text
stringlengths
28
334k
<s>[INST] yeah, the prison of your Mind. So those [/INST] are the darker moments. Exactly. These are the darker moments. </s><s>[INST] Yeah, it's in the darker moments. The mind does feel like you're trapped and alone in a room with it. [/INST] Yeah. And there's this this scene in the movie which like where he just breaks out with his guitar and there's this prostitute in the room, he starts throwing stuff and then he like, you know, breaks the window, he throws the chair outside and then you see him laying in the pool with his own blood like, you know, everywhere. And then there's these endless hours spent fixing every little thing and lining it up and it's this whole sort of mania versus you know, you can spend hours building up something and just destroyed in a few seconds. One of my turns is that song. It's like I feel cold as attorney kid writers dry as a funeral drum and then the music feels like run to the bedroom, there's a suitcase on the left and you find my favorite ax. Don't look so frightened. This is just a passing phase. One of my bad days just so beautiful. I need to rewatch it. So, but imagine watching this as a teenager it like ruins your mind like so many. It's just such harsh imagery and then um, you know, Anyway, so, so there's the dark moment and then again, going back to sting now it's the political songs, Russians and I think that song should be a new national anthem for the US, not for Russians but for red versus blue. Mr Khrushchev says, we will bury you. I don't subscribe to this point of view. It would be such an ignorant thing to do if the Russians love their Children to what is it doing? It's basically saying the Russians are just as humans as we are. There's no way that they're going to let their Children die. And then it's just so beautiful. How can I save my innocent boy from Oppenheimer's deadly toy. And now that's the new national anthem. Are you reading? There is a no monopoly of common sense on either side of the political fence. We share the same biology regardless of ideology. Believe me, when I say to you, I hope the Russians love their Children too. There's no such thing as a winnable war. It's a lie we don't believe anymore. I mean it's beautiful, right? And for God's sake, America wake up, these are your fellow americans there, your your fellow biology. You know, there is no monopoly of common sense on either side of the political fence. It's just so beautiful. </s><s>[INST] There's no CRISPR simpler way to say. Russians love their Children to the common humanity [/INST] and remember the what I was telling you. I think in one of our first podcast about the daughter who is crying for her husband for her brother to come back for more and then the virgin mary appears and says, who should I take instead? This turk hears his family hears his Children. This other one he just got married etcetera. And that basically says no, I mean if you look at the lord of the ranks, the enemies are these monsters, they're not human and that's what we always do. We always say they they're not like us, they're different, they're not humans, etcetera. So there's this dehumanization that has to happen for people to go to war. You know, if you realize that's how close we are, genetically one with the other, This whole 99.9% identical. You can't bear weapons against someone who's like that. </s><s>[INST] And the things that are the most meaningful to us in our lives at every level is the same on all sides, on both sides. Exactly. Not just that we're genetically the same [/INST] were ideologically the same. We love our Children, we love our country, we will, you know, we will fight for our family. Yeah, So and the last one I mentioned last time we spoke, which is johnny Mitchell's both sides now. So she has three rounds, One on clouds, One on love and one on life and on cloud she says rows and flows of angel hair and ice cream castles in the air and feather canyons everywhere. I've looked at clouds that way. But now they only block the sun, They rain and snow on everyone. So many things I would have done but clouds got in my way. And then I've looked at clouds from both sides now from up and down and still somehow it's cloud's illusions. I recall I really don't know clouds at all and then she goes on about love how it's super, super happy or it's about misery and loss and about life, how it's about winning and losing and so forth. But now old friends are acting strange. They shake their heads, they say I've changed, well something's lost and something's gained in living every day. So again, that's growing up and realizing that well, The view that you had as a kid is not necessarily that you have as an adult. I remember my poem from when I was 16 years old of this whole, you know, Children danced now all in row and then in the end, even though the snow seems bright without you have lost their light sound that sang and wounded smiled. So this whole concept of if you have love and if you have passion, you see the exact same thing from a different way, you can go out running in the rain or you could just stay in and say uh sucks, I wanna be able to go outside now </s><s>[INST] both sides [/INST] Anyway and the last one is last last one. I promise Leonardo Cohen this </s><s>[INST] is amazing by the way your, I'm so glad we stumbled [/INST] on how much, </s>
<s>[INST] and you uh this might be years ago but I'm not sure. And you're there's an atlantic article you've written um about moving away from a distinction between neurological disorders, quote unquote brain problems and uh psychiatric disorders or quote unquote mind problems. So so on that topic, how do you think about this gray area? [/INST] Yeah, this is exactly this is exactly the evolution that things are going is. You know there's psychiatry and then there were guys and gals in labs, poking cells and so on. Those are the neuroscience. But yeah I think these are moving together for exactly the reason you just cited and where this matters a lot. The atlantic article uh what was called The Brain on Trial where this matters a lot is it's the legal system because the way we run our legal system now and this is true everywhere in the world is you know, someone shows up in front of the judge's bench or let's say there's five people in front of judges bench and they've all committed the same crime. What we do because we feel like hey this is fair is where you're gonna get the same sense, you'll all get three years in prison or whatever it is. But in fact brains can be so different. This guy's got schizophrenia, this guy's psychopath. This guys tweet down on drugs and so on. So that um it actually doesn't make sense to keep doing that. And what we, what we do in this country more than anywhere in the world is we imagine that incarceration is a one size fits all solution and you may know we have the America has the highest incarceration rate in the whole world in terms of percentage of our population we put behind bars. So um, there's a much more refined thing we can do as neuroscience comes in and changes and has the opportunity to change the legal system, which is to say this doesn't let anybody off the hook. It doesn't say oh it's not your fault and so on. But what it does is it changes the equation. So it's not about, hey, how blameworthy are you but instead is about, hey, what do we do from here? What's the best thing to do from here? So if you take somebody with schizophrenia and you have them break rocks in the hot summer sun in a chain gang. Also. Yeah, that that doesn't help those kids for me, that doesn't fix the problem. Um, if you take somebody with a drug addiction who's in jail for you know, being caught with two ounces of some illegal substance and you put him in prison, it doesn't actually fix the addiction doesn't help anything. Um, happily what neuroscience and psychiatry bring to the table is lots of really useful things you can do with schizophrenia with drug addiction, things like this. Um, and that's why. So I I don't know if you just want to run a national non profit called the Center for Science and Law. And it's all about this intersection of neuroscience and legal system. And we're trying to implement changes in every county in every state. Um, I'll just without going down that rabbit hole, I'll just say one of the very simplest things to do is to set up specialized court systems where you have a mental health court that has judges and juries with expertise in mental illness. Because if you go by the way to a regular court and the person says, um or the defense lawyer says this person is schizophrenia. Most of the jury will say, man, I call bullsh it on that. Why? Because they don't know about because they don't they don't know what it's about. And it turns out people who who know about schizophrenia feel very differently as a juror than someone who happens not to know anybody schizophrenia. They think it's an excuse. So, um, you have judges juries with expertise in mental illness and they know the rehabilitative strategies that are available. That's one thing having a drug court, we have judges and juries with expertise and rehabilitative strategies and what can be done and so on. A specialized prostitution court and so on all these different things by the way, this is very easy for counties to implement this sort of thing. And this is this is I think where this matters to get neuroscience into public </s><s>[INST] policy. What's the process of injecting expertise into this? So [/INST] I'll say exactly what it is. A county needs to run out of money. First, I've seen this happen over and over. So what happens is a county has a completely full jail. And they say, you know what, we need to build another jail and then they realize God, we don't have any money, we can't afford this. We've got too many people in jail. And that's when they turn to God, we need something smarter. And that's when they set up specialized court systems. </s><s>[INST] Uh, we're all function best when know when our back is against [/INST] the wall and that's what Covid is good for you. It's because we we've all had our routines and we are optimized for the things we do. And suddenly our backs are against the wall, all of </s>
<s>[INST] And when you say attention, maybe another way to phrase that is you're considering a context, uh, wide context in terms of the wide context of the sentence, in understanding the meaning of a particular word and a computer vision, that's understanding a larger context to understand the local pattern of uh, of a particular local part [/INST] of an image. So basically if you have, say again, a banana in the image, you're looking at the full image first. So whether it's like, you know, you're looking at all the pixels that out of the kitchen of a dining table and so on. And then you're basically looking at the banana also, </s><s>[INST] by the way, in terms of if we were to train the funny classifier, there's something funny about the word, banana. Just going to anticipate that my [/INST] my bearing a banana shirt so </s><s>[INST] it's just bananas on it. Okay so masking has worked for division context as well [/INST] and so this transformer ideas worked as well. So basically looking at all the elements to understand a particular element has been really powerful. Envision. The reason is like a lot of things when you're looking at them in isolation. So if you look at just a blob of pixels, so Antonio turrialba at MIT used to have this like really famous image which I looked at when I was a PhD student but he would basically have a blob of pixels and he would ask you hey what is this? And it looked basically like a shoe or it could look like a T. V. Remote, it could look like anything and it turns out it was a beer bottle but I'm not sure it was one of these three things but basically surely the full picture and then it was very obvious what it was. But the point is just by looking at that particular local window you couldn't figure out because of resolution because of other things. It's just not easy always to just figure out by looking at just the neighborhood of pixels what these pixels are and the same thing happens for language as well </s><s>[INST] for the parameters that have to learn something about the data, you need to give it the capacity to learn the essential things like if it's not actually able to receive the signal at all, it's not gonna be able to learn that signal and to in order to understand images, to understand language, you have to be able to see words in their full context. Okay, what is harder to solve vision or language? Visual intelligence or linguistic intelligence? [/INST] So I'm going to say computer vision is harder. My reason for this is basically that uh language of course has a big structure to it because we developed it, whereas vision is something that is common in a lot of animals, everyone is able to get by a lot of these animals on earth are actually able to get by without language. And a lot of these animals were also deemed to be intelligent, So clearly intelligence uh does have like a visual component to it. And yes, of course, in the case of humans and of course also has a linguistic component, but it means that there's something far more fundamental about vision than there is about language and I'm sorry to anyone who disagrees. But yes, this is what I feel. </s><s>[INST] So that's being a little bit reflected in uh the challenges that have to do with the progress of self supervised learning, would you say? Or is that just a peculiar accidents of the progress of the ai community that we focused on link or we discovered self attention and transformers in the context of language first. [/INST] So like the self supervised learning success was actually uh for vision has not much over the transformers part, I would say it's actually been independent a little bit. I think it's just that the signal was a little bit different for vision than there was for like an L. P. And probably NLP folks discovered it before. So for vision, the main success has basically been this like crops so far taking different crops of images. But as for NLP it was this masking thing, </s><s>[INST] but also the level of success is still much higher for language. [/INST] So that has a lot to do with, I mean I can get into a lot of details for this particular question. Let's go for it. Okay, so the first thing is language is very structured so you are going to produce a distribution over a finite vocabulary english has a finite number of words. It's actually not that large. Uh and you need to produce basically When you're doing this masking thing, all you need to do is basically tell me which one of these like 50,000 words it is. That's it. Now for vision, let's imagine doing the same thing. Okay, we're basically going to blank out a particular part of the imagine we asked the network or this neural network to predict what is present in this missing patch. It's combinatorial e large, you have 256 pixel values if you're even producing basically a seven across seven or 14 cross 14 like window of pixels at each of these 169 or each of these 49 locations you have 256 values to predict. And so it's really, really large and very quickly the kind of like prediction problems that we're setting up are going to be extremely like intractable for us. And so the thing is for NLP it has been really successful because we are very good at predicting like doing this like distribution over a finite set. And the problem is when this set becomes really large, we're going to become really really bad at making these predictions and at solving basically this particular set of problems. So if you were to do it exactly the same way as an LP for vision there is very limited success. The way stuff is working right now is actually not by predicting these mosques. It's basically by saying that you take these two like crops from the image, you get a feature representation from it and just saying that these two features so they're like vectors. Just saying that the distance between these victims should be small And so it's a very different way of learning from the visual signal than there is from NLP. Okay. The other reason is the distributional hypothesis that we talked about the rental period. So a word given its context basic the context actually supplies a lot of meaning to the word now because there are just finite number, finite number of words and there is a finite way in like which we compose them of course the same thing goes for pixels but in language there is a lot of structure so I always say whatever their dash jumped over the fence for example, there are lots of these sentences that you'll get and from this you can actually look at this particular sentence might occur in a lot of different context as well. This exact same sentence might occur in a different context. So the sheep jumped over the fence, the cat jumped over the fence, the talk jumped over the fence. So you immediately get a lot of these words which are because this particular token itself has so much meaning you get a lot of these tokens or these words which are actually going to have to have sort of this related meaning across given this context. Whereas for vision is much harder because just by like pure like the way we captured images, lighting can be different um there might be different noise in the sensor. So the thing is you're capturing a physical phenomenon and then you're basically going through a very complicated five line of like image processing and then you're translating that into some kind of digital signal. Whereas with language you write it down and you transfer it to a digital signal almost like it's a lost list, like transfer and each of these tokens are very very well defined. </s>
<s>[INST] So these are the few words were just a few words. You're trying to like quickly localize the effect [/INST] And I live on it very very very analytically said and I live on it very very very analytically said </s><s>[INST] Thank you. I'm not letting it go. I love it It does the same apply to just conversation in general just how to get better conversation I think a lot of people struggle they haven't securities They have anxiety about conversation I as funny as it's to say I have a lot of anxiety about conversation [/INST] Is that is basically to do the same kind of practice? Yeah some of the techniques you get genuinely just trying to make sure you heard somebody </s><s>[INST] Oh, yeah, what's the best conversation you ever been in except this one, of course I mean, not the best conversation, but what stands out to you as a conversation that changed you as a person, maybe. [/INST] Well, there's probably been a lot of them along the way, I mean, but one that I remember on a regular basis, actually there's two, but when I was in the bureau, I'm at Quantico, I'm there for an in-service, there's another guy from New York, a buddy of mine named Lionel, and we're both trying to decide whether or not we want to try to get into profiling or negotiation because they're both about human dynamics and both of us really like human dynamics. And we're sitting around talking about it and we're talking about several things and he labels me, and I knew he didn't know what he was doing, I think he had picked it up and I had been talking about my family, quite a few things, and he said to me, and I never said this directly, that we were close. But he said to me, sound like your family's really close. And I can remember in a moment like this feeling, just like I felt great in the moment. I mean, what he said just drew together everything that I'd been saying and nailed the essence of it. And I have a very clear recollection of how good that felt in a moment. So a couple of years later, I'm on a suicide hotline. Now I got this line at the back of my head, you know, line technique, reaction, read, whatever you want to call it. Guy calls in on a hotline, and I could tell the dude is rattled by his tone of voice. I mean, just amped up. And he goes, you know, just trying to put a little on the day. I need to help put a little on the day. I gotta put a little on the day. And I said, Oh, you sound anxious. And he goes, he goes, Yeah. Yeah. And he And he came down a little bit and he was a guy that was telling me about, he was battling a disease of paranoia and he's going to go on a car trip with his family the next day. And he knew that on the car trip, he was going to, you know twist himself in the knots. And so the night before he was twisting himself in the knots, and he's laying out everything that he's done to try to beat paranoia and how much his family's helping. going on a car trip with a family because they're going to take them to see a doctor. And so I hit him with the same thing that my buddy Lionel said. I said, sounds like your family's close. He goes, yeah, we are close. And he leveled out a little bit more. And then he started ticking off all the things that he was doing to try to be paranoid. And he sounded determined. And so I said, you sound determined. And he goes, yeah, I am determined. And I'll be fine. Thanks. And that was all I said. So those two conversations, which are overlapping </s><s>[INST] conversations, those two things really stick out in my mind. Do those things like through all the different negotiations and conversations you've had, do they kind of echo throughout? Like you basically, because when you empathize with other human beings, you start to realize we're all the same. And so you can start to pick little phrases here and there that you've heard from other little experiences that we're all about. Like we all want to be to be close with other human beings. We all want love. I think we're all deeply lonely inside. I'm looking for connection. We're just if we're honest about it. And so all humans have that same, all the same different components of what makes them tick. So you kind of see yourself basically just saying the same [/INST] things to connect with another human being. Yeah, there aren't that many different things that we're looking for understanding on or connection on or satisfaction of. There just aren't that many of them regardless. And so yeah, you're looking for it to manifest itself in some form or another, and you're willing to take a guess on whether or not that's what you're seeing or </s><s>[INST] hearing. What advice would you give to me to be better at these conversations? To me and to I tell other people that do kind of interviews [/INST] and podcasts and so on, interviews. </s><s>[INST] I really care about empathy as well. [/INST] Is there kind of as a life-long journey in this process. Well I think, I would advise you to take that approach which is the approach that you're taking. You care about it, you're very curious about it. You see it as a life-long journey. You're fascinated by it. You enjoy learning about it and you definitely do see it as a life-long journey as opposed to this is what I can, If I can acquire this, then I can manipulate people. </s>
<s>[INST] I mean, would it be fair to say you kind of stumbled around a little bit uh through accidents of too early morning of classes and physics and so on until you discovered intrinsic motivation as you mentioned. And then that's it, it hooked you and then you celebrate the fact that this happens to human beings. Yeah, like, [/INST] and what is it that made what I did intrinsically motivating to me? Well, that's interesting and I don't know all the answers to it and I don't think I want to, I want anybody to think that um you should be sort of in any way, I don't know, sanctimonious or anything about it, you know, it's like I really enjoyed doing statistical analysis of data. I really enjoyed running my own experiment, which was what I got a chance to do in the psychology department. That chemistry and physics had never, I never imagined that mere mortals would ever do an experiment in those sciences, except one that was in the textbook that you were told to do in lab class. But in psychology we were already like, even when I was taking psych one, it turned out we had our own rat and we got to after to set experiments. We got to do, okay, do something you think of, you know, with your rat, you know, so it's the opportunity to do it myself and and to to bring together a certain set of things that that engaged me intrinsically. And I think it has something to do with why certain people turned out to be, you know, profoundly, um amazing musical geniuses, right? They get immersed in it at an early enough point and it just sort of gets into the fabric. So my my little brother had intrinsic motivation for music, as we witnessed when he discovered how To put records on the phonograph when he was like 13 months old and recognize which one he wanted to play, not because he could read the labels, because he could sort of see which ones had which scratches which were the different, you know, oh that's rapidly espanol and that's </s><s>[INST] wow, you [/INST] know and and </s><s>[INST] enjoyed that that connected with them somehow. [/INST] And yeah and and there was something that it fed into and you're extremely lucky if you have that and if you can nurture it and can let it grow and let it be an important part of your life, </s><s>[INST] those are the two things is like be attentive enough to, to feel it when it comes like this is something special. I mean I don't know. Uh for example, I really like um tabular data like excel sheets. Like it brings me a deep joy. I don't, I don't know how useful that is for anything but this [/INST] is what I'm talking </s><s>[INST] exactly. So there's like a million, not million but there's a lot of things like that for me and you have to hear that for yourself. Like be like realize this is really joyful. But then the other part that you're mentioning which is the nurture is take time and stay with it, stay with it awhile and see where that takes you in life. [/INST] Yeah. I think I think the the motivational engagement results in the immersion that then creates the opportunity to obtain the expertise. So you know we we can call it the Mozart effect right? I mean when I think about Mozart, I think about, you know the person who was born as the fourth member of the family string quartet, right? And uh and they handed him the violin when he was six weeks old. Alright, start playing, you know, it's just like and um so the level of immersion there was was amazingly profound. But uh hopefully he also had, you know, some something maybe this is where the more uh sort of the genetic part comes in sometimes I think uh you know, something in him resonated to the music so that the synergy of the combination of that was so powerful. So that's what I really considered to be the most artifact. It's sort of the the synergy of something with, with experience that then results in the unique flowering of a particular, you know, mind. Um So I know my siblings and I are all very different from each other. We've all gone in our own different directions and I mentioned my younger brother who was very musical. Um I had my other younger brother was like this amazing like intuitive engineer. Um and my sister, one of my sisters was passionate about. Yeah. Uh and you know, water conservation well before it was uh you know, such a hugely important issue that it is today. So we all sort of somehow these find a different thing. Um and I don't, I don't mean to say it isn't uh tied in with something about about us biologically, but but it's also when that happens where you can find that then, you know, you can do your thing and you can be excited about it. So people can be excited about fitting people on bicycles as well as excited about making neural networks, achieved insights into human cognition </s>
<s>[INST] Can you tell me a little more on how do you pronounce it? Uh Salah's [/INST] Enceladus, </s><s>[INST] Enceladus? Can you tell me a little bit more about Enceladus? Like uh we've been talking about way too much about jupiter saturday doesn't get enough love. No uh Saturn doesn't get as much love. So what's what's Enceladus? Uh is that the most exciting moon of Saturn? [/INST] Depends on your perspective. It's very exciting from a astrobiology perspective. I think Enceladus and titan are the two most unique and interesting moons of Saturn that definitely both get the most attention also from the life perspective. Um </s><s>[INST] So what's the more likely titan or Enceladus for life if you were to bet all your money in terms of like investing which to investigate what are the difference between the two that are interesting to you? [/INST] Yeah, so the potential for life in each of those two places is very different. So titan is the one place in the solar system where you might imagine again, all of this is so speculative, but you might imagine life evolving in the atmosphere. So the from a biology perspective, titan is interesting because it forms complex organic molecules in its atmosphere. It has a dense atmosphere is actually denser than Earth's. It's the only moon that has an atmosphere denser than Earth's and it's got tons of methane in it. What happens is that methane gets irradiated, It breaks up and it reforms with other things in the atmosphere. It makes these complex organic molecules and it's effectively doing prebiotic chemistry in the atmosphere </s><s>[INST] while still being freezing cold. [/INST] Yes. Okay. </s><s>[INST] What what would that be like? Would that be pleasant for humans to hang out there? It's just really cold. [/INST] There's nowhere in the solar system that would be pleasant for humans. Um It would be cold. You couldn't breathe the air. Um </s><s>[INST] What colonization wise if there's an atmosphere is not a big plus? Are still a ton of radiation? Mhm. Okay. So okay so tighten that that's a really nice feature that their life could be in the atmosphere because then it's it's that might be remotely observable or certainly is more accessible if you visit. Okay. So uh what about Enceladus? So that would be still in the ocean? [/INST] Right. And Enceladus has the advantage like I said of spewing material out of its south pole. So you could collect it. But it has the disadvantage of the fact that we don't actually really understand how it's ocean could stay froze or sorry, could stay globally liquid over the age of the solar system. And so there are some models that say that it's going through this um cyclical evolution where the ocean freezes completely and thaws completely. And the orbit sort of um oscillates in and out of these eccentricities. Um And in that case the potential for life ever occurring there in the first place is a lot lower because if you only have an ocean for 100 million years is that enough time. Um </s><s>[INST] And it also means that might be mass extinction events. If it does occur, it just freezes again. Very sad man. I'm this is very depressing all the like slaughter of life elsewhere. How unlikely do you think life is on earth? So when you look, when you study other planets and you study the contents of other planets, does that give you a perspective on um the origin of life on earth, which again is full of mystery in itself, Not the evolution but the origin the first springing to life like from from nothing to life from the basic ingredients to life. I guess another way of asking is how unique are we? [/INST] Yeah, it's a great question and it's one that just scientifically we don't have an answer to. We don't even know how many times life evolved on earth if it was only once or if it happened independently 1000 times in different places, we don't know whether it's happened anywhere else in the universe. Although it feels absurd to believe that we are the only life that evolved in the entire universe. But it's conceivable we just have just no real information. We don't understand really how life came about in the first place on earth. </s><s>[INST] I mean, so if you look at the drake equation that tries to estimate how many alien civilizations are out there, planets have a big part to play in that equation, if you want to bet money uh in terms of the odds of origins of life on earth, I mean, this all has to do with how special and unique as earth, what you land, in terms of the number of civilizations has to do with how unique the rare earth hypothesis is, how rare special is earth, how rare and special is the solar system. Like if you had to bet all your money and a completely unscientific questions, well, no, actually, it's actually rigorously scientific. We just don't know a lot of things in that equation. There's a lot of mysteries about that and it's slowly becoming better and better understood in terms of exoplanets, in terms of how many solar systems out there, where there's planets there, earth like planets. That's getting better and better understood. What's your sense from that perspective, how many alien civilizations out there? So you're [/INST] right that the equation is being better understood, but you're really only talking about the first three parameters in the equation or something, you know, how many stars are there? How many planets per star? And then we're just barely scratching the surface of what fraction of those planets might be habitable. The rest of the terms in the equation are like, how likely is life to evolve, give inhabitable conditions, how likely is it to survive all these things um there are all these huge unknowns. Actually. I remember when I first saw that equation, I think I was, I think it was my first year of college and I thought this is ridiculous. This is a common sense that didn't need to give the given name, you know? Um, and be just a bunch of unknowns. It's like putting our ignorance together in one equation. But I've actually, now I understand this equation. You know, it's not something we ever necessarily have the answer to. It's just gives us a framework for having the exact conversation we're having right now. And I think that's how it was intended in the first place. When it was put into writing was to give people a language to communicate about the factors that go into the potential for aliens to be out there and for us to find them. Um, I I would put money on there being aliens. I would not put money on us having definitive evidence of them in my lifetime. </s>
<s>[INST] So let me ask, you mentioned, you mentioned that Andrew Yang by example, showed you the value of kindness. And do you think the space of uh policies, good policies for humans and for Ai is populated by policies that with kindness or ones that are the opposite exploitation, even evil. So if you just look at the sea of policies we operate under as human beings or if AI system had to operate in this real world, do you think it's really easy to find policies that are full of kindness like would naturally fall into them? Or is it like a very hard optimization problem? [/INST] I mean, there's kind of two optimizations happening for humans. Right? So for humans there's kind of a very long term optimization, which evolution has done for us and we're kind of predisposed to like certain things and that's in some sense what makes our learning easier because I mean we know things like pain and hunger and thirst and the fact that we know about those is not something that we were taught that's kind of innate when we're hungry. We're unhappy when we're thirsty. We're unhappy, won't have pain, we're unhappy. And ultimately evolution built that into us to think about these things. And so I think there is a notion that it seems somehow humans evolved in general, two prefer to get along in some ways but at the same time also to be very territorial and kind of centric to their own tribe, like it seems like that's the kind of space we converged onto it. I mean I'm not an expert in anthropology, but it seems like we're very kind of good within our own tribe but need to be taught to be nice to other tribes. Well he </s><s>[INST] looked at steven pinker, he highlights this pretty nicely. And uh uh better angels of our nature where he talks about violence decreasing over time consistently. So whatever tension, whatever teams we pick, it seems that the long arc of history goes towards us getting along more and more so [/INST] uh </s><s>[INST] so do you think that do you think it's possible to teach RL based robots? This kind of kindness. This kind of ability to interact with humans. This kind of policy even to uh let me ask, let me ask a fun one. Do you think it's possible to teach RL based robot to love a human being and to inspire that human to love the robot back? So to like uh RL based algorithm that leads to a happy marriage. [/INST] That's interesting questions. Maybe I'll answer it with with another question. Right. Because I mean it's but I'll come back to it. So another question can have is okay. I mean how how close does some people's happiness get from interacting with? Just a really nice dog. Like I mean dogs, you come home, that's what dogs do they greet you, They're excited makes you happy when you come home to your dog, you're just like, okay, this is exciting. They're always happy when I'm here. I mean if they don't greet you because maybe whatever your partner took him on a trip or something, you might not be nearly as happy when you get home. Right? And so that kind of, it seems like the level of reasoning a dog house is pretty sophisticated, but then it's still not yet at the level of human reasoning. And so it seems like we don't even need to achieve human love reason to get like very strong affection with humans. And so my thinking is why not? Right? Why Why couldn't within a I couldn't we achieve the kind of level of affection that humans feel among each other or with friendly animals and so forth? It's a question, is it a good thing for us or not? That's another thing. Right? Because I mean, but I don't see why not. Why not? Um, </s><s>[INST] so Elon musk says love is the answer. Maybe he should say love is the objective function and then RL is the answer [/INST] right? Maybe </s><s>[INST] peter thank you so much. I don't want to take up more of your time. Thank you so much for talking today. [/INST] Well, thanks for coming by, Great to have you visit </s>
<s>[INST] So one of the really interesting perspectives that your book takes on a system like this is to see them not to compare a system like this to humans, but to compare it to animals. Of how we see animals. Can you kind of try to again sneak up, try to explain why this analogy is better than the human analogy, the analogy of robots as animals. [/INST] Yeah. And it gets trickier with the language stuff, but we'll get into that too. Um I think that animals are a really great thought experiment when we're thinking about AI and robotics because again this comparing them to humans that leads us down the wrong path both because it's not accurate but also I think for the future we don't want that we want something that's a supplement. But I think animals because we've used them throughout history for so many different things. We domesticated them not because they do what we do, but because what they do is different and that's useful. And it's just like whether we're talking about companionship, whether we're talking about work integration, Whether we're talking about responsibility for harm. There's just so many things we can draw on in that history from these entities that can sense think make autonomous decisions and learn that are applicable to how we should be thinking about robots and Ai and and the point of the book is not that they're the same thing that animals and robots are the same. Obviously there are tons of differences there like you can't, you can't have a conversation with a squirrel. Right? But the the </s><s>[INST] point all the time [/INST] really, by </s><s>[INST] the way, squirrels are the cutest I project so much on squirrels. I wonder what their inner life is. Um I suspect there are much bigger assholes than we imagine. [/INST] Like </s><s>[INST] if it was a giant squirrel, it would fuck you over so fast. If you had the chance, it would take everything you own, it would eat all your stuff because it's small and the furry tail, the furry tail is a, is uh, is a weapon against human consciousness and cognition. It wins us over. That's what cats do to cats out competed squirrels and yeah, no dogs have love, cats have no soul. They, I'm just kidding. People get so angry. I talk to you about cats that I love cats anyway. So yeah. Uh Yeah, you're, you're describing all the different kinds of animals that get domesticated and it's a really interesting idea that it's not just sort of pets. There's all kinds of domestication going on. There all have all kinds of uses [/INST] like </s><s>[INST] the ox that you proposed might be at least historically one of the most useful domesticated animals. [/INST] It was a game changer because it revolutionized like what people could do economically etcetera. So I mean just like robots are gonna change, they're gonna change things economically. They're gonna change landscapes, like cities might even get rebuilt around autonomous vehicles or drones or delivery robots. Like I think just the same ways that animals have really shifted society and society has adapted also to like socially accepting animals as pets. Um I think we're going to see very similar things with robots. So I think it's a useful analogy. It's not a perfect one. But I think it's it helps us get away from this idea that robots can should or will replace people. </s><s>[INST] If you remember what are some interesting uses of animals ferrets for example. [/INST] Oh yeah the ferrets, they still do this. They use ferrets to go into narrow spaces that people can't go into like a pipe or like they'll use them to run electrical wire. I think they did that for princess dies wedding. There's so many weird ways </s><s>[INST] that we've [/INST] used animals and still use animals for things that robots can't do. Like the dolphins that that they used in the in the military. I think the I think Russia still has dolphins and the U. S. Still has dolphins in their navies. Um Mine detection looking for lost underwater equipment. Some rumors about like using them for weaponry. Which which I think Russia is like sure believe that. And americans like no no we don't know who knows. But they started doing that in like the sixties seventies. They started training these dolphins because they were like oh dolphins have this amazing echolocation system that we can't replicate with machines and they're trainable. So we're gonna use them for all the stuff that we can't do with machines or by ourselves. And they've tried to phase out the dolphins. I know the U. S. Has like invested a lot of money in trying to make robots do the mind detection. But like you were saying there are some things that the robots are good at and there's some things that biological creatures are better at. So they still have the dolphins. </s><s>[INST] So there's also pigeons. [/INST] Yeah pigeons. Oh my gosh. There's so many examples that I mean the pigeons were the original hobby photography drone. They also carried mail for thousands of years letting people communicate with each other in new ways. So the thing that I like about the animal analogies, they have all these physical abilities but also sensing abilities that we just we don't have. And like that's that's just so useful and that's that's robots. Right, robots have physical abilities. They can help us lift things or do things that were not physically capable of. They can also sense things. It's </s><s>[INST] just I just feel [/INST] like I still feel like it's a really good analogy. </s><s>[INST] And [/INST] and it works because people are familiar with it. </s><s>[INST] What about companionship and when we start to think about my cats and dogs and pets that seem to serve no purpose whatsoever except the social connection. [/INST] Yeah I mean it's kind of a newer thing </s><s>[INST] at [/INST] least in the United States. Like </s>
<s>[INST] So that contains a lot of that. Hence the imaging. I could tell you a story of what's happening. [/INST] Absolutely. But it is slightly compromised in terms of the resolution. So the deployment of these little micro vessels that water the garden to enable the activity to the neural activity to play out the spatial resolution is in order of a few millimeters And crucially the temporal resolution is the order of a few seconds. So you can't get right down and dirty into the actual spatial and temporal scale of neural activity in and of itself. To do that. You'd have to turn to the other big imaging modality, which is the recording of electromagnetic signals as they're generated in real time. So here the temporal bandwidth, if you like on the temp, the lower limit on the temple resolution is incredibly small. You're talking about, you know, Dallas seconds, milliseconds. And then you can get into the phase IQ fast responses that is in of itself the neural activity and start to see the succession of cascade of hierarchal recurrent message passing evoked by a particular stimulus. But the problem is you're looking at electromagnetic signals that have passed through an enormous amount of magic soup or spaghetti of collectivity and through the scalp and the skull. And it's become spatially very diffused. It's very difficult to know where you are. So, you've got this sort of Catch 22, you can either use an imaging modality, it tells you within mm which part of the brain is activated to be there to when or you've got these electromagnetic E g M E G um setups that tell you to within a few milliseconds when something has responded. Be not aware. So you've got these two complementary measures either indirect via the blood flow or direct via the electromagnets signals caused by neural activity. Uh These are the two big imaging devices and then the second level of responding to the question, what are the yeah from the outside. What are the big ways of of using this this this technology? Um So once you've chosen your the kind of neuro imaging they want to use to answer your questions and sometimes it would have to be both. Um then you've got a whole raft of analyses. Time series analyses usually that you can bring to bear in order to answer your questions or address your hypothesis about those data. And it's interesting that they both fall into the same two camps were talking about before, you know this dialectic between specialization and integration, differentiation and integration. So it's the cartography of the blue biology analyses. </s><s>[INST] I apologize and probably shouldn't interest but just heard a fun word. Uh the blood, [/INST] the apology, apology. It's a theology is um which means the study of blobs. Nothing. Are </s><s>[INST] you being witty and humorous or is there an actual, does the word apology ever appear in a textbook somewhere? [/INST] It would appear in a popular book. It would not appear in a worthy specialist journal, but it's the fond word for the study of literally little blobs on brain map showing activations like the kind of thing that you'd see in, you know the newspapers on on abc or BBC reporting the latest finding from brain imaging? Interestingly though the maths involved in that stream of analysis does actually call upon the mathematics of blobs. So seriously, they actually called soil characteristics. And you know, they have a lot of fancy names in mathematics, </s><s>[INST] we'll talk about about your ideas in free energy principle. I mean there's a echoes of blobs there when you consider sort of uh entities, mathematically speaking. Yes, [/INST] absolutely, yeah. Anyway. Well, circumscribed, well defined you entities of well, from the free energy point of view, entities of anything but from the point of view of the analysis, the cartography of of the brain. Uh These are the entities that constitute the evidence for this functional segregation. You have segregated this function in this blob and it is not outside of the blob. That's basically the if you were a map maker of America. Um and you did not know its structure. The first thing that you're doing constituting or creating a map would be to identify the cities for example, or the mountains and the rivers, all of these uniquely spatially localize double features, possibly topological features have to be placed somewhere because that requires a mathematics to identify what does a set city look like on a satellite image or what does the river look like or what does amount to look like? What would it? Um You know, what data features would it would evidence that that particular top, you know that particular thing that you wanted to put on the map and they normally are characterized in terms of literally these blobs or these sort of another way looking at this is a certain um statistical measure of the degree of activation crosses the threshold and in crossing that threshold uh in the spatially restricted part of the brain, it creates a blob and that's basically what political parametric mapping does. It's basically um mathematically finessed blob ology. </s>
<s>[INST] it's like the Queen here in in the U. K. Is the spokesperson. So [/INST] actually we don't elect </s><s>[INST] whatever. Everybody seems to love her out of Ireland from the outside perspective. Uh But yeah giant egos brilliant people moving forward. Do you think there's um [/INST] actually I would pick up one thing you said just just the brilliant people think because I'm not I'm not saying that people aren't great but I think there is this sort of impression that physicists will have to be brilliant or geniuses which is not true actually and you know you have to be relatively bright for sure. But you know a lot of people a lot of the most successful experimental physicists and not necessarily the people with the biggest brains they're the people who you know particularly one of the skills that are most important in particle physics is the ability to work with others and to collaborate in exchange ideas and also to work hard and it's a sort of often it's more determination or a sort of other set of skills. It's not just being you know kind of some great </s><s>[INST] brain. Very true. So I mean there's parallels to that in the machine learning world if you want to if you want to solve any real world problems which I see as the particle accelerators essentially a real world instance she ation of theoretical physics and for that you have to not necessarily be brilliant but uh be sort of obsessed systematic rigorous sort of unbearable stubborn all those kind of qualities that make for a great engineer. So the scientists purely speaking that practitioner of the scientific method. So you're right. But nevertheless to me that's to me that's brilliant. My dad's a physicist. Uh I argue with him all the time. To me, engineering is the highest form of science and he thinks that's all nonsense that the real work is done by the theoretician. So uh in fact we have arguments about like people like Elon musk for example, because I think his work is quite brilliant but he is fundamentally not coming up with any serious breakthroughs. He's [/INST] just creating </s><s>[INST] in this world implementing, I like making ideas happen to have a huge impact to me. That is that's the Edison that to me is is a brilliant work. But uh to him it's you know, uh messy details that somebody will figure out any way. I [/INST] mean, I don't know whether you think there is an actual difference in temperament between, say a physicist and engineer, whether it's just what you got interested in. I don't know, I mean, you know, a lot of what experimental physicists do is to some extent engineering and it's not what I do. I mostly do data stuff. But you know a lot of people would be called electrical engineers but they trained as physicists but they learn electrical engineering for example because they were building detectors. So there's not such a clear divide I think. </s><s>[INST] Yeah that's interesting. I mean there but there does seem to be like your you work with data there there does seem to be a certain like I love data collection there might be an O. C. D. Element or something that you are more naturally predisposed to. As opposed to theory. Like I'm not afraid of data. I love data and there's a lot of people in machine learning who are more like they're basically afraid of data collection, afraid of datasets, afraid of all that. They just want to stay in more than theoretical and they're really good at it space. So I don't know if that's a genetic that you're bringing the way you do with the way you go to school but looking into the future of LHC uh and other colliders. So there's in the in America there was whatever it was called, the super there's a lot of super [/INST] superconducting supercollider, super desert desert </s><s>[INST] desert tron. So that was canceled the construction of that uh Which is a sad thing but what do you think is the future of these efforts? Will a bigger collider be built? Will LHC be expanded? What do you think? [/INST] Well in the near future um the LHC is gonna get an upgrade. So that's pretty much confirmed I think it is confirmed. Um Which is it's not an energy upgrade. It's what we call a luminosity upgrade. So basically means increasing the data collection rates, so more collisions per second basically because after a few years of data taking you get this law of diminishing returns where each year's worth of data is a smaller and smaller fraction of the lot you've already got. So to get a real improvement in sensitivity, you need to increase the data rate by an order of magnitude. So that's what this upgrade is going to do lHC B at the moment. The whole detector is basically being rebuilt to allow it to record data at a much larger rate than we could before. So that will make us sensitive to whole loads of new processes that we weren't able to study before. You know, I mentioned briefly these anomalies anomalies that we've seen. So we've seen a bunch of very intriguing anomalies in these b quark decays um which may be hinting at the first signs of this kind of the elephant, you know that the signs of some new quantum field or fields may be beyond the standard model. It's not yet at the statistical threshold where you can say that you've observed something but there's lots of anomalies in many measurements that all seem to be consistent with each other. So it's quite interesting. So, you know, the upgrade will allow us to really home in on these things and see whether these are nominees are real because if they are real. Um this kind of connects to your point about the next generation of machines, what we would have seen then is, you know, we would have seen the tail end of some quantum field in influencing these big corks, What we then need to do to build a bigger collider to actually make the particle of that field. So if these, if these things really do exist, so that would be one argument. I mean, I mean, so at the moment, europe is going through this process of um thinking about the strategy for the future. So there are a number of different proposals on the table. One is for sort of higher energy upgrade of the LHC where you just build more powerful magnets and put them in the same tunnel that's a sort of cheap, cheaper, less ambitious possibility. Most people don't really like it because it's sort of a bit of a dead end because once you've done that, there's nowhere to go. Well, um there's a machine called click, which is a compact linear collider, which is an electron positron collider that uses a novel type of acceleration technology to accelerate shorter distances. We're still talking kilometers long but not like 100 kilometers long. Um, and then the, probably the project that is, I think getting the most support will be interesting to see what happens. Something called the future circular collider, which is a really ambitious long term, multi decade project to build a 100 kilometer circumference tunnel under the Geneva region um, the LHC would become a kind of feeding machine, It would just feed, </s>
<s>[INST] So as you watch the events of 9 11 the things that our leaders were saying in the in the minutes hours days, weeks that followed maybe you can give a little bit of a timeline of what was being said. When was the actual invasion of Afghanistan? And also What were your feelings in the minutes weeks after nine [/INST] 11 I was in D. C. I was on the way to american university hearing on NPR what happened. Um and I thought of the american unity logo which is red, white and blue. It's an eagle. And I thought you know Washington is under attack and symbols of american power are under attack. And so um yeah I was quite concerned and at the time lived just a few miles from the capital. And so um you know I felt that it was it was real. So I appreciate the yeah the the sense of anxiety and fear and panic and for 23 years later in D. C. We're constantly getting reports. You know mostly rumors and unconfirmed about all kinds of attacks before the cities. But I definitely appreciate the sense of being under assault but in watching television including Russian television that day because I just I just installed a satellite thing. So I was trying to watch world news and get different points of view and that was quite useful to have an alternative set of eyes in Russian. Yeah. In Russian, yeah </s><s>[INST] the Russians is good enough to understand Russian television [/INST] news. Yeah the news individuals that were coming that were not shown on american television. I don't how they had it but they had they were not filtering anything in the way that the major networks and cable intelligence we're doing here. So it was very unvarnished view of the violence of the moment. You know, in new york city. If people diving from the towers are being just, you know, it was really they didn't hold back on that. Which was quite you know, fascinating much of the world saw much more than actually the american public saw. But to your question, you know, amid that feeling of imminent doom, I watch commentators start to talk about Al Qaeda and then talk about Afghanistan and when the experts was um was born at Ruben um who's at N. Y. U. Is a you know, kind of long very learned um Afghanistan hand. And he's brought on peter Jennings on abc news to to kind of lay this out for everyone. Um and I thought, you know, he had to find job. But I think it was formative in submitting the view that somehow Al Qaeda was synonymous with the space Afghanistan. And I think again I was no Al Qaeda expert then and I'm not now. But I think my immediate thought went to war. And because my background had been with at that point mostly Afghans who have been displaced from decades of war, whom I encountered in Pakistan who are refugees and so on. I thought immediately medium, my mind went to the suffering of Afghan people that this war was going to sweep sweep up. Of course the defenseless people who have nothing to do with politics. So </s><s>[INST] we should give maybe a little bit of context you can speak to. So assume nobody is an expert at anything. So let's just say uh you're you and I are not experts in anything. What is a historian? Were you studying at the time and thinking of policy uh is it is it the full global history of Afghanistan? Is it the region? Were you thinking about the mujahideen and Al Qaeda and Taliban. Were you thinking about the soviet union, the proxy war through Afghanistan? Where you're thinking about Iraq and oil? Like what what's the full space of things in your heart in your mind at the [/INST] time? I mean, this is the moment. Of course it was, you know, that's the sense of, you know, the suffering and the tragedy of the moment of the death. And that was I think I was preoccupied by by the violence of the moment. Um but as the conversation turned to Afghanistan as a kind of theater does not respond to this moment. I think immediately came to mind was that little I knew about Al Qaeda the time suggested that the geography was inaccurate, that this was a global network, a global threat. That this is a kind of, you know, a movement that went beyond borders. And I think the it felt early on that Afghanistan was going to use this as a scapegoat and this intellectually at the time, you know, I was teaching at American University. My courses, you know, touched on a range of subjects, but I was trying to complete a book on Islam in the Russian empire actually. But in doing that research which took me across Russia and Central Asia purely by accident, I had developed an interest in Afghanistan because just again, a series of coincidences, I found myself in touch can the capital of Pakistan without housing do an american friend who was like the king of the market in touch. Can you knew everyone, everyone just afghan merchants there. They found out I didn't have a place to live. I don't know where Afghanistan was. Honestly, this is 1987. Had a big idea it was next door. Well, </s><s>[INST] you lived in this Pakistan. [/INST] Yeah, doing doing decision research. Yeah, because it was, you know, hub of the Russian empire in Central Asia. So just by accident and it with these young afghans who took me in as roommates and then I think that the sense of that community shaped my idea of what Afghanistan is. It was my first exposure to them. They're part of a trading diaspora. They brought, they had brought matches from riga Latvia. They somehow brought um, blow our and our cultural products from, from Egypt and they're sitting in closed containers in Tasca waiting for the Pakistani state to permit them to trade. These guys are mostly hanging out during the day. They'll get dressed up, they put on suits and ties like you're running, they polish their shoes and they would sit around offices, drink tea statues, then they had feasted lunch. Um, and that night we would go out. So part of my research, because I also had a bottle in my research. I was going to the State Archives in Tuscan because of the state of Uzbekistan. You know, that was a very kind of suspicious thing to do. So it took a while to get in. So I had downtime in Tuscan, just like these guys. So I got to know them pretty well and it was really just a, an accidental kind of thing, but grew quite close to them and I developed an appreciation of, um, which now I think again, think of the seeds of all this. Um, these people had already lived Young guys, you know, in the 20s that already lived in 67 countries. They all spoke half a dozen languages. One of my best friends, there had been a kickboxer uh, and break dancer trained in Tehran. His father was a theater person in Afghanistan. Um, he told stories of escaping death in Afghanistan during the civil war, going to Pakistan escaping death there. Um and these were very real stories. </s>
<s>[INST] You can find out what you need on there. It's like books, just as soon as I have. [/INST] And you can learn it deeply. You can drive a nail down through whatever layer cake problem space you've got </s><s>[INST] and learn a cross section there. And not only can you have an impact doing that, you can attain happiness doing that. There's something so fulfilling about becoming a craftsman of a thing. [/INST] Yeah, and I don't want to tell people that, look, this is a good career move, just grit your teeth and bear it. And I do think it is possible sometimes to find the joy in something. Like it might not immediately appeal to you, but I had told people early on in software times that a lot of game developers are in it just because they are so passionate about games. But I was always really more flexible in what appealed to me where I said, I think I could be quite engaged doing operating system work or even database work. I would find the interest in that because I think most things that are significant in the world have a lot of layers and complexity to them and a lot of opportunities hidden within them. So that would probably be the most important thing to encourage to people is that you can, it's like weaponized curiosity. You can deploy your curiosity to find, to kind of like make things useful and valuable to you, </s><s>[INST] even if they don't immediately appear that way. Deploy your curiosity, yeah, that's very true. We've mentioned this debate point, whether mortality or fear of mortality is fundamental to creating an AGI, but let's talk about whether it's fundamental to human beings. [/INST] Do you think about your own mortality? I really don't. And you probably always have to like take with a grain of salt anything somebody says about fundamental things like that. But I don't think about really aging, impending death, legacy with my children, things like that. And clearly it seems most of the world does a lot, a lot more than I do. So I mean, I think I'm an outlier in that where it's more than I do. Yeah, it doesn't wind up being a real part of my thinking </s><s>[INST] and motivation about things. So daily existence is about sort of the people you love [/INST] and the problems before you. I'm very much focused on what I'm working on right now. I do take that back. There's one aspect where the kind of finiteness of the life does impact me. And that is about thinking about the scope of the problems that I'm working on. When I decided to work on, when I was like nuclear fission or AGI, these are big ticket things that are impact large fractions of the world. And I was thinking to myself at some level that, okay, I mean, I may have a couple more swings at bat with me at full capability, but yes, my mental abilities will decay with age, mostly inevitably. I don't think it's a 0% chance that we will address some of that before it becomes a problem for me. I think exciting medical stuff in the next couple decades. But I do have this kind of vague plan that when I'm not at the top of my game and I don't feel that I'm in a position to put a dent in the world some way that I'll probably wind up doing some kind of recreational retro programming or I'll work on something that I would not devote my life to now, but I can while away my time </s><s>[INST] as the old man gardening in the code world. And then to step back even bigger, let me ask you about why we're here. We human beings, what's the meaning of it all? [/INST] What's the meaning of life, John Carmack? So very similar with that last question. I know a lot of people fret about this question a lot and I just really don't. I really don't give a damn. We are biological creatures that happenstance of evolution. We have innate drives that evolution crafted for survival and passing on of genetic codes. I really don't give a damn. I don't find a lot of value in trying to go much deeper than that. I have my motivations, some of which are probably genetically coded and many of which are contingent on my upbringing and the path that I've had through my life. I don't run into like spades of depression or envy or anything that winds up being a challenge and forcing a degree of soul searching with things like that. I seem to be okay, kind of without that. </s><s>[INST] As a brilliant ant in the ant colony without looking up to the sky wondering, why the hell am I here again? So the why of it, the incredible mystery of the fact that we started, first of all, the origin of life on earth and from that, from single cell organisms, the entirety of the evolutionary process took us somehow to this incredibly intelligent thing that is able to build Wolfenstein 3D and Doom and Quake and take a crack at the problem of AGI and create things that eventually supersede human beings. [/INST] That doesn't, the why of it is- It's been my experience that people that focus on, that don't focus on the here and now right in front of them tend to be less effective. I mean, it's not a hundred percent, vision matters to some people, but it doesn't seem to be a necessary motivator for me. And I think that the process of getting there is usually done against like the magic of gradient descent. People just don't believe that just looking locally gets you to all of these spectacular things. That's been the decades of looking at, really some of the smartest people in the world that would just push back forever against this idea that it's not this grand, sophisticated vision of everything, but little tiny steps, local information </s>
<s>[INST] Yeah, so I'll do my best to brief, I'll do my best to reduce human beings into simple descriptions and then you can give me insights of why the hell there's such effective leaders based on my description, not based on your actual deep knowledge of the beings. Uh So that caveat of my inability to speak both the english language and describe humans as well, Let's talk about first Elon musk. So he's known as being quite harsh in the sense of first of all, a very high bar of excellence and uh also willing to what he calls the kind of first principles, thinking of asking the the questions that hurt, which is why the hell are we doing it this way, why can't it be done a lot, but not just better, but a lot better. [/INST] So, so let's I don't want to hear his whole character, I'll go one on one section at a time. So we got a guy that's harsh and and asking the really hard questions, how can that be good or why is that good? Well, first of all, it can be horrible and there's leaders out there that are harsh and they're hated and no one likes them and no one wants to work for them and they never do anything. So what is it that Elon musk does that makes gives him the ability to be harsh. So, I was I was yeah, hearing a description of me when I would give feedback to young seals that had made mistakes during training operations. And the description was that the same thing like this harsh blunt force trauma and just totally direct sledgehammer of truth that I would hit guys with. But it's interesting because I always talk about, you know, building relationships and making sure you're not offending someone. So how do these things match up? Well, I can tell you how they match up when I was being harsh. The guys that I was being harsh with new Without one shred of doubt that I cared about them more than anything else. And that the reason I was giving them his feedback is because I wanted them to be able to lead their troops. I wanted to be able to go accomplish your mission and I wanted them to be able to bring their guys home from war. So I wasn't being harsh because it elevated my ego. I wasn't being harsh because I wanted to denigrate them. I was being actually being harsh because I wanted them to accomplish the mission. So if that's where Ellen comes from, hey listen, we got to make this happen, this is for, this is for the good of the world to do this and people know that then it works. </s><s>[INST] I'll bring this point back up with another guy steve jobs but let me stay on the line for a second. The, the other thing he does, which is interesting. Um, I see the value of this would be great to hear you speak about it. It's unlike many of the other Ceos, very rich billionaires, uh, you know, involved in leading a lot of people. He puts a lot of time into making sure he's on the factory floor. He famously sleeps on the sort of like in the middle of things and he puts a lot of effort. He's also very good at, it is being a low level engineer. So like whatever the task is, he wants to understand the details and he'll talk to the lowest level person in terms of like, you know, somebody who's like uh working literally on putting parts together, he wants to understand what the problem is with the challenges if there's an emergency? He wants to understand the actual details of the problem. Not like delegating into a manager but like because a lot of ceos a lot of managers will, we'll talk about sort of the power and the importance of delegation here. He wants to know if there's a big problem. He wants to know the exact detail. He wants to know the exact problem. He wants to at the fundamental level understand how to solve that problem. What that has to do with materials where there has to do with the actual manufacturing, the mechanical engineering aspect. Like we're talking about like engineering. This is a guy who wears a suit as a ceo tweets about Doris coin but like actual job he's low level engineering. And that to me was always inspiring to see somebody who knows what the funk they're doing. That's what like he gains the respect of engineers at the lowest level. Yeah. I don't know if that's scalable but that's always been inspiring to me and I wonder how many people it's inspiring to. Maybe you can speak to the value of doing that of no matter how high their level of leader is to be able to do the low level ship. [/INST] Yeah and that's that's a common trait that good leaders have and maybe he doesn't necessarily know how to do everything. A good leader but they go down there and talk to the front line troops and say, hey what is the issue that you're dealing with or you know, how can I support you? How can I give you help? And what one key point that you said is, he said, when there's a problem, he gets in there. So there's things happening at his companies that they're working and so he doesn't have to die. I'm not saying he never does, but he doesn't have to spend as much time working on or or looking at some subsystem that's functioning well. He's got a good leader in there that's handling it. And he checks in with that leader and the leader says, yeah, it's working perfectly. He says, great, when there's a problem, that's when he might have to get down there and dig into some details so that he fully understands it, so that he, when he digs down in the details and this is important. He's coming from an altitude where he has uh better, bigger perspective, not necessarily better, but a bigger perspective. So if you sit there and work on a problem, whatever for eight hours and you're staring at, you know, if you are planning a mission and you were you were planning it for eight hours, you're staring at the maps and the charts and you're figuring out where all the troops are gonna be located. And I come in after eight hours and I look at your plan from a from a distant perspective, there's a good chance I'll be able to see holes in your plan that you couldn't see because your perspective was too close. So, so that's good for me to be able to come in from a higher perspective and have a look at it. But also there's times where I need to get down there and actually look, you know, if you're looking at a problem, you say, look, I can't figure out boss, I can't figure out how to get to this target. And I'm looking at it from a distance and I don't see, I might need to start digging in and looking and saying, oh, here's a route that we can take. That actually makes sense, let's try that. So I think it's a good example of someone going up and down in altitude to look at problems, understanding what's happening with the front line troops and at the same time being able to go back to the strategic level and I can, it's probably this way, the reason that he's successful is because he doesn't get stuck down there because if he felt the need to micromanage each and every part on a Tesla, it wouldn't be, it would be very unlikely that he would have the capacity to do all that. Now he can hand over some broad chip design and say, hey, this is what the function needs to be and he gives it to lex and lex goes there with your team and you figured out and you make it happen if he had to actually do that all himself, most likely not possible. So that's what leaders should be doing. They should go elevate and and and and then get down in the weeds when they have to and then go back up. </s>
<s>[INST] makes you that's beautiful. Yeah. But the thing is, this is me saying this, I think your thesis is very strong and correct has elements of correctness, but I still personally put some blame on individuals. Of course. I think, uh, you said Ellen looking up, there's something about childlike wandered him like to his personality, his character, something about, I think more so than others where people can trust them and there's uh, I don't know, sunday brunch is an example of somebody. It was like, there's some kind of, it's hard to put into words, but there's something about the human being where he's trustworthy, he's human in a way that connects to us. And the same with Sergeant Adela. I mean some of these folks, um, something about us is drawn to them even when they're flawed. Even like, uh, so like your thesis really holds up for steve jobs because I think people didn't like steve jobs, but like he delivered products and then they fell in love every time. I guess you could say that the ceo the leader is also a product if they keep delivering a product that people like by being a public and saying things that people like that's also a way to make people happy. But from a social network perspective, it makes me wonder how difficult it is to explain to people why certain things happen. Like to explain machine learning to explain why certain the woke mob effect happens or the certain kinds of like bullying happens, which is like it's human nature combined with the algorithm and it's very difficult to control for how the spread of quote unquote misinformation happens, it's very difficult to control for that. And so you try to decelerate certain parts and you create more problems then you solve and anything that looks at all like censorship can create huge amounts of problems. It's a slippery slope and then you have to inject humans to oversee the machine learning algorithms and anytime you inject humans into the system it's gonna create a huge number of problems. And I feel like it's up to the leader to communicate that effectively to be transparent. First of all designed products that don't have those problems and second of all when they have those problems to be able to communicate with them, I guess that's all going to, when you run a social network company, your job is hard. [/INST] Yeah, I will say the one element that you haven't named that I think you're getting at is just bedside manner which steve jobs. I never worked for him. I never met him in person um had an like an uncanny ability in public to have bedside manner. I mean some of the best clips of steve jobs from like, say Maybe the 80s when he's on this stage and getting questions from the audience about life for, and he'll take this question that is like, how are you going to compete with blah and super boring and I don't even know the name of the company? And his answer is, is if you just asked like your grandfather the meaning of life and you sit there and you're just like, what, like, and there's that bedside manner. Um, and if you lack that, or if that's just not intuitive to you, I think that it can be a lot harder to gain the trust of people and then add on top of that missteps of companies, right? It's, I don't know if you have any friends from the past where like maybe they crossed you once or like maybe you get back together and you're friends again, but you just never really forget that thing. It's human nature not to forget, </s><s>[INST] I'm Russian, you crossed me once [/INST] we </s><s>[INST] solve the problem. [/INST] So my point is there is humans don't forget, and if there are times in the past where they feel like they don't trust the company or the company hasn't had their back. That is really hard to earn back, especially if you don't have that bedside manner. Um, and again, like I'm not attributing this specifically to mark because I think a lot of companies have this issue where one you have to be trustworthy of the company and live by it and live by those actions. And then to I think you need to be able to be really relatable in a way that's very difficult if you're worth like what these people are. </s><s>[INST] It's really hard. Yeah, Jack does a pretty good job of this by being a monk, but [/INST] I also like jackets, shoes, attention. Like he's not out there almost on purpose. He's just working hard, doing square and right. Like I literally shared a desk like this with him at a rodeo. I mean this normal guy who likes painting, I like, I remember he would leave early on Wednesdays or something to go to like a painting class and he's creative, he's thoughtful. I mean, money makes people like more creative and more thoughtful, like extreme versions of themselves. Right? Um and this was a long, long time ago you </s><s>[INST] mentioned that he uh he asked you to do some kind of javascript thing. [/INST] We're working on some javascript together. I like </s><s>[INST] hilarious, like pre twitter early twitter days. You and Jack Dorsey are in the room together talking about javascript solving some kind of menial problem, [/INST] terrible problems. Yeah, I mean not terrible, just like boring, boring widget problem. I think it was the audio widget we were working on at the time, I'm surprised anyone paid me to be in the room as an intern because I didn't really provide any value. I'm very thankful to anyone who included me back in the day. Uh, it was very helpful. So thank you if you're </s>
<s>[INST] the type annotations are there inside the variable as its runtime. [/INST] They're mostly associated with the function object. Not with each individual variable, but uh you can sort of map from from the arguments to the variables </s><s>[INST] And that's what a 3rd party library [/INST] exactly. And the problem with that, is that all that extra runtime type checking uh is going to slow your code down instead of speed it </s><s>[INST] Up, I think uh the reference this uh sales pitchy blog post that says 75% of developers time is spent on debugging. I would say that in some cases that might be okay. It might be okay to pay the cost of performance for the catching of the types, the type errors. [/INST] And in most cases doing it statically before you ship your code to production is more efficient than doing it at runtime piecemeal. </s><s>[INST] Can you tell me about M. Y. P. Y. My pi project. What is it? What's the mission and in general what is the future of static typing in python? [/INST] Well, so my pie was started by finished developer. You so </s><s>[INST] many cool things out of Finland? I gotta say just that part of the world. [/INST] I guess people have nothing better to do in those long cold </s><s>[INST] winters. I [/INST] don't know. I think you lived in England when he invented that stuff actually. But my pie is the original static type checker for python and the type annotations that were introduced with pep 4 84 were sort of developed together with the static type checker. And in fact Yuka had first invented a different syntax that wasn't quite compatible with python and uh U. K. And I sort of met at the python conference in I think in 2013 and we we sort of came up with a compromise syntax that would not require any changes to python and that would let my pie sort of be an add on static type checker for python? </s><s>[INST] Just out of curiosity was like double colon or something. What what was he proposing that would break python. I [/INST] think he was using angular brackets for types like in C plus plus or java generics. </s><s>[INST] Yeah you can't use angular brackets in python would be too tricky. Well [/INST] we the the key thing is that we already had uh syntax for annotations, we just didn't know what to use them for yet. So type annotations were just the sort of most logical thing to to use that existing dummy syntax for. But there was no there was no syntax for defining generics directly. Syntactic lee in the language my pie literally meant my version of python where my refers to yuka, he had a parse er that translated my pie into python by like doing the type checks and then removing the annotations and all the angular brackets from the positions where where he was using them. But a pre processor model doesn't work very well with the typical workflow of python development projects. </s><s>[INST] That's funny. I mean that could have been another major split if it became successful. Like if you watch typescript versus javascript is like a split in the community over types right? That seems to be stabilizing. Now [/INST] it's not necessarily a split. There's certainly plenty of people who don't use typescript but just use the original javascript notation. Just like there are many people in the python world who don't use type annotations and don't use static type checkers. No, </s><s>[INST] I know but there is a bit of a split between typescript and Java's old school javascript E. S. Whatever. Well [/INST] in the javascript world, transpire colors are sort of the standard way of working anyway, which is why typescript being a transpire for itself is not a big deal </s><s>[INST] and transparent for people who don't know. It's what's exactly the thing you said with my pies. It's the code I guess you call it pre processing code that translates from one language to the other and that's part of the culture, part of the workflow of the javascript community. So that's [/INST] right at the same time, an interesting development in the javascript slash typescript world at the moment is that there is a proposal under consideration. It's only a stage one proposal that proposes to add a feature to javascript where just like python, it will ignore certain syntax when running the javascript code and what it ignores is more or less a super set of the typescript annotations syntax </s><s>[INST] interesting. [/INST] So that would mean that eventually if you wanted to you could take typescript uh and you could shove it directly into javascript interpreter without translation. The interesting thing in the javascript world at least the web browser world the web browsers have changed how they deploy and uh they they sort of update their javascript engines much more quickly than they used to in the early days and so there's much less of a need for translation in javascript itself because most browsers just support the most recent version of Atmos script. </s><s>[INST] Just an attention of attention. Do you see if you will recommend somebody use the thing, would you recommend typescript or javascript? I [/INST] would recommend typescript just </s><s>[INST] because of the strictness of the typing, [/INST] it's an enormously helpful extra tool that helps you sort of keep your head straight about what your code is actually doing. </s><s>[INST] I [/INST] mean it's it's it helps with editing your code, it helps with ensuring that your code is not to incorrect and it's actually quite compatible with javascript. Never mind this syntactic sort of heck that is still years in the future. But any library that is written in pure javascript can still be used from typescript programs and also the other way around, you can write a library in typescript and then exported in a form that is totally consumable by javascript. That sort of compatibility is is sort of the key to the, to the success of typescript. </s>
<s>[INST] which is the bag, [/INST] you know like when the, when the, you know the douche bags to go to Vegas and unbutton your </s><s>[INST] dress shirt. [/INST] And the problem with the pull over hoodie is you can't do the douchebag thing where you on button but then still get the like the stomach because the thing is the ultimate look. Could be like, you know, military tank pull over hoodie and if you get a little hot you take off the hoodie but you're like crazy and </s><s>[INST] shape. So it gives you that flexibility. [/INST] Yeah, it's given the zippers given some flexibility and it's like maybe you want to keep your jacket on, like it's considered like a hoodie to be like a jacket. If you want to keep your jacket on then </s><s>[INST] you [/INST] might you might want to do this as opposed to pulling all the way off, you know? So and it's just comfort. But then you get, okay, can I do a jogging pant on this with the last elasticity now people argue about climate uh, where we are with the climate, I take responsibility as being the most influential um, designer of all time, uh, to um, to say we're gonna use biodegradable uh, clothing. Now, the issue there is um, the elastic is not biodegradable. So that means it's actually better to use jeans and a belt than to have an elastic waist bed because elastic waistband is not biodegradable. So I used the planet as a big, the future of the planet is a big piece of the way I engineer and the way we talk about where designs are going, </s><s>[INST] the constraints on your design and engineering is given by the planet by the future of the planet. [/INST] Yes. That could almost make jewish people like me again, </s><s>[INST] every time you say jewish people, I think I've been maybe reading a little too much about World War Two. But man, I'd recommend you listen to some audio books or read some books on the holocaust because like, it's heavy, it's heavy, it will put into context the impact of your words. Uh, [/INST] would you read books on the current holocaust that black people are in? </s><s>[INST] I mean, I read uh, what [/INST] have you read about abortion? </s><s>[INST] I've read, um, a lot of short form writing and I've listened to a lot of debates because it's really humbling that the the question of when does life begin is a really difficult question for me as an engineering scientist. It's a philosophical question. I [/INST] mean, we could just go on population control, not like if abortion is right or wrong, we could say factually the clinics were made by eugenics for population control and it is controlling the population as is the never being given a 40 acres and a mule. So you don't have the opportunity. And when the people that do have the opportunity are separated from our people, our tribe and place in suburban communities, next test chris rock, put it, the dentist and you know, whitewashed and made to shut the funk up and you know, vote left or whatever. You know, uh, *** are supposed to do when we make it as opposed to saying, okay, we're building schools, were building up choirs, we're building up our own leagues, basketball teams, our own factories. We started the first, uh, sportswear factory in America since World War Two was actually, uh, this factory I put in Cody, so You know, I'm 45 years old. We're on this journey right now. It's the other thing about this, it's like people just in general, they love me so much. I'm like, actually a hard guy to really hate for a long period time just because like because like my huge cock and </s><s>[INST] that's what I noticed. I didn't, I didn't understand why he showed it to me when we first met, but now I understand [/INST] it's </s><s>[INST] very nice. Congratulations. I know you don't talk about it, but your hat does say, 20, for um if you run for president, what kind of ideas would you represent that [/INST] were beings with engineering opportunities? I would represent just as you served a platform here. There's something that happened on my last run that I thought, I feel I know was brilliant. It was noisy, but it was brilliant. Had one rally and in the rally I just let people come up and I gave them a platform. It's our responsibility to listen to the pain and hear the pain and understand even when we're the ones that cause the pain like what my tweet, it's my responsibility to hear you and understand why you feel like that, But it's our responsibility as the people to understand each other </s><s>[INST] to give people a voice. People [/INST] need the voice and even right now what I'm doing or how God is using me. I'm showing where our voices are being muted. There's professors that are actually intelligent actually have multiple degrees that have been canceled from their schools and they don't have a music industry or a fan base or a shoe design or a smoking hot ex wife to complain about. They've just got the truth of what they saw and what they dedicated to this country and to education that has been muted by schools that have been taken over with an agenda. And so your you want the brightest minds to be these professors and then you mute them and they have nowhere to go and you might get a guy now that went from being someone's favorite professor to he's working at Starbucks, like, like he was back at school or like he was back in high school. </s><s>[INST] So even if that voice is about anger and hate, it still deserves to be heard. [/INST] Yeah, it deserves to be heard and we deserve to ask why, you know, like you have to ask why. I just feel like that's what's I feel like that is sympathizing Mr huge cock. I'm just saying that it just needs to be </s>
<s>[INST] And if it's Bitcoin, if it's gold, it's a way for multiple nations to partake. So if you were to imagine a future where we move from the fiat standard back to the gold standard and then to the Bitcoin standard or skipping that, going directly to the Bitcoin standard, what would it take? Is it gradual, is it immediate? What are possible trajectories that take us, well, basically where the final sort of empirical observation is that you overtake, Bitcoin overtakes first gold and then bonds in terms of its monetary power in the world. But like just specifically from a government perspective, how do we move the United States, China, Russia, India, European Union to a Bitcoin standard? [/INST] I'm not entirely concerned about whether governments move or not. In fact, I'd be very happy for them not to move as long as possible so that individuals can accumulate more and more Bitcoin while it's still cheap. So the people will move and the governments will catch up. Yeah, and I think this is kind of what I allude to. I mean, the point of the Fiat standard, the Fiat standard is really a Bitcoin book. It talks about Fiat most of the time, but it does so to analyze Bitcoin and the rise of Bitcoin. In the final chapter, I discuss how I think this relationship plays out. The way that I tend to think of it is that most likely what's going to happen is we're gonna have kind of a financial apartheid where there's going to be two monetary systems. One is government controlled and it comes with increasing amounts of surveillance and inflation. And then if you want, you can just opt out of that and get into Bitcoin and it's likely going to be difficult for governments to stop people from getting into Bitcoin for all of the technical reasons that make it very hard to stop Bitcoin. So then we have this alternative that is Bitcoin, which is not inflationary and does not have a central authority that can censor it. I think gradually is my hope and I also think my most likely scenario, but maybe I am biased because everybody thinks what they want is what's gonna happen. I think we're just gonna witness the same relationship because governments make their currency so that they can devalue them and Bitcoin thrives on that. And more and more people are gonna learn, more and more people are gonna find out. And whether it's through curiosity or self-interest or through the destruction of the national currency, all roads lead to Bitcoin. So more and more people are gonna buy Bitcoin, the price of Bitcoin is going to go up. And as it goes up, Bitcoin becomes a more significant part of the world economy. And this is something that skeptics don't get. Like a lot of the academic skeptics to Bitcoin, they offer up all of these theories about why they think Bitcoin can't work and then they present it and they think, they've delivered the knockout blow as if Bitcoin needs their permission or the world is going to need their permission. Well, the reality is people are gonna join Bitcoin out of greed, out of self-interest. Number go up technology is really what's going to get everybody in. And that's really the Trojan horse for fixing the world. Come for the greed and stay for the revolution. It's gonna keep going up because people don't like to be poor, except for most economists and academics. People don't like to be poor. People don't enjoy getting their wealth destroyed and they care more about their self-interest than they care about economic theories about whether this works as money or not. They see their cousin escaped hyperinflation and managed to get a bigger house because they bought Bitcoin five years ago. They realized maybe I should stop mocking my cousin and start buying more Bitcoin. And this is I think an indomitable force that's going to continue. And one thing, most Bitcoiners tend to lean toward an apocalyptic transition. Fiat's gonna collapse. We're gonna get hyperinflation. Everything's gonna be terrible. And then we're gonna move to Bitcoin. And I present the case for why I think maybe that might not be the case. Maybe we won't get this kind of apocalyptic scenario. And this was like the conclusion of the Fiat standard, which is once you realize that mining fiat is creating debt and Bitcoin is allowing. So in order to have fiat money, we need to have people borrow. We need to have people make loans. And the problem that Fiat money runs into today is that if you want to save money, if you want to hold the savings, you have a problem, where do you put your savings? So you put your savings in debt and the creation of more bonds. Wherever you take your savings, you create a bubble in those things. And this is why we see a bubble in the stock market, a bubble in the bond market, a bubble in housing. It's because people are looking for savings, looking for a place where they can save. All of those things are crappy savings instruments, because they're like, they're like copper, in that there's nothing to stop the people behind them to make more of them. House builders can build more houses, governments can issue more bonds, crappy, fraudulent companies can list on the stock market and make more stocks. Well, Bitcoin finally offers us an outlet, we don't need to keep creating more debt, we can invest in this asset that is hard, and that is internationally liquid, and that nobody can make more of. So there is no bubble in it. There is no mechanism for somebody to increase the supply and bring the price crashing down, like with copper and real estate and bonds. So Bitcoin is the way out and this is why I think there's a good case to be made for why the fiat authorities might embrace Bitcoin because they'll see it is their way out of this enormous debt bubble that everybody is stuck in. Particularly the richest and most powerful people in the world, and richest and most powerful governments in the world are the world's biggest borrowers. They're the ones in a lot of debt. So a continuous slow devaluation of the value of that debt, as people upgrade and move on to a hard asset that continues to appreciate is the </s>
<s>[INST] And I guess the bigger picture there is, it's not trivial to know that if you place another human empower, uh, to replace the current human empower, that things are going to be better. There could be a lot worse because there's a momentum to a system, a system is bigger than just this leader. Even when that leader has a huge amount of power, [/INST] that's absolutely right. And, you know, he grew up in that, you know, same system now, he's younger than Putin. So he's got a different generational perspective and he's not wedded to the soviet union or, you know, kind of, some concept of the Russian empire doesn't seem to spend a lot of time, I don't know what he's doing, you know, in jail, but he's probably not sitting around, you know, reading and, you know, the kind of the great kind of tracks of Russian history could be actually, but I mean, I think, you know, Navalny has a different world view and a different perspective, just like Medvedev was different, you know, in his time in the presidency and made some, you know, changes and some innovations there, but don't think that they're going to be radically different because Gorbachev, I mean, he was so different from Andropov and Chernenko, no, this is the person, but he was also constrained by the system and he wanted to have changed, but he wanted evolutionary change, he didn't know how to do it, but he didn't want to bring the whole system down, look at crush off when he came in, you know, after that whole period of, you know, everybody trying to figure out what to do after Stalin had died, and there was all this kind of back and forth and eventually Christoph emerges and, you know, he tries to make changes to the system, but he's also a creature of very specific context. He's grown up in the same system and, you know, kind of brings all kinds of elements of chaos there into the whole thing and, you know, gets into a standoff the United States, that we know, as the Cuban missile crisis and eventually, you know, gets removed, you know, we're looking at what's happening in the United Kingdom right now, they've just turned through three Prime Ministers and actually five prime ministers in, you know, kind of as many years, but all of those Prime ministers have come out of the context of the Conservative Party and the whole, you know, kind of just shades of, you know, the same thing, they've all come out of the same academic and, you know, kind of privileged backgrounds, even richie Cenac, the new Prime Minister is the first, you know, indian or anglo indian Prime Minister and british history. It was a kind of phenomenal, you know, kind of child of indian immigrants, but also a person of great privilege from the same academic and party background as the others, you know, so there are always differences with those human beings, but those contexts matter a lot. </s><s>[INST] What is the probability that Russia attacks Ukraine with a tactical nuclear weapon? [/INST] Well, Putin has definitely been thinking about it, right? I mean, he's the kind of person, if he's got an instrument, he wants to figure out how to use it. You know, we look at Polonium, we look at, you know, we look at all kinds of things, you know, that he's also presided over in Syria, he has put in charge of the war in Ukraine now General, so american is known as General Armageddon, you know, the kind of person who, you know, pretty much facilitated the use of chemical weapons in Syria, you know, for example, so, you know, don't think that Putin hasn't thought about how ruthless he can possibly be. The question is really the calculation, it says his estimation of the probability that will get the desired effect. We keep talking about this idea of escalate to deescalate, that's not what the Russians, you know, how they call it, but it's the whole idea that you do something really outrageous to get everybody else to back off. Now, when you talked about the precedent that the United States set of detonating the nuclear weapons in Hiroshima Nagasaki, what, you know, he obviously meant, the President of using nuclear weapons of course, which of course, we would then say, well, we showed then how the impermissible itty of ever doing that again. But what he's talking about is the President of escalating to such an extent that you stopped the war, because he reads that saying, well, you know, the, I dropped the bombs on Hiroshima Nagasaki, the war was brought to a quick conclusion. Of course, there's a huge debate in America about whether it was necessary to do that. Whether the war was ending anywhere did that really, you know, kind of change the minds of the Japanese high command and they're all kind of books and being written about that. And of course, you know, the revulsion that people felt in the work of that was just, you know, just the shock of, of what actually happened, and we've spent, you know, 70 years, you know, basically coming to terms of the fact that we did something like that, you know, the firebombing, you know, we've we've also looked at all the bombing, you know, in Vietnam and everywhere and you know, the all these massive bombing campaigns and realizing that actually often had the opposite effect on Nagasaki might have contributed. And there's a lot of scholarship suggesting it did to the end of the war, but all of the big bombing campaigns, the destruction actually prolonged was because they made people fight back as we're kind of seeing in the case of Ukraine. So Putin has to calculate the probability that if he uses some tactical nuclear weapon that it will get the desired effect, which is get us to capitulate and Ukraine to capitulate us to capitulate in the United States and Europeans not supporting Ukraine anymore, pushing towards the negotiating table negotiating Ukraine away and Ukraine saying, okay, we give up like happened in Hiroshima and Nagasaki in Japan. So it's it's his calculation, you know, as much as anything else, which is really important. So we have to show him that he won't get that </s>
<s>[INST] So so for me I mean everybody's different but yeah I'm definitely not representative of the general population in the sense that I do the same thing every day. Like I eat the same like I do everything the same the same thing um wear the same thing clearly uh this or the black shirt. Uh So it's frustrating when Alexa doesn't get what I'm saying because I have to correct her every time. The exact same way. This has to do with certain songs. Like she doesn't know certain weird songs are like and doesn't know I've complained to Spotify about this. Talk to the R. D. Head of R. D. A. Spotify a stairway to heaven after correcting every time it doesn't play well at that point correctly. Cover of of [/INST] steroid to happen. So I should figure you should send me or next time it fails. This is free to send it to me. We'll take care of it. Okay well let's Zeppelin is one of my favorite. Rather it works for me so like shocked. It doesn't work </s><s>[INST] for you. This is an official [/INST] bug report. I'll put </s><s>[INST] I'll put it I'll make it public and make every retweeted we're gonna fix the steroid have him anyway. But the point is uh you know I'm pretty boring and do the same things but I'm sure most people do the same set of things. Uh Do you see Alexa sort of utilizing that in the future for improving the experience? [/INST] Yes. And not only utilizing, it's already doing some of it, we call it where Alexa is becoming more self learning. So uh Alexa is now auto correcting millions and millions of utterances in the U. S. Without any human supervision involved. The way it does it is let's take an example of a particular song. Didn't work for you. What do you do next? You either played the wrong song and you said Alexa. No that's not the song I want or you say Alexa play that you try it again and that is a signal to Alexa that she may have done something wrong. And from that perspective we can learn uh if there's that failure pattern or that action of song A was played when song B was requested. Uh It's very common with station names because play NPR you can have uh and be confused as an M. And then you for a certain accent like mine people confuse my N. N. Em all the time because I will uh in an accent there confuse able to humans. It is for Alexa to uh and in that part, but it starts auto correcting and we collect uh we correct a lot of these automatically without a human looking at the </s><s>[INST] failures. So the one of the things that's for me missing in Alexa, I don't know if I'm a representative customer, but every time I correct it, it would be nice to know that that made a difference, you know what I mean? Like the sort of like I heard you like uh [/INST] some acknowledgment of that. We </s><s>[INST] work a lot with with Tesla, we study the autopilot and so on and a large amount of the customers they use Tesla autopilot, they feel like they're always teaching the system almost excited by the possibility of teaching. I don't know if Alexa customers generally think of it as their teaching to improve the system and that's a really powerful thing [/INST] against, I would say it's a spectrum, some customers do think that way and some would be annoyed by Alexa acknowledging that are uh so there's again, no one, you know, while there are certain patterns, not everyone is the same in this way, but we believe that again, customers helping Alexa is a tenant for us in terms of improving it and more self learning is by again, this is like fully unsupervised, right? There is no human in the loop and no labeling happening and based on your actions as a customer Alexa becomes smarter. Again, it's early days, but I think this whole area of teachable ai is gonna get bigger and bigger in the whole space, especially in the eye assistant space. So that's the second part where I mentioned more conversational, this is more self learning. The third is more natural. Uh And the way I think of more natural is we talked about how Alexis sounds and uh and we have done a lot of advances in our text to speech by using again neural network technology for it to sound very </s><s>[INST] human like and the individual texture of the sound, to the timing, the tonality, tone, everything [/INST] I would think in terms of uh there's a lot of controls in each of the places for how I mean the speed of the war is the prosthetic patterns, the uh the actual </s><s>[INST] smoothness [/INST] of how it sounds. All of those are factors. And we do a ton of listening tests to make sure that what naturalists, how it sounds should be very natural. How it understands requests is also very important. Like and in terms of like we have 95,000 skills or and if we have imagine that and many of these skills you have to remember the skilling and say Alexa ask uh they're tied skill to tell me X. Right? Or uh now if you remember the skill name that means the discovery and the interaction is unnatural and we're trying to solve that by what we think of as again uh this was you don't have to have the app metaphor here. These are not individual apps. Right? Even though they're so you you're not sort of opening one at a time and interacting. So it should be seamless because its voice and when it's wise you have to be able to understand these requests independent of the specificity like a skill name and to do that. What we have done is again build a deep learning based capability where we short list a bunch of skills when you say Alexa, get me a car and then we figure it out. Okay it makes meant for an Uber skill versus the left or based on your preferences. And then you can rank the responses from the skill and then choose the best response for the customer. So that's on the more natural other examples of more natural is like we were talking about lists for instance and you wanna you don't wanna say Alexa add milk, lexa are eggs, Alexa art cookies, Alexa heart cookies, milk and X. And that in one shot. Right? So that works, that helps with the nationalists. We talked about memory. Like uh if you said you can say Alexa, remember I have to go to mom's house or you may have entered a calendar event through your calendar. That's linked to Alexa. You want to remember whether it's a in my calendar or did I tell you to remember something or some other reminder? Right. So you have to now independent of how customers create these events? It should just say Alexa. When do I have to go to mom's house and it tells you when you </s>
<s>[INST] What where would you put love on? [/INST] I would not say he's a specialist. I'd say his topical is the strongest move, topical is the strongest move. Yeah. Uh And and the the interesting thing about the the specialist versus the blender, there's a counter, right? Every move has a move that theoretically should be the right choice. So if you're a single move guy, uh there's going to be a guy out there who will get you. Yeah, it'll be very difficult for you to beat that guy. Um But like when you come to like a tournament, typically specialists do much better in tournament scenarios because their singular move can get them through a tournament very quickly and efficiently. Whereas you get a blender in a tournament, they typically will have longer and more difficult matches and by right. Yeah, yeah, but in super match format, typically blenders do better. </s><s>[INST] So we uh offline also talked about arm sumo or uh freedom arm wrestling, I don't know how you want to call it, but freedom uh Exactly North american way. Uh So what, so this is this is this idea and I watched a few videos and it looks fun, is basically removing the restriction of having to keep your elbow on the pad and just being able to arm wrestle over the whole table. I think you've mentioned that the criticism that gets is it might be injury prone or something like that. So, can you describe this arm sumo freedom arm wrestling idea [/INST] when you come to freedom arm wrestling, basically, it removes the limitation of a standard arm wrestling table. Right? So basically every single thing is a freedom arm wrestling table. Some are better than others. All right, So, looking for that nice table where we can kind of stand apart from each other and were anatomically, you know, in a fairly safe position. And the rules and freedom, the way you win is like the knuckles must either touch the tabletop or you hold it off the edge for for a three count, Right? So this is the main way to win. Yes, you can foul, like if you lift your eyeball up, it's still a foul, but you have the entire playing surface, so your elbow is no longer limited to Eur seven by seven or seven by nine pad. So you can move it all over the table. You can move your body around the table a </s><s>[INST] bit too. And if it's a big table, your body can largely be on the [/INST] table. Yeah, so basically, it's like adjusting your ring size. So arm wrestling, you're fighting in a phone booth, right? So you get your fighting in a field, you're fighting, you know, just bigger. So it just it just makes the sport bigger. Yeah, this is Japan, </s><s>[INST] but even on a small table there, even in a slightly larger phone booth, you can get a a lot more fun and variety. [/INST] Very interesting. I love it. I think it makes the sport bigger. I actually believe that it's the future of the sport. I really do </s><s>[INST] because it makes it more accessible. Like you don't need the equipment to do it at the bar, all that kind of stuff. [/INST] Less, less equipment requirements. Kids, most kids start freedom. Like most kids aren't wrestling school desks. Yeah. And like if you see a guy on the street and you're like whatever, like you cannot wrestle anywhere. You don't need to bring your table around with you </s><s>[INST] if uh we talked about the elite level, if somebody was interested in starting an arm wrestling or like going from just like, you know, I go to the gym, you kind of lift, you've arm wrestled a few times trying to get better at it, trying to learn how do you advise? Like getting better to where you can beat your closest buddies, that first step, [/INST] first step, I'd say fine. People find people find good people volume get, we'll get with the club, get with people who know what they're doing, who can mentor you </s><s>[INST] and that's really cool. I got to meet, I realized there's a club in Austin, sure there's been a lot of places [/INST] where we got this app called arm back. Mhm </s><s>[INST] Yeah, which is a app that helps you find other people. They're [/INST] very easy, but I mean, they're all over social networks. I mean, it's kind of widespread now, but yeah, find people, find people and it's just much easier to learn with another person and you'll get stronger that way. But I mean, do this, do the lifts. If you go to the gym, just start doing the lifts uh and right away, those will technically prepare you. </s><s>[INST] What are what are the lists can we describe? [/INST] So, I'd say if you want to just keep it very very simple. Let's just talk about three. There's more there's much more than three. But like when you talk about energy allocation, these three lifts in my opinion should be like 90% of your investment is very big. These three lifts. Ah And the exact percentages can you can argue about it, but we'll we'll we'll start off with the cupping of the wrist. Just this, it's a simple thing and do it with a cable. Uh You know, you can get a thicker diameter. So it kind of, you know, is more on your fingers where an armrest is going to attack you, right? Because any good arm rest is gonna attack your fingers. So like </s><s>[INST] open hand. [/INST] No, no. Well, I mean, for health, yes, you could. But like if you want to be really specific, you train exactly the way you would at a table in the position that you actually start that </s><s>[INST] hatch and then you're just doing this kind of [/INST] to your center. Your people people, one of the, one of the big misconceptions in arm wrestling is that you're aiming for that pin pad. </s>
<s>[INST] at every level. So the ability to walk is a kind of No. [/INST] Yes. Yes. </s><s>[INST] That that there's a dance between the physics that enables this process and just participating in the process is the act of knowing, [/INST] right? And there's a really weird form of memory, you have for this kind of knowing. It's called yourself </s><s>[INST] what can you elaborate? [/INST] Well, you you so </s><s>[INST] so [/INST] we talked about how all the how all the different other kinds of knowing had specific kinds of memory, semantic memory for proposition procedural right episodic for perspective, all what do you what's the kind of memory that is the coordinated storehouse of all of your agent arena relationships, All the roles, you can take all the identities, you can assume all the identities. You can </s><s>[INST] what's what's the self do you mean like consciousness or like [/INST] senior sense of self </s><s>[INST] sense of self in this world? That's not consciousness, That's uh like an agency or something, [/INST] right? It's an agent arena relationship. </s><s>[INST] And so in an agent arena relationship is the sense of the agent. [/INST] And and and that the agent belongs in that arena </s><s>[INST] whatever the agent is, whatever the arena is, Because it's probably a bunch of different framing of how you experience that. [/INST] Yeah. And you and you do you have all within your identity as a self, you have all kinds of roles that are somehow contributing to that identity but are not equivalent to that identity? </s><s>[INST] Yeah. I wonder if like my two hands have different because there's a different experience to me picking up something with my right hand and then my left hand. So are those like uh [/INST] that's a really cool question lex </s><s>[INST] And they certainly feel like their own things and that could be just uh anthropomorphize ation based on cultural narratives and so [/INST] on. It could but I think it's a legitimate empirical question because it also could be sort of ian gilchrist stuff. It could be you're using different hemispheres and they sort of have different agent arena relationships to the environment. This is a really important question in the cognitive science of the self. Does that does that hemispheric difference mean your multiple or you actually have a singular self? </s><s>[INST] So it's important to understand how many cells are there? [/INST] Yes, I think so, but </s><s>[INST] that's that's just like a quirk of evolution as it's not Surely you can't be fundamental to cognition, having multiple cells or a singular self. [/INST] It depends again, because uh we're getting far from the answer to the question you you originally asked me, do you want me to go back to that first or answer that </s><s>[INST] question? I already forgot everything. What's [/INST] the functionality of religion. </s><s>[INST] Yes. [/INST] Okay. Okay. And then we can return to the self. Okay. So you said, you know, you have all these propositions and etcetera etcetera and they different from the religions and they're not they don't seem to be considered legitimate by many people. </s><s>[INST] But [/INST] yet there's something functioning in the religions that is transforming people and making them wiser. And I put it to you that the transformations are largely occurring at those non proposition all levels, the procedural, the perspective all and the participatory and those are the ones by the way that are more fundamentally connected to meaning making because remember the propositions are representational and they're dependent on the non proposition, all non representational processes of connectedness and relevance realization. So religion goes down deep to the non proposition and works there. That's the functionality we need to grasp. Well, </s><s>[INST] you talk about tools essentially that humans are able to incorporate into their cognition. Psycho technologies like language is one, I suppose, uh, isn't religion than a psycho technology? [/INST] It would be a Yeah, an ecology of psycho technologies. Yes. </s><s>[INST] And the question is that Nietzsche ruined everything by saying God is dead. Uh, do we have to invent the new thing go to from the old phone, create the iphone, invent the new psycho technology that takes place of religion. [/INST] And so when the madman in Nietzsche's text goes into the marketplace, who's he talking to? He's not talking to the believers, he's talking to the atheists and he says, do you not realize what we have done, right? We have taken a sponge and wiped away the sky. We are now forever falling. We are unchained from the sun. We have to become worthy of this. </s><s>[INST] No, [/INST] no, no, no. But there's a point there. The point is right, there's one thing to rejecting the proposition, there's another project of replacing the functionality that we lost when we reject the religion. </s><s>[INST] So his worry that is Nihilism takes hold. You don't ever replace the thing that religion the role the religion played in our [/INST] maybe it's it's hard to tell what he actually, because he's so multi vocal. Um, I I'll speak for me rather than I think it is possible to using the best cognitive science and respectfully eggs opting what we can from the best religion and philosophy, philosophical traditions. Because there's things like stoicism that are in the gray line between philosophy and religion, buddhism is the same, doing that best proxy that best expectation we can come up with that functionality without having to buy into the particular proposition all sets of the legacy religions. That's my proposal. I call that the religion, that's not a religion. </s><s>[INST] So things like stoicism or modern stoicism, those things don't, don't you think in some sense they naturally emerge. Don't you think there's a longing for meaning? [/INST] So, stoicism arises during the Hellenistic period, when there was a significant meaning crisis in the ancient world because of what had happened after the breakup of alexander, the Great's Empire. So, if you if you compare Aristotle to people who are living after uh alexander. So Aristotle grows up in a place where everybody speaks the same language has the same religion. His ancestors have been there for years. He knows everybody after alexander, the Great's empire broken has broken up. People are now thousands of miles away from the government, They're surrounded by people because of the diasporas, right? The diasporas, I should say they're surrounded by people that don't speak their language don't share their religion. That's why you get all these mother religions emerging, right? Universal model religions like ISIS, etcetera. So there is a there is what's called domiciled, there's the killing of home, there's a loss of a sense of home and belonging and fitted nous during the hellenistic period. And stoicism arose specifically to address that. And because it was designed to address a meaning crisis, it is no coincidence that it is coming back into prominence right now. Well, </s>
<s>[INST] Yeah, so you know wrestling, I wrestled all through high school and middle school definitely. So it's an individual sport, I did a lot of individual sport, tennis, those kinds of things. But I think even with wrestling and tennis, you're still on a team, you can still like, there's still a camaraderie there. I feel like with chess especially you go on your own with the tournaments like you really are alone, but I, I mean I always personally just had a, like a very self critical mind in general. I would not this one of the reasons I decided not to play chess because I think when I was really young I met somebody uh who was able to play blindfold chess, they were teaching me, they were laying in there on the couch, trash drinking and smoking and there [/INST] were Yeah, </s><s>[INST] exactly. Um they're now a faculty, somewhere in the United States, I forget where, but he um making jokes talking to others and he would move the pieces like he would yell across the room and I remember thinking that if a person is able to do that, then that kind of world, you can live in inside your mind that becomes the chessboard to me. That meant like the chessboard is not just out here, it could be in here and you could do these beautiful, you can create these beautiful patterns in your mind. I thought like I had such a strong pull towards that or where I had to decide either I'm gonna dedicate everything to this or not. Uh you can't do half ast. And then that's when I decided um to walk away from it because I had so much other beautiful things in my life. I loved mathematics, I loved everything was beautiful to me. I thought chess would pull me all in and there was nothing like it. I think in my whole life since then, I think it's such a dangerous addiction. Um it's such a beautiful addiction, but it's a dangerous one, depending on what your mind is like. [/INST] It reminds me of something I thought of before I stopped competing as much and I'd look at people and think, imagine being </s><s>[INST] so [/INST] intelligent that you could become a grandmaster and yet only spending the rest of your life being a grandmaster because it's one of those things where it does require a lot of mental power, but by doing chess, you're not going to be able to explore other subjects deeply and not in a way that is bad, necessarily more in admiration and wondering what else could have been because I've just seen people get to these levels of obsession where it's all they want to do and they're grandmasters, but they're not even top players, so they're never going to make a living out of it, they'll make like maybe 30 40 K a year max. They can't even focus on their competitive chess because they have to supplement it by, you know, teaching and doing things they don't like, and it's just because of how strong of an obsession it can be because it truly is very intellectually rewarding. Um and I think that's what people are addicted to in the self improvement, but you can get that from a lot of other things as well. </s><s>[INST] I think for me, what I was inspired by that stuck with me is that human being could be so good at one thing, but to me, that person on the college drink and so on, I assumed he was the best chess player in the world like that to be able to play inside your head. Um It just felt like a feat that's incredible. And so I fell in love with the idea that I hope to be something like that in my life at something, it would be pretty cool to be really good at one thing and like, life in some sense is a search for the things that you could be that good at, I didn't even think about like how much money it doesn't make or any of that is, can I fall in love with something and make it a life pursuit where I can be damn good at it and being damn good at it is the source of enjoyment. Not not like um not to win because you want to win a tournament or win because uh like you just want to be better somebody else. No it's for the beauty of the game itself or the beauty of the activity itself. And then you realize that that's one of the compelling things about chess. It is a game with rules and you can win if you want to be really damn good in some aspect of life like that it's harder, it's harder and we're weirder pursuit. Don't [/INST] you feel like you kind of did that with computer science or ai related things like getting that level of damn good. </s>
<s>[INST] of the southern application. Like what do you like if you can comment? Uh I don't know if you're familiar or interested in space. What kind of A six. What kind of hardware is generally used these days for the to do the actual computation for the proof of work. [/INST] Sure. So in the case of Bitcoin and ethereum are a bit different. So in the case of Bitcoin there is an algorithm called shot to 56. It's just a hash function. And so the puzzle is just coming up with a number where the hash over the numbers below some threshold. And so because the hashes are designed to be random, you just have to keep on trying different numbers until one works. And the A six are just like specialized circuits that contain. And if circuits for evaluating this hash over and over again and you have like millions or billions of these hash evaluators, it's just stacked on top of each other inside of a box. And you just keep on running the box 24 7. </s><s>[INST] and the six, there's literally specialized hardware designed for this. Yes. This is living an amazing world. Another tangent. I'll come back to the basics but uh this quantum computing throw a wrench into any of this. [/INST] Very good question. So quantum computers have two main kind of families of algorithms that are relevant to cryptography. One is assures algorithm ensures algorithm is one that kind of completely breaks the hardness of uh some specific kinds of mathematical problems. So the one that you've probably heard of is it makes it very easy to factor numbers. So I figure out kind of what prime factors are the kind of that you need to multiply together to get some number. Even if that number is extremely big. Shore's algorithm can also be used to break elliptic curve cryptography. Um, it can break like any kind of hidden order groups. Like it breaks a lot of kind of cryptographic, nice things that we're used to. But the good news is that for every and of major use of uh things that shore's algorithm breaks, we already know of quantum proof alternatives. Now we don't use these quads improve alternatives yet because in many cases they're 5 to 10 times was efficient. But and the crypto industry in general kind of notice that this is coming eventually and it's kind of ready to take the head and switch to that stuff when when we have to the second algorithm that is relevant to cryptography is Grover's algorithm. And in Grover's algorithm might even be a more familiar to ai people that's basically usually described as solving search problems. But the idea here is that if you have a problem of the form, find a number that satisfies some property um then if with a classical computer you need to try and end times before before you find the number, then with a quantum computer, you only need to do a square root of n computations. And the Grovers could potentially be used for mining, but there's two possibilities here. One is that Grover's could be used for mining and whoever creates the first working quantum computer that could do Grovers will just mind way faster than everyone else and we'll see another round of uh what we saw when a six came out, which is the kind of the new hardware just kind of dominated the old stuff and then eventually it switched to a new equilibrium. But by </s><s>[INST] the way, way faster. Not exponentially faster. Radically fast. Radically faster. Which is not sort of uh It's not game changing, I would say it's like a six like you said, it [/INST] would be. Exactly yeah. So it would not necessarily break proof of work as of right now. The other kind of possible world right, is that quantum computers have a lot of overhead. There's a lot of complexity involved in maintaining quantum states. And there's also as we've been realizing recently, making quantum computers actually work requires kind of quantum error correction which requires kind of 1000 real cubits per logical cubit. And so there's the very real possibility that the overhead of running a quantum computer will be higher than the speed up you get with Grover's which would be kind of sad but which would also mean that given proof of work we'll just keep working fine. </s><s>[INST] So beautifully put. So so proof of work is the core idea of Bitcoin. Is there other core ideas before we kind of take a step towards the origin story and the ideas of ethereum. Is there other stuff that were key to the white paper of Bitcoin? [/INST] There is proof of work and then there's just the cryptography is just kind of public keys and signatures that are used to uh verify transactions. Those two of the big things. </s><s>[INST] So then what is um the origin story? Maybe the human side but also the technical side of ethereum. [/INST] Sure. So I joined the Bitcoin community in 2011 and they started by just writing, I first wrote for this sort of online thing called Bitcoin weekly. Then I started writing for Bitcoin magazine and uh </s><s>[INST] sorry to interrupt you have this funny kind of story true or not is uh that you're disillusioned by the downsides of centralized control. From your experience with, wow world of warcraft, is this truer you're just being witty, [/INST] I mean the event is true of the fact that that's the reason I do decentralization is witty. </s><s>[INST] Maybe just a small tangent. Do you have you always had a skepticism of centralized control? Is that has that feeling evolved over time or is that just always been a core feeling that decentralized control is the future of human society. [/INST] It's definitely been something that felt very attractive to me ever since I could afford that, such a figure as possible possible even. Yeah, </s>
<s>[INST] freedom, low taxes, all those kinds of things [/INST] that uh, Puerto rico stands for. It's uh, texas on the other hand, I know everyone in the squad </s><s>[INST] demise right texas. A compromise between those two. [/INST] Actually, I must say that everyone on the squad myself included loves texas. Uh, that there's no question about that. I know. Um Gordon? Loves it. Gary craig Nikki that everyone who comes here just loves texas that is incontestable. Um, of course in texas, there's many great cities. Austin is uh always been one of my favorites. I love Dallas, I love Austin. Um, and it has the advantages of better infrastructure as a, as a place to train. Um, it has a much higher population density so that you could get a larger number of prospective students and former larger squad. Um, it would uh, it would definitely be a fantastic place to, to open up a gym. Um, I couldn't give an answer off the top of my head, It would be a big move if we did make that move. But deep, the basic idea would be very agreeable to everyone on the team. I will say that. </s><s>[INST] Well, I'll just have to call my Russian connections to threaten the right kind of people. And uh I definitely would love the way you approach training, the way you approach to martial arts is uh it's something that uh that I deeply admire as a scholar of these arts. So it would be amazing if you do come here. But either way it would be amazing to train together. Let me ask a big, ridiculous question. What do you think is the meaning of this whole thing? We talked about at the beginning of the conversation about death and the fear of it. The other big question we ask about life is its meaning? Do you think there's a meaning to our existence here on this little spinning ball? [/INST] That's uh you throw in some some powerful questions. That's the most powerful. Well um for most of human existence the meaning of life was very very simple survival. The only thing that humans cared about was just surviving. Because it was so damn difficult for the early years of human existence on this earth. If you look in ourselves as biological agents, everything about our body is set up for one mission and that is survival. Every reflex. We have every element of our structure is just built up on the battle to survive. And then humans did something remarkable. They elevated themselves through the use of technology and social structure to the top of the food chain. Yeah, so they went from extremely, extremely vulnerable. If you take a a naked human being alone and put them in the Serengeti plains in africa they're in some deep shit, Okay, if you look at a human being as a survival organism just by itself naked, they among the most feeble at that task in the entire animal kingdom. Mhm. You compare us with predatory animals. We are weak and soft and easily killed. But if you take that same human and put them in a group and you give them basic technology, steel, a spear, a knife, he goes from the bottom of the food chain to pretty much at the top. And so humanity found itself in a crisis that emerged out of its own success. For most of its history. Their only interest was the battle to survive. And they did it. I don't know how they did it, but they did it, they got through ice ages, droughts, famines, disease, everything. And they found a way to get to the top of the food chain. And that's where it all got interesting because that organism whose only interest was in survival had for the first time in their history, a more or less guaranteed survival. And so the big question now is now, what we survived. There's no more danger. The average human being finds himself in a world now where there's almost zero danger from predatory animals. Where getting a meal is the easiest thing ever wait, getting to and from work, it's not problematic at all. Where the majority of infectious diseases, medical complaints can be resolved in a hospital fairly easily. Yeah. And so they start casting their mind around, okay, what do I do now? And so the minute mankind's existence became more or less guaranteed, the problems shift from survival to meaning. And we found ourselves grappling with a whole new issue that had never occurred to our ancient forefathers, but which now becomes one of the centerpieces of our modern lives. </s><s>[INST] I mean when you look at your own life, when you look back that you think I did a hell of a good job, You know, Hunter? S Thompson has this line that I often think about that 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 roadside in a cloud of smoke, thoroughly used up, totally worn out and loudly proclaiming, wow, what a ride! That's which is the complete opposite of survival or not complete opposite of survival, but basically embracing danger. Embracing risk going big. Just living life to the fullest. So within that context, what would make you proud of a life well lived? When you look back, you john Donna heart, looking back at your life [/INST] first, I will address that question. But let's first look at why hunter Thompson could say that because his life was more or less guaranteed and safe. If you look at animals in the animal kingdom, the pattern of their life is very simple, they take the least risk possible to secure their existence. Lions, powerful creatures. But when they go hunting, they typically go for the weakest animals they can kill in order to eat because they don't want to take the risk of injuring themselves knowing that if they do, they die. So the brute reality is the only people who can talk about having casual danger and their lives are those whose lives are guaranteed </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] to meta mathematics just [/INST] yet. We'll maybe get to math mathematics. But but it's it's uh so let me not let me explain the group ID and things later. But so let's come back to the universe. Um always a good place to be in. So, </s><s>[INST] so what does the universe has to do with the ruling, add the rubio space and how that's possible. We connected to why the thing exists at all and why there [/INST] is just one of them? Yes. Okay, So here's the point. So the thing that had confused me for a long time was let's say we get the rule for the universe. We hold it in our hand. We say this is our universe. Then the immediate question is, well, why isn't another one? And you know, that's kind of the, you know, the sort of the lesson of Copernicus is we're not very special. So how come we got universe number 312 and not universe quadrillion quadrillion quadrillion. And I think the resolution of that is the realization that there that the universe is running all possible rules. So then you say, well, how on earth do we perceive the universe to be running according to a particular rule? How do we perceive definite things happening in the universe? Well, it's the same story. It's the observer. There is a reference frame that we are picking in this rural space and that that is what determines our perception of the universe with our particular sensory information and so on. We are parsing the universe in this particular way. So, here's the way to think about it in in in physical space. We live in a particular place in the universe and you know, we could live in alpha centauri, but we don't, we live here. Um and similarly in rural space, we could live in many different places in real space, but we happen to live here. And what does it mean to live here? It means we have certain sensory input. We have certain ways to parse the universe. Those are our interpretation of the universe. What would it mean to travel in real space? What it basically means is that we are successively interpreting the universe in different ways. So, in other words, to be at a different point in real space is to have a different, in a sense, a different interpretation of what's going on in the universe. And we can imagine even things like an analog of the speed of light as the maximum speed of translation in real space and so on. So, </s><s>[INST] wait, what's the interpretation? So rubio space? And we I'm confused by the we and the interpretation and the universe. I thought moving about in real space changes the way the universe is is the way [/INST] we would perceive it, the way that </s><s>[INST] ultimately has to do with the perception. So it doesn't really rule real space is not somehow changing, like uh branching into another universe or something like that. [/INST] Just part of the point is the whole point of this is the rule EOD is sort of the encapsulated version of everything that is the universe running according to all possible. </s><s>[INST] We think of our universe, the observable universe as it's things. So we're a little bit loose with the word universe then, because wouldn't really add potentially encapsulate a very large number, like comment, Oh, really large, maybe infinite set of what we human physicists think of as universes. [/INST] That's an interesting, interesting parsing of the word universe, right? Because what we're saying is just as we're at a particular place in physical space where at a particular place in rural space for at that particular place in real space, our experience of the universe. Is this just as if we lived at the center of the galaxy, our universe, our experience of the universe will be different from the when it is given where we actually live. And so what we're saying is our when you might say, I mean, in a sense, this this really adds sort of a super universe, so to speak. Um, but it's all entangled together. It's not like you can separate out, you can say, let me it's like when we take a reference, okay, it's like our experience of the universe is based on where we are in the universe. We could imagine moving to somewhere else in the universe, but it's still the same universe. </s><s>[INST] So there's not like universes existing in parallel. [/INST] No, </s><s>[INST] because [/INST] because the whole point is that if we were able to change our interpretation of what's going on, we could perceive a different reference frame in this. Really odd. </s><s>[INST] Yeah, but that's not that's not that's just yeah, that's the same ruling ad that's the same universe. You're just moving about. This is just coordinates. [/INST] And so the way that's the reason that's interesting is imagine the extraterrestrial intelligence or the alien intelligence, we should say the alien intelligence might live on alpha centauri, but it might also live in a different place in real space. </s><s>[INST] It can live right here on earth. It just has a different reference frame that includes a very different perception of the universe. And then because that really all spaces very large, I mean, [/INST] do we get to communicate with them? </s><s>[INST] Right. That's yeah. But it's also well, one thing is how different the perception of the universe could be. [/INST] It could be bizarrely unimaginably completely different. And I mean, one thing to realize is even in kind of things I don't understand. Well, you know, I I I know about the kind of Western tradition of understanding, you know, science and all that kind of thing. You know, you talk to people who say, well, I, you know, I'm really into some, you know, Eastern tradition of this, that and the other and it's really obvious to me what, how things work. I don't understand it all, but you know it is not obvious I think with this kind of realization that there's these very different ways to interpret what's going on in the universe. That kind of gives me at least it doesn't help me to understand that different interpretation, but it gives me at least more respect for the possibility that there will be other interpretations </s>
<s>[INST] but it didn't really start out there because well, what what happened before [/INST] that? Well, we don't know. So this is where it gets into a lot of speculation. And </s><s>[INST] let's go, I mean, [/INST] let's go there. Okay, sure. So, you know, </s><s>[INST] nobody [/INST] Can prove what happened before T equals zero. And whether there are other universes out there. I like to say that these are sort of on the boundaries of science. They're not just ideas that we wake up at three in the morning to go to the bathroom and say, oh well let's think about what happened before the Big Bang. Or let there be a multiplicity of universes. In other words we have real testable physics that we can use to draw certain conclusions that are plausibility arguments based on what we know. Now, admittedly there are not really direct tests of these hypotheses. That's why I call them hypotheses. They're they're not really elevated to a theory because a theory in science is really something that has a lot of experimental or observational support behind it. So their their hypotheses but they're they're not unreasonable hypothesis based on what we know about general relativity and quantum physics. Okay. And they may have indirect tests in that if you adopt this hypothesis, then there might be a bunch of things you expect of the universe. And lo and behold that's what we measure. But we're not actually measuring anything at T less than zero or we're not actually measuring the presence of another universe in this multiverse. And yet there are these indirect ideas that stem fourth. So it's hard to prove uniqueness and it's hard to completely convince oneself that a certain hypothesis must be true. But you know, the more and more tests you have that it satisfies let's say there are 50 predictions it makes and 49 of them are in are things that you can measure. And then the 50th one is the one where you you want to measure the actual existence of that other universe or what happened before t equals zero and you can't do that. But but you've satisfied 49 of the other testable predictions. And so that's science right now. A conventional condensed matter physicist or someone who deals with real data in the laboratory might say oh you cosmologists. You know that's not really science because it's not directly testable. But I would say it's sort of testable but it's not completely testable. And so it's at the boundary. But it's not like we're coming up with these crazy ideas among them quantum fluctuations out of nothing. And then inflating into a universe with you might say, well you created a giant amount of energy but in fact this quantum fluctuation out of nothing. You know in a quantum way violates the conservation of energy. But you know who cares that was a classical law anyway. And then an inflating universe maintains whatever energy it had be at zero or some infinite sizable amount in a sense the stuff of the universe has a positive energy but there's a negative gravitational energy associated with him. It's like I drop an apple. I got kinetic energy energy of motion out of that. But I did work on it to bring it to that height. So by going down and gaining energy of motion positive 12345 units of kinetic energy? It's also gaining or losing depending on how you want to think of it negative 12345 units of potential energy. So the total energy remains the same and inflating universe can do that. Or other physicists say that energy isn't conserved in general relativity. That's another way out of creating a universe out of nothing, you know? But the point is that this is all based on reasonably well tested physics. And although these extrapolations seem kind of outrageous at first, they're not completely outrageous there within the realm of what we call science already. And maybe some young whippersnapper will be able to figure out a way to directly test what happened before to equal zero or to test for the presence of these other universes. But right now we don't have a way of doing </s><s>[INST] that. So, speaking of young whippersnappers, roger Penrose, Yeah. So he kind of has a, you know, idea that we there might be some information that travels from whatever the heck happened before the Big Bang is that isn't about it. So, do you think it's possible to detect something like actually experimentally be able to detect some I don't know what it is radiation. Some some sort [/INST] of the cosmic </s><s>[INST] microwave background radiation. [/INST] There may be ways of doing </s><s>[INST] that. But is it is it philosophically or practically possible to detect signs that this was before the Big Bang? Or is it or is it what you said? Which is like everything we observe will, as we currently understand, we'll have to be a creation of this particular observable universe. [/INST] Yeah, I mean, you know, if you it's very difficult to answer right now, because we don't have a single verified, fully, self consistent, experimentally tested quantum theory of gravity. And of course, the beginning of the universe is a large amount of stuff in a very small space. So you need both quantum mechanics and general relativity. Same thing if our universe re collapses and then bounces back to another Big Bang, you know, there's also ideas there that some of the information leaks through or survives. I don't know that we can answer that question right now because we don't have a quantum theory of gravity that most physicists believe in. And belief is perhaps the wrong word that most physicists trust, because the experimental evidence favors it, right? You know, there are various forms of string theory. There's quantum loop gravity. There are various ideas but which, if any, Will be the one that survives the test of time and more importantly, within that, the test of experiment and observation. So, my own feeling is probably these things don't survive. I don't think we've seen any evidence in the cosmic microwave background radiation of of information leaking through similarly. Um, the one way or one of the few ways in which we might test for the presence of other universes as if they were to collide with ours that would leave a pattern of temperatures signature in the cosmic microwave background radiation. Some astrophysicists claim to have found it, but in my opinion, it's not statistically significant to the level that would be necessary to have such an amazing claim. Right? You know, it's just a 5% chance that the microwave background had that distribution just by chance. 5% isn't very long odds if you're claiming that instead that you're that you're finding, you know, evidence from another universe. I mean, it's like if the large hadron collider people had claimed after gathering enough data to show the Higgs particle, when there was a 5% chance, it could be just a statistical fluctuation in their data. No, they required five sigma five standard deviations, which is roughly one chance in two million that this is a statistical fluctuation of no physical </s>
<s>[INST] Yeah, I would love, I would love to sort of interview and understand the lives of the folks that post that kind of stuff. I mean they're they're human beings. They have interesting journeys. Also I think they often don't realize. I think they don't realize their comment will be read by anybody, especially you they think like, and they also don't realize you're a human being. I feel like that's it's so interesting to watch it. Like some guy because I posted on twitter for like a minute, uh, that I'm talking to you and asking for questions. I deleted that tweet because [/INST] like </s><s>[INST] 95% of the people were talking about cheating talk about the cheating. All right, I got it. Thank you. This is not going to be helpful at all. So I was like, all right. But in that time, like there's one comment which I'm it's hilarious to me that you found that one comment. The one comment says like this seems like a waste of time or something. Like why lame guest [/INST] list. And </s><s>[INST] then used like responded something like with a question mark. [/INST] Yeah, I wanna </s><s>[INST] talk about this. [/INST] He responded, He responded even after you deleted this week. He said he doesn't know what value I would bring because I just make videos about chess games. And that's true. You've had some absolutely brilliant people on. But I also looked at this gentleman's profile and he his he was one of the folks that put things about his family and God and his politics in his twitter bio. And I started thinking maybe I said something in some video and I made a joke about religion or something. Just some offhand five second thing somewhere that someone turns me into just an absolute outcast in their household. They can no longer watch me. And that has happened. That has happened. I'll record a 30 minute video and I'll make a joke about something and some phrasing and that's it. I've lost the viewer forever. And they will let me know. They will write me an email and I just don't think people should be that serious. Yeah, there's </s><s>[INST] some of that because I'll I've seen people say that sometimes about me, but I see it more with others. They'll say, uh, you know, I used to be like, Joe Rogan gets this. Uh, I used to be a huge fan of joe Rogan until he said this, right. It's like one. Um, first I do wonder if you were ever really a big fan. That's that's one question mark I have, but the other is like, I think when you should be more lenient with each other in terms of how much stupid ship we say. And, and you know, if you actually, I wish people were able to sort of introspect on their own, on the own on the stupid ship, they say themselves like to have a little bit of empathy, like I wish there was a way to read all the emails you've ever written and just to see or maybe do a search engine for all the stupid shit you've said in emails in the past and like summarize it and to reveal it to yourself that, like, you have bad days, you have good days, you have emotional days. Uh you have stoic days, you have, sometimes you have like, uh you take very different political views than you do on other days, and it's like, it's all over the place. And if you're a creator, if you're putting stuff out all the time, you're gonna have those and you're you're still, you're still a full like complex bag of emotions and thoughts and ideas and contradictions and all that, like, you shouldn't judge a person by a single statement, and even when you do, you should try to infer the best possible interpretation of that statement. I feel like that that's just a healthier way to interact with the world and with other humans. It's like, I wonder what's the best possible interpretation of the thing they just tweeted or they said like what? Let's let's imagine that the person saying those words is actually a really good human being and what do they mean when they said that thing about anal beads so [/INST] good for so long. </s><s>[INST] Yeah, right? [/INST] Uh </s><s>[INST] or whatever it is, like, you know, they didn't mean to be offensive to the sexuality of a certain group, they're just talking about, they're talking about L. B. It's like they're not like sometimes it's humor, sometimes it's actually genuinely uh embodying like a political viewpoint and like walking with it thinking through it for a few days, like like taking it seriously empathizing not just for a brief moment, but for a time, like walking with an idea and allowing yourself to express it. Like playing Devil's. I do that all the time [/INST] with </s><s>[INST] myself in conversation. I do too, and I find I have to say I'm playing Devil's Advocate, like you have to be very explicit, but with myself, I'll just do it [/INST] in </s>
<s>[INST] Beautiful. [/INST] Whatever we'll do that normal price without any questions. Okay, okay, refill refill. You have to assume that you have never took it then. My </s><s>[INST] Okay. We talked about coming to, here's to you doing good three hours in. We talked about the journey to America a little bit but let's take a step back. It seems like an unlikely journey that has to do with a bunch of different factors. Ideas, hopes and dreams and goals and plans. Why did we move to America as a family. Can you tell the story? They're narrowly and broadly as does our big family. [/INST] That's a lot of details. A lot of like a interesting stuff which happened at the same time together. First of all, I was already in France most of time, which made situation easier to go to America, but absolutely significant role was played by captain's family. </s><s>[INST] What is the Kaplan's family? [/INST] Yeah, it is. Uh, </s><s>[INST] our last name is Friedman. [/INST] Yes, </s><s>[INST] picking attention. Yeah. What's, what's Kaplan? [/INST] It's a, it's the name of our, for your grand grandmother, yours, my grandmother, my great grandmother, your great grandmother. Right? So her name was epileptic and when her family came in America, they changed them to captains. Yeah. And uh it was forbidden to contact family </s><s>[INST] during the period to reach outside the country, the soviet union to. So there's this big family, we're not at that time, not big, but now big Kaplan family that came to the United [/INST] States. Yeah. And uh my father, he your grandfather had this interesting picture and without much hopes. He wrote a letter without speaking english. And you saw this letter where it is said like a jew newspaper. It's it the word jew was </s><s>[INST] G g G [/INST] E W newspaper, Cincinnati. That's it. America. And uh </s><s>[INST] well he got to his destination [/INST] and that's like a miracle that the letter came to destination. </s><s>[INST] It's interesting because the newspaper published the letter uh it's uh it's kind of America and that yeah, it's uh it's a miracle. So that started, they gave a catalyst. That was a catalyst. [/INST] It was a connection and just as a result, you know, we met and just uh and it was a catalyst for me to accept the position already from France position of a full professor in university of Illinois and Chicago. And that's actually how we moved to Chicago. </s><s>[INST] So did you ever think that you would come to America? [/INST] Honestly, no, even with my good friends, we were usually talking and my plans when I understand that it's better for a scientist to go like outside of the soviet union europe, then you would go to France and my choice was clearly friends. And we usually say that I spoke with Boris potemkin that I've always said that I will go to France. I said well and I want to go to yeah, to America well, but actually having all the way up. So </s><s>[INST] uh yes, okay, [/INST] I spoke way better french language. </s><s>[INST] Yeah. And I started taking french speaking french that there was, there was there was an alternate reality where we moved to France and I'm french and you're [/INST] french and chances for that. We're very </s><s>[INST] High 50 50 kind of thing. I remember there being is pretty certain that we're going to France. [/INST] Yeah, it was more than 50%. Yeah, because we have already, I mean it was very, very high chance you remember the picture I show you over there when we're with french people without being timid husky. If you remember, I just forever remember like I've been chilling husky, He loves you. He used to like, oh, he's alive. Yeah. And he plays very nice piano. It's a video, very nice people and </s><s>[INST] it's a different world of scientists. I mean, uh um, perhaps more pure in their pursuit of science, more support for the kind of labs and the spirit of the scientific process. It's uh, America's academic research system is a little bit more capitalistic I guess in a [/INST] American professor spends about 50% of time looking for funding </s><s>[INST] and they're a little bit more independent meaning their own little start up more, it's very difficult to do an institute and so on. Uh speaking of which I don't know how I forgot to mention, but the institute, you're, you've headed the Drexel than I am plasma institute for a long time [/INST] From 2002, </s><s>[INST] From 2002, what was that journey like of all the many brilliant people that have worked there through the years, All the different ideas. Having an institute in America is an interesting thing in itself, although what's the journey been like, [/INST] wow, it was very exciting and very challenging and I would say that I worked very hard, but I would say I was very much lucky that I was able to bring, who is me, A nice group of people um with a nester good cell polish nev and more recently originally chant and they need to bring in a lot now and I've been others, so it was a lot of people and they were good and it was a very nice feeling of how to say camaraderie, camaraderie and including including Greg who made a huge contribution to that enormous. Um so it is </s><s>[INST] like my brother, yep and I've been on the outside of that sort of looking in so I know a lot of these people uh there there's there's almost like a part of family. I know they're part of our story in America really and I know the [/INST] and we have a handsome and remember of uh nighttime plasma Institute. Yeah, go ahead. Don't be shy, no uh no, no fear, no fear. Don't be shy. Go ahead. </s><s>[INST] Np Np I did you write [/INST] that </s>
<s>[INST] are trying to sabotage it, where's the alignment? The challenge is, of course, is the system becomes more and more intelligent. It can escape the box of the objective functions and the constraints it's supposed to operate under. It's very difficult, as the more intelligent it becomes, to anticipate the unintended consequences of a fixed objective function. And so there'll be just, I mean, this is the sort of famous paperclip maximizer. In trying to maximize the wealth of a nation or whatever objective we encode in, it might just destroy human civilization. Not meaning to, but on the path to optimize. It seems like any function you try to optimize [/INST] eventually leads you into a lot of trouble. So we have a paper recently that looks at Goodhart's Law. Basically says, every metric that becomes an objective ceases to be a good metric. So in our paper, we're basically, actually the paper has a very cute title. It's called Death by Round Numbers and Sharp Thresholds. And it's basically looking at these discontinuities in biomarkers associated with disease. And we're finding that a biomarker that becomes an objective ceases to be a good biomarker. That basically, like the moment you make a biomarker, a treatment decision, that biomarker used to be informative of risk, but it's now inversely correlated with risk because you use it to sort of induce treatment. In a similar way, you can have a single metric without having the ability to revise it. Because if that metric becomes a sole objective, it will cease to be a good metric. And if an AI is sufficiently intelligent to do all these kinds of things, you should also empower it with the ability to decide that the objective has now shifted. And again, when we think about alignment, we should be really thinking about it as, let's think of the greater good, not just the human good. And yes, of course, human life should be much more valuable than many, many, many, many, many, many, many things. But at some point, you're not gonna sacrifice the whole planet to save one human being. </s><s>[INST] There's an interesting open letter that was just released from several folks at MIT, Max Tegmark, Elon Musk, and a few others that is asking AI companies to put a six-month hold on any further training of large language models, AI systems. Can you make the case for that kind of halt and against it? [/INST] So the big thing that we should be saying is what did we do the last six months when we saw that coming? And if we were completely inactive in the last six months, what makes us think that we'll be a little better in the next six months? So this whole six-month thing, I think, is a little silly. It's like, no, let's just get busy, do what we were gonna do anyway. And we should have done it six months ago. Sorry, we messed up. Let's work faster now. Because if we basically say, why don't you get a spot for six months, and then we'll think about doing something, in six months, we'll be exactly the same spot. So my answer is, tell us exactly what you were gonna do the next six months. Tell us why you didn't do it the last six months and why the next six months will be different. And then let's just do that. Conversely, as you train these large models with more parameters, the alignment becomes sometimes easier. That as the systems become more capable, they actually become less dangerous than more dangerous. So in a way, it might actually be counterproductive to sort of fix the March 2023 version and not get to experience the possibly safer </s><s>[INST] September 2023 version. That's actually a really interesting thought. There's several interesting thoughts there. But the idea is that this is the birth of something that is sufficiently powerful to do damage and is not too powerful to do irreversible damage. At the same time, it's sufficiently complex to be able for us to enable to study it. So we can investigate all the different ways it goes wrong, all the different ways we can make it safer, all the different policies from a government perspective that we want to in terms of regulation or not, how we perform, for example, the reinforcement learning with human feedback in such a way that gets it to not do as much hate speech as it naturally wants to, all that kind of stuff. And have a public discourse and enable the very thing that you're a huge proponent of, which is diversity. So give time for other companies to launch other models. Give time to launch open source models. And to start to play where a lot of the research community, brilliant folks, such as yourself, start to play with it before it runs away [/INST] in terms of the scale of impact it has on society. My recommendation would be a little different. It would be let the Google and the meta Facebook and all of the other large models, make them open, make them transparent, make them accessible. Let OpenAI continue to train larger and larger models. Let them continue to train larger and larger models. Let the world experiment with the diversity of AI systems rather than sort of fixing them now. And you can't stop progress. Progress needs to continue in my view. And what we need is more experimenting, more transparency, more openness, rather than, oh, OpenAI is ahead of the curve. Let's stop it right now until everybody catches up. I think that doesn't make complete sense to me. The other component is we should, yes, be cautious with it and we should not give it the nuclear codes, but as we make more and more plugins, yes, the system will be capable of more and more things. But right now, I think of it as just an extremely able and capable assistant that has these emerging behaviors, which are stunning rather than something that will suddenly escape the box and shut down the world. And the third component is that we should be taking a little bit more responsibility for how we use these systems. Basically, if I take the most kind human being and I brainwash them, I can get them to do hate speech overnight. That doesn't mean we should stop any kind of education of all humans. We should stop misusing the power that we have over these influencer ball models. So I think that the people who get it to do hate speech, they should take responsibility for that hate speech. I think that giving a powerful car to a bunch of people or giving a truck, or a garbage truck, should not basically say, oh, we should stop all garbage trucks because we can run one of them into a crowd, no, people have done that. And there's laws and there's regulations against running trucks into the crowd. Trucks are extremely dangerous. We're not gonna stop all trucks until we make sure that none of them runs into a crowd. No, we just have laws in place and we have mental health in place and we take responsibility for our actions when we use these otherwise very beneficial tools like garbage trucks for nefarious uses. So in the same way, you can't expect a car to never, you know, do any damage when used in, especially like specifically malicious ways. And right now we're basically saying, oh, well, we should have this super intelligent system that can do anything, but it can't do that. I'm like, no, it can do that, but it's up to the human to take responsibility for not doing that. And when you get it to like spew malicious like hate speech stuff, you should be responsible. </s>
<s>[INST] and yet another chapter of an amazing life. You love football, like, you meant you played football, What position did you play? Awesome. So, um maybe we can talk a little bit about your love of football and the fact that you are part owner of The Pittsburgh Steelers. So, I mean, where do we start to start at the beginning? Well let's start at the end. Why the Steelers? What attracted you to the uh first of all, I think not to be controversial, but one of the best uniforms in football in terms of just called the black and gold, just [/INST] decal only on one side. Yeah, it's great. Yeah, the helmet, look, I've bled black and gold since I was a little boy, I grew up in upstate new york and uh the first football game I ever saw was the Steelers in the Super Bowl is a really little kid and it just, I mean Jack Lambert and joe green and franco Harris and those guys were like came down from Olympia, the Mount Olympus or something. And I just was enamored with the team. And because we only had three channels, the only time I get to see him is occasionally when they were the game of the Week or something. Um and I just loved to me what they stood for the toughness and they played football, you know the way that I thought I thought was was great, It was a huge Jack Lambert fan, our Hall of Fame linebacker who just intimidated everybody. </s><s>[INST] So that was like the that was the decade of the steel curtain, like the, I mean arguably one of the great sort of defensive of in in in football history and also one of the greatest football teams period of in football history. [/INST] I've been a lifelong fan. Um and it was very fortunate to meet Mr Rooney. Uh the Rooney family started the team in 1933. Um got to know him and uh Just was asked to be part of the ownership group. I think it was the end of 2007 first year as part of the group in 2008 we won the Super Bowl and it was like beyond surreal and just beyond surreal. And um you know, it's it's ah it's amazing to be able to do. I mean, the the Rooney family is one of those most revered in sports or the way they conduct themselves. Um Mr Rooney uh passed away I think five years ago now and we lost him but was a champion, helped build the league. I mean, put the league as we know it together. More importantly, it was a civil rights champion, um who created what we now call the Rooney rule uh, to to make sure that we're being fair about giving minority coaches a chance to get hired and um just just as one of the most kind and amazing human beings I've ever ever met. </s><s>[INST] It's incredible what sport does um, like to bring out the best in people to give people hope to inspire people. There is something about football that um, has all the elements of a great sport. It's the teamwork, it's the sort of the combat aspect of it. It's like, it's the purity of it, It's uh of like strength and power and speed and all the elements of like last minute close calls required to to win the game. And uh where referee decisions of course, that's essential for a sport can screw up the whole thing. Just got all of it together, I think. Uh, just, I don't know, it gives the the drama and the triumphs are just beautiful. Like some of my favorite memories, I don't know if it's an accident or this is common with people is just with friends watching football and connecting over that. [/INST] Yeah, well, it's, look, it's an incredible game because there's nowhere to hide, right? You're out there on the field. It, you know, it's uh it's a great game that requires not only all those attributes that you said, but it's it's incredibly complex game. So if you don't know what you're looking at and you don't understand how complex defenses are trying to disguise what they're doing. Offenses are trying to overcome that and and you can set up one play the entire in the entire game. But a team that plays well together right knows their place inside and out, knows their assignments inside and out can overcome and beat a more physically gifted team because of that, you know, work that aspect of working together one of the things that I always loved about sports is just, you're out there, there's a set of rules and there's a scoreboard. So at the end of that game it says, and you can make excuses about the refs or this happened or that happened, but you know, at the end of the day, did you go out and compete and when you went out and were a competitor, how did it work out? Right? And, and the simplicity of that and the purity of that, um, is something that I always have been drawn to. </s><s>[INST] What about the business of sort of owning a team we're putting together a team or trying to like build up a team that's going to be a great team. Like what are some interesting aspects that people might not realize that you can carry over from all the other experience you have in business. [/INST] I think the hardest thing about professional sports right now, it's individuals getting paid money to, to play a sport, which is different than, it's certainly different than amateur. And, you know, the decisions that are hard is when you get to know somebody who's a player on the team and either there at the end of their career or you need to go in a different direction and that person who's done everything that you've asked, you know, whatever the coaches have asked of that person and you get close to them and then when they, when they have to be traded released or whatever happens, it's, you know, that's sad and being able to stand back and in some ways be dispassionate and not be a fan, right? There's a, um I'm on the Baseball Hall of Fame board and uh, one of the, the guys that's on the board of me is jerry Reinsdorf and I think it was jerry who said, you know, if if you act like a fan, you'll be sitting with him um which I thought was kind of funny, </s>
<s>[INST] And I think I've seen you, the writer talk about the demonstration of consciousness from a system like that from a system like Alexa or are a conversational agent. That is what you would be looking for is kind of at the very basic level for the system to have an awareness that I'm just a program and yet why do I experience this or not to have that experience but to communicate that to you? So that's what us humans would sound like if you all of a sudden woke up one day like Kafka right in the body of a bug or something. But in in a computer, you all of a sudden realized you don't have a body and yet you would, you're feeling what you're feeling, you would probably say those kinds of things. So do you think a system essentially becomes conscious by convincing us that is conscious through the words that I just mentioned so by being confused about the fact that why am I having these experiences? So basically I [/INST] don't think this is what makes you conscious. But I do think being puzzled about consciousness is a very good sign that the system is conscious. So if I encountered a robot that actually seemed to be genuinely puzzled by its own mental states and saying, yeah, I have all these weird experiences and I don't see how to explain them. I know I'm just a set of silicon circuits, but I don't see how that would give you my consciousness. I would at least take that as some evidence that there is some consciousness going on there. I don't think a system needs to be puzzled about consciousness to be conscious. Many people aren't puzzled by their consciousness. Animals don't seem to be puzzled at all. I still think they're conscious. So I don't think that's a requirement on consciousness. But I do think if we're looking for signs for consciousness, say in AI systems, one of the things will help convince me that ai system is consciousness if it shows signs of it shows signs of introspectively recognizing something like consciousness and finding this philosophically puzzling. And the way that uh, the way that we do, </s><s>[INST] It's such an interesting thought though because a lot of people sort of wood at the shallow level criticize the touring test or language that it's essentially uh, what I heard, like a dan Dennett criticize it in this kind of way, which is, it really puts a lot of emphasis on [/INST] lying and I'm being able to being able to imitate human beings. Yeah, there's this uh, there's this cartoon of the Ai system studying for the turing test. It's gotta read this book called talk like a human like man, we don't have to waste my time learning how to imitate humans. Maybe the Ai system is going to be way beyond the hard problem of consciousness and it's going to be the same. Why do I need to waste my time pretending that I recognize the hard problem of consciousness to uh in order for people to recognize me as conscious? </s><s>[INST] Yeah, It just feels like, I guess the question is, do you think there's uh, we can never really create a test for consciousness because it feels like we're very human centric. And so the only way we would be convinced that something is consciousness but is basically the thing demonstrates the illusion of consciousness that we can never really know whether it's conscious or not. And in fact that almost feels like it doesn't matter then, or does it still matter to you that something is conscious or demonstrates consciousness? You still see that fundamental [/INST] distinction to a lot of people weather system on is conscious or not matters hugely for many things like how we treat it, can it suffer and so on? But still that leaves open the question, how can we ever know? And it's true that it's awfully hard to see how we can know for sure whether a system is conscious. I suspect that sociologically the thing that's going to convince us that the system is consciousness in part, things like social interaction, conversation and so on. Where they seem to be conscious, they talk about their conscious states or just talk about being happy or sad or finding things meaningful or being in pain. That will tend to convince us if we don't, the system genuinely seems to be conscious. We don't treat it as such. Eventually it's gonna seem like a strange form of racism or species ism or somehow not to acknowledge them. </s><s>[INST] I truly believe that by the way, I believe that there is going to be something akin to the civil rights movement, but for robots. Um, I think the moment you have a Roomba say, please don't kick me. That hurts. Just say [/INST] it. Yeah, </s><s>[INST] I think that will fundamentally change the fabric of our society. [/INST] I think you're probably right, although it's going to be very tricky because to say where we've got the technology where these conscious beings can just be multi created and multiplied by the thousands by, by flicking a switch. So, and the legal status is going to be different, But ultimately the moral status ought to be the same. And yeah, the civil rights issue is gonna be a huge mess. </s><s>[INST] So if one day somebody clones you, another very real possibility. Um, in fact, I find the conversation between two copies of David Chalmers quite interesting. [/INST] Very thought, just who is this idiot? He's not making any sense. </s><s>[INST] So what, uh, do you think he would be conscious? [/INST] I do think he would be conscious. I do think in some sense, I'm not sure it would be me. There would be two different beings at this point. I think they both be conscious and they both have many of the same mental properties. I think they both, you know, we have the same moral status. It would be wrong to hurt either of them or to kill them and so on. Still, there's some sense in which probably their legal status would have to be different if I am the original and that one is just a clone then creating a clone of me, presumably the clone doesn't, for example, automatically own the stuff that I own or </s>
<s>[INST] to add to the list and before, you know, it time is up, just like it is for this conversation, but hopefully it was a fun ride was a huge honor demetrius as you know, I've been a, a fan of yours and a fan of google self driving car and way more for a long time. I can't wait. I mean, it's one of the most exciting if we look back in the 21st century, I truly believe it will be one of the most exciting things we descendants of apes have created on this earth. So I'm a huge fan and I can't wait to see what you do next. Thanks so much for talking to me. [/INST] Thanks thanks for having me. </s><s>[INST] And it's a [/INST] also a huge fan doesn't work honestly like and really enjoyed it. Thank you. </s><s>[INST] Thanks for listening to this conversation. Dmitri Dolgov and thank you to our sponsors trial Labs, a company that helps businesses apply machine learning to solve real world problems. Bling kissed an app I use for reading through summaries of books, better help online therapy with a licensed professional and 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 enjoyed this thing, subscribe on Youtube. Review five stars on Apple podcast, follow on Spotify, support on Patreon, connect with me on twitter at lex Friedman and now let me leave you with some words from Isaac Asimov Science can amuse and fascinate us all, but it is engineering that changes the world. Thank you for listening and hope to see you next time. [/INST] </s>
<s>[INST] And you were deeply involved with that [/INST] at the time. I was very much involved with that. I was like the lead architect, I ended up talking to people who had already developed serious third party libraries that did similar things and sort of taking ideas from them and getting their feedback on my design and eventually we put it in the standard library and after a few years I got distracted. I think the thing the big thing that distracted me was actually type annotations, </s><s>[INST] but [/INST] other people kept it alive and kicking and it's been quite successful actually in the world of python web clients. </s><s>[INST] So initially what are some of the design challenges there in that debate for the pep And what are some things that got rejected? What are some things that got accepted to stand out to you? [/INST] There are a couple of different ways you can handle parallel i O. And this happens sort of at an architectural level in operating systems as well, like Windows prefers to do it one way and UNIX prefers to do it the other way. You sort of you have an object that represents a network endpoint, say connection with a web browser that your client and say you're you're you're waiting for an incoming request. Two fundamental approaches are okay, I'm waiting for an incoming request. I'm doing something else. Come wake me up or of course sort of come tell me when something interesting happened like a packet came in on that network connection. And the other paradigm is we're on a team of a whole bunch of people with maybe a little mind and we can only manage one web connection at a time. So I'm just sitting looking at this this web connection and I'm just blocked until something comes in and then uh I'm already waiting for it, I get I get the data, I process the data and then I go back to the top and say now sort of I'm waiting for the next packet. Those are about the two paradigms. One is a paradigm where there is sort of notionally a threat of control, whether it's an actual operating system, thread or more an abstraction in, we call them tasks, but the task in a or a threat in other contexts is devoted to one thing and it has logic for all the stages, like when it's a web request, like first wait, wait for the first line of the web request parse it because then, you know, if it's a get or a post or put or whatever or an error, uh then wait until you have a bunch of lines until there's a blank line and parts that as heathers and then interpret that and then wait for the rest of the data to come in. If there is any more that you request, expect that sort of standard web stuff. And the other thing is, and there's always endless debate about which approach is more efficient and which approach is more error prone where I just have a whole bunch of stacks in front of me and whenever a packet comes in, I sort of look at the number of the fact that there's some number on the packet and I say, oh that packet goes in this pile and then I can do a little bit and then sort of that pile provides my context. And as soon as I'm done with the processing, I sort of I can forget everything about what's going on because the next packet will come in from some random other client and it's that pile, </s><s>[INST] this pile [/INST] uh and every time a pile is maybe empty or full or whatever the criteria is, I can toss it away or use it for a new space but several traditional third party libraries for asynchronous I o processing in python chose the model of a callback and that's that's the idea where you have a bunch of different stacks of paper in front of you and every time someone gives you a piece gives you a new sheet, you decide which stack it belongs to. And that leads to a certain style of spaghetti code that I find sort of aesthetically not pleasing. And I was sort of never very successful. And I had heard many stories about people who were also sort of complaining about that style of coding. It was very prevalent in javascript at the time, at least because it was like how the javascript event loop basically works. And so I thought well the task based model where each task has a bunch of logic. We had mechanisms in the python language that we could easily reuse for for that. And I thought I want to build a whole library for asynchronous networking i o uh and all the other things that may need to be done a synchronously uh based on that paradigm and so I just chose a paradigm and try to see how far I could get with that. And it turns out that it's pretty good paradigm. So </s><s>[INST] people enjoy that kind of paradigm programming for asynchronous io, relative to callbacks. Okay, beautiful. So how does that all interplay with the infamous guild, the go, the global interpreter lock, maybe can you say what the deal is and how does it dance beautifully with a sen ko [/INST] The global interpreter lock solves the problem that python originally was not written with either asynchronous or or parallelism in mind at all. There was no concurrency in the language, there was no parallelism, there were no threads, only a small number of years into python's initial development, all the new cool operating systems like uh Sun. Os and silicon graphics, I rex and then eventually pas IX and Windows all came with threading libraries that lets you do multiple things in parallel and there is a certain certain sort of principle which is the operating system handles the threads for you and the program can pretend that there are as many cpus as as there are threats in the program uh and those Cpus were completely independently and if you don't have enough Cpus operating system sort of simulates those extra Cpus on the other hand, if you have enough Cpus, you can get a lot of work done by deploying those multiple Cpus, but python wasn't written to to do that. Uh And so as libraries for for multi threading were added to C. But every operating system then there was adding their own version of that. We thought and maybe we were wrong, but at the time we thought, well we quickly want to be able to support these multiple threads Because they seemed at the time in the early 90s when they were new, at least to me, they seemed a cool, interesting programming paradigm. And one of the things that that python at least at the time felt was nice about the language was that we could give a safe version of all kinds of cool new operating system toys to the python programmer. Like, I remember one or two years before threading, I I had spent some time adding networking sockets uh to python and there were very literal translation of the networking sockets that were in the BSD operating system. So UNIX BSD But the nice thing was if you're using sockets from python, then all the things you can do wrong with sockets in C would automatically give you a clear error message instead of just ending up with a malfunctioning hanging program. And so we thought, well we'll do the same thing with threading, but we didn't really want to rewrite the interpreter to be threat safe because that that was was like there would be a very complex re factoring of all the interpreter code and all the runtime code because all the objects were written with the assumption that there's only one thread. And so we said, okay, well we'll take our losses will provide something that looks like threads and as long as you only have a single CPU on your computer, which most computers at the time did uh it feels just like threats because The whole idea of of multiple threats in the Os was that even if your your computer only had one CPU you could still fire up at many threads as you wanted. Well, within reason maybe 10 or 12, not 5000. Uh And so we thought we had conquered the the abstraction of threats pretty well because multi core Cpus were not in, in most python programmers hands anyway. And then of course a couple of more iterations of moore's law and computers getting faster. And at some point, uh the chip designers decided that they couldn't make the Cpus faster, but they could still make them smaller and so they could put multiple Cpus on one chip. And suddenly there was all this pressure about do things in parallel and that's where the the solution we had in python didn't work. And that's that's sort of the moment that the gill became became infamous because the guilt, the guilt was the solution, we used to sort of take this single interpreter and share it between all the different operating system threats that you could create. And so as long as the hardware physically only had one CPU that was all fine. And then as hardware offenders were suddenly telling us all, oh, you got to paralyze everything's got to be paralyzed. People started saying, oh but we can use multiple threads in python and then they discovered, oh, but actually all threats run on a single single core. </s>
<s>[INST] Oh, that makes a lot of sense. [/INST] Yeah, we use that for I may be both Shane and Peter think they invented the term. But then later after the book was published, this guy Mark Gubrid came up to me and he's like, well, I I published an essay with the term AGI in like 1997 or something. And so I'm just waiting for some Russian to come out and say they published that in 1953. But I mean, that term is not dramatically innovative or anything. It's one of these obvious, in hindsight things, which is also for sure. It's annoying in a way because, you know, Josh Habak, who you interviewed is a close friend of mine, he likes the term synthetic intelligence, which I like much better, but it hasn't, it hasn't actually caught on, right? Because, I mean, artificial is a bit off to me because art of artifies is like a tool or something, but, but not all AGIs are going to be tools. I mean, they may be now, but we're aiming toward making them agents rather than, than tools. And in a way, I don't like the distinction between artificial and natural, because I mean, we're we're part of nature also, and machines are part of, are part of nature. I mean, you can look at evolved versus engineered, but that's a different, that's a different distinction. Then it should be engineered general intelligence, right? And then general, well, if you look at Marcus Hutter's book, Universally, what he argues there is, you know, within the domain of computation theory, which is limited, but interesting. So if you assume computable environments, the computable reward functions, then he articulates what would be a truly general intelligence, a system called AIXI, which is quite beautiful. IXC. IXC, and that's, that's the middle name of my latest child, actually, is it? What's the first name? First name is Quarksey, Q-R-X-I, which my wife came out with, but that, that's an acronym for Quantum Organized Rational Expanding Intelligence. IXC. His middle name is, his middle name is X-X-Xiphanes, actually, which is a mean, means that </s><s>[INST] the former principal underlying IXC. But in any case, what's the first name? IXC. In any case, [/INST] you're giving Elon Musk a new child to run for. Well, I did it first. He copied me with this, this new freakish name. But now if I have another baby, I'm going to have to outdo him. It's becoming an arms race of weird geeky baby names. We'll see what the babies think about it, right? Yeah. But I mean, my oldest son, Zarathustra, loves his name, and my daughter, Charizard, loves her name. So, so far, basically, if you give your kids weird names, They live up to it. Well, you're obliged to make the kids weird enough that they like the names, right? It directs their upbringing in a certain way. But yeah, anyway, I mean, I mean, what Marcus showed in that book is that a truly general intelligence, theoretically, is possible, but would take infinite computing power. So then the artificial is a little off, the general is not really achievable within physics, as we know it. And I mean, physics, </s><s>[INST] as we know it may be limited, but that's what we have to work with now. Intelligence is a new freakish name. But now, it's becoming, what you're obliged to make. Infinitely general, you mean, like, yeah, information processing perspective, yeah. [/INST] Yeah, yeah, intelligence is not very well defined either. I mean, what does it mean? I mean, in AI now, it's fashionable to look at it as maximizing and expected reward over the future. But that's, that sort of definition is pathological in various ways. And my friend, David Weinbaum, aka Weaver, he had a beautiful PhD thesis on open-ended intelligence, trying to conceive intelligence in a... Without a reward. Yeah, he's just looking at it differently. He's looking at complex self-organizing systems and looking at an intelligence system as being one that, you know, revises and grows and improves itself in conjunction with its environment without necessarily there being one objective function it's trying to maximize. Although, over certain intervals of time, it may act as if it's optimizing a certain objective function. It's very much hilarious from Stan Slalom's novels, right? So yeah, the point is, artificial, general, and intelligence... Don't work. They're all bad. On the other hand, everyone knows what AI is. And AGI seems immediately comprehensible to people with a technical background. So I think that the term has served as sociological function. Now it's out there everywhere, which... It's stuck. Which baffles me. </s><s>[INST] It's like KFC without the depth of work. Yeah, he's... They're all bad. On the other... Yeah, it's stuck. Which baffles me. It's like KFC. I mean, that's it. We're stuck with AGI probably for a very long time, until AGI systems take over and rename themselves. [/INST] Yeah, yeah. And then we'll be biological. We'll start with GPUs too, which mostly have nothing to do with graphics anymore, right? </s><s>[INST] Biological. We'll start with... I wonder what the AGI system will call us humans. That was maybe... Grandpa. GPs. Grandpa processing unit, yeah. Biological grandpa processing units. Yeah. Okay, so maybe also just a comment on AGI representing before even the term existed, representing a kind of community. You've talked about this in the past, sort of AI is coming in waves, but there's always been this community of people who dream about creating general human level super intelligent systems. Can you maybe give your sense of the history of this community, as it exists today, as it [/INST] existed before this deep learning revolution, all throughout the winters and the summers of AI? Sure. First, I would say, as a side point, the winters and summers of AI are greatly exaggerated by Americans. And if you look at the publication record of the artificial intelligence community, since, say, the 1950s, you would find a pretty steady growth and advance of ideas and papers. And what's thought of as an AI winter or summer was sort of how much money is the US military pumping into AI, which was meaningful. On the other hand, there was AI going on in Germany, UK, and in Japan, and in Russia, all over the place, while US military got more and less enthused </s>
<s>[INST] So let me ask you about a deep psychological effect for you. There's also a drug of martyrdom. So whenever you stand against the flock, you wrote a couple of really good books on the topic, the most recent false alarm. I stand as the holder of truth that everybody who is alarmist is wrong. And here's just simple, calm way to express the facts of the matter. And that's very compelling to a very large number of people. They want to make a martyr out of you. Is that, are you worried about your own mind being corrupted by that, by enjoying standing against [/INST] the crowd? No, no, no. There's very little, I guess I can see what you're saying sort of in a literary way or something. There's very little comfort or sort of usefulness in annoying a lot of people. Whenever I go to a party, for instance, I know that there's a good chance people are going to be annoyed with me. And I would love that not to be the case. But what I try to do is, sorry, I try to be very polite and sort of not push people's buttons unless they sort of actively say, so you're saying all kind of stupid stuff on the climate, right? And then try to engage with them and say, well, what is it you're thinking about? And hopefully during that party and then it ends up being a really bad party for me. But anyway, so I'll end up passively convincing one person that I'm not totally stupid, but no, I'm not playing the martyr </s><s>[INST] and I'm not enjoying that. Yeah, still being poetic here. [/INST] That's so interesting. I mean, the martyr complex is all around the climate question. Michael Mann, at the far end of the spectrum of activism from where Bjorn is, was a climate scientist, is a climate scientist who was actively attacked by Inhofe and Virginia politicians and really abused in many ways. He had come up with a very prominent model of looking at long-term records of climate change and got this hockey stick for temperature. And he definitely sits there in a certain kind of spotlight because of that. So it's not unique at any particular vantage point in the spectrum of sort of prominent people on </s><s>[INST] the debate. Andrew, you co-wrote the book, The Human Planet Earth at the Dawn of the Anthropocene, which is the new age when humans are actually having an impact on the environment. Let me ask the question of what do you find most beautiful and fascinating about our planet Earth? [/INST] It'd be cheap to say everything, but just walking here this morning under the bridge over the Colorado River, seeing the birds, knowing there's bat colonies, massive bat and colonies around here that I got to visit a few years ago. I experienced one of those bat explosions. It's mind-blowing. I've been really lucky as a journalist to have gone to the North Pole, the camp on the sea ice with Russian help, a camp that was set up for tourists coming from Europe every year. There were scientists on the sea ice floating on the 14,000-foot deep Arctic Ocean, and I was with them for several days. I wrote a book about that too along with my reporting. I've been in the depths of the Amazon rainforest. When I was very young, I was a crew on a sailboat that sailed two-thirds of the way around the world. I was halfway across the Indian Ocean, again, in 14,000-foot deep water. There was no wind. This was way before I was a journalist, 22, 23 years old, and we went swimming. Swimming in 14,000-foot deep water, 500 miles from land, the Western Indian Ocean halfway between Somalia and the Maldives. Is it so mind-boggling, chillingly fantastical thing with a mask on, looking at your shadow, going to the vanishing point below you, looking over at the boat, which is a 60-foot boat, but it just looks like a toy, and then getting back on and being beholden to the elements, the sailboat heading toward Djibouti. Djibouti. Djibouti. </s><s>[INST] Djibouti. Djibouti. [/INST] Emanciti in the power of the elements. Oh, my God. Oh, my God. And then the human qualities are unbelievable. The Anthropocene, I played a bit of a role as a journalist in waking people up to the idea that this era called the Holocene in the last 11,000 years, since the last ice age, had ended. I wrote my 1992 book on global warming, thinking about all that we're just talking about, thinking about the wonders of the planet, thinking about the impact of humans so far in our explosive growth in the 20th century. I wrote that perhaps Earth scientists of the future will name this post-Holocene era for its formative element for us, because we're kind of in charge in certain ways, which is hubristic at the same time. It's like the variability of the climate system is still </s><s>[INST] profound with or without global warming. So this immense, powerful, beautiful organism that is Earth, all the different suborganisms that are on it. Do you see humans as a kind of parasite on this Earth? No, no. Or do you see it as something that helps the flourishing of the entire organism? No, no. That can. Can. Intelligence. Hasn't yet. I mean, the ability of the collective intelligence of the human species to develop all these kinds of technologies, and to be able to have Twitter to introspect onto itself, of who's [/INST] intelligence, of who's... I think we're doing a... In a way we are. It's catch-up. We're always in catch-up mode. I was at the Vatican for a big meeting in 2014 on sustainable humanity, sustainable nature, our responsibility. And it was a week of presentations by Martin Reiss, who's this famed British scientist, physicist who... Been on his podcast. Yeah, great. Well, he's fixated on existential risk, right? Yes, he is. So it was a week of this stuff. And it's... </s>
<s>[INST] no, that just helps me. It's actually bad. So uh and you've been incredible. Uh so I'm I'm learning like I'm afraid of conversation. This is even today, I'm terrified of talking to you. I mean it's it's something I'm trying to remove for myself. Uh there's a guy, I mean I learned from a lot of people, but really um it's been a few people who has been inspirational to me in terms of conversation, whatever people think of him, Joe Rogan has been inspirational to me because comedians have been to being able to just have fun and enjoy themselves and lose themselves in conversation. That requires you to be a great storyteller to be able to uh pull a lot of different pieces of information together, but mostly just to enjoy yourself in conversations and trying to learn that these notes are you see me looking down that's like a safety blanket that I'm trying to let go of more and more. Uh so that's that people love just regular conversation, that's that's what the structure is. Like whatever I would say, I would say maybe like 10 to like, so there's a bunch of you know uh there's probably a couple 1000 PhD students listening to this right now right and they might know what we're talking about but there is somebody I guarantee you right now in Russia, some kid who was just like just smoke some weed is sitting back and just enjoying the hell out of this conversation. Not really understanding, you kind of want some boston dynamics videos, he's just enjoying it. Um And I salute you sir. Uh No, but just like there's so much variety of people that just have curiosity about engineering, about science is about mathematics and and also like I should uh I mean uh enjoying it is one thing but also often notice it and inspires people to, there's a lot of people who are like in their undergraduate studies trying to figure out what uh trying to figure out what to pursue and though these conversations can really spark the direction there of their life and in terms of robotics, I hope it does because I'm excited about the possibilities for robotic springs on that topic. Um Do you have advice? What advice would you give to a young person about life? [/INST] A young person about life for a young person about life and robotics. </s><s>[INST] Uh It could be in robotics, it could be in life in general, it could be a career, it could be a relationship advice, it could be running advice just like there. Um That's one of the things I see you like to talk to like 20 year olds, they're they're like how do I how do I do this thing, what do I do? Um If they come up to you, what would you tell them? [/INST] I think it's an interesting time to be a kid these days. Everything points to this being sort of a winner. Take all economy and the like I think the people that will really excel okay in my opinion are going to be the ones that can think deeply about problems. Um You have to be able to ask questions actually and use the internet for everything. It's good for and stuff like this. And I think a lot of people will develop those skills. I think the leaders thought leaders, you know, robotics, leaders, whatever. I'll be going to be the ones that can do more and they can think very deeply and critically. Um and that's a harder thing to learn. I think 1 1 path to learning that is through mathematics through engineering. Um I would encourage people to start math early. I mean I I didn't really start, I mean I was always in the the better math classes that I could take but I wasn't pursuing super advanced mathematics or anything like that until I got to admit I think mitt let me up and uh really started the life that I'm living now. But yeah, I really want kids to, to dig deep really understand things, building things too. I mean pull things apart, put them back together. Like that's just such a good way to really understand things and expect it to be a long journey, right? It's a you don't have to know everything. You're never going to know everything. </s><s>[INST] So think deeply and stick with it. Uh huh [/INST] enjoy the ride but just make sure you're not. Yeah, just just make sure you're you're you're stopping to think about why things work. </s><s>[INST] It's true. It's it's easy to lose yourself in the in the in the distractions of the world. [/INST] We're overwhelmed with content right now, but you have to stop and pick some of it and really understand it. </s>
<s>[INST] to say really, probably implied biological life. [/INST] Right? Right. But </s><s>[INST] you're saying, I mean, we'll explore this more, but you're saying it's really a spectrum, and it's all just a kind of computation. And so it's a full spectrum. And uh we just make ourselves special by weaving a narrative around our particular kinds of computation. [/INST] Yes. I mean, the thing that I think I've kind of come to realize is, you know, at some level a little depressing to realize that there's so little that's deliberating. Well, yeah, but I mean, it's, you know, it's the story of science, right? In, you know, from Copernicus on it's like, you know, first we were like, convinced our planet's at the center of the universe. No, that's not true. Well, then we were convinced that something very special about the chemistry that we have as biological organisms. That's not really true. And then we're still holding out that hope, oh, this intelligence thing we have that's really special. Um I don't think it is, however, in a sense, as you say, it's kind of liberating for the following reason, that you realize that what special is the details of us, Not some abstract attribute, that we could wonder, oh, it's something else going to come along and also have that abstract attribute. Well, yes, every abstract attribute, We have something else has it. But the full details of our kind of history, of our civilization and so on. Nothing else has that. That's what, you know, that's our story, so to speak. And that's sort of almost by definition special. So I I view it as not being such a I mean I was initially I was like, this is bad, this is this is kind of, you know, how can we have self respect about, about the things that we do? Then I realized the details of the things we do, they are the story. Everything else is kind of a blank canvas. </s><s>[INST] So Maybe on a small tangent, you just made me think of it. But what do you make of the monoliths in 2001 Space Odyssey in terms of aliens communicating with us and sparking the kind of particular intelligent computation that we humans have? Is there anything interesting to get from that sci fi? [/INST] Yeah, I mean, I think what's what's fun about that is, you know, the monoliths are these, you know, 1 to 49 perfect cue Boyd things and in the earth for a million years ago, whatever they were portraying with a, with a bunch of apes and so on. A thing that has that level of perfection seems out of place. It seems very kind of constructed very engineered. So that's an interesting question. What is the, what's the techno signature, so to speak? What is it that you see it somewhere? And you say my gosh, that had to be engineered. Um Now the fact is we see crystals which are also very perfect and you know, the perfect ones are very perfect. They're nice polish leader or whatever. Um and so in that sense, if you say, well, it's a sign of sort of, it's a techno signature that it's a perfect, you know, perfect political shape, policy, federal shape, that's not true. And so then it's an interesting question. What what is the, you know, what is the right signature? I mean like, you know, Kaos, famous mathematician, you know, he had this idea, you should cut down the Siberian forest in the shape of sort of a typical image of the proof of the pythagorean theorem on the grounds that there's a kind of cool idea didn't get done, but you know, it's on the grounds that the Martians would see that and realized, gosh, there are mathematicians out there. Um It's kind of, you know, it's the in his theory of the world that was probably the best advertisement for the cultural achievements of our species. Um but you know, it's it's a it's a reasonable question. What do you what can you send or create that is a sign of intelligence in its creation or even intention in its creation? </s><s>[INST] You talk about if we were to send a beacon? Can you, what, what should we send is math? Our greatest creation is uh what is our greatest creation? [/INST] I think, I think and it's a it's a philosophically doomed issue. I mean in other words you send something, you think it's fantastic, but it's kind of like we are part of the universe. We make things that are, you know, things that happen in the universe computation, which is sort of the thing that we are in some abstract sense and sense, using to create all these elaborate things we create is surprisingly ubiquitous. In other words, we might have thought that, you know, we've built this whole giant engineering stack that's led us to microprocessors that's led us to be able to do elaborate computations. But this idea, the computations are happening all over the place. The only question is whether whether there's a thread that connects our human intentions to what those computations are. And so I think, I think this question of what do you send to kind of show off our civilization in the best possible way? I think any kind of almost random slab of stuff we've produced is about equivalent to everything else. I think it's one of these things where it's a non </s><s>[INST] romantic way of phrasing it, I just started to interrupt. But I just talked to uh Andrew in whose uh the wife of Carl Sagan. And so I I don't know if you're familiar with the Voyager. I mean she was part of sending, I think brain waves of, you know, [/INST] uh I want you to her. </s>
<s>[INST] okay. So to summarize them so well you brilliantly described, I just want to make sure we're keeping it went all over the place, you know, you didn't, you're, you're pretty on point. But so the first thing is basically, which is difficult. I wonder if we can break it apart a little bit is don't trust authority essentially keep asking why [/INST] be respectful without trusting authority. Right? </s><s>[INST] Right. Which is, and then the second thing is be the kind of person that others like training with her, like being around sort of uh being a good friend. So so many people just enjoy being around. So one is completely, which is, yeah, you're right, it's attention, which is like completely disrespect the, the way that things are done. So asking why constantly one of it is your own flaws and not understanding the fundamentals of what's being described. And then once you get good enough not understanding, um, like go in against the fact that the instructor doesn't understand [/INST] and my inability to understand what you're saying that doesn't invalidate it. And that's something like you mentioned, like mention keeping in mind our own flaws and then also again the flaws that any of us have is the instructor to your point and I guess I can speak to being kind of weird, I don't, you know, I like to sit in the corner, but um, so everyone's a little bit different, some people, you know, I wasn't terribly popular in high school, you know, like, and like high school very much, but anyway, you know, we're not gonna be rude to people though, it was never going to bully anybody if you said hello to me, I'd say hello back, I would hold the door for you if you walk by, you know, and I would just say like simple things like that, go a long, long, long way and I actually takes us back to our, um, to our social discussion where I'm like, oh man, how do I become great at jujitsu? It's like, we'll start by not pissing off this person who can beat the crap out of me and not disrespecting the person who is probably that the clear is the closest thing to a font of knowledge at that time for me. So, and then recognizing that I should do that for its own virtue because it's the right thing to do and I should try to treat people decently, but beyond that even selfishly, it's in my interest to do </s><s>[INST] that. But see the thing is, this is interesting is um, there's a culture in martial arts, the culture that I like where the instructor legitimately so carries aura of authority and it's not comfortable to really ask why I'm not, it's a skill to be able to have a discussion as a white belt, the black belt instructor of like why is it done this way? Like and saying why again? Like would I mean it's a skill to show that you're actually legitimately a curious and passionate and compassionate student versus like somebody who's just being an annoying dick who saw some stuff on youtube. There's a line between to walk there. I I just wondered because like it's the drilling thing and you know, I um for example, like in my and when, when I was coming out, there was so much emphasis placed on the closed guard for example, and you might, you might actually teach me now, I don't know. But to me it was like why do I need to master the close guard? Like why is the closed guard on top of the bottom? But the bottom really, this is the fundamental basics would you get? So [/INST] who decided that </s><s>[INST] my body is not? My body says this is wrong. I'm like this like I have short legs but doesn't even matter the length of legs. There's something about me that just, I don't understand how leverage here works for my particular body. So it's just, it's a feel thing to like, it feels like in my basic understanding of leverage and movement and timing and so on. It feels like there's certain like butterfly guard or even like half basically every guard except close guard. I can play, I can dance close guard feels like you're shutting down. Uh, like the play that [/INST] is that wrong or is that make sure that's what you want because that's almost like an innate characteristic of this guard position, but it's not sold that way. Hey, this is a good guard. It's like, hey man, here's a bow and arrow versus and you know how to use this thing right? Like make sure you're far away and like up on a hill or something because you can take that bone out, run up on something and try to use it. But if nobody told you not to do that and they told you it's foundational, its very foundation. It's very important </s><s>[INST] to everything else to [/INST] write, that's back to the shrimp ng thing. How many things are we taught that even if it's not, let's say itself is not a garbage thing might be effectively garbage. You could give me a Ferrari, but if I try to make it fly, it's not gonna work. If you're like, here's a plane, here's another plane, Here's another plane, Here's another plane. Here's a Ferrari. I'm like, oh, it must be a different type of plane. Like you could be forgiven for for leap if we're going there, you know, like maybe the wings come out or you just go fast enough, it's like a bullet, you can make these crazy leaps in your mind and people are doing that all the time. So if you don't provide the context for me or worse yet you provide improper context, like how, how much of a problem is that going to be? </s>
<s>[INST] this. I wonder was pronounced WsL is never actually pronounced the whistle. I like it. I have no [/INST] idea. But there have been things like that for longest seguin, for example, which is a wonderful collection of. Take all your favorite tools from UNIX and Linux and just make them work perfectly on Windows. And so that's a something that's been going on for at least 20 years if not longer. And I use that on my one remaining Windows machine uh routinely because it's for if you're doing something that is batch computing command suitable for command line, uh That's the right way to do it because the Windows equivalents are if nothing else not familiar to me, </s><s>[INST] but I should, I would definitely recommend to people to if they don't use sigma to try whistle. I I've been so excited that I could use bash you bash, write scripts quickly In windows, it's changed my my life. Okay. What's your perfect programming set up? What computer, what operating system with keyboard? What editor? [/INST] Yeah. Perfect. Is too strong a word. It's way too strong a word. Um What I used by default, I have a uh at this point a 13 inch Macbook Air which I use because it's kind of a reasonable balance of the various things I need. I can carry it around. It's got enough computing, Horse bar screens, big enough keyboards. Okay. Um and so I basically do most of my computing on that. Um I have a big Mac in my office that I use from time to time as well, especially when I need a big screen, but otherwise it tends not to be used as much. Um uh </s><s>[INST] editor [/INST] I use mostly SaM, which is an editor that rob pike wrote long ago at Bell Labs. And </s><s>[INST] that sarge interrupted. Does that proceed vis I does that post [/INST] it. Post dates both V. I. And E max. Um It is derived from rob's experience with E. D. E. N. V. I. </s><s>[INST] Um [/INST] that's the original UNIX editor. Oh wow. Dated probably before you were born. So </s><s>[INST] what's uh actually, what's the history of editors? Can you, can you briefly because this is your fat. I used imax, I'm sorry to say, I'm sorry to come out with that. But uh what's what's the kind of interplay there? So in [/INST] ancient, ancient times, like, call it the first time sharing systems. Going back to what we're talking about, there were editors. There was an editor on C T S. S that I don't even remember what it was called. It might have been edit um where you can type text, program text and it would do something or document text </s><s>[INST] and [/INST] save it. You could edit it usual thing that you would get an editor. Um and ken, Thompson wrote an editor called QED, which was very, very powerful. But these were all totally a command base. They were not most or cursor based because it was before mice and even before cursors because they were running on terminals that printed on paper. Okay. No, no CRT type displays, let alone L A D S. Um And so then when UNIX came along, ken took Q E D and stripped way way, way, way down. And that became an editor that he called A D. It was very simple, but it was a line oriented editor. And so you you could load a file and then you could talk about the lines, one through the last line and you could um, you know, print ranges of lines, you could add text, you could delete text, you could change text or you could do a substitute command that would change things within a line or within groups of lines. So you can work on the parts of a </s><s>[INST] file essentially. You know [/INST] you can work on any part of it the whole thing or whatever but it was entirely command line based and it was entirely on paper. Okay. Paper. And that meant that you changed. Yeah. Right. Real paper. And so if you change the line you have to print that line using up another line of paper to see what change caused. Okay so when when CRT displays came along then you can start to use cursor control and you can sort of move where you were on the screen in uh </s><s>[INST] without reprinting every printing. [/INST] And one of there were a number of editors there. The one that I was most familiar with and still use is V. I. Which was done by Bill Joy. And so uh that dates from probably the late 70s as a guess. And uh it took full advantage of the cursor controls. I suspected imax was roughly at the same time but I don't know I've never internalized imax. So so I use at this point I stopped using E. D. All I can um I use V. I sometimes and I use SAM when I can. </s><s>[INST] And SAM is available on most systems. It [/INST] Was it is available. You have to download it yourself from typically the Plan nine operating system distribution. It's been maintained by people there and so </s><s>[INST] I'll get home tonight. I'll try it. It's cool. It sounds it's uh sounds sounds fascinating although my love is with Lisbon imax have went into that hippie world of, I [/INST] think it's a lot of things. What religion were you brought up with? That's </s><s>[INST] true, that's right. Most of the actual programming I do is C. C plus plus and python. But my weird sort of my religious upbringing is in list. So can you take on the impossible task and give a brief history of programming languages from your perspective? [/INST] So I guess you could say programming languages started probably in what the late forties or something like that. People used to program computers by basically putting in zeros and ones using something like switches on a console. Uh and then or maybe holes in paper tapes, something like that. So extremely tedious, awful whatever. And so I think the first programming languages were uh relatively crude assembly languages. Where people would basically write a program that would convert Pneumonic, like add a. D. D. Into whatever the bit pattern was that corresponded to an add instruction. And they would do the clerical work of figuring out where things were. So you could put a name on a location in the program and the assembler would figure out where that corresponded to when the thing was all put together and dropped into memory. Um and early on. And this would be the late forties uh very early fifties there were assemblers written for the various machines that people used you may have seen in the paper just a couple of days ago, Tony Becker died. He did this thing in Manchester called the called Auto Code, a language which I knew only by name. Um, but it sounds like it was a flavor of assembly language sort of a little higher in some ways. Um, and it replaced the languages alan turing wrote, which you put in zeros and ones, but you put it in backwards order because that was a hardware worked very </s>
<s>[INST] wild is wild, isn't it as well how few people are funded? Yes. How much impact they have. Yes. Maybe that's a feature not a bug. I don't know, [/INST] maybe yes, exactly, at least early on like it. So I know, Yeah, </s><s>[INST] it's like olympic, athletes are often severely underfunded, but maybe that's what brings out the greatness. [/INST] Perhaps Yes, correct. Exactly. Maybe this is essential part of it because I do think about that in terms of, I currently have an incubator for open source startups, like what I'm trying to do right now is create the environment. I wish that existed when I was leaving academia with Numpy and trying to figure what to do. I'm trying to create those opportunities and environment so uh and that's just what drives me still is how do I make the world easier for the open source entrepreneur? Uh </s><s>[INST] let me stay, I mean, I could probably stand up, I have for a long time but um, this is fun question so Andrea apathy leads the Tesla autopilot team and he's also one of the most like legit programmers. I know it's like he builds stuff from scratch a lot and that's how he builds intuition about how problem works. He built it from scratch and I always love that. And the primary language he uses python uh, for, for the intuition building but he posted something on twitter saying that they got a significant improvement on some aspect of their like data loading, I think by switching away from np dot square root. So the Numpy is implementation of square root, two, math, a square root and then somebody else commented that you can, you can get even a much greater improvement by using the vanilla python, square root, which is like [/INST] Power 0.5. Power </s><s>[INST] 0.5. And it's fascinating to me. I just wanted to [/INST] uh so </s><s>[INST] that Absolutely, that was some shade throwing at some. [/INST] No, no. But also we're </s><s>[INST] talking about it's a good way to ask the trade, opportune usability and efficiency broadly in Numpy but also in these specific weird quirks of like a single function. [/INST] So, on that point, if you use a numpy math function on a scalar, it's going to be slower than using a python function on that scalar. But because the math object in Numpy is more complicated, right? Because you can also call that math object on a array. And so effectively it goes through a similar machinery. There aren't enough of the which you would do it. You could do like checks and fast paths. So yeah, if you're basically doing a list, if you run over a list, in fact, for problems that are less than 1000, even maybe 10,000 is probably if you're going more than 10,000, that's where you definitely need to be using a raise. But if you're less than that. And for reading, if you're doing a reading process and essentially it's not compute bound and I o bound. And so you're really taking lists of thousands of time than doing work on it. Yeah, you could be faster just using python straight up python, </s><s>[INST] but also, and then this is the society. And there's the fundamental questions when you look at the long arc of history, it's very possible that NP does grow is much faster. [/INST] It could be </s><s>[INST] so like in terms of like don't worry about it. It's the, the evils of over optimization or whatever, all the different quotes around that is uh, and sometimes obsessing about this particular little cork is not, is not sufficient [/INST] for somebody like if you're, if you're trying to optimize your path, I mean, agree premature optimization creates all kinds of challenges, right? Because now, but you may have to do it. </s><s>[INST] I believe the quote is it's through the vaults of all evils. Right. [/INST] Let's get news. I think somebody else </s><s>[INST] he's, well, doc news is kind of like Mark Twain people just attribute [/INST] it's fine because brilliant. So no, I was a low tech user myself and so I have a lot of respect and he did more than that of course. But uh, yeah, someone I really appreciate in the computer science space. Yeah, I don't, I think that's appropriate. There's a lot of little things like that where people actually, if you understood it, you go. Yeah, of course. That's the case. Like the other part, the other part I didn't mention and number was a thing we wrote early on and I was really excited by number because it's something we wanted was a compiler for python syntax and I wanted it from the beginning of not writing numpy because of this function question like taking the power of a raise is really that you can write functions using all of it. It has implicit looping, right? So you don't worry about this in dimensional four loop with four loops for four statements you just say big four dimensional array. I'm gonna do this operation, this pluses minuses reduction and you get this is called victimization in other areas but you can basically think at a high level and get massive amounts of computation done with the added benefit of oh it can be paralyzed easily. It can be put in parallel. You have to think about that. In fact it's worse to go d composure. You write the four loops and then try to infer parallelism from four loops. That's actually harder problem than to take the array problem and just automatically paralyzed that problem. That's what And so functions in umpire called universal functions you funk. So square root is an example of a you think there are other sign co sign ads attract in fact one of the first libraries to cyp I was something called special where I added vessel functions and all these special functions that come up in physics and I added them as you funk. So they could work on a race. So I understood you thanks very very well from day one inside of America was one of the things we tried to make better in numpy was how do they work? Can they do broadcasting? What is broadcasting mean? But one of the problems is okay, what do I do with a python scalar? So what happens? The python scalar gets broadcast to a zero dimensional array, and then it goes to the whole state machinery as if it were a 10,000 dimensional array. And then and then and then it kind of unpacks the element and then does the addition. That's not to mention the function that calls in the case of square root is just to see live square root. Right? In some cases like python's power, there's some optimizations are doing for that. That could be faster than just calling to see lab square root </s>
<s>[INST] Yeah, there is the degree to which America is still the beacon of these ideas on which the country was founded and it's been able to live out in better and better forms, sort of live out the actual ideals of the founding principles versus [/INST] with the desire to improve, imperfect union. </s><s>[INST] Yeah. Well, as I generally have hope that people want to sort of, in terms of gratitude, people are aware how good it feels to be grateful. Um it's a better life psychologically, the resentment is a thing that destroys you from within. So I just, I feel that people will long for that and we'll find that that's that's the american way some of the division that we reveal now has to do with new technologies, like social media, that kind of is a small kind of deviation from the path we're on, because it's a new, we got a new toy, just like nuclear weapons, [/INST] which is relatively new. Um but we need to find reasonable attitudes towards these things and that's why I say, like it matters how you and by feedback on social media, because we were all going through it to some </s><s>[INST] extent, [/INST] and we're learning and we've got to learn how to do this without going mad. You know, I say, this was my, my minimalist call two friends in this era was the main job is not to go insane. Yeah. </s><s>[INST] Yeah. And yeah, like walk towards sanity, because, you know, I'm sure there's a hunter? S Thompson quote in there like insanity and the weekends can be at least fun. [/INST] Okay, do </s><s>[INST] you have advice for young people? Uh they just put down their Tiktok and are listening to this podcast in high school and college about how to have a career, how to have a life that can be part of [/INST] so april question. But uh of course, I mean I can give specific advice for people who want to be writers and so on. But that's a bit niche. Maybe. Um </s><s>[INST] writers will be very interesting. Sorry to interrupt. Also how to put your ideas down on paper and ideas develop them and have the guts to, to go to a large audience, especially when the ideas are sort of controversial or dangerous or difficult. [/INST] The main thing to do is to breed. When I was a schoolboy, I ever have a book in my pocket side pocket of my jacket on his side pocket and would read. And that wasn't just as I was Scottish in some way, but because I discovered probably at some point in my early teens I discovered something I wrote about this one, I discovered the books were dangerous, </s><s>[INST] which was a [/INST] thrilling discovery. Um I discovered that they could contain anything and also people didn't know what you were reading. Remember I get far too young an age I read the doors of perception of Aldous Huxley and I didn't make head or tail of it probably, but I knew that it was about something really interesting and dangerous and I thought constantly when I read poetry or read history, I was just constantly thrilled and wanted to know more. And and if you want to become a writer, you you have to be a reader. Um and you have to read the best staff. Um and and you know, obviously people disagree or agree on what that is and you'll find the people that really impress you. But I know I just came across certain writers who just knocked me off my feet. Um and when you find those people read everything and cling on to them and find other people like that, find other writers like that, people who are connected by history or scholarship or circles or whatever </s><s>[INST] for you. Was it fiction or nonfiction? Is there a particular books that you just remember or just give you pause? Well, [/INST] I remember that the first book that absolutely threw me was The Lord of the Flies by William Golding, which used to be a sign text and everyone's a bit snotty about because it's so popular. Um But I was thrown because I think it was the first adult book I read in that I had been used to the world of Children's literature of everything ends up fine in the end. The lost all get found. You know, this was the first book I read where that's not the case the world turns out differently. And I remember for days afterwards I was just in a state of shock. I couldn't believe what I just discovered. And partly because I sort of intuitive, it must be true. And of course that is not to say that the Lord has lots of scholarship on what Children do in the situation of being on the island when they do congregate and anyhow. But yes, that was a sort of introduction to the adult world. And it was shocking and thrilling. And um and I wanted more of it. Um it </s><s>[INST] was dangerous and [/INST] it was dangerous. And then of course when I became interested in sex alone, I realized I was gay. I write books for a very, very good way to learn about what I was and that was even more dangerous in a way. And I thought nobody knows what I know and you </s><s>[INST] discovered sex that was an invention in books. You [/INST] know what I mean? Nobody, No, no, no, no. What I mean is that is that one of the things that gay people have when they're growing up is it you have this terribly big secret and you don't think the world will ever know, you hope the world will never know. And um It's been called by one psychologist, the little boy with a big secret. And so if you discover that other people have the same secret, there's a sort of thank God for that. Um but I mean that's just a version of what everybody gets in reading in a way, which is the thrill of discovery that somebody else thought something you thought only you thought, I mean one of the grass, one of the greatest thrills in all of literature is when a voice comes from across the centuries and seems to leave a handprint, </s>
<s>[INST] ideas are allowed to clash. Especially in the structure of a university where at least I would say there's some set of rules, some set of civility. I think I would rather read Mein Kampf to understand people that hate. There is also a quality to disagreement that we should strive for, and I think a university is a place where when disagreement and even hate is allowed, [/INST] it's done in a high effort way. You know, somebody asked me once about what books I would want to have as required reading in literature courses, and I listed Mein Kampf, and they were horrified, and I said, well, it's one of the most important books of the 20th century. I mean, six million Jews died, an enormous number of other people died, because one guy wrote a book called Mein Kampf and took it seriously. It's one of the most important books ever written. How can an educated person not have at least breathed through Mein Kampf? It's not a great read, though. It's not a great read. He was not a great writer, but you do get a </s><s>[INST] sense for the sociopath that was Adolf Hitler. Yes, because he really acted on the words that he wrote, and it was there, and if people took that work [/INST] seriously, they would have understood. It's one of the most important books of the 20th century, and it's politically incorrect to read it. </s><s>[INST] It's crazy. But can you speak to the efforts to increase diversity in universities, which I think is embodied in this DIE effort of diversity, inclusion, [/INST] and equity programs? Where do they go right? Where do they go wrong? Okay, let me tell you, first of all, this may surprise a lot of people. I am opposed to affirmative action, and I think that what it does is it labels people by their race, by their religion, and by their national origin. Precisely what we don't want people to do is be pigeonholed in those categories. The reason that affirmative action has become the way that universities decide on who gets admitted is because historically people in what's called marginalized groups, blacks, gays, Hispanics, have been discriminated against in the admissions process. Now, what I have suggested is that instead of affirmative action, and by the way, here's a prediction. The Supreme Court is going to abolish affirmative action. There's a case pending, a Harvard case. There were two cases joined together, one of a public university and one of a private university. The private university is Harvard. I predict that the Supreme Court will vote 6-3 to abolish affirmative action. It is on its face. It is a violation of equal protection of the law. Some groups are favored because of race or ethnicity. It is a classic violation of equal protection clause. When affirmative action was approved, the deciding vote was Justice Sandra Day O'Connor. She wrote a very famous opinion in which she said, I am hesitate to vote to keep up to affirm the notion of affirmative action because it's such an obvious violation of equal protection. But we have an urgent problem in the society. We are not educating our members of racial and ethnic minorities and we have to try to get them into our colleges. So I think it should be approved for 25 years and it should be, in 25 years, it should have performed its role. Well, it hasn't and the 25 years is coming up. I think it's three or four years left. The Supreme Court is going to abolish it. You can take my word for that because it is such an obvious violation of equal protection. Why do the affirmative action come into play? Because the secondary and elementary schools are so bad. Public secondary and elementary schools are so bad. Why are they so bad? Partly because of the control that the teachers union has. Randy Weingarten runs the public school system in the United States and what I have suggested is that the effort should be to, this is an emergency, it's a national emergency, to improve the quality of elementary and secondary education and one way to do it is to hire teachers who are fabulous teachers rather than necessarily members of the union. I have come to oppose public workers unions. I am a very strong supporter of unions in the private sector. Why do I think there's such a difference between unions in the public sector and the private sector? In the private sector, management is arguing, bargaining with its own money and with the money of shareholders. In the public sector, there's only one side. There is the teachers union and then there's a school committee that is dealing with the taxpayers money, not their own, and so it's a very skewed power balance. So as supportive as I am of private sector unions, I am in an opposition of public sector unions. They're very destructive and I think without the teachers union, teachers who are really skilled will be able to get jobs. They would not have to worry about the seniority of teachers who long since have given up really creative teaching and we have to improve the public educational system. My late wife and I had a classmate. We have a son who's now 44 who went to the public schools in Cambridge. He has a friend, first name Eugene, who was black kid from Roxbury whose mother understood that the schools in Roxbury were terrible. The schools in Cambridge were pretty good. He lived in our house Monday to Friday and he went to school with Isaac in the Cambridge Public Schools. Elsa and I would show up the school committee meetings when there was bargaining between the teachers union and the school committee. The teachers union objected to our being there. We argued with taxpayers. We have a kid in the school and we have his best friend lives with us and goes to school with them. We have a real interest and the school committee walked out of the bargaining session. The city council then reconsidered his vote and they voted that citizens, taxpayers, parents of kids in the school could not show up to these negotiation sessions. I thought that was absolutely outrageous, but I understood why because these contracts are crazy. No sane municipality should enter into some of these contracts. I have become an opponent of the National Teachers Association, the Cambridge Teachers Association. I don't think there should be unions for public employees because there's no real bargaining going on. I think that the public school system will never be improved as long as the teachers are </s>
<s>[INST] It's the best way to support this podcast. We've got notion for startups express VPN for privacy. Rocca for style on it for supplements and indeed for hiring, choose wisely my friends and now onto the full ad reads as always no ads in the middle. I try to make this interesting but if you skip them, please still check out our sponsors. I enjoy their [/INST] stuff. Maybe you will </s><s>[INST] too. This show is brought to you by notion, a note taking and team collaboration tool. It combines note taking, document sharing, wikis, project management and much more into one space that's simple, powerful and beautifully designed. A lot of people care a lot about note taking and talk to me a lot about it. You know, I started back in the old school days of imax and vim. Imax was my weapon of choice. But now in the modern day in the 21st century, you've got to be using the best tools for note taking uh way better way fancier than the old school imax. Although I should say imax still has a purpose and what everybody recommends what all the cool kids recommend if you look at like what the top recommendation is for note taking is going to be notion. Now notion also wants me to tell you not just about their note taking, but the fact that it's awesome for startups, it's like operating system as they say for running every aspect of the company as it grows notion is running a special offer just for startups, you get up to $1000 off of notions team plan by going to notion dot com slash startups to give you a sense. That's almost a year of free notion for a team of 10 go to notion dot com slash startups. That's notion dot com [/INST] slash startups. </s>
<s>[INST] why like why would you say that [/INST] because of that propaganda? Because I think a lot of the problem for a certain type of mentality is Hitler didn't mass murder equally. So as long as you're killing just one group, it's a problem. But if you're murdering everyone equally all of a sudden it's like, what are you going to do? So the fact that you were saying the whole time or is not common knowledge, the fact that mouse 50 million dead are not common knowledge and Richard Nixon can be raising a glass to him in china. These are things that I think the West has not done a good job, reconciling </s><s>[INST] knock knock, [/INST] who's there </s><s>[INST] frank frank? Who frank you for being my friend Michael [/INST] and the heart attacks will say frank you for being my friend. </s><s>[INST] You got to do like this. Alright, yeah, okay. Not back to Hitler. Do you think Hitler could have been uh stopped? We kind of talked about it a little bit in terms of how to what is the brave thing to do in the time of Nazi Germany? But do you think, I mean, I'm not even gonna ask about Stalin in terms of Stalin had been stopped because they're probably the answer is there's no, but on the Hitler side, because Hitler had been stopped. [/INST] I think a lot of these things, a lot of luck has to play with it. He was almost assassinated. Um if you mean by like the West, it's very hard. I mean, </s><s>[INST] yeah, by the german people to, I mean, it could, like, if we're politically speaking, there was a rise to power through the thirties through the twenties really? I mean like can whoever, it's not about Hitler, it's about that kind of way of thinking that totalitarian control that always leads to trouble? Uh, sometimes the mass scale could that have been stopped in Germany or maybe in the soviet union, [/INST] I think this is one of the best arguments against radicalization in the States, which is how do you engage When you have like 30% of population who are members of a party which is dedicated to systemically overthrowing the existing democracy Stalin gave orders that the communists who had a pretty sizable um population, the Reichstag that their target shouldn't be the nazis, but the liberals and the social democrats, and they invented the term social fascists for them. So instead of there just like, like jihadis, instead of taking their sights on nazism, they set their sights on the moderates because they wanted they figured the choice between Hitler and us, we're going to win. And this was a huge gamble and they were all killed or had to flee and the ones who fled were killed also by Stalin. So, to my understanding, so this is a easy way where he could have been uh certainly heavily mitigated. </s><s>[INST] What about France and England that it was obvious that Hitler was lying and they wanted peace so bad that they were willing to put up with it, even after Czechoslovakia, like, like this is the anti pacifist argument, which is like they should have threatened military force more. [/INST] But then the other anti the anti anti pacifist argument is if you're going to remember Barack Obama had that the red line, if you cross this red line in Syria, we're going to go in and assad whatever is like, yeah, cool. And he's like, okay, well, sorry. So, if you're threatening force, there's a great song lyric, uh uh don't show your guns unless you intend to fight, right? So, if it's very clear with with free countries through what's in the press, whether the institutional will is there to follow through on these threats. So, I think you have been very hard for Chamberlain to rally the british people to take on Hitler just after the great I mean, the suffering that Britain's took the great War, they still, you know, obviously it means so much more of them than it does to us in the west. </s><s>[INST] What about what do you make of Churchill then? Like, why was Churchill able to rally the british people? Why was he uh like, do you give much credit to Churchill for being one of the great forces in stopping Hitler in World War Two? [/INST] I don't think that's really in dispute. Um I think he was very much regarded as this kind of the right man at the right time. Um and I think Chamberlain took a gamble. He the expression peace in our time was neville Chamberlain when he signed the peace with Hitler, and he goes, we now have peace in our time, now, go home and get a good night's sleep, that's what he said, because he's like, all right, you know, he's going to stop here and it's not impossible that if you just gave him, like if you gave Saddam Hussein kuwait, it's not impossible that he's not gonna, you know, invade Saudi Arabia next, something like that. </s><s>[INST] Let's see. Okay. But everything I've read, it's like of course there's there's uh it's not impossible, but when you're in the room with Hitler, you should be able to see like man to man. Like, like to me, a great leader should be able to see past the facade and see like, like yes, everything in life is a risk, but it seems like the right risk to take with Hitler. Like it's surprising to me, I know there's charisma but it's surprising to me, people did not see through this facade. [/INST] I I really hate the idea of hindsight and everything being 2020 and I think it's a very good idea. Generally not speaking, generally not in this specific instance to give our ancestors more credit than they than than we tend to give them because people often, here's a great example from another context which is lightning rods. People always talk about religious people being stupid and superstitious and they weren't, they often were very well reasoned an example of this is lightning rods, which is every year, whatever town the church was the tallest building and that's the one that always got hit by lightning and got caught on fire now what? It's a coincidence that it's always the church, like that makes logical sense that there didn't realize, Well, it's because the tallest and therefore that attracts electricity. And in fact when they invented lighting rods, this is a controversy because it's like, well, how is God going to show his displeasure if now is striking this lightning round, not burning down the church? So, a lot of times things are a lot more coherent than we give them credit for. And again, Chamberlain didn't he's the head of the parliamentary party. Um so he does not have the freedom in a sense that Hitler would to be like, all right, we're doing this again, boys. We don't know what it's like in a room with Hitler. Come on. That's that's we really have no idea. </s>
<s>[INST] is more stringent, yeah. The configuration of the plasma, sorry. Are tokamaks by far more popular [/INST] for research and development currently than stellarators? Of the concepts which are there, the tokamak is by far the most mature in terms of its breadth of performance and thinking about how it would be applied in a fusion energy system. And the history of this was that many, in fact, you asked if we go back to the history of the plasma and fusion center. The history of fusion is that people, scientists had started to work on this in the 1950s. It was all hush hush and cold war and all that kind of stuff. And it's like they realized, holy cow, this is really hard. We actually don't really know what we're doing in this because everything was at low temperatures, they couldn't get confinement. It was interesting. And they declassified it and this is one of the few places that the West and the Soviet Union actually collaborated on was a science. Even during the cold war. Even during the middle of the cold war, it was really, and this actually perpetuates all the way till now for we can talk about the project that that is sort of captured in now. But, and the reason they declassified it is because like everything like kind of like sucked basically about trying to make this confinement in high temperature plasma. And then the Russians, then the Soviets, came along with this device called a Tokamak, which is a Russian acronym, which basically means magnetic coils arranged in the shape of a donut. And they said, holy cow, like everyone was stuck at like a meager like half a million degrees, half a million degrees, which is like infusion terms of zero basically. And then they come along and they say, oh, we've actually achieved a temperature 20 times higher than everybody else. And it's actually started to make fusion reactions and everyone just go, oh, you know, no way. It's just hype from the, it's like, there's no way because we failed at this. It's a great story in the history of fusion is that then, but they insisted said, no, look, you can see this from our data. It's like, this thing is really hot and it seems to be working. This is, you know, late 1960s. And there was a team that went from the United Kingdom's fusion development lab and they brought this very fancy, amazing new technology called a laser. And they use this laser and they shot the laser beam like through the plasma. And by looking at the scattered light that came from the, they go, basically the scattered light gets more broadened in its spectrum if it gets hotter. So you could exactly tell the temperature of this. And even though you're not physically touching the plasma, it's like, holy cow, you're right. It is like, it is 10 million degrees. And so this was one of those explosions of like everyone in the world then wanted to build a token back because it was clearly like, wow, this is like so far ahead of everything else that we tried before. So that actually has a part of the story to MIT in the Plasmas infusion center was, why is there a strong fusion in a major fusion program at MIT? It was because we were host to the Francis Bitter Magnet Laboratory, which is also the National High Field Magnet Laboratory. Well, you can see where this goes, right? From this, you know, and we're kind of telling the stories backwards almost, but you know, the advent of a tokamak along with the fact that you could make very strong magnetic fields with the technology that had been developed at that laboratory, that was the origins of sort of pushing together the physics of the plasma containment and the magnet technology and put them together in a way that I would say is, you know, a very typical MIT success story, right? We don't do just pure science or pure technology. We sort of set up this intersection between them. And there were several pioneers that of people at MIT, like Bruno Coppe, who's a professor in the physics department and Ron Parker, who was a professor in electrical engineering and nuclear engineering. It's like even the makeup of the people, right, has got this blends of science and engineering in them. And that's actually was the origin of the Plow Science and Fusion Center, was doing those things. So anyway, so back to this. So why, so yes, tokamaks have been, have achieved the highest in magnetic fusion by far, like the best amounts of these conditions that I talked about. And in fact, pushed right up to the point where they were near QP of one. </s><s>[INST] They just didn't quite get over once. Even during the Cold War. So can we actually just linger on the collaboration across different nations? Just maybe looking at the philosophical aspect of this. Even in the Cold War, there's something hopeful to me besides the energy that these giant international projects are a really powerful way to ease some of the geopolitical tension, even military conflict across nations. There's a war in Ukraine and Russia. There's a brewing tension and conflict with China. Just the world is still seeking military conflict, cold or hot. What can you say about sort of the lessons of the 20th century in these giant projects [/INST] in their ability to ease some of this tension? So it's a great question. So as I said, there was a reason because it was so hard. That was one of the reasons they declassified it. And actually they started working together in some sense on it as well too. And I think it was really, there was a heuristic or altruistic aspect to this. It's like, this is something that could change the future of humanity and its nature and its relationship with energy. Isn't this something that we should work on together? Right, and that went along in those ones. And in particularly that any kind of place where you can actually have an open exchange of people who are sort of at the intellectual frontiers of your society, this is a good thing, right? Of being able to collaborate. I've had the, I mean, I have had an amazing career. I've worked with people from, it's like hard to throw a dart at a country and on the map and not hit a country of people that I've been able to work with. How amazing is that? And even just getting small numbers of people to bridge the cultural and societal divides is a very important thing. Even when it's a very teeny fraction of the overall populations, it can be held up as an example of that. But it's interesting that if you look at then that continued collaboration, which continues to this day, is that it was, this actually played a major role, in fact, in East-West relations or like Soviet-West relations, is that back in the Reagan-Gorbachev days, which of course were interesting in themselves of all kinds of changes happening on both sides, right? But still like a desire to push down the stockpile of nuclear weapons and all that, within that context, there was a fairly significant historic event that at one of the Reagan-Gorbachev summits is that they had really, they didn't get there. Like they couldn't figure out how to bargain to the point of some part of the tree deck anymore, the details of it anymore. But they needed some kind of a symbol almost to say, but we're still gonna keep working towards something that's important for all of us. What did they pick? A fusion project. And that was in the mid-1980s and actually then after, so they basically signed an agreement that they would move forward to like literally collaborate on a project whose idea would be to show large net energy gain in fusion's commercial viability and work together on that. And very soon after that, Japan joined, as did the European Union. And now that project, it evolved over a long period of time and had some interesting political ramifications to it. But in the end, this actually also had South Korea, India and China join as well too. So you're talking about a major fraction of, and now Russia, of course, instead of the Soviet Union. And actually that coalition is holding together despite the obvious political turmoil that's going around on all those things. And that's a project called ITER, which is under construction in the South of France right now. </s>
<s>[INST] So there's no so let me ask the hard question is uh maybe it's an impossible question is how do we resolve that conflict [/INST] in Israel and Israel or </s><s>[INST] anywhere anywhere where the instinct is to reach out in us and uh to say f you? And uh the people, [/INST] here's my here's what I think that the only way the two warring sides, or two sides that are opposed to one another can ever really come together is when there's mutual respect, we get just more water. Uh, when there's mutual respect and and and as and they can see each other as equals. And there's and when there's mutual fear, you know, where, where one side says, we don't dare cross the line with this other side and the other side says the same thing. I think then you can kind of reach across that thing and say, okay, we'll stay here, you stay here, we'll we'll mingle in cultural ways and we'll have interchange, you know, winter marriage, that uh But as soon as one side has no power, as the jewish people have had no power throughout the diaspora forever, right? Then it's just human nature. You can see it in trump and what he does to any vulnerable minority, right? Um it's it's and he's not alone. I'm not blaming him alone. That's human nature. So, I do think that that idea of like, fuck you, if you cross the line will kill you is really a good way is a is a good place to start from, because now you can sit down on opposite sides of the table and say, you know, what do we have in common? How can we we want to raise our Children, you want to raise your Children, how can we do this in a way that's that, that we're not hurting each other. </s><s>[INST] So, you kind of said that you need to arrive at a balanced, some kind of balance of power, but you haven't spoken to the fact that there's deeply rooted hatred of the other. So is there no way to alleviate that hatred? Or is that, I mean, what, what role does love and hatred [/INST] can go away? I really do. I mean, if you look at, even even now that I haven't seen this in person, but they say that the Saudis and the Israelis are collaborating on certain things, you know, by their mutual fear of, or antagonism to Iran. I do think that even really long, long, longstanding hatreds and animosities, thousands of years old can can go away under the right circumstances </s><s>[INST] in uh, on what time scale? [/INST] I mean that, for instance, I don't know if </s><s>[INST] people have to die, do generations have to die and pass away? And new generations come up with less hate? Or can a single individual learn to not hate? [/INST] I think a single individual can learn to not hate because it certainly doesn't seem to, over thousands of years doesn't seem to work. You know, we keep thinking that that's gonna happen, but I think it's we're in a real spiritual realm here, when you're talking about that, you're in a realm of, you know, buddha, jesus, whatever, something like that, that where uh, you know, uh, a true change of soul happens, but I do think that's possible. </s><s>[INST] So what do you think is the future of warfare, especially with what many people see as the expansion of the military, industrial conflicts? What do you, I know you're not a military historian, I'm asking more as a metaphor, uh, and we'll do, what do you see us as people continuing to fight? [/INST] You know, it's a really great question because I think now with uh social media tv movies, all of these things that create empathy across cultures, it becomes harder and harder, I think I think to totally demonize the other, the way it was in previous wars. I also think, I don't really see an appetite for people wanting to go to war these days and in a way, I don't know if that's good or bad, it's like everybody is so fat and lazy and so concerned with how many clicks they're getting that, you know, whereas I know at the start of World War One, both the younger generations were eager to go to war, You know, I think it was, it was, it was insane, but it was that sort of warrior archetype that we were talking about before, that, that generational um, testosterone arrows thing where's nowadays, I don't know, I mean it's hard to say there's not going to be another war because there always are, but it's sort of hard to imagine people getting off their ask these days to do anything. </s><s>[INST] Well it's funny that you mentioned social media as a place for empathy. Sure, but it's a, in a sense it's a place for uh for war, hatred, hatred and and perhaps ah the positive aspect of hatred on social media is that it's somewhat less harmful than murder. Uh and so it kind of dissipates sort of the hateful uh you get the hate out at um Yeah and uh you know, at a less yeah, on a daily basis and thereby never boils up to a point where you want to kill. [/INST] It's also a really weird thing that's going on. I don't know if anybody really understands like with video games where kids are acting out these incredible horror things, right? But you know that if they cut their finger, they would like freak out, you know. Um And I also don't think that many of the people that are hateful on social media, if they were face to face with the person wouldn't, so there's a sort of a two yeah to mental spheres happening at the same time and I don't know how that maps </s>
<s>[INST] Isn't that kind of a brilliant little trick of taking a series of data that is consistent and removing one element in that series and then uh teaching the algorithm to predict that element isn't that first of all, that's quite brilliant. Um it seems to be applicable in anything that has the constraint of being a sequence that is consistent with the physical reality. Um the question is, are there other tricks like this that can generate the self supervision signal? [/INST] So sequence is possibly the most widely used one in NLP for vision. The one that is actually used for like images, which is very popular these days, is basically taking an image and now taking different crops of that image. So you can basically decide to crop, say the top left corner and Ukrop say the bottom right corner and asking a network to basically presented with a choice, saying that okay, now you have this image, you have this image, are these the same or not? And so the idea basically is that because different, like in an image, different parts of the image are going to be related. So, for example, if you have a chair on the table, basically these things are going to be closed by versus if you take, again, if you have like a zoomed in picture of a chair, if you're taking different crops, that's going to be different parts of the chair. So the idea basically is that different crops of the image are related. And so the features or the representations that you get from these different crops should also be related. So this is possibly the most widely strict these days for self supervised, living in computer vision. </s><s>[INST] So again, using the consistency that's inherent to physical reality in in visual domain, that's, you know, parts of an image are consistent and then in the uh, language domain or anything that has sequences like language or something that's like a time series that you can chop off parts in time. It's similar to the story of our NNS and CNN's of our enemies and covenants. You and yang liu kun wrote the blog post in March 2021 titled Self supervised Learning The Dark matter of intelligence. Can you summarize this blog post and maybe explain the main idea or set of ideas. [/INST] The blog post was mainly about sort of distilling. I mean this is really an accepted fact. I would say for a lot of people now that self supervised learning is something that is going to be playing important roles for machine learning algorithms that come in the future. And even now, </s><s>[INST] let me just comment that we don't yet have a good understanding what dark matter [/INST] is true. </s><s>[INST] The [/INST] the metaphor </s><s>[INST] doesn't exactly transfer, but maybe maybe it's actually perfectly transfer is that we don't know where we have an inkling it will be a big part of whatever solving intelligence looks [/INST] like. So I think that's the way it's done right now is I would say the first step towards what it probably should end up like learning on what it should enable us to do. So the idea for that particular piece was self sequestering is going to be a very powerful way to learn common sense about the world or like stuff that is really hard to label. For example, like is this uh piece of rare heavier than the cup. Now for all these kinds of things, you have to sit and label these things. So supervised learning is clearly not going to scale. So what is the thing that's actually going to scale? It's probably going to be an agent that can either actually interact with it to lift it up or observe me doing it. So if I am basically lifting these things up, it can probably reason about this is taking him more time to lift up or the velocities different, whereas the velocity for this is different, Probably this one is heavier. So essentially by observations of the data, you should be able to infer a lot of things about the world without someone explicitly telling you this is heavy, This is not, this is something that can pour, This is something that cannot pour. This is somewhere that you can sit. This is not somewhere that you can sit, </s><s>[INST] but you just mentioned ability to interact with the world, There's so many questions that are yet to be that are still open which is how do you select a set of data over which the self supervised uh learning process works? How much interactivity, like in the active learning or the machine teaching context, is there? What are the rewards signals? Like how much actual interaction there is with the physical world, that kind of thing. Uh So that that's a that could be a huge quiet and then on top of that, which I have a million questions about which we don't know the answers to, but it's worth talking about is this how much reasoning is involved, how much accumulation of knowledge versus something that's more akin to learning or whether that's the same thing, but so were like it is truly dark matter, [/INST] we don't know how exactly to do it, but we are I mean a lot of us are actually convinced that it's going to be a major thing in machine learning </s><s>[INST] and let me reframe it then that human supervision cannot be at large scale the source of the solution to intelligence. So there has the machines have to discover the supervision in the natural signal of the [/INST] world. I mean the other thing is also that humans are not particularly good labelers are not very consistent. For example, like what's the difference between the dining table and the table? Is it just the fact that one, like if you just look at a particular table, what makes us say one is dining table and the other is not humans are not particularly consistent and not like very good sources of supervision for a lot of these kind of edge cases. So it may be also the fact that if we want like want an algorithm or want a machine to solve a particular task for us. They can maybe just specify the angle. Um and like the stuff in between. Uh we really probably should not be specifying because we're not maybe going to confuse it a lot actually. </s>
<s>[INST] but that was in Austin. Yeah, okay. [/INST] Um, and you know, we only, but at that time were only, it took a tremendous amount of engineering. It took a tremendous amount of validation to get to that point. But you know, we only did it a few times and I only did that, it was a fixed route, It was not kind of controlled environment, but it was a fixed route and we only did a few times. Uh then uh and 2016, end of 2016, beginning of 2017 is when we founded the company, that's when we kind of, that was the next phase of the project where I want to uh we believed in kind of the commercial vision of this technology and it made sense to create an independent, empty, you know, within that alphabet umbrella to pursue this product that scale beyond that in 2017, later in 2017 was another really A huge step for us. Really big milestone where we started, it was October of 2017 where when we started regular driverless operations on public roads that first day of operations we drove uh, in one day, in that first day, 100 miles and driverless fashion. And then we, the most, the most important thing about that milestone was not that 100 miles in one day, but that it was the start of kind of regular, ongoing driverless operations. </s><s>[INST] And when you say driverless, it means no driver. [/INST] That's exactly right. So on that first day we actually had a mix and uh, some, uh, we didn't want to like, you know, be on youtube and twitter that same day. So, and uh, and many of the rights, we had somebody in the driver's seat but they could not disengage like the car, not just engaged, but actually on that first day some of the miles were driven and just completely empty </s><s>[INST] drivers seat. And this is the key distinction that I think people don't realize, you know, that oftentimes when you talk about autonomous vehicles, you're, there's often a driver in the seat that's ready to, uh, to take over, uh, what, what's called a safety driver and then Waymo is really one of the only companies, at least that I'm aware of, or at least as like boldly and carefully and all and all that is actually has cases and now we'll talk about more and more or there's literally no driver. So that's another the the interesting case of where the driver is not supposed to disengage, that's like a nice middle ground. They're still there but they're not supposed to disengage. But really there's the case when there is no okay, there's something magical about there being nobody in the driver's seat. Like, just like to me, you mentioned um the first time you wrote some code for free space navigation of the parking lot that was like a magical moment to me, just sort of as an observer of robots. The first magical moment is seeing an autonomous vehicle turn, like make a left turn, like apply sufficient torque to the steering wheel to where like there's a lot of rotation and for some reason and there's nobody in the driver's seat. For some reason that that communicates that here's a being with power that makes a decision. There's something about like the steering wheel because we perhaps romanticized the notion of the steering wheel. It's so essential to our conception, our 20th century conception of a car and it turning the steering wheel with nobody in driver's seat. That to me, I think maybe two others. It's really powerful. Like this thing is in control and then there's this leap of trust that you give like I'm gonna put my life in the hands of this thing that's in control. So in that sense when there's no but no driver in the driver's seat. That's a magical moment for robots. So I'm uh I got a chance to uh last year to take a ride in uh in my vehicle. And that that was the magical moment. There's like nobody in the driver's seat. It's like the little details. You think it doesn't matter whether it's a driver or not, but like if there's no driver and the steering wheel is turning on its own, I don't know. That's magical. [/INST] It's absolutely magical. Like I have taken many of these rights and completely empty car, no human in the car pulls up. You know, you call it on your cell phone, it pulls up, you get in, it takes you on its way, there's nobody in the car but you right. That's something called fully driverless power. Writer only mode of operation. Uh yeah, it is magical. It is transformative. This is what we hear from our writers. It really changes your experience and not like that. That really is what unlocks the real potential of this technology. Uh but coming back to our journey, you know, that was 2017 when we started uh truly driverless operations. Then in 2018 we've launched our public commercial service called Waymo one. Um in phoenix. Uh in 2019 we started offering truly driverless writer only writes to our early writer population of users. And then uh 2020 as souls have been a pretty interesting year. One of the first one that's about technology but more about the maturing and the growth of uh remote as a company. We raised our first round of external financing uh this year, you know, we were part of alphabet, so obviously we have access to, you know, significant resources but as kind of on the journey of a maturing as a company that made sense for us to, you know, partially go externally uh in this round. So you were raised about $3.2 billion dollars uh from, you know that round we've also, you know uh started putting our fifth generation of our driver, our hardware that is on the new vehicle, but it's also a qualitatively different set of self driving hardware. That's that is now in the jail rps. So that was a very important step for us. </s>
<s>[INST] That's why... That's how much you're drinking. Here's the fun part about sandboxes. The AI knows about them. [/INST] It has the tools to crack them. Look, the fundamental problem of computer security is computational irreducibility. Because the fact is, any sandbox is never going to be a perfect sandbox. If you want the system to be able to do interesting things, I mean, this is the problem that's happened, the generic problem of computer security, that as soon as you have your firewall that is sophisticated enough to be a universal computer, that means it can do anything. And so long as if you find a way to poke it, so that you actually get it to do that universal computation thing, that's the way you kind of crawl around and get it to do the thing that it wasn't intended to do. And that's sort of… Another version of computational irreducibility is you can, you know, you can kind of… you </s><s>[INST] get it to do the thing you didn't expect it to do, so to speak. There are so many interesting possibilities here that manifest themselves from the computational irreducibility here. There's just so many things can happen because in digital space things move so quickly. You can have a chatbot, you can have a piece of code that you can basically have chat GPT generated viruses, accidentally or on purpose, and they are digital viruses. Yes. And they could be brain viruses too. They convince kind of like phishing emails. Yes. [/INST] They can convince you of stuff. Yes. windows. Yes. They can convince you. Yes. And no doubt, you can, you know, had the loop of the machine learning loop of making things that convince people of things is surely going to get easier to do. And then what does that look like? Well, it's again, we humans are, this is a new environment for us. And admittedly, it's an environment which a little bit scarily is changing much more rapidly than, I mean, people worry about, climate change is going to happen over hundreds of years and the environment is changing, but the environment for, in the kind of digital </s><s>[INST] environment might change in six months. So one of the relevant concerns here in terms of the impact of GPT on society is the nature of truth that's relevant to Wolfram Alpha, because computation through symbolic reasoning that's embodied in Wolfram Alpha as the interface, there's a kind of sense that what Wolfram Alpha tells me is true. So we hope. Yeah. I mean, you could probably analyze that, you could show, you can't prove that it's always [/INST] going to be true, computation or disability, but it's going to be more true than not. Look, the fact is, it will be the correct consequence of the rules you've specified. And in so far as it talks about the real world, that is our job in sort of curating and collecting data to make sure that that data is quotes as true as possible. Now, what does that mean? Well, it's always an interesting question. I mean, for us, our operational definition of truth is, somebody says, who's the best actress? Who knows? But somebody won the Oscar and that's a definite fact. And so that's the kind of thing that we can make computational as a piece of truth. If you ask these things, which a sensor measured this thing, it did it this way, a machine learning system, this particular machine learning system recognized this thing, that's a sort of a definite effect, so to speak. And there is a good network of those things in the world. It's certainly the case that particularly when you say, is so-and-so a good person, that's a hopelessly... We might have a computational language definition of good, I don't think it'd be very interesting because that's a very messy kind of concept, not really amenable to kind of... I think as far as we will get with those kinds of things is I want X. There's a kind of meaningful calculus of I want X and that has various consequences. I mean, I'm not sure, I haven't thought this through properly, but I think a concept like </s><s>[INST] is so-and-so a good person, is that true or not? That's a mess. That's a mess that's amenable to computation. I think it's a mess when humans try to define what's good, like through legislation, but when humans try to define what's good through literature, through history books, through [/INST] poetry, it starts being pulled. I don't know. That particular thing, it's kind of like we're going into kind of the ethics of what counts as good, so to speak, and what do we think is right and so on. I think that's a thing which one feature is we don't all agree about that. There's no theorems about, there's no theoretical framework that says this is the way that </s><s>[INST] ethics has to be. Well, first of all, there's stuff we kind of agree on and there's some empirical backing for what works and what doesn't from just even the morals and ethics within religious texts. So we seem to mostly agree that murder is bad. The certain universals that seem to emerge. I wonder where the murder of an AI is bad. Well, I tend to think yes, but I think we're going to have to contend with that question. [/INST] I wonder what AI would say. Yeah. Well, I think one of the things with AIs is it's one thing to wipe out that AI that has no owner. You can easily imagine an AI kind of hanging out on the internet without having any particular owner or anything like that. And then you say, well, what harm does it, it's okay to get rid of that AI. Of course, if the AI has 10,000 friends who are humans and all those 10,000 humans will be incredibly upset that this AI just got exterminated, it becomes a slightly different, more entangled story. But yeah, I know I think that this question about what do humans agree about, it's, there are certain things that human laws have tended to consistently agree about. There have been times in history when people have sort of gone away from certain kinds of laws, even ones that we would now say, how could you possibly have not done it that way? That just doesn't seem right at all. But I think this question of what I don't think one can say beyond saying, if you have a set of rules that will cause the species to go extinct, that's probably, you could say that's probably not a winning set of laws, because even to have a thing on which you </s>
<s>[INST] We're speaking english. So like you said, you're a different person in english and Russians in Russia, you might answer that differently, but in english, [/INST] I'm an optimist and I I generally believe that there is all, you know, even although the perspectives agree there's always a place for for a miracle, I mean it's always been like that with my life. So my life has been I've been incredibly lucky and things just miracles happen all the time with this company with people I know with everything around me. And so I didn't mention that book, but maybe in search of the miraculous or in search for miraculous or whatever the english translation for that is good Russian book too, for everyone to read. Um </s><s>[INST] yeah, I mean if you put good vibes, if you put love out there in the world, miracles somehow happen. Yeah, I believe that too. Or at least I believe that, I don't know. Uh let me ask the most absurd final ridiculous question of, we talked about life a lot. What do you think is the meaning of it all? What's the meaning of life? [/INST] I mean France was probably gonna be pretty cheesy. Um but I think the state of love is once you feel it um in a way that we discussed before, I'm not talking about falling in love where um </s><s>[INST] just love [/INST] to yourself to to other people, to something to the world, that state of bliss that we experience sometimes whether through connection with ourselves with our people, the technology. Um there's something special about those, those women's. So um, we'll see if anything that's, that's the only if it's not for that then for for what else are we really trying to do that? </s><s>[INST] I don't think there's a better way to end it. And talking about love Virginia. I told you offline that there's something about me that felt like this. This was talking to you, meeting you in person. It will be a turning point for my life. I know that might be sound weird to hear, but it was a huge honor to talk to you. I hope we'll talk again. Thank you so much for your time. [/INST] Thank you so much. </s><s>[INST] Thanks for listening to this conversation with Eugenia cuda and thank you to our sponsors doordash, dollar shave club and cash app, click the sponsor links 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 Podcasts 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 Carl Sagan, the world is so exquisite with so much love and moral depth that there's no reason to deceive ourselves with pretty stories of which there is little good evidence far better, it seems to me and our vulnerability. It's to look death in the eye and to be grateful every day for the brief but magnificent opportunity that life provides. Thank you for listening and hope to see you next time. [/INST] </s>
<s>[INST] yet, but I think that there's this feeling that you captured with your body language and so on the like the, I don't want to do another set that feeling the people I've seen that are good at not procrastinating are the ones that have trained themselves to like the moment they would be having that feeling. They just, it's like zen like sam hairstyles and you don't experience that feeling, just march forward. Like I talked to Ellen about this a lot actually offline. It's like he doesn't have this. It's it's it's the way I think he talks about the way I think about it is it's like you just pretend you're like a machine running an algorithm like you know this, you should be doing this not because somebody told you so on this is probably the thing you want to do. Like look at the big picture of your life and just run the algorithm. Like ignore your feelings. Just running, just [/INST] framing, frame it differently. Yeah. You know, Yeah, you can frame it as like you can feel like homework or it can feel like you're like you're living your best life or something when you're doing your work. Um </s><s>[INST] maybe reframe it, but I think ultimately is whatever. Reframing you need to do, you just need to do it for a few weeks and that's how the habit is formed and you stick with it. Like um I've, I'm now on a on a on a kick where I exercise every day, it doesn't doesn't matter what that exercises, it's not serious, it could be 200 push ups, but it's the thing that like I make sure exercise every day has become way, way easier because of the habit and I just um and I don't like at least with exercise because it's easier to replicate that feeling. I don't allow myself to go like I don't feel like doing right [/INST] well, I think about that even just like little things like I brushed my teeth before I go to bed and it's just a habit and it is effort. Like if it was something else, I would be like, I don't go to the bathroom, I'm gonna do that and I just feel like I'm just going to lie down right now, but it doesn't even cross my mind. It's just like that I just robotically go and do it and it almost has become like a nice routine. It's like, oh this is part of the night, you know, it's like morning routine for me, stuff is like, you know that that stuff is kind of just like automated. It's funny </s><s>[INST] because you don't like go like I don't think I've skipped many days, I don't think I skipped any days brushing my teeth like unless I didn't have a tooth, but like I was in the woods or something and what is that? Because it's annoying [/INST] to me, There is um there so the character that makes me procrastinate, the instant gratification monkey, that's what I've lived with him, right? And there's the rational decision maker and the instant gratification monkey and these these battle with each other. Um But the for procrastinator, the monkey wins. I don't think the monkeys, you know, if you know you read about this kind of stuff, I think that the this kind of more primitive brain is always winning and in the non procrastinators, that primitive brain is on board for some reason. Um And isn't resisting. So but but when I think about brushing my teeth, it's like the monkey doesn't even think there's an option to not do it, so it doesn't even like get there's no hope monkey has no hope there, so it doesn't even like get involved and it's just like yeah you know we have to just like kind of like robotically just like you know, it's kind of like Stockholm syndrome, just like oh no no I have to do this. Um it doesn't even like wake up, it's like yeah we're doing this now for other things, the monkeys like oh no no no, most days I can win this one. And so the monkey um puts up that like fierce resistance and it's like it's it's a lot of it's like the initial transition, so I think of it as like jumping into cold pool where it's like I will spend the whole day pacing around the side of the pool in my bathing suit just being like, I don't want to have that one second when you first jump in and it sucks. And then once you're, once I'm in, once I jump in, I'm usually, you know, once I start writing and suddenly I'm like this is this isn't so bad, okay, I'm kind of into it and then someone, you can't tear me away, you know that? Then I suddenly, I'm like, I get into a flow so it's like once I get into cold water, I don't mind it, but I will spend hours standing around the side of the pool and by the way, I do this in a more literal sense when I go to the gym with a trainer In 45 minutes, I do a full full ass workout and it's not because I'm having a good time, but it's, it's it's because is that you have to go to class feeling right? But when I go to the gym alone, I will literally do a set and then dick around my phone for 10 minutes before the next set and I'll spend over an hour there and do way less. So it is um the transition, once I'm actually doing this set, I'm never like, I don't want to stop in the middle now. It's just like I'm gonna do this and I feel happy I just did it. So it's something, there's something about transitions that is very, that's why procrastinators relate a lot of places. It's, I will procrastinate getting ready to go to the airport um even though I know I should leave it three so I cannot be stressed, I'll leave at 3 36 and I'll be super stressed once I'm on the way to the airport immediately. I'm like, why didn't I do this earlier? Now I'm back on my phone doing what I was doing. I just had to get in the damn car or whatever. So um yeah, there's some very, very odd, irrational, </s>
<s>[INST] So it's not winner take all with one particular demand. Okay, so there's a million questions that spring up right there. But first link on this topic and say, what is proof of work? What is proof of stake? Just zooming in on each of those. [/INST] And what are the differences? Okay, so they all have the same three properties of pick someone in charge, do something and validate it. The difference is that the picking mechanism for proof of work is you have to solve a puzzle. So it's basically like buying lottery tickets and you can buy a certain amount every second with your computing devices. And some of them are ASIC resistance. You run them on like a laptop or a GPU. And some of them are you specialized hardware that you have to either manufacture or buy from someone who sells it to you. And that's just how many tickets per second you can get. And eventually you hit those magic numbers. And when you do, it means you have the right to make the block. And generally you bundle the block making with the proof of work system. Now you can do this looking for a single or you can do this to actually shard it and look for multiple block makers at the same time. So there are sharded proof of work protocols. Like Prism is an example of that. And actually Ethereum got started this way with Spectre and Ghost and Phantom, the Avi Zohar's work and Yonatan Sumlopinski. But the basic idea is you pick some collection of people, they make some collection of things and there's some way to sort it all out, serialize it and prevent double spends. Great. Proof of stake is the same, but it's a synthetic resource. So instead of doing things, they say, well, if you had 25% of the hash power on average over a long period of time, you'd probably win 25% of the time. Well, why don't we just introduce some randomness sin from some source and then 25% of the time on average over a long period of time, you'll win. So it's a synthetic resource but you still have to do the other two things. You still have to make the block and you still have to validate the block. The big difference is this step in the proof of work world is horrendously expensive. You use more energy than the nation of Switzerland. And the problem with that is that you have less resources for the other two. And the other problem with that is that if this is horrendously expensive, you have an economy of scale kick-in. So what ends up happening is the system becomes less decentralized over time because you have these vertically integrated operations. I mean, not everybody can go build a mining facility on a volcano in El Salvador. Not everybody can go to Mongolia and set up a five gigawatt power plant and a huge data thing. Not everybody has access to the patented ASICs that people produce. Because what if I don't sell it to you and I have the patent on it? Or what if I control the supply chain for these things? So you'll end up having centralization around maybe 10 or five major operations as we've seen historically with proof of work. And that means you end up having a ruling class of a mining oligarchy in the system. Proof of stake, if you design the parameters correctly, you actually get more decentralized over time. Because as the currency goes up in value, the distribution of the currency tends to get more egalitarian. For example, Bill Gates, when he started Microsoft, he has 64% of the shares. Now he has less than 5% of the shares. So this founder drift over time, as the value goes up, divestment occurs, you have more and more and more people coming in. That means there's more people who can participate in the consensus. You can even tune economic parameters. And this is what we did with Cardano and Ouroboros. We created this concept of K in the system and it's just a parameter. And it's like a forcing factor that tends to accumulate a certain amount of stake pool. So you can set it to 200 and then 500 and 1,000 and so forth. But the basic idea is as the price of ADA goes up, you make K larger and then you end up, in practical terms, having a larger and larger set of actors making blocks that are unique and distinct. And the other good thing is this is a virtual resource instead of a physical resource, which means it's portable by the click of a button. So let's say China says, mining is bad, we're gonna shut it all down. And it looks like they're moving in that direction. You have all these people in WeChat just like trying to sell miners or trying to figure out how the hell do I move miners because they have these huge data centers they've constructed. You can't exactly go and grab a server and like take it with you, it's huge. It's a lot of work. And if the government sees it, well, it's their property now. A virtual resource, you can click a button and redeploy it to a different jurisdiction. So to me, for a virtual asset, it makes a lot more sense to try to tie your security to something endogenous, something within the system, because it's just like the asset, it can move anywhere at a click of a button. And human beings have a much harder time </s><s>[INST] attacking something like that. Well, so people, maybe you could sort of play devil's advocate and say, what is the strength of proof of work system? Because some people would argue that proof of work has, because it's outside the system, it's tied to physical resources, it's more secure. [/INST] It's less prone to attack by large groups of people. Yeah, that's a great question. And the first question we had was, could proof of stake actually work or not? So the problem was that the engineers kind of led, when the science should have led. And so there were all these POS protocols that came out in the early 2010s, like Peercoin was the first and then NXT and others came out. And there they had suffered from things like the random number generation wasn't good, they had grinding attacks and nothing at stake and all these other things. And there's a lot of beautiful properties for proof of work from a theoretical sense. We even wrote a paper called GKL named after the authors, Juan Gray, Nico Leonardis and Agulos Gassis, our chief scientist. It's got 1100 citations now, it was published in 2015. But basically all it did is just modeled a blockchain and created some security properties for it. And then it started talking about, well, what does proof of work actually do for you? And it turns out it does a lot. It's an asynchronous system, you can bootstrap from Genesis. So if Eve joins the network and Wally joins the network and Daisy joined the network, then you give them some different chains, like five or 10 different chains, they can run a calculation and they will always pick the longest chain, the heaviest chain inside the system. That's a great property of proof of work. Until we published Ouroboros Genesis in 2018, you actually needed to solve that and proof of stake with a trusted checkpoint. So some actor had to be observing, watching the whole thing and creating checkpoints. And then when new people joined in, they would only be able to distinguish between a chain based upon a checkpoint telling them that. So you have to do a lot of really wonky crazy math to show and create this notion of like density to be able to show that that's possible. But there's a lot of properties of proof of work that were super hard to replicate and emulate in the proof of stake world. Macaulay kind of revolutionized the whole VRF thing. There was a group out of Cornell that talked about better network conditions. They wrote a paper called Sleepy. We did Genesis, we also did the very first proof of secure protocol, but that was six years of work and like 12 papers. And it's still not done. There's still a few polishing things that have to be cleaned up because this is a physical resource and there's something there. But there's a flaw to proof of work that is a little problematic. It's a winner take all type of a system. So maximalism is kind of philosophically and computationally built into it. Let's say you have two proof of work systems and they have roughly the same market cap and hash rate and they use the same algorithm. Then the problem is if the miner comes in and let's say the miner has enough resources to have 51% for any of these chains, they actually have a perverse incentive to come and destroy one chain and short sell the asset. It's called a gold finger attack and then go mine the other asset because they're not bound to that asset. They're not loyal to it. And they can make just as much profit mining this as they can make mining the other system and the markets allow them to profit from the destruction of a system. So that's something that proof of stake doesn't suffer from because the only way you can participate in a proof of stake system is you have to actually own equity and you have to have ownership in that system. So if you go and destroy Daisy's chain, it would just be a net loss for the most part unless you have really messed up markets or something like that. So there's always trade offs and all these things. And this is why I like this concept of going one to N and having multiple resources because why not have proof of work and proof of stake together? If the proof of work is useful, not wasted computation, and why not add other things like create incentives for network relay? Right now there's no incentives in the system for you to run peer to peer nodes and the shared data. Right now it's not a problem, but if you're running like Amazon Web Services level of bandwidth, it could cost you like $5,000 a month in bandwidth just to run a full node or something like that. No one would do it. So then your system will centralize along the weakest link, whether it be the storage layer, the computation layer or the network layer of the system. So if you can incentivize the resources differently, then you'll be in a beautiful position where you end up having a resilient system </s>
<s>[INST] Uh Perhaps he just said it for religious reasons and so on, but in particular sort of a world of interaction without contact. So action at a distance, it didn't make sense to them. On a sort of a human interpretation level doesn't make sense to you, that things can affect other things at a distance. [/INST] It does. But you know that. So that was one of Newton's worries. You're actually right in a slightly different way about the religious worries. He um he was smart enough. This is off the topic, but still fascinating. Newton almost invented chaos theory. As soon as he invented classical mechanics, he realized that in the solar system. So he was able to explain how planets move around the sun. But typically you would describe the orbit of the earth, ignoring the effects of jupiter and Saturn and so forth, just doing the Earth and the sun. He kind of knew, even though he couldn't do the math, that if you included the effects of jupiter and Saturn, the other planets in the solar system would be unstable, like the orbits of the planets would get out of whack. So he thought that God would intervene occasionally to sort of move the planet's back into orbit, which is how the only way you could explain how they were there, presumably forever. But the worries about classical mechanics were a little bit different to worry about gravity in particular, it wasn't worried about classical mechanics were about gravity. How in the world does the earth know that there's something called the sun 93 million miles away that is exerting gravitational force on it. And he said he literally said, you know, I leave that for future generations to think about because I don't know what the answer is and in fact people under emphasize this, but future generations figured it out. Pierre Simone laplace in uh circa 1800 showed that you could rewrite Newtonian gravity as a field theory. So instead of just talking about the force due to gravity, you can talk about the gravitational field or the gravitational potential field and then there's no action at a distance. It's exactly the same theory empirically, it makes exactly the same predictions. But what's happening is instead of the sun just reaching out across the void, there is a gravitational field in between the sun and the earth that obeys an equation Laplace equation cleverly enough, and that tells us exactly what the field does. So even in Newtonian gravity, you don't need action at a distance. Now, what many people say is that Einstein solved this problem because he invented general relativity and in general relativity, there's certainly a field in between the earth and the sun, but also there's the speed of light as a limit in laplace theory, which was exactly Newton's theory, just in a different mathematical language, there could still be instantaneous action across the universe, Whereas in general relativity, if you shake something here, it's gravitational impulse radiates out at the speed of light, and we call that a gravitational wave, and we can detect those. So, but I I really it rubs me the wrong way to think that we should presume the answer should look one way or the other, like, if it turned out that there was action at a distance in physics, and that was the best way to describe things that I would do it that way. It's actually a very deep question, because when we don't know what the right laws of physics are, when we're guessing at them, when we're hypothesizing at what they might be? We are often guided by our intuitions about what they should be. I mean, Einstein famously was very guided by his intuitions and he did not like the idea of action at a distance. We don't know whether he was right or not. It depends on your interpretation of quantum mechanics, and it depends on even how you talk about quantum mechanics within anyone interpretation. </s><s>[INST] So, if you see every forces a field or any other interpretation of action at a distance, he's just stepping back to sort of cave man thinking, do you really? Can you really sort of understand what it means for a force to be a field that's everywhere. So, if you look at gravity, like what do you think [/INST] about? I think so </s><s>[INST] is this something that you've been conditioned by society to think that to map the fact that science is extremely well predictive of something to believing that you actually understand it. Like you can intuitively on the how as the degree that human beings can understand anything that you actually understand it. Are you just trusting the beauty and the power of the predictive power of science [/INST] that depends on what you mean by this idea of truly understanding something, right? You know I mean can I truly understand Fermat's last theorem? You know? It's easy to state it. But do I really appreciate what it means for incredibly large numbers? Right. Um Yeah, I think yes, I think I do understand it but like if you want to just push people on well but your intuition doesn't go to the places where Andrew wiles needed to go to prove Fermat's last theorem and I can say fine. But I still think I understand that the arab and likewise, I think that I do have a pretty good intuitive understanding of fields, pervading space time, whether it's the gravitational field or the electromagnetic field or whatever. The Higgs field. Um Of course one's intuition gets worse and worse as you get trickier in the quantum field theory and all sorts of new phenomena that come up in quantum field theory. So our intuitions aren't perfect. But I think it's also okay to say that our intuitions get trained right? Like you know, I have different intuitions now that I had when I was a baby. That's okay. That's not an intuition is not necessarily intrinsic to who we are. We can we can train it a little bit. </s>
<s>[INST] It's it's tempting though. It's so interesting how companies get tempted to to [/INST] help. It's </s><s>[INST] like and you step in and it's almost like a drug and then you can't you forget I mean like all of us in life doesn't have to be cos you get distracted and maintaining focus. Like you're you're absolutely right. The way for coin based add value to the world is to maximize the mission that it's on not not other not other stuff. And when you get wealthier and more successful there's becomes more and more tempting to just help out in some other shallow ways and fascinating and you just kind of brought that to light so it was very refreshing and it shouldn't be controversial to sort of focus on just getting stuff done. But [/INST] let me ask you, I mean do you think that this it's all these things tied together, There's like a general trend of like more censorship. You know, there's like more canceled culture. Um there's uh some of these like freedom values are kind of you know, even like freezing people's accounts like the trucker thing that happened? And it seems like there's a general trend of um more authoritarian you know, policies there. But do you think that do you feel like the tide is turning on that like there's counter examples to it we've seen recently </s><s>[INST] and I think it's the last gasp of the old way of doing things. And so there's desperation. So because to be fair it's kind of the internet which is where is the source of a lot of this where people have a voice is making the power centers of the world really nervous. And so that's where that's coming from, I think, and and the internet is tricky. It's weird. It's full of bots, it's full of like misinformation of all kinds, full of large groups with conspiracy theories and so on. Uh and I mean misinformation broadly, people are misusing the word misinformation, they're just governments are just labeling random things with misinformation just to censor them. Um but I just think it's just like a new world where the internet is really finally taking hold, where there's billions of devices and everybody has a voice. It's almost uh basically governments and powerful people are slightly losing hold of power and they're starting to freak out a little bit. That's it. And so and then once you have young people that are coming up now gain power, I think we'll rebalance everything. And and then there's like you said, promising signs um that it's obvious that the majority of people want freedom and that means a lot of things, that means economic freedom, that means freedom to have a voice um freedom to move around, freedom to act in the way they, you know, without without reasonable sort of um limitations by people that don't have their best interests. And I I gain more hope from just regular people that are fighting and like demanding the being able to have freedom of speech or more specifically sort of resisting crude overreach of government in the acts of censorship, at least in the United States. Uh and hopefully that percolates out to the rest of the world that's struggling on a much more basic level where people are being put in prison for the words they say, not just banned from [/INST] twitter. </s><s>[INST] What are some lessons from your failures and your successes about what it takes to run a company. [/INST] I think one of the things that I've learned about leadership is that, you know, I never really thought of myself as a very natural leader to be honest. I don't I don't think I was a natural leader, but so I always envisioned, you know, good leaders as like these military generals, like they seem so like confident and they're just like bark orders, you know, like charge that hill and do this. And I was I was actually like more introverted and kind of um I wasn't really confident in the way I communicated and uh you know, and so what I realized is that there's lots of different kinds of leaders, you can be any kind of ceo you want, right? I was kind of more of like a product, technical focus ceo and I preferred to sort of hear everyone's opinion and it wasn't just gonna like render a decision in the room in some kind of heated moment and like piss off half the people, I would be like, all right, I'm gonna go think about it and I'll send you my decision later today or tomorrow or whatever. And so I would I found ways to kind of make it work for me, where I could basically I always tried to avoid like um you know when people getting like super emotional about something and like I think they're they're thinking their judgment goes down right, and like never make a decision when you're angry, right? And so if I would always sort of try to get a sense of are these people like trying to be right or are they trying to seek the truth? You know, and you can do these little tricks like you know, okay you argue that person's position and you argue the other one and like see if you can genuinely represent it now, I know you're listening and you know these kind of things. Um but I guess sorry, get back to your question about leadership, I think I basically just kept doing things that were a little outside my comfort zone and then my comfort zone kept getting bigger </s><s>[INST] and bigger, you [/INST] know? And so that's I think that's how you build confidence is you do the thing that's scary and it's like a little outside and like when I first started coin base, I have never managed anybody, I would have I would have never I would've been scared to death to have put out like a very controversial opinion like that and sort of Alright 5% of people will go, you know, we didn't know what it was gonna be by the way, it could have been 1%, it could've been 50% like. But we went into it scary because it was a scary thing. I was like I don't know, I think this is right, I'm just gonna do it. </s>
<s>[INST] Yokohama Bay, the U.S. and Japanese leaders in Sinai. This is not that. So what stands out to you as brilliant ideas during this time and actions, too, of [/INST] Lincoln, Abraham Lincoln? So I mentioned that his values. I think a number of the things that he does that are quite extraordinary. First, in emancipating the slaves. Now, the slaves were freeing themselves, but Lincoln recognizes that he needs more labor in the Union Army, and he recognizes that there's still a lot of resistance. And what he does is he makes the case for freeing the slaves based on the argument, not just of the moral value of that, but based on how that will benefit the North. He's able to convince non-abolitionists to pursue abolitionist policies by serving their own interests. What he's basically saying by 1863 or 64 is, I can ask for more white soldiers, or I can bring in former slaves. Would you like me to take your son, or would you like me to put it in? It's the same thing Franklin Roosevelt does during World War II. He says, we need to build more planes and more tanks, and I'm sending all the soldiers off to Europe. I've got all this African American population in the South. Wouldn't you like me to move them up to Chicago so we can win this war and build things in the factories? So Lincoln uses the war to move the country forward morally, even if at times he's convincing people by using other </s><s>[INST] other reasons. And I think that's great politics. I guess that's one of the components of great leadership, is do the right thing for the wrong reasons. [/INST] Or publicly sounding wrong reasons. Find ways to move people. What we talked about before. Different stories move different people, so you can tell different stories. He tells one set of stories to the religious leaders who are abolitionists, and a different set of stories to the New York bankers. And that's leadership. You tell different kinds of stories to move people to a new position. The other thing Lincoln is really brilliant at is managing the the international side of this. So one of the real dangers for the Union is that the British will come in on the side of the Confederacy. The Confederates expected the British what, because, again, the Confederates were selling while they're cotton to Britain, and they knew that the British leadership, first of all, was very happy to work with slaveholding societies, even though they didn't have slaves, and number two, that they believe the Union was getting too strong and threatening the British in Canada. So there were many reasons the British might have gone in with the Confederates. But Lincoln mixes sticks and carrots with the British. He threatens them, and when the British actually try to send diplomats to negotiate with Southerners, he interdicts that. He basically initiates a quarantine of the South. On the other hand, he reaches out to them and tries to show that he wants better relations and makes the argument that they will actually benefit more from having the industrial capability of the Union on their side. </s><s>[INST] So he's a very good diplomat. He is considered to be one of the great presidents in the history of the United States. Are there ways that he failed? [/INST] Is there things he could have done better? So he failed in the ways that most great leaders fail, which is that he had a terrible succession plan. His vice president, who I spend a lot of time on in the book, Andrew Johnson, who is probably our worst president ever, Andrew Johnson had no business being anywhere near the presidency. Andrew Johnson was the only Southern senator who did not secede. And so even though he was a Democrat, Lincoln wanted to show that he was creating a unity ticket when he ran for reelection in 1864. This happens today, right? So he put someone on as vice president who he didn't even like, but who we thought was politically useful. Problem is, when Lincoln was assassinated, this guy took over. Andrew Johnson was drunk at his own inauguration. The guy was a true drunkard. He was not prepared to lead in any sense, intellectually, politically, and he was against most of the principles Lincoln was for. And the irony is that when Lincoln is assassinated in April of 1865, Andrew Johnson takes over and he has all the war powers Lincoln had. That was not good planning by Lincoln. And we can look back on it now and say, even though Lincoln is the first president who was assassinated, he should have known that there were people coming for him. It wasn't inevitable that he'd be assassinated, but he should have had a backup plan for who would take over, hopefully someone who was capable of doing the job and Andrew Johnson </s><s>[INST] was not capable. So for me, for personally, if I were to put myself in Lincoln shoes or anybody, any leadership position shoes, it is difficult to think about what happens after my death, after I'm gone, right? To plan well. But at the same time, if you care about your actions to have a long-term impact, it seems like you should have a succession plan that continues on the path, continues to carry the ideals that you've implemented. So I'm not, I'm unsure why people don't do that more often. Like I wonder how much Vladimir Putin spends percentage of time per day thinking what happens after he's gone to help flourish the nation and the region that he deeply cares for. I wonder, and the same is for other presidents, Donald Trump, Joe Biden. They might think politically, like how do I guarantee that it's a Democrat or a Republican? Do they think like visionary for the country? [/INST] I don't know. I wonder. I think that's very rare. And I think what I understand from the literature among business people who talk about this a lot is what ends up happening is you become so powerful, you assume you're always going to be in power. You convince yourself of that. You convince yourself that the end is far away. And of course, for Lincoln, the end could have been far away. He was healthy. He was only in his fifties. He could have lived a lot longer, but it also, it ended fast as it could. And my understanding is that most Americans don't prepare their wills and estates, and it doesn't matter whether they're rich or poor. </s>
<s>[INST] it's a, it's an interesting concept nuclear. It seems like people like everybody that works on nuclear power has shown how safe it is as a source of energy. And uh and yet we are seem to be, I mean based on the history based on the excellent HBO series Russian with the Chernobyl. It seems like we have our risk estimation about this particular power sources uh, drastically inaccurate. But that's that's a fascinating idea that we would use nuclear as a source for our vehicles uh, and not just in outer space. That's cool. I'm going to look into that. That's super interesting. [/INST] Well, just last year trump eased up a little bit on the regulations and Nasa and hopefully others are starting to pick up on the development. So now is a good time to look into it because there's actually some movement, </s><s>[INST] is that a hope for you to explore different energy sources that the entirety of the vehicle uses something like uh, like the entirety of the propulsion systems for all aspects of the vehicle's life travel is the same or electric. Is it possible for it to be the same? Like the kool Aid engine being used for everything [/INST] you could and you would have to do it in the same way we do different stages of rockets now where once you've used up an engine or a stage you let it go because there's really no point in holding on to it. So I wouldn't necessarily want to use the, the same engine for the whole thing, but the same technology I think would be interesting. </s><s>[INST] Okay, so it's possible, all right. But [/INST] uh, in terms </s><s>[INST] of the power source and the power source, that's really interesting. But for the current power sources and its current use cases, what's the use case for electric? Like the the Polaroid engine? Can you talk about where they're used today? [/INST] Sure. So chemical engines are still used quite a bit once you're in orbit, but that's also where you might choose instead to use an electric system and what people do with them. And this includes, you know, the ion engines and hull thrusters and orange in um, is basically any maneuvering you need to do once you're dropped off. There's even if your only goal was to just stay in your orbit and not move for the life of your mission, you need propulsion to accomplish that because the Earth's gravity field changes as you go around in orbit and pulls you out of your little box. There are other perturbations that can throw you off a bit. Um, and then you know, most people want to do things a little bit more interesting like maneuver to avoid being hit by space debris or perhaps lower their orbit to take a higher resolution image of something and then return um at the end of your mission you're supposed to responsibly get rid of your satellite whether that's um burning it up but if you're in G. O. Um you want to push it higher and to graveyard orbit um </s><s>[INST] was geo [/INST] what's so low earth orbit and then geosynchronous orbit or geo stationary orbit </s><s>[INST] and there's a graveyard. [/INST] Yeah, so those satellites are at um like 40,000 km so if they were to try to push their satellites um back down to burn up in the atmosphere, they would need, you know, even more propulsion than they've had for the whole lifetime of their mission. So instead they push them higher where it'll take, you know, a million years for it to naturally deorbit. So we're also cluttering that higher bit up as well but it's not as pressing as as leo, which is low earth orbit where more of these commercial missions are going now. </s><s>[INST] So how hard is the collision avoidance problem there? He said some debris and stuff so like how much propulsion is needed? Like how much is the life of a satellite is just like a crap trying trying to avoid, like what I [/INST] think one of the recent um you know rules of them I heard was per year some of these small satellites are doing like three collision avoidance maneuvers um So that's that's not yeah, but it's not zero um And it yeah, it takes a lot of um planning and people on the ground and you know, none of that really. I don't think right now is autonomous. </s><s>[INST] Oh that's not good. [/INST] Yeah. And then we have a lot of folks taking advantage of moore's law on cheaper spacecraft so they're launching them up without the ability to maneuver themselves and they're like, well I don't know, just don't hit me </s><s>[INST] and three times a year that could be become affordable if it's like if he gets hit maybe it won't be damaged kind of thing. That kind of logic [/INST] Affordable in that instead of launching one satellite they'll lunch you know, 20 small ones. Yeah. So if one gets taken out that's okay. But the problem is that you know, one good sized satellite getting hit Um that's like a ballistic event that turns into 10,000 pieces of debris that then are the things that go and hit the other satellites? Yeah. </s><s>[INST] Do you see a world where like in your sense in your own work and just in the space industry in general, do you see that people are moving towards bigger satellites are smaller satellites? Is there going to be a mix like what and what are we talking, what does it mean for a satellite to be big and was small. What's that [/INST] big? The space industry p Prior to, I don't know, 1990, you know, I guess the bulk of the majority of satellites were the size of a school bus and costs a couple of billion dollars. Um And now our first launches were on um satellites the size of shoe boxes that were built by high school students. So that's very different, you know, to give you the two ends of the spectrum. Um Big satellites will I think they're here to stay at least as far as I can see into the future. Um for things like broadcasting, you want to be able to broadcast to as many people as possible. Um There you also can't just go to small satellites um and say moore's law for things like optics. So if you have an aperture on your satellite, you know, that just that doesn't follow moore's law, that's that's different. So it's always going to be the size that it will be, you know, unless there's some new physics that comes out that I'm not aware of, but if you need a resolution and you're at an altitude that kind of sets your the size of your telescope. Um but because of moore's law, we are able to do a lot more with smaller packages and with that comes more affordability and opening up access to space to more and more people? </s>
<s>[INST] novel you could ever read. [/INST] It's just so crazy watching consciousness </s><s>[INST] come [/INST] into being and </s><s>[INST] then at the same time [/INST] like you're forced to value your time so much. Like when I have creative </s><s>[INST] time now it's so sacred, [/INST] I need to like </s><s>[INST] be really [/INST] freaking </s><s>[INST] on [/INST] it. But the other thing is </s><s>[INST] that um [/INST] I used to just </s><s>[INST] be like a cynic and I used to just want [/INST] to like, my last album was called Miss anthropocene </s><s>[INST] and it [/INST] was like this like it was like a study in villainy, like </s><s>[INST] or like it was like, [/INST] well what if, you know, we have instead of the old gods, we have like new </s><s>[INST] gods and it's like [/INST] Miss Miss anthropocene is like misanthrope like and anthropocene </s><s>[INST] which is like the, you know, [/INST] like </s><s>[INST] and she is the goddess of climate change or [/INST] whatever and he's like destroying the world. And it was just like </s><s>[INST] it was like dark and it [/INST] was like a study in villainy </s><s>[INST] and it was sort of just like like [/INST] I used to like have no problem just making </s><s>[INST] cynical angry scary [/INST] art. Um And not that there's anything </s><s>[INST] wrong with that, but [/INST] I think having kids just makes </s><s>[INST] you such an optimistic just [/INST] inherently makes you want to be an optimist. So </s><s>[INST] bad that like um [/INST] like I feel like more responsibility to make </s><s>[INST] more optimistic things [/INST] and </s><s>[INST] I get a lot of ship for it because [/INST] everyone's like </s><s>[INST] you're so [/INST] privileged. Stop talking about like pie in the sky stupid concepts and focus on like the </s><s>[INST] now. But it's like [/INST] um I think if we don't </s><s>[INST] i. d. eight about um [/INST] futures that </s><s>[INST] could be good. [/INST] We won't be able to get them </s><s>[INST] if everything is Blade Runner, [/INST] then we're going to end up with Blade Runner. It's like we said earlier, life imitates art, like life </s><s>[INST] really does imitate art. And so we really need more [/INST] proto peon or utopian art. Um I think this is incredibly essential for uh the future of humanity. And I think the the current discourse where um </s><s>[INST] that's [/INST] seen as a thinking about </s><s>[INST] proto [/INST] pia or utopia is seen as a dismissal of the problems that we currently </s><s>[INST] have. I think that is an incorrect [/INST] mindset. </s><s>[INST] Um [/INST] and like having kids </s><s>[INST] just makes me want to imagine [/INST] amazing futures that like maybe I won't be able to build, but they will be able to build if they want to. Yeah, it does seem like ideation </s><s>[INST] is a precursor to [/INST] creation, Okay, You have to imagine it in order to be able to build it. And there is a </s><s>[INST] a sad thing about human [/INST] nature that they </s><s>[INST] somehow, a [/INST] cynical view of the </s><s>[INST] world is seen [/INST] as a insightful </s><s>[INST] view. You know, [/INST] cynicism is often confused for </s><s>[INST] insight, which is [/INST] sad to see </s><s>[INST] and optimism is [/INST] confused for naivete. Like you don't you're you're </s><s>[INST] blinded [/INST] by your maybe your privilege or whatever, you're blinded by something, but you're certainly blinded. That's a that's sad. That's sad to see because it seems like the optimists are the ones that create the our </s><s>[INST] future. They're the [/INST] ones that build in order to build </s><s>[INST] the crazy thing. You have to [/INST] be optimistic, you have to be either stupid </s><s>[INST] or [/INST] uh excited </s><s>[INST] or passionate or [/INST] mad enough to actually believe that it can be built and those are the people that built it. My favorite quote of all time is from Star Wars episode eight, uh which I know everyone hates hates. Do you like Star Wars episode eight? No, I </s><s>[INST] yeah, probably. I would say it would probably hate it. [/INST] Yeah, I don't I don't have strong feelings about it. Let me backtrack. I don't have strong </s><s>[INST] feelings about that [/INST] token person. I'm not </s><s>[INST] I'm more, [/INST] I'm more into dragons and orcs and ogres and yeah, I mean forever. </s><s>[INST] I really want to have one [/INST] more son and call him. I thought tao techno to tolkien would be cool. It's a lot of T. S. I like it invalid and tau is 6 to 82 pi. Yeah. </s><s>[INST] Yeah. And then techno [/INST] is obviously </s><s>[INST] the best genre of [/INST] music but also like technocracy </s><s>[INST] just sounds really good. [/INST] Yeah that's right. </s><s>[INST] Techno [/INST] token token. </s><s>[INST] But uh [/INST] Star Wars Episode eight. I know a lot of people have issues with it personally on the record. I think it's the it's the best Star </s><s>[INST] Wars film [/INST] um </s><s>[INST] uh [/INST] Starting </s><s>[INST] trouble today so [/INST] and but don't kill what you hate, save what you love, don't kill what you </s><s>[INST] hate, don't kill what you [/INST] hate, save what you love. And I </s><s>[INST] think we're in a society right now, [/INST] we're in a diagnosis mode, were just diagnosing and diagnosing and diagnosing and were trying to kill what we hate and we're not trying to save what we love enough. And it's um there's this Buckminster fuller quote which I'm going to butcher because I don't remember it correctly, but it's it's it's something along </s><s>[INST] the lines of um [/INST] ah </s><s>[INST] don't like [/INST] try to destroy the old </s><s>[INST] bad [/INST] models, render them obsolete with better models. You know, </s><s>[INST] maybe [/INST] we don't need to destroy the oil industry. Maybe we just create a new great new battery technology and sustainable transport </s><s>[INST] and just make [/INST] it economically unreasonable to </s><s>[INST] still continue to rely [/INST] on fossil fuels. </s><s>[INST] You know. [/INST] Um It's like it's like don't don't care what you hate, say what you love like make new things and just render the old </s><s>[INST] things [/INST] unusable you know it's like if the college debt is so bad like and and universities are so expensive like in this like I feel like education is becoming </s><s>[INST] obsolete you know [/INST] I feel like we could completely revolutionize education and we could make it free and it's like you look at J. Store and like you have to pay to get all the studies and everything like what if we created a DAO that like bought J. Store or we created a dow that was funding studies and those studies were open source like or free for everyone and like like what if we just open source education education and decentralized education and made it free and </s>
<s>[INST] Yeah, that's true. But it's also very difficult to contextualize the amount. So the amount of information processing power required to simulate our universe seems like amazingly huge, [/INST] but you can always raise two to the power of that. Yeah, like numbers get big </s><s>[INST] um and were easily humbled by basically everything around us. So it's very difficult to uh to kind of make sense of anything actually when you look up at the sky and look at the stars and the immensity of it all to make sense of us. The smallness of us, the unlikely nous of everything that's on this earth coming to be, then you could basically anything could be all laws of probability go out the window to me because um I guess because the amount of information under which we're operating is very low. Well, basically, no, nothing about the world around us, relatively speaking. And so, so when I think about the simulation hypothesis, I think it's just fun to think about it. But it's also I think there is a thought experiment kind of interesting to think of the power of computation where there uh the limits of a touring machine sort of the limits of our current computers. When you start to think about artificial intelligence? How far can we get with computers? And that's kind of where the simulation of us is useful to me as a thought experiment is is the universe just the computer, is it just the computation? Is all of this just the computation and sort of the same kind of tools we apply to analyzing algorithms. Can that be applied? You know, if we scale further and further and further? Well, the arbitrary power of those systems start to create some interesting aspects that we see in our universe or is something fundamentally different needs to be created? Well, [/INST] it's interesting that in our universe it's not arbitrarily large, the power that you can place limits on, for example, how many bits of information can be stored per unit area. Right? All of the physical laws, you've got general relativity and quantum coming together to give you a certain limit on how many bits you can store within a given range before it collapses into a black hole. Like the idea that they even exist such a limit is at the very least thought provoking. When naively you might assume, oh, well, you know, technology could always get better and better. We could get clever and clever and you could just cram as much information as you want into like a small unit of space. Um that makes me think it's at least plausible that whatever the highest level of existence is, doesn't admit too many simulations or ones that are at the scale of complexity that we're looking at? Obviously it's just as conceivable that they do and that there are many. But um, I I guess what I'm channeling is the surprise that I felt upon learning that fact that there are the information is physical in this way. </s><s>[INST] Is that there's a finance to it. Okay, let me just even go off on that from mathematics perspective and the psychology perspective. How do you mix? Are you psychologically comfortable with the concept of infinity? [/INST] I think. So, are you okay with it? I'm pretty okay. Yeah. Are you okay? No, not really. It </s><s>[INST] doesn't make any sense to me. [/INST] I don't like how many, how many words, how many possible words do you think could exist that are just like strings of letters? </s><s>[INST] So that that's a sort of mathematical statement as beautiful and we use infinity and basically everything we do everything we do in in in science, Math and engineering. Yes, but you said exist. My the question is you said letters of words. I said words words the to bring words into existence to me, you have to start like saying them or like writing them or like listing them. [/INST] That's an instant creation. How many, how many abstract words exist </s><s>[INST] with the idea of an abstract the the idea of abstract notions and ideas. [/INST] I think we should be clear on terminology? I mean you think about intelligence a lot. Like artificial intelligence, Would you not say that what it's doing is a kind of abstraction, abstraction is key to conceptualizing the universe, you get this raw sensory data. You need I need something that every time you move your face a little bit and they're not pixels but like analog of pixels on my retina change entirely that I can still have some coherent notion of this is lex lex. What that requires is you have a disparate set of possible images hitting me that are unified in an ocean of right? That's a kind of abstraction. It's a thing that could apply to a lot of different images that I see and it represents it in a much more compressed way and one that's much more resilient to that. I think in the same way if I'm talking about infinity as an abstraction, I don't mean nonphysical woo woo. Like ineffable or something. What I mean, is it something that can apply to a multiplicity of situations that share certain common attribute in the same way that the images of like your face on my retina share enough common attributes that I can put this single notion to it. Like in that way infinity is an abstraction. It's very powerful and it's only through such abstractions that we can actually understand, like the world and logic and things. And in the case of infinity. The way I think about it, the key entity is the property of always being able to add one more? Like no matter how many words you can list, just throw an A at the end of one and you have another conceivable word, you don't have to think of all the words at once. It's that property. The Oh, I could always add one more that gives it this nature of infinity nous in the same way that there's certain properties of your face that give it the lexx Nous, right. Um so like infinity should be no more worrying than the eye can always add one more </s>
<s>[INST] for a few years and it felt very different to me. So for Danal of death, I don't know if he says that it's actually possible without really a lot of work to get to the actual terror. Like I think his claim is that in early, early, early childhood development, that's when the terror is real. And then we aggressively construct systems around it of social interaction to sort of construct illusions at the top of it. I'm doing a half as description of this philosophy, but it is interesting to simplify the human mind [/INST] into underlying mechanisms that drive it. Yeah, I was gonna say your thinking seems kind of poetic. Like the way that you're sort of handling these. Yeah. These concepts feel like more like aesthetically driven. </s><s>[INST] Yeah, I think this theme is gonna continue throughout this conversation as we talk about relationships and sex, yes, for sure. I think so. And I think your thinking seems to be very driven by how can I construct an experiment [/INST] to test this hypothesis. </s><s>[INST] Yeah, something like that, something like that. Yeah, but aren't, there's some things, especially that have to do with the human mind that are really messy, really difficult to understand. There's so many uncertainties and mysteries around that we don't yet have the tools to collect the data. Like one of your favorite tools is the survey, is asking people questions and then figuring out different ways to indirectly get at the truth because there's flaws to the survey, and you kind of learn about those flaws and you get better and better at asking the right questions and so on. But that's not, that's indirect access to the human mind. [/INST] But do you think like poetic narratives are? I'm not like saying poetic narratives are bad. Like I think it's like a cool way of like handling concepts, </s><s>[INST] but I'm not sure that they are more rigorous. No, no, no. Okay. No, but like they might be the more correct, like philosophy might be the right way to discuss things [/INST] that were really far from understanding. Yeah, I mean, they might be more useful shorthand. Yeah. Like morality, like I don't think morality it makes any sense, but it's really useful shorthand </s><s>[INST] to use when handling concepts in a lot of the time. Right, like ethics and morality. You could construct studies that ask different questions, like, you know, just having worked autonomous vehicles a lot the the trolley problem gets brought up and I don't know you can construct all kinds of interesting surveys about the trolley problem but does that really get at some deep moral calculus that humans do it's sexy because people like write clickbait articles about it but doesn't really get to like what you value more five grandmas or like three children whatever like they construct these arguments of like if you could steer a train if you could steer an autonomous car which do you choose yeah I don't know I don't know if it's possible with some of those to construct like sometimes the fuzzy area there's some topics that are fuzzing will forever be fuzzy given our [/INST] limited cognitive capabilities I don't know there's a way of looking at things where it's like for example the childhood fetish thing that I was talking about like deploy to your fetishes come from they can develop a narrative for it's like you know I think like this kind of thing is you know you're surrounded by feet when you're a child this cause to put fetishes and This is kind of a cool narrative. I think a lot of people's ideas about philosophy follow the same sort of thing. What is the narrative that is cool? And I think this is useful for meaning-making. I'm very pro-meaning-making. When you're talking about everything is fun because the contrast or whatever. I very much just ascribed for that. I really enjoy that philosophy. I also find everything to be very delightful. And this isn't like a question of truth. We're not like, where's the true delight that we're objectively measuring? this is a frame a poetic frame that you're using to like sort of change the way the light hits the world around you and that's super useful because it like makes you happier or something yeah but also gets to the truth or something yeah </s><s>[INST] I guess if one is true you had another question what is truth you you've actually to jump back you don't believe you believe that free will is an [/INST] illusion so why does it feel like I'm free to make any decision I want it's a cool illusion another product like where it's not of identity the pollution Oh like when he really meds hate in your sense of identity for at least for me it seems like it comes down to the sense of choice like oh I am doing the thinking like what does it mean to do with thinking it's like something in me has exclusive agency over having the spot or not having this thought like the sense of self really comes down to And so when I say that like free will is an illusion </s><s>[INST] I also mean there's something like the self is an illusion identity is a trick of the light, but it's a really fun one Yeah, you think a lot about your identity. Yeah, I have occasionally. Yeah, like you're really struggle with it You're proud of it. I do too. It's not we have different journeys, but mm-hmm [/INST] So I really take a lot of delight in it I used to be very into like deconstructing it like you probably maybe you know I did a bunch of like way too much LSD for a while and at that point very no no ego And now I'm like very ego. I really enjoy having a lot of ego </s>
<s>[INST] we need to pause it. I mean that's incredible. That's that's it's incredible that a robot is the number one selling thing that does something, yep [/INST] everything is </s><s>[INST] essential as vacuuming. [/INST] So we're </s><s>[INST] traditions. [/INST] It's still it's kind of fun to say but they just because this was a crazy idea that that just started you know in a room here um we're like do you think we can do this? So hey let's give it a try. But um but now the robots are starting to understand their environment and if you think about the next step there's two dimensions, I've been working so hard since the beginning of my robot to make robots are autonomous that um you know they're smart enough and understand their task enough. They can just go do it without human involvement. Now what I'm really excited and working on is how do I make them less autonomous meaning that the robot is supposed to be your partner, not this automaton that just goes and does what a robot does. And so that if you tell it, hey I just dropped some flour by the fridge in the kitchen. Can you deal with it wouldn't be awesome if the right thing just happened based on that utterance and to some extent that's less autonomous because it's actually listening to you, understanding the context and intent of the sentence, mapping it against its understanding of the home it lives in and knowing what to do. And so that's an area of research, it's an area where we're starting to roll out features. You can now tell your robot to clean up the kitchen and it knows what the kitchen is and can do that. And that's sort of 1.0 of where we're going. The other cool thing is that we're starting to know where stuff is and why is that important? Well, robots are supposed to have arms, right? Data had an arm, rosie had an arm Robby. The robot had, I mean, you know, they are physical things that move around in an environment. They're supposed to like do work. And if you think about it, if a robot doesn't know anything where anything is, why should it have an arm? But with this new dawn of home understanding that we're starting to go enjoy, I know where the kitchen is. I might in the future no where the refrigerator is. I might if I had an arm be able to find the handle, open it and even get myself a beer. Obviously that's one of the true dreams of robotics is dead robots bringing us a beer while we watch television. But you know, I think that that new category of tasks where physical manipulation, robot arms is a just a potpourri of of new opportunity and excitement. </s><s>[INST] And you see humans as a crucial part of that. So you kind of mentioned that. And I I personally find that really compelling idea, I think full autonomy can only take us so far, especially in the home. So you see humans as helping the robot understand or give deeper meaning to the spatial information, [/INST] Right? It's it's it's a partnership, the robot is supposed to operate according to descriptors that you would use to describe your own home. The robot is supposed to in lieu of better direction kind of go about its routine, which ought to be basically right and lead to home maintained in a way that it's learned you like, but also be perpetually ready to take direction that would activate a different set of behaviors or actions to meet a current need to the extent it could actually perform that task. </s><s>[INST] So I gotta ask you, I think this is a fundamental and fascinating question because a robot has been a successful company and a rare successful robotics company. So Anke G bo Mayfield robotics with a robot curie sci fi works, rethink robotics. These were robotics companies that were founded and run by brilliant people, but all very unfortunately for at least for us roboticists and all went out of business recently. So why do you think they didn't last longer? Why do you think it is so hard to keep a robotics company [/INST] alive? You know, I I um say this only partially in jest that back in the day before Roomba. You know, I was a I was a high tech entrepreneur building robots, but it wasn't until I became a vacuum cleaner salesman that we had any success. So I mean the point is technology alone doesn't equal a successful business. We need to go and find the compelling need where the robot that we're creating can deliver clearly more value to the end user than it costs. And this is not a marginal thing where you're looking at the skin like it's close. Maybe we can hold our breath and make it work. It's clearly more value than the cost of the robot to bring, uh, you know, in the store. And I think that the challenge has been finding those businesses where that's true in a sustainable fashion. You know, the the when you get into entertainment style things, you could be the cats me out one year, but 85% of toys, regardless of their merit, failed to make it to their second season. It's just super hard to do. So, and uh, so that that's just a tough business. And there's been a lot of experimentation around, um, what is the right type of social companion, What is the right robot in the home that is doing something other than tasks people do every week that they'd rather not do. And I'm not sure we've got it all figured out right. And so that you get brilliant roboticist with super interesting robots that ultimately don't quite have that magical user experience. Uh, and thus the that value benefit equation remains ambiguous. </s>
<s>[INST] passionate about. And if the opportunity doesn't exist, how to make money on it, you can create the opportunity [/INST] to be resourceful, figure it out. Don't, don't let anybody tell you can't do it right? I I didn't know that I could have a 200 person judo school that only taught judo because it really didn't exist in this country. You know that it actually charges money like jiu jitsu charges, right? We're talking not, there's plenty of clubs out there that charge 10 bucks a month that might have 100 people, but there's not many that, you know with the tuition is $150 a month having 200 people. So that's a successful business. Um but it wasn't done before, but be passionate about it, understand you're gonna fail, understand you're gonna get knocked down beat up right? There's going to be dark days, but you've got to persevere, you gotta believe in yourself, you gotta have a plan, you have to be willing to learn from other people and that's what I did. I if I didn't know it, I brought somebody in to tell me what am I doing wrong? Like look from the outside, what do you see? Ok, great. Then you gotta be willing to change, going to be willing to adapt, you know? And I think listening, believing in myself and creating opportunity and the other thing is helping others, something I always did in my, in my judo life, in my business life. If somebody came to me and asked for help with, hey man, is there something you can do to help me? I'm trying to get this thing started, you know, I'm trying to get this, this, this dojo off the ground, or I'm trying to run this event series or you know, uh I was creative and trying to figure out a way to help them make it work because if that really was their dream and I can help them do their dream. I felt like that person would then give nothing but good, good comments about us. Good, good, Like they remember it forever. They become like family and they have the best advocates for your business ever. So the kids that I taught at my dojo were treated that way. The people that worked for me get treated that way. The people that my customers that I work with and building their does get treated that way. People that ran tournaments whether it was grapplers quest years ago and helping that guy with a full set of math for his brian simmons with his his thing or you know, uh any of the gracie's, it just it just became like family and then I just work hard and deliver on what I say I'm going to do if I say I'm gonna do what I do it. Mhm. You know, and I think it goes a long way well and I got </s><s>[INST] a comment. So in a small way I've people may not know, I think it's still on Youtube. We previously talked many years ago and [/INST] I remember </s><s>[INST] it uh you were so kind to me and you didn't really know who I was. You just took me as a human being. You welcome me into your dojo. And we just had a conversation on a podcast or whatever the heck you call that thing. And you were just very kind. And uh and you were also just it was the last conversation I had when I showed up to M. I. T. And it stayed with me. So I've resumed during this podcast, but it stayed with me because you said you said that I did a good job at this and people especially at that time didn't tell me that, you know, didn't just that that little act of kindness is probably just a regular part of your day. You had a busy day. It was at the end of the day just saying that that was powerful and that pays off somehow. Um uh thank you for that, but [/INST] I was sincere, right? It was genuine. I felt like I had been to so many interviews when it's around the olympic time. There's lots of beat reporters that come out and they're trying to get your time and they're just, they're there because they have to get the story for their newspaper or their television show. And a lot of times those people show up right and they pronounce my name wrong or they get something wrong about the background or they offend me because they call me five minutes before that they're supposed to be there and say, oh sorry, we're running late, we'll be there an hour and a half. Well, I'm a busy guy too. And you know, like you were, somebody that showed up was so prepared with your notes, knew everything about, like, the history of what I had done. </s><s>[INST] Well, the questions [/INST] you asked were </s><s>[INST] intelligent questions. [/INST] They were well thought out. And at the end of that interview, I was really genuinely impressed and I wanted to let you know you did a great job because you stood out from the rest. </s>
<s>[INST] intelligent autonomous entities, [/INST] right? And people come back with stories that are just astonishing like there's communication between these entities and often they're telling them things that, that the person says our self validating, but it seems like it's impossible, like it really seems like and again, this is what people say oftentimes that it's, it really is like downloading some intelligence from higher dimension or some whatever metaphor you want to use. Sometimes these things come up in dreams where it's like someone is exposed to something that I've had this in a in a dream, you know, where it seems like what they're being exposed to is physically impossible, but yet at the same time self validating, it seems true like that they really are figuring something out. Of course, the challenge is to say something in in concrete terms after the experience that where you could um you know, verify that in any way and I'm not familiar of any examples of that. </s><s>[INST] Well, there's a there's a sense in which I suppose the experience is like um you you're you're a limited cognitive creature that knows very little about the world and here's a chance to communicate with much wiser entities that in a way that you can't possibly understand are trying to give you hints of deeper truths, right? And so there's that kind of sense that you you can take something back but you can't where uh our cognition is not capable to fully grasp the truth, would just get a kind of sense of it. And somehow that process is mind expanding that there's a greater truth out there, right? That seems like what from the people I've heard talk about that, That seems to be what uh it is and that's so fascinating that there's um there is fundamentally to this whole thing is a communication between an entity that is other than yourself entities. So it's not just like a visual experience like uh like you're like floating through the world is there's other beings there which is kind of uh I don't know, I don't know what sort of uh from a person who likes Freud and carl Young, I don't know what to think about that. That being, of course from one perspective is just you looking in the mirror, but it could also be from another perspective, like actually talking to other beings. [/INST] Yeah, you mentioned young and I think that's he's particularly interesting and it kind of points to something I was thinking about saying is that that I think what might be going on natural from a naturalistic perspective. Um so regardless, you know, whether or not there are, you know, it doesn't depend on autonomous entities out there. What might be happening. Is that just the associative net, the level of of learning the the comprehension might be so beyond what someone is used to. That. The only way for the nervous system, for the for the aware sense of self to orient towards it is all by metaphor. And so I do think, you know, when we get into these realms as as as a strong empiricist, I I think we always got to be careful and be as grounded as possible, but I'm also willing to speculate and and sort of cast and that's wide with with caveat, but you know, I think of things like archetypes and you know, you know, it's plausible that there are certain stories, there's certain, you know, we've gone through millions of years of evolution. It may be that we have certain, um, okay characters and stories that are sort of, that our central nervous system are sort of wired to tend to, </s><s>[INST] you know, those stories that we carry those stories in us and this unlocks them in a certain kind of way. [/INST] And we think about stories like our sense of self is basically narrative self as a story and we think about the world of stories. This is why metaphors are always more powerful than um, you know, sort of laying out all the details all the time, you know, speaking in parables, it's like if you really get, you know, this is why as much as I hate it, you know, if you're presenting to congress or something and you have all the best data in the world, It's not as powerful as that one anecdote as as as the mom dying of cancer that had the psilocybin session and it transformed her life, you know, that's a story that's meaningful. And so when this kind of unimaginable kind of change and experience happens with a DMT um ingestion, it these stories of entities, they might be that, you know, stories that are constructed, that is the closest, which is not to say the stories aren't real. I mean I think we're getting two layers where it doesn't really. Right. Yeah yeah it's the closest we can come to making sense out of it because I do what we do know about these psychedelics. One of the levels beyond the receptor is that the brain is communicating with itself in a massively different way. There's massive communication with areas that don't normally communicate. And so it I think that comes with both. Its casting the nets wide. I think that comes with the insights and helpful novel ways of thinking. I do think it comes with false positives. You know that could be some of the delusion. Um And so you know when you're so far out there like with the meaty experience, like maybe alien is the the best way that the mind can wrap some arms around that. </s>
<s>[INST] of molecules and things [/INST] like that. So it's kind of almost explaining if that phenomenon is an important thing, it's kind of telling you that the fluid dynamics which describes fluids as continuous media and so on, isn't isn't really right. But so, you know, so this idea that, you know, there's a there's a it's a it's a tricky thing because as soon as you put randomness in, you have to know, you know what, how much of what's coming out is what you put in versus how much is actually something that's being generated. And what's really nice about these systems where you just have very simple initial conditions and where you get random stuff out or seemingly random stuff out is you don't have that you don't have to argue about, was there something complicated put in? Because it's plainly obvious there wasn't now, as a practical matter in doing experiments, the big thing is if the thing you see is complex and reproducible, then it didn't come from just filtering some quotes randomness from the outside world, it has to be something that is intrinsically made because it wouldn't otherwise be, I mean, you know, the the it could be the case that you set things up and it's always the same each time. And you say, well it's kind of the same, but it's not it's not random each time because it's kind of the definition of it being random. Is it was kind of picked, picked at random each time, so to speak. </s><s>[INST] So is it possible to for sure know that our universe does not at the fundamental level have randomness? Is it possible to conclusively say there's no randomness at the bottom? [/INST] Well, it's an interesting question. I mean, you know, science natural science is an inductive business, right? You observe a bunch of things and you say can we fit these together? What is our hypothesis for what's going on? The thing that I think I can say fairly definitively is at this point we understand enough about fundamental physics that there is if there was sort of an extra dice being thrown, it's something that doesn't need to be there, we can get what we see without that. Now, you know, could you add that in as an extra little feature? Oid um you know, without breaking the universe probably. But in fact almost certainly, yes. But is it necessary for understanding universe? No. And I think actually from a more fundamental point of view, it's it's I think I might be able to argue so. So one of the things that I've been interested in been pretty surprised that I've had anything sent in to say about is the question of why does the universe exist. I didn't think that was a question that I would, you know, I thought that was a far out their metaphysical kind of thing. Uh even the philosophers have stayed away from that question for the most part, it's so such a kind of uh you know, difficult to address question. But I actually think to my great surprise that from a physics project and so on that it is possible to actually address that question and explain why the universe exists. And I kind of have a suspicion, I have not thought it through. I kind of have a suspicion that that explanation will eventually show you that in no meaningful sense, can they be randomness underneath the universe? That is that if there is it's something that is necessarily irrelevant to our perception of the universe. That is that it could be there. But doesn't matter because in a sense we've already, you know, whatever it would do, whatever extra thing it would add is not relevant to our perception of what's going on. </s><s>[INST] So why does the universe exist? How does uh the irrelevance of randomness connect to? Uh the big why question? So, [/INST] Okay, so I mean why does the universe exist? Well, let's see, </s><s>[INST] and it's just the only university [/INST] we got, it's the only one that about that. I'm pretty sure. So now you </s><s>[INST] may be which one which of these topics is better to enter first. Why does the universe exist? And uh why you think it's the only one that exists? [/INST] Well, I think they're very closely related. Okay, okay. So, I mean, the first thing, let's see, I mean this why does the universe exist? Question is built on top of all these things that we've been figuring out about, fundamental physics. Because if you want to know why the universe exists, you kind of have to know what the universe is made of. And I think the well, let me let me describe a little bit about why does the universe exist? Questions So the main issue is, let's say you have a model for the universe and you say, I've got this this program or something and you run it and you make the universe. Now you say, well, how do you actually why is that program actually running? And people say you've got this program that makes the universe, What computer is it running on? Right. What does it mean? What actualize is something, you know, two plus two equals for? But that's different from saying there's to a pile of two rocks. Another pile of two rocks and somebody moves them together and makes four, so to speak. And so what is it that kind of turns it from being just this formal thing to being something that is actualized. Okay, so there we have to start thinking about, Well, well, what do we actually know about what's going on in the universe? Well, we are observers of this universe, but confusingly enough, we're part of this universe. So, in a sense, we what what what if we say, what do we what do we know about what's going on in the universe? Well, what we know is what sort of our consciousness records about what's going on in the universe and consciousness </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] Do you think it becomes, it can become like the base layer for a lot of our financial operations like become the main base layer for all our transactions. So like even even banks will use Bitcoin essentially and like Visa would use Bitcoin as the base there like it would actually operate very similarly at the at the surface layer but at the base there would all be Bitcoin [/INST] that's precisely what I expect and banks and Visa are already using Bitcoin. So Visa has embraced Bitcoin in a really big way actually and it's always funny to the people saying Bitcoin has to change in a certain way so it can compete with Visa. No Visa adopted Bitcoin, right? Paypal adopted Bitcoin square adopted Bitcoin obviously they're not tearing out all of their existing infrastructure but they're totally engaging with this thing. Banks have now begun, they got the green light to provide custody for Bitcoin for their depositors that's the first step eventually like you know it will happen one of two ways either Bitcoin, native financial institutions will become banks that's already happening. There's Bitcoin exchanges that have gotten banking licenses or banks themselves will start to engage with Bitcoin as a reserve asset. It will converge either way. That's totally happening. And yes I mean I don't think Bitcoin is going to power every financial transaction. I think it will coexist alongside sovereign currencies but I think it's a great reserve asset. It's a very powerful asset to build a financial system on top of because it's highly highly auditable. It's something that you can take physical delivery of very cheaply and those are great qualities. If you're a depositor in the bank they can prove to you how much big one they have. They can't really easily prove you know in the old system how much gold they held on deposit and you can easily conduct a run on the bank. You can hold them accountable because you can withdraw it because making a big transaction is pretty easy at the end of the day. Unlike fiat currency, it's like kind of you can't really withdrawal your dollars from the bank. I mean you sort of can but you're not going to want to take delivery of pounds of cash or anything like that. So it's a good modern asset upon which to build a financial system basically. </s><s>[INST] You mentioned square and Visa sort of investing in Bitcoin. What do you make of probably one of the higher profile big investments in Bitcoin which is Tesla and Elon musk. But there's also a few billionaires like the moth and all of them investing. What do you make of this whole movement? Why do you think they're doing it? I mean Tesla is an interesting case. Why do you think Tesla is putting uh buying so much Bitcoin? [/INST] I honestly don't know and I would love to truly know Elon's genuine thoughts on Bitcoin um because he's kind of sending us mixed messages honestly with his embrace of dosh coin which is sort of play full. Not exactly sure. We're trying to what point he's trying to make their so </s><s>[INST] you were involved with dosh coin. You mentioned offline a little bit like in the early days early is like uh played around with it. What do you make of dosh coin? What do you make of Ilan? And does what do you make of this particular meme coin? Is it is it one like a legitimate Cryptocurrency or is it to like a funny internet way of saying f you to the man. [/INST] Yeah it's a good question. I mean so I wasn't like a figurehead in dodge coin or anything but that was totally my introduction to crypto was mining, does coin in my dorm room and then tipping people online in dodge coin which I just thought was the funniest thing. Uh So I guess I was really easy to entertain back in 2013 but it was very playful at the time. There was a culture around dodge coin and the people liked it because it was in opposition to the Bitcoin culture which was really serious and involved lots of Austrian economics and Rothbard and Hayak and stuff like that. So that was my introduction to Cryptocurrency was because I thought the Bitcoin people were pretty lame and they were like way too serious about all this stuff and I was like okay I'll just be a part of the dodge coin community. And they did all these funny publicity stunts like they paid to send the jamaican bobsled team to the olympics. You know like great stuff like they put the dodge coin logo on top of a nascar car. Um and I just that tickled me so much because it's like this made up internet coin, this is back when crypto is pretty novel and still like kind of funny and stuff and that was really entertaining. Fast Forward 7, 8 years. Does corn is way less entertaining now, frankly because it's the leadership laughed the community spirit evaporated. Um The meme didn't persist. I mean does itself is not really a contemporary meme? Right? I mean it's an old meme </s><s>[INST] although that new refreshing to me like does you haven't heard that name in a long time like or does is like in a hat smoking a cigarette. I mean there's some sense where Ellen is reinvigorating the meme and it's funny because like one influential figure could do just that which just speaks to the tension that you're talking about like Tessa is investing Bitcoin and yet he also tweets about Bitcoin but he's [/INST] I mean who am I to question the meme right? Like yeah I I can't you know dissect internet culture and pathetically sit here and tell you it's an invalid meme. You know if people believe in it then it's real. </s>
<s>[INST] So in that context or maybe beyond, how do you explain us humans? How unlikely are we this intelligent civilization or is there a lot of others? Or are we alone in this universe? [/INST] Yeah. </s><s>[INST] You seem to appreciate humans very much. [/INST] I've grown fond of us. Okay, well are </s><s>[INST] nice qualities. [/INST] Um, and like I like that. I mean we're kind of weird. We spread this hair on our heads and then I don't know. So it's kind of weird animal. That's </s><s>[INST] the feature, not a bug. I think [/INST] the weirdness. Um, I hope so. I hope so. Um, I, I think if I'm just gonna answer you in terms of truth, the first thing I'd say is we're done. We're not in a privileged enough position at least as yet to really know much about who we are, how we are, what we're really like in the context of something larger. What the context is like all that stuff. We might learn more in the future are descendants might learn more, but we don't really know very much, which you can either view as frustrating or charming, like that first year of Tiktok or something. Um, but </s><s>[INST] all roads lead back to Tiktok. I [/INST] like it well lately, but, but in terms of, there's another level at which I can think about it where I sometimes think that if you are just quiet and you do something that gets you in touch with the way reality happens. And for me, it's playing music. Sometimes it seems like you can feel a bit of how the universe is and it feels like there's a lot more going on in it and there is a lot more life and a lot more stuff happening and a lot more stuff flowing through it. And I'm not speaking as a scientist now. This is kind of a more my artists like talking and it's uh, uh, so I feel like I'm suddenly in multiple personalities with you. But well, </s><s>[INST] uh, Kerouac, Jack Kerouac said that music is the only truth. What do you uh, it sounds like you might be at least in part, [/INST] there's a, there's a passage in Kerouac's book dr sacks where somebody tries to just explain the whole situation with reality and people in like a paragraph and I couldn't reproduce it for you here. But it's like, yeah, like there are these boldest things that walk around and they make these sounds, you can sort of understand them, but only kind of and then there's like this, it's like this amazing, Like just really quick. Like if if some spirit being or something was going to show up in our reality and I knew nothing about it. It's like a little basic intro of like, okay, here's what's going on here. An incredible passage. </s><s>[INST] Yeah, it's like a one or two sentence summary. Uh Hitchhiker's Guide to the Galaxy, right? Of what this uh mostly harmless. If you think there's truth to that, that music somehow connects to something that words cannot. [/INST] Yeah, music is something that just towers above me. I don't I don't I don't feel like I have an overview of it. It's just the reverse. I don't I don't fully understand it because on one level it's simple, like you can say, oh, it's it's a thing people evolved to coordinate our brains on a pattern level or a or something like that. There's all these things you can say about music which are, you know, some of that's probably true. It's also there's kind of like this, this is the mystery of meaning. Like there's a way that just instead of just being pure abstraction, music can have like this kind of substantiality to it. That is philosophically impossible. I don't know what to do with it. </s><s>[INST] Yeah. The amount of understanding I feel I have when I here the right song at the right time is not comparable to anything I can read on Wikipedia anything I can understand read through in language, their music does connect us to [/INST] something thing there. Yeah, there's, there's some kind of a thing in it. And I've never, ever, I've run across a lot of explanations from all kinds of interesting people. Uh, like that is some kind of, uh, a flow language between people or between people and how they perceive and, and that kind of thing. There's, and, and that sort of explanation is fine, but it's not, it's not quite it either. </s><s>[INST] Uh, there's something about music that makes me believe that panpsychism could possibly be true, which is that everything in the universe is cautious. It makes me think makes me be humble in how, uh, much or how little I understand about the functions of our universe that everything [/INST] might be conscious. Most people interested in theoretical physics eventually land in pen psych is, um, um, but I'm not one of them. I, uh, I still think there's this, um, pragmatic imperative to uh, treat people as special. So I will proudly be a duelist, uh, without people cats. Yeah, I'm not, I'm not, I'm not quite sure where to draw the line or why the lines there or anything like that, but I don't think I should be required to all the same questions are equally mysterious for no line. So I don't, I'm not, I don't feel disadvantaged by that. So I shall remain a duelist, but if you listen to anyone trying to explain where consciousness is in a dualistic sense, either believing in souls or some special thing in the brain or something, you pretty much they screw this. I'm going to be a pen second. </s><s>[INST] A fair enough output. Is there moments in your life that happened that we're defining in the way that you hope others, [/INST] your dog, Listen, I gotta say the moments that defined me, we're not the good ones. The moments that defined me were often horrible. Um, I, I've had successes, you know, but if you ask what defined me, my mother's death, um, um, being under the World Trade Center in the attack, um, the things that the things that have had an effect on me were the most were sort of real world, terrible things which they don't wish on young people at all. Um, and this is, this is the thing that's hard about giving advice to young people that they have to learn their own lessons and lessons don't come easily. And a world which avoids hard lessons is will be a stupid world, you know, and I don't know what to do with it. That's a, that's a little bundle of truth that has a bit of a fatalistic quality to it, but I don't, I don't, this is like what I'm saying that, you know, freedom equals eternal annoyance. Like you can't like, um, there's a degree to which honest advice is not that pleasant to give and I don't want young people to have to know about everything. I think you don't want to wish hardship on them. Yeah, I think they deserve to have a little grace period of naivety. That's pleasant. I mean, I I do you know, if it's possible, if it's Yeah, uh these things are this is like this is tricky stuff. I mean um if you if you okay, so let me try a little bit on this advice thing. I think one thing and in any serious broad advice will have been given 1000 times before for 1000 years, so I'm not gonna I'm not going to claim originality, but I think trying to find a way to really pay attention to what you're feeling fundamentally what your sense of the world is, what your intuition is. If you feel like an intuitive person, what you're um like like to try to escape the constants way of social perception or manipulation, whatever you wish not to escape it entirely. That would be horrible. But to to find to find cover from it once in a while, to find a sense of being anchored in that. To believe in experience as a real thing. Believing in experience as a real thing is very dualistic that goes in that goes with my philosophy of dualism. I believe there's something magical and I instead of squirting the magic dust on the programs. I think experiences something real and something a part of something mystical and </s>
<s>[INST] So he was deeply a man of faith and throughout his life, the nature of that faith has changed as he grew, as he interacted with, I would say a cruel society that he was living. Right, right. You mentioned he inspired Muhammad Ali who I don't think is an overstatement to say is probably the most, quite possibly the most famous American Muslim from America. Could you maybe make a few comments as an athlete yourself? What impact did Islam have on Muhammad Ali's life and vice versa? What impact did he have as a leader, [/INST] as a religious figure on the Muslim community? I think Muhammad Ali, his quotes on Islam are precious because he talks about how he sought the wealth of this world and he found it in Islam. He found a greater meaning and he attributes everything that he became to his faith. His sense of strength and commitment, the willingness to take a stand for the truth when it was extremely unpopular, on the basis of his faith and on the basis of his integrity. I think that he inspired people with his confidence and his coherence. I mean, he was incredibly eloquent. I mean, poetic and just unwavering seemed unbreakable. So as relentless as he was in the ring, he was even more so outside of the ring. The man could not be broken and everything was stacked up against him, but he perseveres and he does so then through Parkinson's and chooses to live a life of giving, a life of service, a life of using his platform to bring up issues of importance and to champion the rights of others. So he wasn't satisfied at any point in his life with simply being a boxing great, a boxing champion. He uses it for so much more. And so he goes down as one of the most famous Americans period of the 20th century. One of the most transformative Americans period of the 20th century, not just American Muslims. And a lot of people that loved him when he died would not have loved him if they were around in the 1960s and the 1970s. They said they loved him when he couldn't speak anymore. Many of those who celebrated him at the time of his death would have been his greatest opponents at the peak of his career. And when he was taking the stands that he was taking. </s><s>[INST] Yeah, he was fearless. And part of this, his faith was helping him take the fearless stance. But throughout all of it, given the strength, I think he's also a symbol of compassion. Through all the fun kind of, yeah, the poetic nature of who he was and the fearless nature of who he was, there's always like a deep love for the sport and for humanity. [/INST] Absolutely. And that's the thing, right? There was so obvious that despite everything that had happened to him, he never loses himself, neither to the fame nor to the fear. He always stays himself. He's authentic. And you know, when I went to his funeral and it was one of the most beautiful things I'd ever seen because everyone in Louisville, Kentucky had a story with Muhammad Ali, right? The guy that he saves from committing suicide, the school kids, the hotel, shuttle driver, the gas station worker, everyone has a story of Muhammad Ali in Louisville, Kentucky. And when he passes away, everybody comes out and stands in front of their homes and they take the casket and they drive around the streets of Louisville. And he had this dream. I'm very close to some of his children. Incredible people, by the way. Just incredible human beings. And he had this dream that he shared with them that he was jogging around the streets of Louisville, Kentucky, and everyone had come out to wave to him. And so he's running around jogging and waving to everybody in the streets of Louisville, Kentucky. Then he gets to the cemetery and he says he flies into the heavens. So his dream, and he had this dream years ago. I mean, if you look at his funeral, it's such a beautiful, you can't make it up. It's such a beautiful moment where it seems to come to reality because everybody in Louisville just comes out and just waves by to his casket. And then when he gets to the cemetery, the gates close and he goes off to be with his Lord. </s><s>[INST] And we pray that it's a good place for him. So Muhammad Ali is probably one of the great 20th century representatives of Islam. For me personally, at least, hopefully I'm not sure of my bias. One of the great modern representatives is Khabib Nurmagomedov, who's a great fighter and a great human being. So you've gotten a chance to meet him. I should also say you're friends, you're good friends with a lot of really interesting Muslim people. I mean, it's such a widespread religion. There's just so much variety of different people that are practicing Muslims. So what does Khabib represent? What do you like about him as a Muslim? What do you like about him as a person, as a representative of the religion? [/INST] I think Khabib, first of all, he is a great person, humble person, he's shown, and now Islam as well, kind of following in that. They're really showing the beauty of faith in their lives, their culture, their values, everything from the way that he carried himself in a principled way. You know, like every Muslim kid grew up in a public school cafeteria before Islamic schools were a thing in the United States, not eating pork, for example, and kind of being the odd person out. So when you got a fighter in the UFC scene and doesn't drink alcohol, kind of maintains like a very consistent, principled attachment to his religion, it really is inspiring. Growing up, we had Hakeem Olajuwon in the 1990s, basketball, who was fasting in the NBA. I think Khabib is that for a lot of people, a lot of young people today, and people in general. And I think beyond that, the values, how he honored his father and how he honors his mother and how he continues to put family first, that's a beautiful part of Islam. That's a beautiful part of our value system. We have a lot of emphasis on family. Family is central to Islam. And his honoring of his father was so beautiful. And again, what he's willing to do for his mother, you know, it's just so beautiful. And I think that we saw it, frankly, even with Morocco and the World Cup. And, you know, there was a lot of Islamophobia in this recent World Cup episode. You know, a lot of the criticism of Qatar, while no government is beyond reproach, certainly no government is beyond reproach, but had very obvious blatant Islamophobic undertones. And then with Morocco rising, being the first African Muslim Arab team, you know, to get that far in the World Cup, what did you see? Beyond the consistent honoring of Palestine, you also saw the honoring of the mothers. Every single time the game would end, they go into a prostration of gratitude. So just like we prostrate in prayer, a prostration of gratitude. And then they go and they kiss their mother's foreheads, dance with their mothers on the field, hug their moms and honor their moms. That's Islam for you. Khabib, after his fight, what does he do? He prostrates, he points up to the heavens, it's God, and then he prostrates. The whole Moroccan team beautifully prostrates. Even when they lost, they prostrated out of gratitude, they honored their mothers. So I think sometimes athletes are able to demonstrate some of these beautiful values of Islam in a way that the world can maybe see them </s>
<s>[INST] Economics allows for higher quality of life. You no longer it's the playground analogy you you said earlier, if there's more resources to play with, unfortunately us humans are more willing to [/INST] play with others </s><s>[INST] and maybe that is the solution and maybe, I mean for me from a technology perspective, innovation engineering helps make everybody's life better and over over that once people's lives become better they start to be um have more time to be empathetic in here [/INST] and they have more to lose when you have more to lose. It actually makes you, I think um countries are less willing to go to war when they have more to lose. And p and and families want peace when they have when when it's good at home. So I think there's an element of that as well </s><s>[INST] and some of it again, taking us back to the other aspect of our conversation is how we're conducting ourselves in conversation online and so on. Because I think actually I'm a big fan of the idea of social media, that is a way for us to [/INST] connect </s><s>[INST] together. I think there's a lot of really strong ideas how to do that well and clearly the initial attempts that kind of just um open it up wide, some of the lesser aspects of human nature can take over when combined with different forces like advertisements and virology and all those kinds of things. But overall [/INST] I </s><s>[INST] love the honesty of the mess of it being presented before us on social media. I was part of me maybe because I don't participate it. Like if somebody is being mean to me or being aggressive and these kinds of things, I enjoy it because it's human nature, but I enjoy it because I don't respond. I think if I responded, I would get pulled into this human nature and then it's not fun, but I I love the like I'll talk to people. In fact, I still visit clubhouse. I don't know if you know what that is. Alright, that's what [/INST] actually, when I was like, well, yeah, </s><s>[INST] well, I was such a Fanboy actually when I first heard you and uh, I was like, I can't believe I get [/INST] David will </s><s>[INST] be, but the Israel Palestine um, topic was something that was very deeply in the heated way uh, discussed on clubhouse. Race relations is the thing that was really heatedly discussed and I now go to clubhouse to practice Russian and they're in Russian. The heated discussion is on basically any topic as meaningless or meaningful as you want in the heat of it just people just screaming and and then calming down and going through the full process. And that, that too is beautiful because that emotion is there and if it is allowed to have a voice, I think ultimately it's, it leads to healing. Um, so that, that felt really healthy. If you learn how to do that at scale [/INST] social media, I wish that it were not as algorithmic lee biased towards conflict. Um, I don't think that that's healthy, but I do, I think it brings a lot of blessings into people's lives if they use it wisely, you know, it can like anything else, it can be awful, but, but it can't, I I've connected to all sorts of people that I never would have known. Um, and that's been wonderful. So </s><s>[INST] let me ask you the big question of advice, what advice would you give to young people today uh that were maybe high school college, thinking about career, thinking about life that can be proud of. [/INST] So the first thing that I would say is that life is longer than you think it is, even though I understand the impulse to be in a rush ah you will have many unfold ing's more even than people of my generation did </s><s>[INST] unfolding. That's just a funny word. It's it's just it's but it feels [/INST] that way. It's like different aspects of your life will come, will will show you different possibilities that you don't imagine at the moment. Um and and I think the second thing that I would say is um I know that this is a very old fashioned, but I would say don't no if to the extent that you can read, don't just and not just on social media, read books, learn things that will give you a broader context for your life than just today or yesterday or the day before. Uh And and I suppose the other thing that I would say is um that to the extent that you can try to develop your own internal metric of both what matters and what is good because you will be exposed to more voices than any generation in history telling you that that's good or this is good, they're called influences influencers, but what they are is voices telling you what you should think and what you should believe. And so have some internal space where you, you where you'll be able to say, for example, I know this person is doing that and it looks great, but that's not me. </s><s>[INST] You have a community of people that um, speak to you with a lot of passion. And do you still have that voice in your own, in the privacy of your own mind that you're able to ignore? Like for a moment, just be with yourself. Think what is right? [/INST] Absolutely. And I think it's partly because I grew up without that. I mean, I grew up with a lot of space in my life. And so I had a chance to develop that voice. That's why I think it's harder for kids today than it was for me. I mean, I grew up when there were three channels, there was 36 and 10, there was abc CBS and NBC and, and that was it. And you spent your evening, you know, playing board games or reading or whatever and there was a lot of space and we played football in the street and you went on your bike in the morning and nobody worried about you and you came home at night and everybody assumed you were fine. Um, and, and so I really feel. And also I went into a religious tradition where I feel like I, I have the opportunity to judge myself by bigger metrics. Um and it's still hard, I don't want to, it's not like, oh, it's I you know, I wear Impenetrable armor, it's still hard. So how much harder for kids today when they don't have that? </s>
<s>[INST] of celebration of misery. [/INST] No, no, no, no, no, no, no. So let me give you a couple more examples and and then I'll answer that question. So another example is I I picked up this book that I had from my childhood and I started reading stories to my kids. And the first story is about these two Children. One is really poor living on the street and the other one is really rich living in the house and the bright light above and the poor one is wishing looking out that window and wishing that he could have that house. And the other one is at the window wishing that he was free that he wasn't sick all the time that you could escape outside. It's only four pages long. And at the end both Children die, one of them dies from cold. The other one dies from illness and you're like, how is that even a Children's story? The next story, I'm like, okay, that's fine, let's keep this one. You know? So I read this to my kids and then I read the next one and the next one is about this this woman whose brother is at war against the Turks and he is going to die. And she praised to the Virgin, please don't let him die. And the virgin appears and she's like, no problem. Tell me who to kill instead. And she's like, anyone anyone know know know, know choose one. How about this turk? This one has two kids, a beautiful family waiting for him at home. It's like, no, no, this one is another one. And then she goes through all the life stories of the other and she's like, no, no, just don't take anyone, she's like, I can't do that, I can you can choose to bring your brother back and he will be depressed for the rest of his life because he didn't fight at or because he didn't go to that battle and he will live without our she like, and in the end, the woman decides to have her brother killed instead because he died with her. I mean this is insane. So, so why am I giving you these examples? It's not a glorification of misery. It's a it's expanding your emotional range, It's teaching you that. And when I read these stories, I'm not, I'm not a jerk, I'm crying out loud, I have tears and I like my face becomes red from the pain that I'm experiencing through these stories. It's just so deeply touching to embrace the suffering not because of an accident, but because of a choice, the sacrifice to embrace the fact that not everything is cute and rosie and always ending well. And I think that we don't do a good enough job of teaching our kids that just life sucks and life is unfair sometimes and that's and that's okay. And sometimes I read a story to my kids. I read a story every night and sometimes the story is horrible and sometimes the story is good and and sort of friendly and happy. And my kids always ask, what's the moral of the story? And sometimes there's a moral and it's like, oh, you should be good or you should be nice, you should be helping each other, etcetera. And sometimes you just know moral and I tell my kids, you know what sometimes just life doesn't make sense and it's okay and you can't comprehend everything. And I think this concept of how do you deal with the bad days comes from the fact that we're taught we're brainwashed into thinking that every day should be a happy day and we're not ready to cope with misery. And the other thing that crying through these stories teaches you is that you don't have it nearly half as bad as you think. Do you see. Do you see what I mean, basically? It tells you that, I mean, my mom would always tell me about how she was transformed as a teenager when she volunteered in the hospital and she saw all these people at the brink of death clinging for life and helping them out the best she could and crying her her heart out when they were dying and how that taught her the appreciation for what we have every day, waking up every morning and saying my life doesn't suck. My life is not nearly half as bad as it could be and and sort of embracing the joy that we have of living where we live in the moment we live and I'm going to go further. If you look at the arc of human, um, life, you know, human existence through the centuries, there's no better way to be alive than now. I mean we're complaining about every single little thing, but life expectancy is at an all time high sickness all time low, pour nous misery all time low. There's no better time to be alive globally Across all of human existence. Number one, number two, here in boston, there's no better place to be alive. If you think about the amalgamation of science engineering technology, the ridiculously awesome people you're bringing every week to your podcast. I mean, this is the ancient Greece of modern society, </s><s>[INST] but the weather still sucks because no, [/INST] let me put it this way. The weather gives us a range of emotions, the full range, full scenic patterns, </s>
<s>[INST] I mean it's a really powerful way to think about those five minute chunks. Just get one of them right in a day. [/INST] Yeah, if you do that for 200 days, your life is in order. You know, I thought I did that with my clients a lot. So a lot of them would come home from work, the guys say and and their wives would meet them at the door and it be a fight right away. You know, and it's a clash there because he he comes home and he's tired and hungry. He's worked all day and he's hoping that, you know, he gets welcomed when he comes back to the home. But then the wife is at home and she's been with the kids all day and she's tired and hungry and she's hoping that when he comes home he'll show her some appreciation for what's happened today. And then they clash. And then they both have problems to discuss because they've had their troubles during the day. And so then every time they get together, They're not like it's a bit of a fight for 20 minutes and then the whole evening is screwed. And so then you think okay here's the deal. It's knocking, the door will open okay? You get to pick what happens when you come home. But you have to figure out what it is. So now this is the deal. You treat yourself properly. You imagine coming home and it goes the way you want and need it to go okay what does that look like? You get to have it but you have to know what it is, what does it look like And you think okay I wanna come home, I want to be happy about coming home. I come home I opened the door. I say hello honey I'm home. My wife says hi it's so nice to hear your voice. She comes up she says hi dear. She gives you a hug. She says how was your day? And you say well we'll sit and talk about that. How was your day? Well we'll sit and talk about that. Do you need something to eat? Probably let's go sit and talk about our day. It's like that sounds pretty good. Okay that sounds pretty good. Might not be perfect. But sounds a hell of a lot better than what we're doing now. So how about we go talk to we'll go talk to your wife and say okay this is what's happening when I come home. I would like it to be better. What would you like to have happened if you could have what you wanted? So she sits down and she thinks okay if he comes home, what do I want to have happen? And then now you got two visions and you say, well what would you like? And you listen and she says what would you like? And you tell her and then you think, okay now can we bring these visions together? So not only do we both get what we want, but because we've brought them together, we even get more than we want. Well who wouldn't agree to that unless they were even down. And that's so exciting. It's not a compromise. It's a union of ideals. That's even makes a better ideal. And then you get to come home and then then there's another rule that goes along with that which is please dear have the grace To allow me to do this stupidly and badly. Well I learned at least 20 times and I'll give you the same leeway and then we'll practice stupidly for 20 times and we'll talk about it and then maybe we'll get it right for the next 10,000 times, right? And you can do that with your whole you can do that with your whole life and you can do that with your kids and you can do that with your family. Like it's not easy. But you can do it's a lot easier than the alternative. </s><s>[INST] Let me ask for some dating advice from Jordan Peterson, How do you find on that topic? The love of your life? [/INST] That's a good question. I was asked that multiple times on my tour three times in a row. In fact because we asked people to use this slide, oh gadget. That's </s><s>[INST] a popular question [/INST] to vary. It always came up to the top and I got asked that three times in a row and I didn't have a good answer. And then I thought why don't I have a good answer? I thought, oh I know why because that's a stupid question. So so why why? Because it's it's putting the cart before the horse. Here's the right question. How do I make myself into the perfect date? You answer that question and you will not have any problem answering the previous question. It's like what I want in a partner. If I offered everything I could do a partner, who would I be, you work on that? Ask that question. Just ask. Just ask yourself, okay, I have to be the person that women would want. Okay, what do they want clean. That's not a bad start reasonably good physical shape. So healthy, productive, generous, honest, willing to delay gratification. So you dance with a woman. It's like what's she doing? What are you two doing? Well, it's a pattern, you're, there's patterns happening around you. That's the music patterns, patterns of being, that's the music. Now can you align yourself with the patterns of being gracefully, that's what she's checking out. And then can you do that with her? And then can you do that in a playful and attentive manner and keep your bloody hands to yourself for at least a minute? And so can you dance in a playful manner? It's like you can go through this in your imagination and you know, you'll know, you know, and then you think, well, how far am I from those things? And the answer is usually, man, it's pretty horrible abyss separating you from that ideal. But the harder you work on offering other people what they need and want, the more people will line up to play with you. And so it's the wrong question. It's like, how can I be the best partner possible? And then you think, well, if I do that, people will just take advantage of me, and that's the non naive objection, right? Because the naive person think well I'll be good and everyone will treat me right? It's like, the cynic says no, I'll be good and someone will take me out and then you think, well, what do you do about that objection? And the answer is, well, you factor that in and that's why you're supposed to be, what is it as soft as a dove and as wise as a serpent. It's like, I know you're full of snakes, I know it maybe I know it more than you do, but we'll play anyways and that's </s>
<s>[INST] So both of the examples you've given, there's some sense in which the social interactions between humans is the kind of moving away from the full responsibility that you as a human in the view of existentialism should take on. So like isn't all isn't a basic conversation a delegation of responsibility just holding a hand there. You're putting the response some of the responsibility into the court of the other person and for the waiter, if you exist in a society, you are generally trying on a roll. I mean all of us are trying on a roll. Me wearing clothes is me trying on the role that I was told to try as opposed to walking around naked all the time. Like there's there's like standards of how you operate and that's not that's a decision, that's not my own, that's me seeing what everyone else is doing and copying them. [/INST] Yeah, exactly. So start thinks that in the ideal you should try to resist that. Other existentialists think that that's actually a clue to how you should live well. So start start says somewhere else. Hell is other people, Why as hell other people for start because other people are making choices also and when other people make choices, they put some pressure on me to think that the choice they made is one that I should uh copy or one that I should sort of promote but if I do it because they did it, then I'm in bad faith for start. So it's it is as if starts view is like we would be better if we were all alone. I mean this is this is really simplifying starts position and this is really just mostly start in a certain period of his of his formation. But anyhow we can imagine that view and I think there's something to the idea that start is attracted to it at least in the mid 40s. </s><s>[INST] Can you dig into hell is other people? Is there some obviously it's kind of almost like a literary, like you push the point strongly to really explore that point, but is there some sense in that other people ruin the experience of what it means to be human? [/INST] I think for start the phenomenon is this like it's not just that you wear clothes because people wear clothes in our society, like you have a particular style, you wear a particular kind of clothes and for start like to have that style authentically in good faith rather than in bad faith, it has to come from you, you have to make the choice, but other people are making choices also and like you're looking at their choices and you're thinking that guy looks good, maybe I could try that one on and if you try it on because you were influenced by the fact that you thought that guy was doing it well, then there's some important sense in which although that's a resource for a choice for you, it's also acting in bad faith. So so God and God wouldn't do that right, God wouldn't be influenced by others decisions. And if that's the model, then that's I think that's the sense in which he thinks hell is </s><s>[INST] what do you think parenting is, then it's like what? Because God doesn't have a parent. So aren't we significantly influenced, first of all, in the first few years of life. Um and then even even the teenager is resisting learning through resistance. So [/INST] absolutely, I mean, I think what you're pushing on is the intuition that the ideal that starts aiming at is a kind of inhuman ideal. I mean, we're there's many ways in which we're not like the traditional view of what God was one is that we're not self generating. We have parents, we were raised into traditions and social norms and were raised into an understanding of what's appropriate and inappropriate to do. And I think that's a deep intuition, I think that's exactly right martin Heidegger, who's the who's the philosophy that start thinks he's sort of taking this from, but I think starts a kind of brilliant french misinterpretation of Iger's german phenomenal logical view. Heidegger says a crucial aspect of what it is to be us is our throne nous were thrown into a situation, were thrown into history, were thrown into our parental lineage were and we don't choose it. That stuff that we don't choose. We couldn't choose if we were God and we existed outside of time maybe, but we're not, we're finite in the sense that we have a beginning that we never chose. We have an end that were, you know, often trying to resist or put off or something and in between there's a whole bunch of stuff that organizes us without our ever having made the choice and without our being the kind of being that could make the choice to allow it to organize us, we have a complicated relationship to that stuff. And I think we should talk about that at a certain point. But the first move is to say so it's just got a sort of descriptive problem. He's missed this basic fact that um there's an awful, there has to be an awful lot about us that's settled without our having made the choice to settle it that way. </s><s>[INST] Right, the throne nous of life you have, that's a fundamental part of life. You can't just escape it. [/INST] Exactly. You can't escape it all together. All </s><s>[INST] together. Yeah, exactly. [/INST] You can't escape it all together. But </s>
<s>[INST] for. And the fundamental metaphor of cognition you said is the interaction of neurons. Is that what is the metaphor? [/INST] No, no. The metaphor. The metaphors we use in in in cognitive psychology are um uh you know things like attention uh the way that memory works. You know, I retrieve something from memory right? You know, a memory retrieval occurs. What is that? You know that's not that's not a physical mechanism that I can examine in its own right. But if we if if but it's still worth having that that </s><s>[INST] metaphorical level. So yeah, I misunderstood actually. So the higher level abstractions is the metaphor that's most useful. Yes. But but what about, so how does that connect to uh the the idea that that arises from interaction of neurons even? Is the interaction of neurons also? Not a metaphor to you? Is or is it literally like that's no longer a metaphor? That's that's already that's already the lowest level of obstructions that could actually be directly studied? [/INST] Well, I'm hesitating because I think what I want to say could end up being controversial. So what I want to say is yes the interaction of the interactions of neurons. That's not metaphorical, that's a physical fact. That's where that's where the causal interactions actually occur now, I suppose you could say, well, you know, even that is metaphorical relative to the quantum events that under like, you know, I don't want to go down that </s><s>[INST] rabbit hole, those turtles on top materials, but there [/INST] is a there's a there's a reduction that you can do. You can say these psychological phenomena are can be explained through a very different kind of causal mechanism, which has to do with neurotransmitter release. And and so what we're really trying to do in neuroscience writ large as I say, which for me includes psychology is to take these psychological phenomena and map them onto neural events. Um I think remaining forever at the level of uh description that is natural for psychology, for me personally, would be disappointing. I want to understand how mental activity arises from neural neural activity. But the converse is also true studying neural activity without any sense of what you're trying to explain uh to me, feels like um at best groping around uh you know, at random </s><s>[INST] now, you kind of talked about this bridging of the gap between psychology and neuroscience, but do you think it's possible, like my love is um like I fell in love with psychology and psychiatry in general, with Freud and when I was really young and I hope to understand the mind and for me understanding the mind at least at a young age before I discovered a I and even neuroscience was to um is psychology. And do you think it's possible to understand the mind without getting into all the messy details of uh neuroscience? Like you kind of mentioned to you, it's appealing to try to understand the mechanisms at the lowest level. But do you think that's needed that's required to understand how the mind works? [/INST] That's an important part of the whole picture. But I would be the last person on earth to suggest that that reality renders psychology in its own right. Um Unproductive. I trained as a psychologist. I I am fond of saying that I have learned much more from psychology than I have from neuroscience. To me, psychology is a hugely important discipline. And and one thing that warms in my heart is that ways of, ways of investigating behavior that Have been native to cognitive psychology since it's you know, dawn in the 60's are starting to become they're starting to become interesting to ai researchers for a variety of reasons. That's been exciting </s><s>[INST] for me to see. Can you maybe talk a little bit about what what you see is um beautiful aspects of psychology may be limiting aspects of psychology. I mean maybe just started off as a science as a field to me was when I understood what psychology is analytical psychology like. The way it's actually carried out is really disappointing to see two aspects. One is how few, how small the end is, how many, how small the number of subject is in studies and two was disappointing to see how controlled the entire, how how much it was in the lab. Uh It wasn't studying humans in the wild, there was no mechanism for studying humans in the wild. So that's where I became a little bit disillusioned to uh psychology. And then the modern world of the internet is so exciting to me. The twitter data or Youtube data of human behavior on the internet becomes exciting because the end grows and then in the wild girls. But that's just my narrow sense. Do you have an optimistic or pessimistic cynical view of psychology? How do you see the field broadly? [/INST] When I was in graduate school, it was early enough that there was still a thrill in seeing that there were ways of doing, there were ways of doing experimental science um that provided insight to the structure of the mind. One thing that impressed me most when I was at that stage in my education was neuropsychology, looking at looking at analyzing the behavior of populations who had um brain damage of different kinds and trying to understand what what the what the specific deficits were that arose from a lesion in a particular part of the brain and the kind of experimentation that was done and that's still being done to get answers in that context. Was so creative and it was so um deliberate. You know, it was good science. Uh an experiment answered one question but raised another and somebody would do an experiment that answered that question. And you really felt like you were narrowing in on some kind of approximate understanding of what this part of the brain was </s>
<s>[INST] So the indices need to be able to capture some kind of dynamics [/INST] That we have had indices that capture these dynamics due to the work of Francois devious since 1925. But the economists have not even understood what divisions index truly represented. </s><s>[INST] What do you miss with such crude entities [/INST] then? Well, you missed the fact that you're supposed to have a field theoretic subject. The representative consumer should actually be a probability distribution on the space of all possible consumers weighted by the probability of getting any particular pull from the distribution. We should not have a single gauge of inflation. Like what is that in $1973 any more than you should be able to say. Uh it was 59°F on Earth yesterday. So when we get to the Cryptocurrency, what I'm going to say is that because we didn't found economic theory on the proper marginal revolution because we missed the major opportunity, which is is that the differential calculus of markets is gauge theory. It's not ordinary ah differential calculus. We found that out in finance that it was stochastic differential calculus. We have the wrong version of the differential calculus underneath all of modern economic theory. And part of what I've been pushing for in cryptocurrencies is the idea that we should be understanding that gold is a gauge theory just as modern economic theory is supposed to be a gauge theory and that we should be looking to liberate cryptocurrencies and more importantly, distributed computing from the problem of this unwanted global aspect. Which is the Blockchain. The thing that is most celebrated in some sense about Bitcoin is in fact the reason that I'm least enthusiastic about it, I'm hugely enthusiastic about what Satoshi did, but it's an intermediate step towards trying to figure out what should digital gold actually be if physical gold is a collection of up quarks and down quarks in the form of protons and neutrons held together the corks by gluons with electrons orbiting it held together by photons with the occasional weak interaction, beta decay. All of those are gauge theories. So, gold is actually coming from gauge theory and markets are coming from gauge theory and the opportunity to do locally enforced conservation laws, which effectively is what a Bitcoin transaction is. Should theoretically be founded on a different principle. That is not the Blockchain. It should be a gauge theoretic concept in which effectively the tokens are excitation is on a network of computer nodes and the fact that let's imagine that this is some token, by moving it from my custodianship to your custodianship effectively. I pushed that glass as a gauge theory towards your region of the table. We should be recognizing the gauge theory is the correct differential calculus for the 21st century. In fact it should have been there in the 20th </s><s>[INST] century. You're saying it captures these individual individual dynamics [/INST] much richer. Why should my giving you a token have to be? Why should we alert the global community in this token that that occurred? You can talk about side chains, you can talk about any means of doing this, but effectively we have a problem which is if I think about this differently, I have a glass that is excellent. You have a glass that is absent. We're supposed to call the construct er method on your glass at the same moment we call the destructor method on my glass in order to have a conservation principle. It would be far more efficient to do this with the one system that is known never to throw an exception which is nature and nature has chosen gauge theory in geometry for her underlying language. We now know due to work of Pia Melanie at Harvard Economics in the mid-1990s, um which I was her co author on but I wish to promote her as as as well as this being my idea. Um We know that modern economic theory is a naturally occurring gauge theory and the failure of that community to acknowledge that that work occurred and that it was put down for reasons that make no analytic sense. Uh is important in particular due to the relatively new innovation of distributed computing and Satoshi is brainchild. </s><s>[INST] So you're, you're thinking, we need to have the mathematics that captures, that enforces Cryptocurrency as a distributed system as opposed to centralize one where the Blockchain says that crypto should be uh, it's centralized. The [/INST] abundance economy much discussed in Silicon Valley or what's left of it is actually a huge threat to the planet because what it really is is that it is what Marc Andresen is called, software eating the world and what that means is that you're going to push things from being private goods and services into public goods and services and public goods and services cannot have price and value tied together. Ergo people will produce things of incredible value to the world that they cannot command a price and they will not be able to capture the value that they have created or a significant enough fraction of it. The abundance economy is a disaster. It will lead to a reduction in human freedom. The great innovation of Satoshi is locally enforced or semi locally enforced conservation laws where the idea is just as gold is hard, You know, why is gold hard to create or destroy its because it's created not only in stars, but in violent events involving stars like supernova collisions. Yeah, when gold is created and we transact, we're using conservation laws, the physics determines the custodianship, whatever it is that I don't have you now have. And conversely in such a situation, we should be looking for the abstraction that most closely matches the physical world because the physical world is known not to throw an exception. The Blockchain is a vulnerability. The idea that the 51% problem isn't solved that you could have crazy race conditions, all of these things. We know that they're solved inside of gauge theory somehow. So the important thing is to recognize that one of the greatest intellectual feats ever in the history of economic theory took place already and was essentially instantly buried. And I will stand by those comments, Satoshi wherever you are. I probably know you </s>
<s>[INST] Yeah it's interesting because when you grow from 2%, when you grow and the number of people using it at the scale they're using it. It's going to need to be resistant to governments and institutions messing with it. So it's interesting to see what kind of what kind of Cryptocurrency would be resistant to. That obviously does corn is gonna win. Let's be on. [/INST] Well I mean look for numbers to Cryptocurrency in the world probably by like how useful it is to people is tether which is totally centralized has blacklists. So I'm not saying there won't be like new digital assets that are lumped into this category that have usage but they're not they're not it's not the same innovation as Bitcoin. It's just sort of building on this idea of like a Euro dollar maybe like a dollar that is minted outside of the control of the U. S. Federal reserve right would be a Euro dollar so stable coins are kind of like Euro dollars just minted by private actors in a way, right? But they're still tied to the dollar pegged to the dollar. They're not escaping the system escaping the system is Bitcoin. We aren't reliant on the dollar, we have our own you know full um store value medium of exchange unit of account eventually and you know the Bitcoin world will be denominated in different terms and I think everyone everything else will be tied to it. I really do. It </s><s>[INST] does feel currently like Bitcoin is like like pirates or something like that and they're still like the central banks that are like the main navies of the of the different [/INST] nations. It's </s><s>[INST] just like if you talk about scale so there's going to be a moment. Bitcoin continues to grow and its impact when governments are going to seriously contend with, you know what do we do with this? Do you think about those moments? Is Bitcoin is the Cryptocurrency world in general going to be able to withstand the serious legal pushback from countries from nations, especially authoritarian nations. [/INST] Yeah so it's been interesting, it's been 12 years. Okay, more than 12 years since the token Nakamoto created Bitcoin and they haven't been able to stop it. They have tried, they've tried a lot, I wrote a long essay for quill it on this like like why haven't government's been able to stop Bitcoin and my thesis is essentially that there's been like this mix of different kind of technical social uh economic and political incentives and disincentives that make it very difficult. Um and I think to me that the the best way to think about it is that Bitcoin is like a trojan horse. So just just to actually tell that story just a little bit because I think it's important to understand the classical mythology tail. Um I find this very interesting of the actual trojan horse which was told in in the immediate actually by Virgil right? And the idea was the Greeks had been like trying to take the city of Troy for like a decade at these like impregnable walls and they couldn't do it and ulysses and the rest of the Greek army were like, we don't know what to do. Um so Minerva to the God of strategy in war, you know, kind of like they get this idea from her I guess to actually try to use subterfuge and trickery to take over the city. So the idea is, and this was sort of hatched by ulysses right? To put this horse together, that would kind of be like a gift. So the idea was the Greeks just pretended to leave, right, they deserted, they left behind one soldier and this horse and the trojans looked at it and they were like what is going on here? And they brought in the soldier and the soldiers like look they left there. So sorry for all of the desecration and blood spill, this is their gift to you. It's you know, honoring Minerva, you know, it's like this like you know trophy for you guys. And there were actually people inside troy uh cassandra a profit as well as Laquan who was like a priest who said no no no. This is obviously a trick. This is obviously a trick. Um, but they were like dispatched and ignored because the horse was like it was just like so badass so that the trojans were like bringing in the city so they brought it in themselves. No blood spilled it. All right in the middle of the night. Of course we, what you realize is the horse was packed with greek soldiers and they come out they let the army in which was like hiding behind an island. So this idea that like something could be so attractive that you really can't say no even if you know what's inside of it. Is it played in Bitcoin? So like Bitcoin has this number go up technology right? Is what we call it in a sort of shorthand N. G. O N. G. U. Right? But what people don't realize is that N. G. U. Is like the trojan horse inside the trojan horses. Fdu freedom go up technology. So dictators and rogue regimes and corporations are going to buy mine tax accumulate this thing because it's the best performing financial asset in the world. What they don't realize or they're going to have to ignore is that they're also aiding and abetting this freedom technology which allows individuals to be sovereign and eventually erodes their power. There's no question that rogue regimes and bad actors I've already used and will continue to use Bitcoin. The thing is when you think about a north Korea or Venezuela and that government instructs some of its bureaucrats and cronies and officials to start stealing. Bitcoins are accumulating it or whatever for short term gain to get around sanctions and use it to buy dollars or something like that. Right, which they can't get normally. Well, guess what all those people who the regime has instructed to like figure this thing out and use it. They're all going to realize, oh my God, this is money the government doesn't control and it's gonna spread like a virus. Okay, so this is like the idea of the trojan horse allegory. I think it's so important and powerful with Bitcoin. All the people talking about Bitcoin today on tv, they don't care about freedom and privacy. They just care about number go up. But what they don't realize is what's concealed within and that's very, very powerful to me. </s>
<s>[INST] So the scientific method I apply to non-science, to history, to journalism, to all of these things. [/INST] So that scientific method includes ideas, hateful ideas, ideas also. Correct, if you don't allow hateful ideas. When scientists do experiments, nobody says to them, oh, don't do that experiment, because it would be very bad if that turns out to be accurate, that outcome. That's not the way it works. </s><s>[INST] Every point of view is thrown into the marketplace, whether it's science or whether it's non-science. And that includes the kind of ideas and the kind of discourse that might actually lead [/INST] to an increase in hate on campuses. The First Amendment prohibits speech, which is liable to produce imminent, imminent violence. So for example, the exception is falsely yelling fire in a crowded movie theater. A lot of people misstate it, they say, oh, the exception is yelling fire in a movie theater. Well, if there's really a fire, you're forming a real important function by yelling fire. But it's falsely yelling fire. You start a riot, people would be crushed to try to get out. So that's one of the exceptions of the First Amendment, as the Supreme Court has defined it. There are very few exceptions, and defamation is an exception. I'm not a fan of that exception, frankly. But if you say something about somebody that has serious implications in their life, in their ability, or in a living, if you say accuse somebody of being a pedophile, when it's not true, that person can sue you. My own view is I think that's an unfortunate exception, but I'm not on the Supreme Court. I think that I'm with, a friend of mine was Nat Hentoff, Nat Hentoff who wrote for decades for The Village Voice in New York. He was a friend of mine. He was a free speech absolutist, and he wrote a fabulous book called Free Speech for Me but Not for Thee. </s><s>[INST] And he was an absolutist, and I'm with Nat Hentoff. Even on the defamation aspect, I mean, I agree with you in some sense, just practically speaking. It seems like that the best way in the public sphere to defend against defamation is with more speech, and through authenticity, through authentic communication of the truth as you [/INST] see it. Yeah. You know, at times, the Boston Globe has said something about me that hasn't been accurate. They have variably published my letter to the editor. I'm also not bashful about getting in charge and touch with the reporter. At the end of every column, they give the reporter's email address, and I know people say that I have more access to the media than most people, but all that means is I get </s><s>[INST] the fame more than most people. Can we also comment on, from the individual consumer of speech, there's a kind of sense that freedom of speech means you should be forced to read all of it. Freedom of speech versus freedom of reach. [/INST] We as consumers of speech, do we have the right to select what we read? We do, and nobody can force us to sit in the room and listen to a radio program that we don't want to listen to. Nobody can force us to read a book that we don't want to read. </s><s>[INST] The whole notion of freedom of speech means that people have autonomy on their choices. In order to form a complete mind and complete human being, there's a kind of tension of that autonomy versus consuming as many varied perspectives as possible, which is underlying the ethic of free speech. So on college campuses, it seems like a good way to develop the mind is to get as many [/INST] perspectives as possible, even if you don't really want to. That is the theory. Academic freedom is supposed to be the highest degree of free speech. You should be able to entertain all kinds of hateful, threatening ideas, and the way I put it is, there's something wrong when you can say something with complete abandon without any fear in Harvard Square, whereas on the other side of the fence, you can't say it in Harvard Yard. It should be the opposite. What happens is universities, from the best to the worst, from the most famous to the least well-known, have been taken over by administrators. Researchers do not really subsume academic values. They know nothing about the Constitution. They know nothing about free speech. They know nothing about academic freedom. They feel that their job is to keep order. So they develop speech codes, kangaroo courts to enforce the speech codes, and these are very dire developments. I wrote about them in The Shadow University in 1998 and tried to deal with them in 1999 when I started fire, co-started fire, and I would fire. The reason I'm running currently for the Harvard Board of Overseers is, what I'd like to do is convince the Harvard Corporation, the so-called president and fellows of Harvard College, the chief governing board of the university with the real power. The Board of Overseers is a secondary body, but quite influential, to fire 95 percent of the administrators. It would have a salutary effect on the academics of the university, it would have a salutary effect on free speech and academic freedom, it would cut tuitions by about 40 percent, and it would create a whole different atmosphere on the campus and the same set of MIT or any other place. </s><s>[INST] I think administrators are a very bad influence on American higher education. Can you elaborate the intuition of why this thing that you call administrative bloat [/INST] is such a bad thing for a university? First of all, just in terms of the cost of maintaining, there are more administrators in American higher education than there are faculty members. The course is enormous. Number two, they are inimical to the teaching enterprise and they feel that their job is to control things, to make sure there are no problems and nobody's feelings are hurt. Being called before a dean because you said something that insulted somebody is something that shouldn't happen in American higher education, yet it happens because you have these administrators who think it's their job to protect people from being insulted. You insult a black student, you insult a woman, there's a disciplinary hearing, well there shouldn't be. Black people are accustomed to being insulted, Jews are accustomed to being insulted, women are accustomed to being insulted and it's very good to know who doesn't like you, it's useful, it's essential information to know who doesn't like you. If everybody is forced to say, I love you and nobody can say I hate you, you get a false feel of what life is all about. </s>
<s>[INST] why does it matter that the programmer, the human is uh is bad [/INST] because the programmer is at least with the current state of the art is responsible for writing the code correctly. And it's hard enough to keep track off a recipe that you just Execute one step at a time, chop the carrots, then peel the potatoes, Mix the icing. You need your whole brain when you're when you're reading a piece of code. What what is going on? Okay, we're loading the number of mermaids in variable A. And the number of more men in variable B. And now we take the average or whatever. Uh Like just </s><s>[INST] jumping from metaphor. The metaphor. I like it. [/INST] You have to keep in your head what is in a. What is in B. What is in C. Hopefully you have better names and that is challenging enough. If you have two different pieces of code that are are sort of being executed simultaneously, whether it's using the parallel or the concurrent approach if like A. Is the number of fishermen and B. Is the number of programmers. But in another part of the code is the number of mermaids and B. Is the number of merman. And somehow that's the same variable. If you do it sequentially. If first you do your mermaid more people computation and then you do your people in the boat computation. It doesn't matter that the variables are called A. And B. And that is literally the same variable. Because you you're done with one use of that variable. But when you mix them together, suddenly the number of more people replaces the number of fishermen and your computation goes dramatically wrong. </s><s>[INST] And there's all kinds of ordering of operations that could result in the assignment of those variables. And so you have to anticipate all possible ordering [/INST] and you think you're smart and you'll put a lock around it and in practice in terms of bugs. Per line. Per 1000 lines of code. This is an area where everything is worse. </s><s>[INST] So a lock is a mechanism by which you forbid only one chef can access the oven at a time, something [/INST] like that. </s><s>[INST] And then Sema 4's allow you to do what multiple ovens. [/INST] That's not a bad idea. Because if you're sort of, if you're preparing, if you're baking cakes and you have multiple people all baking cakes, but there's only one </s><s>[INST] oven, then [/INST] maybe you can tell that the oven is in use, but maybe it's preheating. Uh, and so you have to maybe, maybe you make a sign that says oven in use, Uh, and you flip the sign over and it says often is free when you're done baking your cake. That's a lot. That's sort of. And what do you do when you have two ovens? Or maybe you have 10 ovens, you can put a separate sign on each oven. Or maybe you can sort of someone who comes in wants to see at a glance and maybe there's an electronic sign that says there are still five ovens available. Or maybe there are already three people waiting for an oven. So you can, if you see an oven that's not in use, it's already reserved for someone else who got in line first and that's sort of what what what the restaurant metaphor was trying to explain. </s><s>[INST] Yeah. So you're no tasks. You're sitting as a designer of python with a team of brilliant core developers and you have to try to figure out to what degree can any of these ideas be integrated and not. So maybe this is a good time to ask what is a sync IO And how has it evolved since Python? [/INST] wow. Yeah. So we had this really old library for for doing things concurrently, especially things that had to do with I. O. And networking IO was especially a sort of a popular topic. And In the Python Standard Library We had a brief period where there was lots of development and I think it was late 90s, maybe early 2000s. And like two little modules were added that were the state of the art of doing asynchronous io or sort of non blocking a IO which means that you can keep multiple network connections open and sort of service them all in parallel. Like a typical web server does. </s><s>[INST] So I always input Annapolis, your writing either to the network, the network connection or reading and writing to a hard drive storage and you can do the ideas you can do to to multiple while also doing computation. So running some code that does some fancy stuff. [/INST] Yeah. Like when you're writing a web server, when a request comes in a user sort of needs to see a particular web page, you have to find that page maybe in the database and formatted properly and send it back to the client and there's a lot of waiting, waiting for the database, waiting for the network and so you can handle hundreds of thousands or millions of requests concurrently on one machine. Anyway, waste of doing that in python were kind of stagnated and uh I forget it might have been around 2012, uh when someone for the umpteenth time actually said these a sink chat and a sing core modules that you have in the standard library are not quite enough to solve my particular problem. Can we add one tiny little feature and everybody said no, that stuff is not to be, you're not supposed to use that stuff, right? Your own using third party library. And then everybody started a debate about what the right third party library </s><s>[INST] was. [/INST] And somehow I I felt that that was actually a cue for well maybe we need a better state of the art module in the standard library for for multiplexing input, output from different sources. You could say that it spiraled out of control a little bit. It was at the time it was the largest python enhancement proposal that was ever proposed. </s>
<s>[INST] So it puts a mirror to us, the beautiful parts, the ugly parts, the shallow parts, the deep parts, you're right. What [/INST] I would like to see is, you know, I, I miss the days when engaging with content on youtube helped push it into my subscribers timelines. It used to be that when I liked a video safe from veritas iem it would show up in the feed On the front page of the app or the website of my subscribers and I knew that if I liked a video I could send it 100,000 views or more that no longer is true. But I think that was a good user experience when I subscribe to someone when I'm following them, I want to see more of what they like. I want them to also curate the feed for me and I think that twitter and facebook are doing that and also some ways that are kind of annoying, but I would like that to happen more and I think we would see communities being stronger on youtube if it was that way instead of youtube going well technically Michael like this very tasty um video, but people are way more likely to click on carpool karaoke. So I don't even care who they are. Just give them that, not say anything against carpool karaoke. That is an extremely important part of our society. What it means to be human on earth, you know? But </s><s>[INST] I'll say it sucks. [/INST] But, but a lot of people would disagree with you and they should be able to see as much of that as they want. And I mean, even people who don't think they like it should still be really aware of it because it's such an important thing and such an influential thing. But yeah, I just wish that like new channels I discovered that I subscribe to. I wish that my subscribers found out about that because especially in the education community, a rising tide floats all boats. If you watch a video from number file, you're just more likely to want to watch an episode from me whether it be on vessels one or ding, it's not, it's not competitive in the way that traditional tv was where it's like, well if you tune into that show, it means you're not watching mine because they both are at the same time. So helping each other out through collaborations takes a lot of work. But just through engaging commenting on their videos, liking their videos, subscribing to them, whatever that I would love to see become easier and more powerful. </s><s>[INST] So a quick and impossibly deep question. Last question about mortality. You've spoken about death is an interesting topic. Do you think about your own mortality? [/INST] Yeah, every day. It's really scary. </s><s>[INST] So, what do you think is the meaning of life that mortality makes very explicit? So why are you here on earth, Michael? What's the point of this whole thing? Oh, what you know, what does mortality in in the context of the whole universe make you realize about yourself? Just you, Michael stevens? [/INST] Well, uh it makes me realize that I am destined to become an ocean. I'm destined to become a memory and we can extend life. I think there's really exciting things being done to extend life, but we still don't know how to like, you know, protect you from some accident that could happen. You know, some unforeseen thing. Maybe we could like save my connect um and recreate my consciousness digitally. But even that could it could be lost if it's stored on a physical medium or something. So basically, I just think that embracing and realizing how cool it is, that someday I will just be an idea and there won't be a Michael anymore. That can be like, no, that's not what I meant. It'll just be what people like, they have to guess what I meant and they'll remember me and how I live on as that memory. Well, maybe not even be who I wanted to be. But there's something powerful about that and there's something powerful about letting future. People run the show themselves? I think I I'm glad to get out of their way at some point and say all right, it's your world now. </s><s>[INST] So you, the physical entity Michael has have ripple effects in the space of ideas that far outlives you in ways you can't control. But it's nevertheless fascinating to think. I mean especially with you, you can imagine an alien species when they finally arrive and destroy all of us would watch your videos to try to figure out what what were the questions. [/INST] But even if they didn't, you know, I still think that there will be ripples. Like when I say memory, I don't specifically mean people remember my name and my birth date and like there's a photo of me on Wikipedia, like all that can be lost. But I still would hope that people ask questions and, and and teach concepts and some of the ways that I have found useful and satisfying even they don't know that I was the one who tried to popularize it, that's fine. But if earth was completely destroyed, like burnt to a crisp everything on it today, what would the universe wouldn't care? Like jupiter is not going to go, oh no! And that could happen. That is so we do however, have the power to launch things into space to try to extend how long our memory exists. Um what I mean by that is, you know, we are recording things about the world and we're learning things and writing stories and all of this and preserving that is truly what I think is the essence of being a human. We are auto biographers of the universe and we're really good at it were better than fossils, were better than light spectrum were better than any of that. We, we collect much more detailed memories of what's happening, much better data and so that should be our legacy. And I hope that that's, that's kind of mine too in terms of people remembering something or having some kind of effect. But even if I don't, you can't not have an effect that this is not me feeling like I hope that I have this powerful legacy. It's like no matter who you are, you will. But you also have to embrace the fact that that impact might look really small. And that's okay. One of my favorite quotes is from Tess of the D'Urbervilles and it's along the lines of the measure of your life depends on not your external displacement but your subjective experience. If I am happy. And those that I love are happy. Can that be enough? Because if so excellent. </s>
<s>[INST] you [/INST] excited? Yeah and I was reading all these names I was called and I found these so </s><s>[INST] did you think did you ever think that you guys can be so successful like eventually this company would be so successful, did you could you possibly have imagined? [/INST] And no, we never did think that we had 14 failed business models up to 2002 and then we had two winners same year um uh huh. No and then you know, we, I remember the board um because by this time we had some venture capital in the board, went along with us building um Some robots for aiming at the Christmas 2000 to market and We went three times over what they authorized and built 70,000 of them and sold them all uh in that first because we released on September 18 and uh who sold by Christmas so it was so we were gutsy but </s><s>[INST] but yeah, you didn't think this will take over the world. Well this is uh so a lot of amazing robotics companies have gone under over the past few decades. Why do you think it's so damn hard to run a successful? Well there's a [/INST] robotics company. There's a few things. Um One is expectations of capabilities by the found us at an off base. </s><s>[INST] The founder is not the consumer and the founders [/INST] expectations what what can be delivered? Sure mispricing and what a customer thinks is a valid price is not rational necessarily. Yeah and expectations of customers. Um And just the share hardness of getting people to adopt a new technology. And I've suffered from all three of these uh you know I've had more failures and successes in terms of companies I've suffered from all three. Um So </s><s>[INST] do you think um one day there will be a robotics company and by robotics company. I mean where your primary source of income is from robots? That will be a trillion plus dollar company. And so what what would that company do? [/INST] I can't, because I'm still starting robot cos I'm not making any such predictions in my own mind. I'm not thinking about a trillion dollar company. And by the way I don't think you know in the 90s anyone was thinking that Apple would ever be a trillion dollar company. So these are these are very hard to </s><s>[INST] to predict but sorry to interrupt but don't you because I kind of have a vision in a small way, in a big vision in a small way that I see that there would be robots in the home a scale like Roomba but more and that's a trillion dollar, [/INST] Right? And I think there's a there's a real market pull for them because of the demographic inversion, you know, who's who's gonna do all the stuff for the older people. Um There's too many, you know, I'm leading here, it's gonna be too many of us and um um but we don't have capable enough robots to make that economic argument at this point. Do I expect that that will happen? Yes, I expect that will happen. But I got to tell you, we introduced the Roomba in 2000 and two and I stayed another nine years. We were always trying to find what the next home robot would be in Still today. The primary product of 20 years later, almost 20 years later, 19 years later, the primary product is still a Roomba. So I robot hasn't found the next one. </s><s>[INST] Do you think it's possible for one person the garage to build it versus like google launching google self driving car that turns into a mo do you think it's part like this is almost like what it takes to build a successful robotics company. Do you think it's possible to go from the ground up or is it just too much capital investment? [/INST] Yeah. So it's very hard to get there um without a lot of capital and we're starting to see, You know, uh pear chunks of capital for some robotics companies. Um you know, serious bees. It was, I saw one yesterday for $80 million. I think it was for co variant. Um uh Yeah, But it can take real money to get into these things and you may fail along the way. I've certainly failed a rethink robotics. Um and we lost $150 million dollars in capital. So </s><s>[INST] okay, so rethink robotics is another amazing robotics company co founded. So what was the vision there? What was the dream and what are you most proud of? What rethink robotics? [/INST] I'm most proud of the fact that we got um robots out of the cage in factories that was safe. Absolutely safe for people and robots to be next to each other. </s><s>[INST] So these are robotic arms, robotic arms [/INST] were able to pick up </s><s>[INST] stuff and interact with humans [/INST] and that humans could re task them without writing code. And now that's sort of become an expectation for a lot of other little companies and big companies are advertising they're doing </s><s>[INST] that's both an interface problem and also safety problem. Yeah. [/INST] So I'm most proud of that. Yeah, I completely, I let myself be talked out of what I want to do and you know, you've always got, you know, I can't replay the tape, I can't replay it. Maybe, maybe you know, if I had been stronger on, and I remember the day I remember the exact meeting, um, </s><s>[INST] can you take me through that meeting? [/INST] Yeah. Um, So I'd said that I'd set as a target for the company that we were going to build $3,000 robots with force feedback. Um, that was safe for people to be around, wow, that was my goal. And we built, so we started in 2008 and we had prototypes built of plastic, plastic gearboxes. And at the $3,000, you know, uh, lifetime or $3,000, I was saying, we're going to go after not the people who already have robot arms and factories. The people would never have a robot arm. We're gonna go after a different market. So we don't have to meet their expectations. And, and so we're going to build it out of plastic. It doesn't have to have a 35,000 our lifetime, it's gonna be so cheap that it's optics, not Capex. Um, and so we had, we had a prototype that worked reasonably well, but the control engineers were complaining about these plastic gearboxes with a beautiful little planetary gearbox. Um, but uh, we could use something called series elastic actuators. We embedded them in there. We can measure forces were, you knew when we hit something, etcetera. The control engineers were saying, yeah, but this is talk ripple because these plastic gears, they're not great gears and this ripple. And trying to do force control around this ripple is so hard and I'm not going to name names. But I remember one of the mechanical engineers saying we'll just build a metal gearbox with spur gears and it will take six weeks will be done. Problem solved. Two years later we got to get the spur gearbox working. Yeah, we cost reduced in every possible way we could. Um Yeah, but now the price went up to and then the ceo at the time said, well we have to have two arms, not one arm. So our first robot product Baxter now cost $25,000. Mhm. And the only people who are gonna look at that were people who had arms and factories because that was somewhat cheaper to arms and arms and factories. But they were used to 0.1 millimeter reproduce reproducibility of motion and certain velocities. And we kept thinking, but that's not what we're giving you. You don't need position repeatability. Use force control like a human doesn't know. No, but we want we want that repeatability. We want that repeatability as all the other robots have that repeatability. Why don't you have that repeatability? </s>
<s>[INST] No, but the aliens have worked that out, surely. Statistically speaking, there must be a large number of aliens that are way ahead of us on this whole life question, unless there's something about this stage of intellectual evolution that often quickly results in nuclear war and destroys itself. There's something in this process that eventually, I don't know, crystallizes the complexity and either dies or stops developing, but most likely, they already figured it out, and why aren't they contacting us? Some grad student somewhere wants to study a new green planet. [/INST] Well, maybe they have. I mean, I don't have a coherent answer to your question, other than to say that if there are other aliens out there and they're far more advanced, they might be in contact with each other, and we might be at a point where what I'm saying quite critically is it takes two to talk, right? The aliens might be there, but if we don't have the ability to recognize them and talk to them, then the aliens aren't going to want to talk to us. I think that's a critical point that probably if that's a filter, there needs to be an ability for one to communicate with the other, and we need to know what life is before we do that. So we </s><s>[INST] haven't qualified to even join the club to have a talk. Well, I think they still want to teach us how to talk, right? But my worry is that, or I think they would want to teach us how to talk like you do when you meet it. I was going to say child, but that's a human species. And you want to try to communicate with them through whatever devices you can, given what an ant is like. I worry mostly about that humans are just too close-minded [/INST] or don't have the right tools. I'm going to push back on this quite significantly. I would say because we don't understand what life is, and because we don't understand how life emerged in the universe, we don't understand the physics that gave rise to life yet. That means our fundamental description, I'm way out of my pay grade even further out. But I'll say it anyway. You don't get paid much anyway, so I would say that because we don't understand the universe yet, we do not understand how the universe spat out life, and we don't know what life is. is and I think that until we understand that it is going to limit our ability to even we don't qualify to talk to the aliens. So I'm going to say that the they might be there but we just I'm not going to say that I believe in some two dimensional aliens being present. </s><s>[INST] But, yeah, but I think you're just being self critical. Like we don't qualify. I think, I think the fact that we don't qualify qualifies us we're interesting we're interesting in our [/INST] innocence. No, I'm saying that because we don't understand causal chains and the way that that information's propagated in the universe. And we don't understand what replication is yet, and we don't understand how life emerged. I think that we would not recognize aliens, and if someone doesn't recognize you, you wouldn't go and talk to it. You don't go and talk to ants, you don't go and talk to birds, or maybe some birds you do, right? Because you can, there's just enough cognition. So, I'm saying because we don't have enough, our cognitive abilities are not yet where they need to be, </s><s>[INST] we probably haven't been communicating with them. So you don't agree with the dating strategy of playing hard to get? [/INST] Because us humans, that seems to attract us. To attract us. Within a species, that's fine, but I think we don't actually have abstraction. No, actually, I think in this talk, in this conversation, you've helped me crystallize something that I think has been troubling me for a long time with a thermoparadox. I'm pretty sure that a reasonable avenue is to say that you would not go and talk to your cat about calculus, right? But I would still pet it. Sure, but I'm not talking about petting a cat. The analogy is that the aliens are not going to talk to us because we, and I'm using calculus as an analogy for abstraction, because we lack the layer, the fundamental layer of understanding what life is and what the universe is in our reality, that it would be so counterproductive interacting with intelligent alien species that it would cause more angst for the human race. </s><s>[INST] They don't care. Okay, they gotta be self-interested, so they'll probably, they more care about, is it interesting for them? Maybe they, I mean, surely there's a way to pet the cat in this analogy, because even if we lack complete understanding, it must be a very frustrating experience for other kinds of intelligence to communicate with us. Still, there must be a way to interact with us, like perturb the system in interesting ways [/INST] to see what these creatures do. Well, we might actually find the answer. I mean, again, that might be great in a simulation of the Earth, or say, let's say a simulation where we allow an intelligent AI to emerge, right? And that AI, we then give it, the objective is to be curious, interact with other intelligence in its universe. And then we might find the parameters required for that AI to walk, and I think you'll find, if the AI will not talk to other AIs that don't share the ability to abstract to the level of the AI, because it's just a cat, and are you gonna travel </s>
<s>[INST] Human being is controlling it with goggles on. So there's no it is a robot, but there's no way i [/INST] there's no way i human beings controlling it. And so that's already there and I've been interested in this problem for quite a while actually from a roboticist point of view and that's what's happening in alpha pilot, </s><s>[INST] which problem of aggressive flight [/INST] of aggressive flight, fully autonomous, aggressive flight. The problem that I'm interested in and you asked about alpha pod and I'll get there in a second, but the problem that I'm interested in, I'd love to build autonomous vehicles like drones that can go far faster than any human possibly can, I think we should recognize that we as humans have limitations in how fast we can process information and those are some biological limitations like we think about this ai this way too. I mean this has been discussed a lot and this is not my idea per se, but a lot of people kind of think about human level ai and they think that you know ai is not human level one day it'll be human level and humans and eyes they kind of interact versus I think that the situation really is that humans are at a certain place and Ai keeps improving and at some point just crosses off and you know it gets smarter and smarter and smarter and so drawn, raising the same issue. Humans play this game and you know you have to react the milliseconds and there's really you see something with your eyes and then that information just flows through your brain into your hands so that you can command it. There's some also delays on getting information back and forth. But suppose those lazy don't exist. You just just a delay between your eye and your fingers. He's a delay that a robot doesn't have to have. Um So we end up building in my research group, like systems that, you know, see things at a kilohertz, like a human, I would barely hit 100 hertz. So imagine things that c stuff in slow motion Like 10 X. Slow motion. Um It will be very useful, like we talked a lot about autonomous car. So um you know, we don't get to see it, but 100 lives are lost every day just in the United States on traffic accidents. And many of them are like known cases, you know, like the, you're coming through like a, like a ramp going into a highway, you hit somebody and you're off or you know, like you kind of get confused, you try to like swerve into the next lane, you go off the road and you crash whatever. And I think if you had enough compute in a car and a very fast camera right at the time of an accident, you could use all compute, you have like, you could shut down the infotainment system and use that kind of computing resources instead of rendering you use it for the kind of artificial intelligence that goes near the autonomy and you can you can either take control of the car and bring it to a full stop. But even even if you can't do that, you can deliver what the human is trying to do. Humans trying to change the lane but goes off the road, not being able to do that with motor skills and the eyes and you know, you can get in there and I was, there's so many other things that you can enable with what I would call high throughput computing. You know, data is coming in extremely fast and in real time you have to process it. And the current CPUS however fast you clock it are typically not enough. You need to build those computers from the ground up so that they can ingest all that data that I'm really interested in. </s><s>[INST] Just on that point, really quick is the currently, what's the bottom like you mentioned the delays in humans. Is it the hardware? So you work a lot within video hardware? Is it the hardware or is it the software? [/INST] I think it's both. I think it's but in fact they need to be co developed, I think in the future, I mean that's a little bit more than video does sort of like they almost like build the hardware and then they build a neural networks and then they build the hardware back and the neural networks back and it goes back and forth. But it's that co design and I think that, you know like we try to way back we try to build a fast drone that could use a camera image to track what's moving in order to find where it is in the world. This typical sort of visual inertial state estimation problems that we would solve. And you know we just kind of realize that we're at the limit sometimes of doing simple tasks were at the limit of the camera frame rate because if you really want to track things You want the camera image to be 90% kind of like or some somewhat the same from one frame to the next. And why are we at the limit of the camera frame rate? It's because camera captures data it puts into some serial connection it could be USB or like there's something called camera serial interface that we use a lot. It puts into some serial connection and couple wires can only transmit so much data. And you hit the Shannon limit on copper wires and you know you you hit yet another kind of universal limit that you can transfer the data. So you have to be much more intelligence on how you capture those pixels. You can take compute and put it right next to the pixels. Two people are going </s>
<s>[INST] so it can uh do adaptive cruise control things, which is like slow down for cars in front of it, maintain a certain speed and it can also do lane keeping still staying in the lane and do it better and better and better over time. It's very much machine learning based. So there's cameras, there's a driver facing camera too. Um, what else is there? What am I thinking? So the hardware versus software. So open pilot versus the actual hardware of the device. What's, can you draw that distinction? What's one? What's the other? [/INST] The hardware is pretty much a cellphone with a few additions, a cellphone with a cooling system and with a core interface connected to it. </s><s>[INST] And as my cell phone, you mean like qualcomm snapdragon [/INST] Uh yeah, the current holder is a Snapdragon 8 21. Uh, it has wifi radio has melted the radio, it has a screen. Uh, we use every part of the cell phone </s><s>[INST] and then the interface with the car is specific to the car, so you keep supporting more and more cars. [/INST] Um, yeah, so the interface of the car, I mean, the device itself just has four can busses has four can interfaces on it. They are connected through the USB port to the phone. Um, and then, yeah, on those four can busses you connected to the car and there's a little partners to do this course actually surprisingly similar. </s><s>[INST] So can is the protocol polish cars communicate and then you're able to read stuff and write stuff to be able to control the car, depending on the car. So, what's the software side, what's open pilot? [/INST] Um, so, I mean, open pilot is, the hardware is pretty simple compared to open pilot. Open pilot is uh, well, so you have a machine learning model, which it's an open pilot. It's a, it's a blob, It's just a blob of weights. It's not like people are like, oh, it's closed source. I'm like, what's a blob of weights, What do you expect? You know, </s><s>[INST] how primarily neural network based, you will [/INST] open pilot is all the software kind of around that neural network. If you have a neural network that says, here's where you want to send the car. Open pilot actually goes and executes all of that. </s><s>[INST] It cleans up the input to the neural network. It cleans up the output and executes on it so it connects the glue that connects everything together. Runs the [/INST] sensors, does a bunch of calibration for the neural network. Does deals with like, you know, if the car is on a banked road, you have to counter steer against that and the neural network can't necessarily know that by looking at the picture. Um, so you do that with, with other sensors, infusion and localizer. Open pilot also is responsible for um sending the data up to our servers so we can learn from it, logging it, recording it, running the cameras thermally managing the device, managing the disk space on the device, managing all the resources, the device. </s><s>[INST] So what since we last spoke, I don't remember one maybe a year ago, maybe a little bit longer. How has open pilot improved? [/INST] We did exactly what I promised you, I promised you that by the end of the year we would be able to remove the lanes. Um the lateral policy is now uh huh almost completely. And to end you can turn the lanes off and it will drive dry slightly worse on the highway if you turn the lanes off but you can turn the lanes off and it will drive well trained completely end to end and use your data. Um and this year we hope to do the same for the longitudinal policy. </s><s>[INST] That's the interesting thing is you're not doing, you don't appear to be, you can correct me. You don't appear to be doing lane uh detection or lane marking detection or kind of the segmentation task or any kind of object detection tasks. You're doing what's traditionally more called like end to end learning. So and trained on actual behavior of drivers when they're driving the car manually [/INST] and this is hard to do. You know, it's not supervised learning. </s><s>[INST] Yeah. But so the nice thing is there's a lot of data so it's hard and easy. Right? It's uh, we have a [/INST] lot of high quality data. </s><s>[INST] Like more than you need in the senate. Well [/INST] we were more than we do. We have way more data than we need. </s><s>[INST] I mean it's an interesting question actually because in terms of amount you have more than you need. But the, you know, driving is full of edge cases. So how do you select the data you train on? I think this is an interesting open question. Like what's what's the cleverest way to select data? That's the question Tesla is probably working on. Uh, that's, I mean the entirety machine learning. They don't seem to really care. They just kind of select data. But I feel like that if you want to solve if you want to create intelligence systems, you have to pick data well. Right. And so do you have any hints ideas of how to do it? Well, [/INST] so in some ways that is the definition i like of reinforcement learning versus supervised learning. In supervised learning the weights depend on the data. Right? Um And obviously true but the uh in reinforcement learning the data depends on the weights. Yeah. And actually both ways, </s><s>[INST] that's poetry. So it's brilliant. How [/INST] does it know what data in china will let it pick? We're not there yet, but that's the eventual. </s><s>[INST] So you're thinking it's almost like a reinforcement learning framework. [/INST] We're gonna do our l in the world every time a car makes a mistake, user disengages. We train on that and do RL in the world ship out a new model. That's an epoch. Right? </s>
<s>[INST] And even more than that, in the list of possible solutions of how to improve human civilization, orbiting black holes is not on the first page for you. It's not on the first page. Okay, I bet you did not expect us to start this conversation here, but I'm glad the places it went. I am excited on a much smaller scale of Mars, Europa, Titan, Venus, potentially having very bacteria-like life forms. Just on a small human level, it's a little bit scary, but mostly really exciting that there might be life elsewhere in the volcanoes, in the oceans, all around us, teeming, having little societies. And whether there's properties about that kind of life that's somehow different than ours. I don't know what would be more exciting if those colonies of single cell type organisms, what would be more exciting if they're different or they're the same? If they're the same, that means through the rest of the universe, there's life forms like us, something like us everywhere. If they're different, that's also really exciting because there is life forms everywhere. they're not like us. That's a little bit scary. I don't know what's scarier actually. It's both scary and exciting no matter what, right? [/INST] The idea that they could be very different is philosophically very interesting for us to open our aperture on what life and consciousness and self-replicating possibilities could look like. The question on are they different or the same, obviously there's lots of life here that is the same in some ways and different in other ways. When you take the thing that we call an invasive species is something that's still pretty the same hydrocarbon-based thing, but co-evolved with co-selective pressures in a certain environment. We move it to another environment. It might be devastating to that whole ecosystem because it's just different enough that it messes up the self-stabilizing dynamics of that ecosystem. The question of would they be different in ways where we could still figure out a way to inhabit a biosphere together or fundamentally not? Fundamentally, the nature of how they operate and the nature of how we operate would be incommensurable is a deep question. </s><s>[INST] Well, we offline talked about mimetic theory, right? It seems like if they were sufficiently different where we would not even, we can coexist on different planes, it seems like a good thing. If we're close enough together to where we'd be competing, then you're getting into the world of viruses and pathogens and all those kinds of things to where one of us would die off quickly [/INST] through basically mass murder without even- Even accidentally. Even accidentally. If we just had a self-replicating single-celled kind of creature that happened to not work well for the hydrocarbon life that was here that got introduced because it either output something that was toxic or utilized up the same resource too quickly and it just replicated faster and mutated faster. It wouldn't be a mimetic theory, conflict theory kind of harm. It would just be a von Neumann machine, a self-replicating machine that was fundamentally incompatible with these kinds of self-replicating systems with faster </s><s>[INST] OODA loops. For one final time, putting your alien flash God hat on and you look at human civilization, do you think about the 7.8 billion people on earth as individual little creatures, individual little organisms, or do you think of us as one organism with a collective intelligence? [/INST] What's the proper framework through which to analyze it again as an alien? So that I know where you're coming from, would you have asked the question the same way before the Industrial Revolution or before the agricultural revolution when there were half a billion people and no telecommunications connecting them. </s><s>[INST] I would indeed ask the question the same way, but I would be less confident about your conclusions. It would be an actually more interesting [/INST] way to ask the question at that time. But I was nevertheless asked it the same way, yes. Well let's go back further and smaller then. Rather than just a single human or the entire human species, let's look at in a relatively isolated tribe. In the relatively isolated probably sub Dunbar number sub kind of 150 people tribe, do I look at that as one entity where evolution is selecting for based on group selection or do I think of it as 150 individuals that are interacting in some way? Well, could those individuals exist without the group? No, the evolutionary adaptiveness of humans was involved critically group selection and individual humans alone trying to figure out stone tools and protection and whatever aren't what was selected for. And so I think the or is the wrong frame. I think it's individuals are affecting the group that they're a part of, they're also dependent upon and being affected by the group that they're part of. And so this now starts to get deep into political theories also which is theories that oriented towards the collective at different scales, whether a tribal scale or an empire or nation state or something and ones that orient towards the individual liberalism and stuff like that. And I think there's very obvious failure modes on both sides and so the relationship between them is more interesting to me than either of them the relationship between the individual in the collective and the question around how to have a virtuous process between those. So a good social system would be one where the organism of the individual and the organism of the group of individuals is they're both synergistic to each other. So what is best for the individuals and what's best for the whole is aligned. </s>
<s>[INST] You try you get you get a grip. [/INST] Yeah, that we got penalized. </s><s>[INST] So do you like to uh use the, do you like to post to your left? You have a right foot forward, usually you're ready, right? [/INST] I'm writing, but I know he wants my leg so I'm playing my stance just because of this game. Oh, you know all my grips that the first five minutes was to kind of try to neutralize his attacks so </s><s>[INST] he wants to get your left leg. [/INST] Yeah. </s><s>[INST] Uh Yeah, right [/INST] there. Yeah. </s><s>[INST] So how hard is that to stop that? [/INST] I mean, he felt pretty strong coming some, you know, I'm pushing the head down, trying to play with his balance. </s><s>[INST] Yeah. [/INST] If if you, if you see it, there was a pause, go back there. He charged them. There's a pause me standing in front of him. I did that on purpose. </s><s>[INST] What do you mean? [/INST] Just just in front of him because, you know, he tried and I'm like, you fail, I'm here. </s><s>[INST] There's a okay, so you could feel the frustration, [/INST] I could feel his frustrated, his frustration not be able to take me down. </s><s>[INST] Okay, So now and this is just psychological battles and [/INST] you see me walking straight into the middle of the mat and he's circling out. Yeah. See I'm going very slow recovering and </s><s>[INST] he's computing like shit because [/INST] he just made a, you know, effort trying to take me down. He needs to recover and I mean, you need to recover the other guys they're waiting for you do </s><s>[INST] I do I go for another take down because this one failed. Don't need to recalculate the strategy. [/INST] Yeah and he kept trying over and over again and keep failing. I think that frustrated him a lot on that fight. I fell I felt him kind of slowing down suddenly because he was getting nowhere </s><s>[INST] so we're five minutes in. Yeah he keeps so he never got that takedown in the in the [/INST] early </s><s>[INST] let's see. So at this point do you pull guard? Yeah. Okay [/INST] so that's when I fell </s><s>[INST] like [/INST] his mentally he's he's not he's worried now. Did </s><s>[INST] you try to pull close guard here? [/INST] No I knew he was gonna bring Danny in. </s><s>[INST] Okay because that's the defense against pulling closed guard. [/INST] But I like that what I like people bringing the knee between my legs cause see I'm gonna close my guard even with his legging because </s><s>[INST] he's he's he's stopping the, well this is awkward but because [/INST] I was holding his arm that's why he felt he had no hand to post. Got it </s><s>[INST] but still it puts a leg in but you're able to close your garden around you're okay with [/INST] that that I do that really well I sweep people from that position a </s><s>[INST] lot. What's the sweep [/INST] just pushed okay it's just </s><s>[INST] like to your left side. Yeah [/INST] okay </s><s>[INST] because he has no oh it's almost like you mean you're basically around his back a little bit, like [/INST] he knew that like I slept a lot of people with that sweep. So you see, he kept leaning to his left to my right, so I want to push them to my left. So you see him leaning over to my right a lot </s><s>[INST] for him to roll or something, [/INST] you know, I mean he's stuck, he does not really, he's he's </s><s>[INST] stuck there, [/INST] but the one thing he did, he kept off me completely, see that he's leaning to like he's too afraid of my attack now because he, you know, he should lean on me, you know, you should bring the fight to me. So when I felt him, you know, I I knew he was like, he's too worried about my attacks now, </s><s>[INST] so he can't [/INST] yeah, he's </s><s>[INST] back to the center, so [/INST] He's not engaging at that time, he's 100% just defending. So I felt that I'm like he's he doesn't want to engage and he's looking, I knew at that point he wants my foot because our first fight, I had this like the same position, I wasn't holding his arm and he went to attack my foot, which he did, you know, he got. Yeah, so I knew he was looking at my foot which </s><s>[INST] foot, my [/INST] right hand, my right foot, </s><s>[INST] okay, I'm holding, [/INST] I'm holding his arm and </s><s>[INST] now you're going to the back is an arm drag type of thing. [/INST] So the moment that I came off? Um I'm holding his arms so he cannot come up. So you know I'm holding his left arm so he cannot post a hand on the floor and come up. </s><s>[INST] And he's holding your right to try to get you basically to prevent you from attacking. [/INST] Yeah. </s><s>[INST] That's an interesting. And he rolls. [/INST] Yeah he tried to he tried to get me off balance so see now I'm switching I switch the grip on his arm so I can free my left arm. Can I </s><s>[INST] ask you a question? Like [/INST] uh </s><s>[INST] was there a chance he sweeps you here? [/INST] I mean there's always a chance but </s><s>[INST] like that Yeah, [/INST] but see my left arm is free </s><s>[INST] so you can post [/INST] why </s><s>[INST] was your left arm free? Because you were using it to get the data. Okay. So [/INST] I tried the hook now you will see. Yeah, but when I knew his hispanic ng because he didn't move that he completely opened himself up. Like I'm holding his left arm. So by holding their arm he's that prevents him from defending the hook on that side because his arm is being hold across so their arm cannot block the hook. And I mean yeah, so you see when he come up but I would say I mean that's my guess but bushes He's he's a big guy. You know he was like 110 kg. 112, something like that. </s>
<s>[INST] Thanks for listening to this conversation with David will be to support this podcast. Please check out our sponsors in the description and now let me leave you with some words from David himself. The only whole heart is a broken one because it lets the light [/INST] in. </s><s>[INST] Thank you for listening and hope to see you next time. [/INST] </s>
<s>[INST] That was a beautifully articulated vision for the world. So thank you for that. [/INST] Thank you for that. Let's talk a little bit about life and death. I'm pro-life and anti-death. For most people, there's few exceptions and I won't mention here. </s><s>[INST] I'm glad just like your dad, you're taking a stand against death. By the way, you have a bunch of awesome music where you play piano online. Well, one of the songs that I believe you've written, the lyrics go, by the way, I like the way it sounds. People should listen to it. It's awesome. I was, I considered, I probably will cover it. It's a good song. Tell me why do you think it is a good thing that we all get old and die? It's one of the songs. I love the way it sounds, but let me ask you about death first. Do you think there's an element to death that's essential to give our life meaning? The fact that [/INST] this thing ends? Let me say, I'm pleased and a little embarrassed you've been listening to that music I put online. That's awesome. One of my regrets in life recently is I would love to get time to really produce music well. I haven't touched my sequencer software in like five years. I would love to rehearse and produce and edit, but with a two year old baby and trying to create the singularity, there's no time. So I just made the decision to, when I'm playing random shit in an off moment. Just record it. Just record it. Whatever. Maybe if I'm unfortunate enough to die, maybe that can be input to the AGI when it tries to make an accurate mind upload of me. Death is bad. I mean, that's very simple. It's baffling. We should have to say that. I mean, of course people can make meaning out of death. And if someone is tortured, maybe they can make beautiful meaning out of that torture and write a beautiful poem about what it was like to be tortured, right? I mean, we're very creative. We can milk beauty and positivity out of even the most horrible and shitty things. But just because if I was tortured, I could write a good song about what it was like to be tortured. It doesn't make torture good. And just because people are able to derive meaning and value from death doesn't mean they wouldn't derive even better meaning and value </s><s>[INST] from ongoing life without death. Which I very... So if you could live forever, that's awesome. It was like a death is bad. I mean, that's very which I very definite. Yeah. Yeah. So if you could [/INST] live forever, would you live forever? Forever. I, my, my goal with longevity research is to abolish the plague of involuntary death. I don't think people should die unless they choose to die. If I had to choose forced immortality versus dying, I would choose forced immortality. On the other hand, if I chose, if I had the choice of immortality with the choice of suicide, whenever I felt like it, of course, I would take that instead. And that's the more realistic choice. I mean, there's no reason you should have forced immortality. You should be able to live until you get sick of living, right? And that will seem insanely obvious to everyone, 50 years from now, and they will be so... I mean, people who thought death gives meaning to life, so we should all die, they will look at that 50 years from now, the way we now look at the Anabaptists in the year 1000, who gave away all their positions, went on top of the mountain for Jesus to come and bring them to the ascension. I mean, it's ridiculous that people think death is good because you gain more wisdom as you approach dying. I mean, of course it's true. I mean, I'm 53, and the fact that I might have only a few more decades left, it does make me reflect on things differently. It does give me a deeper understanding of many things, but I mean, so what? You could get a deep understanding in a lot of different ways. Pain is the same way. We're going to abolish pain, and that's even more amazing than abolishing death, right? I mean, once we get a little better at neuroscience, we'll be able to go in and adjust the brain so that pain doesn't hurt anymore, right? And that, you know, people will say that's bad because there's so much beauty in overcoming pain and suffering. Oh, sure, and there's beauty in overcoming torture too, and some people like to cut themselves, but not many, </s><s>[INST] right? I mean, to the ascension. That's an interesting, but to push back again, this is the Russian side of me. I do romanticize suffering. It's not obvious. I mean, the way you put it, it seems very logical. It's almost absurd to romanticize suffering or pain or death, but to me, a world without suffering, without pain, without death, it's not obvious what that [/INST] you can say in the people's Zoo. The people torturing each other. </s><s>[INST] I guess what I'm trying to say, I don't know if I was presented with that choice what I would choose [/INST] because to me, this is a subtler matter, and And I've posed it in this conversation in an unnecessarily extreme way. So I think the way you should think about it is what if there's a little dial on the side of your head and you could turn to how much pain hurt? Turn it down to zero, turn up to 11, like in spinal tap if it wants, maybe through an actual spinal tap, right? So I mean, would you opt to have that dial there or not? That's the question. The question isn't whether you would turn the pain down to zero all the time. Would you opt to have the dial or not? My guess is that in some dark moment of your life, you would choose to have the dial implanted </s>
<s>[INST] Yeah, and that's true because in the marketplace of ideas that could be a company that springs up, that gives Alex shows a platform and the United States is not going to prevent those companies from functioning. Of course there's uh from a technological tech from a technology perspective, there is a ws removing parlor from the platform and gets a little weird, you know, as you get closer and closer to the computer infrastructure, because then you get closer and closer to the state actually, the more you get to the infrastructure that's usually managed by the state, the closer it gets to the control of the state, I would argue AWS is pretty damn close to infrastructure that's kind of controlled by the State. If you especially look at other nations china Russia. There's uh I don't know who runs the computer infrastructure for Russia and china, but I bet the state has complete oversight over that. And so that level of computer infrastructure having control about which social networks can and cannot operate is very uncomfortable to me. But you're right. I think it's good to focus on the obvious violations of these principles as opposed to the gray areas. Of course, the gray areas are fascinating. You mentioned H. R. F. Human Rights Foundation, what is it? What is its mission? [/INST] Yes, I've been working for HF Since 2007. Um We are a charity and nonprofit 51 C three based in new york and our mission is to promote and protect individual rights and freedoms in authoritarian societies around the world. So again, we define about 95 countries as authoritarian meaning it's either a one party state or opposition politicians are outlawed or persecuted. There's no real free speech, there's no press freedom, there's no independent judiciary, there really aren't checks and balances and even trying to create like a human rights organization or like an environmental group would be illegal. Um, and the majority of the world's population lives in that environment. That's very important. You said 53%, 4.3 billion people. And </s><s>[INST] I saw you outlined a lot of different sources of suffering in the world. And then you sort of put people living under authoritarian governments as like more than all of them. Uh, I forget, I forget all the examples you provided, but [/INST] sure, I mean, it's </s><s>[INST] uh, yeah, maybe you can mention if you remember [/INST] the number of people who are refugees, the number of people who suffer from natural disasters, the number of people who live under abject poverty, the number of people who don't have access to clean drinking water. All of these are dwarfed by the number of people who live under authoritarianism. And yet it's not something that we talk about a lot because people are mercantilist and the powers that be are happy to sacrifice freedoms and privacy for money. We live in a profit seeking world to get evidence of this. Take a look at the list of sponsors of the upcoming olympics in china where the CCP is currently committing genocide against the weaker population. Or look at the number of people and the famous investors who went to Saudi Arabia a couple months ago for the Davos in the desert, Ray Dalio was there all kinds of people were there and or at least they were invited and they said they were going to go and this is a government that, uh, at the time was torturing a female activist who just wanted to drive a car. This is a government that had murdered Jim Acosta G uh, in a brutal fashion just a couple of years earlier. So, I mean, at the end of the day, when, when it comes down to brass tacks, I mean, you know, the powers that be that even the free countries are led by people who are very, very happy to sacrifice all these pretty words about human rights when when it comes down to profits, unfortunately. </s><s>[INST] So do you think capitalism that's maybe one of the flaws of capitalism is, it turns a blind eye to injustices against human nature against the human rights. Like it turns a blind eye to authoritarian governments. [/INST] Look, I think that at the end of the day, like free trade is actually really good. Um, and you can just look at France and Germany as an example of how like a capitalist structure would develop if you have to capitalist actors, they're very unlikely to fight each other is very unlikely to be violence. Right. These are two countries which basically murdered some large percentage of each other's male population three times in 100 years in three different wars. Right? And now today or is like unthinkable. And a lot of that is because of increased collaboration, increased trade. So when you have to capitalist actors, they act in a very productive way with each other. Um, but as soon as you introduce an authoritarian actor, all bets are off. So I think what you have is a conflict between capitalist actors and authoritarian actors. And at the end of the day, people need to yes, have more than just capitalist intentions in the geopolitical level I'm talking about they need to actually take a stand for principles. Otherwise you have athletes and businesses and governments that are all too happy to to do business with the chinese Communist Party for example. Right now, I think that there is a little more than just kind of the pure the pure profit. Yes. </s>
<s>[INST] in contact with them regularly. So that could be embodied robotics or that could be social media algorithms. I think that has a very significant impact and people often think like ai needs to be super smart to have an impact. I think it needs to be super integrated with society to have an impact and more and more that's happening even if they're dumb. [/INST] Yeah. Yeah. The I mean a lot of my exposure, two robots is that I'm associated with a combat robotics team and I've been to a few battlebots competitions and that's not like a lot of ways that's pretty far from the kind of robotics you're talking about because these robots are remote controlled. They're not autonomous. Um And so um they're they're pretty simple, but um, it's interesting to watch people's emotional reactions to different robots. So there was one that was in the last year's season, the 2020 season called Rusty that uh was just uh like put together out of spare parts and it looked kind of cute and it became this huge crowd favorite because you could see it was made of like salad bowls and, you know, random pieces of hardware that this guy had like scavenged from his farm. And so immediately people kind of fell in love with this one particular robot, whereas they might, other robots might be like the bad guy. And uh, if you think of professional wrestling, you know, the heel and the baby face. So people do for reasons that are hard to understand form these emotional reactions </s><s>[INST] and we form narratives in the same way we do when we meet human beings would tell stories about these objects and they can be intelligent and they could be biological, that they could be uh almost almost close to inanimate objects. Not to me is kind of fascinating. And if robots choose to lean into that, it creates an interesting world, [/INST] if they start using feedback loops to make themselves cuter, </s><s>[INST] not just cuter, but everything that humans do, let's not, let's let's let's let's not speak harshly robots, humans do the same. [/INST] Like it was wasn't meaning it in uh, but right, humans based on feedback will change their appearance </s><s>[INST] just on instagram all the time. How do I look cuter? That's the fundamental question I ask myself. [/INST] So why wouldn't why wouldn't a robot want to? It's like, oh wow, people people really don't like the, you know, quad mount machine gun, you know, on top of my turret, maybe I should get rid of that. And that would, you know, people would feel more eddies or </s><s>[INST] or lean into it [/INST] proud of it. </s><s>[INST] Uh like uh you won't take my gun, whatever they're saying is uh dead cold hands. Um I mean they're they're personality adding personality. Especially you can start to heal, you can start to weave narratives. I think that's um fascinating place where what there's this feedback loop like you said, where ai when especially when it's embodied, put some mirror to ourselves, just like other humans are close friends, they kind of teach us about ourselves, We teach each other and through that process grow close. And to me it's so fascinating to um to expand the space of deep meaningful directions beyond just humans. Mhm. That uh that's the opportunity I see with with robots and AI systems and that's why I don't like my biggest problem with social media algorithms is the lack of transparency is not the existence of the algorithms is well there's there's many things. One is the data, data should be controlled by the individual by people themselves. So but also the lack of transparency and how the algorithms work [/INST] and change your perception of what's real. Yeah. Hidden ways. Yeah. </s><s>[INST] In hidden ways. Like you should be aware just like when you take I don't know if you take psychedelics, you should be aware that you took the psychedelic. It shouldn't be a surprise. And second you should I mean uh become a student and a scholar and there should be researched on there should be open conversation about how your perception has changed and you and then you are become your own guide in this world of alter perception because arguably none of Israel [/INST] you get to choose </s><s>[INST] the flavor of real. Um I mean this is something you explore quite a bit. Do you yourself? I think that there is a bottom to it where there is reality. There's a base layer of reality that physics can explore and our human perception sort of layer stuff. Is there is there let's go to plato is there such a thing as truth? [/INST] I lean towards the platonic view of things. So I believe that mathematical objects haven't a reality that it's not all made up by human minds. Um and I don't know where that reality comes from. I can't explain it but but I do think that mathematical objects are discovered and not uh invented um the um I did a lot of not a lot, but I did some some reading of who's a role when I was writing an anthem. Um and he's a, You know, 20th century phenomenology gist. And he's writing in the he's writing at the same time as as scientists are starting to understand atoms and and becoming aware that um, that when we look at this table, it's really just a slab of almost entirely vacuum. And there's a very sparse uh arrangements of tiny, tiny little particles there um occupying that space that interact with each other in such a way that our brains perceived this object. So that's kind of kind of the beginnings of phenomenology. Um and um and his stuff is pretty hard to um hard to read. Uh you really have to take it in small bites um, and go a little bit at a time. But he's trying to come to grips with these with these kinds of questions. </s>
<s>[INST] Yeah, I mean I had this. This comes from Louie Louie C k [/INST] uh had a </s><s>[INST] show damn. I love that line. I mean there's uh he's talking to an older gentleman and louise is all like sad about um Losing a loved one. Or like getting rejected essentially like a breakup. And then the older gentleman give us some advice saying like basically criticizes louis for saying why are you moping around because this is the most this is the best part. Like losing love is the best part because that's the real losses when you forget like feeling shitty about having gone through a breakup is when you most intensely appreciate what that person meant to you. Like you most intensely feel love and some strange way by realizing that you've lost it by missing it, wishing at this moment. I wish I had that like that feeling that that's when you feel that love the most the absence of it. So the the older gentleman gives advice that that that's the best part and it can if you're good with it, it can last for the longest. [/INST] It </s><s>[INST] could be the most sort of, for a long experience of deep appreciation and emotion and so on. So that, that's kind of um that's a nice way to look at loss, which is a reminder of how much somebody meant to us. [/INST] Yeah, I mean, I think there's a lot of truth in that. Um, because yeah, you wouldn't care so much if it weren't something that mattered to you. So it's always a signpost to the direction you really want to go to. That's always what it is. Um, and it's interesting to see the way that the mystical versions of many of the great religions all point in this direction, whether you're looking at Sufism or, or the Kabbalah or in christian mysticism. You see this idea that the longing for what you lack is the very thing that gives you what you're longing for. So the longing is the cure. I mean that's the way the Sufi poet, Rumi puts it. The longing is the cure. Um, you know, and he says be thirsty like be as thirsty as you possibly can. That's what you want to be. </s><s>[INST] The good stuff is the wanting not to having [/INST] Yeah, </s><s>[INST] yeah, of course, tell that to a person that just broke up and they'll be like shut up asshole devices, sucks, I wish I had her him back. [/INST] Yeah, No, absolutely. Those are the kinds of life lessons that only work when you kind of step away for a while. They don't work in the moment, in the moment of excruciating. There is something about the fact of knowing that all humans are in that experience together. That is also incredibly uplifting. </s><s>[INST] Well, that takes time for people to realize like, um you know, like heartbreak in your early teenage years or something like that could feel like this is completely the most novel [/INST] in </s><s>[INST] the most dramatic uh pain that any human has ever felt, right, or maybe even when you're younger. And then one of the process, one of the things you realize is that everybody goes through this, that can be an awakening to the fact that we're all in this together. This human condition is not just a personal experience experience we all share. And that's uh that's the kind of love, the unity of [/INST] it. You </s><s>[INST] can get to experience [/INST] really deep kind of love. And I feel like, you know, we're we are prevented from perceiving that love as it's actually like the most obvious kind of love. And it's right there and it happens all the time, but were prevented from perceiving it because we're not really supposed to talk about things like that. It's like there's something unseemly about it. </s><s>[INST] Well, it's also in the in the West is this individualist society. So like there's a pressure to sort of see the individual as a distinct sovereign entity that um experiences things. And it's not the unity between people is not it's not obviously sort of communicated and talked about as part of the culture. [/INST] Yeah, it's not part of the culture and yet, you know, you see it in our behaviors because we're humans. So you know, why do people listen to sad music? I mean one reason is they're hearing expressed for them. Like the musician is basically saying to them this thing that you have experienced, I've experienced it too. So have lots of other people and but they're saying it all without words and it's transformed into something beautiful and there's something about that that's just incredibly elevating and people don't know it. But there's one study that I have in bittersweet, they found that people whose favorite songs are there happy songs play it on their playlist about 100 and 75 times with people who love sad music, play them about 800 times and they say that they feel connected to the sublime when when they're listening to that music. </s><s>[INST] What what do you think that is? So what is that, what what is it in music that connects us to the sublime through sadness? [/INST] I mean I have a bunch of different theories like the whole reason I started writing this book is because I kept having this reaction reliably to sad music and I realized that for people who I knew who were religious believers, the way they described their experience of God was what I was experiencing when I would hear that music, like all the time it happens over and over again. </s><s>[INST] So you you wonder what that is [/INST] and yeah, so I started wondering what that is. Um and lots of people have tried to figure out, you know what that's all about. Um and there are different theories that it's expressing, its like a kind of catharsis for our difficult emotions, that it's as we were saying, a sense of being in it together, we don't react in that sort of uplifted way when you just see um like a slideshow of sad faces, which is something researchers have actually tested. No one really cares when they're seeing the slide to the sad faces, but the sad music, they're really reacting and also they don't really react when they're hearing music expressing other negative emotions like martial music or something like that. It's just the sad music that gives people this elevated sense of wonder. So I think it's the combination of the sadness and the beauty and I think it's just tapping into the essence of the human source code, which is a kind of spiritual longing, whether we're atheists or believers, there's this feeling of longing for a state and a place of perfect love and perfect unity and perfect truth and all of it and like an acute awareness that we're not there in this world and, you know, in religions, we expressed that through the longing for Mecca or Eden or Zion and artistically we express it with Dorothy longing for somewhere over the rainbow or you know, harry potter enters the story at the precise moment that he's become an orphan. Um, so he's now going to spend the rest of his life longing for these parents who he can never remember. And that's, there's something about that state that's at our very core and I think that's why we love it so much. </s>
<s>[INST] Yeah, that's how I feel too. There's open the eyes, I think, open muse or something like that. The system, It's cool. But it's like it's not compelling. For some for some reason, it could be a psychological reason to maybe we need to have a human being, a tortured soul behind the music. I don't know. [/INST] Yeah, no, that absolutely, I completely agree. But yeah, whether or not we'll have one day we'll have, you know, a song written by an Ai engine to be in like in top charts, musical charts. I wouldn't be surprised. I wouldn't be surprised. </s><s>[INST] I wonder if we already have one and it just hasn't been announced. We wouldn't know how hard is the multi protein folding problem is that kind of something you've already mentioned, which is baked into this idea of greater and greater complexity of proteins like multi domain proteins. Is that basically become multi protein complex. [/INST] Yes, you you got it. Right. So, so it's sort of it has the components of both of protein folding and protein protein interactions because in order for these domains, I mean many of these proteins actually, they never form a stable structure. You know, one of my favorite proteins, you know, and pretty much everyone who who works in the I know whom I know who works in, you know, with proteins. They always have their favorite proteins. Right. So one of my favorite proteins, probably my favorite proteins. The one that I worked when I was a post dog is a so called post synaptic density 95 pc 95 protein. So it's uh it's one of the key actors in uh in the majority of neurological processes at the molecular level. So it's a and it's essentially it's a it's a key player in the post synaptic density. So this is the crucial part of the synapse where a lot of these chemical processes are happening. So it's it has five domains. Right? So five protein domains is pretty, you know, large proteins. Uh I think uh 600 something. I mean I said uh but you know the way it's organized itself, It's flexible. Right? So it acts as a scaffold. So it is used to bring in other proteins. So they start acting in the orchestrated manner. Right, So, and the type of the shape of this protein, It's in a way there are some stable parts of this protein but there are some flexible and this flexibility is built in into the protein in order to become sort of this multi functional uh machine. </s><s>[INST] So do you think that kind of thing is also learn able through the alpha fold to kind of approach? [/INST] I mean the time will tell </s><s>[INST] is it another level of complexity? Is it uh like how big of a jump in complexity is that whole thing? To [/INST] me it's it's yet another level of complexity because when we talk about protein protein interactions and there is actually a different challenge for this called capri. And so this that is focused specifically on macro molecular interactions, protein protein, protein, Jenna, etcetera. So uh but it's you know, there are different mechanisms uh that govern molecular interactions and that need to be picked up say by a machine learning algorithm. Uh interestingly enough, we actually we participated for a few years in this competition. We typically don't participate in competitions. Uh I don't know, uh don't have enough time, you know, because it's very </s><s>[INST] intensive, it's [/INST] A very intensive process. But we participated back in uh you know, about 10 years ago. So, and the way we entered this competition. So we design a scoring function. So the function that evaluates whether or not your protein protein interaction, it's supposed to look like experimental assault. Right? So the scoring function is very critical part of the of the model prediction. So we designed it to be a machine learning fun. And so it was one of the first machine learning based scoring function used in Capri. And uh you know, essentially, you know, I learned what should contribute, what are the critical components contributing into the protein protein interaction. </s><s>[INST] So this this could be converted into learning problem and thereby could be it could be [/INST] learned, I believe so, yes. </s><s>[INST] Do you think α Fold two or something similar to it from deepmind or somebody else will be will result in a Nobel prize or multiple Nobel prizes? So like the, you know, obviously, maybe not. So obviously you can't give a Nobel prize to the computer program, uh you at least for now give it to the designers of that program, but is do you see one or multiple Nobel prizes where Alpha fold two is like a large percentage of what that prize is given for. Would it lead to discoveries at the level of Nobel prizes? [/INST] I mean, I think we are definitely destined to see the Nobel price becoming sort of, to be evolving with the evolution of science. And the evolution science is such that it now becomes like really multifaceted, right? Where you you don't really have like a unique discipline, You have sort of the the a lot of cross this disciplinary talks in order to achieve, uh sort of, you know, really big advancements, uh you know, so I think, you know, the computational methods will be acknowledged in one way or another and in a as a matter of fact, uh you know, They were first acknowledged back in 2013. Right? Where, you know, the first three people were you know, awarded the normal price for the product for study, the protein folding, right? The principal and you know, I think all three of them are computational biophysicist. All right. So um you know that I think is is unavoidable. You know, it will come with the time. Um the fact that alpha fold and you know, similar approaches because again, it's a matter of time that people will embrace these uh you know, principle and we'll see more and more such, you know, such tools coming into play. But you know, these matters will be critical in a in a scientific discovery. No, no doubts about it. </s>
<s>[INST] see. But thinking of the kind of mechanism that's required to do walking as a controller is like a as a as a neural network. I think I think it's a compelling notion, but it discards quietly or at least makes implicit the fact that you need to have something like common sense reasoning to walk. It's not, it's an open question whether you do or not, but the my intuition is to be to act in this world. There's a huge knowledge base that's underlying it somehow there's so much information of the kind we have never been able to construct in our in your networks on artificial intelligence systems period, which is like, it's humbling. Uh, at least in my imagination, the amount of information required to act in this world humbles me. And I think saying that Nicola was gonna accomplish it is missing, is missing the fact that we don't yeah, we don't have yet a mechanism for constructing something like common sense reasoning and what's your sense about to linger on how much, you know, to linger on the idea of what kind of mechanism would be effective at walking? You said, just a neural network, not maybe the kind we have, but something a little bit better. We'll be able to walk easily. Don't you think? It also needs to know like huge amount of knowledge that's represented under the flag of common sense [/INST] reasoning how much common sense dollars do we actually have, imagine that you are really hard working through all your life and you form to new concepts every half hour. So you end up something like a million concepts because you don't get that old. So a million concept. That's not a lot. </s><s>[INST] It's not just a million concepts. I think it would be a lot. I personally think it might be much more than a million. But [/INST] if you think just about the numbers, you don't live that long. If you think about how many cycles do your neurons have in your life is quite limited. You don't get that old. </s><s>[INST] Yeah, but the powerful thing is the number of concepts. Uh and they're probably deeply hierarchical in nature. The relations as you described between them is the key thing. So it's like even if it's like a million concepts, the graph of relations that's formed in some kind of perhaps some kind of probabilistic relationships. That's the that's what's common sense reasoning is the relationship between things [/INST] that Yeah, so in some sense I think of the concept as the address space for our behavior programs and the behavior problems allow us to recognize objects and interact with them. Also mental objects and a large part of that is the physical world that we interact with which is this rest extend our thing which is basically navigation of information in space. And basically it's similar to a game engine. It's a physics engine that you can use to describe and predict how things that look in a particular way that feel when you touch them, particular way that appropriate, exceptional of auditory perception and so on, how they work out. So basically the geometry of all these things and this is uh Probably 80% of what our brain is doing is dealing with that with this real time simulation. And by itself a game engine is fascinating, but it's not that hard to understand what it's doing right in. Our game engines are already in some sense, uh approximating the the fidelity of what we can perceive. So if we put on an Oculus quest, you get something that is still relatively crude with respect to what we can perceive. But it's also in the same ballpark already right. It's just a couple orders of magnitudes away to home saturating our perception in terms of the complexity that it can produce. So in some sense, it's reasonable to say that our computer that you can buy put into your home is able to give a perceptual reality that has a detail that is already in the same ballpark as what your brain can process and everything else. Our ideas about the world. And I suspect that they are relatively sparse and also the intuitive models that reform about social interaction. Social interaction is not so hard. It's just hard for us nerds because we all have our wires crossed. So we need to produce them. But the prayers are present in most social animals. So it's interesting thing to note is that many um domestic social animals, like cats and dogs have better social cognition than Children. </s><s>[INST] I hope so. I hope it's not that many concepts fundamentally to do to exist in this world. [/INST] So for me, it's more like I'm afraid so because this thing that we only appear to be so complex to each other because we are so stupid. It's a little bit depressing. </s><s>[INST] Yeah. Well, that's yeah, to me that's inspiring. If if we're indeed as as um as stupid as it [/INST] seems, the things our brains don't scale and the information processing that we built tend to scale very well. </s><s>[INST] Yeah. But I mean, one of the things that worries me is that, you know that the fact that the brain doesn't scale means that that's actually a fundamental feature of the brain. You know, the all the flaws of the brain. Everything we see that we see as limitations. Perhaps there's a fundamental the constraints on the system could be the requirement of its power which is like different than our current understanding of intelligence systems were scale. Especially with deep learning, especially with reinforcement learning the hope behind open Ai and deep mind, all the major results really have to do with huge compute. And it could [/INST] Also be that our brains are so small, not just because they take up so much glucose and other body like 20% of the glucose. So they don't arbitrarily scale, but there's some animals, like elephants which have larger brains than us and they don't seem to be smarter, right elephants seem to be autistic. They have very, very good motor control and they're very good with details, but they really struggle to see the big picture. So you can make them re create drawings stroke by stroke. They can do that, but they cannot reproduce the still life. So they cannot make a drawing of a scene that I see. There will always be only able to reproduce the line drawing at least as far from what I could see in their experiments. So why is that maybe smarter elephants would meditate themselves out of existence because their brains are too large. So they basically the elephants that were not autistic, they didn't reproduce. </s>
<s>[INST] of whatever outrageous fortune may come next. I don't know, I don't know, I don't know, I don't know, again, disagreeing with an expert here. Yes, I think that's generally good advice, but I think you mentioned vulnerability, I think it's like I've just been doing a lot of research on rocket engines and rocket fuel. Speaking of fuel, I just think I get a lot from being vulnerable because vulnerable leads to intimacy in friendships and relationships, I get a lot from being intimately close with human beings, just on a friendship, on a ideal level, in conversations and so on. And so I would rather err on the side of vulnerability. To me, pride is destructive. I think I already have a pretty good engine that says like, life is awesome. I don't need help for that. That's fine. That one is working. I just feel like the way to face the world that's full of uncertainty, that could be full of cruelty is with humility and gratitude. I don't know, this pride thing, it feels like, I know that for a lot of people, it's really important to really work on pride, to make sure they don't crumble under the pressure of like, they don't give into this insecurity that destroys them. But I just, for me, empirically speaking, I seem to be happier facing the world with humility and just being grateful. The pride, I'm really worried about. [/INST] Like, it feels more destructive than anything. See, what I think, as you're telling me that, I don't want to be presumptuous, but I make some thoughts or some conclusions that tell me, hey, you're in a pretty healthy place, right? And the reason I say that is because I agree completely about vulnerability. I mean, think about humility and gratitude make us vulnerable, right? Like, wow, I'm grateful, thank you, I'm grateful for you. You know, we could get shot down or something, something bad could happen, something could make us feel bad. So yes, we need vulnerability. If we try and eliminate vulnerability, we're living miles into the envy land, right? So you're describing a healthy vulnerability, but then my brain says that's because on the other side of the seesaw, so to speak, has to be a healthy sense of self, whether we call it self-esteem or healthy pride. And then I'll cite what I think is the evidence for that is you describe the negative voice, right, as like the grumpy cat, right? But that's a good negative voice to have, right? Because it's telling you like, hey, that wasn't your best. Like, come on, do better or, right? Like you can do better like this. You know, there's a negative voice in some ways, but it believes in you, right? Where that voice could be, it could be a negative voice that says, you didn't do that well because you suck, You don't deserve anything good, right? Why should you even be alive, right? I mean, that's the negative voice that can gain so much force if there isn't a balance of healthy self-esteem. So I think because you're well balanced, you have what you need and then having more of it seems like, oh, that's not so good, but there are people whose negative voice isn't the grumpy cat, it's hateful, right? And then that's a person who needs to bring that </s><s>[INST] into greater balance. Yeah, I think my negative voice is like a grumpy cat, that's like a French existentialist, maybe a little bit of a nihilist, but it's just kinda- Sartre's cat. Yeah, Sartre's cat, so it doesn't get hateful. It's not like a Hitler cat, so it's a little more... Yeah, I guess there is kinda like this line that we've come across a couple of times between the benign and the malignant. But of course, you have to monitor that line. I think you have to be careful when you face really difficult situations of as you've gone through life, more and more difficult, you face a lot of loss and suffering, especially later in life. Oh, you have to be careful with that voice. That grumpy cat can get awfully confident. And then if you don't have any source of positive emotions [/INST] in your life, you can become too heavy of a burden. Sartre, right? Yes. Which I think this leads us to, I think is a really important fact, right? That there are some people, like a significant subset of people who get happier as they get older. They have more contentment, a stronger sense of self. You may think, how could that ever happen, right? Like we're getting closer to death, we're accumulating insults, right? Like everything hurts a little bit more, we have less energy and we accumulate losses and traumas. Why would anyone be healthier across time, be happier across time? And what we see is it's linked to the things that we're talking about, right? It's linked to say, let's say vulnerability versus pride. Like there's a good balance there, right? There's a lot of humility, there's a lot of self-esteem. The person is spending a lot of time standing back from the tapestry and looking at it, right? And what can come into people is in sort of a sense of equanimity. Like I sort of understand, you know, I'm being the best person I can be. And that's not always even great. And there are things that I don't feel great about even while I'm trying to do that. But look, I'm being who I'm choosing to be, right? And that doesn't have to be in some big way. I'm not saying that means any one specific thing. That can mean the person who's taking care of their cat and tending their garden, like that's enough. We have to have, you know, love the ability to put good things out in the world. And to put our ability to work and be, to make things different out into the world and make things better. And if we're doing that, we get happier across time because we come to a sense of peace with ourselves. I'm not supposed to be everything. I'm not supposed to do everything. I'm not supposed to fix everything, right? I'm also not supposed to suffer all the time for the things I haven't gotten right. You know what? I guess I'm kind of, and it leads back to Winnicott, right? The British physician, I'm good enough. And that seems to help people feel happy, you know, contentment and be generative and productive into later life. It's like, that's what we all should be wanting but it's even, it's kind of an afterthought though. Some people are like that as opposed to, wait a second, right? </s>
<s>[INST] That's one way to maintain privacy, right? Is like in order to protect the contents of this conversation for example, we could just generate like millions of deepfake conversations where you and I talk and say random things. So this is just one of them and nobody knows which one is the real one. This this could be fake right now. [/INST] Classic steganography technique. </s><s>[INST] Okay. Another absurd question about intelligent life because uh you know, you're you're an incredible programmer outside of everything else. We'll talk about just as a programmer. Uh Do you think intelligent beings out there, the civilizations that were out there had computers and programming? Did they do we naturally have to develop something where we engineer machines and are able to encode both knowledge into those machines and instructions that process that knowledge, process that information to make decisions and actions and so on. And would those programming languages if you think they exist be at all similar to anything we've developed. [/INST] So I don't see that much of a difference between quote unquote natural languages and programming languages. Uh huh um Yeah, I think there's so many similarities. So when asked the question, what do alien languages look like? I imagine they're not all that dissimilar from ours and I think translating in and out of them uh wouldn't be that crazy. </s><s>[INST] It was difficult to compile like DNA to python and then to see that there is a little bit of a gap in the kind of language as we use for for touring machines and the kind of language is nature seems to use a little bit maybe that's just we just haven't we haven't understood the kind of language that nature uses well yet. [/INST] DNA is a CAD model, it's not quite a programming language, it has no sort of cereal. Uh huh, execution. It's not quite uh yeah, it's a cat model. Um so I think in that sense we actually completely understand it. The problem is um you know, uh well simulating on these CAD models, I played with it a bit this year is super computational intensive if you want to go down to the molecular level where you need to go to see a lot of these phenomenon like protein folding. Um So yeah, it's not that it's it's not it's not that we don't understand it, it just requires a whole lot of compute to kind of compile it </s><s>[INST] for human minds, it's inefficient. Both for the problem for the data representation and for the programming, [/INST] it runs well on raw nature. Everyone's well in raw nature. And when we try to build emulators and simulators for that. Uh well the man's law and I've tried it. </s><s>[INST] It runs in. Yeah, you've commented elsewhere. I don't remember where that one of the problems is simulating nature is tough and if you want to sort of deploy prototype, I forgot how you you put it, but it made me laugh. But animals or humans would need to be involved in order to in order to try to run some prototype code on. Like if we're talking about Covid and viruses and so on. If you were trying to engineer some kind of defense mechanisms like a vaccine against Covid or all that kind of stuff that doing any kind of experimentation, like you can with like autonomous vehicles would be very technically cost technically and ethically costly. [/INST] I'm not sure about that. I think you can do tons of crazy biology and test too because I think my bigger complaint is more, all the tools are so bad, </s><s>[INST] like literally you mean like, like I'm not crazy and [/INST] I'm not high petting shit like you're handing me up. I got to know. No, no, there has to be some uh </s><s>[INST] huh like automating stuff and and like the Yeah, but human biology is messy. Like it seems like [/INST] look at those Theranos videos, they were a joke. It's like it's like a little Gantry Xy Gantry high school science project with the pipe at like </s><s>[INST] really something you can't [/INST] build like nice micro fluid IX and I can program the, you know, computation to bio interface. This is going to happen. But like right now if you are asking me to pipette 50 ml of solution amount, it was just so crude. </s><s>[INST] Okay, let's get all the crazy out of the way. So a bunch of people asked me since we talked about the simulation last time we talked about hacking the simulation, do you have any updates? Any insights about how we might be able to go about hacking simulation If we indeed do live in a simulation? [/INST] I think a lot of people misinterpreted the point of that South by talk. The point of the south by talk was not literally to hack the simulation. Uh I think that this, this is, this is an idea is literally just I think theoretical physics, I think that's the whole, you know, the whole goal. Right? You want your grand unified theory? But then okay, build a grand unified theories for exploits right? I think we're nowhere near actually there yet. My hope what? That was just more to like like are you people kidding me with the things you spend time thinking about? Do you understand like kind of how small you are you are, you are bites and God's computer really? And the things that people get worked up about, you </s><s>[INST] know? so basically it was more a message of, we should humble ourselves that we get to like what, what are we humans in this bike code. [/INST] Yeah. And not just not just humble ourselves, but like, like I'm not trying to like make you feel guilty or anything like that. I'm trying to say. Like literally look at what you are spending time on. Right? </s>
<s>[INST] with low level, the building blocks all look similar. [/INST] Yeah, and they're not even that low level, we're not talking about, like, like neurons were talking about this very complex circuit that exists throughout the neocortex is remarkably similar. It's like, yes, you see variations of it here and they're more of the cell left and that's not all so on. But what Marcus argued was it says, you know, if you take a section of your cortex, Why is one a visual area and one is a auditory area or why? His answer was it's because one is connected to eyes and one is connected to ears </s><s>[INST] literally. You mean just its most closest in terms of the number of connections [/INST] to censor, literally. If you took the optic nerve and attached it to a different part of the cortex, that part would become a visual region. This actually this experiment was actually done by Margot, Lancaster boy. And uh in in developing I think it was the murders, I can't remember, it was some animal and there's a lot of evidence to this. You know, if you take a blind person, a person is born blind at birth, they are born with a visual neocortex. Um it doesn't may not get any input from the eyes because there was some congenital defect or something. And that region becomes does something else, it picks up another task. So uh and it's it's so it's just it's just very complex thing, it's not like, oh they're all built on neurons. No, they're all built in this very complex circuit. And uh and somehow that circuit underlies everything. So this is uh it's called the common cortical algorithm if you will uh some scientists just find it hard to believe and they just can't believe that's true, but the evidence is overwhelming in this case. And so a large part of what it means to figure out how the brain creates intelligence and what is intelligence in the brain is to understand what that circuit does. If you can figure out what that circuit does um as amazing as it is, then you can then you then you understand what all these other cognitive functions are. </s><s>[INST] So if you were to sort of put neocortex outside of your book on intelligence, you look, if you wrote a giant toma textbook on the Neocortex and you look uh maybe a couple of centuries from now, how much of what we know now will still be accurate two centuries from now. So how close are we in terms of [/INST] understanding? I have to speak from my own particular experience here. So I run a small research lab here. It's like it's like any other research lab in the sort of the principal investigator, there's actually two of us and there's a bunch of other people and this is what we do. We started the Neocortex and we published our results and so on. So about three years ago we had a real breakthrough in this in this field tremendous spectrum. We started, we now publish, I think three papers on it. Um and so I have I have a pretty good understanding of all the pieces and what we're missing. I would say that almost all the empirical data we've collected about the brain, which is enormous. If you don't know the neuroscience literature, it's just incredibly bic and uh it's for the most part all correct, it's facts and and experimental results and measurements and all kinds of stuff, but none of that has been really assimilated into a theoretical framework. It's, it's data without it in the language of thomas Kuhn, the historian would be a sort of a pre paradigm science, lots of data, but no way to fit in together. I think almost all of that's correct. There's gonna be some mistakes in there. Um and for the most part, there aren't really good coaching theories about how to put it together. It's not like we have two or three competing good theories which ones are right which ones are wrong. It's like people just like scratching their heads. You know, some people have given up on trying to like figure out what the whole thing does. In fact, there's very, very few labs that we that we do that focus really on theory and all this unassimilated data and trying to explain it. So it's not like we haven't we've got it wrong. It's just that we haven't got it at </s><s>[INST] all. So it's really, I would say pretty early days in terms of understanding the fundamental theories forces of the way your mind works. I [/INST] don't think so that I would have said that's true five years ago. So as I said we had some really big breakfast on this recently and we started publishing papers on this. So um uh you could get that but so I don't think it's I'm an optimist and from where I sit today most people would disagree with this, but from where I sit today, from what I know uh it's not super early days anymore. We are. It's you know the way these things go is it's not a linear path, right? You don't just start accumulating and get better and better and better. You know you got all the stuff you've collected. None of it makes sense. All these different things we just started around and then you're gonna have some breaking points all of sudden. Oh my God. No we got it. Right. So that's how it goes in science. And I personally feel like we passed that little thing about a couple years ago, all that big thing a couple years ago. So we can talk about that time will tell if I'm right but I feel very confident about it. That's what I want to say it on tape like this. Uh </s>
<s>[INST] So what's your prediction about the biden trump debates again? I just have this weird, maybe we'll return to, maybe not in this. How do we put more love into the world? And like one of the things that worries me about the debates is, it will be um, it will be the world's greatest troll against the grandpa on the porch who grabbed his bats. Yeah. And it will not put more love into the world. It will, it will create more mockery for like, [/INST] Joe Biden did a great job against Paul Ryan in 2012. Paul Ryan was no lightweight. No one thought he was a lightweight. Joe biden handed Sarah Palin her ass in 2008, which isn't as easy as you think because she's a female. So you're going to come off as bullying that doesn't have to worry about. So the guy isn't um, I think he is in the stages of like cognitive decline. Um, so I think it's going to be interesting. Uh, I want it to be um, like mike Tyson beating up a child because it will be a source of amusement to me. Um, but I don't know how it's gonna go because possible that joe biden would be the mike Tyson this. Yes, because in his last debate with Bernie, he was perfectly fine. And again, the guy was a center for decades and I don't think anyone, if you look at joe biden in 2000 and 10 would have thought the sky is going to be how his ass handed him a debate, You wouldn't think that at all. So I don't know who we're going to see. Plus he's got a lot of room to attack trump. So I'm sure he's going to come strapped and ready and he's gonna have his talking points and watch trump dance, try to tap dance around him. And if he's in a position, I know the rules of the debate are to actually nail him to the wall, it might actually, I'm sure he's gonna have a lot of lines to the problem is trump is the master counterpuncher. So he, like when Hillary, you know, had her lines, she's like, well, it's a good thing that donald trump isn't in charge of our legal system. And he's like, yeah, you'd be in jail. It's like, it's like, like lady, you set him up. </s><s>[INST] It is painful to watch those, those debates. I mean, there's something, uh, I think it's actually analogous um come to think of it, your conversation with me right now some sleepy joe, I'm playing the role of sleepy joe. I actually connect to uh joe because they're so [/INST] incontinent. </s><s>[INST] There's like these weird pauses that I do the same, I do the same thing and annoys the sh it onto me that like uh in mid sentence, I'll start saying a different thing. Take a tangent. I'm not as slow and drunk as I sound always, I swear more intelligent underneath it, drunk. Exactly, but the result one of those is true, but not both. Yeah. And and and trump. Just like you are a master counterpuncher, so just give me messy. [/INST] Here's the other thing in all seriousness, chris Wallace is the moderator. Chris Wallace has interviewed trump several times and he was a tough, tough questioner. So I don't think he's going to come in there with softball questions. I think he's really going to try to nail trump down, which is tough to do. I like him a lot. Yeah, he's and he's like, mr president sir, that's not accurate, blah, blah blah. He's done it and trump gets very frustrated because he doesn't just let him say whatever he wants and he hits him with the follow up. </s><s>[INST] He's I guess he's on Fox News and he I listened to his sunday program every once in a while. Uh he gives me hope that I don't know, there's something in the voice like that he's not bought. [/INST] He's I I there's no question, he's going to take this seriously, which I think is the best you could hope for in a moderator. </s><s>[INST] Like it feels like there's people that might actually take the mainstream media into a place that's going to be better in the future and like we need people like him, [/INST] you mean like robes fear? </s><s>[INST] What do you mean? Like [/INST] taking the mainstream media to a better future? Like bring out the guillotines? Mhm. Okay. See you </s><s>[INST] you you put your anarchist hat back on, why [/INST] don't they just do as much of an anarchist? But yeah, I get what you're saying. </s><s>[INST] You don't think there should be a centralized place for news? There isn't now? Well, that's what mainstream media is supposed to represent. Broken. Well, it's not whatever uh what would you call that? A place where people traditionally said was the like the legitimate source of truth. That's what the media was supposed to represent? [/INST] Uh That's their, that's their big branding accomplishment. That was never true. Yeah, because if you here's what happens, we remember the spanish american war. Remember the main we have to take cuba yellow journalism, Willie Randolph hearst, right, then record scratch, and then we're all objective. Like when did this transition happen? According to people, when you were saying that the Kaiser is the worst human being on earth when you were downplaying Stalin and downplaying Hitler's atrocities when when you were saying we had to be in Vietnam at what Wmds, when did it change? It never changed. You just are better con artists at a certain point and now the mask is </s><s>[INST] dropping. Yeah. But don't you think there's um at its best like investigative journalism can uncover the truth in a way that uh that like Reddit uh Sub Reddit's can't [/INST] you know, I read it, sure, I agree that it's best. Absolutely. That's not even dispute. </s>
<s>[INST] Yeah, I would trust those aliens though, because they probably want to do different medical procedures than I do. I saw a thumbnail for a video that I'm proud of myself for not clicking on about a man who has claimed that he had sex with aliens. And I was like, not clicking on that? Because I would probably watch it for like 20 minutes, and then I should be doing work. Oh, I see. And I'm actually happy, because I get to imagine all the different possibilities that could have been for that man who has sex with aliens. [/INST] This is true. How do you suffer not clicking on that? Oh, I see. Do you just have like a really high </s><s>[INST] like resting happiness state? Yes, yeah. [/INST] It's probably like a mushroom state, yeah. </s><s>[INST] Wow, do you do mushrooms? I've done mushrooms before. It was very awesome, but like more intensely awesome. But like, because I was just looking at nature, it makes nature even more beautiful, I think. But it's already pretty beautiful. I haven't done MDMA. People say that I should. It's very nice, yeah. Yeah, anyway, but I'm already, yeah. What did you call it? [/INST] Resting happiness state? It's very nice, yeah. </s><s>[INST] Yeah, high resting happiness. Yeah, that's a good way to describe it. But it's not like some of it is genetic that you're able to notice the beauty in the world. And some of it is practiced where you realize focusing on the negative things in life, like unproductively is, it just doesn't help your mind flourish. So like, you just noticed that and it's like, I mean, I think people with like depression learn that or like probably with trauma too is like there's certain triggers. Like if you're, if you suffer from depression, you have to kind of consciously know there's going to be triggers that will like force you to spiral down. And so just avoid those triggers. Some people have that with diet, with food and so on. And so I just don't like, whenever there's shady things happening or shady people flourish, unless I can help, unless I can have some help. Like why focus on it? Yeah, anyway, back to your upbringing. [/INST] What was the journey of escaping that? I, well, I left home like kind of early because my dad and I were not getting along by the time I was a teenager, but I still Christian for a while. And I lost my faith after I think I moved away and I started having friends that weren't religious or like weren't raised in the super conservative environment that I came from. And I think, this was not conscious at the time, this is my hindsight story, but I believe that like being exposed to a culture in which I had the capacity to believe like allowed my brain to actually seriously consider the thought that maybe all of the stuff was untrue. That I had been taught like 6000 year old earth and evolution is a lie and macro evolution and all of this stuff. Because like, when you're immersed in an environment like that, I don't think you actually have a choice. Like your brain has to believe these things because this is a survival thing. Like if you believe this, you'll be, if you believe the wrong thing, it'll be totally cast out. Even if they're not gonna cast you out, you're gonna be cast out in like communion with others because we were always told you can't like trust non-believers really, they don't have a moral compass, they're gonna screw you over. And so I'm like well I can't be that, like everybody's gonna outcast me internally. So anyway I wasn't, I don't think I actually had the capacity to seriously question my faith, even though I thought that I was questioning it quite hard, until I got into an environment where it was safe to do so. And once I started being able to make friends who were not religious, I'm like oh if I lose my faith, I'm still gonna have some sort of community. And then at that At that time I went through some questioning </s><s>[INST] and then I lost my faith. So in that, given your friends, given your situation, you now have the freedom [/INST] to think, essentially. Or at least the ability to think of something </s><s>[INST] that was acceptable in the new culture, yeah. I mean, is there a danger of adopting the beliefs of the new culture? So there's some aspect of just being able to think freely, which you weren't able to do when you were growing up, just to think, look at the world and wonder how it works. [/INST] That kind of thing. I mean, you work it within certain boundaries. There's certain basic assumptions. And as long as you were following those basic assumptions, which is, to be fair, it's kind of what we're doing now. We have, have I gone and done the personal research that evolution is the thing that's going on? Have I looked at the age of the stones? No, I haven't, I'm trusting other people. Which I think is a fair choice to make, given where I'm at right now. </s><s>[INST] Yeah, but you're also assuming there's causality in the universe, time is real. Yeah, that first of all, the thing that your senses are perceiving is real. [/INST] You're assuming a lot of things. Yeah, I think it's better just to become aware of the assumptions you're making, like, as opposed to not making this assumptions at all. You have to assume something, and it's very suspicious, right? That I went out of this very conservative culture and now, well, I guess I don't believe things that are super in line with the current culture. I think this is why I feel a little bit safer right now. Because when I was Christian, I believe generally Christian things. But now I believe a bunch of things Like people really hate it canceled online all the time. I'm like okay, this is a sign that maybe you're thinking independently, if you're able to think things that are completely at odds with the people around you. And to be fair, this is a little bit easier to do when it's like general culture, but it's much harder to do with your peer group. Like the people that you trust, your friends, the people whose opinions you respect like, disagreeing with those people is very difficult </s>
<s>[INST] can actually just because the word doomed is so interesting. Let me give you some options. Multiple choice quiz. Yeah. Uh Space time we can say is reality the way we perceive it doomed um wrong or fake because doomed just means it could still be right and we're now ready to go deeper. So it's not wrong. It's not a complete deviation from a journey toward the [/INST] truth, right? It's like earth air fire and water is not wrong. There is earth air fire and water. That's a useful framework, but it's not fundamental, </s><s>[INST] right? Well, there's also wrong, which is they used to believe as I recently learned that George Washington was the president, the first president of the United States was bled to death for something that could have been easily treated because it was believed that you can get actually, I need to look into this further. But I guess you get toxins out or demons out. I don't know what you're getting out with the bleeding of a person. But so that ended up being wrong but widely believed as a medical tool. So it's also possible [/INST] that </s><s>[INST] our assumption of spacetime is not just doomed, but it's wrong. [/INST] Well, if we believe that it's fundamental, that's wrong, but if we believe it's a useful tool, but </s><s>[INST] he could see. But bleeding somebody to death was believed to be a useful tool and that was wrong. It wasn't just not fundamental. It was very, I'm sure there's cases in which bleeding somebody would work, but it would be a very tiny, tiny tiny percentage of cases. So it could be that it's wrong. Like it's a side road that's ultimately leading to a dead end as opposed to a truck stop or something that you can get off of [/INST] my feeling is is not the dead end kind of thing. I think that the, what the physicists are finding is that there are these structures beyond space time, but they project back into space time. And so space time, when they, when they say space time is doomed, they're explicit, they're saying it's doomed in the sense that we thought it was fundamental. It's not fundamental. It's a useful, absolutely useful and brilliant data structure, but there are deeper data structures like cosmological politics and and and space time is not fundamental. What is doomed in the sense that it's wrong is reductionism, </s><s>[INST] which is saying spacetime is fundamental, right? [/INST] Right? The idea that that somehow being smaller in space and time or spacetime is a fundamental nature of reality. That is that's that's just wrong. It turned out to be a useful heuristic for for thermodynamics and so forth. And and several other places, reductionism has been very useful, but that's some sense an artifact of how we use our interface. Um, </s><s>[INST] yes, so you're saying size doesn't matter. Okay, this is very important for me, ultimately, [/INST] ultimately, it's useful for, for theories like thermodynamics and also for understanding brain networks in terms of individual neurons and neurons in terms of chemical systems inside cells. That's all very, very useful. But but the idea that we're getting to the more fundamental nature of reality, no, when you, when you get all the way down in that direction, you get down to the corks and gluons, what you realize is what you've gotten down to is not fundamental reality, just the irreducible representations of a data structure, that's all you've gotten down to. So you're always stuck inside the data structure. So, you seem to be getting closer and closer. I went from neural networks to neurons, to neurons, to chemistry, chemistry, to particles, particles to clerks and gluons. I'm getting closer and closer to the No, I'm getting closer and closer to the actual structure of the data structure of space and time. The irreducible representations, that's what you're getting closer to. Not to a deeper understanding of what's beyond space. Time </s><s>[INST] will also refer [/INST] we'll </s><s>[INST] return again to this question of dynamics because you keep saying that space time is doomed, but mostly focusing on the space part of that. It's very interesting to see why why time gets the bad cred too because how do you have dynamics of that time is the thing I'd love to talk to you a little bit about. But let us return um, your brilliant whirlwind overview of the different theories of consciousness that are out there. Thank you. What is consciousness if outside of space time. [/INST] If we think that we want to have a model of consciousness, we as scientists then have to say, what do we want to write down? What what what kind of mathematical modeling were going to write down? Right? And if you think about it, there's lots of things that you might want to write down about. Consciousness was really complicated subject. Um so most of my colleagues are saying, let's start with matter or neurons and and say what properties of matter could create consciousness. But I'm saying that that whole thing is out space time is doomed, That whole thing is out. We need to look at consciousness Qua consciousness in other words, not as something that arises in space and time, but perhaps is something that creates space and time as a data structure. So what do we want? And here again, there's no hard and fast rule. But what you as a scientist have to do is to pick which you think are the minimal assumptions that are going to allow you to boot up comprehensive theory. That is the trick. So what do I want? So what I chose to do was to have three things I said that there are conscious experiences feeling of headache, the smell of garlic, um experiencing the color red. There are those are conscious. So that's a primitive theory and the reason I want few primitives why? Because those are the miracles of the theory, right. The primitives. The assumptions of the theory of the things you're not going to explain. Those are the things you assume. </s>
<s>[INST] and, and even if you think you can ignore it, just reading it will have a little bit of an effect on your mind. I think that's, I think that's right over time, I might accumulate. So the documentary, but in general, uh, it mentioned or kind of emphasized and talked about erin's sexuality or sort of, they were discussing basically the idea that he was a homosexual and some of the trauma, some of the suffering that he endured his life had to do with sort of fear given the society of, of what his father would think of, what others around him, especially in sports culture and football and so on. So, I don't know, in your interaction with him, was do you think that maybe even leading up to a suicide, do you think his struggle with coming to terms of the sexuality had a role to play in much of his difficulties? [/INST] Well, I'm not going to talk about my interactions with them and anything I derived from, from that, but you know, what I will say is that, um, a story broke on the, on the radio, uh, at some point during the trial that Aaron had been in the same sex relationship with someone and some sport, local sportscasters, local boston sportscasters are we really mushroomed, uh, the story. So, um, uh, he and everyone, I was aware of it. Um, you'll, you also may know from the court record that the prosecutors floated a, uh, specious theory, um, for a minute, but then backed off of it, that, you know, that Aaron was that there was some sort of uh, I guess gay rage at work with them and that might be a cause a motive for the killing. And uh, luckily they really backed off of that. That was quite an offensive claim and in theory. So, um, but to answer your question more directly, I mean, I have no idea why he killed himself. It was a surprise and a shock. I was scheduled to go see him like a couple of days after it happened. I mean, he was anxious uh, for uh, Jose and I to come in and do the appeal from the murder which he was convicted for. He wanted us to take over that appeal. Um, He was talking about going back to football. I mean, he said, well you talked about this earlier. You talked about the sort of innocent aspect of him. He said, you know, well, Ron maybe not, maybe not the patriots, but you know, I want to get back in the league. And I was like, you know, Aaron, that's, that's gonna be tough man. Uh, but uh, but he really, you know, he really believed it. And uh, and then, you know, for a few days later that to happen. It was just, it was a real shock to me. </s><s>[INST] Like when you look back at that at his story, does it make you sad? [/INST] Very, very, I thought so, one I believe he absolutely did not commit the crimes that we could acquitted him on. I think that was the right answer. Uh for for for that. Uh I don't know enough about Bradley, the first case. I'm sorry to make a make an opinion on, but in our case, uh you know, uh it was just he had the misfortune of family, a famous name and the police department just really just just just really got got on him there. So um uh yes, it's it's it's I miss him a lot. It was very very sad, surprising. </s><s>[INST] Yeah. And and I mean just on the human side, of course, we don't know the full story, but just everything that led up to suicide, everything right up to uh an incredible professional football player, you know, that whole story if [/INST] remarkably talented athlete, remarkably talented athlete. </s><s>[INST] And it has to do with all the all the possible trajectories, right, that we can take through life as we were talking about before. And some of them lead to uh to suicide sadly enough. And it's always tragic when you [/INST] have some </s><s>[INST] you know, somebody with uh with great potential result in and the things that happened. People love it. When I ask about books, I don't know if uh uh whether technical like legal or fiction nonfiction books throughout your life have had an impact on you. If there's something you could recommend or something you could speak to about something that inspired ideas, insights about this world complicated world of ours. [/INST] Oh wow. Uh yeah, so uh I'll give you a couple. Uh so one is a contingency irony and solidarity by Richard Ward E. He's he's passed away now, but was a uh philosopher at some of our major institutions, Princeton, Harvard stanford, um Contingency irony in solidarity, at least. That's the book that really helped me work through uh a series of thoughts. So it stands for the proposition that uh that are most deeply held beliefs are contingent, that there there's nothing beyond history or prior to socialization. That's definite story of the human being that's already. Um and he says that our most deeply held beliefs are received wisdom and highly contingent along a number of registers. And he does that. But then goes on to say that uh he nonetheless uh can hold strongly held beliefs recognizing their contingency but still believes them to be true and accurate. And it helps you to work through uh what could be an intellectual tension uh other words. So, so you don't delve into one, doesn't delve into relativism, everything is okay, but it gives you a vocabulary to think about uh how to negotiate these these these realities. Uh </s>
<s>[INST] that I was actually recently just complaining that there's not enough content on the famine the thirties of you know, of of stuff, there's so much on Hitler, like I love the reading I'm reading so long, it's been taking me forever. The Rise and Fall of the third Reich Yeah, I love it, but [/INST] I've got the book to complement that, that you have to read. It's called the ominous parallels. It's Lana pick off, and it's the ominous parallels, and it's about it's about the causes of the rise of of of Hitler, but a philosophical causes. So, whereas the Rise and Fall is more of a, kind of, uh, the existential kind of what happened. Um, but really delving into the intellectual intellectual currents that led to the rise of Hitler and </s><s>[INST] maybe highly recommend that and basically suggesting how it might rise another. [/INST] That's the ominous parallel. So, the parallel he draws is to the United States, And he says those same intellectual forces are rising in the United States, and this is this was published, I think in published in 81, was published in 82. So, it's published a long time ago, and yet you look around us and it's unbelievably predictive, sadly about the state of the world. So, I haven't finished Nine Man story, I don't want to I don't </s><s>[INST] know if you want me to know, but on that point, I'll have to let's please return to it. But let's now for now, let's talk, [/INST] let me also say, just because I don't forget about Mr jones. It is to the point you made, there are tons of movies that an anti fascist, anti Nazi and that's good. But they're way too few movies that are anti communist, just almost not. And it's very interesting and if you remind me later, I'll tell you a story about that. But uh so she publishes anthem and and then she starts and she's doing okay in Hollywood and she's doing okay with with the play. And then she starts on her on on the book, the fountainhead, and she writes the Fountainhead And it comes out she finishes it in 1945 and she's uh she sends it to publishers and publisher after publisher after publisher turn it down And it takes 12 publishers before this, this editor reads it and says, I want to publish this book and he basically tells his bosses, if you don't publish this book, I'm leaving right. Um and they don't really believe in the book, so they published just a few copies, they don't do a matte look. And the book becomes a bestseller from word of Mouth and they land up having to publish more and more and more. And and it's you know, she's basically gone from this immigrant who comes here with very little command of english and and it to all kinds of odds and ends jobs in Hollywood too. You know, writing one of the seminal, I think american books, she is an american author. I mean if you read the fountainhead, it's not Russian, this is not Nevsky, </s><s>[INST] It feels it feels like a symbol of what America is in the 20th century. And I mean, probably maybe you can. So there's a famous kind of sexual rape scene in there. Is that is that like a lesson you want to throw in some controversial stuff to make your philosophical books work out? I mean, is that why why was it so popular? Uh, do you have a sense? [/INST] Well, because I think it illustrated, first of all, because I think the character is a fantastic, it's got a real hero. And I think that the whole book is basically illustrating this massive conflict that I think went on in America then is going on today. And it goes on in a big scale politics all the way down to the scale of the choices you make in your life. And and the the issue is individualism versus collectivism. Should you live for yourself? Should you live for your value? Should you pursue your passions? Uh, should you or should you do what your mother tells you? Should you follow your mother's passions? And uh, that's it's a it's it's very, very much an individual book about individuals and people relate to that. But it obviously has this massive implications to the world outside. And at the time of collectivism just having been defeated communism. Well, not fascism. And and and and you know, the United States representing individualism, right, has defeated defeated collectivism, but we're collectivist ideas are still popular in the form of socialism and communism and for the individual, this constant struggle between what people tell me to do, what society tells me to do, what my mother tells me to do and what I think I should do. I think it's unbelievably appealing, particularly to young people who are trying to figure out what they want to do in life, trying to figure out what's important in life. Um, it had this enormous appeal. It's romantic, it's bigger than life. The characters are big heroes. It's very american in that sense. It's about individualism, it's about the triumph of individualism. And uh, so I think that's what related. And it had this big romantic element from the, I mean, when I use romantic, I use it kind of in the in the sense of, uh, a movement in art, but it also has this romantic element in the sense of a relationship between a man and woman whose that's very intriguing. It's not only that there's a, I would say almost rape scene, right? Um, I would say, but it's also that this woman is hard to understand. I mean, I've read it more than once and I still can't quite figure out Dominique, right? Because she loves him and she wants to destroy him and she marries other people. I mean, think about that too. She's writing a book in the 1940s. There's lots of sex. There's a woman who marries more than one person has having sex with more than one person. Very unconventional. She's having married, she's having sex with walk, even though she's not married to work. This is 1945. And it's um it's very jarring to people. It's very unexpected, but it's also a book of its time. It's about individuals pursuing their passion, pursuing their life and not caring about convention and what people think, but doing what they think is right. And so, so I think it's it's it's uh I encourage everybody to read it </s>
<s>[INST] Bitcoin and ethereum seem to be dominating the space, But who knows what 10 2030, 50 100 years from now it looks like. Anyway, I hope to talk to a bunch of folks from the Cryptocurrency space on this podcast soon including once again the great, the powerful metallic Budarin. So again, if you get cash out from the app store, Google play and use collects podcast, you get $10 and cash out will also donate $10 to first an organization that is helping to advance robotics and stem education for young folks around the world. And now here's my conversation with Charles Isabel and Michael Littman? You'll probably disagree about this question, but what is your biggest would you say disagreement about either something profound and very important or something completely not important at all. [/INST] I don't think I have any disagreements at all. I'm </s><s>[INST] not sure that's [/INST] True. We walked into that one didn't. </s><s>[INST] So one thing that you sometimes mention is that and we did this one on air to as it were whether or not machine learning is computational statistics. [/INST] It's not but it is. Well, it's not and in particular and more importantly, it is not just computational statistics. </s><s>[INST] So what's missing in [/INST] the picture all the rest of </s><s>[INST] it, which is missing because you can't be wrong now. Well, [/INST] it's not just the statistics. He doesn't even believe this. We've had this conversation before. If it were just the statistics then we would be happy with where we are. </s><s>[INST] It's not just the stuff that's why it's computational [/INST] statistics. If it was just the computation </s><s>[INST] agree that machine learning is not just statistics, [/INST] it's not just that we can agree on that. Where is it? Just computational statistics, </s><s>[INST] computational [/INST] computational what is the computational </s><s>[INST] computational statistics? This is take us into the realm of computing. [/INST] It does. But I think perhaps the way I can get him to admit that he's wrong is that it's about rules. It's about rules. It's about symbols, it's about all these other things. It's not </s><s>[INST] about rules. Say statistics [/INST] about it's not just the statistics. It's not just a random variable that you choose and you have a probability? I think </s><s>[INST] you have a narrow view of statistics. [/INST] Okay, well then what would be the broad view of statistics that would still allow it to be statistics and not say history. That would make computational statistics. Okay. Well </s><s>[INST] okay. So I I had my first sort of research mentor, a guy named Tom Landauer taught me to do some statistics right? And I was annoyed all the time because the statistics would say that what I was doing was not statistically significant and I was like but but but and basically what he said to me is statistics is how you're going to keep from lying to yourself. Which I thought was really deep. [/INST] It is a way to keep yourself honest in a particular way. I agree with that. </s><s>[INST] And so you're trying to find rules. I'm just going to bring it back to rules. Wait, wait, wait. Could you possibly try to define rules? Even regular statisticians, non computational statisticians do spend some of their time evaluating rules. Right? Applying statistics to try to understand is this is this does this rule capture this, does this not captured like hypothesis testing or like confidence intervals? Like like like more like hypothesis. Like I feel like the word statistics literally means like a summary, like a number that summarizes other numbers. But I think the field of statistics actually applies that idea to things like rules to understand whether or not a rule is [/INST] valid. The software engineering. Statistics. No programming languages. Statistics. No. Because I think there's a very it's useful to think about a lot of what ai and machine learning is or certainly should be a software engineering as programming languages. Just if to put it in language that you might understand the hyper parameters beyond the problem is the </s><s>[INST] hyper parameters has too many syllables for me to understand [/INST] the hyper parameter. Uh, that goes around it, right. It's the decisions you choose to make. It's the metrics you choose to use. It's the </s><s>[INST] lost. You want to say the practice of machine learning is different than the practice of statistics. Like the things you have to worry about and how you worry about them are different. Therefore they're [/INST] different at a very little. I mean at the very least it's that that much is true. It doesn't mean statistics, computational otherwise aren't important. I think they are. I mean, I do a lot of that for example, but I think it goes beyond that. I think that we could think about game theory in terms of statistics, but I don't think it's very as useful to do. I mean the way I would think about it or a way I would think about it is this way chemistry is just physics. </s><s>[INST] But [/INST] I don't think it's as useful to think about chemistry as being just physics. It's useful to think about it is chemistry, the level of obstruction really matters here. </s><s>[INST] So, I think it is there are context in which it is useful that way right now, finding that connection is actually helpful. And I think that's when I when I emphasized the computational statistics thing, I think I think I want to befriend statistics and [/INST] not absorb them. Here's the here's the a way to think about it beyond what I just said. Right, So what would you say? And I want you to think back to a conversation had a very long time ago. What would you say is the difference between, Say the early 2000's I CML and what we used to call nips nerves. Their difference. A lot of, particularly on the machine learning that was done there. </s><s>[INST] I cmos around that [/INST] long. Oh yeah, </s><s>[INST] so I clear is the new conference, new ish. [/INST] Uh Yeah, I guess so. </s><s>[INST] And I cmos around in two [/INST] 1000 I see Ml predates that </s><s>[INST] I think my most cited. I see ml papers from 94, [/INST] Michael knows this better than me because of course he's significantly older than I. But the point is, what is the difference? The difference between ice ml in Europe in the late 90s, early 2000s. </s><s>[INST] I don't know what everyone else's perspective would be, but I had a particular perspective at that time which is I felt like I see mel was more of a of a computer science place and the nips europe's was more of an engineering place. Like the kind of math that happened at the two places as a computer scientist I felt more comfortable with the I. C. M. L. Math and the number of people would say that that's because I'm dumb and that's such an engineering thing to say. So [/INST] I agree with that. Part of what I do a little differently. Actually had a nice conversation with tom Dietrich about this in twitter on twitter just a couple of days ago I put a little differently which is that I see Ml was machine learning done by computer scientists and nerves. Was machine learning done by computer scientists trying to impress statisticians. Which was weird because it's the same people at least by the time I started paying attention. But it just felt very very different. And I think that that perspective of whether you're trying to impress the statisticians or you're trying to impress the program which is actually very different and has real impact on what you choose to worry about and what kind of outcomes you come too. So I think it really matters. Think competition, statistics as a means to an end. It is not an end in some sense. Um And I think that really matters here in the same way that I don't think computer science is just engineering or just science or math or whatever but okay </s><s>[INST] so I'd have to now agree that now we agree on everything. [/INST] Yes. Yes. The important thing here is that my opinions may have changed. But not the fact that I'm right I think is what what we just came through. </s><s>[INST] My opinions may have changed and not the fact that I'm [/INST] wrong. That's right. </s><s>[INST] Lost me. I'm not [/INST] even think I lost myself there to wear. Well </s><s>[INST] this happens to us sometimes we're Sorry, how does neural networks change this? Just leaving linger on this topic? Change this idea of statistics. How big of a pie statistics is one of the machine learning thing, like because it sounds like hyper parameters and also just the role of data. You know that people are starting to use this terminology software two point oh, which is like the act of programming as a as a like you're a designer in the hyper parameter space of neural networks and you're also the collector and the organizer and the cleaner uh of the data and that's part of the programming. Uh So how did on in europe's versus I CML topic? What's the role of neural networks and redefining the size and the role of machine learning. [/INST] I can't wait to hear what Michael thinks about this. But I would add one. But that's true. I will force myself. I think the there's one thing I would add to your description which is the kind of software engineer parties. What does it mean to debug for example. But this is a difference between the kind of computational statistics view of machine learning and computational view of machine learning which is I think one is worried about the equation as it were and by the way this is not a value judgment, I just think it's about perspective. But the kind of questions you would ask, you start asking yourself what does it mean to program and develop and build the system is a very computer science view of the problem. When if you get on data science, twitter and check on twitter, you actually hear this a lot with the the economist and the data scientist complaining about the machine learning people was with it's just statistics and I don't know why they don't don't see this, but they're not even asking the same questions, they're not thinking about it as a kind of programming problem. And I think that that really matters just asking this question I actually think is a little different from uh programming and hyper parameter space and sort of collecting the data. But I do think that that immersion really matters. So I'll give you a quick a quick example the way I think about this. So I teach machine learning Michael and I have Qatada Machine Learning class which has now reached out of 10,000 people at least for the last several years for somewhere there's about and my machine learning assignments are of this form. So the super the first one is something like implement these five algorithms, K and N and S. S. VMS and boosting and decision trees and neural networks and maybe that's it, I can't remember and when I say implement, I mean still the code. I am completely uninterested. You get zero points for getting the thing to work and I want you spending your time worrying about getting the corner case right of you know what happens when you are trying to normalize distances and the points on the thing and so you divide by. I'm not interested in that right steal the code. However you're going to run those algorithms on two datasets. The data sets have to be interesting. What does it mean to be interesting? Well datasets interesting if it reveals differences between algorithms which presumably are all the same because they can represent whatever they can represent. And two data sets are interesting together if they show different differences as it were And you have to analyze them, you have to justify their interesting this and you have to analyze the whole bunch of ways. But all I care about is the data in your analysis, not the programming and I occasionally end up in these long discussions with students. Well I don't really, I copy and paste the things that I said the other 15,000 times it's come up which is good but the only way to learn really understand it's to code them up which is a very program or software engineering view of the world. If you don't program that you don't understand it which is by the way, I think is wrong in a very specific way, but it is a way that you come to understand because then you have to wrestle with the algorithm. But the thing about machine learning is not just sorting numbers were, in some sense, the data doesn't matter what matters. Is that well, this algorithm working these abstract things upon the less the other machine learning the data matters, it matters more than almost anything and not everything, but almost anything. And so as a result, you have to live with the data and don't get distracted by the algorithm per se. And I think that that focus on the data and what it can tell you and what question is actually answering for you as opposed to the question you thought you were asking is a key and important thing about machine learning and is away the computational ist as opposed to statisticians bring a particular view about how to think about the process. The statisticians, by contrast being I think I'd be willing to say a better view about the kind of formal math that's behind it and what an actual number ultimately is saying about the data and those are both important, but they're also different. </s><s>[INST] I didn't really think of it this way, is to build intuition about the role of data, the different characteristics of data by having two data sets are different and they reveal the differences and the differences. That's that's a really fascinating, That's a really interesting educational approach. The students love it, but not right away. [/INST] Love it later at the end. Not at the beginning, </s><s>[INST] not even immediately after. I feel like there's a deep, profound lesson about education there that you can't listen to students about whether what you're doing is the right or the wrong thing. [/INST] Well, as a wise, uh, Michael Lipman once said to me about Children, which I think applies to teaching is you have to give them what they need without bending to their will. And students were like that, you have to figure out what they need, your curator. Your whole job is to curate and to present because on their own they're not going to necessarily know where to search. So you're providing pushes in some direction and learn space and you have to give them what they need in a way that keeps them engaged enough so that they eventually discovered what they want and they get the tools they need to go and learn other things off. </s><s>[INST] What's your view? Let me put on my Russian hat, which believes that life is like Russian hats, by the way, if you have what I would like this. Those are ridiculous. Yes, but in a delightful way. But sure, what do you think is the role of, we talked about balance a little bit, what do you think is the role of hardship and education. Like I think the biggest things I've learned, like what made me fall in love with math for example, is by being bad at it until I got good at it. So like, like struggling with a problem which increased the level of joy I felt when I finally figured it out and it always felt with me with teachers, especially modern discussions of education, how can we make education more fun, more engaging, more, all those things? Or from my perspective is like, you're maybe missing the point that education, that life is suffering, education is supposed to be hard and that actually what increases the joy you feel when you actually learn something? Is that ridiculous? Do you like to see your students suffer? Okay, so this may be a point where we differ, [/INST] I suspect not going to go on. </s><s>[INST] Well, what would your answer me? I wanna hear you first. Okay, well what I was going to not answer the question, you [/INST] know what I was going to suffer? No, </s><s>[INST] no, no, no, no, no. I was I was going to say that there's, I think there's a distinction that you can make in the kind of suffering, right? So I think you can be in a mode where you're you're suffering in a hopeless way versus your suffering in a hopeful way, right? Where you're like, you can see that if you you still have, you can still imagine getting to the end right? And as long as people are in that mindset where they're struggling, but it's not a hopeless kind of struggling. That's, that's productive. I think that's really helpful. But it's struggling. Like if you break their will, if you leave them hopeless. No, they don't sure some people are gonna whatever lift themselves up by their bootstraps, but like mostly you give up and certainly takes the joy out of it and you're not going to spend a lot of time on something that brings, you know, joy. So it's a, it is a bit of a delicate balance, right? You have to thwart people in a way that they still believe that there's a way through, [/INST] right? So that's a, that we strongly agree actually. So I think, well, first off struggling and suffering aren't the same thing, right? </s><s>[INST] One. You [/INST] know, I actually appreciate the poetry and I, one of the reasons I appreciate it is that they are often the same thing and often quite different, right? So you can struggle without suffering. You can certainly suffering suffer suffer pretty easily. You don't really have to struggle to suffer. So I think that you want people to struggle, but that hope matters. You have to, they have to understand that they're going to get through it on the other side and it's very easy to confuse the two. Um, I actually think Brown University has a very, just philosophically has a very different take on the relationship with their students, particularly undergrads from a place like Georgia tech, which is, which universities better? Uh, well, I have my opinions on that. </s><s>[INST] Remember Charles said, it doesn't matter what the facts are. I'm always right. [/INST] The correct answer is that it doesn't matter. They're different. Um, </s><s>[INST] but clearly a, he went to a school, like the school where he is as an undergrad. I went to a school, specifically the same school though, it was changed a bit in the, in the intervening years. No, I was talking about your detect and I went, yeah, and I went to an undergrad place. It's a lot like the place where I work now and so it does seem like we're more familiar with these models. There's a similarity between Brown and Yale. Yeah, I think that, I think they're quite similar [/INST] and Duke </s><s>[INST] Duke has some similarities to, but it's got a little southern [/INST] drawl. You kind of worked, you sort of worked at universities that are like the places where you learned and the same would be true for me. </s><s>[INST] Are you uncomfortable venturing outside the box? Is that what you're saying, [/INST] joining out </s><s>[INST] what I'm saying, Charles is definitely, he only goes to places that have instituted the name, [/INST] It has worked out that way. Well, academic places anyway. Well, no, I was a visiting scientist at U penn or visiting visiting something that you've been. </s><s>[INST] Oh wow, I just, I just understood your joke, which one I like, I like to set these sort of time bomb the institute is and uh Charles only goes to places that have institute in the name. So I guess Georgia I forget that Georgia tech is Georgia Institute of Technology. [/INST] The number of people who referred to as Georgia Tech University is large and incredibly, it's one of the few things that generally gets under my </s><s>[INST] skin, but like schools like MIT have as part of the ethos. Like there is, I want to say there's a, there's an abbreviation that someone taught me like I H T. F P. Something like that. Like there's a, there's a, there's an expression which is basically, I hate being here, which they say so proudly and that is definitely not the ethos at Brown. Brown is, there's a little more pampering and empowerment and stuff and it's not like we're going to crush you and you're going to love it. So yeah, I think there's a, I think the ethos is are different. That's interesting. [/INST] Yeah, we had drowned river. What's that graduate from Georgia tech. This is a true thing. Feel free to look at uh, if you lot of schools have this, by the way, no, check was barely the first </s><s>[INST] BRANDEIS has it had it? I feel like Georgia tech was the first [/INST] uh, first of all it was it was the first time I think I had the first master degree stop that. Uh, first masters in computer science </s><s>[INST] actually. [/INST] Well that too, but way back in the 60s. Um, yeah, you're the first information and computer science master's degree in the country. Um, but the uh, Georgia tech, it used to be the case in order to graduate from Georgia tech, you have to take a drown proofing class were effectively, they threw at you up if you didn't drown, you got to graduate. I I believe so there was certainly versions of it, but I mean luckily they ended it just before I had to graduate because otherwise we have never graduated. It was going to happen, I want to say 84 83 someone around them, they ended it. But uh, yeah, I used to have to prove you could tread water for some ridiculous amount of time or you too, you can graduate knows more than two. Okay, well it was in the </s><s>[INST] bathtub, [/INST] it was in a pool, but it was a real thing. But that idea that you know, push you fully clothed, yeah, fully clothed and I don't </s><s>[INST] think, I bet it was that and not tied up because like who needs to learn how to swim when you're tied nobody, but who needs to learn to swim when you're actually falling into the water dress. That's a real thing. I think your facts are getting in the way with a good story. That's fair. That's fair. I think [/INST] the narrative matter, whatever it was you had to, it was called drown proofing for a reason. The point of the story, Michael uh is struggle. It's, well, no, but that's good. It doesn't, it doesn't bring it back to struggle. That's a part of what Georgia tech has always been and we struggle with that by the way about what we want to be, particularly as things go. But you, you sort of, how much can you be pushed without breaking and you come out of the other end stronger right there. There's a saying, we used to when I was an undergrad, there was Georgia tech building tomorrow the night before, it was just kind of kind of idea that give me something impossible to do and I'll do it in a couple of days because that's what I just spent the last four or five or six uh </s><s>[INST] ethos definitely stuck to you having now done a number of projects with you, you definitely will do it the night [/INST] before. That's not entirely true. There's nothing wrong with waiting until the last minute, the secret is knowing when the last minute is right. </s><s>[INST] That's, that's brilliantly put. Yeah, that's, that is a definite Charles statement that I am trying not to embrace. [/INST] I appreciate that because you helped move my last minute, </s><s>[INST] that's a social construct that we converged together. What the definition of last minute is, we figure that out altogether. In fact mitt, you know, I'm sure a lot of universities have this, but it has like my tee time that everyone has always agreed together that there is such a concept and everyone just keeps showing up like 10-15-20, depending on the department late to everything. So there's like a weird drift that happens. It's kind of fascinating. [/INST] There were five minutes, five minutes. In fact, the classes will say, well, there is no longer true actually, but it used to be a class was started eight, but actually started 805 and ends at nine. Actually didn't at age 55 everything's five minutes off and nobody expects anything to start until five minutes after the half hour, whatever it is, it still exists. It hurts my head. </s><s>[INST] Well, let's rewind the clock back to the fifties and sixties when you guys met. How did you? I'm just kidding. I don't know. But what can you tell the story of how you met? So you've like the internet and the world kind of knows you as, as, as, as connected in some ways in terms of education of teaching the world. That's, that's like the public facing thing. But how did you, as human beings and as collaborators? Uh, [/INST] I think there's two stories. One is how we met and the other is how we got to know each other. I'm not going to, I'm going to say that we came to understand that we </s><s>[INST] had some common something. Yeah, it's funny because on the surface, I think we're different in a lot of ways, but there's something, Yeah, I mean that's [/INST] just constant. There you go afternoon. So I will tell the story of how we met and I'll let Michael tell the story of how we okay, okay, so here's how we met. Um I was already at at that point it was 18 C Labs has a long interesting story there. But anyway, I was there and Michael was coming to interview. He was a professor at Duke at the time, but decided for reasons that he wanted to be in New Jersey. Uh and so that would mean Bell Labs slash 18 T labs. Uh and we were doing the interview interviews very much like academic interviews. Uh and so I had to be there. We all had to meet with him afterwards and so on one on one, but it was obvious to me that he was going to be hired Like no matter what because everyone loved him. They were just talking about all the great stuff he did. Oh I did this great thing and you just won something at Triple AI think or maybe you got 18 papers in Tripoli. </s><s>[INST] I got the best paper award it to play I for the crosswords. [/INST] Right? Exactly. So that it all happened and everyone was going on and on and on about actually tender was so incredibly nice things about you. Really? Yes. So he can </s><s>[INST] be very grumpy. Yes, that's nice to [/INST] hear. He was grumpily saying very nice things, that it does make sense. So, you know, so it was going to come. So why were we, why was I meeting him? I had something else. I had to do a camera. What it was probably involved comments. </s><s>[INST] Remember meeting me as inconveniencing his afternoon. [/INST] So he came, so eventually came to my office, I was the middle trying to do something, I can't remember what and he came and he sat down and for reasons that are purely accidental, despite what Michael thinks. My desk at the time was set up in such a way that is sort of an L shape and the chair on the outside was always lower than the chair that I was in. And you know, the kind of point was the only </s><s>[INST] reason I think that was on purpose is because you told me it was on purpose. I don't [/INST] remember that. Anyway. The thing is that, you know, it kind of, his </s><s>[INST] guest chair was really low so that he could, he could look down at everybody. The idea [/INST] was just to simply create a nice environment that you were asking for a mortgage. And I was going to say no, that was a very simple idea here. Anyway, so we said that we just talked for a little while and I think he got the impression that I didn't like him. It wasn't true, strongly got the talk was really good. And by the way it was </s><s>[INST] terrible. And after right after the talk, I said to my host Michael Kearns, who ultimately was my boss. I'm a friend and a huge fan of Michael. Yeah, yeah, he is a remarkable person. Um I after my talk today, I went into the um, racquetball. He's good at basketball. No, but basketball, racquetball squash, squash, [/INST] squash, racquetball squash, which is not racquetball, Yes, squash. No, and I hope you you hear that Michael </s><s>[INST] u as a game, not his skill, because I'm pretty sure he's alright, there's some competitiveness there. But the point is that there was like the middle of the day I had full day of interviews, I met with people, but then in the middle of the day I gave a job talk and then um and then there was going to be more interviews, but I pulled Michael aside and I said, I think it's in both of our best interest if I just leave now because that was so bad that it's just be embarrassing if I have to talk to any more people like you look bad for having invited me, like it's just let's just forget this ever happened. So I don't think the talk went well, [/INST] it's one of the most Michael lippman set of sentences I think I've ever heard he did great, or at least everyone knew he was great. So maybe didn't matter, I was there, I remember the talk and I remember him being very much the way I remember him now on any given week. So it was good. And we met and we talked about stuff. He thinks I didn't like him because he </s><s>[INST] was so grumpy. Must be in the chair thing, the chair thing and the low voice I think like obviously and that like that like slight like skeptical look. Yes, I I have no idea what you're talking about. [/INST] Probably didn't have any idea what you were talking about. Anyway, I liked him. He </s><s>[INST] asked me questions, I answered questions, I felt bad about myself. It was a normal day, [/INST] normal candy left </s><s>[INST] and then he left and that's how can we take it? And then I got hired and I was in the group, can we take a slight tangent on the on this topic of it sounds like maybe you could speak to the bigger picture. It sounds like you're quite self critical, who Charles. No, you, I think I can I can do better. I can do better. I'll try me again. I'll do better. But yeah, that was like a like a three out of 10 response. Uh let's try to work it up to five and six. Uh You know, I remember Marvin Minsky said uh on a video interview, something that the key to success in academic research is to hate everything you do. Uh for some reason I think I followed that because I hate everything. He's done a good line. That's a that's a keeper. But what do you do find that resonates with you at all in how you think about talks and so [/INST] on? I would say it differently. It's </s><s>[INST] not [/INST] that's such an M I. T. View of the world. So I remember I remember talking about this one as a student. You know, you were basically told I will clean it up for the purpose of the podcast. Uh My workers crap, My work is crap. My workers crap, my workers crap. Then you like, go to a conference or something like everybody else's work is crap. Everybody else's work is crap. And you feel better and better about it relatively speaking and then you sort of keep working on. I I don't hate my work that resonates with me. Yes. I've never hated my work, but I have I have been dissatisfied with it and I think being dissatisfied being okay with the fact that you've taken a positive step, the derivative is positive. Maybe even the second derivative is positive. That's important because that's a part of the hope, right? But you have to. But I haven't gotten there yet. If that's not there, That I haven't gotten there yet, then, you know, it's hard to, it's hard to move forward. I think. So, I by that, which is a little different from hating everything that you do. </s><s>[INST] Yeah, I mean, there's there's things that I've done that I like better than I like myself. So it's separating me from the work essentially. So I think I am very critical of myself, but sometimes the work I'm really excited about and sometimes I think it doesn't happen [/INST] right away. So I found the work that I've liked, that I've done most of it. I liked it in retrospect more when I was far away from it in time, </s><s>[INST] I have to be fairly excited about it to get done, [/INST] No excited at the time, but then happy with the result, but years later, or even Michael back, you know what, that actually turns out that turned out to matter or oh, gosh, It turns out I've been thinking about that. It's actually influenced all the work that I've done since without realizing it. That's smart. Yeah, that guy had a future. Yeah, I think so, yeah. So I think there's something to it. I think there's something to the idea you gotta, you know, hate what you do. But it's not quite hate, it's just being unsatisfied and different people motivate themselves differently. I don't happen to motivate myself with self loathing. I have been to motivate myself and something else. </s><s>[INST] So you're able to sit back and be proud of in retrospect of the work you've done [/INST] well and it's easier when you can connect it with other people because then you can be proud of them </s><s>[INST] people. [/INST] And then the question is still safely hate </s><s>[INST] yourself. It's [/INST] win win, Michael or at least win lose, which is what you're looking for, </s><s>[INST] wow, there's so many levels. Uh, so how did you actually meet? Meet? So my, the way I think about it is because we didn't do much research together at age 20, but, but then we all got laid off. So that was the other way, sorry to interrupt. But that was like one of the most magical places historically speaking. Uh [/INST] they did not appreciate what they had </s><s>[INST] and how do we uh I feel like there's a profound lesson in there too. How do we get it? Like what was, why was it so magical? It's just a coincidence of history or is there something special about some really good managers and people who really believed in machine learning as this is going to be important. Um, let's get the people who are thinking about this in creative and, and insightful ways and put them in one place and [/INST] star. But even beyond that, right, it was, it was Bell labs at its heyday and even when we were there, which I think was passed it and to be clear, </s><s>[INST] he's gotten to be at Bell labs. I never got to be at Bell labs joined after [/INST] That should have been 91 as a grad student. So I was there for a long time. Um, every summer twice </s><s>[INST] I worked for companies that had just stopped being the last Bell core and then 18 T labs, so Bell labs was several locations or for the researchers, like definitely Jerseys involved somehow. They're all in Jersey. [/INST] Yeah, they're all over the place, but they were in a couple places in Murray Hill was the labs place. Um, so </s><s>[INST] you, you had, you had an office in Murray Hill at one point in your career? [/INST] Yeah, I played ultimate frisbee on the cricket pitch at Bell Labs in Murray Hill. And then it became 18 T labs when split off with loose during what we call try best picture supposed to be better than Michael </s><s>[INST] kearns. Ultimate frisbee. [/INST] Yeah, yeah. </s><s>[INST] But I think that was not boasting. I think that I think Charles plays a lot of ultimate and I don't think [/INST] I yes, but that wasn't the point. The point is, yes, </s><s>[INST] I have played on a championship winning ultimate frisbee team or whatever ultimate team with Charles. So I know how good he is. [/INST] He's really good, how good I was anyway, when I was younger. But the thing is, I know </s><s>[INST] how young he was, when he gets so much younger than now. He's older [/INST] now. Michael is a much, much better basketball player than I was. Yes, no, not Michael, I'm very clear, </s><s>[INST] I've not played basketball with you. So you don't know how terrible I am, but you have a probably a pretty good guess [/INST] that you're not as good as Michael kurtz. </s><s>[INST] He's tall and [/INST] he cared about it. Very athletic, very good living. I live here with Michael anyway, but we were talking about something else, although I no longer remember what it was, what we were talking about, but also laps. So uh, this was kind of cool about what was magical about it. The first thing you have to know is that Bell Labs was an arm of the government, right? Because 18 T was an arm of the government. It was a monopoly. Uh, and you know, every month you paid a little thing on your phone bill, which turned out was a tax for like all the research that bell labs was doing and you know, they invented transistors and the laser and whatever else is the big </s><s>[INST] bang or whatever. The cosmic background [/INST] radiation. Yeah, they did all that stuff. There's some amazing stuff with directional microphones. By the way, I got to go in this room um, where they had all these panels and everything and we would talk to one another, he lose some panels around and then he would have me step two steps to the left and I couldn't hear a thing he was saying because nothing was bouncing off the walls and then he would shut it all down and you could hear your heartbeat deeply disturbing to hear your heartbeat. You can feel it. I mean, you can feel it now, there's so much, all this sort of noise around. Anyway, Bell Labs is about pure research. It was a university in some sense, the purest sense of the university, but without students. So it was all the faculty working with one another and students would come in to learn, they would come in for three or four months, you know, during the summer and they would go away. But it was just this kind of wonderful experience. I could walk out my door. In fact, I would often have to walk out my door and deal with rich sudden and Michael kearns yelling at each other about whatever it is, they were yelling about uh, the proper way to prove something or another. And I could just do that and day mcallister and Peter stone and, and all of these other people including it's tender. And then eventually Michael and it was just a place where you could think thoughts And it was okay because so long as once every 25 years or so, somebody invented the transistor, it paid for everything else, you could afford to take the risk. And then when that all went away it became harder and harder and harder to justify it. As far as the folks who were very far away we're concerned. And there was such a fast turnaround among middle management on the TNT side that you never had a chance to really build a relationship, at least people like us didn't have a chance to, to build relationship. So when the diaspora happened, um, it was amazing, right, Everybody left and I think everybody ended up at a great place and made a huge made to continue to do really good work with with machine learning. But it was a wonderful place and people will ask me, you know, what's the best job you've ever had And as a professor anyway, the answer that I would give is um, well, probably Bell Labs in some very real sense and I will never have a job like that again because Bell labs doesn't exist anymore. And you know, Microsoft research is great and google does good stuff and you can pick, I remember you can tell if you want to but Bell labs was magical. It was around for it was an important time. It represents a high water mark in in basic research in the US. </s><s>[INST] Is there something you could say about the physical proximity and the chance collisions like we live in this time of the pandemic where everyone is maybe trying to see the silver lining and accepting the remote nature of things. Is there one of the things that people like faculty that I talked to miss is the the procrastination like the chance to like everything is about meetings that are supposed to be, there's not a chance to just uh you know, talk about college book or whatever. Like go into discussion. That's totally pointless. [/INST] So it's funny you say this because that's how we met met is exactly that. So I'll let Michael say that. But I'll just add one thing which is just that uh you know, research is a social process and it helps to have random social interactions, even if they don't feel social at the time. That's how you get things done. Having one of the great things about um the air lab when I was there, I don't quite know what it looks like now, once they moved buildings, but we had entire walls that were white boards and people would just get up there and they were just right and people would walk up and you have arguments and you explain things to one another and you got so much out of the freedom to do that. You had to be okay with people challenging every fricking word you said, which I would sometimes find deeply irritating. But most of the time it was it was quite useful, but the sort of pointlessness and the interaction was, in some sense, the point at least for me. </s><s>[INST] Yeah, I mean you I think offline yesterday mentioned josh Tenenbaum and he's very much he put his man, he's such an inspiration in in the child like way that he pulls you in on any topic. Doesn't even have to be about machine learning or the brain, he'll just pull you into a closest rideable surface, which is still you can find whiteboards and mighty everywhere and and just like like basically cancel all meetings and talk for a couple hours about some some aimless thing. And it it feels like the whole world, the time space continuum kind of warps and that becomes the most important thing. And then it's just it's definitely something worth missing in this, in this world where everything's remote. There's some magic to the physical [/INST] presence. Whenever I wonder myself whether it really is as great as I remember it. I just go talk to josh. </s><s>[INST] Yeah. You know that's funny. There's a few people in this world that carried the the best of what particular institutions stand for, right? And this [/INST] uh josh. I mean, I don't, my guess is he's unaware of this. That's the point </s><s>[INST] that the masters are not aware of their mastery. So I mean, yes, But but first attention know how did you meet me? So I'm not sure what you were thinking. But my when it started to dawn on me that maybe we had a longer term bond was after we all got laid off. And you had decided at that point that there were still paid were given an opportunity to like do job search and kind of make a transition. But it was clear that we were done and I would go to my office to work and you would go to my office to keep me from working. That was that was my recollection of it. You have decided that there was no really no point in working for the company because our relationship with the company was it was done. [/INST] Yeah, but remember I felt that way before him, it wasn't about the company, it was about the set of people, they're doing really cool things and it always, always been that way. But we were working on something together. Oh </s><s>[INST] yeah, yeah, that's right. So at the very end we all got laid off. But then our boss came to, our boss's boss came to us because our boss was Michael kearns and he had jumped ship brilliantly, like perfect timing, like things like right before the ship was about to sink, he was like got to go and and landed perfectly because Michael Cairns and the leaving the rest of us to go like this is fine. And then it was clear that wasn't fine. And we were all toast. So we had this sort of long period of time and but then our boss figured out, okay, wait, maybe we can save a couple of these people if we can have them do something really useful. And uh the useful thing was, we were going to make a basically an automated assistant that could help you with your calendar, you could like tell it things and it would respond appropriately. It would just kind of integrate across all sorts of your personal information. And so me and Charles and Peter Stone were this were set up as the crack team to actually solve this problem, other people, maybe we're too theoretical that they thought and, and, but we could actually get something done, so we sat down to get something done and there wasn't time and it wouldn't have saved us anyway. And so it all kind of went downhill. But the interesting, I think coda to that is that our boss's boss is a guy named Ron brockman and he, when he left 80 and because we were all laid off, he went to DARPA, started up a program there that became Kahlo, which is the program from which Siri sprung, which is a digital assistant that helps you with your calendar and a bunch of other things. Um, it really, you know, in some ways, got its start with me and Charles and Peter trying to implement this vision that Ron brockman had, that he ultimately got implemented through his role at DARPA. So when I'm trying to feel less bad about having been laid off from what is possibly the greatest job of all time. Um, I think about, well, we kind of helped birth Siri, that's something [/INST] and he did other things too, but the, we got to spend a lot of time in his office and talk about, </s><s>[INST] we've got a lot of time in my office. Yeah, yeah, yeah. And so then we went on our merry way, everyone went to different places, Charles landed at Georgia tech, which was, uh, what he always dreamed he would do. And so that worked out well. Um, I came up with a saying at the time, which is luck favors the Charles, it's kind of like luck favors the prepared, but Charles like, like he wished something and then it would basically happen just the way he wanted. It was, it was inspirational to see things go that way things worked out and we stayed in touch and then, um, I think it really helped when you were working on, I mean you kept me in the loop for things like threads and, and the work that you're doing at Georgia tech. But then when they were starting their online Master's program, he knew that I was really excited about moocs and online teaching and he's like, I have a plan and I'm like, tell me your plan. He's like, I can't tell you the plan yet because they were deep in negotiations between Georgia tech and Udacity to make this happen and they didn't want it to leak. So Charles wood kept teasing me about it, but wouldn't tell me what was actually going on. And eventually it was announced and he said, I would like you to teach the machine learning course with me. I'm like, that can't possibly work. Um, but it was a great idea and it was, it was super fun. It was a lot of work to put together, but it was, it was really great and was that the first time you thought about, first of all, was it the first time you got seriously into teaching? I mean, you know, I'm trying to get the findings like this is already and I had after you jump too, so like there's a little bit of jumping around in time. Yeah, sorry about that, big jump in time, so like the moocs thing, so Charles got Georgia tech and he may be Charles, maybe this is [/INST] A 2002, </s><s>[INST] He got to Georgia Tech in 2002 and but and worked on things like revamping the curriculum, the undergraduate curriculum so that it had some kind of semblance of modular structure because computer science was at the time moving from a fairly narrow specific set of topics to touching a lot of other parts of of of intellectual life and the curriculum was supposed to reflect that. And so um Charles played a big role in in kind of redesigning that and then [/INST] and for my and for my my labors I ended up to his associate dean </s><s>[INST] right, he got to become associate Dean of charge of educational stuff. Be a valuable lesson if you're good at something, uh they will give you responsibility to do more of that thing until you show competence. Don't show competence. If [/INST] you know what the responsibility, here's what they say. Uh the reward for good work is more work. The reward for bad work is less work, which I don't know depending on what you're trying to do that week. One of those is better than the other. One of the problems with the word works are to interrupt </s><s>[INST] is that it seems to be an antonym in this particular language. We have the opposite of happiness, but it seems like they're they're like, that's one of, you know, we talked about balance. It's always like work life balance always rubbed me the wrong way as a terminal. And I know it's just words like the opposite of work is play ideally work his play. [/INST] Oh, I can't tell you how much time I spend. Certainly was a bell Labs would except for a few very key moments as a professor I would do this to. I just cannot believe they're paying me to do that because it's fun. It's something that I would I would do for a hobby if I could anyway, so that's what it worked. I'm sure you want to be saying </s><s>[INST] that when this is being recorded as [/INST] a dean, that is not true at all. I need to raise. But but I think here with this that even though a lot of time passed, you know, Michael, I talked almost everywhere. We texted almost every day during the period </s><s>[INST] Charles. At one it took me there was the I. C. M. L. Conference, the machine learning conference was in Atlanta. I was the chair. The general chair of the conference Charles was my publicity chair or something like that or fundraising chair. Yeah. Um, but he decided to be really funny if he didn't actually show up for the conference in his own home city. Uh, so he didn't, but he did at one point, picked me up at the conference in his Tesla and drove me to the Atlanta mall and forced me to buy an iphone because he didn't like how it was to text with me and thought it would be better for him if I had an iphone, the text would be somehow smoother. And it was, and it was, [/INST] and it is and his life has been in </s><s>[INST] my life is better. And so, but, but it was, yeah, Charles forced me to get an iphone so that he could text me more efficiently. I thought that was an interesting moment. It [/INST] works for me anyway, so we kept talking the whole time and they eventually did the, we did the teaching thing and it was great and there's a couple of reasons for that by the way. One is, I really wanted to do something different. Like you've got this medium here, People claim it can change things. What's the thing that you could do in this medium that you could not do otherwise? Uh, besides edit. Right. I mean, what could you do and being able to do something with another person with that kind of thing. It's very hard. I mean you can take turns, but teaching together, having conversations very hard. Right? So that was a cool thing. The second thing you may excuse to do more stuff with </s><s>[INST] him. Yeah. I always thought he makes it sound brilliant. Um and it is, I guess. But at the time it really felt like I've got a lot to do Charles is saying and it would be great if Michael could teach the course and I could just hang out. Yeah, just kind of coast on [/INST] that. Well, that's what the second class was more like that because it was explicit </s><s>[INST] first class, it was at least half. But the structure, once again, letting the facts get in the way of a good story. I should just like Charles. [/INST] But that's the fact that he saw. But that was, that was kind of yeah, that was sort of true for 76 42 which is the reinforcement learning class because that was really his class. You started with reinforcement learning, we started, I didn't interim machine learning 76 41 which is supervised learning, unsupervised learning and reinforcement learning, decision making cram, all that in there. Kind of assignments that we talked about earlier and then eventually, about a year later we did a follow on 76 42 which is reinforcement learning and decision making. The first class was based on something I've been teaching at that point for well over a decade and the second class was based on something Michael had been teachers actually, I learned quite a bit teaching that class with him. But he drove most of that. But the first one I drove most of all my material. Although I had stolen that material originally from slides I found online from Michael who had originally stolen that material from, I guess slides he found online probably from Andrew more because the jokes were the same. Anyway, at least some of the least when I found the slide, some of the stuff with yes, every machine learning class Todd in early 2000 stole from Andrew more particular joke to the at least the structure now I did and he did actually a lot more with reinforcement learning and such and game theory and those kinds of things. But you know, we all sort of built world. No, no, no, no. I mean in teaching that class, </s><s>[INST] the coverage was different than, [/INST] than what other people were starting. Most people are just doing supervised learning and maybe a little bit of, you know, clustering and whatnot. But we took it all the way to a lot of it just comes from Tom Mitchell's book. Oh no. Yeah, except, well, half of it comes from Tom Mitchell's book. Right? The other half doesn't, this is this is why it's all readings right. Because certain things weren't invented when tom was right. Uh, but it was, it was quite good, but there's a reason for that besides, you know, just I wanted to do it. I wanted to do something new and I wanted to do something with him, which is a realization, which is despite what you might believe, he's an introvert and I'm an introvert or I'm on the edge of it being an introvert anyway. But both of us, I think, um, enjoy the energy of the crowd. Right? There's something about talking to people and bringing them into whatever we find interesting that is empowering energy, energizing or whatever. And I found the idea of staring alone at a computer screen and then talking off of materials less inspiring than I wanted it to be. And </s><s>[INST] I had in fact done a mook for Udacity on algorithms and it was a week in a dark room, talking at the screen writing on the little pad and I didn't know this was happening. But they had watched the crew had watched some of the videos while you like in the middle of this and they're like, something's wrong, you're sort of shutting down. Um, and I think a lot of it was, I'll make jokes and no one would laugh and I felt like the crowd hated me. Now of course there was no crowd. So like it wasn't rational, but it's a little, each time I tried it and I got no reaction. It just was taking the energy out of my performance out of my [/INST] presentation. Fantastic metaphor for grad school anyway by working together. We could play off each other and have it and keep the </s><s>[INST] energy up because you can't you can't let your guard down for a moment with Charles. He'll just he'll just [/INST] overpower you. I have no idea we're talking about but we would work really well together I thought and we knew each other so I knew that we could we could sort of make it work. Plus I was the associate dean. So they had to do what I told him to do, we had to do that, we had to make it work. And so it worked out very well. I thought well enough that we with </s><s>[INST] great power comes great [/INST] power. That's right. And we became smooth and curly and that's when we did the the the overfitting thriller video. </s><s>[INST] Yeah. So what can we just uh moving curly. Where that? Okay so the and then it happened, it was completely spontaneous. Names you go by [/INST] uh were students, He </s><s>[INST] was he was lecturing so the way that we structured the lectures is one of us is the lecturer and one of us is basically the student. And so the he was lecturing [/INST] on the lecture, prepares all the materials, comes up with the quizzes and then the student comes in not knowing anything. So it's just like being on campus. Uh and I was doing game theory in particular the prisoners, the </s><s>[INST] prisoners dilemma. And so he needed to set up a little prisoner's dilemma grid. So he drew it and I could see what he was drawing and the prisoner's dilemma consists of two players to parties. So he decided he would make little cartoons of the two of us. And so there was uh two criminals right that we're deciding whether or not to rat each other out. Um One of them he drew as a circle with a smiley face and a kind of goatee thing, smooth head and the other one with all sorts of curly hair. And he said this is smooth and curly. I said smooth and curly. He said you know smooth with a V. It's very important that it has the and and then the students really that the students really took to that like they they found that relatable. [/INST] He started singing Smooth Criminal by Michael Jackson </s><s>[INST] and that those those names so that so we now have a video series that an episode are kind of first actual episode should be coming out today. Um Smooth and clearly on video where the two of us discuss uh episodes of Westworld, we watch Westworld and we're like what does this say about computer science [/INST] and we never we did not watch it. No, it's on season three or whatever we have as of this recording is on season three and now two episodes total. Think about three. What </s><s>[INST] Do you think about Westworld two episodes in so I can tell you so far. I'm just guessing what's going to happen next. It seems like bad things are going to happen with the robots uprising. [/INST] So I have not. I mean, you know, I vaguely remember a movie existing. So I assume it's related to that. But </s><s>[INST] that was more of my time than your time Charles. [/INST] That's right. Because you're much older than I think the important thing here is that uh, its narrative, right? It's all about telling a story. That's the whole driving thing. But the idea that they would give these referees that they would make people, they would remember remember the </s><s>[INST] awful things that happened happened. Who [/INST] could possibly think that was going? I got to I mean, I don't know. I've only seen the first two episodes or maybe the third one. I think I believe you know </s><s>[INST] what it was. You know what the problem is that the robots were actually designed by Hannibal Lecter. That's true. [/INST] So </s><s>[INST] like what do you think is going to happen? Bad things. [/INST] It's clear that things are happening and characters being introduced and we don't yet know anything. But still, I was just struck by how it's all driven by narrative and story. And there's all these implied things like programming. Half the programming interface is talking to them about what's going on in their heads, which is both. I mean artistically it's probably useful to film it that way, but think about how it would work in real life. It just seems very creative. But there was we saw in the second episode, there's a screen, you can see things they were wearing like state in the world. It was quite interesting to just kind of asked this question so far. I mean I assume it veers off into never never land at some point, but uh </s><s>[INST] I'm also a fan, a guy named Alex Garland, he's a director of ex Machina and he is the first I wonder if Kubrick was like this actually, is he like studies what would it take to program an ai systems? Like he's he's curious enough to go into that direction. On the West Wall side. I felt there was more emphasis on the narratives than like actually asking like computer science questions like how would you build this? How would you uh [/INST] how would you debug it? I still think to me that's the key issue if they were terrible to buggers. Yeah, </s><s>[INST] well they said specifically, so we make a change and we put it out in the world and that's bad because something terrible could happen. Like if [/INST] you're putting things out of the </s><s>[INST] world and you're not sure whether something terrible is going to happen, you're probably your process [/INST] is probably I just feel like there should have been someone whose sole job it was to walk around poke is headed and say what could possibly go wrong over and over again. </s><s>[INST] I would have loved if there was an I did watch a lot more and I'm not giving anything away. I would have loved it if there was like an episode where like, like the new intern is like debugging a new model or something and like it just keeps failing and they're like all right. And then more turns into like an episode of Silicon Valley or something like that versus like this ominous ai systems that are constantly like threatening the fabric of this world that's been created. Yeah. And you know, [/INST] the other, this reminds me of something that so I agree with that, that actually very cool. At least for the small percentage of people who care about the bugging systems. But the other thing is debugging the serie it falls into the thing of the Sequels. Fear of the book. Oh my gosh, anyway, so a </s><s>[INST] nightmare show. It's a [/INST] horror movie. I think that's where we lose people. By the way early on is the people who either decide either figure out debugging or think debugging is terrible. This is where we lose people in computer. This is part of the struggle versus suffering, right? You get through it and you kind of get the skills of it or you just like this is dumb and this is a dumb way to do anything. And I think that's when we lose people. But um uh well I'll leave it at that. But I think that I think that that there's something really, really neat about framing it that way. But what I don't like about all of these all of these things and I love text marketing by the way, the ending was very depressing. </s><s>[INST] Uh One of the things after talking to Alex about, he says that the thing that nobody noticed he put in is uh at the end spoiler alert, the robot turns and looks at the camera and smiles briefly. And to him he thought that his definition of passing the touring the general version of the turing test or the consciousness test Is smiling for no one mm Like like mhm. Not you know, it's it's like the [/INST] chinese room kind of experiment is </s><s>[INST] not always trying to act for others but just on your own being able to have a relationship with the actual experience and just like take it in. I don't know he said like nobody noticed [/INST] the magic of this vague feeling that I remember the smile but now you just put the memory in my head. So probably not. But I do think that that's interesting. Although by looking at the camera, you are smiling for the audience, right? You're breaking the fourth wall it seems I mean well that's a limitation of the medium but I like that idea but here's the problem I have with all of those movies, all of them. Um is that but I know why it's this way and I enjoy those movies. Um And Westworld is uh it sets up the problem of Ai as succeeding and then having something we cannot control. But it's that's not the bad part of Ai the bad part of Ai is the stuff we're living through now, right? It's using the data to make decisions that are terrible. It's not the intelligence that's going to go out there and surpass us and you know, take over the world or you know, lock us into a room to starve to death slowly over multiple days. It's instead the tools that we're building that are allowing us to make the terrible decisions we would have less efficiently made before, right? You know, computers are very good at making us more efficient, including being more efficient at doing terrible things. And that's the part of the eye we have to worry about. It's not the you know, true intelligence that we're going to build sometime in the future, probably long after we're around. Um But you know, I just I think that whole framing of it sort of misses the point, even though it is inspiring. And I was inspired by those ideas, right? That I got into this in part because I wanted to build something like that philosophical questions are interestingly, but you know, that's not where the terror comes from, the terror comes from the everyday </s><s>[INST] and you can construct situations in the subtlety of the interaction between Ai and the human, like with social networks, all the stuff you're doing with interactive artificial intelligence, But you know, I feel like cal 9000 came a little bit closer to that when in 2001 Space Odyssey because it felt like a personal assistant, you know, it felt like closer to the ice systems we have today and and the and the real things we might actually encounter, which is over relying uh in some fundamental way and are like dumb assistance or on social networks, like over offloading too much of us onto uh uh you know, onto things that require internet and power and so on and thereby becoming powerless as a standalone entity. And then when that thing starts to misbehave in some subtle way, it creates a lot of problems. And those problems are dramatized when you're in space because you don't have a way to walk away. [/INST] Well, as the man said, once, once we started making the decisions for you, it stopped being your world, right? That's the matrix, Michael, in case you don't, you don't remember. But on the other hand, I could say no, because isn't that what we do with people anyway? You know, this kind of the shared intelligence that is humanity is relying on other people constantly. I mean, we we hyper specialized, right? As individuals, we are still generally intelligent. We make our own decisions in a lot of ways. But we leave most of this up to other people and that's perfectly fine and by the way, everyone doesn't necessarily share our goals. Sometimes they seem to be quite against us. Sometimes we make decisions that others would see us against our own interests and yet we somehow manage it, manage to survive. I'm not entirely sure why an Ai would actually make that worse or even different. Really. </s><s>[INST] You mentioned the Matrix. Do you think we're living in a simulation? It does feel like a thought game more than a real scientific question? Well, I'll tell you why I like, I think it's an interesting thought experiment. See what you think from a computer science perspective, it's a good experiment of how difficult would it be to create a sufficiently realistic world that us humans would enjoy being in. That's almost like if we're living in a simulation, then I don't believe that we were put in the simulation. I believe that it's just physics playing out and we came out of that. Like, I don't I don't I don't think so. You think you have to build the universe? I think the universe itself, we can think of that as a simulation. And in fact, I try sometimes I try to think about to understand what it's like for computer too. Start to think about the world. I try to think about the world, um things like quantum mechanics where it doesn't feel very natural to me at all. Um and it really strikes me as I don't understand this thing that we're living in. It has, there's weird things happening in it that don't feel natural to me at all now, if you want to call that as the result of a simulator. Okay, I'm fine with that. But like, I don't know the bugs in the simulation. [/INST] There's the bugs. I mean the interesting thing about the simulation is that it might have bugs. I mean, that's the thing that there would be bugs for the people </s><s>[INST] in the simulation. They're just that's just reality. [/INST] Unless you were enough to know that there was a bug. But I think back to the Matrix, the way I don't think </s><s>[INST] that we live in a simulation created for us. Okay, I would say that. I [/INST] think that's interesting. I actually never thought about it that way. I mean, you, the way you asked the question though, could you create a world that is enough for us humans? It's an interestingly self referential question because the beings that created the simulation probably have not created the simulation. That's realistic for them, but we're in the simulation. And so it's realistic for us. So we could create a simulation that is fine for the people in the simulation as it were. That would not necessarily be fine for us as the creators of the simulation, but </s><s>[INST] while you can, you can forget, I mean, when you go into the, if you play video games virtual reality, you can if some suspension of disbelief or whatever, uh, becomes the world it becomes the world even like in brief moments you forget that another world exists. I mean that's what like good stories do they pull you in question? Is is it possible to pull, you know, our brains are limited. Is it possible to pull the brain in to what we actually stay in that world longer and longer and longer and longer and like not only that, but we don't want to leave. And so especially this is the key thing about the developing brain is if we journey into that world early on in life often, [/INST] how would you even know? Yeah, </s><s>[INST] so I but like from a video game design perspective from a Westworld perspective is I think I think it's an important thing for even uh computer scientists to think about because it's clear that video games are getting much better and virtual reality, although it's been ups and downs just like artificial intelligence, It feels Like virtual reality will be here in a very impressive form. If we were to fast forward 100 years into the future in a way that might change society fundamentally. Like if I were to, I'm very limited in predicting the future as all of us are. But if I were to try to predict, like in which way I'd be surprised to see the world 100 years from now, it be that or impressed it be that we're all no longer living in this physical world, that we're all living [/INST] in a virtual world, you really need to re calculating God, bye Sawyer. It's a hell he'll read it in the night. It's a very easy read, but it's assuming you're that kind of reader, but it's a, it's a good story and it's kind of about this, but not in a way that it appears. And I uh, really enjoyed the thought experiment. Um, I think it's pretty sure it's robert Sawyer anyway, he's apparently Canadians top science fiction writer, which is why the story mostly takes place in Toronto. But it's a, it's a very good, uh, it's a very good sort of story that that's sort of imagine a very different kind of simulation hypothesis sort of thing from, say, the Egg, for example. You know, you know, I'm talking about the short story, um, by the guy who did the martian who wrote The martian, </s><s>[INST] you [/INST] know, the book. </s><s>[INST] So, we had this whole discussion that Michael doesn't, uh, doesn't partake in this exercise of reading. [/INST] He doesn't seem to like it, which seems very strange to me, considering how much he has to read. I read all the time. I used to read 10 books that every week when I was when I was in sixth grade or whatever. It was a lot of it's science fiction, a lot of it, a lot of history, but I love to read. But anyway, you should re calculating God, I think you will, you know, it's very easy read. Like I said I think you'll enjoy sort of the ideas that it presents. </s><s>[INST] Yeah. I think the thought experiment is quite interesting. Uh One thing I've noticed about people growing up now, I mean we talk about social media but video games is a much bigger, bigger and bigger and bigger part of their lives and the video games have become much more realistic. I think it's possible that yeah the three of us are not uh maybe the two of you are not familiar exactly what the numbers we're talking about here, [/INST] like the number of people, it's bigger than movies, right? It's it's huge. I used to do a lot of the narrow computational narrative stuff. </s><s>[INST] I understand that economists can actually see the impact of video games on the labor market. That that there are there there's fewer young men of a certain age participating in like paying jobs then you'd expect. And and that they trace it back to video [/INST] games. I mean the problem with star trek was not warp drive or teleportation, It was the Holodeck. But if you have the Holodeck, that's it, that's it. You go in the holiday, You never come out. I mean it just never made once. I saw that. I thought, okay, well so this is the end of humanity as we know, right? They've invented the holiday </s><s>[INST] because that feels like the singularity not some G. I. Or whatever, it's some possibility to go into another world that can be artificially made better than this one [/INST] and slowing it down so you live forever or speeding it up so you appear to live forever or making the decision of when to die. </s><s>[INST] And then most of us will just be old people on the porch yelling at the kids these days in their virtual reality, but they won't hear us because they've got headphones on. So I mean we're winding back to moocs is their lessons that you've speaking of kids these days, uh [/INST] I'll </s><s>[INST] fix it in post. That's Charles's favorite phrase, [/INST] fix it in post, fix it in post it and post it all when we were recording all the time. Whenever the editor didn't like something or whatever, I would say we'll fix it in post. He hated that. He hated that more than anything in the way </s><s>[INST] of saying I'm not going to do it [/INST] again, </s><s>[INST] You know, you're on your own for this one, [/INST] but it always got fixed in post. </s><s>[INST] Exactly. So uh is there something you've learned about? I mean it's interesting to talk about movies. Is there something you've learned about the process of education about thinking about the present? I think there's two lines of conversation to be had here is the future of education in general you've learned about, and more presently is the education at times of covid [/INST] the second thing in some ways matters more than the first for at least in my head for, not just because it's happening now, but because I think it's reminded us of a lot of things coincidentally today, there's an article out by a good friend of mine who's also a professor at Georgia tech, but more importantly, a writer and editor at the atlantic, I named Ian bogus. Um, and the title is something like americans will sacrifice anything for the college experience. Uh, and it's about why we went back to college and why people wanted us to go back to college and it's not, you know, greedy presidents trying to get the last dollar from someone. It's because they want to go to college and what they're paying for is not the class is what they're paying for is the college experience is not the education, it's being there. I believe this for a long time that we continually make this mistake of people want to go back to college as being, people want to go back to class. They don't look back to campus, They want to move away from home. They want to do all those things that people experience. Um, it's a rite of passage. It's a, it's an identity if I can, if I can steal some of them, Ian's words here and I think that's right. And I think what we've learned through Covid is it has made it, the desegregation was not the desegregation of the education from the place of the university place and that you can get the best anywhere you want to turn that there's lots of reasons why that is not necessarily true. The desegregation is having it shoved in our faces. That the reason to go again, that the reason to go to college is not necessarily to learn, it's to have the college experience and that's very difficult for us to accept, even though we behave that way. Most of us when we were undergrads, you know, a lot of us didn't go to every single class we learned and we got it and we look back on and we have, we have the learning experience as well, obviously, particularly us, because this is the kind of thing that we do, and my guess is that's true of the vast majority of your audience, but that doesn't mean the, I'm standing in front of you telling you this is the thing that people are excited about. Um, and that's why they want to be there, primarily why they want to be there. So to me, that's what Covid has forced us to deal with. Um, even though I think we're still all in deep denial about it, um, and hoping that it will go back to that, And I think about 85% of it will, will be able to pretend that that's really the way it is again, and we'll forget the lessons of this. But technically what will come out of it or technologically will come out of it is a way of providing a more dispersed experience through online education and these kinds of remote things that we've learned and we'll have to come up with new ways to engage them in the experience of college, which includes not just the parties or whatever kids do, but the learning part of it so that they actually come out four or five or six years later with having actually having actually learned something. So, um, I think the world will be radically different afterwards and I think technology will matter for that. Just not in the way that the people who were building the technology originally imagined it would be. And I think this would have been true even without Covid, but Covid has accelerated that reality. So it's happening in two or three years or five years as opposed to 10 or 15. </s><s>[INST] That was an amazing answer that I did not understand. [/INST] So it was </s><s>[INST] passionate and and shots, but I don't know, I just didn't know I'm not trying to criticize, I think, I don't think I'm getting it. So you mentioned disaggregated. So what's [/INST] that? Well, so you know, the power, the power of technology that if you go on the west coast and hang out long enough is all about, we're going to disaggregate these things together. The books from the bookstore, you know, that kind of a thing and then suddenly amazon controls the universe, right? And technology is a disruptor, right? And people have been predicting that for higher education for a long time, but certainly this is, this is </s><s>[INST] this the sort of idea like students can aggregate on a campus someplace and then take classes over the network anywhere. [/INST] This is what people thought, what's going to happen or at least people claim it was going to happen. Right. That because </s><s>[INST] my daughter is essentially doing that now. She's on one campus but learning in a different [/INST] campus and Kobe makes that possible, right? Kobe makes that legal but avoidable. But the idea originally was that, you know, you and I were going to create this machine learning class and it was going to be great and then no one else would be the machine learning class. Everyone trades. Right. That was never going to happen. But you know, something like that. But I feel like you </s><s>[INST] didn't address that. So why, why, why is it that? Why? [/INST] I don't think that will be the </s><s>[INST] thing that happened. The college experience. Maybe I maybe I missed what the college experience was. I thought it was piers. People hanging [/INST] a large part of it is piers. Well, it's peers and independence. </s><s>[INST] Yeah, but you can do classes online for all of that. [/INST] No, no, no, no. Because we're social people. Right? So you want to take the </s><s>[INST] classes that also has to be part of an experience. [/INST] It's in a context in the context of the university and by the way it actually matters that Georgia tech really is different from Brown? </s><s>[INST] I see because then students can choose the kind of experience they think is going to be best for [/INST] them. Okay. I think we're giving too much agency to the students and making an informed decision. But the truth, but yes, they will make choices and they will have different experiences and some of those choices will be made for them. Some of them will be choices they're making because they think it's this, that or the other. I just don't want to say I don't want to give the idea homogeneous. Yes. It's certainly not homogeneous, right? I mean Georgia tech is different from Brown. Brown is different from pick your favorite state school in Iowa Iowa State. Okay. Which I guess is my favorite state school in Iowa. But you know, these are all different. They have different context and a lot of those contexts are there about history. Yes. But they're also about the location of where you are there. About the larger group of people who around you. Whether you're in Athens Georgia and you're basically the only thing that's there as a university, you're responsible for all the jobs or whether you're at Georgia State University which is an urban campus um where you're surrounded by, you know, six million people uh, in your campus where it ends and begins in the city and it begins, we don't know, it actually matters where there are small campus or large companies. Why </s><s>[INST] is it that if you go to Georgia tech, you're like forever proud of that and you like say that to people at dinner like bars and whatever. And if you not, you know, if you get a degree in an online university somewhere, you don't, that's not a thing that comes up at a bar. [/INST] Well, it's funny you say that. So the students who take our online masters by several measures are more loyal than the students who come on campus. Certainly for the master's degree, the reason for that, I think you'd have to ask them. But based on my conversations with them, I feel comfortable saying this is because this didn't exist before. I mean we talk about this online masters and that it's preaching, you know, 11,000 students and that's an amazing thing. And we're admitting everyone, we believe we can succeed without a 60% acceptance rate. It's amazing, right? It's also a 66 $100 degree. The entire degree called 6600 and 7000 depending on how long you take, uh, dollar degree as opposed to 46,000 the cost to come on campus. Um, so that feels, and I can do it while I'm working full time and I've got a family and a mortgage and all these other things. So it's an opportunity to do something you wanted to do, but you didn't think was possible without giving up two years of your life as well as all the money and everything else the life that you have built. So I think We created something that had an impact. But importantly we gave a set of people opportunities, they otherwise didn't feel they had. So I think people feel very loyal about that. My biggest piece of evidence for that besides the surveys is that we have somewhere north of 80 students might be 100 at this point who graduated But come back in ta for this class for basically minimum wage, even though they're working full time because they believe they believe in in sort of having that opportunity they want to be a part of something now, will they will generation three feel this way 15 years from now when people have that same sense. I don't know. But right now they kind of do. And so it's not the online, it's a matter of feeling as if you're part of something right? We're all very tribal, right? Um and I think there's something very tribal about being a part of something like that, being on campus. Makes that easier going through a shared experience makes that easier. It's harder to have that shared experience. If you're alone. Looking at a computer screen, we can create ways to make </s><s>[INST] that it's impossible. It is that the question is it still is the intuition to me. And it was at the beginning when I saw something like the online Master's Program is that this is going to replace universities [/INST] and they won't replace universities. But </s><s>[INST] where is it? Why? [/INST] Because it's living in a different part of the ecosystem, right? The people who are taking it already adults, they've they've gone through their undergrad experience there. I think their their goals have shifted from when they were 17. Um, they have other things that that are going, but it does do something really important, something very social and very important, right? You know, this whole thing about, you know, don't build the sidewalks, just leave the grass and the students or the people will walk and you put the sidewalks where they create paths, this kind of thing. Um, they're architects who apparently believe that's the right way to do things. The metaphor here is that we we we created this environment. We didn't quite know how to think about the social aspect, but you know, we don't have time to solve all, do all the social engineering. Right? Um, the students did it themselves. They created, um, You know, these groups like on Google Plus, there's like 30 something groups created in the first year because somebody had these cool plus. Um, and they created these groups and they divided up in ways that made sense. We live in the same state, We're working on the same things, We have the same background or whatever and they created these social things. We sent them t shirts and they were, we have all these great pictures of students putting on their t shirts as they travel around the world. I climbed this mountaintop and putting this t shirt on. I'm a part of this. They were part of them. They created these social environment on top of the social network and the social media that existed uh, to create this sense of belonging and being a part of something. They found a way to do it right. And I think they had other, it scratched an itch that they had, but they had scratched some of that itch that might have required to be physically in the same place long before. Right? So I think, yes, it's possible and it's more than possible. It's necessary. But I don't think it's going to replace the university as we know it. The university as we know, it will change. But there's just a lot of power in the kind of rite of passage kind of going off to yourself. Maybe there'll be some other rite of passage that will happen. That's the driver somewhere else. So, </s><s>[INST] the university is such a fascinating uh, mess of things. So just even the faculty position is a fascinating mess. Like it doesn't make any sense. It's, it's stabilized itself, but like why are the world class researchers spending a huge amount of time or their time teaching and service. Like you're doing like three jobs and, and I mean it turns its maybe an accident of history or human evolution. I don't know, it seems like the people who are really good at teaching are often really good at research. There seems to be a parallel there, but like it doesn't make any sense that you should be doing that at the same time. It also doesn't seem to make sense that your place where you party, it's the same place where you go to learn calculus or whatever. But [/INST] it's a safe space </s><s>[INST] space for everything, [/INST] relatively speaking, it's a safe space now. By the way, I feel the need very strongly to point out that we are living in a very particular weird bubble, right? Most people don't go to college and by the way, the ones who do go to college, they're not 18 years old, right there, like 25 or something. I forget the numbers. You know, the places where we've been, where we are. Uh, they look like whatever we think the traditional movie version of universities are, but for most people, it's not that way at all. By the way, most people who drop out of college, it's entirely for financial reasons. Right? So, you know, we're talking about a particular experience. Um, and so for that set of people, which is very small, but larger than it was a decade or two or three or four certainly ago. Uh, I don't think that will change my concern, which I think is kind of implicit in some of these questions is that somehow we will divide the world up further uh into the people who get to have this experience and get to have the network and they sort of benefit from it and everyone else while increasingly requiring that they have more and more credentials in order to get a job as a barista, right? You gotta have a Master's degree in order to to work at Starbucks, we're going to force people to do these things, but they're not going to get to have that experience and there'll be a small group of people who do, who continue to, you know, positive feedback loop etcetera etcetera. I worry a lot about that, which is why for me. Um and by the way, here's an answer to your question about faculty, which is why to me that you have to focus on access in the mission. I think the reason whether it's good, bad or strange, I mean I agree, it's strange, but I think it's useful to have the faculty member, particularly large r one universities where we've all had experiences uh that um you tie what they get to do and with the fundamental mission of the university and let the mission drive. What I hear when I talk to faculty is they love their PhD students because they're creating they're reproducing basically, right? And it lets them do their research and multiply, but they understand that the mission is the undergrads and so they will do it without complaint mostly because it's a part of the mission and why they're here and they have experiences within themselves and it was important to get them, get them where they were going. The people tend to get squeezed and that, by the way of the master students who are neither the phds who are like us nor the undergrads, we we have already bought into the idea that we, we have to teach though. That's increasingly changing anyway. I think tying that mission in really matters and it gives you a way to unify people around, making it an actual higher calling. Education feels like more of a higher calling to me than even research, because education, you cannot treat it as a hobby if you're going to do it well, </s><s>[INST] but that's the, that's the push back on this whole system is that you should, education will be a full time job, right? And like, it's almost like research is a distraction from that. [/INST] Yes. Although I think most of our colleagues, many of our colleagues would say that research is the job and education is the distraction, </s><s>[INST] but that's the beautiful dance. It seems to be that that tension in itself is, seems to work, seems to bring out the best in uh, in the faculty like [/INST] that, but I will point out two things. One thing I'm going to point out, the other thing I want Michael to point out because I think Michael is much closer to the, to the sort of the ideal professor in some sense than I am. </s><s>[INST] You're the platonic sense of a professor. I don't know what he meant by that. He is the dean, so he has a different experience. [/INST] I'm giving him, I'm giving him time to think of. The profound thing is going to sound good. But let me, let me point this out, which is that We have lecturers in the College of Computing where I am, uh, there's 10 or 12 of them depend on account as opposed to the 90 or so tenure track faculty. Those 10 lecturers who only teach, well, they don't only teach, also do service. They some of them do research as well, but primarily they teach, They teach 50% over 50% of our credit hours and we teach everybody right? So they're doing not just, they're doing more than eight times the work of the tenure track faculty, um, just more closer to nine or 10. And that's including a great courses. Right? So they're doing this, they're teaching more. They're touching more more than anyone and their beloved for it. I mean, so we recently had a survey, we do these, everyone does these alumni surveys, you hire someone from outside to do whatever. And I was really struck by something. He saw these really cool numbers. I'm not going to talk about it because, you know, it's all internal confidential stuff. But one thing I will talk about Is there was a single question we asked our love and these are people who graduated, you know, born in the 30s and 40s all the way up. The people who graduated last week, right? Um well, last semester, um, yeah, uh, and there was a question, name, a single person who had a strong positive impact on you, something like that. </s><s>[INST] I think it was special impact, [/INST] special impact on you. And then so they got all the answers from people and they created a word cloud. That was clear word cloud created by people who don't do word clouds for living because they had one person whose name like appeared like nine different times, like Phillip Phil dr Phil, you know, whatever, but they got all this and I looked at it and I noticed something really cool. The five people from the College of Computing I recognized we're in that cloud and um, four of them, We're lecturers, the people who teach two of them relatively modern. Both were chairs of our division of computing instruction one just one retired, one is going to retire soon, and the other two were lecturers I remembered from the 1980s. Um, two of those four, actually, we have 1/5 person was Charles. That's not important, I don't tell people that. But the Two of those people are teaching awards are named after. Thank you, Michael. Two of those are teaching awards are named after? Right? So when you ask students, alumni, people who are now 67 years old, even, you know, who touched them? They say the dean of students, they say the big teachers who taught the big introductory classes that got me into it. There's a guy named Richard barker is on there, who's who's who's known as a great teacher. The Phil. Adler guy who, who I probably just said his last name, but I know the first name is Phil because he kept showing up over and over again. Uh, Famous Adler </s><s>[INST] is what it said. Okay, so different people spelled it differently. So he appeared multiple [/INST] times. So he was clearly, it was a professor in um, the business school. Um, but when you read about him and I went to read amongst, I was curious who he was. You know, it's all about his teaching and the students that he touched, right? So whatever it is that we're doing and we think we're doing that's important and why we think the university's function. The people who go through it. They remember the people who were kind to them, the people who taught them something and they do remember it. They remember it later. I think that's important. That's what the mission matters. </s><s>[INST] Yeah. Not to completely lose track of the fundamental problem of how do we replace the party aspect of universities? Uh, before we go to the what makes the platonic professor do you uh do you think like what in your senses the role of moocs in this whole picture during covid? Like are we should we desperately be clamoring to get back on campus? Or is this a stable place to be for a little while? I don't know. I know that it's that the online teaching experience and learning experience has been really rough. I think that people find it to be a struggle in a way that's not a happy positive struggle that when you got through it you just feel like glad that it's over as opposed to I've achieved something. So, you know, I worry about that, but you know, I worry about just even before this happened, I worry about lecture teaching is how how well is that actually really working as far as a way to do education as a way to to inspire people? I mean all the data that I'm aware of seems to indicate and this kind of fits I think with Charles's story is that people respond to connection, right? They actually feel if they're if they feel connected to the person teaching the class, they're more likely to go along with it, they're more they're more able to retain information, they're more motivated to be involved in the class in some way and and that really matters people, You mean to the human themselves. So can't you do that actually perhaps more effectively? Yeah. Online, like you mentioned science communication. So I I literally, I think learned linear algebra from Gilbert strang by watching M. I. T. Open courseware when I was a drug like and he was a personality was a bit like a, you know, tiny in this tiny little world of math, there's a bit of a rock star. Right? So you kind of look up to that uh to that person, can't that replace the in person education, [/INST] it can help, I will point out something, I can't share the numbers, but the we have surveyed our students and even though they have feelings about what I would interpret its connection, I like that word, um, in the different modes of classrooms, there's no difference between how they, how well they think they're learning for them. The thing that makes them unhappy is the situation they're in. And I think the last lack of connection, it's not whether they're learning anything, they seem to think they're learning something anyway. Right? In fact, they seem to think they're learning it equally well uh presumably because the faculty are putting in or the instructors more generally speaking, are putting in uh the energy and effort to try to make certain that there What they curated can be expressed to them in a useful way, but the connection is missing. And so there's huge differences in what they prefer and as far as I can tell, what they prefer is more connection, not less. That connection just doesn't have to be physically in a classroom. I mean, look, I used to teach 348 students on the machine learning class on campus. You know why that was the biggest classroom on campus. They're sitting in the theaters, they're sitting in theater seats. I'm literally on a stage, looking down on them and talking to them, right? There's no, I mean we're not sitting down having a one on one conversation, reading each other's body language, trying to communicate and going up. We're not doing any of that. So, you know, if you're, if you're past the third row, it might as well be online anyway. Is the kind of thing that people said, Daphne has actually said some version of this um that online starts on the third row or something like that. And I think that's, that's not yeah, I like it. I think it captures something important, but people still came by the way, even the people who had access to our material would still come to class. I mean </s><s>[INST] there's a certain element about looking to the person next to you, it's just like their presence, their, their, their boredom and like when the parts are boring and their excitement, when the parts are exciting, like and sharing in that like unspoken kind of uh yeah, communication, like in part the connection is with the other people in the [/INST] room watching, watching the circus on tv alone is not ever been to a movie theater and been the only one there at a comedy. It's not as funny as when you're in a room full of people all laughing. </s><s>[INST] Well you need, maybe you need just another person. It's like as opposed to many, maybe, maybe there's some kind [/INST] of, well, there's different kinds of connection, right? </s><s>[INST] And there's different kinds of comedy. Well, in the sense that we're learning today, I wasn't sure if that was going to land, but just the idea that different jokes, I've now done a little bit of stand up and so different jokes work in different sized crowds to where sometimes if, you know, if it's a big enough crowd, then even a really subtle joke can take root someplace. And then that cues other people and it kind of, there's a whole statistics of, [/INST] I did this terrible thing to my brother. So when I was really young I decided that my brother was only laughing at, that comes when I left, He was taking cues from me. So I like purposely didn't laugh just to see if I was </s><s>[INST] funny things. You really want to do both sides. I [/INST] did both sides. And uh, and at the end of it, I told him what I did, he was very upset about this and from that day on he </s><s>[INST] lost his sense of humor. [/INST] No, no, no, no. Well, yes. But from that day on he, he left on his own. He stopped taking cues for me. So I want to say that, you know, it was a good thing that I did, </s><s>[INST] but it was mostly means [/INST] yes, but it was mostly me. But it's true though. It's true, right? That the people, I think you're right. </s><s>[INST] But okay. So that's where does that get us? That gets us the idea that, I mean, certainly movie theaters are a thing, right? Where people like to be watching together, even though the people on the screen can aren't really co present with the people in the audience. The audience is present with themselves by the way. At that point, it's an open question is being raised by this. Whether movies will no longer be a thing because netflix is audience is growing. So that's, it's a, it's a very parallel question for education. Will movie theaters still be a thing right? In 2000 and I think, I think the argument is that there is a feeling of being in the crowd that isn't replicated by being at home watching it and that there's value in that. And then I think just, but it scales better online. [/INST] I feel like we're having a conversation about whether concerts will still exist after the invention of the record or the cd or wherever it is. Right? You're right, concerts are dead. Um, well, </s><s>[INST] okay. Before I think the joke is only funny if you say it before [/INST] now, </s><s>[INST] right? Yeah, three years ago. It's like, well no, obviously always to publish this until we have a [/INST] vaccine now, you know, we'll fix it in post. But I think the, the important thing is the virus, concerts changed </s><s>[INST] right? [/INST] First of all, movie theaters weren't this way right? In like the sixties and seventies, they weren't like this. Like blockbusters were basically what with jaws and star wars created blockbusters right? Before then there weren't like the whole summer shared summer experience didn't exist In our lifetimes. Right? Certainly you are well into adulthood by the time this country. So it's just a very different. It's very different. So what, what we're, we've been experienced in the last 10 years. It's not like the majority of human history, but more importantly concerts, right? Concerts means something. Most people don't go to concerts anymore. Like there's an age where you care about it, you sort of stop doing what you keep listening to music or whatever and not at all. So I think that's a painful way of saying that. Um, it will change. It's not the same thing as a going away replaces too strong of a word, but it will change. It </s><s>[INST] has to actually like to push back. I wonder because I think you're probably just throwing that your intuition out I want. Uh and it's possible concerts more people go to concerts now. But obviously much more people listening to this dumb when they then before there was records, uh, it's it's possible to argue that uh if you look at the data uh that it just expanded the pie of what music listening means. It's possible that like universities grow in the, in the parallel or the theaters grow. But also more people get to watch movies, more people get uh like be educated. So I hope that you, and to the extent that we can grow the pie and have education being not just something you do for four years when you're done with your other education. Um, but it would be a more lifelong thing that would have tremendous benefits, especially as the economy in the world changed rapidly. People need opportunities to stay abreast of these changes. And so I don't know, I could, I could, it's all part of the ecosystem. [/INST] It's all to the good. I mean, you know, I'm not gonna have an argument about whether we lost fidelity, we went from laser, just the DVds or record players to cds. I mean I'm willing to grant that that is true. But convenience matters And the ability to do something that you couldn't do otherwise because of the convenience matters. And you can tell me I'm only getting 90% of the experience, but I'm getting the experience, I wasn't getting it before or wasn't lasting as long or it wasn't as, I mean this just seems this just seems straightforward to me. It's gonna, it's going to change. It is for the good that more people get access and it is our job to do two separate things, One to educate them and make access available, that's our mission, but also for very simple selfish reasons, we need to figure out how to do it better so that we individually stay in business, we can do both of those things at the same time. They are not in um they maybe intention but they are not mutually exclusive. </s><s>[INST] So you've educated some scary number of people. So you've seen a lot of people succeed, find their path through life. Is there a device that you can give to a young person today about computer science, education about education in general, about life, about uh whatever the journey That one takes in there maybe in their teens in their early 20's sort of in those underground years as you try to go through the essential process of partying and not going to classes and yet somehow trying to get a degree [/INST] if you get to the point where you're far enough up in the, in the hierarchy of needs that you can actually make decisions like this, then find the thing that you're passionate about and pursue it and sometimes it's the thing that drives your life and sometimes it's secondary and you'll do other things because you've got to eat right, you got a family, you gotta feed, you've got people, you have to help or whatever and I understand that and it's not easy for everyone, but um always take a moment or two to pursue the things that you love, the things that bring passion and happiness to your life, and if you don't, I know that sounds corny, but I genuinely believe it, and if you don't have such a thing then you're lying to yourself, you have such a thing, you just have to find it and it's okay if it takes you a long time to get there. Rodney Dangerfield became a comedian in his fifties, I think it certainly was in his twenties, and lots of people failed for a very long time before getting to where they were going. Um you know, I try to have hope and it wasn't obvious. I mean, you know, you and I talked about the experience that I had a long time ago with with a particular police officer wasn't my first one, wasn't my last one, um but you know, in my view, I wasn't supposed to be here after that and I'm here. So it's all gravy, so you might as well go ahead and grab life as you can because of that. That's that's sort of how I see it, while recognizing, again, the delusion matters, right, allow yourself to be deluded, allow yourself to believe that it's all gonna work out just don't be so deluded that you you missed the obvious, uh and you're going to be fun, it's going to be there, it's going to be, they're gonna work out </s><s>[INST] what do you think? I like to say choose your parents wisely because that has a big impact on your life. Yeah, I mean, you know, I mean there's a whole lot of things that you don't get to pick um and and and whether you get to have, you know, one kind of life for a different kind of life can depend a lot on things out of your control. But I really do believe in the passion, excitement thing. My I was talking to my mom on the phone the other day and essentially what came out is that computer science is really popular right now and and I get to be a professor teaching something that's very attractive to people and she, she was like trying to give me some appreciation for how Foresight fel I was for choosing this line of work as if somehow I knew that this is what was gonna happen in 2020, but that's not how it went for me at all. Like I I studied computer science because I was just interested, it was just so interesting to me. I didn't, I didn't think it would be particularly lucrative and I've done everything I can to keep to keep it as unlu accretive as possible. Um some of my, you know, some of my friends and colleagues have have not done that and I pride myself on my ability to just remain unknown rich, but but but but but I do believe that like I'm glad, I mean, I'm glad that it worked out for me. It could have been like, oh, I, what I was really fascinated by is this particular kind of engraving that nobody cares about. But so I got lucky and the thing that I cared about happen to be a thing that other people eventually cared about. But I don't think I would have had a fun time choosing anything else like this was the thing that kept me interested and engaged. Well, one thing that people tell me, especially around the early undergraduate and the internet is part of the problem here is they say there's passionate about so many things. How do I choose a thing which is a harder thing for me to know what to do with Is there any [/INST] I mean, don't you know what I mean? You know, a long time ago I walked down the hallway and I took a left turn. Yeah. I could have taken a right turn and my world could be better or it could be worse. I have no idea. I have no way of </s><s>[INST] knowing. Is there anything about this particular hallway that's relevant or you just in general [/INST] choices? You were on the </s><s>[INST] left. It sounds like you regret not taking the right. Oh, no, not at all. You brought it up. [/INST] Well, because it was a term on the left was Michael Dimon's office. Right? I mean these sorts of things happen. Right? But </s><s>[INST] here's the thing, By the way, it was just a blank wall. It wasn't, it would [/INST] have really hurt. He tried first. But it's true, right? That, you know, I, I think about Ron brockman, right? I I went, I took a trip I wasn't supposed to take and I ended up talking to to, to, uh, wrong about this. And I ended up going down this entire path that allowed me, I think get tenure. But by the way, I decided to say yes to something that didn't make any sense. And I went down this educational, but it would have been, you know, who knows? Right? Maybe if I hadn't done that, I would be a billionaire right now, I'd be Elon musk. My life could be so much better. My life could also be so much worse. You know, you just got to feel that sometimes you have decisions you're going to make, you cannot know what's gonna you should think about it, right. Some things are clearly smarter than other things. You've got to play the odds a little bit. But in the end, if you've got multiple choices, there's lots of things you think you might love go with, the thing that you actually love, The thing that jumps out at you and sort of pursue it for a little while. The worst thing that will happen is you took a left turn instead of the right term and you ended up merely happy. </s><s>[INST] So so accepting, so taking a step and just accepting, accepting that that don't like questions questioning life is long and there's time to actually pursue. Every once in a while you have to put on a leather suit and make a thriller video [/INST] every once in </s><s>[INST] a while. Everyone. Yeah, I was told that you actually danced, but that part was edited out. [/INST] I don't dance. There was a thing where we did do the zombie thing, We did do the zombie that wasn't edited out. It just wasn't put into the final thing. I'm quite happy, but there was a reason for that too, right? Like I wasn't wearing something right. There was a reason for that. I can't remember what it was. Is that what it was? I can't remember. Anyway, the right thing happened </s><s>[INST] exactly. Took the left turn and end up being the right thing. So a lot of people ask me that are a little bit tangential to the programming, the computing world. And they're interested to learn programming, like all kinds of disciplines that are outside of the particular discipline of computer science. What advice do you have for people that want to learn how to program or want to either taste this little skill set or discipline or try to see if it can be used somehow in their own life. [/INST] What stage of life? </s><s>[INST] Uh It's one of the magic things about the internet, of the people that write me is, I don't know [/INST] because my answer is different for, for my daughter is taking ap computer science right now. Hi johnny. Um she's uh she's amazing and doing amazing things and my son is beginning to get interested and I'll be really curious where he takes it. I think he's, his mind actually works very well for this sort of thing and she's doing great. But one of the things I have to tell her all the time, she points well, I want to make a rhythm game. So I want to go for two weeks and then build a rhythm game. Show me how to build a rhythm game and it starts small, learned the building blocks and how to take the time to have patients. Eventually you'll build a rhythm game. I was in grad school when I suddenly woke up one day over the Royal East. Um and I thought, wait a minute. I'm a computer scientist. I should be able to write pacman in an afternoon and I did not with great graphics. It was actually very cool game, I had to figure out how the ghost moved and everything. And I did it in an afternoon in pascal on an old apple two Gs. Um but if I had started out trying to build pac man, I think it probably would have ended very poorly for me, luckily back then there weren't, you know, these magical devices, we call phones and software everywhere to give me this illusion that I could create something by myself from the basics inside of a weekend like that. I mean that was combination of years and years and years. Right before I decided I should be able to write this and I could. So my advice if you're early on is you know, you've got the internet, there are lots of people there to give you the information, Find someone who cares about this. Remember they've been doing it for a very long time. Take it slow, learned the little pieces, get excited about it and then keep the big project you want to build in mind. You'll get there soon enough because as a wise man once said, life is long. Sometimes it doesn't seem that long but it is long and you have enough time to build it all out. All the information is out there. But start small, you know, generating fibonacci numbers. That's not exciting. But it'll be a programming language. Well there's only one programming languages lisp but if you have to pick a programming language, I guess in today's what would I do? I guess I do </s><s>[INST] python is basically list but with better syntax blasphemy C with c syntax. How about that? [/INST] So you're gonna argue that c syntax is better than anything. Anyway. Also I'll go I'm gonna answer despite what tell </s><s>[INST] me, tell your story about the somebody's dissertation that had a list program in [/INST] it. So funny. This is uh this is Dave dave Dave Mcallister who is a professor at M. I. T. For a while and then he came in our labs and now he's now he's a technology technical to Chicago uh brilliant. Go uh such an interesting anyway his thesis uh it was a theory improver and he decided to have as an appendix His actual code which of course was already in list because of course it was like the last 20 pages are just right parenthesis. It's just wonderful. Like they that's programming right there pages upon pages of right parenthesis. Anyway, Elizabeth the only real language, but I understand that that's not necessarily a place where you start, python is just fine, python is good if you're of a certain age, if you're really young and trying to figure it out, graphical languages that let you kind of see how the thing works and that's fine too. They're all fine. It almost doesn't matter. But there are people who spend a lot of time thinking about how to build languages that get people in the questions, are you trying to get in and figure out what it is or do you already know what you want? And that's why I asked you what stage of life people because if you're different stages of life, you you would you would attack it differently. </s><s>[INST] The answer to that question of which language keeps changing. I mean there's some value to exploring uh, a lot of people write to me about Julia. There's there's there's like more modern languages that keep being invented, Rust and, and Katelyn, and there's stuff that for people who love functional languages, like lisp that there apparently there's echoes of that, but much better in the modern languages and it's worthwhile to uh, especially when you're learning languages, it feels like it's okay to try one. That's not like the popular one. But, you know, I think you get that you get that way of thinking almost no matter what language. And if you, if you push far enough, like it can be assembly language, but you need to push pretty far before you start to hit the really deep concepts that you would get sooner in other languages. But like, I don't know, computation is kind of computation is kind of touring equivalent is kind of computation. And so it's so it matters how you express things, but you have to build out that mental structure in your mind. And I don't, I don't think it's super matters which language, [/INST] I mean, it matters a little because some things are just at the wrong level of abstraction. I think assemblies at the wrong level, abstract for someone coming in new. Um, I think that someone </s><s>[INST] coming in [/INST] new for frameworks big frameworks are are quite a bit um, you know, you got to get to the point where I want to learn any language means I just pick up a reference book and I think of a project and I go through it in a weekend. You gotta you gotta get there. You're right though. The languages that are designed for that are it almost doesn't matter, pick the ones that people have built tutorials and infrastructure around to help you get kind of kind of eased into it because it's hard. I mean I did this little experiment with um I was teaching intro to see us in the summer as a favor. Ah yeah, which is anyway, I was teaching, I was teaching, introduced this as a favor. It was very funny because I go in every single time and I would think to myself, how am I possibly going to fill up an hour and a half talking about for loops, Right. And there wasn't enough time. It took me a while to realize this. Right? There are only three things right? There is reading from a variable, writing to a variable and conditional branching everything else is syntactic sugar, right? This syntactic sugar matters, but that's it. And when I say that's it, I don't mean it's simple. I mean it's hard, like conditional branching loops variable. Those are really hard concept. So you shouldn't be discouraged by this. Here's a simple experiment and I'm going to ask you a question now you're ready to go, X equals three. Okay, Y equals for what is X 3? What is why for why this stuff? It's easy, why equals X. Y equals X. What is why 3? That's right. X equals seven. What is why? </s><s>[INST] That's one of the trickiest things to get for programmers that there's a memory and the variables are pointing to a particular thing of memory and sometimes the languages hide that from you and they bring it closer to the way you think [/INST] mathematics works. Right? So in fact, Mark does style, who worries about these sorts of things? Are used to worry about these sorts of things. Anyway, had this kind of belief that actually people when they see these statements actually was something like something like was X. That you have now made a mathematical statement that Y and X are the sand, </s><s>[INST] which you can if you just put like an anchor in front of it. [/INST] Yes. But people that's not what you're doing, right? </s><s>[INST] I thought, [/INST] and I kind of asked the question and I think had some evidence for this. I'm hardly study is that most of the people who didn't know the answer, we weren't sure about the answer. They had used spreadsheets. </s><s>[INST] Uh [/INST] So it's a it's a it's you know, um it's by it's by reference or by name really, right? And so depending upon what you think they are, you can completely different answers. The fact that I could go, one could go two thirds of the way through a semester and people still hadn't figured out in their heads when you say Y equals X. What that meant tells you it's actually hard because all those answers are possible. In fact when you said, oh if you just put an ampersand in front of it, I mean that doesn't make any sense for an intro class. And of course a lot of language don't even give you the ability to think about it. In terms of ampersand, do we want to have a 45 minute discussion about the difference between equal E. Q. And equal in lisp? I know you do, but you know you could do that. This is actually really hard stuff. So you shouldn't be, it's not too hard. We all do it, but you shouldn't be discouraged. That's why you should start small so that you can figure out these things. You have the right model in your head, so that when you write the language you can execute it and build a machine that you want to build, right? Yeah. </s><s>[INST] The funny thing about programming on those very basic things is the very basics are not often made explicit, which is actually what drives everybody away from basically any discipline. But program is just another one. Like even a simpler version of the equal sign that I kind of forget is in mathematics equals is not [/INST] assignment. </s><s>[INST] Like I think basically every single programming language with just a few handful of exceptions equals is assignment. You have some [/INST] other operator </s><s>[INST] for equality. And you know even that like everyone kind of knows it once you started doing it but like you need to say that explicitly or you just realize it like yourself, otherwise you might be stuck for you said like half a semester you could be stuck for quite a long time. And I think also part of the programming is being okay in that state of confusion for a while. It's it's to the debugging point. It's like I just wrote two lines of code, why doesn't this work and staring at that for like hours trying to figure out and then every once in a while you just have to restart your computer and everything works again. And then and then you just kind of stared into the void with the tear slowly rolling down [/INST] your eye. By the way, the fact that they didn't get this actually had no impact on. I mean they were still able to do their assignments because it turns out their misunderstanding wasn't being revealed to them by the problems that we were. It's being found actually. Yeah I wrote a a program a long time ago actually for my Master's thesis and in C. Plus plus I think or see I guess we'll see and it was all memory management terrible. Um And it wouldn't work for a while and it was some kind of it was clear to me that it was overriding memory and I just couldn't, I was like, look, I got a paper due time for this. So I basically declared a variable At the front and the main, that was like 400 k. Just an array. It worked because wherever I was scribbling over memory, it would scribble into that space and it did matter. And so I never figured out what the bug was, but I did create something to sort of deal with it around it and you know, that's crazy. That's crazy. It was okay because that's what I wanted. But I knew enough about memory, managed to go, you know, management to go, you know, I'm just going to create an empty array here and hope that that deals with the scribbling memory problem? Uh, and it did, that takes a long time to figure out. And by the way, the language you first learned probably this garbage collection anyway, so you're not even gonna come up across, you're gonna come across the problem. </s><s>[INST] Mm. So we talked about the Minsky idea of hating everything you do and hating yourself. Uh, so let's end on a question that's going to make both of you very uncomfortable, which is what is your Charles, what's your favorite thing that you're grateful for about Michael and Michael, what is your favorite thing that you're grateful for about Charles. [/INST] Well, that answer is actually quite easy. His friendship. </s><s>[INST] He's still the easy and yeah, I can tell you what I hate about Charles. My good answers. The thing I like most about Charles, he sees the world in a similar enough but different way that it's sort of like having another life. It's sort of like I get to experience things that I wouldn't otherwise get to experience because I would not naturally gravitate to them that way. And so he just just shows me a whole other world. It's [/INST] awesome. Yeah, the the inner product is Not zero for sure. It's not quite one 0.7, maybe just enough that you can learn </s><s>[INST] just enough that you can learn. That's the definition of friendship. The inner product is point [/INST] seven yeah, I think so. That's the answer to life. Really, </s><s>[INST] Charles sometimes believes in me when I have not believed in me. He can, he also sometimes works as an outboard confidence that he has so much, so much confidence and self, I don't know where comfortable nous okay, let's go with that. Um that I feel better a little bit. If he, if he thinks I'm okay then maybe I'm not as bad as I think I am at the end of the day, Luck favors the Charles. It's a huge honor to talk with you, thank you so much for taking this time, wasting your time with me. It was an awesome conversation, you guys inspiration too. A huge number of people and to me, so I really enjoy [/INST] this, enjoy it as well. Thank you so much. And by the way, if luck favors the charleston is certainly the case that I've been very lucky to know you. </s><s>[INST] I'm going to add that part out. Thanks for listening to this conversation with Charles is bow and Michael Littman and thank you to our sponsors. I fly to greens, super nutritional drink eight sleep, self cooling mattress master class online courses from some of the most amazing humans in history and cash app. The app I used to send money to friends. Please check out the sponsors in the description to get a discount and to support this podcast. If you enjoy this thing, subscribe on youtube, review it with five stars on apple podcast following Spotify, support on Patreon, connect with me on twitter, elects Friedman and now let me leave you Some words from Desmond tutu. Don't raise your voice, improve your argument. Thank you for listening and hope to see you next time. [/INST] </s>