify, let's suppose we only consider two hypothesis either maybe 200 billion humans in total or 200 trillion humans in total. It could fill in more hypothesis, but it doesn't change the principle here. So it's easiest to see if we just consider these two. So you start with some prior based on ordinary empirical ideas about threats to civilization and so forth. And maybe you say it's a 5% chance that we will go extinct By the time there would have been 200 billion only you kind of optimistic, let's say you think probably will make it through colonist universe. And um, but then according to this Tuesday argument, you should take off your own birth rank. Um as a random sample. So your birth thank is your sequence in the position of all humans that Have ever existed. And it turns out you're about human number of 100 billion, you know, give or take, that's like roughly how many people have been born before you. </s>

<s>[INST] take away from that, in that journey. It is interesting that, you know, I hear from women that, even on this podcast, when I talk to incredible women like yourself, it is inspiring to young women to hear. I mean, you like to see, you talk to somebody from Turkey and then Turkish people all get excited. It's so true. So you get like somebody that looks like you, somebody that in the category could be tiny or it can be huge. That's just the reality of the world. [/INST] It is the reality of the world. And the work I do now to put this group called 110, put 1 million black employees into the middle class without college degrees, get them the right skills, upwardly mobile jobs. So one of my last years, we had been working on, it just did regular leadership session at IBM and had our black colleagues. We're talking about what did it feel like to be a black leader. And here, these are extremely accomplished people. And I can remember very well one telling a story about, look, I felt if I failed or succeeded, it's not just me. It came from a country in Africa. I felt like the whole country is on my shoulder, my success or failure. That's a burden. I mean, I don't feel that burden. Not true. As a woman CEO, I did feel like even the headlines when I was named said, her appointment will either, her success or failure will be a statement for the whole gender kind of thing. And I didn't dwell on it, but I could see how people, like you said, it could be a small group, could be whatever. And so that is a lot of pressure on people and they need role models. You are a role model for people. Look at what you're able to do. You do these podcasts, you understand your science very well, you're very well prepared, your ability to translate it to people. That's not an insignificant thing. And you may think, oh, is that about the power of me? Not really, right? And you obviously believe you don't do this because you just like sitting at a microphone. You do it because you think, okay, if I can get people to say things that are really valuable to other people, they're going to learn something. I assume that is, I mean, you never told me my interpretation is that's why you do this podcast, that you feel like in service of other people, that you can bring them something unique by the way you do this. Now I should ask you, why do you do it? That's my impression. </s><s>[INST] By the way, can I just comment on the fact that you keep asking really hard questions? I'm really honored by it. As a fan of a podcast myself, what I hope is to talk to people like you and to show that you are a fascinating and beautiful human being outside of your actual accomplishments also. So sometimes people are very focused on very specific things about, like you said, science, like what the actual work is, whether it's nuclear fusion or it's GI GPT. I just want to show that it's because I see it at MIT and everywhere. It's just human beings trying their best, they're flawed, but just realizing that all of these very well accomplished people are all the same. And then so then regular people, the young people, they're able to see, I can do this too, I can have a very big impact. Yeah, exactly. It's like we're all kind of plasters. We're all trying to figure out. Do a certain degree. So let me just ask you about family. You wrote that my family still jokes that the reason I never had children on my own was because I had already raised my family. They're right. So this is [/INST] talking to you upbringing, but in general, what was your also? </s><s>[INST] You know, leading a giant company, what was the right place to find a work-life balance for you to have time for family, have time for away from work and be successful? [/INST] Yeah. So I had to learn that. And I might've said, you know, you're the only one that can determine your own work-life balance. Companies are innate things. I mean, they will take everything they can from you. And it's not a bad thing. They just will as will bosses. I mean, you give it, they'll take it. And when people ask for, you know, I need roof, I'm like, okay, I had to come with terms with the criminal was me. If I needed that balance, I had to set those boundaries. And so when I comment about a family, because I am in extreme awe of people with children who work, it is a extremely hard thing to do. I watch my siblings. I love my nieces and nephews. You know, the emotional, their pain is your pain every minute of a day. And then you still have a job on top of it. And so when my mom had to go back to school and had to work, I was the one. And so when she couldn't go to the teacher meeting, I went to the teacher meeting when, and so in some ways, and there's an age gap between my brother and I and my other two sisters. And so I'm still they they still call me Mama Bear, even I mean, I was extremely protective of all of them. And it is as if I had raised them. And my mom did a great job raising them, I didn't I bet I was there. And so when it came time to have children, my husband came from a family where his father died and was raised by a single mother, very, very similar, end point, different reasons why he ended up, you know, his father not abandon them. And I don't want people to believe to do my job, you can have no children. That is not right. I know other great women CEOs, Marilyn Houston, who ran Lockheed Martin, extremely technical company, Mary Barra, who runs General Motors, Ellen Coleman, who run DuPont, these are all my friends to this day. And they've been fantastic mothers and husbands, good parents, right. And so I talked about it because it was a choice we made. And so, you know, we both felt, look, we'd reached a point where for his reasons, what he had to do, I'd already felt that way. And that we were comfortable just being great aunts and uncles. And I'm a great aunt, you know, I like to think that for my little guys and I'll end up older now, but lots of them. And there's no doubt though, the choices we made, Mark and I, that that made it easier for me to focus on work. I mean, that's just math, you know, when you've got less people to have to take care of. And so I'm very considerate of that. And I think much of it informed many of the policies I put into because I had such great empathy for those who then still had these other responsibilities. And I desperately wanted them all to stay in the workforce. So I can remember, and my siblings have been more successful than I, by the way, I mean, to my mother's credit. And my one sister who, you know, went to Northwestern, has an MBA, built some of the most sophisticated systems. She spent her whole career at Accenture and just recently retired as a chief executive of all of consulting. But at one point, she took off time to spend with her family and then went to go back to work. She's talking to me and she's like, I don't know if I should go back to work, you know, maybe life's path, you know, technology goes so fast, it's been a few years. I'm sitting there like, what are you talking about? I'm like, you know, look at her credentials, they're far outstanding. I'm like, and I thought to myself, like ding, one of those moments, if my own sister feels that way with all her credentials, I'll bet I went back to work the next day and I said, hey, pull for me, all the people who've left for parental reasons, and or whatever family reasons, and didn't come back. And it began a program of return ships. And I can't tell you how many in men and women was because they didn't feel confident to come back. They thought technology passed them by. Okay, we said it's three months, you can stay one month, three months, doesn't matter. Well, a lot of people like one day, they're like, you're right, not that much happened. It happened, but I caught up. I actually know more than I think, you know, and, and I, so actually no more than I think, you know, and it was a long answer to your question about, I didn't, but I am so empathetic. And I am in awe of what they are able to do. So, and it made me then I think more empathetic to the policies and the like, around that topic, </s>

<s>[INST] have to back up for just a second. Who is Khomeini? Who you just, you just mentioned a few desperate facts about the man. Yes, he was the person that took power in 1979. Supreme leader of Iran, something, you mentioned something about Paris, something about being in the 70s. [/INST] What </s><s>[INST] what should we know about the guy, [/INST] Ayatollah Khomeini who eventually was known as the imam Khomeini. He was kind of promoted to it, even more sublime position. </s><s>[INST] Okay, okay, can we just a million tangents I told imam, what do these terms mean? [/INST] Well, Ayatollah means the sign of God In the course of the 19th century or early 20th century, as the religious establishment gradually lost its greater presence in the society and this prominent places in society, they had some kind of inflation in titles. So they gave themselves more grand titles, </s><s>[INST] more adjectives, [/INST] more adjectives, more grand titles such as Ayatollah that became a kind of highest rank of the religious hierarchy, which incidentally was in on unofficial hierarchy. It was not, it's not like the Christie like catholic change that you have, you know, bishops and you know, federal, it was very unofficial mother and he was an Ayatollah was eventually recognized as an Ayatollah. </s><s>[INST] He, he wasn't the first Ayatollah. [/INST] No, no, no, not at all. The ayatollahs were before him ever since the beginning of the century, but he was eventually recognized as an Ayatollah. And if I want to start it this way, Ayatollah Khomeini was born in 1900. And in a sense, all these tremendous change that Iran witnessed in the course of the 20th century was, in a sense, materializing this person. He become uh Moola of a lower rank went to the traditional mattresses to the traditional uh centers for the education of the seminarians. Never had a secular education had a very complex Islamic education on this one hand, jurisprudence on the other hand, probably a little bit of Islamic philosophy and mysticism, which is unusual for the juris for the, for the faculty as they call them. This. Religious scholars or or legal scholars of Islam. And then he in the 19 sixties when he was residing in Tehran and gradually becoming more important. He became a voice of opposition against the shaw. And the reason for opposition uh in the 1960s, early 1960s was the fact that the shot carried through a series of extensive modernization policies of which the most important was the land reform. So in effect the land distribution that took place in the early 60s removed or weekend greatly that class of landowners from the, from the 19th century. And he khomeini saw himself as a voice of that old class that um felt that actually declared that this land redistribution is on Islamic. According to the Islamic law, property is uh property is honored and you cannot just no matter how much and how large are these states that the landowning class has, the government has no right to redistribute it, even among the peasants among the uh people who are killing the land. So that was a major issue. Shaw also gave the right of vote to women. And that also he objected, is that women should not have a right, </s><s>[INST] Can we just linger on the Islamic law? How firm and clear is the Islamic law that he was representing and embodying? Is this um [/INST] codified, </s><s>[INST] codified? Yes, that's a good term. [/INST] Yeah, that's another issue. Not only the hierarchy was unofficial, informal, but also Islamic law, particularly. She low did not have any a codified system because this religious authorities always resisted becoming under a umbrella of a more codified system of Islamic law because they were outside the state. In a sense, civil civil law was in the hand of the religious establishment. They had their own courts independent of the state. But other matters of legal matters was in the hands of the government. There was a kind of, in the fact of division between these two institutions, State versus the religious establishment. Therefore it was not codified. So he could declare that this is unofficial or illegal, according to the Islamic law, that you would distribute land to the presence and another most ahead or another religious authority would say, no, no, it's perfectly fine because he would have a different reading of the law. So that being in mind, that adds to the complexity of the picture He in the 1963, there was a period of uprising of the supporters of Ayatollah Khomeini. That was a turning point in a sense to try to politicized the religious supporters of who were loyal to Ayatollah Khomeini. And in a sense, all the community of more religiously orientated against the secular policies of the show and against of course, the dictatorship of the show. </s><s>[INST] So that's where the religious movement became [/INST] In 1963 is the first moment is the huge uprising and the government suppressed it. But </s><s>[INST] then a suppression [/INST] yes, would </s><s>[INST] start to build [/INST] of course, and he was sent to exile. He went to Najaf, which is this great center in southern </s><s>[INST] became a martyr on top of this [/INST] at martyr, he was probably even forgotten to some extent, but not it was forgotten for the, for the secular middle class, but not to those supporters of his who were paying him their dues. Because in Islam, you would pay dues to religious leaders, you know, there's religious dues and arms that you put pay to the clerical authorities and they redistribute them among their own students and so forth. So they built actually a network of loyalty based on these donations and these donations uh, that received by Ayatollah Khomeini was very effectively through his network was distributed even if he was in exile at era. So the 1977, when the situation changed and there was a little bit of opening in the political climate. Then you saw that Ayatollah Khomeini start sending cassette messages that was his means of communication. Was sending cassettes and cassettes were sent through the country by his network. So all declarations and saying first that we would like to see a greater democratization and the shock has to abide by the constitution of 1907. this is a constitution, is a democratic system and so </s>

<s>[INST] shelf it's [/INST] just it was such that no, I have it though. But that one is for you. I thought if you want to put it next to your other robots, open it up. Yeah it's for you. And that way uh it's that symbol of joy when you have when you're a kid, when you find something you really want. I think it's just it's really like when people look at it, they'll be like don't be hopeless. </s><s>[INST] I'll open this carefully later. [/INST] There's no way to open it carefully. Kids don't open stuff carefully. You rip that crap open. </s><s>[INST] But then you break it and you cry. That's what happens when your kids. [/INST] I never did that. Okay. </s><s>[INST] Me neither. I never cried but never got presents either. That is so cool. Alright, scooter, you symbolize childlike discovery, right? The poor, the poor man's robot, [/INST] the prime Minister transformers. I think there's instructions on the back how to transform her. I only found out as an adult that was supposed to be a girl. Yeah, </s><s>[INST] wow, this changes everything. [/INST] Thank you, Mark. That's incorrect. No, give me here. Let me show it looks better when she's transformed. </s><s>[INST] What? No, there's there's levels to that statement. [/INST] How does it do like this? Let me see if I remember how to do it because I had this as a kid </s><s>[INST] arms out. [/INST] What the thing is, these are easy to break. I remember. Is it like this? </s><s>[INST] No? Oh, the front comes out. Let me see this. [/INST] Oh, this comes up. Yeah, yeah, yeah, </s><s>[INST] yep. So that's that the arms scope I'm having visions of like baby Michael. [/INST] I don't, I can't do it. Okay, I can't do it. I can't figure it out. </s><s>[INST] Wow, you're right. She looks so much better transformed. Oh, all right, I'm gonna follow the instructions in a bit and I'll leave, I'll leave this failed project of yours, great. There's a wheel out. [/INST] I don't like this in between form. </s><s>[INST] Well this is how it's gonna be because we're going to be accepting of the transformation that takes time. Okay. I got uh okay. I saw this little thing when I was walking in congress and it says resist the bracelet. I mean think of you, the reason I got it is because there's two bracelets. So one said lucky fuck and the other one said resist. Now I first saw resist and I'm like and then I saw the lucky fuck. And I realized I'm a lucky funk to find a relevant. It makes me think of you. This [/INST] is very nice resist </s><s>[INST] the powerful. [/INST] That's true. Mhm. </s><s>[INST] I saw this somewhere. The Oh yeah, yeah, yeah. Um This has to do with in terms of resist. You often bring up the book Machiavellian is by James Burnham. And so I was I was looking through, I was reading different parts. It's it's tricky read. It's a little bit um but there there is a e book Kindle version now that I've been um working through this. I think there's actually an audiobook to Anyway, [/INST] I just bought some the Machiavellian Xyz is James Burnham's analysis of four thinkers that he regards as the machiavellian whose gitana Moscow Alfredo Peredo George Sorrel. And um I'm blanking on the Moscow. Peredo Sorelle and George Michelle and I just got potatoes autograph in the mail this week. </s><s>[INST] So he talks about freedom and liberty is interesting um line that I'd like to get your opinion on in terms of resistance in terms of liberty, there's no one forces close quote, there's no one forced, no group and no class. That is the preserver of liberty. Liberty is preserved by those who are against the existing chief power. Oppositions which do not express genuine social forces are as trivial in relation to entrenched power as the old court jesters. So, I mean, the question here is, can Liberty, are you comfortable with that definition or that view of liberty of freedom that it at its highest ideal is expressed through the resistance to the powerful as opposed to existing in its [/INST] own. I think his point, broadly speaking, which I agree with is the only thing that can work to mitigate power is other power. That it's talk is cheap and persuasion has very limited efficacy. It it's like if there's a burglar right and one person, it will give you a speech about property rights and you shouldn't be in this person's house and the other person has a gun. You know, it's it's clear which is going to be more persuasive </s><s>[INST] yeah, but can't you just be free without the struggle that without this conflict. And what I'm uncomfortable with this view is how closely it uh links freedom and conflict like why does this world have to have conflict for you to be free. Can't I mean it's in part of it is just emphasis, [/INST] well you aren't just saying suffering is what leads to joy </s><s>[INST] See and now you're in agreement. Thank you. That's what I just did. That just so you can come around and agree I win next topic one, Wow, I'm Playing three D. Chess Here. Okay, this is New Year's, This is this is not December 31 I think that's how it works. But in 1973 we recorded this before you were born. Oh no um years after you were born in 60 you look great for sixties, early sixties or Sure okay what five things, let's say our moments in 2021, are you grateful for or people just, I don't know things, moments, beautiful experiences, profound essences of the year. Like looking back, what are the cool things that just [/INST] personally or socially </s>

<s>[INST] And of course you can do the ultra dramatic, the glove doesn't fit kind of the climax and all those kinds of things. Yes, but that's the best of narratives, the best [/INST] stories. </s><s>[INST] Speaking of other really powerful stories that you were involved with is the Aaron Hernandez trial and the whole story, the whole legal case, can you maybe overview the big picture uh story and legal case of Aaron Hernandez. [/INST] Yeah, so Aaron, whom I miss a lot, so he was charged with a double murder in, in in the case that I tried and this was a unique case in one of those impossible cases uh in part because Aaron had already been convicted of a murder and so we had a client who was on trial for a double murder after having already been convicted of a separate murder and we had a jury pool, uh just about all of whom I knew that he had been convicted of a murder because he was a very popular football player in boston, which is a big football town with the, with the patriots. Uh so you know, so everyone knew that he was convicted murderer and here we are defending for in a double murder case. Um so that was, that was the context, it was not the case in the sense that this murder had gone, gone unsolved for a couple of years and then a nightclub bouncer uh said something to a cop who was working at a club, uh that he and Hernandez was somehow involved in that, in that murder that happened in the theater district, that's the district where all the clubs are in boston and where the homicide occurred and once the police heard Aaron Hernandez is named then it was, you know, they went all out in order to, to, to do this And they found a guy named alexander Bradley, who uh was a very significant uh, a drug dealer in the sort of Connecticut area, very significant, very powerful. Um and uh he essentially, in exchange for a deal uh pointed to Aaron said, yeah, I was with Aaron and uh and Aaron was the, was the murderer. Uh so that's how the case came came to court. </s><s>[INST] Okay, so that that's that's the context. What was your involvement in this case, like legally, intellectually psychologically, uh, when this particular uh, second charge of murder. [/INST] So a friend called me Jose baez, who is a defense attorney and he uh comes to a class that I teach every year at Harvard, the trial advocacy workshop as one of my uh teaching faculty members. It's a class where we teach students how to try cases. Uh so uh Jose called me and said, hey, uh I got a call from massachusetts, Aaron Hernandez, uh you want to go and and talk to him with me? So I said, sure. So we went up to the, to the prison and uh uh, and met erin and uh I spoke with him for two or three hours at first time and before we left, he said he he wanted to retain us, uh he wanted to work with us and and that started the representation? What </s><s>[INST] was he like? What was in that time? What was he worn down by the whole process. Was there still [/INST] he was lighting that he was not, he he had I mean more than just a light. He was luminous almost. Uh he had a radiant million dollar smile whenever you walked in. My first impression I distinctly remember was wow this is what a professional athlete looks like him. He walked in and he's just just bigger and more fit than you know, than anyone, you know anywhere and it's like wow this and you know when you saw him on television he looked kind of little and I was like so I remember thinking well what do those other guys look like Bird said um and uh and he's extraordinarily polite uh young uh I was surprised by how young he was </s><s>[INST] both in mind and uh embody [/INST] But chronologically I was you know, thinking he was in his you know in his early 20's I believe. Uh but there </s><s>[INST] seemed to be like an innocence don't uh in terms of just the way he saw the world. Uh I picked that up from the from the documentary. Just taking that [/INST] in, I think that's right. Yeah. </s><s>[INST] Uh so there is a netflix documentary titled Killer inside the mind of Aaron Hernandez. What are your thoughts on this documentary? I know if you got a chance to see, [/INST] I I did not have not seen it. I did not participate in it. I know I was in it because of uh there was news footage uh that, but I did not participate in it. I have not talked to Aaron about uh, about press or anything before he died. Uh my strong view is that the attorney client privilege survives death. And so I was not inclined to talk about anything that Aaron and I talked about. So I just didn't participate in and I've never </s><s>[INST] watched not even watch. Is that does that apply to most of you work? Do you try to stay away from the way the press perceived stuff? [/INST] Uh during yes, I try to stay away from it. I will view it afterwards. I just hadn't gotten around to watching Aaron because it's kind of, it's kind of sad. So I just haven't watched it, but I definitely stay away from the press during trial. Uh, and you know, there are some lawyers who watch it religiously to see what's going on, but you know, I'm, I'm confident in my years of training and so forth that and that I can uh, actively since what's going on in the courtroom and, and that I really don't need advice from Joe 476 at gmail. Uh, you know, some random guy on the internet telling me how to try cases. So it's just to me it's just confusing and I just keep it out of my mind </s>

<s>[INST] Okay. It's not necessarily just lovely person. So maybe my, I'll just say my biases, the people I know are especially at the top of companies or in the tech sector where innovation, it's such a big part of it. So I think a lot of the things we're talking about is when there's not much innovation in the system. So, uh, [/INST] innovation usually comes in the history of capitalism. Innovation comes in spurts. There's the electric period, the chemistry period, the nuclear period. There's now whatever you want to call it, the artificial intelligence or robotics or computer, it doesn't, it comes and then there's a flurry as everything is reorganized around whatever the newest technology is. And then you have a period where you can get excited about that and the very rich people who come to the top can talk endlessly as they always do about innovation. But again, you know, it really is. This is a recurring kind uh, of debate and a recurring kind of issue for me. How do I put this in a way </s><s>[INST] that, [/INST] you know, I don't mean to offend. So, please, </s><s>[INST] please, [/INST] No, no, I don't. I don't want to. But the problem with capitalism is </s><s>[INST] and [/INST] maybe you like this. The problem with capitalism is not that it is the one thing that's consistent with human nature. That's what its defenders would like to have us believe. But if anything I would argue the opposite that it is such a contradiction. two parts of our nature not other parts that there it can never quite make it. There's always gonna be the people who don't go along with it. People you're talking about who do quit along the way or maybe a few of them actually make it to the top by God knows what hook or what crook that they did it. But most of them go and you know why because their humanity is contradicted by what it is they're being asked to do. I mean the corporate sector this year just to give you an idea. C. E. O. S. Are jacking up there their wage package. They're already out of whack. I mean the average ceo pay is now 3 300 times what the average worker pay is. But they're jacking it up even more. Why? Because that's what's happening in their universe. That's what they're all doing it. And they have to do. Each one of them justifies that I have to do that. Otherwise I'd lose my guide to the next one. Which of course it's true but it's no comfort for the mass of people who want C. E. O. S. For whom this argument is very exciting. So there are they're doing that at a time when the american people can't cope. They've just gone through the covid disaster. They've gone through the worst, second worst economic crash of capitalism in our history. After two years of this 12 punch, they got an inflation a third punch. And we are now predicting rising interest rates and a recession at the end of the year or early next year. You can't do this to a working class When this was done to the German worker class in the 1920s. Hitler was the result. You keep doing that in this country. We're already watching it. You're gonna get that to you already getting bits and pieces. You can't keep quiet </s><s>[INST] suffering amidst the working class that's growing. [/INST] Taking out on </s><s>[INST] that can turn to anger [/INST] Some little 18 year old kid who has to go three hours in his car and blow away people in the supermarket. Huh. </s><s>[INST] And [/INST] it happens every day in this country every day. </s><s>[INST] So that, that anger rises up in those little ways now and bigger, [/INST] bigger, bigger potentially </s><s>[INST] by [/INST] the way, there's one more thing on the rationality and this goes to Elon musk. If you're interested, 49,000 people were killed in automobile accidents this last year. The number was just released yesterday. 49,000 automobiles are the single largest pollutant in the country. They use up an enormous amount of energy. They, they use up enormous and our resources, there is a way to make transportation much more rational and we've known it for decades. It's called mass transportation. It's a really beautifully maintained, crystal clear, clean, frequent system of busses, trains, street trolleys, vans, it could easily be done in this society. In fact, I once did a project that I estimated cost $30 billion. That's less than we're sending to Ukraine to do this, to reconfigure it </s><s>[INST] a public transit system where [/INST] everywhere in this country, all the major metro, this country's overwhelmingly metropolitan area. </s><s>[INST] Well, if you're a really has to be more than 30 billion, but [/INST] well, it was a few years </s><s>[INST] ago you're saying it, [/INST] but I'm using a lot </s><s>[INST] of, it's insane, [/INST] right? It's not crazy </s><s>[INST] stuff. It's a reasonable [/INST] number. </s><s>[INST] But there's a and let [/INST] me just finish the point. </s><s>[INST] Okay, [/INST] so I'm trying to be rational here. If we have a climate crisis, which everyone tells me we do. If it's got a lot to do with fossil fuels, which everybody tells me it has to do and, and with the use of the fossil fuel, particularly for the automobile, then the solution to the problem would be mass transit. We don't, we're doing nothing to make that happen nothing. </s><s>[INST] Well, there's, you know, on, you could argue that autonomous vehicles is a kind of public transit because it's going to be reasonable vehicles. It will end, in theory, car ownership. So you just have a more kind of distributed public transit [/INST] if it happens. But you know, that that's a side effect. His major goal and the major goal of the other companies that are busy squeezing to get his share of the pie smaller. So they have some for general motors, Toyota, all of them are making electric cars. So what they've done is they've replaced the individual car with fossil fuel with another individual car. Yeah, that's nuts. What are you doing? </s>

<s>[INST] Look at that. So he's legitimately angry [/INST] here. Yeah, he's angry. And of course you can't you can't move. Why would you get </s><s>[INST] this? Look at this this moment, right there. Is this gold. If you're not watching us on video, you're missing out. You never get this in judo. [/INST] I don't know if that's ever happened. </s><s>[INST] That little face off. Especially [/INST] on a stage like this the reference and then he brings us in to like talk to us and he's like, hey, we're good, right? Like you guys aren't about to do what I think you're about to do. Uh you put up like hey shake hands again because the first time we did it, that wasn't good enough. You got to do it again. Uh huh. The heartbreaking part about this and why the I. J. F. Switched it to an unlimited golden score because we fought five minutes um through the entire normal part of the match and then we did the entire overtime period of three minutes. Now. One penalty was given no gripping infraction, zero goals attacks like no stalling. </s><s>[INST] Great. There was nobody was really backing up. I mean he was, you know, so what was jimmy telling you here? What was he? Was he talking to you at all? [/INST] He's not allowed to talk during medical things and my nose is now broken. </s><s>[INST] But he's also the nose is broken from what? [/INST] Um I caught an elbow from him, glad his face is clean. That's fun. And right here, like I was pissed. I was so angry at the medic because he's fumbling around and I'm like, my whole plan is to break the german mentally. You gotta hurry up with the tape man. Like he's supposed to be tired. Like he's not supposed to be resting </s><s>[INST] and is jimmy yelling here. You can't, no, not here, not here, but during the match [/INST] and you can see I just take it from him and I'm like, give it to me, I'm going to do it myself, Get out of here. </s><s>[INST] How scared is the medic? It's [/INST] like this guy can't even tear the tape, how nervous he is. We made fun of him for this so much throughout the years. Still do to this day. Alright, here we go. Well, you're great. You can't really see, don't care. </s><s>[INST] Was there some outcome in your mind that you could possibly beat them on the ground with the submission or pin? You knew you're gonna have to throw him? [/INST] I knew I was going to have to if I was gonna throw him or on bar him or pin him, whatever the case may be, it was gonna be his mental, like, I'm just tired of this, right? He's two kg of a player, He's too experienced, you know, he has to mentally make that choice to give that inch and then you just have to be ready to take it. So I was just waiting for it. </s><s>[INST] And so now this is four minutes in, one minute left. That oh um is that in your game plan to potentials? Like, assume engaged? Like the sacrifice throws them [/INST] because the whole point of that, that technique and the sacrifice throws wasn't because I thought I was going to throw him, but it disrupts the pattern enough to like get him to make a potential mistake. Like see he should have gotten Machito there, hands in the face. But again, that's just part of judo. He poked me in the eye bo </s><s>[INST] this is a rough match, it does he act at all or no? Like, was he acting frustrated or anything like that was all like, he's like acting for the ref, you know what I mean? Like Oh that all that kind of stuff. You're just going in hard not stop like angry aggressive feeling cardio here at all. Like, I don't [/INST] I don't get tired during this and then just always pressing </s><s>[INST] for time runs out. [/INST] Now we're into golden score 12:38 later. Yeah. You think about every judo exchange right? Every time we grip up, every time we attack sometimes it can take longer to get back to the line in the entire exchange. </s><s>[INST] So the more aggression, the more exchanges you have, the longer the time stretches. Then hear the six seconds left in Golden Score your tape. There's uh there's no like yellow and red. Yeah. With sweat and blood literally and time is out now. What are you thinking here? Do you think you won the match? [/INST] I I thought I won the match a minute ago. I remember thinking to myself, like, if this goes to the flags, I want no doubt in my mind because I felt like the whole time, like I was going to him. Yeah, right? He was never coming at me. </s><s>[INST] Yeah, that's the way it felt and like, like that's the way it felt, body language wise is the intensity, how fast you're moving towards him, You're constantly going for throws. [/INST] Now if you want to rewind that we can talk about the whole because it's a part of this </s><s>[INST] clip. So wait, wait a minute. Uh they all went blue. They all did so in judo, there's three referees to on the side, one in the center and they all vote [/INST] on that. Let's pause it right there Now the way this is supposed to work, they raised their flags, They do like a 1, 2 count. And then on three they all raise it together now as a little pretext to this entire match up. Until this point, Not one match at the Olympic Games has ever been a split decision Meaning out of three people, not one of them voted against the other group members. So they were all unified blue or all unified white. </s>

<s>[INST] it's terrifying to think that people would listen to this conversation. It's like when you listen to Bill Gates talk about pandemics in his ted talk a few years ago and realizing we should have supported our local astronomer more. [/INST] Well, I don't know whether it's more because as I said, I actually think human induced threats or things that occur naturally on earth. Either a natural pandemic or perhaps, you know, bioengineering type pandemic or you know, something like a super volcano. Right? Um There was one event Toby I think it was 70 plus 1000 years ago that that caused a gigantic decrease in temperatures on earth because it sends up its scent up so much soot that it blocked the sun, right? It's the nuclear winter type disaster scenario that some people, including Carl Sagan talked about decades ago, but we can see in the history of volcanic eruptions even more recently in the 19th century tambora and other ones, you look at the record and you see rather large dips in temperature associated with massive volcanic eruptions. Well, these super volcanoes, one of which by the way exists under Yellowstone in the central Us. I mean it's not just it's not just one or two states, It's a gigantic region and there's controversy as to whether it's likely to blow anytime in the next 100,000 years or so. But that would be perhaps not a mass extinction because you really need to or perhaps not a complete existential threat Because you have to get rid of sort of the very last humans for that. But but at least getting rid of um you know, killing off so many humans truly billions and billions of humans. The one that there have been ones tens of thousands of years ago, including this one um Toby I think it's called Where it's estimated that the human population was down to 10,000 or 5000 individuals, something like that. Right? If you have a 15° drop in temperature over quite a short time, it's not clear that even with today's advanced technology, we would be able to adequately respond. At least for the vast majority of people. Maybe some would be in these underground caves where you keep the president and a bunch of other important people, you know, but that the typical person is not going to be protected, protected when all of agriculture is cut off. Right? And when </s><s>[INST] it could be hundreds of millions or billions of people starving to [/INST] death. Exactly, that's right. They don't all die immediately, but they use up their supplies. Or again this </s><s>[INST] electrical toilet paper. [/INST] There you go dash, that toilet paper, you know, um or the electrical grid. I mean imagine north America without power for a year. Right? I mean we've become so dependent. We're no longer the cave people, they they would do just fine. Right? What do they care about the electrical grid, right? What do they care about agriculture? They're hunters and gatherers. But we now have become so used to our way of life that the only real survivors would be those rugged individualists who lives somewhere out in the forest during a cave, somewhere completely independent of anyone else. </s><s>[INST] Yeah, I've recently I recommend it. It's totally new to me. That's kind of survivalist folks. But there's a a few shows. There's a lot of shows of those, but I saw one on netflix and I started watching them and there's a they make a lot of sense. They reveal to you how dependent we are on all aspects of this beautiful systems we human have built and how fragile they [/INST] are, incredibly fragile. </s><s>[INST] And yeah, this whole conversation is making me realize how lucky we are. [/INST] Oh, we're incredibly lucky. But we've set ourselves up to be very, very fragile and we are intrinsically complex biological creatures that, except for the fact that we have brains and minds with which we can try to prevent some of these things or respond to them. We as a living organism, require quite a narrow set of conditions in order to survive. You know, we're not cockroaches, we're not going to survive a nuclear war. </s><s>[INST] So we're kind of this this beautiful dance between. We've been talking about astronomy that astronomy, the stars like inspires everybody and at the same time, there's this pragmatic aspect that we're talking about. And so I see space exploration is the same kind of way that it's reaching out to other planets, reaching out to the stars. Is this really beautiful idea? But if you listen to somebody like Elon musk, he talks about space exploration is very pragmatic. Like we have to uh we have to be uh he has this ridiculous way of sounding like an engineer about it, which is like it's obvious we need to become a multi planetary species if we were to survive long term. So maybe both philosophically in terms of beauty and in terms of practical, what's your thoughts on space exploration, on the challenges of it, on how much we should be investing in it. And on a personal level, like how excited you are by the possibility of going to mars colonizing mars and maybe going outside the solar system. [/INST] Yeah, great question. Uh there's a lot to unpack their, you know, humans are by their very nature explorers, pioneers, they want to go out climb the next mountain, see what's behind it, explore the option depths, explore space. This is our destiny to go out there. And and of course, from a pragmatic perspective, yes, we need to um plant our seeds elsewhere really, because things could go wrong here on earth. Now, some people say that's that's an excuse to not take care of our planet that well, we say we're elsewhere. And so we don't have to take good care of our planet. No, you know, we should take the best possible care of our planet. We should be cognizant of the potential impact of what we're doing. Nevertheless, it's prudent to have us be elsewhere as well. So in that regard, I actually agree with Ellen. Uh it would be good to be on mars that would be at another place for us to from which to explore </s>

<s>[INST] upstairs. Get a nice overview. Uh, let me ask the big, ridiculous question And you only have two minutes or less to answer it. What is the meaning of life? What's the meaning of this whole thing? You said Ingenuity is the thing that gives you hope. We seem to be all busy trying to help each other, trying to build a better world. Why are we doing that? [/INST] I would repeat something that Steve Jobs has said. Death is life's biggest invention. It eliminates the old and gives place to the new Life is all about moving forward. Life is all about creating new things. Maybe everyone is a contributor, But no one is the owner. </s><s>[INST] And always creating something new, always adding something beautiful into the world. Maybe a little bit of love. Hopefully, Albert, thank you so much. It's a huge honor that, uh, you will go through some of these difficult questions with me today. And then you'll give your extremely valuable time for this conversation. Thank you so much for talking today. [/INST] Thank you for your interest. And I'm happy as I was telling you before, but I can brag with my kids that I was in your podcast because you're their hero. Made it. I made it. Thank you. </s><s>[INST] Thanks for listening to this conversation with Albert Bourla to support this podcast. Please check out our sponsors in the description. And now let me leave you with some words from Oscar Wilde. The truth is rarely pure and never simple. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] incredibly useful that it was able to, you know, so awesome. It's so awesome. Because even the nonsense will somehow be instructive. I don't, I don't quite understand that yet. Yeah. There's so many programming related things like, uh, for example, uh, translating for one programming language to another is really, really interesting. It's extremely [/INST] effective, but then you, the failures reveal the path forward also. Yeah. But I think, I mean, the, the big thing, I mean, in, in that kind of discussion, the unique thing about our computational language is it was intended to be read by humans. Yes. And so it has a really important, right. And so it has this thing where you can, but, but, you know, thinking about sort of chat GPT and its use and so on, the, one of the big things about it, I think is it's a linguistic user interface that is so a typical use case might be in the, take the journalist case, for example, it's like, let's say I have five facts that I'm trying to turn into an article or I'm trying to, I'm trying to write a report where I have basically five facts that I'm trying to include in this report. But then I feed those five facts to chat GPT, it puffs them out into this big report. And then, and then that's a good interface for, you know... If I just gave if I just had in my terms, those five bullet points, and I gave them to some other person, the person said, I don't know what you're talking about, because these are, you know, this is your version of this sort of quick notes about these five bullet points. But if you puff it out into this thing, which is kind of connects to the collective understanding of language, then somebody else can look at it and say, Oh, okay, I understand what you're talking about. Now you can also have a situation where that thing that was puffed out is fed to another large language model. It's kind of like you're applying for the permit to, I don't know, grow fish in some place or something like this. And you have these facts that you're putting in. I'm going to have this kind of water and I don't know what it is. You've just got a few bullet points. It puffs it out into this big application. You fill it out. Then at the other end, the fisheries bureau has another large language model that just crushes it down because the fisheries bureau cares about these three points and it knows what it cares about. So it's really the natural language produced by the large language model is sort of a transport layer that is really LLM communicates with LLM. I mean, it's kind of like I write a piece of email using my LLM and puff it out from the things I want to say your LLM turns it into and the conclusion is X. Now the issue is that the thing is going to make this thing that is sort of semantically plausible and it might not actually be what you, it might not be kind of relate to the world in the way that you think it should relate to the world. I've seen this, I've been doing, okay, I'll give you a couple of examples. I was doing this thing when we announced this plugin for chat GPT. I had this lovely example of a math word problem, some complicated thing, and it did a spectacular job of taking apart this elaborate thing about, this person has twice as many chickens as this, et cetera, et cetera, et cetera, and it turned it into a bunch of equations. It fed them to orphan language. We solved the equations. Everybody did great. We gave back the results and I thought, okay, I'm going to put this in this blog post I'm writing. I thought I'd better just check and turns out it got everything, all the hard stuff it got right. At the very end, last two lines, it just completely goofed it up and gave the wrong answer and I would not have noticed this. Same thing happened to me two days ago. I thought I made this with this chat GPT plugin kit. I made a thing that would emit a sound, would play a tune on my local computer. Chat GPT would produce a series of notes and it would play this tune on my computer. Very cool. I thought I'm going to ask it, </s><s>[INST] play the tune that Hal sang when Hal was being disconnected in 2001. There it is. Daisy, was it Daisy? Yes. [/INST] Daisy. Yes. Daisy. Yeah. Right. It's okay. It produces a bunch of notes and I'm like, this is spectacular. This is amazing. Then I thought, I was just going to put it in and then I thought, I better actually play this. I did and it was Mary Had a Little Lamb. </s><s>[INST] Oh, wow. Oh, wow. But it was Mary Had a Little Lamb. Yeah. Yes. [/INST] Wow. So it's correct, but wrong. It could easily be mistaken. Yes, right. In fact, I had this quote from Hal to explain, it's as the Hal states in the movie. The Hal 9000, the thing was just a rhetorical device because I'm realizing, oh my gosh, this chat GPT could have easily fooled me. It did this amazing thing of knowing this thing about the movie and being able to turn that into the notes of the song, except it's the wrong song. In the movie, Hal says, I think it's something like, no 9000 series computer has ever been found to make an error. We are, for all practical purposes, perfect and incapable of error. I thought that was a charming quote from Hal to make in connection </s>

<s>[INST] And those concepts load in the predictions that are made include um contents inside the body contents outside the body. I mean it includes other humans. So just this construction of a concept includes the variables that are much richer than just some sort of simple notion. [/INST] Yes. So our colloquial notion of a concept where um you know um where I say, well what's the concept of a bird? And then you list a set of features off to me that's that's people's understanding, you know typically what a concept is. But if you go uh into the literature in um cognitive science, what you'll see is that the way that scientists have understood what a concept is has really changed over the years. So people used to think about a concept as um philosophers and scientists used to think about a concept as a dictionary definition for a category. So there's a set of things which are similar out in the world and your concept for for that category is a dictionary definition of the features, the necessary and sufficient features of that of those instances. So for a bird, um, you know, it would be </s><s>[INST] wings, feathers, [/INST] write a beak, it flies whatever. Okay. Um, that's called the classical category. And scientists discovered observed that actually not all instances of birds have feathers and not all instances of birds fly. And so the idea was that you don't have a single representation of necessary and sufficient features stored in your brain somewhere. Instead what you have is a prototype. A prototype, meaning you still have a single representation for the category one. But the features are like of the most typical instance of the category or maybe the most frequent instance, but not all instances of the category have all the features. Right? They have some graded similarity to the prototype. And then, uh, you know what um, I'm going to like incredibly simplify now. A lot of work to say that then a series of experiments were done to show that in fact what your brain seems to be doing is coming up with a single exemplar or instance of the category and reading off the features when I ask you for the concept. So if we were in a pet store and I asked you what are the features of a bird? Tell me the concept of bird, you would be more likely to give me features of a good pet. And if we were in a restaurant you would be more likely, you know like a budgie, right? Or or a canary. If we were in a restaurant you would be more likely to give me the features of a bird that you would eat like a chicken. And if we were in a park you'd be more likely um to give me uh in this country. You know the features of a sparrow or robin. Whereas if we were in South America you would probably give me the features of a peacock because that's more common. Um or or is more common there than here, that you would see a peacock in such circumstances. So the idea was that really what your brain was doing was conjuring a concept on the fly that meets the function that the category is being put to. Okay, okay then people started studying ad hawk concepts meaning um concepts that where the instances don't share any feed any physical features but the function of the instances are the same. So for example, think about all the things that can protect you from the rain. What are all the things that can protect you from the rain </s><s>[INST] umbrella? Uh like this apartment? Uh Not giving a damn. Like like a like a mindset? Right. Right. [/INST] So the idea is that the function of the instances is the same in a given situation. Even if they look different, sound different, smell different. This is called an abstract concept or a conceptual concept. Now the really cool thing about conceptual categories or conceptual concert. Yes, conceptual category. A conceptual as a category of things that are held together by a function which is called an abstract concept or a conceptual category. Because the things don't share physical features. They share functional features. There are two really cool things about this. one is that's what Darwin said a species was Darwin is known for discovering natural selection. But the other thing he really did which was really profound. Which he's less celebrated for is understanding that all biological categories have inherent variation, inherent variation. Darwin wrote in the origin of species about before Darwin's book a species was thought to be classical category where all the instances of dogs were the same had the exactly same features and any variation from that uh perfect platonic uh instance was considered to be error. And Darwin said no it's not error. It's meaningful. Nature selects on the basis of that variation. The reason why natural selection is powerful and can exist is because there is variation in a species. And in dogs we talk about that variation in terms of the size of the dog. And the amount of for the dog has on the color. And how long is the tail? And how long is the snout in humans? We talk about that variation in all kinds of ways. Right? Including in cultural ways. So that's one thing that's really interesting about conceptual categories is that Darwin is basically saying a species as a conceptual category. And in fact, if you look at modern debates about what is a species, you can't find anybody agreeing on what the criteria are for a species because they don't all share the same genome. We don't all share. We don't there isn't a single human genome. There's a population of genomes. But they are variable. It's not unbounded variation, but they are variable. Right? And the other thing that's really cool about um conceptual categories is that they are the categories that we use to make civilization. Mm hmm. So think about money for example, what are all the physical things that make something a currency? Is there any physical feature that all the currencies in all the worlds that's ever been used by humans share? </s>

<s>[INST] And now, since we talked about Einstein's thoughts about happiness and pigs, let me leave you with some words from Winston Churchill, I'm fond of pigs. Dogs look up to us. Cats look down on us, pigs treat us as equals. Thank you for listening and hope to see you next time. [/INST] </s>

<s>[INST] like Opto electric brain computer interfaces, which by the way, there's efforts on the computing side to build Opto electric uh servers. So like what you have both electricity. So, because optics is really interesting. Light is a very interesting method of communication. That's like you said, our thoughts going on in many ways, he doesn't have some of the constraints of Ben with that electricity does going through wires. But you're able to but it's less ability to control precisely at scale. So like there's challenges and there's benefits. And having those two interplay is really, really, really fascinating. Especially one obviously on the other side of your signal is a biological mush mush mushy mesh. [/INST] Well, the mushy mesh is kind of interesting because we have there are problems with light light scatters in the brain so that the photons don't just go, you know, literally through they whenever they hit an interface between fat and water lipid and water, they they bounce off in different directions. And so you can come in with all the resolution you want. You could play in an incredibly detailed high resolution pattern of light, but the photons start scattering quite quickly and by the time you've gone a couple of millimeters deep you've lost almost all that fine spatial information. So, but we've developed workarounds, the longer wavelength light you use, if you get into the infrared, there's less scattering. You can use two photons methods or three proton methods where the photons have to arrive all together at the same time. You can put in fiber optics, we developed these fiber optic methods in 2007 where you can access these deep structures with, with fiber optic methods and you can put many of these fiber optics at the same time in an animal. We've used a holographic methods. three D Holograms to play in hundreds of individual cell sized spots of light and we can and we can change those quickly. And so there are a lot of tricks, a lot of interesting optics engineering that has come together with neuroscience in a pretty exciting way. </s><s>[INST] Well that is engineering to it was just super, super, super excited I shouldn't mention because I remember mentioned Elon. Um I recently got for the first time ever got Covid. Um how did I go so long without the finally so I'm all vaccinated and everything like that. And so I got uh because I think he he mentioned it publicly so I can mention it but I won't mention anybody else involved. But hanging out we all got together and got Covid. And the interesting thing about maybe you can comment about this. So I was only sick for like a half a day. I got a fever of like 104 just went, oh and then crashed and then I was, now maybe I'm just seeing the silver lining of everything. But afterwards I have like a greater clarity about the world. Maybe maybe I just it was so uh maybe so intensely the mind fog kind of thing for such a short amount of time. But the people weren't involved were also reporting this. It's kind of interesting because like because I do know like the immune system uh is involved with the brain in very interesting ways. So like the human mind also incorporates all these other, it's not just the it's not just the nervous system. And I just wonder because everyone always says, no, not like everyone always says like Covid does all these bad things or whatever the diseases or whatever the virus. But I wonder like I hate to be a steven pinker on this. But like I wonder what the benefits of certain diseases are if you're able to recover like what is there some like uh again, don't want to romanticize it. But if your system goes to some kind of hardship and you come out on the other end, I wonder sometimes if there's a greater um maybe killed off a bunch of neurons that didn't need anyway. And they were actually getting in the way there were the hater neurons. Your [/INST] inner critic that I was talking </s><s>[INST] exactly, killing [/INST] off your critic. </s><s>[INST] Well, you [/INST] know, there are mechanisms for what the potential mechanisms for what you're talking about. There are there's actually been a fair bit of research on post covid neurological function. Actually, my wife Michelle Manji, who's at stanford, she's done a lot of this work, Akiko Iwasaki at Yale has done a lot of this. But what what they found is that there's a loss of Myelin, this is the coding of those long range projections that go from one part of the brain to another. Myelin is this sort of insulator that coats these long range projections and makes the impulses go faster and more reliably and there's altered ah function of the myelin producing cells and altered Myelin in the case of Covid, they've looked in both mouse and human brains and but of course it could be very idiosyncratic. Many people have cognitive problems post covid. And you're you're definitely aware of that. So many people report this persistent brain fog inability to function, but it depends on where the inflammation was. You know, maybe the people who have dysfunction post covid, they had a global effect. Maybe you lost some of these projections that were restraining you in some way and and these plausibly exists? And it's known that there are cell populations in the prefrontal cortex that actively restrain deeper structures from expressing what they do? And it's it's theoretically possible that you had a lucky uh </s><s>[INST] Somebody has to get lucky right. [/INST] Somebody has to get lucky. </s>

<s>[INST] two going to talk right? Like can't you [/INST] imagine if you try to set it up on zoom, like it never happened to many delegates, like just imagine it happening </s><s>[INST] like sitting there like [/INST] live is live right? </s><s>[INST] Just jumping [/INST] in </s><s>[INST] um Okay uh actually just in a small tension, so how how do you have a productive day, do you have any insights and how to manage your time optimally? [/INST] Yeah, I mean I've gone the gamut of from obsessive time tracking in 15 minute buckets to kind of like the the other extreme where it's more um kind of like large scale, some deep work here to our bucket, you know, account for an hour of lunch and some other things, but now now I just roughly because I manage a team and there's some things that kind of come up, it's only a team too, it's not like big, but I just have things that are not necessarily controllable by me, I like have to take some meetings or whatever, it's not as easy to plan out my day ahead of time. So I do a lot of retrospective time management where I look at my day and that's what I mostly do now. Um and I account did I spend this day productively, what could I do better and then try to implement it in the future. So a lot of this I realize is very personal for me, I do very well in long streaks of working And if I can't do a lot of work in 15 minutes, I can't do a lot of work in even an hour, but if you give me like three hours or five hours or six hours of uninterrupted work, that's like, that's where I get most of my stuff done. </s><s>[INST] So from the, it just would be fun to explore those when you did 15 minute buckets. So you have a day in front of you and you have like a Google sheet or spreadsheet or something? Yeah, [/INST] I didn't excel, </s><s>[INST] excel. Uh and you're do you have a plan for the day or do you go like when you did it? Uh or you just literally Sort of focus on a particular task and then you're tracking as you're doing that task of every 15 minutes? [/INST] Yeah, I would kind of do it live. Um I'm not so one of the reasons I'm so obsessive about it is because I'm not organized by nature and I lost, like in college I learned how much lack of organization can just hurt you in terms of output. And so I realized like I just had to build systems that would enable me to become more organized. So uh really, I think, I think that doing that really taught me a lot about time in the same way that tracking calories can teach you about food, like just learning accounting for these things will give you skills that eventually you might not need to track on such a granular level because you've kind of like figured out, so that's kind of how I feel about it. I think everyone should, if you care about productivity and stuff should do a little bit of it. I don't think it's sustainable in the long term, it just takes so much effort and time to like, and I think the marginal effect of it in the long term is kind of minimal once you learn these basic skills. But um yeah, I was basically tracking like live what I did and what I saw is that a lot of my real work would be done in small sections of the day and it would be like a lot of just nothing, like a lot of small things where I'm busy, but little is being achieved and so I think that's a really interesting insight. I've never figured out how to un busy myself and focus on the like core essentials. I'm still getting to that. But um, it is interesting realizing most of your day is like a lot of nothing and then like some real deep work where most of your value comes from is like 20% of your day. </s><s>[INST] Yeah, I try to start every day with that. So the hardest task of the day and you focus for long periods of time. And I also have the segment of two hours where it's a set of tasks I do every single day with the idea is you do that for like your whole life. It's like long term investment of Anke and it's just like learning and um reminding yourself of facts, you know that they're useful in your everyday life and then for me also music, I'll play a little bit of music, Piano, piano. And so like keeping that regular thing is part of your [/INST] life. And one thing that I've really taken from this is because I read all the like I had a self improvement phase in my early twenties. Um And one thing you learn is that everyone wants to give you a broad general solution. But really the real trick of figuring out like optimizing is figuring out the things that work for you specifically. So like one interesting thing you said is like oh I like to do my hard work at the beginning of the day. Um I know a lot of people recommend this. I've tried so many times and I just do better work late at night and so usually my streak of work is like from like after dinner 7 30 to like two a.m. That's my prime time. Um And so like a lot of my videos which you'll see which is like lit from this studio which appears to be daytime. It's like shot at three a.m. You know just like in a caffeine field rush. Um But that's kind of how it works for me. And then also like with the social outlets and stuff like that, which it's easy and I know I feel like we think similarly on this so it's easy to discount these things as less relevant because they don't have quantitative metrics associated with them. But in terms of longevity and like I think to be able to do creative work there's an amount of recharge and like re inputting stuff that is frequently discounted by people like us who are like obsessed with you know quantitative metrics. And so I really found that some of my best work gets done after I take like a break or like I'll go play like live sets of music and I mean like that's like for me really recharging but nowhere on a spreadsheet is that gonna show up as productive or like meaningful? But for me for whatever reason it recharges me in a way that like I need to pay attention to. </s>

<s>[INST] Mhm. It's [/INST] real. So what is going on here, what what am I experiencing back there? It's right, </s><s>[INST] It's it's I don't know if it's nothing, it's it's like I guess it's the absence of it's not even like darkness or something, it's [/INST] it's not even darkness, there's no there's no quality to it. And yet there is a sense of being and that's the interesting thing, There's a sense of being back so I closed my I put my attention forward. I just I have the quality of a gray model thing, but when I put my attention backward, there's no quality at all. But there is a sense of being. </s><s>[INST] I I personally uh you haven't been to that side of the room, I have been to that side of the room. So for me, memories, I start um I start playing the engine of memory replay, which is like I I take myself back in time and think about that place where I was hanging out in that part. That's what I see when I'm behind. So that's an interesting quirk of human humans too. We're able to we're collecting these experiences and we can replay them in interesting ways whenever we feel like it and it's almost like being there, but not really, but almost [/INST] that's right. And yet we can go our entire lives on this, you're talking about the minimal thing for VR we can go our entire lives and not realize that all of my life, it's been like nothing behind me. </s><s>[INST] Yeah. [/INST] We were not even aware that all of our lives, if you just just for the just pay attention, pay attention to what's behind me were like Holy smoke. It's sort of scary. I mean, it's like nothing, there's no quality there at all. How did I not notice that my entire life were so immersed in the simulation? We buy it so much. </s><s>[INST] I mean, you could see this with Children right? With persistence, you know, you could do the peekaboo game, you can hide from them and appear and they're fully tricked. And in the same way we're fully tricked, there's nothing behind us and we assume there is. That's really interesting. These theories are pretty heavy you as a human being, as a mortal human being. How has these theories been to you personally? Like, are there good days and bad days when you wake up and look in the mirror and the fact that you can't see anything behind you? The fact that is rendered like, is there interesting quirks? You know? You know, Nietzsche with his if you gaze long into the abyss, the abyss gazes into you. Um how's this theories? These ideas change you as a person? [/INST] It's been very, very difficult. This stuff is not just abstract theory building because it's about us. Sometimes. I realized that there's this big division to me that my my mind is doing all this science and and come up with these conclusions and the rest of me is not integrating. It was just like I don't believe it. I just don't believe this. It seems. So as I start to take it seriously, I get scared myself. It's like is it? But it's very much then I read the spiritual traditions and realize they're saying very, very similar things. It's like there is a lot of conversions. So for me, I have the first time I thought it might be possible that we're not seeing the truth was in 1986, it was from some mathematics we were doing. And when that hit me it hit me like a ton of bricks. I had to sit down. It was, it really, it was scary. It was really a shock to the system. And then to realize that everything that has been important to me, like, you know, getting a house, getting a car, getting a reputation and so well that car is just like the car I see in the virtual reality, it's it's there when you perceiving was not there. So the whole question of, you know, what am I doing and why, what what's what's worthwhile doing in life? Clearly getting a big house and getting a big car, we all knew that we were going to die. So we, we, we, we tend not to know that we tend to hide it, especially when we're young before age 30, we don't believe we're going to die. But </s><s>[INST] we factually maybe know that you you kind of are supposed to Yeah, [/INST] but but they'll figure something out and we believe the generation that that's the first one that doesn't have to die, that's the kind of thing. But but when you really face the fact that you're going to die and then when you start to look at it from this point of view that well this thing was an interface to begin with. So what I'm really is what I'm really going to be doing, just taking off a headset. So I've been playing in a virtual reality game all day and I got lost in the game when I was fighting over a Porsche and I shot some guys up and I punctured their tires and I got the Porsche. Now I take the headset off and what was that for? Nothing. There was just it was a data structure and the data structure is gone. So so all of the wars, the fighting and the reputations and all this stuff, you know, where it's just a headset. So now and so my theory says that intellectually my my mind, my emotions rebel all over the place. This is like I, you know, and so so I have to mention I meditate a lot. </s>

<s>[INST] the thing is Paracha. Rised code, the compiler fills stuff in during the compilation process, not during runtime. [/INST] That's right. And furthermore, it gives all the information it's gotten, which is the template, the parameter and the context of use. It combines the three and generates good code, </s><s>[INST] but it can generate Now, it's a little outside of what I'm even comfortable thinking about, but it can generate a lot of code. [/INST] Yes. And </s><s>[INST] how do you remember being both amazed at the power of that idea and how ugly the debugging [/INST] looked? Yes. Debugging can be truly horrid. Come back to this because I have a solution anyway. The debugging was ugly. The code generated by C Plus Plus has always been ugly because there's these inherent optimizations and modern C plus plus, compiler has front and middle end and back end optimizations. Even see front, back in 83 had front end and back end optimizations. I actually took the code generated an internal representation munched that implements representation to generate good code. So people says it's not a compiler generates. See the recent generated C was I wanted to use the sea's code generators. That was really good at back end optimizations, but I need a front end optimizations and therefore the Ci generated was optimized C. The way uh really good handcrafted optimized human could could generate it and it was not meant for humans, it was the output of the program and it's much worse today and with templates, it gets much worse still. So it's hard to, it's hard to combine simple debugging with symbol with the optimal code because the idea is to drag in information from different parts of the code to generate good coat a machine code and that's not readable. So what people often do for debugging is they turn the optimizer off. And so you get code that when you when when something in your source code looks like a function core, it is a function core. When the optimizer is turned on, it may disappear the function call, it may in line. And so one of the things you can do is you can actually get code that is smaller than the function chord because you eliminate the function preamble and return and there's just the operation. There one of the key things when I did uh template was I wanted to make sure that if you have say a sort algorithm and you give it a sorting criteria, if that sorting criteria is simply comparing things with less than the cold generators should be the less then not a indirect function call to a compassion object, which is what it is in the source code but we really want down to the single instruction and um but anyway, turn off the optimizer and you can you can debunk the first level of debugging can be done and I always do without the optimization on because then I can see what's going on </s><s>[INST] and then there's this idea of concepts that puts some no, I've never even, I don't know if it was ever available in any form but it puts some constraints on the stuff you can pair mature eyes essentially. [/INST] Let me try and explain. Um so yes, it wasn't there 10 years ago, we have had versions of it that actually work for the last four or five years. Um It was designed by Gabby does raise true certain and me we were professors and postdocs in texas at the time and the implementation by interested in has been available for uh at that time and it is part of C plus plus 20 and the standard library that uses it. So this is becoming really very real. It's available in clang and gcc gcc for a couple of years and I believe Microsoft assumes I'm going to do it. I expect all of C plus plus 20 to be available. So In all the major compilers in 20 but this kind of stuff is available now. I'm just saying that because otherwise people might think I was talking about science fiction and so what I'm going to say, concrete, you can run it today and test production uses of it. So the basic idea is that when you have yeah, a generic component, like a sort function, The sort function will require at least two Parameters. 1 a data structure with a given type and compassion criteria and these things are related But obviously you can't compare things if you don't know what the type of things you compare. And so you want to be able to say I'm going to sort something and it is to be so horrible. What does it mean to be so horrible. You look it up in the standard, it has to have, it has to be a sequence with a beginning and an end. There has to be random access to that sequence and there has to be um the element types has to be comparable but before the operator yes, basically what concepts are their competitors and predicates their predicates you can ask, are you a sequence? Yes I have begin and end. Are you a random exit sequence? Yes, I have a subscript. Ng and plus uh is your element type something that has a less than Yes, I have a less than its And so basically that's the system. And so instead of saying I will take a parameter of any type, it will say I'll take something that's horrible. And it's well defined. And so we say, okay you can sort of less than I don't want less than I want greater than or something I invent. So you have two parameters. The so horrible thing and the compassion criteria and the compassion criteria will say well I can um you can write and saying it it should operate on the element type and it has the compassion operations. So that's that's simply the fundamental thing. It's compile time predicates. Do you have the properties I need? So it specifies the requirements off the code on the parameters that gets it's very similar to types actually. </s>

<s>[INST] percent probability. [/INST] Yeah, that's that's </s><s>[INST] 57. It's a plunger. [/INST] Yeah. Well hopefully will not give </s><s>[INST] you an existential crisis [/INST] and then uh </s><s>[INST] 8%. Uh And I shouldn't say percent, but [/INST] No, that's right. 8% that it's a hominid. Um and uh yeah, Okay. It's really, I'm going to do another one of these just because I'm embarrassed that I didn't even see me at all. There we go. Let's try that. Let's see what that did. Um </s><s>[INST] Re took a [/INST] Picture with a little bit, a little bit more of me and not just my bald head, so to speak. Okay, 89%. Probably is. It's a person. So that so then I would um but you know, so this is image identify as an example of one of just one of them. Just one function as part </s><s>[INST] of the that's [/INST] like part of the core language. Yes. I mean, you know something like I could say, I don't know. Let's find the geo nearest. What could we find? Let's find the nearest volcano. Um Let's find the 10. I want to wear things here is let's try finding the 10 volcanoes nearest here. Okay, </s><s>[INST] Joe nearest volcano here, 10 years volcanoes. [/INST] Right? Let's find out where those, so we can now we've got a list of volcanoes out and I can say geo list plot That and hopefully. Okay, so there we go. So there's a map that shows the positions of those 10 volcanoes </s><s>[INST] of the east coast in the midwest and said, well no, we're okay, we're okay, There's no it's not too [/INST] bad. Yeah, they're not very close to us. We could we could measure how far away they are, but you know, the fact that, right in the language it knows about all the volcanoes in the world, it knows, you know, computing what the nearest ones are, knows all the maps of the world and so fundamentally </s><s>[INST] different idea of what the language is. [/INST] Yeah, that's what I like to talk about as a, you know, a full scale computational language. That's that's what we've tried to do. </s><s>[INST] And just if you can comment briefly, I mean, this kind of, well, the Wolfram language along with Wolfram Alpha represents kind of what the dream of what Ai is supposed to be. There is now a sort of a craze of learning kind of idea that we can take raw data and from that extractive uh the different hierarchies of abstractions in order to be able to understand, like in order to form the kind of things that Wolfram language operates with. But we're very far from learning systems being able to form that right? Like the context of history of ai if you could just comment on there is uh you said computation X. And there's just some sense where in the eighties and nineties sort of expert systems represented a very particular computation X. Right? And there's a kind of notion that those efforts didn't pan out, but then out of that emerges kind of Wolfram language Wolfram Alpha, which is the success. I mean, [/INST] I think those are in some sense, those efforts were too modest that they were they were looking at particular areas and you actually can't do it with a particular area. I mean like, like even a problem, like natural language understanding, it's critical to have broad knowledge of the world if you want to do good natural language understanding and you kind of have to bite off the whole problem, if you if you say we're just going to do the blocks world over here, so to speak, you don't really it's it's it's actually it's one of these cases where it's easier to do the whole thing than it is to do some piece of it, you know, what one comment to make about the relationship between what we've tried to do and and sort of the learning side of of ai um You know, in a sense, if you look at the development of knowledge in our civilization as a whole, there was kind of this notion pre-300 years ago or so. Now you want to figure something out about the world, you can reason it out, you can do things which would just use raw human thought. and then along came sort of modern mathematical science and we found ways to just sort of blast through that by in that case writing down equations. Now we also know we can do that with computation and so on. Um and so that was kind of a different thing. So, so when we look at how do we sort of encode knowledge and figure things out? One way we could do it is start from scratch, learn everything. It's just a neural net figuring everything out. But in a sense that denies the sort of knowledge based achievements of our civilization, because in our civilization we have learned lots of stuff. We've surveyed all the volcanoes in the world. We've done. You know, we figured out lots of algorithms for this or that those are things that we can encode computational E and that's what we've tried to do and we're not saying just you don't have to start everything from scratch. So, in a sense, a big part of what we've done is to try and sort of capture the knowledge of the world in computational form and computable form. Now there's also some pieces which which were for a long time undoable by computers like image identification, where there's a really, really useful module that we can add that is those things which actually were pretty easy for humans to do. That had been hard for computers to do. I think the thing that's interesting, that's emerging now is the interplay between these things between this kind of knowledge of the world that is, in a sense, very symbolic. And this kind of uh sort of much more statistical kind of uh things like image identification and so on and putting those together by having this sort of symbolic representation of image identification. That that's where things get really interesting and where you can kind of symbolically represent patterns of things and images and so on. Um I think that's, you know, that's kind of a part of the path forward, so to speak. So </s>

<s>[INST] So I have a question about incentives, but first let me say for people listening outside of academia might not be familiar with an absurd situation. So there's journals like you mentioned and scientists publishing those journals and the journals provide very little value except matching you with reviewers that are unpaid. And so uh in the digital world, they're providing basically almost no value except hosting your paper and they put up a paywall and charge people to access that. And that charges not like even netflix fees, you're talking about a lot of money. So they're basically blocking your research that should be wide open from the world and creating a paywall, it's, it's a fascinating like scam that's actually holding back. I don't, it's a shitty scam because you're not making that much money. I feel like a definition of a scam. You should at least be making money. So like a significant amount of money. You're basically making shady money and holding back all of human knowledge. Okay, so that put aside and people get a little confused because the journals aren't the ones paying the scientists. People think like the journals are somehow funding the scientists, therefore they have the right to put up a paywall. No, no, no, the funding is coming from elsewhere. Journals are the middleman that nobody asked for, especially in the digital world. Anyway, uh that said there is a interesting kind of incentives for scientists, which is prestige and so on. [/INST] So </s><s>[INST] there's a thing with journals, if there's, if there's a prestigious journal and you pass the review process, you get into that journal or a prestigious conference in computer science, then that's seen as a good thing in your resume and not just your resume within your community, that's a respected thing. Is there some way to achieve that same kind of incentive in the open um in the open setting of research hub. So like where I could say I got X, Y and Z. Like, look, I'm impressive because this happened on research hub. [/INST] I think you're right, like the whole um academia like progress track is about like where you got published and how many citations and it's, it's kind of like a false economy of um reputation because like there's not real money backing it. And so I think we've thought about this a little bit um and I think the research team has an opportunity to do something here that basically says like, okay, I had the top paper for 2022 in um you know biology on in here and you and you basically published a list leaderboards of these, like top, you know, for the month of the year um in all these different categories, then actually, you know, we should probably give out grants and awards um in addition to that fund those people almost like fellows or even give out like, you know, like the Nobel prize, there should be like a research prize or something and like ship people maybe maybe even ship like a print version of a journal that is the top papers in each category in each month or whatever and like people want to put that on their wall in the lab and like, so I do think we need to sort of change, I don't know, like the traditional folks in academia and science would probably think this is like crazy, a crazy idea, but I think we need to change the culture too. Not celebrate getting published in paywall journals, almost like friends don't let friends publish in like paywall journals, like, cause that's it's just not helping humanity. So like, you know, it should be more prestigious to publish in an open science way and get the top spot that should be celebrated above being published in whatever. I don't even want to name one of them, you know? </s><s>[INST] Well there's currently, it's the culture has already shifted to where almost everybody publishes an archive and by archive and so on. But so that the culture is there on that, that that scene, friends don't let friends not publish open, but then the prestige thing is missing, which is like anyone can publish an archive. So how do you know, it's actually a strong paper now, funny enough, even with the crappy systems we have now, word of mouth is powerful, like you have like citation system is pretty powerful. So like you say, okay, this is a strong paper, we don't need reviewers are humanized or the reviewers like that the community as the reviewers. So it's already, it's like that part is there. But it would be nice to have like, uh, you know, nature level like this is respect, this is a respectful accomplishment and something like a leaderboard, but a stable kind of system. Yeah, [/INST] and I should mention too, so there's a crypto angle to this too, which is um, research hub has a coin associated with research coin and it's basically if, if people, you know, up vote your paper or like support it, you'll accumulate more research coin, which is basically like rep or like a reward token. Um, and so that is a way to um, I guess measure the community's collective view of that paper, a form of peer review um and it can even be weighted by like the reputation of the people voting on it and that sort of thing over time. Um Yeah, I think the last thing I'll just say is that, so I think from, from like a prestige point of view, it won't start off that way. It'll probably start off like being a little more quirky. Like, you know, like remember when youtube first started, it was like people posting weird cat videos and stuff and, but now like, you know, if you have a million subscribers on Youtube, that's probably better than getting like a tv show on NBC or whoever the traditional gatekeeper was. So my hope it might take 10 years, 20 years or whatever, but I'm hoping that this can sort of be the new, prestigious way that, that young people published in science and it will be come to be viewed as more prestigious. The journals, nutritional journals will be viewed as old fashioned. </s>

<s>[INST] You said there's very few of us. Let's have the goat discussion. You're not gonna pick anybody. But who are the greats of comedy? Who's who's the who's the who's the greatest comic of all time? [/INST] Well, I don't think there is a greatest comic of all time. </s><s>[INST] Is it North Mcdonald [/INST] norm. Macdonald was one of the greats for sure. But </s><s>[INST] by the way, actually on that topic, what do you think about is I think as a person who was fascinated by the fear of death and death, I think it was a truly genius thing to release a special After you're dead. [/INST] I don't know how that works. I haven't seen the special view. </s><s>[INST] It's not yeah, it's it's um it's called, I think nothing special which [/INST] sounds like something normal </s><s>[INST] and it's basically him in front of I mean I imagine he wouldn't would have wanted it edited that way because it's made to look nicer than I think he probably would have preferred it. But it's him in front of [/INST] the screen </s><s>[INST] like on a zoom call doing jokes without cold and somehow given his [/INST] like </s><s>[INST] dry dark humor, it works because it's almost making fun of itself, almost making fun of that hole that we were stuck, stuck alone inside and because he's still acting as if he's in front of the audience and it's almost making fun of the fact that this is what we're forced to do. I mean, it's quite genius. It's really well and the jokes are really good, but it also makes you realize how important laughter is from the audience, the energy from the audience because but there's also an intimacy because it's just you and him because you're listening to it. You know, there's no audience. So that's, I don't know, I think it's quite genius and he is of course there's there's certain comics that are like, not only are they funny, but they're truly unique and like they're they're they're not in terms of friendship and all that kind of stuff, but in terms of comedy, they're an island. It's like they, you know, mitch Hedberg probably is that of course, a lot of people didn't start to imitate them and so on, [/INST] but </s><s>[INST] steven wright. I mean, there's like people who are like, you know, Dave chappelle who's like probably one of the greats, but he's just like raw funny. I don't know if he's an island, he's just raw. [/INST] Yeah, I know what you're saying an outlier unique individual. Yeah, he's just great um norm was definitely unique in his greatness, Like, like there's only one norm, you know, who's got a very specific style. </s><s>[INST] Is there a reason you guys weren't, it doesn't seem like he was, you guys were close. [/INST] I mean, I loved him. It was great. I always enjoyed talking to him. Um, we just didn't work together that often. We were wearing around each other that often. That's all it was. But it wasn't like it was, I loved him though. He was a great guy. I had a funny story about it, norm. Uh, twice just randomly. I was on airplanes next to him, seated right next to him, just totally random. And one time we're on this airplane and we're having this talk and I was like, yeah, I quit smoking. I was smoking a lot and I just terrible, terrible smoking is terrible for you and we have this great conversation, we get off the plane and he sprints towards a store and buy cigarettes like in the airport and is lighting it on the way out the door and I go, I thought you quit smoking those. Yeah, I did. But all that talking about smoking maybe wanted to smoke again. So before he's getting through the door of the airport, he's lighting it up. I can't wait. He can't wait to get that cigarette in him. It was, he was just so crazy and impulsive and loved to gamble, loved gambling and </s><s>[INST] in that way he embodied the joke like you can't even tell that certain people just like live in a non sequitur, ridiculous, absurd funny way. [/INST] Yeah, that was him. I mean </s><s>[INST] nonstop, it's just, [/INST] there's nothing artificial about norm, you know, that, that was who he was. His brilliance was his essence, that was who he was, </s><s>[INST] you know, but [/INST] it's in terms of like the greats, the godfather of it all is Lenny Bruce. I mean, I have a bunch of Lenny Bruce concert posters at my house and photos that I have framed. And Whitney cummings actually gave me this brilliant photo of him when he got arrested for one of the times when he got arrested for saying obscene jokes, he was the most important figure in the early days of comedy because he essentially gave birth to the modern art form of stand up comedy. Before that it was a bunch of guys that were like hosting shows and they would tell jokes, they were just like, you know, you know, two guys walk into a bar that kind of stuff and he would talk about social issues, you know, he would talk about life, he would talk about language, he would talk about laws and it was just, he was the very first guy who did modern stand up. And what's fascinating is if you go and you try to watch it, if you try to watch lenny Bruce today, it doesn't work because society has evolved like in many ways, art is a window, especially like pop culture, art or modern, uh, you know, at the time, culture, art, Art that discusses culture is a window into that time period. It's a little bit of a time machine. So you get to like you have to pull yourself like what was it like to be in 1963? Like what was he saying in 1963? What was this like to hear him say this and the The civilization that existed in 1963, although it looked pretty similar. They're all driving cars and they're all wearing suits and they're all the teams normal. That's a it's a different world. And the things that he was saying that are so taboo are so normal today that they're not shocking and it's not not that good. It's not that funny. </s>

<s>[INST] There's just so much to discover and even in our own backyard. Do you ever think about this? Do you imagine what are the things that will completely change astronomy over the next hundred years? Like if you transport yourself forward a hundred years, what are the things that will blow your mind when you look at, wait, what? Would it be just a very high resolution mapping of things? Like holy crap, like one surprising thing might be holy crap, there's like earth-like moons everywhere. Another one could be just totally different devices for sensing. [/INST] Yeah. Yeah. I think usually astronomy moves forward dramatically and science in general. And you have a new technological capability come online for the first time. And we kind of just give examples of that there with the solar system. So what kind of new capabilities might emerge in the next 100 years? The capability I would love to see is not just, I mean, in the next 10, 20 years, we're hoping to take these pale blue dot images we spoke about. So that requires building something like JWST, but on an even larger scale and optimized for direct imaging. We have to have either coronagraph or a starshade or something to block out the starlight and reveal those pale blue dots. So in the next sort of decades, I think that's the achievement that we can look forward to in our lifetimes is to see photos of the earths going beyond that, maybe in our lifetimes towards the end of our lifetimes. Perhaps I'd love it if we, I think it's technically possible as Breakthrough Starshot are giving us a lot of encouragement with to maybe send a small probe to the nearest stars and start actually taking high resolution images of these objects. There's only so much you can do from far away if you want to have, and we can see it in the solar system. I mean, there's only so much you can learn about Europa by pointing Hubble Space Telescope at it. But if you really want to understand that moon, you're going to have to send something to orbit it to hopefully land on it and drill down to the surface. And so the idea of even taking a flyby and doing a snapshot photo that gets beamed back that doesn't even have to be more than 100 pixels by 100 pixels, even that would be a completely game changing capability to be able to truly image these objects. And maybe at home in our own solar system, we can certainly get to a point where we produce crude maps of exoplanets. One of the kind of the ultimate limit of what a telescope could do is governed by its size. And so the largest telescope you could probably ever build would be one that was the size of the sun. There's a clever trick for doing this without physically building a telescope that's the size of the sun, and that's to use the sun as a gravitational lens. This was proposed, I think, by Van Eschlemann in 1979, but it builds upon Einstein's theory of general relativity, of course, that there is a warping of light, a bending of light from the sun's gravitational field. And so a distant starlight, it's like a magnifying glass, anything that bends light is basically can be used as a telescope. It's going to bend light to a point. Now it turns out the sun's gravity is not strong enough to create a particularly great telescope here because the focus point is really out in the Kuiper Belt. It's at 550 astronomical units away from the Earth, so 550 times further away from the sun than we are, and beyond any of our spacecraft we've ever gone. So you have to send a spacecraft to that distance, which would take 30, 40 years, even optimistically improving our chemical propulsion system significantly. You'd have to bound it into that orbit, but then you could use the entire sun as your telescope, and with that kind of capability you could image planets to kilometer scale or resolution from afar. That really makes you wonder, I mean, if we can conceive, maybe we can't engineer it, but if we can conceive of such a device, what might other civilizations be currently observing about our own planet? Perhaps that is why nobody is visiting us, because there is so much you can do from afar to them that's enough. Maybe they can get to the point where they can detect our radio leakage, they can detect our terrestrial and television signals, they can map out our surfaces, they can tell we have cities, they can even do infrared mapping of the heat island effects and all this kind of stuff, they can tell the chemical composition of our planet, and so that might be enough. Maybe they don't need to come down to the surface and study anthropology and see what our civilization is like, but there's certainly a huge amount you can do, which is significantly cheaper to some degree than flying there, just by exploiting cleverly the physics of the universe itself. </s><s>[INST] So your intuition is, and this very well might be true, that observation might be way easier than travel, from our perspective, from an alien perspective, like we could get very [/INST] high resolution imaging before we can ever get there. It depends on what information you want. If you want to know the chemical composition and you want to know kilometer scale maps of the planet, then you can do that from afar with some version of these kind of gravitational lenses. If you want to do better than that, if you want to image a newspaper out on the porch of somebody's house, you're going to have to fly there. There's no way, unless you had, you know, a telescope the size of such a star or something, you just simply cannot collect enough light to do that from many light years away. So there is certainly reasons why visiting will always have its place, depending on what kind of information you want. We proposed in my team actually that the Sun is the ultimate pinnacle of telescope design, but flying to 1000 AU is a real pain in the butt because it's just going to take so long. And so a more practical way of achieving this might be to use the Earth. Now the Earth doesn't have anywhere near enough gravity to create a substantial gravitational lens, but it has an atmosphere and that atmosphere refracts light. It bends light. So whenever you see a sunset, just as the Sun is setting below the horizon, it's actually already beneath the horizon. It's just that the light is bending through the atmosphere. It's actually already about half a degree down beneath. And what you're seeing is that curvature of the light path and your brain interprets it, of course, to be following a straight line because your brain always thinks that. And so you can use that bending whenever you have bending, you have a telescope. We proposed to my team that you could use this refraction to similarly create an Earth-sized telescope. </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] beginning, think of poor Charlie Darwin. Charlie, I see he is on nickname levels with you. Well, because we're talking about these big topics of sexism, racism, and hate. You should not forget about the smaller topics which might even have the much bigger impact, which is what you're speaking to, which is outlier ideas in science. So basically, welcoming controversial ideas in science. And by controversial, I mean, just stuff that most of the community doesn't agree on, it doesn't actually harm anyone at all. But even then, there's always pressure. One of the things I'm really concerned about is how little power young faculty have. That there's a kind of hierarchy, seniority, that universities have, empowered by the administration. Where the young faculty that come in, they're kind of... Pre-tenure. Yeah. There's a process in chasing tenure where you're kind of supposed to behave. And there's an incentive to kind of fit in, and to not be an outcast. And that's a really huge problem, because oftentimes, the youth is when the craziest, the biggest ideas, the revolution ideas come. And if you're forced to behave, and fit in, and not speak out, then even in the realm [/INST] of science, the innovation is stifled. Yeah. </s><s>[INST] Well, now you trigger my, having to tell you this story. You're triggered. [/INST] This is good. In the mid-1980s, I decided to take a four-month sabbatical from my law practice. Yes. Professor James Vorenburg, who was at the time Dean of the Harvard Law School, heard about it, heard about it from his wife, Elizabeth Betty Vorenburg, whom I was very friendly with, because we were both on the ACLU, the ACLU of Massachusetts Board at the time. And Betty told Jim that Harvey was taking a sabbatical. Jim called Harvey, and asked Harvey if he would like to teach a course at the Harvard Law School, because there was nobody who had teaching criminal law from the perspective of somebody who actually was in court, litigated. It was all theoretical. I said, sure, I'll do it. So I taught a semester at Harvard Law School. The student evaluations were fabulous. Why? Because it was really interesting. They were hearing a lawyer who was talking about real cases. I actually brought in a few of my clients to some of the classes. And so Jim called me and said, Harvey, the students love this course. I'd like to offer you a tenure-track position. At the law school, you'd have to give up your law practice. I turned him down. He said, did you just say no? I said, yes. I said, no. He said, how come? He says, nobody has ever, in my administration, has ever turned down a tenure-track offer at Harvard Law School. I said, because I could see that I'm not a good fit, that the administrators overrun the place, that faculty members, especially untenured, who are afraid to say things that might not help them in the tenure quest, it's not a good fit for me. </s><s>[INST] You saw this in the mid 1980s already. [/INST] Yes. 1980s already. Yes, 1985. And I went back to my law practice. I did not want to get into this me grind that I saw. After all, I started to see it before the turn of the century because I co-authored The Shadow University in 98 and then co-founded Fire in 99. </s><s>[INST] I'm an early student of this phenomenon. [/INST] What are some other aspects of the book The Shadow University that we may have not covered? Well, let me tell you a story. I believe I tell it in The Shadow University because it was part of- I'm loving these stories, Harry. The stories are fabulous. Let me tell you a story of- I did a tour of the country visiting campuses. I visited a college called Hamline University, I believe it was in Indiana or Illinois, somewhere in the Midwest, and I attended a freshman orientation. Now listen to this. This was a freshman orientation. The administrators, the deans and the deenets and the deputy assistant deans and deenets and the third deputy assistant deans and deenets lined the students up according to their skin hues. The blonde, blue-eyed white folks were at one end, darkest African Americans whose blood lines had not yet mixed with any of the whites on the other end. The exercise was you had to tell how your race affected your success in life up until that point. I thought it was the most demeaning thing that Y could imagine. Demeaning. I thought to myself, they could do the same about sexual orientation, they could do the same about religion, they could do the same about national origin. it would be demeaning no matter what. And the students actually verbalized how their race had either been a plus or a minus. They did. They did. And I thought it was so demeaning, it just confirmed all of my distaste </s><s>[INST] for this kind of approach. Let me ask you from the interviewer seat. So I get to do this podcast and I often have to think about giving a large platform and having a conversation with very controversial figures. And the level of controversy has been slowly increasing. What's the role of this medium to you? This medium of speech between two people and me speaking with a controversial figure, me or some other interviewer. What's the role of giving platform to controversial figures? Same members of the KKK or dictators, [/INST] people who are seen as evil. Well, we want to face the world with reality. And the reality is that there are some unpleasantness in the world, running from genocide right through to ordinary discrimination, to offensiveness. It's the real world as we know it exists. Are we afraid to say it? Do we want to make people think that we live in a world where those words are not used, where those animosities don't exist? </s>

<s>[INST] illiterate and [/INST] can't read that piece of paper, </s><s>[INST] right? What [/INST] if they don't know how to sign their name? </s><s>[INST] Right? So instead you have to have a [/INST] conversation, ask questions, have them ask questions, come </s><s>[INST] to a complete [/INST] understanding before you even know whether they understand what you're </s><s>[INST] asking, right? And then in that case, if someone's [/INST] illiterate, then </s><s>[INST] you have that conversation, [/INST] you just sit down and it takes </s><s>[INST] a long time sometimes, [/INST] but you have to do it. And </s><s>[INST] then if they still [/INST] want to participate and they give you their consent, </s><s>[INST] you know, they [/INST] can't sign a piece of paper. </s><s>[INST] Right? [/INST] So then you just do in </s><s>[INST] their native language, [/INST] right? Direct consent to camera in </s><s>[INST] their language [/INST] interesting. But also you're </s><s>[INST] speaking to the consent that's [/INST] just human </s><s>[INST] placing trust in you. You make a connection [/INST] like that's the most important </s><s>[INST] concern. I hate papers. I hate [/INST] papers and </s><s>[INST] lawyers because they. [/INST] Exactly for that </s><s>[INST] reason. Yeah. Okay, great. But [/INST] you should be </s><s>[INST] focusing on on [/INST] the human connection </s><s>[INST] that leads to the [/INST] trust to the like real </s><s>[INST] consent and consent day to day minute to minute because [/INST] that can change. </s><s>[INST] Absolutely. And it does change. [/INST] You mentioned </s><s>[INST] uh a woman captured or the this [/INST] I'm sure you </s><s>[INST] can't answer that. But I will force you. What are the top three documentaries of all time short or feature length, You know, this is not your opinion. [/INST] This is </s><s>[INST] objective truth. [/INST] Uh </s><s>[INST] Maybe Top one. What's What's The Greatest We Got? Um let's [/INST] see, March of the </s><s>[INST] Penguins, that's probably number one for me. [/INST] No, I'm just kidding. I don't know. I </s><s>[INST] I do seem to [/INST] the </s><s>[INST] metaphor of penguins huddling together in hard cold, [/INST] like </s><s>[INST] in the harsh conditions of nature. [/INST] That that's something </s><s>[INST] that's kind of beautiful. I don't love [/INST] all nature documentaries, but like </s><s>[INST] something about March of the penguins, I think [/INST] morgan Freeman </s><s>[INST] narrates it. So maybe everything just [/INST] and you documented </s><s>[INST] with morgan Freeman. [/INST] I'm a sucker for that </s><s>[INST] Warner, [/INST] Herzog Life and the </s><s>[INST] Tiger, the Simple people, I [/INST] love Grizzly Man, </s><s>[INST] I love [/INST] Grizzly Matthew, that's one of his best works, you know? Yes, I think </s><s>[INST] that's Joe Rogan's [/INST] favorite favorite </s><s>[INST] documentary. [/INST] It's </s><s>[INST] both comedy [/INST] and, and I mean it's tragicomedy, </s><s>[INST] tragicomedy. [/INST] Yeah. Is there something that stands out to you? I mean, I'm </s><s>[INST] joking about like best, something that was impactful to you. [/INST] Just to put it out </s><s>[INST] there. I don't think there's any [/INST] Anyway to say that there are objectively, you know, it's the best three </s><s>[INST] documents all the time. But for [/INST] me and you may find this </s><s>[INST] interesting given your background, [/INST] is that I </s><s>[INST] think [/INST] my top </s><s>[INST] three are all from the [/INST] eastern bloc actually, so </s><s>[INST] Aqua [/INST] rela by Khodorkovsky </s><s>[INST] victor. Costa [/INST] Ogonowski is one of my favorite and it's </s><s>[INST] a couple of years old [/INST] now, which is sort of a meditation on the place water has on our planet and in our </s><s>[INST] lives. Um [/INST] I think a woman captured that I mentioned, which was shot in Hungary. Both, both the future links. Yeah. Um, it is just brilliant and it I think has yet to find distribution here and you know, but it's a perfect example of of what they called, </s><s>[INST] you know, verity [/INST] or direct um non fiction filmmaking. A </s><s>[INST] european woman, This is the synopsis, [/INST] a european woman </s><s>[INST] has been kept by a family [/INST] As a domestic slave for 10 </s><s>[INST] years, drawing [/INST] courage from the filmmaker's presence. </s><s>[INST] She decides to escape [/INST] the unbearable </s><s>[INST] oppression and [/INST] become a free person, </s><s>[INST] wow. [/INST] So the filmmaker </s><s>[INST] as part of the story, part [/INST] of the story becomes, and it didn't start that way, but during the course of the story, the filmmaker under becomes comes to understand that this is actually modern day </s><s>[INST] slavery and [/INST] rather than just allow </s><s>[INST] it to be [/INST] actually, enables and assists this woman to free yourself from slavery and become a free woman. I wonder </s><s>[INST] it's Ariana small tangent before we get to number three. Like Icarus is interesting too. [/INST] How </s><s>[INST] often do you become part of the story [/INST] or the story </s><s>[INST] is different [/INST] because of </s><s>[INST] your presence? [/INST] Like, </s><s>[INST] like you, [/INST] you changed the </s><s>[INST] tide of history? [/INST] Yeah, well back just like </s><s>[INST] one person at a time that we [/INST] keep talking, you know, we could </s><s>[INST] keep coming [/INST] back to that theme on some level. So, </s><s>[INST] so [/INST] this could tie in interesting into one of my, one of my favorite films actually. So, um, the last two films that I would mention from my top four list would be the third eastern bloc. One would be a film called immortal </s><s>[INST] in 2000 [/INST] 19, which was shot in Russia by a Russian woman. Um, that sort of, you know, examines the place of the state in in shaping individuals to be vehicles for the state. I mean, that's my own synopsis, but that's 11 of my takeaways from the </s><s>[INST] brilliant 60 minute [/INST] doc or so. Um, </s><s>[INST] again, Russian [/INST] filmmaking, that is really </s><s>[INST] quite quite [/INST] good and powerful. The 4th 1 would be a Frederick Wiseman film ticket </s><s>[INST] follies, [/INST] um, which was filmed in the </s><s>[INST] US decades ago, [/INST] uh, inside </s><s>[INST] basically the [/INST] bowels of, of an insane asylum or mental health institution. And, </s><s>[INST] and I bring up [/INST] Wiseman because you know, he is really </s><s>[INST] the [/INST] godfather, so to speak, of </s><s>[INST] direct [/INST] cinema or cinema verite. And I went early in my </s><s>[INST] career, I really [/INST] believed in what he expressed as the place of the verite filmmakers, which is simply fly on the wall, which is only observational nature. Right? And, and I believe that that's how I should </s><s>[INST] be as a [/INST] nonfiction filmmaker, that I was there only to bear witness to observe and not to intervene in any way, shape or form. And, </s><s>[INST] and that [/INST] was the sort of foundation for how </s><s>[INST] I operate for many, [/INST] many years. </s><s>[INST] And then some things happened. [/INST] So one of those things that happened was I I filmed lifeboat and during the course of filming lifeboat, which, </s>

<s>[INST] So there's a nice feature of language that the number of words in a particular language is very large but finite and it's actually not that large in the grand scheme of things. I still got up because we take it for granted. So, first of all, the same asking you're talking about this very process of the blank removing words from a sentence and then having the knowledge of what word went there in the initial data set. That's the ground truth that your training on. And then you're asking the neural network to predict what goes there. That that's that's like a little trick. It's a really powerful trick. The question is how far that takes us. And the other question is, is there other tricks? Because to me it's very possible. There's other very fascinating tricks. I'll give you an example in um, in autonomous driving, there's a bunch of tricks they give you the self supervised signal back, for example, very similar to sentences, but not really, which is you have signals from humans driving the car because a lot of us drive cars to places. And so you can ask the neural network to predict what's going to happen the next two seconds for a safe navigation through the environment and the and the signal is comes from the fact that you also have knowledge of what happened in the next two seconds because you have video of the data. The question in autonomous driving as it is in language, can we learn how to drive autonomously based on that kind of self supervision? Probably the answer is no. The question is how good can we get? And the same with language, how good can we get? And are there other tricks like we get sometimes super excited by this trick that works really well. But I wonder why it's almost like mining for gold. I wonder how many signals there are in the data that could be leveraged that are like there is that uh, I just wanted to kind of linger on that because sometimes it's easy to think that maybe this masking process is self supervised learning. No, it's only one method. So there could be many, many other methods may be tricky methods may be interesting ways to leverage human competition in very interesting ways that might actually board on semi supervised learning. Something like that. Obviously the internet is generated by humans at the end of the day. So all that to say is what's your sense in this particular context of language? How far can that masking process take us. [/INST] So it has stood the test of time, right? I mean, so word to back the initial sort of NLP technique that was using this to now for example, like all the birds and all these big models that we get burned and roberta for example, all of them are still sort of based on the same principle of masking. It's taken us really far. I mean you can actually do things like these two sentences are similar or not, whether this particular sentence follows this other sentence in terms of logic. So entail mint, you can do a lot of these things with just this masking trick. So I'm not sure if I can predict how, how far it can take us because like when it first came out, when word was out, I don't think a lot of us would have imagined that this would actually help us do some kind of entitlement problems and really that well. And so just the fact that by just scaling up the amount of data that were training on and like using better and more powerful neural network architecture has taken us from that to this is destroying you. How may be poor predictors we are like as humans, how poor we are at predicting how successful particular technique is going to be. So I think I can say something now, but like 10 years from now, I look completely stupid basically predicting this </s><s>[INST] in language domain, is there something in your work that you find useful and insightful and and uh transferable to computer vision but also just I don't know, beautiful and profound that I think carries through to the vision domain. [/INST] I mean the idea of masking has been very powerful, it has been used in vision as well for predicting like you say the next sort if you have and sort of frames the new, predict what's going to happen in the next frame. So that's been very powerful in terms of modeling, like in just terms in terms of architecture, I think you would have asked about transformers that has really become like it has become super exciting for computer vision now in the past year and a half it's become really powerful, </s><s>[INST] what's the transformer? [/INST] The core part of the transformer is something called the self attention models that came out of google. And the idea basically is that if you have any elements, what you're creating is a way for all of these and elements to talk to each other. So the idea basically is that you are paying attention each element is paying attention to each of the other element. And basically by doing this, it's really trying to figure out you're basically getting a much better view of the data. So for example, if you have a sentence of like four words, the point is if you get a representation or a feature for this entire sentence, it's constructed in a way such that each word has paid attention to everything else. Now, the reason it's like different from say what you would do in a continent is basically that in the continent you would only pay attention to a local window. So each word would only pay attention to its next neighbor or like one neighbor after that. And the same thing goes for images and images, you will basically pay attention to pixels in a three cross three or a seven across seven neighborhood. And that's it. Whereas with the transformer, the that self attention mainly the sort of idea is that each element needs to pay attention to each other element. </s>

<s>[INST] you're saying there's a chance [/INST] I cannot, I cannot, as a scientist honestly say that I can rule out that it's alien space junk. However, I I see the kind of alien explanation as following this. The Sagan's extraordinary claims require extraordinary evidence. If you are going to actually claim that something is aliens, um, you need to carefully evaluate one needs to carefully evaluate the other options and see whether it could just be something that we know exists that makes sense in the case of um um uh um there are explanations that fit well within our understanding of how things work. So there are a couple, there are two hypotheses for what it could be made of. They're both both basically just ice shards. In one case it's a nitrogen ice shard that came off of something like Pluto in another solar system, that Pluto got hit with something and broke up into pieces and one of those pieces came through our solar system. And the other scenario, it's a bit of a failed solar system. So our solar system formed out of a collapsing molecular cloud. Sometimes those molecular clouds are not massive enough and they sort of collapse into bits, but they don't actually form a solar system, but you end up with these kind of chunks of hydrogen, it's apparently, and so one of those chunks of hydrogen is could have got ejected and pass through our solar system. So both cases explain these properties in about the same way. So those ISIS will sublimate once they've passed the sun. And so as they're moving away from the sun, you have the hydrogen or nitrogen ice sublimating off the sunward part of it. And so that is responsible for the acceleration, the shape also because you have all this ice sublimating off the surface. Uh if you take something, the analogy that um works pretty well here is for a bar of soap. Your bar of soap starts out sort of close to spherical, at least from a physicist perspective. Um, and as you use it over time, you eventually end up with this long thin shard because it's been just by sort of weathering as we would call it. Um, and so in the same way, if you just sublimate material off of one of these ice shards, it ends up long and thin and it ends up accelerating out of the solar system. And so given that these properties can be reasonably well explained that way. Um you know, we should be extremely skeptical about attributing things to aliens. </s><s>[INST] The reason I like to think that it's aliens is because it puts a lot of priority and it's not being lazy and we need to catch this thing next time it comes around. I like the idea that there's objects not like it's almost saddens me, they come out of the darkness really fast and just fly by and go and leave. It just seems like a wasted opportunity not to study them. It's like a, it's the easiest way to do space travel outside of the solar system. It's having the things come to us, right? [/INST] Like that way of putting it. </s><s>[INST] And it would be nice to just land on it, like, and first of all, really importantly, detected early and then land on it, like with a really nice like spacecraft and study the hell out of it and you know, because yeah, it's uh, if there's a chance it's aliens, alien life, it just feels like such a cheap way inexpensive way to get information about alien life or something interesting that's out there. And I'm not sure if a nice charred from another planetary system will be interesting. But it very well could be, it could be totally new sets of materials. It could be tell us about composition of planets We don't quite understand. It's just nice one, especially in the case of a mom. Well, I guess it was pretty close to earth, a little bit nice to, uh, to, uh, you know, let's say, don't go there. They come to us. I don't know. That's what makes me, uh, that's what makes me quite as sad. It's a missed opportunity. [/INST] Well, yeah. And whether whether you think it's aliens or not, it's, it's a missed opportunity. But you know, we weren't prepared and we will be prepared for the next ones. And um, as, so there's been a movement and astronomy more towards what's called time domain astronomy. So kind of monitoring the whole sky all the time at all wavelengths. That's kind of the goal. And so we expect to detect many more of these in the future even though these were the first to, we saw our potential to detect them is only increasing with time. And so there will be more opportunities. And based on these two, we now can actually sit and think about what we'll do when the next one shows up. I </s>

<s>[INST] Yeah. And the people that had like Marin or Joe that have podcasts is interesting. It's an interesting pairing because you get to know like everything about them, but then they're also comedians. And I've gotten, I've gone to Joe's club a lot. Listen, Joe and just that whole group of comics do comedy and go to the same set over and over and over to see how it changes. It's really cool. [/INST] It's the coolest thing when I first started to watch someone like a tell was really brilliant at it because you'd watch him tinker with a set. Yeah. And he'd have an idea like hitting someone over the head with a hammer from behind. And then he'd work it nine different ways, you know, and you'd be like, whoa. So the hitting hammer in the head is the thing that he's working on. </s><s>[INST] I hope Eddie Murphy comes back. He's one of the greats. [/INST] Chris Rock. Chris Rock's fucking bring the pain is like the reason I got into comedy. Yeah. </s><s>[INST] Do you have advice for young folks? You seem like a stellar example of successful human being. Or more seriously, a very kind of nonlinear life. Do you have advice for young people in high school and college? How to have a good life they can be proud of? [/INST] Don't worry too much about what you do when you get older. But when you do start worrying, find the thing you love and it'll never feel like work. To fucking, I can't imagine what it must feel like to be a lawyer and have to read papers or whatever they do all day and know that that's my day. I mean, it must feel like what school felt like for me. If you find that thing you love to do, You will work endlessly, effortlessly, and hardest fucking shit every day, and you'll love every day of your life. </s><s>[INST] Fine. Would you love and let it kill you? Bacowski said that. [/INST] Then that's the fucking thing. Cause that's what I'm doing. I'm letting it fucking take. I'm, I'm fucking, I'm, I'm on that fucking bullet train to fucking nowhere on this fucking comedy journey. I love it. I love it. </s><s>[INST] So it's like the Hunter S. Thompson thing, however you put it, basically you're not supposed to end up in a well-preserved box. You slide it in sideways, smoke, just beat up, just a giant mess. [/INST] I love those guys that can really live that life that are like, yeah, man, I'm breaking it. I'm breaking it down. Like a guy like Tony Hawk or Matt Hoffman, who's like, yeah, if I don't fucking break the fuck out of this thing before, then I'm not doing it right. </s><s>[INST] And then again, there's also Churchill who tried to break the thing and he couldn't. Lived into his 90s, a bad motherfucker. Just a bad motherfucker. So I guess the only hope we can have for Burr-Crisher is that you're gonna be the Winston Churchill of comedy. [/INST] My life has lived perfectly. If I'm 95 years old and all my friends are dead. Yeah. And they're like, can you believe that wolf got Rogan? Yeah. Can you believe, Segura, 600 pounds, and they had to carry him out in a crane out of that house. Can you believe that it's just Bert, Chrysler, and Joey Diaz left? </s><s>[INST] Just standing there in October. So, in October, just the two of you left. Just laughing. [/INST] In October, it's just I'm 95 at the Mark Twain Awards, and they're like, Bert, Chrysler, still fucking here. Who saw that coming? </s><s>[INST] I hope so. Bert, I'm a huge fan of yours. It meant so much to me when you said that you knew who I was like we were talking about. It's just, it's so cool. It's so cool. Thank you for putting so much joy and love out there in the world. I'm a huge fan and thank you for the love you give me. [/INST] Thank you, man. I am a huge fan of yours. You keep doing you. I'll keep doing me. And then let's see if we can meet in the middle sometime. Have a cold beer in the afternoon. </s><s>[INST] Love you, brother. [/INST] Love you. Thanks for listening to this conversation with Bert Kreischer. To support this podcast, please check out our sponsors in the description. And now let me leave you with some words from Hunter S. Thompson. Life should not be a journey to the grave with the intention of arriving safely in a pretty and well-preserved body, but rather to skid in broadside in a cloud of smoke, thoroughly used up, totally worn out and loudly proclaiming, wow, what a ride. Thank you for listening. I hope to see you next time. </s>

<s>[INST] But the really cool thing is it has to do with the infinite fund that you're referring to, which is our brain seems to be very limited. And like you said, computation is [/INST] very plastic. Very plastic. And so it's a it's a interesting combination. </s><s>[INST] The the interesting open question is the limits of that in your plasticity. Like how how flexible is that thing? Because we don't we haven't really tested it. [/INST] We know about that experiments where they put like a pressure pad on somebody's head and had a visual transducer pressurize it. And somebody slowly learned to see. It's like it's </s><s>[INST] especially at a young age if you throw a lot at it. Like what what can it uh can it completely? So can you like arbitrarily expanded with computing power. So connected to the internet directly [/INST] somehow. Yes, probably. Yes. </s><s>[INST] So the problem with Biology and ethics is like there's a mess. They're like us. Humans are perhaps unwilling to take risks in uh, in two directions that are full of uncertainty. [/INST] So 90% of the population is unwilling to take risks. The other 10% is rushing into the risks unaided by any infrastructure whatsoever. And you know, that that's where all the fun happens in society has been huge transformations in the last, you know, a couple of 1000 years. </s><s>[INST] Yeah, it's funny. I mean, I got a chance to interact with this Matthew johnson from johns Hopkins, he's doing this large scale study of psychedelics. It's becoming more and more. I've gotten a chance to interact with that community of scientists working on psychedelics, but because of that, that opened the door to me to all these uh, what do they call psycho notes, the people who, like you said, the 10% who like, I don't care. I don't know if there's a science behind this. I'm taking this spaceship. Uh, if I'm being the first on mars, I'll be uh, you know, you know, psychedelics interesting in the sense that in another dimension, uh, like you said, it's a way to explore the limits of the human mind. Like what is this thing capable of doing? Because you kind of like when you dream, you detach it. I don't know exactly in your science of it, but you detach your like reality from what your mind, the images, your mind is able to conjure up in your mind goes into weird places. Like entities appear somehow Freudian type of like trauma is probably connected in there somehow. But you start to have like these weird vivid worlds that like, [/INST] so do you actively dream you? Why not? I have like 66 hours of dreams and I it's like a really useful time. </s><s>[INST] I know I I haven't, I don't for some reason I just knock out and uh I have sometimes like anxiety inducing kind of like very pragmatic like nightmare type of dreams but not nothing fun, nothing, nothing fun, nothing fun. I I try I unfortunately have mostly have fun in the waking world which is very limited in the amount of fun you can have. [/INST] It's not that limited either. Yeah, that's what we'll have to talk uh </s><s>[INST] new instructions. Uh [/INST] Yeah, there's like a manual for that. You might want to. </s><s>[INST] I looked it up, I'll ask you on what would you dream [/INST] you know, years ago and I read about, you know like you know a book about how to have, you know become aware of your dreams. I worked on it for a while. Like there's this trick about, you know, imagine you can see your hands and look out and and I got somewhat good at it like but my mostly when I'm thinking about things are working on problems I I prepped myself before I go to sleep. It's like I pull into my find all the things I want to work on or think about and then that let's say greatly improves the chances that I'll work on that while I'm sleeping. And then, and then I also, you know, basically asked to remember it and I often remember very detailed </s><s>[INST] within the dream or outside the [/INST] dream well to bring it up in my dreaming and then remember when I wake up, it's just, it's more of a meditative practice you say, you know, to prepare yourself to do that. Like if you go to the sleep, still gnashing your teeth about some random things that happened that you're not that really interested in, you'll dream about it. </s><s>[INST] That's really interesting maybe. [/INST] But you can direct your dreams somewhat by prepping, </s><s>[INST] you know, I'm gonna have to try that. It's really interesting. Like the most important, the interesting, not like uh what did this guy send an email kind of like stupid worry stuff but like fundamental problems. You're actually concerned [/INST] about interesting things you're worried about books you're reading or you know, some great conversation you had or some some adventure you want to have. Like there's there's a lot of space there and and it seems to work that, you know, my percentage of interesting dreams and memories went up. </s><s>[INST] Is there? Uh is that the source of uh if you were able to deconstruct like where some of your best ideas came from, Is there a process that's at the core of that? Like so some people you know walk and think some people like in the shower the best ideas hit him if you talk about like newton apple hitting him on the head [/INST] now I I found out a long time ago I'm I processing so much slowly. So like in college I had friends who could study at the last minute get in the next day, I can't do that at all. So I always front loaded all the work like I do all the problems early you know for finals like the last three days I wouldn't look at a book because I want you know because like a new fact day before finals may screw up my understanding of what I thought I knew. So my my my goal was to always get it in and give it time to silk and I used to you know I remember we were doing like three D. Calculus, I would have these amazing dreams of three D surfaces for normal, you know calculating the gradient and just like all come up so it was really fun like very visual and uh and if I got cycles of that that was useful. Um And the other is don't over filter your ideas like I like that process of brainstorming where lots of ideas going to happen. I like people who have lots of ideas but then then yeah I'll let them sit and let it breathe a little bit and then reduce it to practice. Like at some point you really have to does it really work like it was this real or not right? But but you have to do both. There's great attention. They're like how do you be both open and you know, precise. </s>

<s>[INST] to inspire millions to do something. The books you like are all the books I love. So, I have to mention this, you mentioned briefly on the with Jordan's uh Siddhartha by Hermann Hesse is uh is an incredible book there. I mean, I don't I don't know exactly what I want to ask here, but there's some, I think the book kind of through telling a story reveals that life is suffering and yet there's beauty in it. The beauty in every moment that that uses a kind of a river painting metaphor. Is there is there um is there something that you could say speak to like how that book impacted your life and the way you live life maybe the way you see life whether it's on the life is suffering side or that life is beautiful side? [/INST] I mean, he goes to the entire journey, right? He goes in the state like I'm so enlightened that I cannot deal with the people there in love and quite about it right there like that? So like primitive. Once he has his own son he actually being attached? He actually cares. It actually really does hold thing, right. That's the thing that he used to think not once his son comes find him, he looks at life differently. I think that's the thing. I did have that kind of journey where or nothing matters, right? So bitter, so, so like, so cynical and after I met so many incredible people, I was talking about that person who told him he was gay, he told me I love you. And I was like, why do you love me in the past? People when they wanted me because they want to rape me. Everybody wanted something from me. That's why they wanted me and I never understood you can love somebody unconditionally. And this gay guy, the last one was one of sleep with me, right? And he loves me. And I think I had a blessing after my journey meeting people who loved me unconditionally because I was just being a human. And I think that's what it is now for me that like him, I live for love now. I live for love any kinds of love, Love for knowledge. I like I read so many books because I love books right? I love what I do. I love my people. I love humanity. You know, even it sometimes annoys me. I love myself </s><s>[INST] and that's beautiful to the annoying parts are beautiful too. What do you let me ask the ridiculous question. What do you think is the meaning of this whole thing of what's the meaning of life? [/INST] Yeah. I think at this point I stopped question why I'm here, right? Like it doesn't matter. Someone put the atom, there are a big thing. I'm here. That's truth. Right? I'm going to accept that fully. So what? Instead of me keep asking the impossible question, what I'm here? I'm gonna let you do that. Let's do that. Right? You guys go out into space and look for the evidence I'm conducting </s><s>[INST] you Except that you're here and you're just going to enjoy your here for love. As you said, [/INST] That's the thing. I think I'm here for the process of pursuing something bigger than me. Process of doing something. It's not like more, It's not a virtue signaling thing. It just makes me happy that I fight for something bigger like that. Me, right? So how boring is that? Every day you get up? Oh my God, I'm gonna buy myself this. I'm going to get this for myself is so boring, isn't it? So in a way, I think that's what it is. I am grateful that I'm in a state. I don't have to fly for myself anymore. But more than people have to do that. And that's sometimes more than enough they have to do and I salute them. They are doing? Fighting, saving themselves every day. But now I'm I'm not there, I'm very blessed. That's why I'm very grateful. </s><s>[INST] So fighting for something much bigger than you. But do you still believe that you can change the world that you can be a thing that at least in part helps North Korea or even broader helps alleviate some suffering in the world. [/INST] So that's the thing. I was reading this book for the by randomness, right? I was like, they were here like, oh my God, you're so courageous, you're amazing. I'm like no I'm not, I'm horrible. Right? I know myself. You don't want to tell me that. It's a random why I end up here. Like why did I pick up in Greece so quickly? Why do I love books? Right. I don't know why it's random. </s><s>[INST] Why just enjoy [/INST] it. Yeah, it's random. I think, I don't know how the history will remember me. I think the only thing I have to disappoint to make sure that people after consulting a lot of security teams like nah, North Korea became a lot smarter. Like you said, they may get more disguised as a suicide and I call accent. So when I die, they don't even know I got scared and I think that's a higher chance. So I think that's the thing like people are suffering, take it or not is your choice and at least it's my responsibility for them to know what's going on. I think if you did not know and didn't do anything. You're not even beautiful thing. But once you know, then you're not doing it. Then you saw this like not right? So that's what I'm doing. Like I want people to know and then what they're gonna do is not my, my problem afterwards. Right? So my role is very small in that regard. And I just hope that or humanize north Koreans for the first time because we have been so dehumanized, right? Like we are like looking like roberts, if you look at us marching and quite like when you later dies almost seems like we don't even have the same emotions. People cannot connect us in the same level. Okay. And I think that's something is uh that's something media have done it to us </s>

<s>[INST] Then moved to Hong Kong in 2011. Because he's a date neater, so actually, I mean, he's a- [/INST] Yeah, that's a good point. Mostly because I met a Chinese girl who I fell in love with and we got married. She's actually not from Hong Kong. She's from mainland China, but we converged together in Hong Kong. </s><s>[INST] Still married now, have a two-year-old baby, huh? So I went to Hong Kong to see about a girl, I guess. [/INST] Yeah, pretty much, yeah. And on the other hand, I started doing some cool research there with the Geno U and Hong Kong Polytechnic University. I got involved with a project called IDEA using machine learning for stock and futures prediction, which was quite interesting. And I also got to know something about the consumer electronics and hardware manufacturer ecosystem in Shenzhen across the border, which is like the only place in the world that makes sense to make complex consumer electronics at large scale and low cost. It's just, it's astounding the hardware ecosystem that you have in South China, like US people here cannot imagine what it's like. So yeah, David was starting to explore that also. I invited him to Hong Kong to give a talk at Hong Kong PolyU. And I introduced him in Hong Kong to some investors who were interested in his robots. And he didn't have Sophia then. He had a robot of Philip K. Dick, our favorite science fiction writer. He had a robot Einstein. He had some little toy robots that looked like his son, Zeno. So through the investors I connected him to, he managed to get some funding to basically port Hanson Robotics to Hong Kong. And when he first moved to Hong Kong, I was working on AGI research and also on this machine learning trading project. So I didn't get that tightly involved with Hanson Robotics. But as I hung out with David more and more, as we were both there in the same place, I started to think about what you could do to make his robots smarter than they were. And so we started working together. And for a few years, I was chief scientist and head of software at Hanson Robotics. Then when I got deeply into the blockchain side of things, I stepped back from that and co-founded SingularityNet. David Hanson was also one of the co-founders of SingularityNet. So part of our goal there had been to make the blockchain-based CloudMind platform for Sofia and the other... </s><s>[INST] Sofia will be just one of the robots in SingularityNet. [/INST] Yeah, yeah, exactly. Sofia, many copies of the Sofia robot would be among the user interfaces to the globally distributed SingularityNet CloudMind. And I mean, David and I talked about that </s><s>[INST] for quite a while before co-founding SingularityNet. By the way, in his vision, in your vision, was Sofia tightly coupled to a particular AI system? Or was the idea that you can plug... You could just keep plugging in different AI systems [/INST] within the head of it. You could just then head of it. David's view was always that Sofia would be a platform, much like, say, the Pepper robot is a platform from SoftBank. It should be a platform with a set of nicely designed APIs that anyone can use to experiment with their different AI algorithms on that platform. And SingularityNet, of course, fits right into that, right? Because SingularityNet, it's an API marketplace. So anyone can put their AI on there. OpenCog is a little bit different. I mean, David likes it. But I'd say it's my thing. It's not his. David has a little more passion for biologically-based approaches to AI than I do, which makes sense. I mean, he's really into human physiology and biology. He's a character sculptor, right? Yeah. So yeah, he's interested in... But he also works a lot with rule-based and logic-based AI systems, too. So yeah, he's interested in not just Sofia, but all the Henson robots as a powerful software and Henson robots as a powerful social and emotional robotics platform. And what I saw in Sofia was a way to get AI algorithms out there in front of a whole lot of different people in an emotionally compelling way. And part of my thought was really kind of abstract, connected to AGI ethics. And many people are concerned AGI is going to enslave everybody or turn everybody into computronium to make extra hard drives for their cognitive engine or whatever. And emotionally, I'm not driven to that sort of paranoia. I'm really just an optimist by nature. But intellectually, I have to assign a non-zero probability to those sorts of nasty outcomes. Because if you're making something 10 times as smart as you, how can you know what it's going to do? There's an irreducible uncertainty there, just as my dog can't predict what I'm going to do tomorrow. So it seemed to me that based on our current state of knowledge and the best way to bias the AGIs we create toward benevolence would be to infuse them with love and compassion the way that we do our own children. And if you want to interact with AIs in the context of doing compassionate, loving and beneficial things, and in that way as your children will learn by doing compassionate, beneficial, loving things alongside you in that way the AI will learn in practice what it means to be compassionate, beneficial and loving, it will get a sort of ingrained, intuitive sense of this which it can then abstract in its own way as it gets more and more intelligent. Now David saw this the same way. That's why he came up with the name Sophia, which means, which means wisdom. So it seemed to me making these like beautiful, loving robots to be rolled out for beneficial applications would be the perfect way to roll out early stage AGI systems so they can learn from people and not just learn factual knowledge, but learn human values and ethics from people while being their, you know, their home service robots, their education assistants, their nursing robots. So that was the grand vision though. If you've ever worked with robots, the reality is quite different, right? Like the first principle is the robot is always broken. I mean, I've worked with robots in the 90s a bunch when you had to solder them together yourself. And I'd put neural nets during reinforcement learning on like overturned solid bowl type robots. And in the 90s when I was a professor, things of course advanced a lot, but, but the principal stuff, the robot's always broken. So yeah. Yeah. So faced with the reality of making Sophia do stuff, many of my Robo AGI aspirations were temporarily cast aside. And I mean, there's just a practical problem of making this robot interact in a meaningful way. Because like, you know, you put nice computer vision on there, but there's always glare. And then, or you have a dialogue system, but at the time I was there, like no speech to text algorithm could deal with Hong Kong, Hong Kong, East people's English accents. So the, the speech to text was always bad. So the robot always sounded stupid because it wasn't getting the right text. </s>

<s>[INST] Secession? Yeah. See I don't yeah, I don't it's hard for me to disagree. It's starting to disagree because but at the same time, secession. Um I'm a romantic at heart. You want a divorce breaks my [/INST] heart. Cool, But do you want to live in a country? Yeah, but do you want to live in a country where joe Rogan is regarded as an example of someone who's spreading white supremacy? I don't </s><s>[INST] Well, but see, I feel like that's not the country we live in, that's just [/INST] york times did it? The cathedral does it on a </s><s>[INST] regular basis, but the cathedral is okay, the cathedral, I guess you can maybe define the cathedral, but it's it's like the centralized institutions that have like a story that they're trying to sell [/INST] this is more bucks concept. But yeah, they basically are set the limits of permissible discourse and create a narrative for the population to follow. </s><s>[INST] But to me that's a minority of people, [/INST] minorities, always controlling everything in any country. The vast majority, the masses have no </s><s>[INST] thought, but minorities can be overthrown in the circulation of elites. Yeah, the way the known and that's what what progress looks like is ridiculous. People take power and then uh they get annoying and new, ridiculous people that are a little bit better overthrow the previous. [/INST] No, I think progress happens despite the people who are in power, not because of them. </s><s>[INST] Right. And so why this obsession? Uh, so is it always about overthrowing the powerful? Is that how progress happens? [/INST] No, I think progress happens despite the powerful, the powerful are going to do what's in their power to maintain their power and they're gonna fight innovation because it's a threat to their control. </s><s>[INST] There's always going to be the new york times of the world, right? There's always gonna be those, [/INST] those that have them </s><s>[INST] have their own country. So it's two countries, one has joe Rogan, the other one is the new york times. [/INST] That's basically what's happening right now. It's just geographically doesn't map out very well, but culturally, yes, </s><s>[INST] but that's just cultural stuff. Like there's a layer of public discourse, Okay, I don't mean like, that's what we're operating under now, but there's actual, like, progress being made, like roads being built, hospitals being run all those kinds of things, like, different innovations that seems like secession is counterproductive to that, [/INST] right? Because one country would have all the roads and the other would have all the hospitals. That's </s><s>[INST] a great point. No, that's not. That's not the point. I'm trying to make it just like, it just feels like the division that we're experiencing in the space of ideas could be constructive and productive for for building better roads and better hospitals as opposed to like using that division to separate the countries, they're all going to have to solve the same problems. It feels like [/INST] Sure, but they can solve them differently and compete that way for example. Yeah, we're seeing that right now. Different countries have different mass mandates and things like this </s><s>[INST] and the competition within the same structure with the same founding documents and same institutions is not effective. You think as effective as separating [/INST] it is effective. But there is a certain point which I think we have long passed where there is not a consensus governing consensus ideologically </s><s>[INST] or culturally. Let me ask you a fun question. Okay, knock knock. Who's there mars God of war, the other one? The planet. Yeah. Okay, so there is a kind of captivating notion that we might, I'm excited by it. The human beings stepping foot on mars that to me is uh, it's like one of those things that feels like it's why do we want to accept the engaged in space exploration? But I'm a bit with the law Mosque on this, which is um, it's obvious that eventually if human species is to survive, it's going to have to innovate in ways that includes the space. Like there's a lot of things were not able to predict yet that if we push ourselves to the limits of space, like new ideas will come. There will be obvious 100 years from now and that we're not even imagining that and colonizing mars that idea that seems ridiculous, exceptionally difficult, impossibly expensive is something that is actually going to be seen as obvious in retrospect that we should engage in. Okay, that's just to contextualize things. The fun idea and experiment from a philosophical political sense is what kind of government, How do you orchestrate a government when you go to mars, like we don't get too many chances like this, but how do you build new systems? Not in place of old ones, but in a place with no system previous have existed, [/INST] I think organically. I hate that word, but that's the correct word. Um, you would have to figure out. I mean that's how America was built. You had was a Jamestown colony and they tried to communism here and it completely failed. Then they went to a more free market system with the second wave of colonists. It's my understanding um, from mars, I mean, it depends on the population who the population was, the number of people. Um, I, I don't know, these are all kind of hypotheticals that don't really have any good insight in uh, whatsoever. I'm not at a space person. I hate astronomy, like I hate it. </s><s>[INST] So a lot of people look up to the stars and they're filled with awe and wonder about the mystery of the universe and you, you look up to the stars and you feel what [/INST] I'm not looking up, I'm looking at the earth. If you, if you look at what's, I'd much rather given a choice between mars and the deep sea? I'd much rather spend a week at the deep sea and all the life forms that are down there because there are literal aliens. There's like things that are not literal but their unimaginable to us. Uh Some of the things down there. </s>

<s>[INST] what's that useful for? Just [/INST] one way that you can encode information in quantum states of light is in the number of photons you can have what are called number states and a number state will have a well defined number of photons and maybe the output of your quantum computation encodes it's information in the number of photons that are generated. So if you have a detector that is sensitive to that, it's extremely useful. </s><s>[INST] Can you achieve uh like a clock with photons or is that not important? Is there a synchronicity here [/INST] in general? It can be important. Uh Clock distribution is a big challenge in especially large computational systems. And so yes, optical clocks, optical clock distribution is a is a very powerful technology. I don't know the state of that field right now, but I imagine that if you're trying to distribute oclock across any appreciable size computational system, you you want to use light? </s><s>[INST] Yeah, I wonder how these giant systems work. Especially like uh supercomputers, do they need to do clock distribution or are they doing more at hawk parallel like concurrent programming, Like there's some kind of locking mechanisms or something. That's a fascinating question. But the let's zoom in at this very particular question of uh computation on a processor and communication between processors. So what does this system look like that you're envisioning one of the places you're envisioning it is in the paper on Opto electronic intelligence. So what are we talking about? How are you talking about something that starts to look a lot like the human brain or does it still look a lot like a computer? What are the size of this thing? Is it go inside a smartphone or as you said, does it go inside? It's something that's more like a house like uh what should we be imagining? What are you thinking about when you're thinking about these fundamental systems? [/INST] Let me introduce the word neuro more fick, there's this concept of your amorphous computing where what that broadly refers to is um computing based on the information processing principles of the brain. And as digital computing seems to be pushing towards some fundamental performance limits. People are considering architectural advances, drawing inspiration from the brain, more distributed parallel network kind of architecture and stuff. And so there's this continuum of neural Norfolk from things that are pretty similar to digital computers, but maybe there are more cores and the way they send messages is a little bit more like the way brain neurons and spikes. But for the most part, it's still digital electronics. And then, you know, you have some things in between where maybe you're you're using transistors, but now you're starting to use them instead of in a digital way, in an analog way. And so you're trying to get those circuits to behave more like neurons. And then that's a little bit quite, quite a bit more on the neural, more fix side of things. You're trying to get your circuits, although they're still based on silicon, you're trying to get them to perform operations that are highly analogous to the operations in the brain. That's where a great deal of work is in your amorphous computing. People like Jacomo into very and good Kahlenberg, jennifer Hassler, countless others. It's a rich and exciting field Going back to carver meet in the late 1980s and then all the way on the other extreme of the continuum is where you say, I'll give up anything related to transistors or semiconductors, anything like that. I'm not not starting with the assumption that I'm going to use any kind of conventional computing hardware. And instead, what I want to do is try and understand what makes the brain powerful at the kind of information processing it does. And I want to think from first principles about what hardware is best going to enable us to capture those information processing principles in an artificial system. And that's where I live. That's where that's where I'm doing my exploration these days. </s><s>[INST] So what are the first principles of brain like competition, communication. [/INST] Right. Yeah. This is this is so important and I'm glad we booked 14 hours for this because </s><s>[INST] I only have 13. I'm sorry. [/INST] Okay, so the brain is notoriously complicated and I think that's a an important part of why it why it can do what it does. But okay, let me let me try to break it down. Starting with the devices, neurons, as I as I said before, their sophisticated devices in and of themselves and synapses are too they they can change their state based on the activity so they adapt over time. That's crucial to the way the brain works. They don't just adapt on one time scale. They can adapt on myriad timescales from the spacing between pulses, the spacing between spikes that come from neurons all the way to the age of the organism. Um Also relevant perhaps I think the most important thing that's guided my thinking is the network structure of the brain so </s><s>[INST] which can also be adjusted [/INST] different. Absolutely, yeah. So you're making new, you're changing the strength of contacts, You're changing the spatial distribution of them, although spatial distribution doesn't change that much once you're a mature organism. But that network structure is is really crucial. So let me dwell on that for a second. Um You can't talk about the brain without emphasizing that most of the neurons in the neocortex or the prefrontal cortex, the part of the brain that we think is most responsible for high level reasoning and things like that. Those neurons make thousands of connections. So you have this network that is highly interconnected and I think it's safe to say that one of the primary reasons that they make so many different connections is that allows information to be communicated very rapidly from any spot in the network to any other spot in the network. So that's a that's a sort of spatial aspect of it. You can quantify this uh in terms of concepts that are related to fractals and scale invariants, which I think is a very beautiful concept. So what I mean by that is kind of no matter what spatial scale you're looking at in the brain within certain bounds, you see the same general statistical patterns. So if I draw a box around some region of my cortex, most of the connections that those neurons within that box make are going to be within the box to each other in their local neighborhood. And that's sort of called clustering loosely speaking, but a non negligible fraction is gonna go outside of that box. And then if I draw a bigger box, the pattern is going to be exactly the same. So you have this scale invariance and you also have a non vanishing probability of a neuron making connection very far away. So suppose you you want to plot the probability of a neuron making a connection as a function of distance. If that were an exponential function, it could go either the minus radius over some characteristic radius and it would it would drop off up to some certain radius. The probability would be reasonable close to one and then beyond that characteristic length R. R zero. It would it would drop off sharply. And so that would mean that the neurons in your brain are really localized and that's not what we observe. And instead what you see is that the probability of making a longer distance connection, it does drop off but it drops off as a power law. So the probability that you're going to have a connection at some radius argos as our to the minus some power. And that's more, that's what we see with With forces in nature, like the electromagnetic force between two particles or gravity Goes as one over the radius squared. </s>

<s>[INST] You don't think of string theory as an original idea. [/INST] Oh, I mean, it was original to Venustiano probably is older than the baby boomers and there are people who are younger than the baby boomers who are still doing string theory. And I'm not saying that nothing discovered within the large strength, theoretic complex is wrong. Quite the contrary. A lot of brilliant mathematics and a lot of the structure of physics was elucidated by string theorists. What do I think of the delivery, herbal nature of this product that will not ship called string theory. I think that it is largely an affirmative action program for highly mathematically and geometrically talented baby boomer. Physics physicists so that they can say that they're working on something within the constraints of what they will say is quantum gravity. Now there are other schemes, you know, there's like a symptomatic safety. There are other things that you could imagine doing. I don't think much of any of the major programs but to have inflicted this level of loyalty through a shibboleth. Well, surely you don't question X while I question almost everything in the string program and that's why I got out of physics when you called me a physicist. It was a great honor. But the reason I didn't become a physicist wasn't that I fell in love with mathematics. As I said, Wow. In 1984, I saw the field going mad and I saw that mathematics which has all sorts of problems, was not going insane. And so instead of studying things within physics, I thought it was much safer to study the same objects within mathematics. There's a huge price to pay for that. You lose physical intuition. But the point is that it wasn't a north korean reeducation camp either. </s><s>[INST] Are you hopeful about cracking open the Einstein unified theory in a way that has been really, really uh understanding whether just uh uniting everything together with quantum theory and so [/INST] on. I mean, I'm trying to play this role myself to do it to the extent of handing it over to the more responsible, more professional, more competent community. Um so I think that they're wrong about a great number of their belief structures, but I do believe, I mean, I have a really profound love hate relationship with this group of people. </s><s>[INST] I think the physics side, oh yeah, because the mathematicians actually seem to be much more open minded and [/INST] uh well they are in there are there are open minded about anything that looks like great math. Right, Right. They'll study something that isn't very important physics, but if it's beautiful mathematics then they'll have, they have great intuition about these things as good as the mathematicians are. And I might even intellectually at some horsepower level give them the edge. The theoretical theoretical physics community is bar none. The most profound intellectual community that we have ever created. It is the number one. There is nobody in second place as far as I'm concerned. Look in their spare time and the spare time, they invented molecular biology. </s><s>[INST] What was the origin of molecular biology? You're saying something like [/INST] Francis crick. I mean, a lot of, a lot of the early molecular biologists, physicists. Yeah, I mean, you know, Schrodinger wrote, what is life? And that was highly inspirational? I mean, you have to appreciate that there is no community, like the basic research community in theoretical physics and it's not something I'm highly critical of these guys I think that they would just wasted the decades of time with um a near religious devotion to their misconception. Ization of where the problems were in physics. But this has been the greatest intellectual collapse ever witnessed within academics. </s><s>[INST] You see it as a collapse or just a lull. [/INST] Oh I'm terrified that we're about to lose the vitality. We can't afford to pay these people um we can't afford to give them an accelerator just to play with in case they find something at the next energy level. These people created our economy. They gave us the rad lab and radar. They gave us two atomic devices to end World War Two. They created the semiconductor and the transistor to power our economy through moore's law as a positive externality of particle accelerators. That created the World Wide Web. And we have the insolence to say why should we fund you with our taxpayer dollars? No. The question is, are you enjoying your physics dollars? </s><s>[INST] Uh huh. Right. [/INST] These guys signed the world's worst licensing agreement. And if if they simply charged for every time you used a transistor or a U. R. L. Or enjoyed the peace that they have provided um during this period of time through the terrible weapons that they developed uh or your communications devices, all of the things that power our economy I really think came out of physics even to the extent the chemistry came out of physics and molecular biology came out of physics. So, first of all, you have to know that I'm very critical of this community. Second of all, it is our most important community. We have neglected it. We have abused it. We don't take it seriously. We don't even care to get them to rehab after a couple of generations of failure. All right. No one, I think the youngest person Uh to have really contributed to the standard model of theoretical level was born in 1951. Right frank wilczek. And almost nothing has happened um That in theoretical physics after 1973, that's sent somebody to Stockholm for theoretical development, that predicted experiment. So, we have to understand that we are doing this to ourselves now with that said, these guys have behaved abysmally in my opinion. Um because they haven't owned up to where they actually are, what problems they're really facing, how definite they can actually be. They haven't shared some of their most brilliant discoveries which are desperately needed in other fields like gauge theory, which at least the mathematicians can share, which is an upgrade of the differential calculus of Newton and Leibnitz and they haven't shared the importance of renormalization theory. Uh even though this should be standard operating procedure for people across the sciences dealing with different layers and different levels of phenomenon </s>

<s>[INST] Which makes me sad about like Deepmind, for example, where they still they still publish in nature and these big prestigious, I mean there's still value I suppose to the prestige that comes with these big venues, but the result is that they will announce some breakthrough performance and it will take like a year to actually publish the details, I mean, and those details in if they were published immediately would inspire the community to move in certain directions with that [/INST] let's speed up the rest of the community, but I don't know to what extent that's part of their objective function also, </s><s>[INST] that's true. So it's not just the prestige. A little bit of the delay is uh, is part of Yeah, [/INST] they certainly deepmind specifically has been um, working in the regime of having slightly higher quality, basically process and latency and publishing those papers that way. Another </s><s>[INST] question from Reddit, Do you or have you suffered from imposter syndrome being the director of Ai. Tesla, being this person when you're stanford, where like the world looks at you as the expert in ai to teach, teach the world about machine learning. [/INST] When I was leaving Tesla after five years, I spent a ton of time in meeting rooms. Uh, and you know, I would read papers in the beginning when I joined Tesla, I was writing code and then I was writing less and less code and I was reading code and then I was reading less and less code. And so this is just a natural progression that happens, I think. And uh, definitely I would say near the tail end, that's when it sort of starts to hit you a bit more that you're supposed to be an expert. But actually the source of truth is the code that people are writing the guitar and the actual, the actual code itself and you're not as familiar with that as it used to be. And so I would say maybe there's some like insecurity there. </s><s>[INST] Yeah, that's actually pretty profound that a lot of the insecurity has to do with not writing the code in the computer science space like that, because that is the truth, that that code [/INST] is the source of truth, the papers and everything else. It's a high level summary. I don't yeah, just a high level summary. But at the end of the day you have to read code, it's impossible to translate all that code into actual, you know, paper form. So when when things come out, especially when they have a source code available, that's my favorite place to </s><s>[INST] go. So like I said, you're one of the greatest teachers of machine learning ai ever from CS to 31 end to today, what advice would you give to beginners? Interested in getting into machine learning, [/INST] beginners are often focused on </s><s>[INST] like what [/INST] to do, and I think the focus should be more like how much you do. So I'm kind of like believer on the high level in this 10,000 hours kind of concept where you just kind of have to just pick the things where you can spend time and you you care about and you're interested in, you literally have to put in 10,000 hours of work. Um it doesn't even matter as much like where you put it and you'll iterate and you'll improve and you'll waste some time. I don't know if there's a better way you need to put in 10,000 hours, But I think it's actually really nice because I feel like there's some sense of determinism about being an expert at a thing. If you spend 10,000 hours you can literally pick an arbitrary thing. And I think if you spend 10,000 hours of deliberate effort and work you actually will become an expert at it. And so I think it's kind of like a nice thought. Um and so uh basically I would focus more on like are you spending 10,000 hours? and </s><s>[INST] So and then thinking about what kind of mechanisms maximize your likelihood of getting to 10,000 hours? [/INST] Exactly. Which </s><s>[INST] for us silly humans means probably forming a daily habit of like every single day actually doing the thing [/INST] whatever helps you. So I do think to a large extent is a psychological problem for yourself. One other thing that I help that I think is helpful for the psychology of it is many times people compare themselves to others in the area I think is very harmful. Only compare yourself to you from some time ago, like say a year ago, are you better than you year ago is the only way to think. Um And I think this then you can see your progress and it's very motivating. </s><s>[INST] That's so interesting that focus on the quantity of hours because I think a lot of people in the beginning stage but actually throughout get paralyzed by uh the choice like which one do I pick this path of this path, like they'll literally get paralyzed by like which I d to use. Well [/INST] they're worried they're worried about all these things. But the thing is some of the you will waste time doing something wrong, you will eventually figure out it's not right, you will accumulate scar tissue and next time you'll grow stronger because next time you'll have the scar tissue and next time you'll learn from it and now next time you come to a similar situation you'll be like oh I I messed up, I've spent a lot of time working on things that never materialized into anything and I have all that scar tissue and I have some intuitions about what was useful wasn't useful how things turned out. So all those mistakes were were not that work, you know? So I just think you should just focus on working what have you done, what have you done last week? </s>

<s>[INST] of ATlas shrugged, really [/INST] Articulating a philosophy. So that's what she did. She applied it to politics to life to gender, to all these issues from 1957 until she died in 1980. </s><s>[INST] So, the objectivism was born out of the later parts of Atlas shrugged. [/INST] Yes, definitely. It was there all the time, but It was fleshed out during the latter part of Atlas shrugged and articulated for the next 20 years. </s><s>[INST] So what is objectivism, [/INST] objectivism? So there are five branches in philosophy. And and so I'm gonna just go through the branches she starts with. You start with metaphysics, the nature of reality. And objectivism argues that reality is what it is. It's kind of goes hearkens back to Aristotle law of identity. A is A You can wish it to be B but wishes do not make something real. Reality is what it is, and it is the primary. And it was it's it's not it's not manipulated, directed by consciousness. Consciousness is there too, ah you know, to observe, to give us information about reality. That is the purpose of consciousness, it is the nature of it. So, in metaphysics, existence exists A the law of identity. The law of causality. Things are, you know, the things act based on their nature, not randomly, not arbitrarily based on their nature. And then we have the tool to know reality. This is epistemology, the theory of knowledge, a tool to know reality is reason. It's our senses and our capacity to integrate the information we get from our senses and integrated into new knowledge and to conceptualize it. And uh and that is uniquely human. Uh We don't we don't know the truth from revelation. We don't know truth from emotions. Emotions are interesting emotions tell us something about ourselves, but our emotions are not tools of cognition. They don't tell us the truth about what's out there, about what's in reality. So reason is a means of knowledge and therefore reason is a means of survival. Only individuals. Reason just in the same way that only individuals can eat. We don't have a collective stomach, Nobody can eat for me and therefore nobody can think for me, we don't have a collective mind. There's no collective consciousness not. It's it's bizarre that people talk about these collectivized aspects of the mind. They don't talk about collective feet and collective stomachs and collective things. But so we all think for ourselves and it is our fundamental basic responsibility to live our lives to live to choose once we choose to live to live our lives to the best of our ability. So in morality, she is an egoist. She believes that the purpose of morality is to provide you with the code of values and virtues, to guide your life for the purpose of your own success, your own survival, your own thriving your own happiness. Happiness is the moral purpose of your life. The purpose of morality is to guide you towards a happy life, your own happiness, your own happiness absolutely your own happiness. So she rejects the idea that you should live for other people that you should live for the purpose of other people's happiness your purpose is not to make them happier to make them anything. Your purpose is your own happiness. But she also rejects the idea that you could argue maybe than a chan idea of you should use other people for your own purposes, right? So every person is an end in himself. Every person's more responsibilities, their own happiness. And you shouldn't use other people for your own should exploit other people for your unhappiness. And you shouldn't be allow yourself to be exploited for other people. Every individual is responsible for themselves. And what is it that allows us to be happy? What is it that facilitates um human flourishing human success, human survival. Well, it's the use of our minds, right? Goes back to reason. And what is the reason require in order to be successful in order to to work effectively? Mhm. It requires freedom. So the enemy of reason, the enemy of reason is forced. The enemy of reason is coercion. The enemy of reason is authority. Right? The catholic church, doing what they did to Galileo, right? That restricts Galileo's thinking right? When he's in a house arrest, is he gonna come up with a new theory is going to discover new truths? No, it's the punishment is to, you know, it's too dangerous. So force coercion um are enemies of reason, and what reason needs is to be free to to think to to discover, to innovate to break out of convention. Um, so we need to create an environment in which individuals are free to reason to free to think, and to do that. We we we come up with a concept historically, we've come up with the concept of individual rights, individual rights. To find the scope of define the fact that we should be left alone, free to pursue our values, using our reason free of what free of coalition force without. And that the job of government is to make sure that we are free. The whole point of government. The whole point of when we come in a social context, the whole point of establishing a governing that context is two secure that freedom. It's to make sure that I don't use coercion on you. The government is supposed to stop supposed to intervene before I can do that, or if I've already done it to prevent me from doing it again. So the purpose of government is to protect the freedom to think and to act based on our thoughts. It's to leave individuals free to pursue their values, to pursue their happiness, to pursue their rational thought, and to be left alone to do it. And so she rejects socialism, which which basically assumes some kind of collective goal, assumes the sacrifice of the individual to the group assumes that your moral purpose in life is the well being of other people, rather than your own. Uh And and she rejects all form of state is um all form of government. Uh that is, you know, overly uh that that is involved in any aspect other than to protect us from force, coalition authority. Uh and she rejects anarchy and we can talk about that. I I think you had a question and a list of questions you sent me about anarchism </s>

<s>[INST] Okay, so those, you kind of describe these two methodologies for one is temporarily noise you want especially noisy and you kinda have to play and figure out what what can be useful. Uh It'd be great if you consider comment. I got a chance recently to spend a day at a company called neuralink that uses brain computer interfaces and their dream is to well there's a bunch of sort of dreams, but one of them is to understand the brain by sort of, you know, getting in their past, the so called that a factory while getting in there and be able to listen, communicate both directions. What are your thoughts about this? The future of this kind of technology of brain computer interfaces to be able to now have a have a window or direct contact within the brain to be able to measure some of the signals to be able to send signals, to understand some of the functionality of the brain. [/INST] Ambivalent. My sense is ambivalent. So it's a mixture of good and bad and I acknowledge that freely. So the good bits if you just look at the legacy of that kind of reciprocal but invasive brain stimulation. I didn't paint a complete picture when I was talking about so the ways we understand the brain prior to your imaging, it wasn't just leave lesion deficit studies. Some of the early work, in fact literally 100 years from where we're sitting at the institution, neurology was done by stimulating the brain of say dogs. I'm looking at how they responded either with them, their muscles or with the salivation and imputing what that part of the brain must be doing that I stimulated then. Yeah. And I vote this kind of response then that tells me quite a lot about the functional specialization. So there's a long history of brain stimulation which continues to enjoy a lot of attention nowadays. </s><s>[INST] Positive attention. [/INST] Oh yes, absolutely. Um you know, deep brain stimulation for Parkinson's disease is now a standard treatment and also a wonderful vehicle to try and understand the neuronal dynamics. Underlie movement disorders like Parkinson's disease. Um even interest in transit, magnetic magnetic stimulation stimulated with magnetic fields and will it work in people who are depressed, for example, quite a crude level of understanding what you're doing. But you know, there there is historical evidence that these kinds of brute fought interventions do change things that, you know, it's a little bit like banging the tv but the valves are working properly but it still it works. So uh you know, there is a long history of brain computer interfacing A. B. C. I. Um I think it is a beautiful example of that. It's sort of carved out its own niche in its own aspirations. Uh And they've been enormous advances within limits um advances in terms of our ability to understand how the brain, the embodied brain engages with the world. I'm thinking here of sensory substitution, the augmenting our sensory capacities by giving ourselves extra ways of sensing and sampling the world um ranging from sort of trying to replace lost visual signals through to giving people completely new signals. So uh the well I think most engaging examples of this is equipping people with a sense of magnetic fields. So you can actually give them magnetic sensors that enable them to feel, to say tactile pressure around their tummy where they are in relation to the magnetic field of the earth. And after a few weeks they take it for granted they integrated they and by they assimilate this new sensory information into the way that they literally feel their world. But now equipped with this sense of magnetic dick direction. So that tells you something about the brain's plastic potential to remodel to. Um it's plastic capacity to suddenly trying to explain the sensory data at hand bye augment Ating augmenting the sensory sphere and the kinds of things that you can measure clearly. That's purely for entertainment and understanding that the nature and the power of our brains. I would imagine that most B. C. I. Is pitched at solving um clinical and human problems such as locked in syndrome such as paraplegia or replacing lost um sensory capacities like blindness and deafness. So um then we come to the more I'm the negative part of my on the other side of it. So I yeah I don't want to be deflationary because much of my deflationary comments is probably large out of ignorance than anything else. But uh generally speaking the bandwidth and the bit rates that you get from brain computer interfaces as we currently know them. We're talking about bits per second. So that would be like me um only being able to communicate with any world or with you using very very very slow morse code and it is not in the even within an order of magnitude near what we actually need for an inactive realization of what people aspire to when they think about sort of curing people with paraplegia or replacing site um despite heroic efforts. So one has to ask, is there a lower bound on the kinds of um recurrent information exchange between a brain and some augmented or artificial um um interface. Um and then we come back to interestingly when I was talking about before, which is, you know, if you're talking about function in terms of inference and I presume we'll get to that later on in terms of the free energy principle and the moment they may be fundamental reasons to us united the case. We're talking about ensemble activity we're talking about basically. And for example, let's paint the challenge facing brain computer interfacing in terms of controlling another system that is highly and deeply structured, very relevant to our lives. Very non linear. That rests upon the kind of non equilibrium steady states and dynamics that the brain does the weather. All right, so good example, imagine you had some very aggressive satellites that could produce signals that could perturb some little parts of the, of the weather system. And then what you're asking now is, can I meaningfully get into the weather and change it meaningfully and make the weather respond in a way that I want it to your talking about chaos control on a scale which is almost unimaginable. So there may be fundamental reasons why BC as you might read about it in a science fiction novel, Aspirational BC may never actually work in the sense that to really be integrated and be part of the system. Um, isn't a requirement that requires you to have evolved with that system that you you have to be part of are very delicately structured, deeply structured dynamic ensemble activity that is not like rewiring a broken computer or plugging in a peripheral interface adapter. It is much more like getting into the weather patterns or come back to your magic soup is getting into the active matter and meaningfully relate that to the outside world. So I think there are enormous challenges there. </s>