Datasets:

64bits

/

lex_fridman_podcast_for_llm_vicuna

like 14

[ { "from": "human", "value": "And you're looking at the very early days of the introduction of the variety." }, { "from": "gpt", "value": "Yes, exactly. When it was still a little bit more organizeable. But the variety of different types of metal pore stars we have is stark. Many different types of stars, many patterns we have sort of identified, but they are still crazy ones out there that we're still trying to kind of fit in." }, { "from": "human", "value": "So what kind of stars have been discovered? So you've, already a while ago, helped discover the star HE 1327-2326. Great name. Yes. And HE 1523-0901. What can you say about these stars and others that have been found?" }, { "from": "gpt", "value": "Yes. I love them. They're my baby stars." }, { "from": "human", "value": "What do you call your baby stars?" }, { "from": "gpt", "value": "Well, I'm probably the only one. Well, I'm probably the only one who can spit out these names without cheating. Are there nicknames? That's not allowed. Well, some colleagues at conferences have just called them Anna Star or Freeble Star because they didn't want to learn the phone number. You know, I get it." }, { "from": "human", "value": "The phone number. Are there nicknames? No, that's not allowed. The phone number." }, { "from": "gpt", "value": "These numbers are actually based on older sets of coordinates for these stars. So yes, the minus in the middle means that they're in the southern hemisphere. So negative is in the southern hemisphere. Positive is in the northern. And then 13 and 15 means they're sort of observable in the middle of the year." }, { "from": "human", "value": "Okay, so it's to do with the observation and where it was observed." }, { "from": "gpt", "value": "Yes, yes, yes, yes. But they have very different stars, both absolutely significant career defining actually for me, but really push the envelope in very different ways. So AG 1327, the first one that you mentioned, that was the second, second generation star that we found. And you know, usually people say like, oh, the first one is a big one and the rest is nobody cares. But to us, it proved that yes, we can do it. Because one, astronomers live in a sort of way of, you know, there are a lot of serendipitous discoveries and we, that's really great. But we need to show that we can do it again. Because then we're onto something and it's not just some kind of weird quirk. And there are a lot of quirks in the universe, but we want to know, is that a real thing? Does that happen regularly? Is there something that we can learn? When is that a piece of the story? And so finding the second one that was even a little bit more extreme than the first one really showed, yes, our search techniques work. We can find these stars. They provide an important part to the story in the sense that if we had more than two stars, and by now we have about 10-ish or so, what do they tell us about the nature of the very first stars? And what we found, again, working with the theorists, of course, who run these supernova models, is that, so actually, let me, let me, before I get into this, these two stars had huge amounts of carbon relative to iron. So we usually use iron as a reference element for what we call the metallicity. So the overall metal content, the overall amount of heavy elements in it." }, { "from": "human", "value": "So that's why it's called iron deficient." }, { "from": "gpt", "value": "That's right. So these stars are incredibly iron deficient, which means they must be of the second generation because there was, and interestingly enough, there was this discrepancy. A normal supernovae, until then, we thought would get us so much iron, you would distribute that in the gas cloud, and then you would form this little star that we're observing. But the iron abundance that we measured was actually much lower than that. And I already mentioned, you can't take things away. That must mean these early massive pop three, we call them population three, the first stars, they must have exploded in a different way than we previously thought. They can't output as much iron because they just can't. Otherwise, it wouldn't match our observations. Got it. And so that's when we started to work" }, { "from": "human", "value": "with several theory groups, otherwise it wouldn't..." }, { "from": "gpt", "value": "Got it. ...on supernova yields. So what comes out of... From the explosion of the supernova." }, { "from": "human", "value": "From the explosion of the supernova. That's cool. Supernova yields. And so this one was not yielding much iron." }, { "from": "gpt", "value": "Well, we needed to concoct a theoretical supernova that made less. And it's actually surprisingly difficult, because you can always add more in the universe, but you can't take stuff away. So Japanese colleagues kind of came up with the idea of a fainter supernova that just doesn't have enough oomph when it explodes. So somehow, there's less iron coming out. But at the same time, then these stars showed huge overabundances of carbon, a thousand times more carbon. So how do you now get a thousand times more carbon out of these poor first supernovae, right? That was the theoretical challenge. And because we didn't have just one star, but two, that really spurred the field to think about what was the nature of the first stars? How did they explode? What are the implications? Because if they are not as luminous and bright and energetic, that has consequences for these early proto-galaxies in which they must have been located in terms of blowing the gas out, let's say, and disrupting the system. So much higher chance for the earlier system to stay intact for longer, right? So there's a whole tale of consequences. And this is what I mean with we need to find the story because you do one thing and it's like the dominoes, there are consequences everywhere. And suddenly you have a different universe, right?" }, { "from": "human", "value": "Mm-hmm. What could possibly be a good explanation for something that yields a lot of carbon and doesn't yield a lot of iron?" }, { "from": "gpt", "value": "Well, it's not so much an explanation, more like finding a mechanism for what happens in supernovae and the official term, what was sort of, as I said, cooked up in order to explain the observations. And we have, by the way, found a whole bunch more of these stuffs, so that holds. And it's called a fallback mechanism. So actually during the supernova explosion, a massive black hole emerges. And so some of the material falls back onto the black hole. Oh, boy. Here is a vacuum cleaner now plopped into the middle, right?" } ]

[ { "from": "human", "value": "Like a temporary one that just cleans up some of the elements." }, { "from": "gpt", "value": "Well, sort of, right? Because if you think of the, we haven't talked about this yet, but if you know what a star looks like, a massive star looks like in its interior before it explodes, you have hydrogen and helium still on the outskirts, and then you have your layers of heavy and heavy elements all the way up to iron. So you have an iron core in the center. And because you can't get any energy out of iron when you want to fuse to iron atoms anymore, right? That's when the supernova explodes, or occurs, really. It's actually an implosion first, and then you have a bounce of the sort of neutron star phase that occurs in the process. And then, you know, the star just gets disrupted. Yeah. It's like this giant, you know, basketball. And then, whoa, it all goes up. An implosion first, an explosion after. Yeah. And so in the process, right, if you make your black hole basically big enough, it will suck away some of the iron, because that's the closest in terms of the layers. You hold on to it. You don't let it escape. And carbon is much further out. You let it all go. Nice." }, { "from": "human", "value": "And so that is so awesome. It all goes up. An implosion first, an explosion after. And so that explains why you can have a big oomf and not much iron yield. Yes, yes. So is this explained the HE 1327? Correct." }, { "from": "gpt", "value": "And others like it. Yes, yes, correct, yes. So there's a well-established now that the lower the iron abundance of the stars are, the higher the carbon sort of gets." }, { "from": "human", "value": "And carbon is such an interesting element in that regard." }, { "from": "gpt", "value": "If we come back to the formation of the first low mass stars, right, so we had the hotter gas, just hydrogen and helium that made the first stars. There were 100 solar masses or so because the gas couldn't cool enough. So they were big and puffy. Carbon then, coming from the first stars, probably led to enough cooling in these gas clouds" }, { "from": "human", "value": "that enabled the formation of the first low mass stars." }, { "from": "gpt", "value": "So think about what happened if there wouldn't have been any carbon or the properties of the carbon atom would be different. It would not have cooled the gas in such significant ways perhaps. There wouldn't be any low mass stars. We wouldn't be here today, right? And we're carbon-based. And so I think carbon is really the most important element in the universe for a variety of reasons because it just enabled this whole evolution that we're now observing and literally seeing in the sky. And it's really fascinating." }, { "from": "human", "value": "So combined with the fact that you have the iron deficient, so all of that is probably important to creating humans." }, { "from": "gpt", "value": "Yeah, yeah, we need all the elements. But if you don't have stars, you know, like the sun, small stars that can actually host planets, that have long lifetimes, you need long, long lifetimes if you want to have a stable planet and develop humans." }, { "from": "human", "value": "So carbon is kind of important in many ways." }, { "from": "gpt", "value": "Yeah, yes, yes." }, { "from": "human", "value": "This is perhaps an interesting tangent. If I could just mention that you interviewed military Dresselhaus, carbon queen, the remarkable life of the nanoscience pioneer. Is there something you could say about the magic of carbon and the magic of Milly?" }, { "from": "gpt", "value": "Well, Milly was certainly magic. She was a professor at MIT for many decades. I met her a number of times. Her photograph, actually a young and an older, Milly is still on the wall every time I step out of the elevator in one of the buildings, I see it. She pioneered all sorts of carbon nanowork. So she was a material scientist, very far removed from what I do on a daily basis. But yes, carbon has amazing properties when you study it. And again, that's indeed another aspect of why carbon is so fascinating, not just in the cosmos, but also for us, making us, creating us in the way that we can use it. It's wonderful." }, { "from": "human", "value": "Just sometimes think about this chemical evolution in this big philosophical way that we're the results of that chemical evolution. We're made of this stuff. We're made of carbon." }, { "from": "gpt", "value": "Yes, we're made of store stuff. Yeah, and it came- Class taking him right." }, { "from": "human", "value": "Yeah, and it came- Class taking him right. I mean, it's almost like a cliche statement, but it's also a materials, a chemical, a physics statement, that we came from hydrogen and helium. And that's somehow this formation has created this interesting complexity of soup that made us. What are we supposed to make of that? Like what? Did we just get really lucky? Why did we get all this cool stuff?" }, { "from": "gpt", "value": "Yeah, that's a good question." }, { "from": "human", "value": "I don't think it's a question that has an answer. I keep just asking why. But it's just this incredible mystery. So much cool stuff had to happen. So much, sorry, hot stuff had to happen to create us." }, { "from": "gpt", "value": "And so much could have gone wrong, and there would have been another outcome. And it's actually amazing how many things kind of fell in place. I mean, maybe that's all sort of soft deterministic in some ways, right? We are who we are because that was the path. Maybe we would have ended up being robots. I don't know. But it's certainly wonderful to, you know, a scientist for us to help contribute unraveling our cosmic history, right? I always say the biological evolution on Earth was absolutely facilitated by the chemical evolution of the universe, right? And one doesn't go without the other. And that evolution- From a human perspective." } ]

[ { "from": "human", "value": "From a human perspective. That evolution seems to be creating more and more complexity. The kind of interesting clumping of cool stuff seems to be accelerating and increasing. It's hard not to see as humans that there's some kind of purpose to it. Like a momentum towards complexity and beauty." }, { "from": "gpt", "value": "Well, beauty's in the eye of the beholder. But yes, everything gets more complicated." }, { "from": "human", "value": "But there's also a beauty to the chemically pristine universe in the early days. Yes, yes." }, { "from": "gpt", "value": "In the early days. Certainly, yes, yes. I love the desert with its nothingness. It has so much aesthetics and appeal." }, { "from": "human", "value": "Yeah. If we came from nothing, we'll return to nothing. So what about HE 1523? What's exciting? A red giant star. Yeah." }, { "from": "gpt", "value": "That's another one of your babies. Yes." }, { "from": "human", "value": "13.2 billion years old." }, { "from": "gpt", "value": "Yeah, so that one isn't quite as iron deficient as the other one. So probably not a second generation star, but easily third, fourth, fifths or so. We can't really pin it down, but it's also not super important for us. What is important is that that star has a very different chemical composition in the sense that yes, we have all the elements up to iron there. They have sort of normal ratios, which means kind of the same as most other old stars and not too different from the sun or at least different in quantifiable ways. But it has this huge overload of very heavy elements. And what was so nice about that star in particular was that I could measure the thorium and the uranium abundance. And again, that was the second of its kind, but the uranium abundance could be more well determined. So we had a better grasp on that. Now, why are thorium and uranium interesting? They are radioactive elements. They decay. Thorium has a half-life of 14 billion years, I believe, and uranium of 4.7, which, you know, to folks on Earth is a really long time, but those kind of timelines are really good when you want to explore the early universe. So there are two questions now that kind of come to mind. Where do these elements come from? And what do they tell us, right? And these, as we know, these heavy elements are made in a specific process. It's a neutron capture process, usually referred to as the R process for rapid neutron capture process. We talked about seed nuclei before, right? So we still don't exactly know where this process can occur. So you have, let's say, a lone iron atom somewhere, and it is in an environment where you have a strong neutron flux, which means there must be lots of neutrons around. And again, when we talk about the site, we can surmise and ponder where that might be the case. But you have this iron atom, and you bombard it with neutrons, and you do it incredibly fast. Now, what happens in the process? That iron atom, you know, you collect lots of neutrons, it becomes really big and unstable. So it's a heavy neutron-rich nucleus that wants to decay because it's not stable. It's way too big. And so let's say you add only one neutron to it. That would already make it unstable, so it will then, it has a characteristic decay time that's called the beta decay time scale. So it will decay to a stable nucleus, so the neutron will convert to a proton, and that makes it stable. If you know a bombard, lots and lots and lots of neutrons onto that seed nucleus within the time scale of the beta decay, that's how you get to this huge fat neutron-rich nucleus that then wants to decay, right? So the rapid process is you have your seed nuclei, they get bombarded, you create these really heavy neutron-rich nuclei. They're heavier than uranium even. The neutron flux stops, and then all these heavy nuclei, they decay. And they make all these stable isotopes that we know of, all the way up to thorium and uranium." }, { "from": "human", "value": "So that rapid nuclei decay is what creates all the funnels." }, { "from": "gpt", "value": "Correct, yes, correct. And the whole thing is done within two seconds. So just to add to the rapid here, literally the snapping on my hand, it's all there. In my talks, I often, I have this nice simulation that illustrates this creation of these heavy nuclei, and I always say, this is the only simulation you will ever see that's slower than real time. Because in astronomy, we show, oh, this is how a galaxy forms, 13 billion years in 30 seconds. Really short, right? This is the opposite. Me showing you this, the elements are long-made." }, { "from": "human", "value": "So where and when does this happen?" }, { "from": "gpt", "value": "Does this process happen? So you need the strong neutron flux." }, { "from": "human", "value": "That's the pumping of the neutrons." }, { "from": "gpt", "value": "Yes, that's right. And so there are not that many options, right? So where do you find lots of neutrons in the universe? So it's neutron stars, right? Neutron stars form in the making of supernovae of the explosions. Okay, so maybe some of this heavy material gets sort of made in the making of the supernova explosion and then gets expelled. Or you have neutron stars. So if the neutrons star so far, usually that's the leftover of the supernova. If you have two from a binary pair, so stars usually actually show up in pairs. And so it's not too unusual to create a pair of neutron stars that will still orbit each other after both of their progenitor stars have exploded. And those two neutron stars will orbit each other diligently. But as we know now, thanks to LIGO, the gravitational wave observatory, I mean, we know already that before, but now it's been measured by LIGO is that these two neutron stars, they will orbit each other for like forever. But in the process, they will lose energy. So that orbit is what we call the orbit decays and eventually the two neutron stars will merge and that results in an explosive event that has roughly the energy of a supernova, but the process is completely different. And the cool thing is when these two neutron stars collide, they produce a gravitational wave signature because neutron stars are super dense objects. They're like giant atomic nucleuses. So there's a lot of interesting physics happening already. And so if you basically form a super neutron star by smashing two into each other, more interesting physics happens. And that means that there's this ripple sent out into the space, the space-time continuum, basically, what do people say, the ripples of space-time. It's like you drop a rock into water, you see the waves coming. So that's exactly what happens when two neutron stars merge and this is neutrons galore. It's really violent to smash two neutron stars that are so dense already into each other. And in 2017, one of these events occurred and the LIGO and Virgo gravitational wave observatories, they detected that. And then the astronomers pointed their telescopes in that direction and they indeed observed what we call the electromagnetic counterpart. So there was something seen in the sky that faded over the course of two weeks. And that light curve, that light, was exactly what you get when you create all these heavy neutron-rich nuclei in the r process and then the neutron flux stops. And then it takes about two or three weeks for most of them of these nuclei to decay to stability. So we saw, the astronomers saw in this electromagnetic counterpart, the nuclear synthesis of heavy elements occurring. And that's just awesome." } ]

[ { "from": "human", "value": "That's amazing. Awesome. So that's electromagnetic counterpart to the gravitational waves that were detected with two neutron stars colliding aggressively violently to create a super neutron star. And that's where you get all the neutrons and the neutron flux somehow. And then the whole shebang that happens in two seconds and creates a bunch of..." }, { "from": "gpt", "value": "So that confirmed that one of the sites for sure is for the r process to occur is neutron star mergers. Interestingly enough, I have to mention this here, a year prior in 2016, my former grad student, Alex G and I, we discovered a small dwarf galaxy that is currently orbiting the Milky Way, it's called reticulum two, that was full of ancient iron deficient stars that also had a strong signature of these heavy elements, exactly like HE 1523. We weren't looking for that. I actually wanted to prove that they had really low levels of heavy elements because that's what we had seen in all the other dwarf galaxies. And I was dead set on showing that that is yet the case again and that that is a typical signature of early star formation. We already talked about low strontium and barium abundances and the oldest stars, right? This is what we had seen anecdotally in the ancient dwarf galaxies that are surrounding us." }, { "from": "human", "value": "So that's an ancient dwarf galaxy." }, { "from": "gpt", "value": "That dwarf galaxy has a bunch of ancient stars in it. Yes, yes. And so now we find reticulum two and the stars show the signature of the rapid neutron capture process, the R process, and we are like, okay, these stars are located in a dwarf galaxy right now. We have environmental information. They are not lost in the galaxy where we don't know where they actually came from. No, we know these stars were formed in that galaxy because they're still in it. And we already deduced from that, that it must have been a neutron star merger that went off in reticulum two at early times that polluted the gas from which all our little stars form." }, { "from": "human", "value": "Can you speak to what a dwarf galaxy is? Can you speak to what this reticulum two dwarf galaxy is that is orbiting the Milky Way galaxy? Yeah. That's going to be eaten by it presumably?" }, { "from": "gpt", "value": "It totally is going to be eaten. Okay. I can't tell you exactly when. Yeah, the Milky Way remains surrounded by dozens of small dwarf galaxies. They're collections of stars. Some of them, we call them ultra-faint dwarf galaxies because they now only contain, I don't know, a few thousand stars. Very, very faint." }, { "from": "human", "value": "They're still detectable?" }, { "from": "gpt", "value": "Yes, because they're fairly close and we detect actual individual stars in them. So I've observed some of the faintest stars, you know, you possibly observe with current telescopes in these dwarf galaxies because I was like, I need to know what the chemical composition is because there are leftovers from the early universe, right? They did not get eaten. So they're still in their native surroundings. It's like getting the lions in the wild, right? I got to study those and compare to the counterparts that got eaten and are now in the Milky Way." }, { "from": "human", "value": "So presumably most of those stars, it's not all those stars in that dwarf galaxy are really ancient." }, { "from": "gpt", "value": "They're all really ancient because actually, as it turns out, if you have a small galaxy, there was a process early on in the universe called reionization that kind of heated up everything. And together with some supernova explosions in an early shallow, you know, bound system, all these little systems lost their gas. It was sort of blown out or it simply evaporated or both, probably both. And so these systems have been unable to continue to form stars since. So it's the best for our stellar archaeologists that you could hope for because it's a whole bunch of stars still sitting there. It's not just one, it's a whole bunch of them still sitting there ever since and literally nothing has happened to them. They've just been waiting there for us." }, { "from": "human", "value": "So from the stellar archaeology perspective, what is like juicier and more interesting? The old stars in the outskirts, they have been eaten of the outskirts of Milky Way or the stars in the dwarf galaxies. Of all the things you love about the world, you said you love stars. So which do you love more of your church?" }, { "from": "gpt", "value": "Of all the things you love about the world. That's a hard one. I mean, I love them all, of course. They serve different purposes. The stars in the Milky Way, I can get much, much, much better data for them because they're brighter. They're closer. So they're brighter. And that tickles my fancy." }, { "from": "human", "value": "And they have interesting kinematics, presumably." }, { "from": "gpt", "value": "Yes, yes. And we can get that. And so HD1523, for example, that one is really bright, only it's a red giant. So it's intrinsically bright and it's fairly close. And so the data I got for that was insanely good and that yielded this uranium detection and thorium detection. I can never get that kind of data for a dwarf galaxy star. So that's a big trade off. But the environmental information that we get along with the basic information of what these stars in each dwarf galaxy is really, really valuable in establishing for example, the site information. Because the galaxy is still there. So nothing crazy could have happened. So to close that loop, probably some heavy elements come out of supernovae here and there. But somehow my theory colleagues tell me that a normal supernova just doesn't have enough omph to really get an R process going and doing it all. So you need these orbiting supernovae. We need them probably the neutron star mergers or we need a special kind of supernova that's maybe extremely massive or heavily rotating or does something else funny, right? To really kind of get that particular process going. But the normal supernovae don't do it, right? So only a little bit comes out. But you could come along and say, Anna, why don't you just take 100 supernovae together to build up the yield, right? But then I come along and say like, look, the dwarf galaxy is still intact today. If you would have plugged in 100 supernovae into this little system early on, it would have blown apart. It would have blown apart past five supernovae or 10. So that's a really important constraint that we have that these systems are still alive, right? So it helps us to pin down where certain processes could have possibly happened." } ]

[ { "from": "human", "value": "And so it's just a different type of information that we get. It'd be amazing if we could talk about the observational aspect of this, the tools of observation. So what telescopes have you used? Do you use? And what does the data look like? And I think I've read a few interesting stories about the actual process of day-to-day observation. A bunch of probably late nights." }, { "from": "gpt", "value": "Well, yeah, astronomers are doing it all night long. So we have lots of late nights." }, { "from": "human", "value": "We have lots of late nights." }, { "from": "gpt", "value": "Can you explain the all night long aspect of this? Well, let me start by saying I mostly these days use the Magellan telescopes in Chile. They are a 6.5 meter telescope, which means the mirror diameter is 6.5 meter. That's not the largest that is out there, but it's among the largest. And I use a spectrograph because I'm a spectroscopist. I don't take pictures. And that particular spectrograph at that telescope is actually unusually efficient. So it kind of makes up for the fact that the mirror isn't as large in, let's say, the 8 meter telescopes from the Europeans or so. So I'm very happy with that. Efficiency, meaning? How many photons get collected sort of per time units? Because that's always the limiting factor. Prior to the pandemic, we would travel to Chile to do our observations. Those telescopes are the, that's the last observatory where people were sort of supposed to travel there and take their own observations. Most other observatories basically have staff there by now" }, { "from": "human", "value": "who take the observations for humans. So there's the directly, the scientists are specifying where to point the telescope and the certain area and collecting the data, making sure the data is collected well, the cleaning of the data, the offloading of the data, all that kind of stuff." }, { "from": "gpt", "value": "Yeah, so it's mostly done for them. Obviously, that's super convenient, but it also takes away a central part of what the work of an astronomer is, which is data collection. We don't have an experiment in the basement where we can go day and night or whenever we please and ask a certain question of the apparatus. Let's turn this knob and see what happens. Let's turn that knob and see what happens. We only have one experiment, which is the universe. What we see is what we get. I think it's so important to take an active role in that. So I really love going to the observatory. I've taken many students there over the years to teach them and to just show them what it means to be an astronomer. Because you go to these remote mountaintops and it's such a magical environment. You wait there for the sun to go down and then you get ready and you look outside. It's such a serene environment. It's a little bit out of this world." }, { "from": "human", "value": "You're sitting there, so the sun goes down. It's the evening, late evening. What does it look like? What are some of the most magical experiences of that process?" }, { "from": "gpt", "value": "Well, when you're on top of a mountain, climbers, I guess, get to see that probably otherwise. It's very calm and the colors are so beautiful. I always become much calmer when I'm there. I'm just A, because I'm just there for one purpose only. That's data collection. I can say no to my emails. I can say no to everything else because I'm observing. There's literally less distractions" }, { "from": "human", "value": "because you're just there to do one thing." }, { "from": "gpt", "value": "Also, the emails somehow seem less significant. Yeah, it's just you can't afford to focus on this one thing. It just kind of does something to you. It's a little hard to describe, but if you then fast forward, maybe I can speak a little bit about that. I have done a lot of astrophotography there as well. I'm observing faint dwarf galaxy stars. These are like 45 minutes, 55 minute exposures, so you actually have a lot of time. I would run outside and just lay on the ground under the southern Milky Way. Beautiful, right up there. I would just lay there like the snow angel and just stare up there and just kind of let my thoughts pass through my brain. I'm one of it. We talked about this in the beginning. This is when I personally have the feeling that I'm a part of it. I belong here rather than feeling kind of small. Yes, I'm small, but there are many other small things, and lots of small things make one big hole. And we're part of that big hole." }, { "from": "human", "value": "So that's looking at the stars and we're part of that big hole. And so that's looking at the inner spirals of the Milky Way galaxy." }, { "from": "gpt", "value": "And just this dark sky with the bright stars. I have described this in my book years ago. If the Milky Way is all bright above you, you don't need a moon or anything. You can walk in the starlight and you will find your way. There are no trees there for safety reasons, but you wouldn't even run into a tree, right? I mean, you can almost see the shadow from the starlight because it's such a dark sight and the stars are so bright. And these are kind of moments that kind of change you a little bit. You see the unity of it all. Yeah, and it's just you and nature and-" }, { "from": "human", "value": "You see the unity of it all." }, { "from": "gpt", "value": "You know, with modern civilization and all of that, I think we often try a little bit too hard to be removed from nature, you know, to be independent of it and figuring it all out. But at the end of the day, we're just a part of it. And that really helps me to remember that we're one and the same." } ]

[ { "from": "human", "value": "Well, that fills me with hope that I tend to think of us humans in the very early days of whatever the heck we are. So that makes me think thousands, tens of thousands, hundreds of thousands of years from now that we'll be reaching. Whatever we become, we'll be traveling out there to explore more and more and more. No." }, { "from": "gpt", "value": "So what you're doing is the early days of exploration with the tools we have. No, yes, the early seafarers looking at the sky for navigation." }, { "from": "human", "value": "Yeah, coming up with different theories of what's on the other side, that the earth is starting to gain an intuition that the earth may be around. And then we might be able to navigate all the way around to get to the financial benefits of getting spices from India, whatever the reason, whatever the grant funding process is all about. But ultimately actually results in a deep understanding of the mystery that's all around us. And I mean, just to travel out there. I mean, to me, the discovery of life in the solar system. I really hope to see that in my lifetime. Some kind of life, bacteria, something may be dead." }, { "from": "gpt", "value": "Because that means there's life everywhere." }, { "from": "human", "value": "And that's just the kind of stuff that might be out there. All the different environmental conditions, chemically speaking, that are out there. And it just seems like when you look at Earth, life finds a way to survive, to thrive in whatever conditions. And so maybe that process just kind of humbles you as it's super exciting to know that there is life out there of different forms. And of course, that raises the question of what is life even? We tend to have a very human-centric perspective of what is a living organism and what is intelligence and all this kinds of stuff. And all the work in artificial intelligence now is trying to challenge our ideas of what makes human beings special. I think we're doing that through all kinds of ways. And I think you're working some part doing that as well. Like the unity you feel is realizing we're part of this big mechanism of nature, whatever that is, that's creating all kinds of cool stuff. From the humble, pristine origins to today. So if you could just kind of linger on the process of the data, what does the data look like? And how does the raw data lead to a discovery of an ancient star?" }, { "from": "gpt", "value": "Well, as a spectroscopist, we have to, I guess, talk for a brief moment about what a spectrum is. Everyone, I hope, has seen a rainbow in the sky. That is basically what we're doing. We don't send the starlight through a raindrop that then gets bounced around and splits up the light into the rainbow colors. We do it with a spectrograph, so basically a prism. So we send the starlight through a prism of sorts, and that splits it up. And then we record exactly that. So it's a little 2D picture, actually, of a spectrum. Now, it's not going to look colorful, it's just black and white. Different colors have, of course, different energies. That's what we record. More specifically, we record it as wavelengths, so wavelengths and frequency and energies all the same at the end of the day. We process that little image in the sense that we do a crosscut and then sum up a few columns so that we get all the data that we recorded. And what we see is a, it's a bit funny to describe just with words, but a wiggly line with lots of dips. So the 2D process spectrum, we call it continuum, so it's just a flat line, basically, and then there are dips. So the interesting things are the dips. If you think back of the rainbow, what we actually see in our stars is not just a rainbow, but it would be a rainbow with lots of black lines in it, which means certain little pieces of color have been eaten away by a certain amount. And so we can no longer see it as well, or not at all. Why is that happening? So if we come back to our stars, what we're observing, we're observing the stellar surface. We can actually never peer with our telescopes inside. We only ever can go after the surface. And the surface contains, or the surface layer contains different kinds of elements. Every one of those types of atoms, so elements are just different types of atoms, they absorb different photons that are coming from the hot core where the fusion is occurring. And so that means that if you were the observer with a spectrograph or without, you will see the starlight, but certain frequencies, certain energies of that light will have been absorbed by all the different atoms in the gas. So you see less of them. And so those are the dips. And the strength of the dips tell us which element was it and how much of that element was or is in the star. So we have many, many, many dips. The solar spectrum, for reference, all the dips are overlapping because the abundance of all the elements is so high, it's actually a very complicated spectrum. My spectra really looked like a straight line, and then there's a dip here, and then the straight line again is dip there. The sun doesn't have straight lines. I mean, that's just all absorbed in some form or another. But the old stars have so little of all the elements. That there are only occasionally these dips that then indicate, okay, that one at that wavelength was iron, and here we have carbon, and there's magnesium and sodium, and oh, there's a little strontium line here. So we have a much easier way to map out this barcode that the spectrum pretty much is at the end of the day, and to then measure the strength of these, we call it absorption lines, to then calculate with existing codes that mimic the physics of the stellar atmospheres, like how much was absorbed, how many, what kind of elements were present in the stellar atmosphere. And so this is how we get to our abundance measurements, and then all together that gives us the chemical composition and that particular signature in that star." } ]

[ { "from": "human", "value": "Do you ever look at the raw spectrograph in the absorption line? And are you able to see into it some interesting non-standard outlier kind of patterns? Or does this have to do heavy amount of processing?" }, { "from": "gpt", "value": "We actually process our, it's fairly straightforward to do our processing. We do it at the telescope. So I often take a shorter exposure first, let's say 10 or 15 minutes. So mostly when I do discovery work, we would just take a quick look spectrum, then reprocess it while we observe the next star. Then we take a quick look. We have what I call the summary plot. It's a collection of little areas in the spectrum that have the key positions, the positions of the key elements in it. And it's kind of like reading the tea leaves. I have stared at so many spectra. I just need to see our summary plot and I can tell you exactly what the numbers are going to be." }, { "from": "human", "value": "And also to tell if it's going to be promising to look at further." }, { "from": "gpt", "value": "Exactly. And so that's a thumbs up, thumbs down. Are you worth my time or not? In most cases, it's not or it's good enough. We can do a basic analysis, maybe publish this as part of a larger sample, just so we output that we have observed the star and their basic nature that that's an important part to publish as well. And yeah, I had a run. So now we do remote observing. I do all of this now from my home, from my living room all night long. And I often work with colleagues. So we do it over Zoom and we process the data. We look at it, same thing still. And we just found a star that had a very low iron abundance. And then we decided, okay, that looks interesting. We're just going to keep exposing. So we took more data on it on the spot and we're writing up the paper right now. How do you know where to point the telescope? It's not random. There's a lot of work that goes into that. I began my career by answering, trying to answer that question, as in like doing the search process. That's why I called my book that I've written some time ago. Searching for the oldest stars because searching is one thing. It's very time consuming. And then on top of that, not everyone finds, right? And I often don't find, but I keep searching because our techniques have established that, yes, we can do it if we're just patient enough and keep going because it's a numbers game. And that's often the case in science. And that's something that not enough is talked about. How tedious it is and how long it takes to get to that one discovery, right? That moves the field further. And how difficult it is to believe that there is a thing to be discovered. Yes, yes. We have the saying, I learned this, I think, from my supervisor. One star is a discovery, two is a sample, and three is a population. So as soon as you found three of roughly the same kind, you're done. But you need to get there. Probably the first is the hardest, right? Yes. But it kind of remains really hard. But the thing is that at past three, many of us are, okay, we solved that problem. We started three times, so we can do it. That's a thing, right? That's a population. Three iron deficient stars, let's say, right? That's one puzzle piece. Now we can move on to the next thing." }, { "from": "human", "value": "Probably the first is the hardest, right?" }, { "from": "gpt", "value": "That's an indicator that there's many more of them, potentially. Yes, yes, yes, yes. So to cut a long story short about the searching, we started early on with what's called low resolution spectroscopy of many stars. So for example, my thesis work almost 20 years ago was piggybacking off a quasar survey that had collected. So quasars are basically giant, supermassive black holes that are really far away. So you only see one big bright light point. So it looks like a star, but it's actually just a giant supermassive black hole that outshines its own galaxy. And people had been trying to study those and they had taken little spectra of all things in the sky. And it turns out, oh, you can fish out the actual stars from that and look for certain signatures that might indicate a low metallicity star. So stars with low abundances. And so it was painstaking work to then take medium resolution spectroscopy to get a little bit more information and to use approximations and to kind of get candidates that we can then eventually take to the big class like Magellan to get a high resolution spectrum. So we really see the dips of all the individual elements that then give us the final answer as a yay or nay. These days, with another grad student, I developed a new technique to use images actually of all the stars in the sky taken with very narrow filters. So it's like you're wearing very specific glasses that only let so much light through. And so we can do similar things through having several narrow band filters, what we call it, to fish out things that have no absorption over here. So just the straight line and then a little dip here, so a little something there. And that has proven fairly successful in recent years. So looking at the entire, looking at a broader regions of space, regions of space. That's right. Because these stars are a little bit like the needle in the haystack, right? There are not that many left over. And certainly the galaxy has made plenty of stars in between. We need to comb through all of those to get to the goods. So we always start with millions and then work our way down. And in the end, we have like three good candidates." } ]

[ { "from": "human", "value": "I wonder how those ancient stars feel that they were noticed. They probably know that nobody pays attention. No, I'm just kidding. We're all special, right? So are the stars. It's good. It's inspiring, even if you're the outcast. In your pristine nature, you still might nevertheless be noticed. I'm hoping the same about humans if somebody's observing us." }, { "from": "gpt", "value": "I'm just kidding. We're all special, right? So are the stars. It's good if somebody's observing us." }, { "from": "human", "value": "Is there something else you could say that's about the challenges of this kind of high precision measurement that you're doing? So this kind of collection of data looking," }, { "from": "gpt", "value": "trying to pull out the signal from the noise out there that you're doing. Well, that's literally what we're doing in multiple ways, actually. So we're trying to find the needle in the haystack and then we find something. And then it turns out it's just a little bit too faint to actually get the kind of data quality on it that we would like or that would be warranted given the potential of the star. It's like, ugh." }, { "from": "human", "value": "So there's always noise. There's always a little bit of noise and you have to try to say how special is this when you're looking at the absorption line?" }, { "from": "gpt", "value": "So the most iron poor stars, their iron lines are so tiny that they're literally almost in the noise. So you need incredibly good data to make detections. And the funny thing is we're looking for the nothingness of, let's say, the iron lines, but then we don't want nothing, because if there's nothing in the spectrum, we can't measure anything. We can only get an upper limit, but we'd really like a measurement. So we are looking for the last little bit that you could possibly detect. And that's the strong function of the brightness of the star, because the telescopes have the size that they do. That's not going to change for a while. Hopefully eventually it will, but it's going to be at least 10 years out. And so, yes, we're often literally stuck in the noise because we can't make the measurement. So actually the record holder for the most iron poor star only has an upper limit. We can't get enough data on this to actually pinpoint a measurement to then take it to our theory colleagues and say like, give me this little iron out of your first star. So it's a bit frustrating, but also super exciting at the same time." }, { "from": "human", "value": "So let's go to both sides of that spectrum. What's like the most exciting discovery to you personally? Where is there a moment you remember that you saw a piece of data and your heart skipped a bit?" }, { "from": "gpt", "value": "Yeah, yeah, of course. Is it HE 1327? That was definitely one of those moments. I wasn't actually present at the telescope, but we were sent the data immediately from our colleague. And we just looked at it and our eyes got really wide and was like, oh my God, is this really what you think it is? So we had to run some numbers and it was. And these are magical little moments. The thing is, often we have false positives. And so there's always this kind of period and often it's, I don't know, 10, 15 minutes where you need to make some tests to kind of make the decision. Is this really something I should keep observing now? Is this really as good as I think or am I being fooled by something? So actually if you take a spectrum of a white dwarf, a white dwarf is the leftover core of a star" }, { "from": "human", "value": "like the sun that has gone extinct." }, { "from": "gpt", "value": "And white dwarfs have lost all their outer atmosphere. So it's just the hydrogen-helium core. So they look like a metal-poor star because that's only hydrogen-helium left, right? But the hydrogen lines that you can see in the spectrum of our stars and of the white dwarfs are a little bit wider than normal. So you need to have a good eye just to check, does this look a little bit wider than us? Is this a white dwarf who's fooling me here, right? And so it's like, this moment, it's like, oh my God. It's just minutes of nervousness. Yes, yes. And sometimes, you know, it's a dud and sometimes it's not." }, { "from": "human", "value": "What's been a big that you remember heartbreak, like a painful low point? Is it all leading up to the first? Is it all about HE 1327 again, just the leading up to it? Or has there been like a, yeah, has there been like low points in the search?" }, { "from": "gpt", "value": "That's a good question. I mean, you know, it starts with mundane things as in like, you won your telescope time, you travel there, and the weather is completely cloudy, it rains, and you had three nights, which is a lot, and you go home empty-handed. So that's definitely a low point. Probably not what you were thinking of, but there is a certain occupational hazard to it." }, { "from": "human", "value": "Which requires a kind of resilience and a patience." }, { "from": "gpt", "value": "Yeah, yeah, and you just got to learn to live with it. Coming back to reticulum too, actually, you know, that little dwarf galaxy, that was a run that we had, and the weather was incredibly bad. And I had sent my student there, and I was at home, and he calls me at 2am, and he was like, Anna, I think I observed the wrong star, I'm so sorry. There is this line there, this European line, and it looks like a metal-rich star. And I was like, it's cool. We all make mistakes, send me the data, send me that summary plot. And so I look at it, you know, I was like, super tired. It's like, I can't really tell, it doesn't look wrong, but I can't tell you right now that it's right either. So why don't you go to the next target? And he calls me back an hour later, Anna, it looks just the same. What am I supposed to do? And then I joked, well, maybe we found an R-process galaxy. Let's go to the next one. And the weather was degrading. And so to cut a long story short, we had to come, so he was observing the right stars. It was an R-process galaxy. The first one we had ever discovered, totally unpredicted. We had no idea that this was a thing. I mean, you know, of course, we thought that, you know, such a thing might possibly exist because why not, right? Neutron submerges happen somewhere. Crazy supernovae, probably too. But we were not prepared in that moment to find this thing. And in the end, the weather was getting worse and worse, and we wanted to see how many R-process stars are in this galaxy. So we managed by a hairline to observe the nine brightest stars, but the data quality was atrocious." } ]

[ { "from": "human", "value": "And the weather affects the data quality." }, { "from": "gpt", "value": "Yes, absolutely, because these were really faint stars. And so we were really lucky by making a very tight strategy of getting the absolute bare minimum for all the stars. So we could at least take a very crude look. Is it a yay or is it a nay? We couldn't even say yes or no, just to get an idea because we needed to know. Why was that important? Because we could only observe this system again nine months later." }, { "from": "human", "value": "So there's always a window of observation." }, { "from": "gpt", "value": "Yes, it was setting. This was our chance and it was going away with the clouds, you know? That was super high stakes. But we just made it. Really, it was almost impossible. And the thing is, this is such a serendipitous moment, inner serendipitous moment. The enhancement of these heavy elements was so strong that even in this really crappy data," }, { "from": "human", "value": "we could still see the enhancement. That was super high stakes." }, { "from": "gpt", "value": "The absorption was so strong it stuck out of the noise. If that enhancement wouldn't have been as strong, we would not have been able to say anything because we wouldn't have been able to tell. But because it was so extreme, it lent us a hand, despite the weather and all, to say like, yes, this is it. So that was quite the night." }, { "from": "human", "value": "Luck. I mean, a lot of this is just luck. So that was the first our process galaxy discovered." }, { "from": "gpt", "value": "Yeah. Yes. I didn't sleep all that much then." }, { "from": "human", "value": "Do you have hope? Are you excited about James Webb Space Telescope and other telescopes in the future" }, { "from": "gpt", "value": "that increase the resolution and the precision of what can be detected out there? Absolutely. Data with tea is fantastic already. I am not planning to use it personally, although I think I'm on one or two observing proposals, actually, because similar to what we already spoke about, we're interested in the same thing. We're just kind of looking at a different sides of the fence, right? I have my old surviving stars and I concoct these little stories about what the earliest galaxies may have looked like, what the objects were that contributed energy and elements and all these things. My JWST colleagues, they try to detect some of these earliest photons from these earlier systems to look at the energetics and other things. What was there? How many these kinds of things, right? So together, we're trying to explore this first billion years, but we do it in very complementary ways. And so I'm very excited to see what they can come up with and how that helps me to" }, { "from": "human", "value": "inform my stories better and more comprehensively. What do you think is the future of the field of stellar archaeology? How much can we... Maybe what are the limits of our understanding of this first billion years of our universe?" }, { "from": "gpt", "value": "Well, obviously, lots of limitations in the sense that I always say, I have a metal pore star for any of your questions because there are so many different kinds out there. And we still find new patterns sometimes, right? And there needs to be an explanation. The question is, is it ultimately just one quirky star or is it two or is it three, right? Is it a sample, is it a population? So we haven't concluded that kind of work yet." }, { "from": "human", "value": "So every metal pore star is a kind of data point that you can use to" }, { "from": "gpt", "value": "improve the quality of your model of how is the evolution of the early universe. Yes, and I would say we've made huge progress over the last 20 years. When I joined that field, it was in its infancy. And there was this serendipitous discovery of that first second generation star. And we have filled in the canvas a great deal since then. And this is what I have greatly enjoyed about doing so because there was so much discovery potential. And it's been dying down a little bit because of all the progress. It's on the up and coming again because there are so many large spectroscopic surveys in the works now that will just provide a different level of data that we haven't had before. I'm sort of of these older generation. I have only very few colleagues. I work in small teams and I observe every single star myself. Whatever I can, I do myself. I don't generally take other people's data, at least not certainly not in the end stage. And I'm not a big data kind of person, although we all headed that that way. I certainly use data from the Gaia astrometric satellite for the kinematics, for example. But that's personally a new thing for me to use sort of big sky surveys. That are available, so it's still very sort of hand-grown field where we do our individual observations. I have enjoyed that a lot, but that's about to change." }, { "from": "human", "value": "So one star at a time. Yes. I mean, there's power to that, to build up intuition of the early universe by looking one star at a time." }, { "from": "gpt", "value": "Yes, absolutely. And this is how you can really drill down on the questions that you have, right? Because you control what data you get. Otherwise, you have the data that you have, right? You get what you get and you don't get upset. I don't like that. I'm a little bit snobby. I really like to formulate my questions, go to the telescope, and then come with me. I will try to get it." }, { "from": "human", "value": "And also develop the intuition of where the data can be relied upon and where it can't and all the different quirks of the data and all that kind of stuff. Sometimes a lot is lost in the aggregation of the noisy data." }, { "from": "gpt", "value": "Yeah, yeah, yeah, yeah. Yeah, yeah, yeah. And that's always the danger if you have someone else's data that you just don't really understand the limitations and completeness things, how certain things were set up, and you get out what you put in. So I'm really particular about that, and it certainly paid off for me. That's one of the main notions that I try to teach in my classes and to my students, that you need to be able to formulate your question really well because otherwise you're going to get an answer to a different question, but you won't notice that the goal pulse has shifted in the meantime, right? So your interpretation can only be as good as the question. If you need to change your question, that's cool. Do it, but then it needs to pair up with your interpretation again. And so knowing, really being in the know about every step of what happens, that leads to quality results, I think. That's why I have sometimes little trouble with sort of big data and statistical analysis. Yes, on average, that's true. I'm not debating that, but I'm the kind of person I like to look at the outliers, so not the bulk, but the special ones. And they just need to be treated in a different way, and there needs to be an acknowledgement of that, different ways for different things." } ]

[ { "from": "human", "value": "So big data can look at divorce rates, and perhaps you and I are more interested in the" }, { "from": "gpt", "value": "individual love stories. Yes, that works for me." }, { "from": "human", "value": "So I don't know if it's possible to say, but what do you think is the big discoveries that are waiting? Is it on the different dynamics of the yield, the common narrative, the common story of how some of these metal, poor stars are formed?" }, { "from": "gpt", "value": "Is it where are the discoveries in this field that you think will come? I think the individual discoveries are actually, we've made most of those, certainly through individual stars. Finding yet another second generation star is incredibly important for me, but isn't really going to move the needle. Finding 50 of them or 100 of them, that would move the needle, but that's an order or two magnitudes up, and new search techniques and new surveys may enable that. But would you still call that a discovery, right? So that's just a scale. This is scale. Yes. So I think about it more like literally of the puzzle. Let's say you have a thousand piece puzzle and you have 900 pieces in there." }, { "from": "human", "value": "So that's just a scale. This is scale. Yes." }, { "from": "gpt", "value": "If you're a person like me, I want to get to the last ones. I'm not going to leave it. It's like, okay, I see broadly what this is going to look like, right? I'm done now. No, I want to get to the last one. Is the picture globally going to change? No. Are we going to figure out all the details and how it really works? Yes." }, { "from": "human", "value": "So really careful, detailed map out the ancient stars of our universe." }, { "from": "gpt", "value": "Getting into it. Because I think that's what many of us scientists are a little bit detailed obsessed. But I think that's our job too, right? To really kind of make it airtight, to really walk away saying, I fully understand this. Not just broadly, but we really know now. And so more and more of that is going to happen. And so I think this is probably true across astronomy. These individual 10 sigma discoveries become less and less. If they were easy, we would have made them already, right? Which means we have made many of them. But really filling in the details is the next sort of level of discovery. Maybe we need to find a new word for that. The hopes and expectations that go along with the word discovery are so enormous. We may not always be able to live up to that. But it doesn't mean that we're not finding out new things. It's just a different kind of quality because the questions have shifted. You close one door, suddenly there are 10 new open doors that we want to explore and march through." }, { "from": "human", "value": "And that's finding these last puzzle pieces here and there that really make it airtight. Yeah, so there's a lot of value and a lot of power and beauty to the discovery in the big picture of our universe and in the details. Yes. It's a bowl of both of you. We need both." }, { "from": "gpt", "value": "It's a bowl of both of you. We need both, absolutely." }, { "from": "human", "value": "Perhaps drifting into the philosophical. Let me ask about the Big Bang as we kind of encroach onto it. So your work is kind of taking steps back through time in a weird way. Do you think we'll get to deeper and deeper understand the really, really early days of the Big Bang? And the philosophical question, do you think we'll be able to understand what was before the Big Bang or why the Big Bang happened? You think about that stuff?" }, { "from": "gpt", "value": "Not with stars, for better or for worse, because stars only probe the time when they were formed. And the Big Bang is surely before then. I mean, I often talk to my students about the difference between math and physics. Let me give you an example. We talked earlier about AG 1523, and I was happy to share with you that I measured thorium and uranium, but I actually didn't quite close that loop. So we did this to try to attempt to calculate an age for these stars, right? But they rely on us knowing how the R process works, how these elements are created, where it happens, and then how those elements get dispersed into the gas and end up in the next generation star. So quite a few question marks. So that's how we got to the age of 13.2 billion years. This is probably not accurate, but this is the best calculation we could do. And the reason why I'm bringing this up is that that was actually the average of multiple elemental ratios that each gave a certain age, and then we averaged that. Because for better or for worse, this is the best we can do. So some of these numbers said, oh, this star is 15 billion years old. And then others said, oh, this is 10 billion years old. And so I often use that in my class to say like, what's the good news? And what's the bad news here? Some ratio said 15, something 10, right? Is 15 correct? And then I asked them and some people will say something. And so the thing here is that it's an absolutely correct calculation given the mathematical and physical model that we constructed. But does it make sense? No, it doesn't. If we believe the universe is 13.8 billion years old, 15 is ridiculous. Yet it is correct." }, { "from": "human", "value": "Isn't that interesting? Correct from a mathematics perspective." }, { "from": "gpt", "value": "Yes, it is not incorrect because this is what I calculated. Nobody made a mistake. Now we can question whether that's a good model. But that's a separate issue." }, { "from": "human", "value": "So you're saying physicists are much closer to truth than mathematicians?" }, { "from": "gpt", "value": "Well, it depends. Sometimes yes and sometimes no, right? So what our job as physicists is to take the mathematical model, calculate our numbers, and then ask the question, does this make sense? Now, in the case of 15, it doesn't. But we took the average anyway because that was the best we could do. All right. Let's put that aside. Let's apply the same sort of thinking to the Big Bang, right. Math can tell us things that we as physicists cannot grasp because it doesn't make sense to us. Now in the case of the Big Bang that's the special case because we don't actually know what's supposed to make sense. And this is where things get interesting. But this is where math will ultimately be the winner because we can no longer say, that's makes sense or this doesn't make sense because the physics has broken down." } ]

[ { "from": "human", "value": "So because the physics is broken down. But math breaks down too in the singularity of things. Well. Or no." }, { "from": "gpt", "value": "Well. Or no." }, { "from": "human", "value": "Depending on who you ask. Sure, sure." }, { "from": "gpt", "value": "This is the current question, right. How far, how much further can we push math, let's say to the front of the Big Bang, if there is such a thing." }, { "from": "human", "value": "What's the front in the back? What's the front? Well, before the Big Bang. Oh, before the Big Bang. The front, okay. To clarify, be all the doorways in the entrances." }, { "from": "gpt", "value": "Well, before the Big Bang. Oh, before the Big Bang. To clarify, be all the doorways in the entrances. So how far can we let the math go before that stops to make sense, right? And I don't know what the answer is to that, but it's really cool that because math doesn't have, is not limited by our physical nature, it can probably go a little bit further than the physics. Yeah." }, { "from": "human", "value": "Yeah. And math can go into more dimensions than four dimensions comfortably." }, { "from": "gpt", "value": "Yeah. Comfortably. And it's judgment free because it just calculates things on its own. Whereas as physicists, we are so judgmental. Yeah. This makes sense. This doesn't make sense, right?" }, { "from": "human", "value": "It doesn't get any worse. Yeah, it's such a beautiful dance. It's so amazing that through this dance, you can explore the origins of the universe. Like, doesn't the Big Bang just blow your mind that this thing has just started from a point? Yeah. And now we're here. Yeah, yeah, yeah, yeah. Hydrogen and helium. And then all the stuff you're studying, I mean, this evolution of chemistry created humans. And we're here talking. And there's a lot more to the story." }, { "from": "gpt", "value": "Yeah. And now we're- Yeah, yeah, yeah." }, { "from": "human", "value": "It's amazing. Yeah, yeah, yeah. Uh, and this kind of march that you're doing is observing data. Yeah, yeah, yeah. Is there, you're looking at old light and old data." }, { "from": "gpt", "value": "But only a few thousand years, right? Just a few thousand years. That's the difference between me and my JWST colleagues. Yes. Their objects, that light has traveled 13 billion years or whatever it was to us. And they're observing that now. My light has only traveled a few thousand years." }, { "from": "human", "value": "It's nothing, right? Just a few thousand years. So whatever you observe now is likely still going on." }, { "from": "gpt", "value": "Yes." }, { "from": "human", "value": "These stars are alive and kicking and having a blast. A thousand years. Just a few thousand years. It's all it takes. If we can travel close to the speed of light, maybe we can reach out there." }, { "from": "gpt", "value": "Yeah. We wouldn't have any planets around those stars though." }, { "from": "human", "value": "So that's, is that a definitive intuition?" }, { "from": "gpt", "value": "Well, what are planets made of? Elements, right? To take the Earth. All heavy elements, right? The universe needed to reach a certain stage first to have produced enough of all these elements to actually make a planet." }, { "from": "human", "value": "So on average, you're okay, right?" }, { "from": "gpt", "value": "So that took quite a few billion years." }, { "from": "human", "value": "So they're not going to have a mechanism for forming planets. You could have visitors probably, but the kinematics of that are weird, are unlikely." }, { "from": "gpt", "value": "Yeah, I would say so." }, { "from": "human", "value": "So they're interesting in that they reveal the early chemical evolution of the universe. Yes. Not that they're, they could be good vacation spots, but not. Well, if you like a worm." }, { "from": "gpt", "value": "Yes. Well, if you like a worm. Just no planet islands to go to to chill." }, { "from": "human", "value": "In your book, you highlight the major contributions in the field by many women. Some of these women were not, as you describe, immediately credited for their discoveries. So for me, from computer science perspective, the story also tells Harvard computers." }, { "from": "gpt", "value": "Who were these women and what can you just say about the nature of science and humanity? Discovering things is part of the human nature, right? And so it has happened for the longest time, not just by men, but also by many women. The field of stellar astronomy, which is my field, has particularly benefited from many discoveries made by women. You mentioned the Harvard computers. That's a term used for women who worked about 100 years ago at the Harvard College Observatory. And they were hired for their low wages and willingness to do diligent and patient work to comb through the big data of the day. So the observatory director, they were carrying out large sky surveys at the time. And they needed, that data needed to be processed and looked at and analyzed. And so many women or several dozens or one or two dozen women over the years were hired to do this work. And in the process, because they were looking at the actual data and they were smart, even though they had often no formal education, they made a lot of discoveries simply by being in tune with what they were doing. So they weren't robots as the term computer would perhaps lead on. So any jump cannon classified thousands and thousands of spectra and found out that you can, you know, stars have different temperatures and their spectra look according. We still use that classification sequence today. Cecilia Penger-Poshkin later on in I think 1925 was one of the first women to obtain a PhD in stellar astronomy. And she figured out, she calculated that the sun is mostly made of hydrogen and helium. That seems normal to many of us these days, but at the time, it was thought that celestial" }, { "from": "human", "value": "objects are made of the same thing as the earth. That's a gutsy, amazing discovery." }, { "from": "gpt", "value": "It was later termed the most important thesis of humankind or something like that. What a revelation to realize that stars are made of hydrogen and helium, right? And this was exactly the time when people figured out why stars are shining, namely because of nuclear fusion and that it's protons and, you know, the tunneling effect that leads to the actual fusion. Otherwise, you know, the protons repulse each other, they don't come together. And so what an incredible time it was back then. And so stars and nuclear physics were very closely related and it remains that now it's called nuclear astrophysics. And so many women had many contributions to that. Of course, prior to that, Marie Curie discovered two new elements. Ah, so awesome. Radium and polonium. Lisa Meitner discovered nuclear fission. That is the basis for understanding the R process. This is exactly what happens in the R process. You know, the heavy nuclei, let's say uranium, if you bombarded with a neutron, we talked at length about it, it will decay. It will, well, not decay, actually, it will fission. It will split into barium and krypton, let's say. So two lighter elements. That's exactly what we observe. I have always a higher abundance of barium than the heavier elements because of this fission cycling that she calculated in 1938, 1939. So many, many contributions and it's just so remarkable. If you just take that body of work, that changed how we do things, how we see the universe, how we understand things has led to so many subsequent discoveries, good ones and bad." } ]

[ { "from": "human", "value": "Well, all of that is taken together. That's progress." }, { "from": "gpt", "value": "All of it is taken together. That's progress, right. Science is what it is, we have to decide what we do with that knowledge, we can always use things for good or for bad." }, { "from": "human", "value": "That's part of the human endeavor as well. And also part of the human endeavor and the human nature is the issues with corruption and credit assignment, and all these kinds of things that make this whole ride so damn interesting about what's right and wrong and about the nature of good and evil. And that seems to surface itself in all kinds of places, all the time." }, { "from": "gpt", "value": "Yes, yes, yes, yes, yes, yes. Lisa Meitner was nominated for the Nobel Prize 40 times, more than that even. It's amazing. She holds the record for that. She never received it. Case in point." }, { "from": "human", "value": "Yeah, and of course the Nobel Prize has its complexities. One is the credit assignment, but two, even in astronomy, sort of assigning credit to a handful of folks was so many more contributed as a complicated story also. Yeah, it's very complex. Okay, sorry for the romantic question, but what do you use the most beautiful idea in astronomy, in stellar astronomy?" }, { "from": "gpt", "value": "Well, so early on, you know, when I was in high school, I was thinking like, okay, well, what do I want to do when I grow up, right? I knew I wanted to do astronomy, but I was a little bit torn because my interests were definitely stars, stellar astronomy, but also chemistry. I always had a fascination about the elements, so Marie Curie was a big role model. My friend actually made a beautiful, produced a beautiful movie about the discovery of the elements. This is a theater play, but digitized, where when I saw it, I could actually kind of relive the sort of discovery moment that Marie Curie had. It sent shivers down my spine. It was fantastic. I mean, this is the kind of thing that I wanted to experience. But yeah, so nuclear physics and element creation and formation was really interesting to me, chemistry, the element stars, and all of that. I was like, I don't know if I ever find something that combines all of these things. Then I ended up in Australia, and I met this person, and he was working on old stars. As I was sitting in his talk, hearing about this for the first time, it clicked all over my head. I was like, oh my God, it all fell in place because we can use these old stars to study the elements, to learn how they're formed. We can get these clean signatures that help us inform the nuclear synthesis processes. Of course, I need to know a lot about stars too, so it's like all together. That was sort of a moment of magic. Then the fact that I have now done that for 20 years, it's just like I won the lottery. It all clicked into place. So in some sense, it's an ongoing love story for me, if I could say it like that, where I found my stars, my thing. I am fortunate enough to be able to keep doing that. I'm happy to see where it will take me. It's an evolution, as with every relationship. If you don't march forward, you move backwards. I'm not interested in moving backwards, so I'm letting the field" }, { "from": "human", "value": "and the discoveries and the findings lead me to... It all clicked into place." }, { "from": "gpt", "value": "It's not hard for me to follow my hunches. Sometimes even at the telescope, it's like, let's take a look at this one. I have a good feeling. Then usually something good or not bad pops out at the end. I really like that. I have the freedom to do that, that I'm allowed to follow my hunches. Too many people, I think, are boxed in with their job or their life that they don't have that kind of freedom. That's really important to me, and I certainly try to make use of that. I also try to teach that to others to trust them, to learn. You need to learn your things, but then you need to also trust that knowledge, and you have a grasp on it. You get out what you put in. Being able to contribute in meaningful ways to our knowledge about our cosmic ancestry, our cosmic history, that's a wonderful thing." }, { "from": "human", "value": "In this way, your personal love story with the stars evolves. What advice? You've already spoken to it a little bit, but what advice would you give to young people that are trying" }, { "from": "gpt", "value": "to find the same kind of love story in their career, in their life? It seems increasingly hard for folks to find that. Sometimes I feel that young people have all the opportunities these days, and that's wonderful, but it's almost like that leads to some... What's the right word? They're a little bit too tired to make all the decisions, because at some point, you need to put your eggs in a basket, and you need to be okay with that. We can't do all the things, even though we're often told you can be president too, and I think that's really important to convey, but at the end of the day, we can only have one job or one type of profession. I'm not saying you need to be locked in, but it's hard to change 180 degrees, and so lots of people I think are often afraid to really dig in, at least for some time, and get their hands real dirty, and really learn from the bottom up. On one thing. On one thing, because they're afraid they're missing out on 99 other things. On one thing. But life is a little bit missing out on 99 other things, because we only have 24 hours in a day. I have that feeling very often. There are so many things I would like to do, many things I would like to try to be good at. Sometimes I wish I had a different job, because I have other interests too, but I realized, okay, I can only do one thing, so I have no regrets, but this is a general feeling that I think I would think most of us have, but if it stops you from really drilling down on one thing, to become an expert on one thing, to become really good at one thing, that you call your own, then it just makes it difficult." } ]

[ { "from": "human", "value": "And so a fulfilling life is in part likely to be discovered in a singular pursuit of a thing," }, { "from": "gpt", "value": "of one thing. For at least for a time. For some time, with your heart and your hands, because I think most people long to own something. We all, I think, want to leave some legacy of some sorts, for our children, for humanity, for this planet. And I think it's really important for young people to strive for that and not lose sight or trade that for all the opportunities, because an opportunity is nothing if you don't do anything. You need to do something at the end of the day. So I chat with lots of people about this, and I often start by just saying, hey, tell me what you don't like, because it's much easier to let out what's not on your plate. And then this way we get a little bit closer, and then it's like, well, why don't you take a risk and just sign up for something for three months?" }, { "from": "human", "value": "But that's what it feels like to narrow down. That's what it feels like. And it is a risk. Commitment is a risk, because you're basically sacrificing all the other possible options. But then I guess you have to trust the magic you noticed in that thing. If you notice one" }, { "from": "gpt", "value": "thing, just stick with it. And then maybe there's something there. Yes, right. And this moment of kind of feeling it in your entire body and mind that this is the right thing. Getting there is probably really hard. But if you don't try, you won't find out. The hard stuff is the fun stuff. That's also another thing you can find out. And then there is that, yes." }, { "from": "human", "value": "Somehow, it doesn't make sense. You also mentioned that you've taken a little stroll into the artistic representation of yourself. Can you speak to that for a little bit?" }, { "from": "gpt", "value": "Yes. Well, I already just mentioned sometimes I wish I had more time to do other things. So I find little sideways, I guess, to pursue things that I like besides astronomy. Or at least I try to find connections. And so some years ago, I, again, with the help of my friend who made this Marie Curie movie, she and I wrote a one-woman play where I actually portrayed Lisa Meidner, who was an Austrian-German nuclear physicist from Germany. So I have the right accent for that. And we wrote this play about this moment of discovery of nuclear fission. Again, this is an absolutely critical piece that explains my work today. And we all stand on the shoulder of giants. She was one of those giants. And in some ways, it's, of course, a way for me to acknowledge other people's work that have come before me. It's a wonderful way to highlight the contribution by a prominent woman. And the way I do it is it's a 25-minute play in costume where I relive for people the moment of discovery. Then I turn into myself, and then I give a 30-minute presentation on the art process and the creation of heavy elements, because the audience can now perfectly understand that the public audience, given the historic backdrop of this discovery, that they just lived through my presentation. And it's a wonderful compliment that almost spends 100 years from one woman to the next passing on the torch. And when we write up our results in, let's say, in magazines like Nature and Science, it's always about the result on the golden platter, perfectly prepared. The discovery is never described, only ever the results. You asked me beforehand, what does it feel to be at the telescope in this moment? I'm happy to talk about this, but it's nowhere written ever. Nobody really talks about it. And so having a form of theater of the arts to bring this exciting moment that is what we all want to experience as scientists to a wider audience is so profound and so rewarding. And they all love it because everyone can understand a moment of discovery. I was looking for something and then I found it. It's like your misplaced khakis, right? Or love. Yes, yes. Everyone can understand it. The glorious experiences, yes. The implications and the findings, that is much harder to understand for anyone. This is where the scientists' work truly lies. This is our job. But the moment of discovery is easy and it's beautiful and it needs to be said. And so taking my audience on this journey, what is the perils? What are my worries? And then, ah, here is the moment of discovery. Let me tell you about it. It profoundly" }, { "from": "human", "value": "transformed me. And here's how it went, right? It's so good. And art or love. Everyone can understand it. The glorious experiences, yes. And art is a way to reveal this fundamentally human" }, { "from": "gpt", "value": "side of science. Yes, yes. The problem with science is that's people doing it. Maybe not a" }, { "from": "human", "value": "problem, but that is it. That's also what makes it beautiful, right? I mean, humans are fascinating and we're able to come up with these ideas through all the struggle, through all the hardship," }, { "from": "gpt", "value": "through all the hope, through all the search. And so the art's a great way to to portray that and to broadcast that, right? I think this is how the audience really should be interacting with scientists, much less about the findings, but really more about this yearning for answers, right? I need to find these khakis. I need it because I need to go, right? It's like, now, now. And then, ah, God, here it is. Now I can go my merry ways. It's so relatable. We just need to find more and better ways to to do that. So I hope to turn this into also a digitized version at some point to again, make it more accessible. I hope so too. So far, I'm just doing it in person." } ]

[ { "from": "human", "value": "But I would love it. I think I would love it. I think a lot of people would love to see it. So I hope you do just that. Let me ask you a big ridiculous question. You look up at the stars, you look up at the early, early, early stars. So let me ask the big question that we humans often" }, { "from": "gpt", "value": "ask and struggle to answer. What's the meaning of this whole thing? Why are we here? We talked about, you know, the biological evolution requires the chemical evolution for all of this to kind of play out. And carbon played this important role. And, you know, in some sense, we're just a consequence of all of these things being the way they are. Right. So maybe this is just where we are supposed to be, because, you know, the laws of physics sort of work the way they do. And we talked much about the variety of of everything, really. And certainly, you know, from over here to over there and things in the vicinity of where the sun and the solar system formed, they were the way they were. And life maybe wasn't a necessary consequence of that. In some sense, I like to believe that because then it becomes reproducible and we can apply that same argument elsewhere." }, { "from": "human", "value": "If it's total chance. Right. That makes it harder. And that's not truly satisfying to scientists. So it's it's a consequence of psychological evolution, which is a consequence of biological evolution, which is consequence of chemical evolution, consequence of physical evolution" }, { "from": "gpt", "value": "and whatever, whatever disciplines, it's turtles on top of turtles. Turtles all the way down. Yes." }, { "from": "human", "value": "Yes. I, yeah, I, yeah, you have studied some of the most ancient turtles. Yes." }, { "from": "gpt", "value": "At the very bottom of the thing. Yes. That's right. They live for quite a while." }, { "from": "human", "value": "Yes, they do. Well, thank you for your incredible work. Thank you for highlighting both the human side and the deep scientific side. It's just I'm a huge fan of your work and thank you for everything you do. And thank you for talking today. This is awesome. Of course. It was wonderful. Thank you. Thanks for listening to this conversation with Adam for Bell to support this podcast. Please check out our sponsors in the description. And now let me leave you with some words from Douglas Adams and hitchhiker's guide to the galaxy. Far out in the uncharted backwaters of the unfashionable end of the western spiral arm of the galaxy lies a small, unregarded yellow sun orbiting this at a distance of roughly 92 million miles is an utterly insignificant little blue-green planet whose ape descendant life forms are so amazingly primitive that they still think digital watches are a pretty neat idea. Thank you for listening. I hope to see you next time. I hope to see you." } ]

[ { "from": "human", "value": "And one of them is drinking an Athletic Greens drink. Maybe it can be part of your life in the same kind of way. They'll give you a free one-year supply of vitamin D and five free travel packs with your first purchase" }, { "from": "gpt", "value": "when you go to athleticgreens.com slash Lex." }, { "from": "human", "value": "Go to this is the Lex Freedom Podcast. To support it, please check out our sponsors in the description. And now, dear friends, here's Harvey Silverglate. You co-founded the Foundation for Individual Rights and Expression, also known as FIRE, a legendary organization that fights the freedom of speech for all Americans in our courtrooms, on our campuses, and in our culture. So let's start with a big question." }, { "from": "gpt", "value": "What is freedom of speech? First of all, the organization, when I co-founded it, in 1999, was called the Foundation for Individual Rights in Education. It focused on free speech issues on college campuses in academia. And only earlier this year did we decide to expand our reach beyond the campuses, which is why the name, although the acronym FIRE remains, it's now the Foundation for Individual Rights and Expression. The E used to be education. The E used to be education, it's now expression. And we basically do a lot of the cases the ACLU used to do. The ACLU now amores us. They're a progressive organization rather than a civil liberties organization. And we've taken the role of dealing with free speech in the society generally. And now this is a particularly, an era prone to censorship. Everybody thinks they're right and that people who disagree with them should not be able to voice their views. It's a very difficult period right now, both on campus and off campus. It's about as intolerant an era as I can remember. I'm gonna be 81 May 10th. I was born on Mother's Day, 1942. And I can't remember it being this bad. I was born during the McCarthy era. So that says a lot." }, { "from": "human", "value": "And it sort of reminds me of that. Well, let's start with that, almost a philosophical question, a legal question, a human question, what is this freedom that you care so much about," }, { "from": "gpt", "value": "that you fought for so much freedom of speech? It is the most important right that Americans have. It's not a coincidence or an accident that it's named in the First Amendment to the Constitution. Without it, no democratic society can be democratic for long. And I'm an absolutist. That is, I believe that, for example, people say to me, but what about hate speech? Well, hate speech is much more important than love speech. And the reason is I'm much more interested in knowing whom I should not turn my back on than I am interested in figuring out who loves me or who likes me. So hate speech is the most important in my view. And yet it's banned in, for example, schools. It's unbelievable. Kids are not schooled into understanding the glory of the First Amendment when schools say to them they shouldn't say things that are gonna make somebody feel bad. I mean, the purpose of speech is to express honest views that people have. So I believe hate speech is as important as love speech," }, { "from": "human", "value": "and my view is more important. So it should be brought to the surface rather than operate in the shadows. Absolutely, absolutely. What is the connection between freedom of speech" }, { "from": "gpt", "value": "and freedom of thought? Well, in a free society, thoughts start in the brain and then they come out the mouth." }, { "from": "human", "value": "So they're different ends of the same spectrum. So do you, the censorship of speech, eventually leads to a censorship of thought?" }, { "from": "gpt", "value": "Of course, censorship of the mode" }, { "from": "human", "value": "by which other people know what you're thinking. So there's some aspect of our society that the thinking is done collectively, and without being able to speak to each other," }, { "from": "gpt", "value": "we cannot do this kind of collective thinking. And out of speech, the theory is that ultimately out of speech comes truth. That isn't necessarily so. But I do think that when there's free speech, better decisions are made, because people put their views on the table in a frank, accurate way, and then those views mix together and clash. And out of that usually comes the better decision. Not always, but usually, more often than not. But if somebody is not allowed to sit at the table of decision-making, then the decision-making process is poorer, less robust, less diverse," }, { "from": "human", "value": "and ultimately less successful. Can you elaborate on the idea of free speech absolutism? So hate speech can be quite painful to quite a large number of people." }, { "from": "gpt", "value": "Does this worry you? Does this worry you? Yep, living in a free society requires that you expose yourself to some discomfort. You call it pain. It's maybe emotional pain. It's not physical pain, but it's the price we pay for living in a free society. Every so often, we're insulted. We're emotionally hurt. Think of the alternative. All the alternatives are worse. Nobody ever promised us a rose garden. We're lucky to be in a country that has a First Amendment. It's also the most diverse country in the world because of immigration. I mean, my grandparents, my father's side came over from Russia. My mother's side came over from Poland. I'm very happy that my grandparents came in from Russia. I would not want to be in Russia today. I'd probably be sharing a cell with a Wall Street Journal reporter. So I'm thankful that they came in, and this is a great country. It's got troubles right now, but our country doesn't. And we've had, before we had a civil war, we had segregation, we had the decimation of the Indians. We're not perfect, but it's the best place in the world" }, { "from": "human", "value": "for somebody who values liberty. So you don't think that hate speech can empower large groups that eventually lead to physical action," }, { "from": "gpt", "value": "to physical harm to others? No, I don't. I think that we have developed a culture in which it's understood that if you don't like what you hear, you talk back. You write something. We don't punch each other. We insult each other. Is insulting great? Well, I don't know, it's okay. I used to, as a kid in Brooklyn, where I was born, I was born and raised in Bensonhurst, we used to say sticks and stones can break by bones, but names can never harm me. And it's absolutely true. What was true when I was five is true when I'm almost 81. So I've lived a long time, I've seen it all. And I'm talking from experience as well as theory." } ]

[ { "from": "human", "value": "It's what happens when you reach your 80s. I read that you had this line" }, { "from": "gpt", "value": "that you cannot be protected from being called an asshole." }, { "from": "human", "value": "Correct, especially if you're an asshole, an asshole. Well, that's, but you don't have to be an asshole to be called an asshole. That's correct." }, { "from": "gpt", "value": "And I think the internet has taught me that as well. Well, the internet has posed a particular challenge to free speech absolutist because of some of the stuff that's on there is godawful. But I have no different rule for freedom of speech on the internet than I have in newspapers or in lectures" }, { "from": "human", "value": "or in classrooms or conversations among people. What do you think about the tension between freedom of speech and freedom of reach as is kind of sometimes termed. So the internet really challenges that aspect. It allows speech to become viral" }, { "from": "gpt", "value": "and spread very quickly to a very large number of people. It allows speech to... Well, you know, we've had revolutions in the modalities of communication. After all, newspapers were the first challenge. Radio and television posed a new challenge. The FCC tried, but ultimately gave up the attempt to control obscenity, for example. And the Supreme Court has been pretty close. The one thing that liberal and conservative Supreme Courts, right now we're in a conservative era due to Trump nominations. During much of my life, the Warren court, it was William O. Douglas, Brennan, liberal court. One thing they agree on is free speech. They don't agree on much else, but they do agree on free speech. And I think the reason is that they recognize that, well, my group is in the ascendants today, but it may not be tomorrow. And I want to have objective, clear rules so that when I'm in the minority, I'm able to voice my opinion. And so it's one of the few things that both sides of the political spectrum agree on. The only people who don't are the people way over on the right that I call the fascists and the people way over on the left who are the communists. But with respect to most people in this, on the political spectrum, Republicans, Democrats, socialists, libertarians, they agree on the primacy of free speech" }, { "from": "human", "value": "because it protects them when protection is needed. So to you, even on the internet," }, { "from": "gpt", "value": "free speech absolutism should rule. Yes, nobody's going to die. Remember, death threats are not protected. Nobody's going to die. So people are going to be a little bit insulted. That's the price you pay for living in a free society. And it's a small price, in my view. Some people don't have as tough a hide as others, well, then develop it. I don't mean to sound cruel, but you know, you're living in a free society," }, { "from": "human", "value": "develop a tough hide. So that's the cost of living in a free society. Yep, there's a cost. The thing is that it can really hurt at scale to be cyberbullied, to be attacked for the ideas you express, or maybe ideas you didn't express, but that somebody decided to lie about you" }, { "from": "gpt", "value": "and use that to attack you. There's a cost. Well, first of all, there are, there are some exceptions to the First Amendment. libel and slander is an exception. Direct threats are an exception. If you say such and such, I will murder you. That is not lawful. If you say to somebody, if you say about somebody, oh you know, you beat your wife, that is not lawful, if in fact the person knows you don't beat your wife. There are some limits, defamation is one, direct threats are another. The first limit is not absolute, but it's more absolute than it is in any other society, and it's pretty near absolute. For example, fraud. If you sell somebody a car and you say, oh, this is in great running shape, and in fact it's an old jalopy and it's not going to make it more than 10 miles, that's fraud. That's not free speech. Free speech is not absolute, there are these limits, but they're very narrow specific categories" }, { "from": "human", "value": "of limits. There's gray area here because while legally you're not allowed to defame a person, in the court of public opinion, especially with the aid of anonymity on the internet, rumors" }, { "from": "gpt", "value": "can spread at scale, hundreds of thousands of people can make up things about you. You have to defend yourself. Using more speech. We're through freedom of speech, we're big boys and girls. You have to defend yourself. In some societies, if you say something, right now if you say something nasty about Putin, you'll end up in the Gulag, if you say something nasty about Biden, you end up in the New York Times. Where would you rather be?" }, { "from": "human", "value": "Well, let's talk about using more speech. The thing you've done for over 20 years, which is fight for the freedom of speech on college campuses." }, { "from": "gpt", "value": "Why is freedom of speech important on college campuses? It's important everywhere in the society, but it's most important on college campuses. Why? Because that's where we educate our young citizens. If you are educated under a notion that some dean can call you on the carpet, because you say something which is considered racist, or you can say something which is considered dangerous to social cohesion, then it's not a liberal arts college, no. It's the theory that fusion I used in The Shadow University." }, { "from": "human", "value": "A book you've written, The Shadow University. 1998. 1998." }, { "from": "gpt", "value": "You were ahead of a lot of these things, by the way." }, { "from": "human", "value": "I'm afraid that as a pessimist, I always saw the bad side of things. Betrayal of Liberty on America's campuses, The Shadow University, a book you co-authored" }, { "from": "gpt", "value": "with Alan Charles. Yes, with one of my Princeton classmates, Alan Charles Kors, who's now an emeritus professor of enlightenment history at the University of Pennsylvania. I only taught for one semester, and I can go into that later, the reason that I did not continue to teach in colleges. At Harvard Law School, I taught a course in the mid-1980s. But in any event, the college campuses are one of the most important for free speech. This is where people get education. And if you don't really get a good education, if certain points of view are not allowed to be expressed, because education comes from the clash of ideas. And you then have to decide, this is how you become a thinking adult. You have to decide which ideas make more sense to you, which ones you're going to follow. The college experience is transformative. And if there is censorship on campuses, it's highly destructive of the educational enterprise, and ultimately to the entire society. We have in the sciences, we have a scientific method. Scientific method is you try experiments, and you see which ones work, and then you develop theories based upon the results of experiments. Well, this is not much different from every other aspect of life. You have to entertain different views on different subjects. You hear all the views, and you make a decision as to which ones accurate and which ones not." } ]

[ { "from": "human", "value": "So the scientific method I apply to non-science, to history, to journalism, to all of these things." }, { "from": "gpt", "value": "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." }, { "from": "human", "value": "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" }, { "from": "gpt", "value": "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." }, { "from": "human", "value": "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" }, { "from": "gpt", "value": "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" }, { "from": "human", "value": "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." }, { "from": "gpt", "value": "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." }, { "from": "human", "value": "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" }, { "from": "gpt", "value": "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." }, { "from": "human", "value": "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" }, { "from": "gpt", "value": "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." } ]

[ { "from": "human", "value": "Outside of the university you do graduate eventually outside of the university and that's ultimately the mission of the universities is to prepare you to make you into a great a human being into a great leader that can take on the problems of the world." }, { "from": "gpt", "value": "The problems of the world." }, { "from": "human", "value": "And you don't do it by treating you like a little flower. But what role does the university have to protect students? To women, African Americans, anybody, Jews," }, { "from": "gpt", "value": "anybody who gets, can be victim of hate speech. They protect you from physical assault. If somebody physically assaults you, then they get punished. But they shouldn't protect you against insult, because that is a violation of academic freedom, the freedom of the insulter to insult you. And also, as I said, it's very useful to know who doesn't like you. It's useful for the so-called victim. I think it's to say, I wanna know who doesn't like me." }, { "from": "human", "value": "It's as important to me as knowing who likes me. But do you also believe in this open space of discourse" }, { "from": "gpt", "value": "that the insulter will eventually lose? I think that's true. I think that the insulter eventually will wear out his or her welcome. I do." }, { "from": "human", "value": "But I like to know who the insulters are." }, { "from": "gpt", "value": "Because it gives you a deeper understanding of human nature. Yeah, and usually, by the way, my experience has been that the insulters have generally not been as smart as the people they've insulted. And that's probably one of the reasons they insult them, because they feel inferior. I mean, I'm not trying to be a psychoanalyst here, but a lot of the people who are the haters" }, { "from": "human", "value": "are pretty low down on the intellectual scale. Anyway, 95% of administration, you would fire, you're calling to fire 95% of the administration. People should know. I think people that don't really think about the structure, the way the universities work, are not familiar, I think, with the fact that administration, there's a huge bloat of administration. When you think about what makes a great university, it's about the students, it's about the faculty, it's about the people that do research, if it's a research university, they don't think about the bureaucracy of meetings and committees and rules and paperwork, and all that, and all the people that are involved with pushing that kind of paper. And there's a huge cost to that, but also slows down and suppresses the beautiful variety that makes the university great, which is the teaching, the student life, the protests, the clubs, all the fun that you can have in university, all the very kind of exploration, which you can't really do once you graduate. It's the place, the university is a place to really explore in every single way. So let me just talk about this important thing because I'm very fortunate to have contacted you almost by accident in a very important moment in your life. You're running for the Harvard Board of Overseers. What is this board? How much power does it have? And what would you do if elected?" }, { "from": "gpt", "value": "Okay, first of all, I have a prediction. Yes. That in about five years, they're gonna probably change the name because Overseers reminds people of the slavery era, and we're in such a politically correct era now that the English language is being restricted, corrupted is the way I put it, because certain words are forbidden. We have some problems in this country, and I think a part of the problem is the educational system has lost the sense of what academic freedom and free speech are all about. And I think it's essential that the educational system begin to take more seriously what free speech and academic freedom really are. That's why I'm running for the Harvard Board of Overseers." }, { "from": "human", "value": "So let me just link on the role of the administration in protecting free speech. So what often happens, I think you've written about this, is there's going to be a few, maybe a small number of hypersensitive students and faculty that protest. So how does Harvard administration resist the influence of those hypersensitive protesters in protecting speech and protecting even hate speech?" }, { "from": "gpt", "value": "Harvard has done fairly well under the presidency of Lawrence Bacow. I have had a couple of meetings with Bacow. I like Bacow. I have donated to Harvard a print of my late wife, took a picture of Bob Dylan and Allen Ginsburg when the Rolling Thunder review got to Harvard Square. And it's sort of an iconic photograph. She called it the music lesson because it's got Dylan teaching Ginsburg how to play the guitar. And I donated one of those to Harvard. It's hanging in Bacow's office. He, the new president, Claudine Gay, is not known for respecting academic freedom and free speech. People have said to me, well, give her a chance. Well, I'm willing to give her a chance, but she does have a record. And she's a bureaucrat. I don't think she believes in free speech and academic freedom. I think she's a progressive, not a liberal. I'm not happy with the appointment of Claudine Gay. And it has made more essential" }, { "from": "human", "value": "my attempt to get on the board of overseers. So let's talk about the board of overseers. And you're run for it. The specifics, actually. It would be nice because I think you're a writing candidate and the election is over on May 16th. Yes. And I think there are specifics. I'll probably give them in the intro. I'll give links to people, but the specifics are complicated. Let me just mention that you have to be Harvard alumni." }, { "from": "gpt", "value": "So I've graduated from Harvard." } ]

[ { "from": "human", "value": "You have to, in order to run and in order to vote. In order to vote. And the process, I imagine, is not trivial, but this is done online. And if you're an alumni, you should have received an email from a particular email address, harvardatmgelectionservicescorp.com. And presumably there's a way to get some validation number from that email, and then you go online, you enter that validation number and you vote. And to vote for Harvey, you have to enter his name, correctly, Harvey Silverglate, and spell it correctly. Obviously, I'm imagining this because I'm MIT, not Harvard. So I'm imagining the process is not trivial. You have to click on things. You have to follow instructions that are not trivial. And I'll also provide an email if the process is painful. It doesn't work for you that you can email. Email Harvard and complain. IT help at harvardidu and so on. I'll provide all the links. But is there something else you can say" }, { "from": "gpt", "value": "about the voting process, what you're running on? This is my second run. The first time I got enough signatures to get on the ballot. Then the Harvard Alumni Association sent out a letter to all living Harvard alums recommending that they vote for the officially nominated candidates that excluded two petition candidates of whom I was one. And I wrote to the Alumni Association and I said, you have now sent out the curriculum VTIs and the policy positions of all these officially nominated candidates. There are two petition candidates on the ballot. I would like to be able to send out my positions to the voters. They wrote me back saying, our policy is to only send out the policy positions and the platforms of officially nominated candidates. Can you believe that? Well, this is a liberal arts college, right? From the, we're from the clash of ideas, truth emerges. Well, really, this is what I call Harvard Alumni Association. What I call Harvard's not so subtle means of candidate suppression. Not voter suppression, candidate suppression, and everybody can vote, but not everybody can run. It becomes a liberal arts college where the clash of ideas will produce the truth. We'll worry about the clash of ideas on the board of overseas. The board of overseas is important. It doesn't have the same power as the Harvard Corporation, the so-called president and fellows of Harvard College, but it's very influential and very important, and it would be a great perch for me to try to exert influence for the university to get back to where it was before it was taken over by the administrators." }, { "from": "human", "value": "Well, I'm pretty sure that most of Harvard alumni, most of the students currently going to Harvard, most of the faculty at Harvard probably stand behind their ideas and the ideals that you stand behind, the people that love" }, { "from": "gpt", "value": "Harvard and want to stand for and be. See, the alumni were educated in an era when these concepts were taken more seriously and before the administrators took over. So I do think if I get my message out, I'm gonna win the seat, and if I win a seat, I will have a great perch for trying to convince the real power that be, which is the Harvard Corporation, to do the things that I'm suggesting, you know, get rid of 95% of the administrators, get rid of the speech codes, reduce tuition by 40%, all of these salutary benefits. Can you imagine if Harvard became the most affordable college in the United States?" }, { "from": "human", "value": "Well, the affordability is another aspect, but I think before that, just the freedom of expression, freedom of speech, freedom of thought. It's America's greatest universities, I think, is something that everybody would agree on. It would have a tremendous effect on the whole country. And is there something to say about the details of how difficult it is for alumni to vote?" }, { "from": "gpt", "value": "Well, experience with this, experience with this. You could vote online or you can vote by paper ballot, you could request a paper ballot, and all I could say is that the hard part is getting the message out. My name doesn't appear on the ballot because I couldn't get enough signatures. Well, Harvey, Harvey Silverglate. S-I-L-V-E-R-G-L-A-T. You know, when my grandparents arrived from Russia, the name in Russia was something like Zilberglit, and the immigration officer had several choices. He could have said silver gate. Gate is a real, silver and gate are real English words. He could have said silver glade, G-L-A-D-E. Those are real English words. That's how my name is often the spell, either silver gate or silver glade. Silver glade is a nonsense syllable, and why the immigration officer chose to transliterate Zilberglit as silver glade, I'll never understand, and it is the cause of endless mistakes in my name." }, { "from": "human", "value": "Well, the fundamental absurdity of life is also the source of its beauty. Yes. Anyway, we shall spell it out and we shall get yell loud and wide that everybody who has ever graduated from Harvard should vote for you if they believe in the ideals of the great American universities, which I think most people do. The idea of life. Let me also ask about diversity, inclusion, and equity programs. You've had a few harsh words to say about those. You know, the idea of diversity, I think, is a beautiful idea. You said that Harvard's idea of diversity is for everyone to look different and think alike. Correct. Can" }, { "from": "gpt", "value": "you elaborate? And be comfortable. And be comfortable. Yeah. First of all, it is impossible, if liberal arts education is taken seriously, it's impossible for students to feel comfortable. Why? Because one of the roles of college is to challenge all the beliefs that they grew up with, which mostly are the beliefs inculcated by parents and by elementary school teachers. And the idea is to be able to challenge those thoughts, those ideas. And if you don't have free speech and academic freedom, those views get reified. They do not get challenged. So it violates the fundamental role of higher educational institutions to have any restrictions at all. That's number one. Number two, as I think I said earlier, if people, students are not allowed to be frank with one another, they don't really learn about one another. And, you know, I've given a lot of lectures in which I said, and I think students now understand it, I'm much more interested in hearing from the people who hate me than the people who love me. I'm much more interested in knowing who disagrees with me than people who agree with me. That's how I learn, and that's how they learn, the clash of ideas, which is the theory behind the First Amendment, that truth will somehow emerge, or if not truth, at least a better truth, a truer truth, a more useful truth, if" } ]

[ { "from": "human", "value": "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," }, { "from": "gpt", "value": "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" }, { "from": "human", "value": "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" }, { "from": "gpt", "value": "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." }, { "from": "human", "value": "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," }, { "from": "gpt", "value": "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" } ]

[ { "from": "human", "value": "unionized. So that to you is at the core of the problem that results in the kind of inequality of opportunity that affirmative action is designed to solve." }, { "from": "gpt", "value": "If the educational system in the elementary and high school levels is improved, we wouldn't need affirmative action. These kids would get" }, { "from": "human", "value": "good educations. So from all backgrounds, poor kids in the United States will get" }, { "from": "gpt", "value": "good education if public unions are abolished. Correct. Incidentally, the" }, { "from": "human", "value": "postal service would probably work better too. That's a whole other conversation. Yes. But to you at the core of the problem of the inequality in universities that diversity, inclusion, and equity programs are trying to solve is the public education system... Sure. Correct. secondary education. Yes. Correct. Elementary and secondary... Elementary and secondary education. Well then, is there use? What is the benefit? What is the drawback of ADIE, diversity inclusion and" }, { "from": "gpt", "value": "and equity programs at universities like Harvard. It's an affirmative action, basically. And what it does is it allows the system of elementary and secondary education to be bad, because they could say, oh, we got our kids into Harvard. Yes, but you haven't educated them. And it covers up the wound, and I think we will never improve as long as we're able to cover up the wound. And as I said, affirmative action is gonna be abolished by the Supreme Court. It's a clear violation of equal protection. It was what Sandra Day O'Connor understood, but ignored intentionally, but as an experiment. And I believe it's gonna be abolished, and that's gonna have, that's gonna force" }, { "from": "human", "value": "the elementary and high schools to get serious. Do you see the same issues that you discussed now at Harvard at MIT? We're here in Boston, so I have to talk about the great universities here in Boston. You've written about MIT. I'm a university I love. I'm a research scientist there. Do you see the same kind of issues there? Yes, I do. Do you remember, can you explain the case" }, { "from": "gpt", "value": "of Dorian Abbott Lecture that was canceled at MIT there? Yeah, well, you know, this is not the only, it's not the only incident. There have been incidents all around the country of academics, professors who have views that don't comport with the, as the great Lillian Hellman, another friend of my late wife, said they, she said she refused to cut her garments in order to fit the fashions of the day. Dorian Abbott didn't cut his suit to fit the fashions of the day in his intellectual suit. And so he was, this has happened at Princeton. This has happened at Harvard. This has happened at MIT. The great universities in the country have decided that the clash of ideas is not such a good idea because some people's feelings will be hurt. Well, this is, there was quite a revolt against it. Fire sounded the alarm. And then in the end, the universities were, I believe Abbott was invited to come back. I think he turned him down. He shouldn't have turned him down, but he did. And when the light is cast upon these situations, the universities back down because they're so embarrassed. And the newspapers, because newspapers depend on the First Amendment in order to exist, newspapers tend to give pretty good publicity to these cases of censorship." }, { "from": "human", "value": "So they grow the universities. Yes. So they really emphasize they catalyze the embarrassment. Yes. So is that one of the ways, is that the best way" }, { "from": "gpt", "value": "to fight all of this? Yes, yes." }, { "from": "human", "value": "Sunshine is the best disinfectant. You've written about MIT's connection to Jeffrey Epstein. Yes. He was well connected at MIT and at Harvard. What do you, what lessons do you draw? About human nature, about universities," }, { "from": "gpt", "value": "about all of this from the saga. Let me say this. I believe that universities, if somebody was, for example, donate to a university and donates on the requirement that the building be named after them. If the university is taking donations and the person is funding a building and wants to build a name after them, the building should be named after him, Hummer, or them. Harvard is facing, it's now, with the Sackler building, because the Sacklers had become now a persona non grata because of their role in producing the opioids that caused a huge scandalous opioid addiction. There are people who want to remove the name Sackler from the Sackler Art Museum in Harvard. Larry Bacow, the president of Harvard, to his credit, has refused to do that. If it reminds people that the money was earned through selling opioids, that's good. That's good that people understand that that's where the Sacklers got their money. They should be reminded. In my undergraduate alma mater, Princeton, there's a movement to remove the name Woodrow Wilson because Woodrow Wilson was president of Princeton before he became governor of New Jersey, before he became president of the United States. How he got to be governor of New Jersey was he was so insufferable that the trustees of Princeton got him the nomination to run for governor of New Jersey. They had said, we got to get this guy out of here. And not because he was anti-black and anti-Semitic, because the trustees were as well, but because he just was insufferable, he drove the faculty crazy and they got him out. So Princeton was thinking of changing the name. I wrote a letter to President Icekruber saying, this is part of the university's history. You want to rewrite history falsely? Woodrow Wilson was the president of this institution. He was one of your predecessors. He never answered me either. I think these people, they know they have no answer. The reason I didn't get a response from President Icekruber is the same as the reason I didn't get a response from the headmaster of Milton Academy. They understand that what they're doing is violative of the fundamental precepts of academic institutions. They're ashamed, they feel they have no choice because they feel that they would be criticized for racism, homophobia, blah, blah, blah, blah, blah. Criticized by how many people? Well, they feel that they would be criticized by students and parents and donors. I disagree with that. I actually think there are more people out there that agree with me than agree with them. Yeah, by a large margin. By a large margin in what I call the real world, which is the world outside the campus. But academics are afraid they'd be criticized. They're incredibly thin-skinned. When I say academics, I mean academic administrators. They're very thin-skinned, politically correct, wholly in the now. As I said, I would fire 95% of them and I would be more careful in who I elected to lead these institutions. So I said, Pauline Gay is probably going to be a disaster at Harvard." } ]

[ { "from": "human", "value": "So it takes guts, it takes courage to be in the administration when the task of protecting the freedom of speech is there and also, which in part requires you to admit and to uphold the mistakes you've done in the past. Correct. Not to hide them. Correct." }, { "from": "gpt", "value": "And that to you, I mean, Jeffrey Epstein for Harvard and for MIT is a very recent mistake, recent mistake. Well, there's a debate whether it's a mistake. They took money from him. Yes. Okay. Is it a mistake to take money from bad people? Do you have to do a morals test of a potential donor? I don't think so. It's complicated because if there are no conditions attached to it, I think it's emotionally complicated. I don't think that it is rationally complicated. It's emotionally complicated. It's particularly complicated if they want naming rights. The Jeffrey Epstein biological laboratory, that would be a problem for most universities. I don't think that naming rights have to be given to somebody that you don't think is worthy of having their name. I think that university has the right to say, no, we'll take your money, but we will not name the building after you." }, { "from": "human", "value": "I think they have a right to do that. There's some degree in which you whitewash the name, though, not with naming rights, but if you... You take the money? If you take the money, it allows the person in public discourse to say that they're collaborating," }, { "from": "gpt", "value": "they're working together with Harvard and with MIT. Well, I have a problem with universities making morals tests of donors because not every donor is as bad as Epstein, but some of the donors made their money in industry by being rapacious," }, { "from": "human", "value": "by paying low wages, by exploiting people. You can make the case that accepting money from the Department of Defense, from DARPA, from the United States organizations that contributed to waging war and killing hundreds of thousands of civilians over the past few decades, folks like the tenured professor Noam Chomsky will make the case that that is far more evil than accepting money from Jeffrey Epstein. Yes. Still, Jeffrey Epstein is a known pedophile." }, { "from": "gpt", "value": "Yes. So that's why I say I would not give him naming rights. I think the university has the autonomy to not give naming rights." }, { "from": "human", "value": "But I think that giving morals tests to donors is a Pandora's box. What do you think about the aftermath of the Jeffrey Epstein saga? It feels like, I'm not familiar with Harvard's response, but MIT's response seemed to fire a few scapegoats, and it didn't seem like a genuine response to the evils that human beings are capable of, sort of like rising to the surface, the description in a fully transparent way of all the interactions that happened with Jeffrey Epstein and what that means about the role of money in universities, what that means about just human beings in" }, { "from": "gpt", "value": "power. Money is essential to run a university. One of the reasons it's essential is because the university is artificially requires huge amounts of money, and that's partly because of the administrative army that they support, and they would be less dependent on the Jeffrey Epstein's of the world if they didn't have" }, { "from": "human", "value": "it, so it's sort of all part of the same circle. But there's a tension here, you're saying, we shouldn't be putting a morals test on money, but actually if you expand the amount of money needed to run the university, you're going" }, { "from": "gpt", "value": "to make less and less, more and more unethical decisions of accepting the money. Correct. And to say that, I am flexible enough to say that I don't think I would name a building after somebody who is truly evil. I think the university has the right to limit the naming rights for a donor. If I was an absolutist, I would not even say that, but I'm not an absolutist. I have my limits, and that's one of them." }, { "from": "human", "value": "The Jeffrey Epstein Biological Laboratory, it's a little bit much. It feels like there should be a requirement on, there should be moral requirements on who to accept money from. But the question is, the concern you have is about who gets to decide, and what's the" }, { "from": "gpt", "value": "alternative? Correct. I think there is no alternative. I think that turning down donation, because you don't approve of the conduct of the donor," }, { "from": "human", "value": "is a Pandora's box. But I'm just sickened by the fact that an evil human being was allowed to walk in the halls of a university I love." }, { "from": "gpt", "value": "So what do we do with that? Well, are you telling me that none of the students are evil? Are you telling me none of the faculty members are evil? Are you telling me none of the administrators are evil?" }, { "from": "human", "value": "But that doesn't... Sure, sure. So scapegoating, saying that Jeffrey Epstein is evil, can help us forget, can aid us in forgetting that there is other evil in the world, and some of it might be roaming still the halls of MIT and Harvard." }, { "from": "gpt", "value": "Hey, listen, I won't tell you the name, but I represented somebody in the MIT administration a few years ago, who was charged with sexual improprieties against students. And as a lawyer, I represented that person. People say, how could you represent, some of the people I represent are bad people. See, how can you represent them? I say, well, if I was a cardiologist and this person had a heart attack on the street and I didn't deliver CPR, I would have my license taken away. I'm a lawyer, the only difference between my obligation and the doctor's obligation is the Constitution gives people the right to assistance of counsel. They don't have, the Constitution says nothing about the assistance of cardiologists. I have a very high duty to represent unpopular people. Well, I think I apply the same test to college donors. The university should not have a morals test. Who's money to take? I do draw a line about naming rights of buildings. And as I say, that's an inconsistency with my absolutism. But I just, emotionally, I just can't deal with having, as I said, the Jeffrey Epstein Biological Laboratory." } ]

[ { "from": "human", "value": "Well, for me, emotionally, there's nothing that sickens me more in the university than the abuse of power." }, { "from": "gpt", "value": "Right." }, { "from": "human", "value": "And there's an awful lot of people who abuse power in the university. And especially when it comes to abuse power over students. So sexual harassment, so in the realm of sexual abuse of power and all kinds of other." }, { "from": "gpt", "value": "Well, it is a crime to use one's power position in order to take sexual advantage of a student. It's a crime." }, { "from": "human", "value": "This is not a close question. Yeah, but there's a legal crime and there's a deeply ethical crime and there's an emotional response that I have. You are a good lawyer and perhaps a good man to want to defend some folks who are evil in this world. I don't think I have that emotional fortitude. Well, then you shouldn't be a criminal defense lawyer or a cardiologist. I think you're right. I'm still deeply sickened by Jeffrey Epstein and the faculty, the administration that still might be in these great American universities that are abusing their power in small ways and big ways. But that's human nature. You get a little bit of power and you're a bad man or a bad woman and you take advantage of it. We see that in the smallest of ways and in the biggest of ways in institutions and regimes all across the world. Boy, Harvey, it's a complicated situation." }, { "from": "gpt", "value": "Well, it's a complicated world and it's complicated to be a human being and this is nothing new." }, { "from": "human", "value": "And we should talk about it without restriction. All right, just to linger on liberal arts, in 2014 and probably still today, you wrote that liberals are killing the liberal arts. Yes." }, { "from": "gpt", "value": "So can you explain? Yes, the problem with, I'm a political liberal. The problem with the political left is that it has divided between what's called progressives and liberals. Liberals are people of the left who believe in the First Amendment, an absolute First Amendment and in due process of law. And the problem with what progressives now, in the pursuit of equality, what they view as equality, they're willing to bend those rules. And this movement actually started in Brandeis, the critical race theory. It started Herbert Marcuse, who was a professor at Brandeis and he came up with his theory. The theory was this, this is right out of Orwell. In order to create true equality in a society where you have some downtrodden and some who are the Uber mentioned, in order to create real equality, you have to reduce the rights of the upper classes and artificially increase the rights of the lower classes. And that will produce, out of unequal treatment, true equality will be attained. This is nonsense. The idea of discrimination producing true equality is nonsense. My view is, as I've said earlier in our discussion, that the way to increase the opportunities for the lower classes is to give them real educations. And until we do that, it's not going to happen. And in order to do that, we have to overcome the problem of the teachers' unions at the elementary and secondary school levels. Until we're willing to do that, honestly, and then improve those schools, we're going to have a problem of a large number of uneducated people who need a boost because we haven't given them proper educations." }, { "from": "human", "value": "What do you think about some of the more controversial faculty in the world? So an example of somebody I've spoken with many times on mic and offline is Jordan Peterson. I'm not sure if you're familiar with his work. Yes. But he is an outspoken critic or proponent of free speech on campus and he's been attacked quite a bit. He's a controversial figure." }, { "from": "gpt", "value": "Which through all of the university to protect the Jordan Peterson's of the world? Yeah. I think the university has an absolute, absolute, not relative, not watery, absolute role, obligation to protect the academic freedom of even the most controversial faculty members. And you can imagine, on a university campus, you have more people who are outliers than you do in the general population. And that's the hope at least. Hopefully, yeah. And those outliers have to be protected. They can't be pressured, they can't be fired, they can't be disabled from spewing their views whether they're considered racist, whether they're considered to be, you know, promote an idea of human society that's considered obnoxious. It doesn't matter if you can't, if you can't have freedom of thought on the college campuses, where can you? You know, then we're lost as a society, we're lost. And as an educational institution, educational institutions no longer will educate, they will indoctrinate. That we have to avoid at all costs." }, { "from": "human", "value": "And we should also remember that the outlier might also be the only bearer of truth. So in Nazi Germany, speaking against the fascism, fascist regime, and communist Soviet Union" }, { "from": "gpt", "value": "speaking against communism, they might hold the key to solving the ailments of that society. Absolutely. And some of the most important discoveries in science, for example, were mocked at the" } ]

[ { "from": "human", "value": "beginning, think of poor Charlie Darwin. Charlie, I see he is on nickname levels with you. Well, because we're talking about these big topics of sexism, racism, and hate. You should not forget about the smaller topics which might even have the much bigger impact, which is what you're speaking to, which is outlier ideas in science. So basically, welcoming controversial ideas in science. And by controversial, I mean, just stuff that most of the community doesn't agree on, it doesn't actually harm anyone at all. But even then, there's always pressure. One of the things I'm really concerned about is how little power young faculty have. That there's a kind of hierarchy, seniority, that universities have, empowered by the administration. Where the young faculty that come in, they're kind of... Pre-tenure. Yeah. There's a process in chasing tenure where you're kind of supposed to behave. And there's an incentive to kind of fit in, and to not be an outcast. And that's a really huge problem, because oftentimes, the youth is when the craziest, the biggest ideas, the revolution ideas come. And if you're forced to behave, and fit in, and not speak out, then even in the realm" }, { "from": "gpt", "value": "of science, the innovation is stifled. Yeah." }, { "from": "human", "value": "Well, now you trigger my, having to tell you this story. You're triggered." }, { "from": "gpt", "value": "This is good. In the mid-1980s, I decided to take a four-month sabbatical from my law practice. Yes. Professor James Vorenburg, who was at the time Dean of the Harvard Law School, heard about it, heard about it from his wife, Elizabeth Betty Vorenburg, whom I was very friendly with, because we were both on the ACLU, the ACLU of Massachusetts Board at the time. And Betty told Jim that Harvey was taking a sabbatical. Jim called Harvey, and asked Harvey if he would like to teach a course at the Harvard Law School, because there was nobody who had teaching criminal law from the perspective of somebody who actually was in court, litigated. It was all theoretical. I said, sure, I'll do it. So I taught a semester at Harvard Law School. The student evaluations were fabulous. Why? Because it was really interesting. They were hearing a lawyer who was talking about real cases. I actually brought in a few of my clients to some of the classes. And so Jim called me and said, Harvey, the students love this course. I'd like to offer you a tenure-track position. At the law school, you'd have to give up your law practice. I turned him down. He said, did you just say no? I said, yes. I said, no. He said, how come? He says, nobody has ever, in my administration, has ever turned down a tenure-track offer at Harvard Law School. I said, because I could see that I'm not a good fit, that the administrators overrun the place, that faculty members, especially untenured, who are afraid to say things that might not help them in the tenure quest, it's not a good fit for me." }, { "from": "human", "value": "You saw this in the mid 1980s already." }, { "from": "gpt", "value": "Yes. 1980s already. Yes, 1985. And I went back to my law practice. I did not want to get into this me grind that I saw. After all, I started to see it before the turn of the century because I co-authored The Shadow University in 98 and then co-founded Fire in 99." }, { "from": "human", "value": "I'm an early student of this phenomenon." }, { "from": "gpt", "value": "What are some other aspects of the book The Shadow University that we may have not covered? Well, let me tell you a story. I believe I tell it in The Shadow University because it was part of- I'm loving these stories, Harry. The stories are fabulous. Let me tell you a story of- I did a tour of the country visiting campuses. I visited a college called Hamline University, I believe it was in Indiana or Illinois, somewhere in the Midwest, and I attended a freshman orientation. Now listen to this. This was a freshman orientation. The administrators, the deans and the deenets and the deputy assistant deans and deenets and the third deputy assistant deans and deenets lined the students up according to their skin hues. The blonde, blue-eyed white folks were at one end, darkest African Americans whose blood lines had not yet mixed with any of the whites on the other end. The exercise was you had to tell how your race affected your success in life up until that point. I thought it was the most demeaning thing that Y could imagine. Demeaning. I thought to myself, they could do the same about sexual orientation, they could do the same about religion, they could do the same about national origin. it would be demeaning no matter what. And the students actually verbalized how their race had either been a plus or a minus. They did. They did. And I thought it was so demeaning, it just confirmed all of my distaste" }, { "from": "human", "value": "for this kind of approach. Let me ask you from the interviewer seat. So I get to do this podcast and I often have to think about giving a large platform and having a conversation with very controversial figures. And the level of controversy has been slowly increasing. What's the role of this medium to you? This medium of speech between two people and me speaking with a controversial figure, me or some other interviewer. What's the role of giving platform to controversial figures? Same members of the KKK or dictators," }, { "from": "gpt", "value": "people who are seen as evil. Well, we want to face the world with reality. And the reality is that there are some unpleasantness in the world, running from genocide right through to ordinary discrimination, to offensiveness. It's the real world as we know it exists. Are we afraid to say it? Do we want to make people think that we live in a world where those words are not used, where those animosities don't exist?" } ]

[ { "from": "human", "value": "The answer is no. But you can whitewash, you can normalize the use of those words and you can whitewash the acceptability of certain leaders. So for example, interviewing Hitler in 1938, 1935, 1936, 1937, 38, those are all different dynamics there. But you can normalize this person" }, { "from": "gpt", "value": "and in so doing create enormous harm. Well, see, I don't see it as normalizing. I see it as exposing. If more people had taken Monckham seriously, Franklin Roosevelt would have acted much sooner. He only got us into the war, as Congress gets into the war, when the Japanese made the mistake of attacking Pearl Harbor. But there were some people in the State Department, there were some people in the administration who were trying, trying to get Roosevelt, see what Hitler was really like and he was blind to it. And this was one of the greatest presidents of the United States ever had. He was blind to it until the Japanese attacked Pearl Harbor. So I think that words, unpleasant ideas as expressed by words are essential for communicating fact and truth and reality. And that's why I think that we should not whitewash language. We should not whitewash the fact that Jeffrey Epstein was pretty close to MIT. And Harvard. And Harvard. And your reality, reality actually means something." }, { "from": "human", "value": "Yeah, but from the role of the interviewer, that's something I have to think a lot about. Whether interviewing Hitler, you said exposing. I think it's hard to know what Hitler's like in a room, but it's also hard to know, I've never met Jeffrey Epstein, it's hard to know what Jeffrey Epstein is like in a room. But I imagine to some degree they're charismatic figures. So exposing them in the interview setting" }, { "from": "gpt", "value": "is not an easy task. Well, interviewing is not an easy job. Yeah. It's not a good idea to have an interview would be an idiot." }, { "from": "human", "value": "All right. I know exactly what you're saying and I know why you're looking at me directly as you say it. I appreciate that, Harvey. All right, let me ask about your friend, your colleague, Alan Dershowitz. And I'll also ask about your review of his most recent book, but before then, it'd be interesting to ask what you think of him as a human being, as a lawyer. He's quite an interesting case. He's represented some of the most controversial figures in history. Including Jeffrey Epstein. Including Jeffrey Epstein, Mike Tyson, Julian Assange, Jim Baker, and Jeffrey Epstein, and even Donald Trump. So he's an interesting figure. What do you think about that?" }, { "from": "gpt", "value": "Clarence Vambulo." }, { "from": "human", "value": "He's in history. What do you think? What do you think about him as a human being, as a lawyer, what he represents" }, { "from": "gpt", "value": "in terms of values and ideals? Well, he's a criminal defense lawyer. And the job of a criminal defense lawyer is to represent accused criminals. He is a lifelong Democrat. He didn't represent Trump because he agrees with him politically. Voted for Hillary, I believe you wrote. He voted for Hillary, yes. That's what he says, and I absolutely believe it. He's a liberal Democrat. But he's a criminal defense lawyer, as well as a professor. And I've represented some very nasty people in my career. I wouldn't go out for coffee with them, but they have constitutional rights to representation. And you take that very seriously. Yes, you notice something that people don't understand about Dershowitz. You take that. He's asked by Trump to represent him in the second impeachment, as well. He turned him down." }, { "from": "human", "value": "Why do you think he turned down? People said, no, he represented Trump in the first impeachment trial..." }, { "from": "gpt", "value": "He represented him only in the first. And it was successful, and when Trump has impeached him the second time, he asks Alan to represent him? Alan has had a life-long policy of only representing somebody once, never twice. Why? Because he never wanted to be a House Council to the mafia. And so he, early on, had this position. He only represents somebody once. The mafia wants a lawyer who's an in-house counsel who represents them in all their cases. So that's the reason. And now I never publicly explained it. I know it's a fact, because I've known him from the day that we met at Harvard Law School, 1964. He was a first year professor. I was a first year student. We both had Brooklyn accents and we hit it off." }, { "from": "human", "value": "We've been close friends ever since. So there's some kind of unethical line that's crossed when you continuously represent a client," }, { "from": "gpt", "value": "continuously represent a- Yeah, he thought it was not so much an ethical line. You have a right to represent mafia people, but he didn't want to be house counsel. He didn't want to be, you know, have them ask him for advice in advance of what they were doing. He was willing to represent somebody once, no matter how awful. Klaus von Bülow was accused of killing his wife. These are pretty nasty people," }, { "from": "human", "value": "but he didn't want to be house counsel to any of them. So you wrote a review of Alan Dershowitz's new book on Donald Trump. The title of that book is Get Trump, The Threat to Civil Liberties Due Process and Our Constitutional Rule of Law." }, { "from": "gpt", "value": "Can you summarize this book and your review of it? Yes, yes. By the way, I co-authored it with my research assistant who's sitting right here. Emily." }, { "from": "human", "value": "Yes, and-" }, { "from": "gpt", "value": "Emily. I thought that the book was another example of the fact that everybody is entitled to a defense and that Alan's being involved with Trump was purely professional. It was not political. It was not philosophical. And I thought that the fact that he was being criticized, he was being shunned because of his connection to Trump. I found very interesting that this is a guy who represented such, I call them distasteful figures as Klaus von Bülow, as Mike Tyson, as OJ Simpson, as Sheldon Siegel. And when he was considered to be a skillful lawyer, made his reputation. And then he represents Donald Trump who, to my knowledge, never killed anybody. And he's suddenly shunned. I thought the hypocrisy of it, the political preening, was very distasteful to me. And it was not only because he was my friend. If he wasn't my friend, I think I'd have the same view. The holier-than-thou nonsense, the hypocrisy of it. They wouldn't talk to him all this being, though. Alan and I are different. I'm not so sensitive. Someone doesn't want to talk to me. No problem, no problem at all. But Alan is considering how controversial his life has been. He's somewhat sensitive. He's somewhat sensitive." } ]

[ { "from": "human", "value": "And I kept telling Alan, Alan, don't let it get to you. Hey, I can relate. I can definitely relate. Taking on some controversial conversations, still where my heart or my sleeve, it hurts. All of it hurts. But maybe the pain makes you a better student of human nature. Maybe that's the case for him. Nevertheless, the book makes a complicated, and I think an interesting point. He opens the book with, not that Donald Trump has announced his candidacy for re-election as president, the unremitting efforts by his political opponents to, quote, get him, to stop him from running at any cost will only increase. These efforts may pose the most significant threat to civil liberty since McCarthyism. So is he right?" }, { "from": "gpt", "value": "He's absolutely right. Because these attempted, for example, the prosecution, the one prosecution that has been brought now with Alvin Bragg in the Manhattan, I have looked at that, and I don't believe that Trump has committed a crime. And yet, Bragg was pressured to bring that. People in his office were threatening to quit if he didn't indict. Holy improper, holy unethical, and he's gonna lose the case. Has Trump committed crimes? Yes, most of their tax crimes. He has cheated on taxes his whole career, as far as I can tell. He could easily be indicted for state and federal taxes, but they're not as sexy. And I think that he's become a target by ambitious politicians, ambitious prosecutors. He has gotten some sympathy, which he doesn't deserve. And a lot of it is, pardon the phrase, political correctness. The better people are not supposed to be Trumpers. I had an interesting experience about Trump. I had two interesting experiences. The more recent one was I was in the house of Lauren Summers, the former president of Harvard, who was driven out by political correctness, by the way. He insulted women biologists. I was in his house when he was still president of Harvard, when the Trump, Hillary Clinton contest took place. And I was with Elsa, we were invited to Summers' house in Brookline, and it looked like Hillary was gonna win, Hillary was gonna win, and the Harvard faculty members, they were all celebrating, they were all figuring out what their cabinet positions were gonna be, blah, blah, blah, blah, blah. And then about 1130 at night, all of a sudden, it was announced that in terms of electoral votes, Trump had just eked out of victory, that Hillary beat him in the popular vote, but he had won the electoral college," }, { "from": "human", "value": "and there was a media depression, and that was- Meaning it was like quiet over the room." }, { "from": "gpt", "value": "The room was absolutely stone silent, and they were all disappointed. Well, that was a memorable moment, and it told me that they were a little bit too overconfident. They were savoring, being part of a presidential administration, ambition had been thwarted. I'm not a great fan of preening ambition. I think it blinds people to realities." }, { "from": "human", "value": "And the resulting arrogance from such ambition." }, { "from": "gpt", "value": "And the arrogance, yes. It's one of the reasons I didn't accept Jim Vornberg's offer to be part of the academic community. I mean, I represent professors, I have friends who are professors, I represent students, I have friends who are students, and I have a great regard for universities and higher education, but I was not about to become part of the culture. I thought that it was not good for me," }, { "from": "human", "value": "and not good for the institution either. That can, a culture that can breed arrogance. Yes. Self-importance. Yep. And in a sense, the election of Donald Trump" }, { "from": "gpt", "value": "was a big FU to such importance. Correct. Such arrogance. And I think he, why I think he managed to pull it off." }, { "from": "human", "value": "To jump topics a little bit. What do you think about something you've written about? What do you think about the mass surveillance programs by the NSA, and also probably by other organizations, CIA, FBI, and others? And broadly, what do you think about the importance of privacy for the American citizen?" }, { "from": "gpt", "value": "Okay, I believe that the FBI should be abolished, because I believe that its culture was so corrupted by its first director, John Edgar Hoover, J. Edgar Hoover, that it is impossible to reform the FBI to make its agents honest, to force them to obey the Constitution, the First, Fourth, and Fifth Amendments especially. And it's a culture that cannot be changed. Hoover established the culture, and no FBI director since has been able to change it. If you go online, I did on YouTube a video for the ACLU of Massachusetts. It was when I was on the board. It was probably when I was president of the board. I was president of the board for two years. I was on the board for 20 years, and I did a video about advising people to never, ever, ever talk to an FBI agent" }, { "from": "human", "value": "when they come knocking on your door. Can you briefly explain the intuition? Yes." }, { "from": "gpt", "value": "Why not to talk to an FBI agent? Yes, they have a system. When they come in and interview you, two agents show up, never one. One asks the question, the other one takes notes. The note-taking agent takes notes, and it goes back to the office and types up a report called a Form 302, which is the official record of what was asked and answered. So when I have a client interviewed by the FBI, I show up, and I always agree, I almost always agree to the interview, but I bring a tape recorder, and I say, all right, I'm gonna tape this. And they say, well, by regulation, we're not allowed to do the interview if it's taped. The record is the 302, the agent's taking notes. I say, well, I have a policy, too. My policy is to never allow a client to be interviewed unless it's recorded. So it's unfortunate, but we're gonna have to end this meeting, and the agents get up and leave. And I've never seen a Form 302 that I consider to be accurate. The agents write down what they wish you had said, rather than what you said. It is a wholly corrupt organization" } ]

[ { "from": "human", "value": "that has not gotten any better since Hoover died. And fundamentally, the corruption is in the culture that is resisting the Constitution of the United States, the first and fourth and fifth amendments." }, { "from": "gpt", "value": "Correct, it's not financial corruption. It is corruption of the mission, and I think it should be abolished. And if we need a federal investigative agency, it should be a new name, a new culture, wholly new members, a new director, and it's impossible to reform the FBI." }, { "from": "human", "value": "Can you elaborate on what exactly is broken about the FBI? Is it the famous saying from Stalin's KGB head, Barry, show me the man and I'll show you the crime? Right." }, { "from": "gpt", "value": "Is it that kind of process? It's that kind of process. They decide who's guilty, and then they go about concocting a case" }, { "from": "human", "value": "against the person who they want to get." }, { "from": "gpt", "value": "So the goal is not to find the truth, or? It's to solve the case and close it" }, { "from": "human", "value": "in intensive reputations. But to show that an innocent man is guilty is also solving the case, from their perspective. So to falsely convict, or falsely imprison" }, { "from": "gpt", "value": "an innocent man is also solving the case. Well, it closes the case if they falsely imprison an innocent man." }, { "from": "human", "value": "They're interested in closing cases. So that's the FBI, but broadly speaking about the surveillance aspect of this, what are your views on the right" }, { "from": "gpt", "value": "that an American citizen has to privacy? Well, wiretapping and electronic surveillance are very, very intrusive. And I think that the circumstance that these tools are used should be narrowed. For example, they're used in a lot of drug cases. Since I don't think drugs should be illegal in any event, I certainly think that it's a terrible violation of privacy to use wiretapping in a drug case. I could see it in cases of murder, possibly in cases of serious extortion, but on other kinds of crimes where they wiretap, especially drug cases, I believe drugs should all be legalized anyway. I think the price we pay as a society is not worth it." }, { "from": "human", "value": "There's on the Wikipedia page for nothing to hide, you're cited. In fact, your book that you gave me today, Three Felonies a Day is cited. So nothing to hide argument. That's an argument that if you're a well-behaved citizen, you have nothing to hide and therefore your privacy can be violated." }, { "from": "gpt", "value": "Well, the problem is that under the federal criminal code, particularly the federal criminal code, it is very easy to be charged with a crime. Now why? Under the constitution, the federal government does not have plenary criminal jurisdiction. That's up to the state. How is it that the feds indict in so many areas of American life? It's because the Supreme Court has allowed the following absolutely insane situation to prevail. Anything can be made a federal crime if in the course of the commission of the crime, the means of interstate communication or travel are used. That means that if you commit a crime, which ordinarily would be a state crime, and you use the telephone or you send a letter, it suddenly becomes federal. That means that the limitation that the founding fathers who wrote the constitution intended to keep the feds out of daily life and to give that jurisdiction to the state has been completely thwarted. Because I can't think of a case where somebody doesn't use the telephone in the course of planning, discussing something that's arguably criminal. And so this limited authority, the federal government, to bring charges in criminal cases is illusory." }, { "from": "human", "value": "Feds can indict a ham sandwich. So basically everybody's guilty. And if the feds wanna bring you in," }, { "from": "gpt", "value": "they can, they can find a way, they can find a way." }, { "from": "human", "value": "And that allows them to terrorize people who are dissidents. Yeah. What is broken, what works about the American criminal justice system from your perspective from all- The jury system. The jury system. Yes. You like the jury system. I like it. Everyday citizens representing-" }, { "from": "gpt", "value": "12th the jury. Everyday citizens- I like that both ordinary people" }, { "from": "human", "value": "have to agree unanimously in order to convict. What do you think about the highest court in the land, the Supreme Court? What works and what is broken about the Supreme Court as an institution?" }, { "from": "gpt", "value": "What are its strengths and weaknesses? The Supreme Court is unfortunately fairly political. And the current Supreme Court is overruling precedents, which it's really improper. Imprecedents should not be overruled so easily. It's about to overrule affirmative action. Now I'm opposed to affirmative action. I think I made that clear earlier in our discussion, but still it's a precedent and it should be given some respect. But in order to propagate a more conservative agenda, the court is treating precedent as if it doesn't have any role. And that's a huge mistake. Some of the congressmen on the Democratic side are looking to enlarge the court in order to basically do what Franklin Roosevelt was not able to do. And that has changed the court's philosophy. But I think that's very short-sighted because this is a long game. This is a republic we have here. And anyone who tries to, for example, enlarge the court from nine to 12 in order to get more liberals on the court, then some other administration will try to enlarge it from 12 to 15 to get more liberals on the court. You'd have a constant fiddling" }, { "from": "human", "value": "with a very important institution. So the law should have more lasting power than the political bickering of the day. Correct. Let me ask you, you've lived one heck of a life. And fought a lot of battles and you continue to do so with the Harvard Board of Overseers. So first of all, thank you for that. But the day, we're all human, we're all mortal. Do you ponder your death? Do you ponder your mortality?" }, { "from": "gpt", "value": "Are you afraid of it? Well, let me say this. My father died at 48. He died because he smoked, he died at 48 because he smoked four packs of camels a day. He got a massive heart attack at 43. He continued to smoke despite that he died at 48. So I did not expect to live this long because I thought it was genetic. It turns out it was cigarettes. So here I am, I'm gonna be 81 on May 10th. I was born on May 10th, 1942, which was Mother's Day coincidentally. And I realize I'm not gonna live forever. I also take pride in the fact that I have demonstrated that a lawyer does not have to go with a law firm in order to manage to make it. You can make your own, write your own, what's the word, write your own ticket in order to. I've done that. I agree that I've had an elite education. I went to Princeton and Harvard Law School, but I don't think you have to necessarily go to elite institutions in order to really make it. You need to work hard. But you shouldn't put yourself in a place where you're not gonna feel comfortable and what's the word, empowered. Like I was used to take Jevor and Berg's invitation for tell your track physician at Harvard Law School. I'll tell you one other story that illustrates this. I was originally pre-med. My freshman, sophomore year at Princeton, I was in the pre-med program. Why? Because my parents wanted me to marry the daughter of our family physician. And the idea was I was to go to medical school. I was gonna go into medical practice with him in Hackensack, New Jersey. We had moved from Brooklyn at the time. Long story why we had to move from Brooklyn, had to do with my father's, having a problem with the Furrier's Union and having his life threatened. And we moved to Maywood, New Jersey because he got a job in a fur shop in Busaic, New Jersey. And a family physician, they had three daughters, the oldest of whom was my age. She went to Hackensack High School. I went to Bogota High School. They're both in North Bergen County. And the idea was that she and I were gonna marry. I was gonna become, I was gonna go to medical school. I was going to take, become a partner of her father in his medical practice in Hackensack. When he retired, I was gonna inherit the practice. This scenario was concocted by Carolyn's mother and my mother. In my sophomore year at Princeton, I won a fellowship to spend that summer between my sophomore and junior year in Paris. I was fluent by then. I had taken the accelerated French course, my freshman and sophomore year, and I went to Paris. It was my first time out of the country. And I spent the entire summer working, supporting myself, participating in the airfare, and I earned money for room and board. And I thought about my life and I decided, number one, I didn't wanna be a physician, I wanted to be a lawyer. Number two, I didn't wanna marry Carolyn. And I came back, I changed from pre-med to pre-law. I broke up with Carolyn, who is by that time, school at Douglas, right down the road from Princeton, she had followed me, or I had followed her. And my life suddenly took a wholly different term. So that summer in Paris, Paris had a outsized effect of my life. Every year, the Bravo Theater shows Casablanca, where Bogart has this great line, he says, we'll always have Paris. And I think to myself, I always used to say to Elsa, we used to see Casablanca every Valentine's Day, because it was such an important movie to me, because Paris was transformative in my life. And we went to Paris every year during my vacation, we went to Paris. That was where she took some great pictures of Isaac, and he's this high and this high, they were hanging up in the house. And so I always, even after Elsa's death, I've seen Casablanca twice now, she died in 2020. And I always think we'll always have Paris." } ]

[ { "from": "human", "value": "We'll always have Paris. Well, Harvey, like I said, I hope you're very successful in your run for the Harvard Board of Overseers. I think what you stand for in the realm of freedom of speech is I think the thing that makes these universities great institutions in American culture. And I'll do everything I can to help you succeed. And I'm really grateful for all the work you've done, and I'm grateful that you would talk with me today. This was amazing. Thank you. Thanks for listening to this conversation with Harvey Silverglate. To support this podcast, please check out our sponsors in the description. And now, let me leave you with some words from Harry S. Truman. Once the government is committed to the principle of silencing the voice of the opposition, it is only one way to go. And that is down the path of increasingly repressive measures until it becomes the source of terror to all its citizens and creates a country where everyone lives in fear. Thank you for listening, and hope to see you next time." } ]

[ { "from": "human", "value": "What are the key differences from the high philosophical level, maybe the technical level between the capabilities of broadly speaking the two kinds of systems, large language models and this computational, gigantic computational system infrastructure that is Wolfram Alpha?" }, { "from": "gpt", "value": "Yeah. So what does something like Chad GPT do? It's mostly focused on make language like the language that humans have made and put on the web and so on. So it's primary underlying technical thing is you've given a prompt. It's trying to continue that prompt in a way that's somehow typical of what it's seen based on a trillion words of text that humans have written on the web. And the way it's doing that is with something which is probably quite similar to the way we humans do the first stages of that using a neural net and so on. And just saying, given this piece of text, let's ripple through the neural net one word and get one word at a time of output. And it's kind of a shallow computation on a large amount of kind of training data that is what we humans have put on the web. That's a different thing from sort of the computational stack that I spent the last, I don't know, 40 years or so building, which has to do with what can you compute many steps, potentially a very deep computation. It's not sort of taking the statistics of what we humans have produced and trying to continue things based on that statistics. Instead, it's trying to take kind of the formal structure that we've created in our civilization, whether it's from mathematics or whether it's from kind of systematic knowledge of all kinds, and use that to do arbitrarily deep computations to figure out things that aren't just let's match what's already been kind of said on the web, but let's potentially be able to compute something new and different that's never been computed before. So as a practical matter, our goal is to have made as much as possible of the world computable in the sense that if there's a question that in principle is answerable from some sort of expert knowledge that's been accumulated, we can compute the answer to that question and we can do it in a sort of reliable way that's the best one can do given what the expertise that our civilization has accumulated. It's a much more sort of labor intensive on the side of kind of creating kind of the computational system to do that. Obviously, in the kind of the chat GPT world, it's like take things which were produced for quite other purposes, namely all the things we've written out on the web and so on, and sort of forage from that things which are like what's been written on the web. So I think as a practical point of view, I view sort of the chat GPT thing as being wide and shallow, and what we're trying to do with sort of building out computation as being this sort of deep, also broad, but most importantly kind of deep type of thing. I think another way to think about this is you go back in human history, I don't know, a thousand years or something, and you say, what's the typical person going to figure out? Well, the answer is there's certain kinds of things that we humans can quickly figure out. That's sort of what our neural architecture and the kinds of things we learn in our lives let us do. But then there's this whole layer of kind of formalization that got developed, which is the kind of whole sort of story of intellectual history and the whole kind of depth of learning. That formalization turned into things like logic, mathematics, science, and so on. And that's the kind of thing that allows one to kind of build these towers of sort of towers of things you work out. It's not just, I can immediately figure this out. It's no, I can use this kind of formalism to go step by step and work out something, which was not immediately obvious to me. And that's kind of the story of what we're trying to do computationally is to be able to build those kind of tall towers of what implies what, implies what, and so on, and as opposed to kind of the, yes, I can immediately figure it out. It's just like what I saw somewhere else in something that I heard or remembered or something" }, { "from": "human", "value": "like this. What can you say about the kind of formal structure, the kind of formal foundation you can build such a formal structure on, about the kinds of things you would start on in" }, { "from": "gpt", "value": "order to build this kind of deep computable knowledge trees? So the question is sort of how do you think about computation? And there's a couple of points here. One is what computation intrinsically is like, and the other is what aspects of computation we humans with our minds and with the kinds of things we've learned can sort of relate to in that computational universe. So if we start on the kind of what can computation be like, it's something I've spent some big chunk of my life studying is, imagine that you're, you know, we usually write programs where we kind of know what we want the program to do and we carefully write many lines of code and we hope that the program does what we intended it to do. But the thing I've been interested in is if you just look at the kind of natural science of programs, you just say, I'm going to make this program, it's a really tiny program. Maybe I even pick the pieces of the program at random, but it's really tiny. By really tiny, I mean, you know, less than a line of code type thing. You say, what does this program do? And you run it. And big discovery that I made in the early eighties is that even extremely simple programs, when you run them, can do really complicated things. Really surprised me. It took me several years to kind of realize that that was a thing, so to speak. But that realization that even very simple programs can do incredibly complicated things that we very much don't expect that discovery. I mean, I realize that that's very much, I think, how nature works. That is, nature has simple rules but yet does all sorts of complicated things that we might not expect. You know, a big thing of the last few years has been understanding that that's how the whole universe and physics works but that's a quite separate topic. But so there's this whole world of programs and what they do and very rich, sophisticated things that these programs can do, but when we look at many of these programs, we look at them. kind of, I don't really know what that's doing, it's not a very human, kind of thing. So on the one hand, we have sort of what's possible in the computational universe. On the other hand, we have the kinds of things that we humans think about, the kinds of things that are developed in, kind of, our intellectual history. And that's, and really, the challenge to sort of making things computational is to connect what's computationally possible out in the computational universe with the things that we humans, sort of, typically think about with our minds. Now, that's a complicated kind of moving target because the things that we think about change over time. We've learned more stuff, we've invented mathematics, we've invented various kinds of ideas and structures and so on. So it's gradually expanding, we're kind of gradually colonizing more and more of this kind of intellectual space of possibilities. But the real thing, the real challenge is how do you take what is computationally possible, how do you take, how do you encapsulate the kinds of things that we think about in a way that kind of plugs into what's computationally possible? And actually, the big sort of idea there is this idea of kind of symbolic programming, symbolic representations of things. And so the question is, when you look at sort of everything in the world, and you take some visual scene or something you're looking at, and you say, well, how do I turn that into something where I can kind of stuff into my mind? mind.\" There are lots of pixels in my visual scene, but the things that I remembered from that visual scene are there's a chair in this place. It's a symbolic representation of the visual scene. There are two chairs and a table or something, rather than there are all these pixels arranged in all these detailed ways. The question then is, how do you take all the things in the world and make some kind of representation that corresponds to the types of ways that we think about things? human language is sort of one form of representation that we have. We talk about chairs. That's a word in human language and so on. How do we take… But human language is not in and of itself something that plugs in very well to sort of computation. It's not something from which you can immediately compute consequences and so on. And so you have to kind of find a way to take sort of the stuff we understand from human language and make it more precise. And that's really the story of symbolic programming. And what that turns into is something which I didn't know at the time it was going to work as well as it has. But back in 1979 or so, I was trying to build my first big computer system and trying to figure out how should I represent computations at a high level. And I kind of invented this idea of using kind of symbolic expressions structured as it's kind of like a function and a bunch of arguments. But that function doesn't necessarily evaluate to anything. It's just a thing that sits there representing a structure. And so building up that structure and it's turned out that structure has been extremely… It's a good match for the way that we humans… It seems to be a good match for the way that we humans kind of conceptualize higher level things. And it's been for the last, I don't know, 45 years or something. It's served me remarkably well." } ]

[ { "from": "human", "value": "So building up that structure using this kind of symbolic representation. But what can you say about abstractions here? Because you could just start with your physics project. You could start at a hypergraph at a very, very low level and build up everything from there, but you don't. You take shortcuts. You take the highest level of abstraction, convert the kind of abstraction that's convertible to something computable using symbolic representation. And then that's your new foundation for that little piece of knowledge and somehow all of that is integrated." }, { "from": "gpt", "value": "Right. So this sort of a very important phenomenon that is kind of a thing that I've sort of realized is just it's one of these things that sort of in the future of kind of everything is going to become more and more important as this phenomenon of computational irreducibility. And the question is, if you know the rules for something, you have a program, you're going to run it, you might say, I know the rules. Great. I know everything about what's going to happen. Well, in principle, you do because you can just run those rules out and just see what they do. You might run them a million steps, you see what happens, et cetera. The question is, can you immediately jump ahead and say, I know what's going to happen after a million steps and the answer is 13 or something. And one of the very critical things to realize is if you could reduce that computation, there isn't a sense, no point in doing the computation. The place where you really get value out of doing computation is when you had to do the computation to find out the answer. But this phenomenon that you have to do the computation to find out the answer, this phenomenon of computational irreducibility, seems to be tremendously important for thinking about lots of kinds of things. So one of the things that happens is, okay, you've got a model of the universe at the low level in terms of atoms of space and hypergraphs and rewriting hypergraphs and so on. And it's happening 10 to the 100 times every second, let's say. Well, you say, great, then we've nailed it. We know how the universe works. Well, the problem is the universe can figure out what it's going to do. It does those 10 to the 100 steps but for us to work out what it's going to do, we have no way to reduce that computation. The only way to do the computation, to see the result of the computation, is to do it. And if we're operating within the universe, there's no opportunity to do that because the universe is doing it as fast as the universe can do it and that's what's happening. So what we're trying to do, and a lot of the story of science and a lot of other kinds of things, is finding pockets of reducibility. That is, you could have a situation where everything in the world is full of computational reducibility. We never know what's going to happen next. The only way we can figure out what's going to happen next is just let the system run and see what happens. So in a sense, the story of most kinds of science, inventions, a lot of kinds of things, is the story of finding these places where we can locally jump ahead. And one of the features of computational reducibility is, there are always pockets of reducibility. There are always an infinite number of places where you can jump ahead. There's no way where you can jump completely ahead, but there are little patches, little places where you can jump ahead a bit, and I think we can talk about physics project and so on, but I think the thing we realize is, we kind of exist in a slice of all the possible computational irreducibility in the universe. We exist in a slice where there's a reasonable amount of predictability. And in a sense, as we try and construct these kind of higher levels of abstraction, symbolic representations, and so on, what we're doing is we're finding these lumps of reducibility that we can kind of attach ourselves to, and about which we can kind of have fairly simple narrative things to say. Because in principle, you know, I say, what's going to happen in the next few seconds? You know, oh, there are these molecules moving around in the air in this room. And oh, gosh, it's an incredibly complicated story. And that's a whole computational irreducible thing, most of which I don't care about. And most of it is, well, you know, the air is still going to be here, and nothing much is going to be different about it. And that's a kind of reducible fact about what is ultimately at an underlying level of computational irreducible" }, { "from": "human", "value": "process. Yes. And life would not be possible if we didn't have a large number of such reducible pockets. Yes. Pockets amenable to reduction into something symbolic." }, { "from": "gpt", "value": "Yes, I think so. I mean, life in the way that we experience it, that, I mean, you know, one might, you know, depending on what we mean by life, so to speak, the experience that we have of sort of consistent things happening in the world, the idea of space, for example, where there's, you know, we can just say, you're here, you move there. It's kind of the same thing. It's still you in that different place, even though you're made of different atoms of space and so on. This is this idea that it's that there's sort of this level of predictability of what's going on. That's us finding a slice of reducibility in what is underneath this computationally irreducible kind of system. And I think that's sort of the thing, which is actually my favorite discovery of the last few years is the realization that it is sort of the interaction between this sort of underlying computational irreducibility and our nature as kind of observers who sort of have to key into computational reducibility. That fact leads to the main laws of physics that we discovered in the 20th century. So this is, we talked about this in more detail, but this is, to me, it's kind of our nature as observers, the fact that we are computationally bounded observers, we don't get to follow all those little pieces of computational irreducibility to stuff what is out there in the world into our minds requires that we are looking at things that are reducible, we are compressing, kind of we're extracting just some essence, some kind of symbolic essence of what's the detail of what's going on in the world, that together with one other condition that at first seems sort of trivial, but isn't, which is that we believe we are persistent in time. That is, you know, so that's the causality. Here's the thing, at every moment, according to our theory, we're made of different atoms of space. At every moment, sort of the microscopic detail of what the universe is made of is being rewritten. And that's and in fact, the very fact that there's coherence between different parts of space is a consequence of the fact that there are all these little processes going on, the kind of knit together, the structure of space. It's kind of like if you wanted to have a fluid with a bunch of molecules in it, if those molecules weren't interacting, you wouldn't have this fluid that would pour and do all these kinds of things. It would just be sort of a free floating collection of molecules. So similarly it is with space that the fact that space is kind of knitted together as a consequence of all this activity in space. And the fact that kind of what we consist of, sort of this series of, you know, we're continually being rewritten. And the question is, why is it the case that we think of ourselves as being the same us through time? That's kind of a key assumption. I think it's a key aspect of what we see as sort of our consciousness, so to speak, is that we have this kind of consistent thread of experience." } ]

[ { "from": "human", "value": "What is some sort of causality? Isn't that just another limitation of our mind that we want to reduce reality into some, that kind of temporal consistency is just a nice narrative to tell" }, { "from": "gpt", "value": "ourselves? Well, the fact is, I think it's critical to the way we humans typically operate is that we have this single thread of experience. You know, if you imagine a mind where you have, you know, maybe that's what's happening in various kinds of minds that aren't working the same way other minds work is that you're splitting into multiple threads of experience. It's also something where, when you look at, I don't know, quantum mechanics, for example, in the insides of quantum mechanics, it's splitting into many threads of experience. But in order for us humans to interact with it, you have to have to knit all those different threads together so that we say, oh yeah, a definite thing happened, and now the next definite thing happens, and so on. And I think inside, it's interesting to try and imagine what's it like to have these fundamentally multiple threads of experience going on. I mean, right now, different human minds have different threads of experience. We just have a bunch of minds that are interacting with each other, but we don't have a ... Within each mind, there's a single thread, and that is indeed a simplification. I think it's a thing, the general computational system does not have that simplification. And it's one of the things people often seem to think that consciousness is the highest level of things that can happen in the universe, so to speak. But I think that's not true. I think it's actually a specialization in which, among other things, you have this idea of a single thread of experience, which is not a general feature of anything that could kind of computationally happen in the universe." }, { "from": "human", "value": "So it's a feature of a computationally limited system that's only able to observe reducible pockets. So I mean, this word observer, it means something in quantum mechanics, it means something in a lot of places. It means something to us humans as conscious beings. So what's the importance of the observer? What is the observer? What's the importance of the" }, { "from": "gpt", "value": "observer in the computational universe? Yeah. So this question of what is an observer, what's the general idea of an observer, that's actually one of my next projects, which got somewhat derailed by the current sort of AI mania." }, { "from": "human", "value": "But- Is there a connection there? Or do you think the observer is primarily a physics phenomena?" }, { "from": "gpt", "value": "Is it related to the whole AI thing? Yes, it is. What is a general observer? We know we have an idea what is a general computational system, we think about Turing machines, we think about other models of computation. There's a question, what is a general model of an observer. There's kind of observers like us, which is kind of the observers we're interested in. We could imagine an alien observer that deals with computational irreducibility and it a mind that's utterly different from ours and completely incoherent with what we're like. But the fact is that if we are talking about observers like us, one of the key things is this idea of taking all the detail of the world and being able to stuff it into a mind, being able to take all the detail and extract out of it a smaller set of degrees of freedom, a smaller number of elements that will sort of fit in our minds. And I think this question, so I've been interested in trying to characterize what is the general observer. And the general observer is, I think, in part, there are many ... let me give an example of a ... you have a gas, it's got a bunch of molecules bouncing around, and the thing you're measuring about the gas is its pressure. And the only thing you as an observer care about is pressure. And that means you have a piston on the side of this box and the piston is being pushed by the gas and there are many, many different ways that molecules can hit that piston, but all that matters is the kind of aggregate of all those molecular impacts because that's what determines pressure. So there's a huge number of different configurations of the gas, which are all equivalent. So I think one key aspect of observers is this equivalencing of many different configurations of a system, saying, all I care about is this aggregate feature, all I care about is this overall thing, and that's sort of one aspect. We see that in lots of different, again, it's the same story over and over again, that there's a lot of detail in the world, but what we are extracting from it is something, a sort of a thin summary of that detail." }, { "from": "human", "value": "Is that thin summary nevertheless true? Can it be a crappy approximation that on average is correct? I mean, if we look at the observer that's the human mind, it seems like there's a lot of very, as represented by natural language, for example, there's a lot of really crappy approximation. Sure." }, { "from": "gpt", "value": "And that could be maybe a feature of it, that there's ambiguity. You don't know, it could be the case. They're just measuring the aggregate impacts of these molecules. But there is some tiny, tiny probability that molecules will arrange themselves in some really funky way and that just measuring that average isn't going to the main point. By the way, an awful lot of science is very confused about this because you look at papers and people are really keen, they draw this curve and they have these bars on the curve and things, and it's just this curve. And it's this one thing and it's supposed to represent some system that has all kinds of details in it. And this is a way that lots of science has gotten wrong. Because people say, I remember years ago I was studying snowflake growth. You know, you have a snowflake and it's growing, it has all these arms, it's doing complicated things. But there was a literature on this stuff and it talked about, you know, what's the rate of snowflake growth? And, you know, it got pretty good answers for the rate of the growth of the snowflake. And I looked at it more carefully, and they had these nice curves of snowflake growth rates and so on. I looked at it more carefully, and I realized according to their models, the snowflake would be spherical. And so they got the growth rate right, but the detail was just utterly wrong. Not only the detail, the whole thing was not capturing, it was capturing this aspect of the system that was, in a sense, missing the main point of what was going on. What is the geometric shape of a snowflake? Snowflakes start in the phase of water that's relevant to the formation of snowflakes. It's a phase of ice, which starts with a hexagonal arrangement of water molecules. And so it starts off growing as a hexagonal plate. And then what happens is... It's a plate. Oh, oh, versus sphere versus plate. Well, no, no, but it's much more than that. I mean, snowflakes are fluffy. Typical snowflakes have little dendritic arms. And what actually happens is it's kind of cool because you can make these very simple discrete models with cellular automata and things that figure this out. You start off with this hexagonal thing. And then the place is it starts to grow little arms. And every time a little piece of ice adds itself to the snowflake, the fact that that ice condensed from the water vapor heats the snowflake up locally. And so it makes it less likely for another piece of ice to accumulate right nearby. So this leads to a kind of growth inhibition. So you grow an arm and it is a separated arm because right around the arm it got a little bit hot and it didn't add more ice there. So what happens is you have a hexagon, it grows out arms. The arms grow arms and then the arms grow arms go arms. And eventually, actually it's kind of cool because it actually fills in another hexagon a bigger hexagon. And when I first looked at this, you know, I had a very simple model for this. I realized, you know, when it fills in that hexagon, it actually leaves some holes behind. So I thought, well, you know, is that really right? So I look at these pictures of snowflakes, and sure enough, they have these little holes in them that are kind of scars of the way that these arms grow out. So you can't fill in back fill holes. So they just keep going up." } ]

[ { "from": "human", "value": "Yeah, they don't back fill. And presumably there's a limitation on how big, like, you can't" }, { "from": "gpt", "value": "arbitrarily grow. I'm not sure. I'm mean the thing falls through the- I mean I think it this you know it hits the ground at some point. I think you can grow in the lab I think you can go to pretty big ones. I think you grow many many iterations of this kind of goes from hexagon it grows out arms, it turns back it fills back" }, { "from": "human", "value": "into a hexagon, it grows more arms again. In 3d? No it's flat usually. Boy why is it flat? Why doesn't it span out? Okay okay wait a minute. You said it's fluffy Fluffy is a three-dimensional property, no?" }, { "from": "gpt", "value": "No. It's fluffy. Snow is... Okay, so, you know, what makes... We're really in it. I like this. Let's go there. I like this." }, { "from": "human", "value": "Let's go there. There's multiple snowflakes become fluffy. Single snowflake is not fluffy." }, { "from": "gpt", "value": "No, no. Single snowflake is fluffy. And what happens is, you know, if you have snow that is just pure hexagons, they can, you know, they fit together pretty well. It's not... It doesn't make... It doesn't have a lot of air in it and they can also slide against each other pretty easily. And so, the snow can be pretty, you know, can, I think, avalanches happen sometimes when the things tend to be these, you know, hexagonal plates and it kind of slides. But then, when the thing has all these arms that have grown out, it's not... They don't fit together very well and that's why the snow has lots of air in it. And if you look at one of these snowflakes, and if you catch one, you'll see it has these little arms and people... Actually, people often say, you know, no two snowflakes are alike. That's mostly because as a snowflake grows, they do grow pretty consistently with these different arms and so on. But you capture them at different times. As they, you know, they fell through the air in a different way. You'll catch this one at this stage. And as it goes through different stages, they look really different. And so that's why, you know, it kind of looks like no two snowflakes are alike, because you caught them at different, at different times." }, { "from": "human", "value": "So, the rules under which they grow are the same. It's just the timing. Okay, so the point is, science is not able to describe the full complexity of snowflake growth." }, { "from": "gpt", "value": "Well, science, if you do what people might often do, which is say, okay, let's make it scientific, let's turn it into one number. And that one number is kind of the growth rate of the arms or some such other thing. That fails to capture sort of the detail of what's going on inside the system. And that's in a sense, a big challenge for science is how do you extract from the natural world, for example, those aspects of it that you are interested in talking about? Now, you might just say, I don't really care about the fluffiness of the snowflakes. All I care about is the growth rate of the arms, in which case you can have a good model without knowing anything about the fluffiness. But the fact is, as a practical, if you say, what is the most obvious feature of a snowflake? Oh, that it has this complicated shape. Well, then you've got a different story about what you model. I mean, this is one of the features of sort of modeling in science. What is a model? A model is some way of reducing the actuality of the world to something where you can readily sort of give a narrative for what's happening, where you can basically make some kind of abstraction of what's happening and answer questions that you care about answering. If you wanted to answer all possible questions about the system, you'd have to have the whole system because you might care about this particular molecule. Where did it go? And your model, which is some big abstraction of that, has nothing to say about that. So one of the things that's often confusing in science is people will have, I've got a model, somebody says. Somebody else will say, I don't believe in your model because it doesn't capture the feature of the system that I care about. There's always this controversy about, is it a correct model? Well, no model is except for the actual system itself, is a correct model in the sense that it captures everything, questions does it capture what you care about capturing. Sometimes that's ultimately defined by what you're going to build technology out of, things like this. The one counterexample to this is if you think you're modeling the whole universe all the way down, then there is a notion of a correct model. But even that is more complicated because it depends on kind of how observers sample things and so on. That's a separate story. But at least at the first level to say this thing about, oh, it's an approximation, you're capturing one aspect, you're not capturing other aspects. When you really think you have a complete model for the whole universe, you better be capturing ultimately everything, even though to actually run that model is impossible because of computational irreducibility. The only thing that successfully runs that model is the actual running of the universe." }, { "from": "human", "value": "Okay, so what you care about is an interesting concept. That's a human concept. That's what you're doing with Wolfram Alpha and Wolfram Language. Is he trying to come up with symbolic representations as simple as possible? A model that's as simple as possible that fully captures stuff we care about?" }, { "from": "gpt", "value": "Yes. So I mean, for example, we could, we'll have a data about movies, let's say. We could be describing every individual pixel in every movie and so on, but that's not the level that people care about. And that level that people care about is somewhat related to what's described in natural language. But what we're trying to do is to find a way to sort of represent precisely so you can compute things. See, one thing we say, you give a piece of natural language, the question is you feed it to a computer, you say, does the computer understand this natural language? Well, you know, the computer processes it in some way, it does this, maybe it can make a continuation of the natural language. Maybe it can go on from the prompt and say what it's going to say. You say, does it really understand it? Hard to know. But in this kind of computational world, world, there is a very definite definition of does it understand, which is could it be turned into this symbolic computational thing from which you can compute all kinds of consequences? And that's the sense in which one has sort of a target for the understanding of natural language. And that's kind of our goal, is to have as much as possible about the world that can be computed in a reasonable way, so to speak, be able to be sort of captured by this kind of computational language, that's kind of the goal. And I think for us humans, the main thing that's important is as we formalize what we're talking about, it gives us a way of kind of building a structure where we can sort of build this tower of consequences of things. So if we're just saying, well, let's talk about it in natural language, it doesn't really give us some hard foundation that lets us build step-by-step to work something out. I mean, it's kind of like what happens in math. If we were just sort of vaguely talking about math, but didn't have the kind of full structure of math and all that kind of thing, we wouldn't be able to build this kind of big tower of consequences. And so in a sense, what we're trying to do with the whole computational language effort is to make a formalism for describing the world that makes it possible to kind of build" } ]

[ { "from": "human", "value": "this tower of consequences. Well, can you talk about this dance between natural language and Wolfram language? So there's this gigantic thing we call the internet where people post memes and diary type thoughts and very important sounding articles and all of that that makes up the training dataset for GPT. And then there's Wolfram language. How can you map from the natural language of the internet to the Wolfram language?" }, { "from": "gpt", "value": "Is there a manual, is there an automated way of doing that as we look into the future? Well, so Wolfram Alpha, what it does, it's kind of front end is turning natural language" }, { "from": "human", "value": "into computational language. What you mean by that is there's a prompt, you ask a question, what is the capital of some country?" }, { "from": "gpt", "value": "Yeah, right. And it turns into, what's the distance between Chicago and London or something? And that will turn into geodistance of entity, city, et cetera, et cetera, et cetera. Each one of those things is very well defined. We know, given that it's the entity, city, Chicago, et cetera, et cetera, et cetera, Illinois, United States, we know the geolocation of that, we know its population, we know all kinds of things about it, which we have curated that data to be able to know that with some degree of certainty, so to speak." }, { "from": "human", "value": "And then we can compute things from this and that's the idea. But then something like GPT, large language models, do they allow you to make that conversion" }, { "from": "gpt", "value": "much more powerful? Okay, so it's an interesting thing, which we still don't know everything about. This question of going from natural language to computational language, in Wolfram Alpha, we've now, Wolfram Alpha's been out and about for 13 and a half years now, and we've achieved, I don't know what it is, 98%, 99% success on queries that get put into it. Now, obviously, there's a sort of feedback loop because the things that work are things people go on putting into it. But we've got to a very high success rate of the little fragments of natural language that people put in, questions, math calculations, chemistry calculations, whatever it is. We do very well at that, turning those things into computational language. Now, from the very beginning of Wolfram Alpha, I thought about, for example, writing code with natural language. In fact, I was just looking at this recently, I had a post that I wrote in 2010, 2011 called something like, programming with natural language is actually going to work. And so we had done a bunch of experiments using methods that were a little bit, some of them a little bit machine learning-like, but certainly not the same kind of idea of vast training data and so on, that is the story of large language models. Actually, I know that that post, a piece of utter trivia, but that post, Steve Jobs forwarded that post around to all kinds of people at Apple, because he never really liked programming languages. So he was very happy to see the idea that you could get rid of this kind of layer of kind of engineering-like structure. He would have liked, I think, what's happening now, because it really is the case that you can, this idea that you have to kind of learn how the computer works to use a programming language is something that is, I think, a thing that, just like you had to learn the details of the opcodes to know how assembly language worked and so on. It's kind of a thing that's a limited time horizon. So this idea of how elaborate can you make kind of the prompt, how elaborate can you make the natural language, and abstract from it computational language? It's a very interesting question, and what chat GPT 4 and so on can do is pretty good. It's a very interesting process. I mean, I'm still trying to understand this workflow. We've been working out a lot of tooling around this workflow." }, { "from": "human", "value": "Natural language to computational language, and the process, especially if it's conversation" }, { "from": "gpt", "value": "like dialogue, multiple queries kind of thing. Yeah, right. There's so many things that are really interesting that work and so on. So first thing is, can you just walk up to the computer and expect to sort of specify a computation? What one realizes is humans have to have some idea of kind of this way of thinking about things computationally. Without that, you're kind of out of luck, because you just have no idea what you're going to walk up to a computer. I remember when I should tell a silly story about myself. The very first computer I saw, which was when I was 10 years old, and it was a big mainframe computer and so on, and I didn't really understand what computers did. It's like, somebody's showing me this computer, and it's like, can the computer work out the weight of a dinosaur? That isn't a sensible thing to ask. You have to give it. That's not what computers do. I mean, in Wolfram Alpha, for example, you could say, what's the typical weight of a Stegosaurus? It will give you some answer, but that's a very different kind of thing from what one thinks of computers as doing. The question of, first thing is, people have to have an idea of what computation is about. I think for education, that is the key thing, is kind of this notion, not computer science, not the details of programming, but just this idea of how do you think about the world computationally. To put, you know, thinking about the world computationally is kind of this formal way of thinking about the world. We've had other ones, like logic was a formal way, you know, is a way of sort of abstracting and formalizing some aspects of the world. Mathematics is another one. Computation is this very broad way of sort of formalizing the way we think about the world. The thing that's cool about computation is, if we can successfully formalize things in terms of computation, computers can help us figure out what the consequences are. It's not like you formalized it with math. Well, that's nice, but now you have to, if you're not using a computer to do the math, you have to go work out a bunch of stuff yourself. So I think, but this idea, let's see, we're talking about natural language and its relationship to computational language. The typical workflow, I think, is first, human has to have some kind of idea of what they're trying to do, that if it's something that they want to build a tower of capabilities on, something that they want to formalize and make computational. So then human can type something in to some LLM system and say vaguely what they want in computational terms. Then it does pretty well at synthesizing welcome language code, and it'll probably do better in the future because we've got a huge number of examples of natural language input together with the Wolfram Language Translation of that. So that's a thing where extrapolating from all those examples makes it easier to do that" } ]

[ { "from": "human", "value": "task. Is the prompter task also debugging the Wolfram Language Code, or is your hope to not do that" }, { "from": "gpt", "value": "debugging? No, no, no. So there are many steps here. The first thing is you type natural language. It generates Wolfram Language Code." }, { "from": "human", "value": "Do you have examples, by the way? Do you have an example, is it the dinosaur example, do you have an example that jumps" }, { "from": "gpt", "value": "to mind that we should be thinking about some dumb example? It's like take my heart rate data and figure out whether I make a moving average every seven days or something and make a plot of the result. So that's a thing which is about two-thirds of a line of Wolfram Language Code. I mean, it's a list plot of moving average of some data bin or something of the data, and then you'll get the result. The vague thing that I was just saying in natural language could, would almost certainly correctly turn into that very simple piece of Wolfram Language Code." }, { "from": "human", "value": "So you start mumbling about heart rate." }, { "from": "gpt", "value": "You arrive at the moving average kind of idea. You say average over seven days. Maybe it'll figure out that that can be encapsulated as this moving average idea, I'm not sure. But then the typical workflow that I'm seeing is you generate this piece of Wolfram Language Code. It's pretty small usually. If it isn't small, it probably isn't right. If it's pretty small and Wolfram Language is one of the ideas of Wolfram Language, is that it's a language that humans can read. It's not a language which programming languages tend to be this one-way story of humans write them and computers execute from them. Wolfram Language is intended to be something which is sort of like math notation, something where humans write it and humans are supposed to read it, as well. And so kind of the workflow that's emerging is kind of this human mumble, some things. Large language model produces a fragment of often language code. Then you look at that, you say, well, typically you just run it first. You see, does it produce the right thing? You look at what it produces, you might say that's obviously crazy. You look at the code, you see, I see why it's crazy. You fix it. If you really care about the result and you really want to make sure it's right, you better look at that code and understand it because that's the way you have this sort of checkpoint of did it really do what I expected it to do. Now you go beyond that, I mean, what we find is, for example, let's say the code does the wrong thing. Then you can often say to the large language model, can you adjust this to do this?" }, { "from": "human", "value": "And it's pretty good at doing that. Interesting. So you're using the output of the code to give you hints about the function of the code. So you're debugging based on the output of the code itself." }, { "from": "gpt", "value": "By the way, the plugin that we have for chat GPT, it does that routinely. It will send the thing in, it will get a result, it will discover, the LLM will discover itself that the result is not plausible and it will go back and say, oh, I'm sorry, it's very polite and it goes back and says, I'll rewrite that piece of code and then it will try it again and get the result. The other thing that's pretty interesting is when you're just running, so one of the new concepts that we have, we invented this whole idea of notebooks back 36 years ago now. And so now there's the question of sort of how do you combine this idea of notebooks where you have text and code and output? How do you combine that with the notion of chat and so on? And there's some really interesting things there. Like for example, a very typical thing now is we have these notebooks where as soon as if the thing produces errors, if they run this code and it produces messages and so on, the LLM automatically not only looks at those messages, it can also see all kinds of internal information about stack traces and things like this. And it can then, it does a remarkably good job of guessing what's wrong and telling you. So in other words, it's looking at things, sort of interesting. It's kind of a typical sort of AI-ish thing that it's able to have more sensory data than we humans are able to have, because it's able to look at a bunch of stuff that we humans would kind of glaze over looking at." }, { "from": "human", "value": "And it's able to then come up with, oh, this is the explanation of what's happening. And what is the data, the stack trace, the code you've written previously, the natural" }, { "from": "gpt", "value": "language you've written? It's also what's happening is one of the things is, for example, when there's these messages, there's documentation about these messages. There's examples where the messages have occurred, otherwise all these kinds of things. The other thing that's really amusing with this is when it makes a mistake. One of the things that's in our prompt when the code doesn't work is read the documentation. And have another piece of the plugin that lets it read documentation. And that, again, is very, very useful because it will figure out sometimes it'll make up the name of some option for some function that doesn't really exist, read the documentation, it'll have some wrong structure for the function and so on. That's a powerful thing. I mean, the thing that I've realized is we built this language over the course of all these years to be nice and coherent and consistent and so on, so it's easy for humans to understand. Turns out, there was a side effect that I didn't anticipate, which is it makes it easy" } ]

[ { "from": "human", "value": "for AIs to understand. It's almost like another natural language, but so Wolfram language is a kind of foreign language. Yes. You have a lineup, English, French, Japanese, Wolfram language, and then, I don't know," }, { "from": "gpt", "value": "Spanish, and then the system is not going to notice. So Wolfram? Yes. Well, yes. I mean, maybe. That's an interesting question because it really depends on what I see as being an important piece of fundamental science that basically just jumped out at us with chat GPT because I think the real question is why does chat GPT work? How is it possible to encapsulate, to successfully reproduce all these kinds of things in natural language with a comparatively small, he says, a couple hundred billion weights of neural net and so on? I think that relates to kind of a fundamental fact about language, which the main thing is that I think there's a structure to language that we haven't really explored very well. It's kind of this semantic grammar I'm talking about about language. We kind of know that ... When we set up human language, we know that it has certain regularities. We know that it has a certain grammatical structure. Noun followed by verb, followed by noun, adjectives, et cetera, et cetera, et cetera. That's its kind of grammatical structure. But I think the thing that chat GPT is showing us is that there's an additional kind of regularity to language which has to do with the meaning of the language beyond just this pure part speech combination type of thing. I think the one example of that that we've had in the past is logic. I think my picture of how was logic invented, how was logic discovered, it really was a thing that was discovered in its original conception. It was discovered, presumably by Aristotle, who listened to a bunch of people, orators, giving speeches. And this one made sense, that one doesn't make sense. You see these patterns of if the Persians do this, then this does that, etc., etc., etc. What Aristotle realized is there's a structure to those sentences, there's a structure to that rhetoric that doesn't matter whether it's the Persians and the Greeks, or whether it's the cats and the dogs. It's just P and Q. You can abstract from the details of these particular sentences. You can lift out this formal structure," }, { "from": "human", "value": "and that's what logic is. That's a heck of a discovery, by the way, logic. You're making me" }, { "from": "gpt", "value": "realize, no. Yeah. It's not obvious. The fact that there is an abstraction from natural language that has where you can fill in any word you want is a very interesting discovery. Now, it took a long time to mature. Aristotle had this idea of syllogistic logic, where there were these particular patterns of how you could argue things, so to speak. In the Middle Ages, part of education was you memorize the syllogisms. I forget how many there were, but 15 of them or something. They all had names. They all had mnemonics, like I think barbera and celerant were two of the mnemonics for the syllogisms. This is a valid argument, because it follows the barbera syllogism, so to speak. It took until 1830, with George Boole, to get beyond that and see that there was a level of abstraction that was beyond this particular template of a sentence, so to speak. What's interesting there is, in a sense, chat GPT is operating at the Aristotelian level. It's essentially dealing with templates of sentences. By the time you get to Boole and Boolean algebra and this idea of you can have arbitrary depth-nested collections of ands and ors and nots, and you can resolve what they mean, that's the kind of thing. That's a computation story. You've gone beyond the pure templates of natural language to something which is an arbitrarily deep computation. But the thing that I think we realized from chat GPT is, you know, Aristotle stopped too quickly, and there was more that you could have lifted out of language as formal structures. I think there's, in a sense, we've captured some of that and some of what is in language. There's a lot of little calculus, little algebras of what you can say, what language talks about. Whether it's, I don't know, if you say, I go from place A to place B, place B to place C, then I know I've gone from place A to place C. If A is a friend of B and B is a friend of C, it doesn't necessarily follow that A is a friend of C. If you go from place A to place B to place B to place C, it doesn't matter how you went. Like logic, it doesn't matter whether you flew there, walked there, swam there, whatever. This transitivity of where you go is still valid, and there are many kinds of features, I think, of the way the world works that are captured in these aspects of language, so to speak. I think what ChatGBT effectively has found, just like it discovered logic, people are really surprised it can do these logical inferences, it discovered logic the same way Aristotle discovered logic, by looking at a lot of sentences effectively and noticing the patterns in those sentences." }, { "from": "human", "value": "But it feels like it's discovering something much more complicated than logic, so this kind of semantic grammar, I think you wrote about this, maybe you can call it the laws of language, I believe you call, or which I like, the laws of thought." }, { "from": "gpt", "value": "Yes. That was the title that George Boole had for his Boolean algebra back in 1830, but yes. Laws of thought? Yes, that was what he said. All right. So he thought he nailed it with Boolean algebra. Yeah." } ]

[ { "from": "human", "value": "There's more to it. There's more to it. It's a good question of how much more is there to it, and it seems like one of the reasons, as you imply that the reason GPT works, ChatGPT works, is that there's a finite number of things to it. Yeah, I mean, it's..." }, { "from": "gpt", "value": "In some sense, GPT is discovering the laws of semantic grammar that underlies language. Yes. And what's sort of interesting is, in the computational universe, there's a lot of other kinds of computation that you could do. They're just not ones that we humans have cared about and operate with. And that's probably because our brains are built in a certain way, and the neural nets of our brains are not that different, in some sense, from the neural nets of a large language model. And so when we think about, and maybe we can talk about this some more, but when we think about what will AIs ultimately do, the answer is insofar as AIs are just doing computation, they can run off and do all these kinds of crazy computations. But the ones that we sort of have decided we care about is this kind of very limited" }, { "from": "human", "value": "set. That's where the reinforcement learning with human feedback seems to come in. The more the AIs say the stuff that kind of interests us, the more we're impressed by it. So it can do a lot of interesting, intelligent things, but we're only interested in the AI systems when they communicate in a human-like way. Yes." }, { "from": "gpt", "value": "About human-like topics. Yes. Well, it's like technology. I mean, in a sense, the physical world provides all kinds of things, you know, all kinds of processes going on in physics. Only a limited set of those are ones that we capture and use for technology because they're only a limited set where we say, you know, this is a thing that we can sort of apply to the human purposes we currently care about. I mean, you might have said, okay, you pick up a piece of rock. You say, okay, this is a nice silicate. It contains all kinds of silicon. I don't care. Then you realize, oh, we could actually turn this into a semiconductor wafer and make it microprocessor out of it. And then we care a lot about it. Yes. And it's this thing about what do we... In the evolution of our civilization, what things do we identify as being things we care about? I mean, it's like when there was a little announcement recently of the possibility of a high-temperature superconductor that involved the element lutetium, which generally nobody has cared about. Yes. But suddenly, if there's this application that relates to kind of human purposes, we start to care a lot." }, { "from": "human", "value": "So given your thinking that GPT may have discovered inklings of laws of thought, do you think such laws exist? Can we linger on that? Yeah." }, { "from": "gpt", "value": "What's your intuition here? Yeah. What's your intuition here? Oh, definitely. I mean, the fact is, look, logic is but the first step. There are many other kinds of calculae about things that we consider about sort of things that happen in the world or things that are meaningful." }, { "from": "human", "value": "Well, how do you know logic is not the last step? You know what I mean?" }, { "from": "gpt", "value": "Well, because we can plainly see that there are things... I mean, if you say, here's a sentence that is syntactically correct, okay? You look at it and you're like, the happy electron, eight, I don't know what, something that it just... You look at it and it's like this is meaningless. It's just a bunch of words. It's syntactically correct. The nouns and the verbs are in the right place, but it just doesn't mean anything. So there clearly is some rule that there are rules that determine when a sentence has the potential to be meaningful that go beyond the pure parts of speech syntax. And so the question is, what are those rules and are there a fairly finite set of those rules? My guess is that there's a fairly finite set of those rules. Once you have those rules, you have a kind of a construction kit, just like the rules of syntactic grammar give you a construction kit for making syntactically correct sentences. So you can also have a construction kit for making semantically correct sentences. Those sentences may not be realized in the world. I mean, I think the elephant flew to the moon, semantically, we know, we have an idea. If I say that to you, you kind of know what that means." }, { "from": "human", "value": "But the fact is it hasn't been realized in the world, so to speak. So semantically correct, perhaps as things that can be imagined with the human mind. No. Things that are consistent with both our imagination and our understanding of physical reality. I don't know. Yeah. Good question." }, { "from": "gpt", "value": "I mean, it's a good question. I mean, it's a good question. It's a good question. I think it is, given the way we have constructed language, it is things which fit with the things we're describing in language. It's a bit circular in the end, because you can, and the sort of boundaries of what is physically realizable, okay, let's take the example of motion. Motion is a complicated concept. It might seem like it's a concept that should have been figured out by the Greeks long ago, but it's actually a really pretty complicated concept, because what is motion? Motion is you can go from place A to place B, and it's still you when you get to the other end, right? You take an object, you move it, and it's still the same object, but it's in a different place. Now, even in ordinary physics, that doesn't always work that way. If you're near a space-time singularity in a black hole, for example, and you take your teapot or something, you don't have much of a teapot by the time it's near the space-time singularity. It's been completely deformed beyond recognition. That's a case where pure motion doesn't really work. You can't have a thing stay the same. This idea of motion is something that sort of is a slightly complicated idea, but once you have the idea of motion, you can start ... Once you have the idea that you're going to describe things as being the same thing, but in a different place, that sort of abstracted idea then has ... That has all sorts of consequences, like this transitivity of motion. Go from A to B, B to C, you've gone from A to C. At that level of description, you can have what are sort of inevitable consequences. They're inevitable features of the way you've sort of set things up. That's I think what this sort of semantic grammar is capturing, is things like that. I think that it's a question of what does the word mean when you say, I move from here to there. Well, it's complicated to say what that means. This is this whole issue of is pure motion possible, et cetera, et cetera, et cetera. Once you have kind of got an idea of what that means, then there are inevitable consequences of that idea." } ]

[ { "from": "human", "value": "But the very idea of meaning, it seems like there's some words that become ... It's like there's a latent ambiguity to them. I mean, it's the word like emotionally loaded words, like hate and love. It's like what do they mean? Exactly. Especially when you have relationships between complicated objects, we seem to take this kind of shortcut, descriptive shortcut to describe like object A hates object B. What's that really mean?" }, { "from": "gpt", "value": "Right. Well, words are defined by kind of our social use of them. It's not a word ... In computational language, for example, when we say we have a construct there, we expect that that construct is a building block from which we can construct an arbitrarily tall tower. We have to have a very solid building block. We have to ... It turns into a piece of code, it has documentation, it's a whole thing. But the word hate, the documentation for that word ... Well, there isn't a standard documentation for that word, so to speak. It's a complicated thing defined by kind of how we use it when if it wasn't for the fact that we were using language ... I mean, so what is language at some level? Language is a way of packaging thoughts so that we can communicate them to another mind. Can these complicated words be converted into something that a computation agent can use? Right. The answer to that is that what one can do in computational language is make a specific definition. If you have a complicated word, like let's say the word eat, you'd think that's a simple word. It's animals eat things, whatever else, but you do programming. You say this function eats arguments, which is sort of poetically similar to the animal eating things. If you start to say, well, what are the implications of the function eating something, can the function be poisoned? Well, maybe it can actually, but if there's a tight mismatch or something in some language. But in what ... How far does that analogy go? It's just an analogy. Whereas if you use the word eat, in a computational language level, you would define there isn't a thing which you anchor to the kind of natural language concept eat, but it is now some precise" }, { "from": "human", "value": "definition of that that then you can compute things from. But don't you think the analogy is also precise? Software eats the world. Don't you think there's something concrete in terms of meaning about analogies?" }, { "from": "gpt", "value": "Sure. But the thing that sort of is the first target for computational language is to take sort of the ordinary meaning of things and try and make it precise, make it sufficiently precise. You can build these towers of computation on top of it. So it's kind of like, if you start with a piece of poetry and you say, I'm going to define my program with this piece of poetry, it's kind of like that's a difficult thing. It's better to say I'm going to just have this boring piece of prose and it's using words in the ordinary way, and that's how I'm communicating with my computer, and that's how I'm going to build this solid building block from which I can construct this whole" }, { "from": "human", "value": "kind of computational tower. So there's some sense where if you take a poem and reduce it to something computable, you're gonna have very few things left. So maybe there's a bunch of human interaction that's just poetic, aimless nonsense. Well, it's just like recreational, like hamster in a wheel." }, { "from": "gpt", "value": "It's not actually producing anything. Well, I think that that's a complicated thing because in a sense, human linguistic communication is there's one mind, it's producing language. That language is having an effect on another mind. And the question of there's sort of a type of effect that is well-defined, let's say, where for example, it's very independent of the two minds, that there's communication where it can matter a lot, sort of what the experience of one mind is" }, { "from": "human", "value": "versus another one and so on. Yeah, but what is the purpose of natural language communication? Well, I think the- So computational language somehow feels more amenable to the definition of purpose. It's like, yeah, you're given two clean representations of a concept and you can build a tower based on that." }, { "from": "gpt", "value": "Is natural language the same thing but more fuzzy? Yeah. Well, I think the story of natural language, that's the great invention of our species. We don't know whether it exists in other species, but we know it exists in our species. It's the thing that allows you to sort of communicate abstractly from like one generation of the species to another. There is an abstract version of knowledge that can be passed down. It doesn't have to be genetics, it doesn't have to be, you don't have to apprentice the next generation of birds to the previous one to show them how something works. There is this abstracted version of knowledge that can be kind of passed down. It still tends to rely because language is fuzzy. It does tend to rely on the fact that if we look at some ancient language where we don't have a chain of translations from it until what we have today, we may not understand that ancient language. We may not understand its concepts may be different from the ones that we have today. We still have to have something of a chain, but it is something where we can realistically expect to communicate abstract ideas, and that's one of the big roles of language. That's been this ability to sort of concretify abstract things is what language has provided." }, { "from": "human", "value": "Do you see natural language and thought as the same, the stuff that's going inside your" }, { "from": "gpt", "value": "mind?" } ]

[ { "from": "human", "value": "Well, that's been a long debate in philosophy. It seems to be become more important now when we think about how intelligent GPT is. Whatever that means. Whatever that means, but it seems like the stuff that's going on in the human mind seems something like intelligence. Yes. And it's language. Well, we call it intelligence. Yeah, we call it. Well, yes. And so you start to think of, okay, what's the relationship between thought, the language of thought, the laws of thought, the laws of the words like reasoning, and the laws of language, and how that has to do with computation, which seems like more rigorous, precise ways" }, { "from": "gpt", "value": "of reasoning. Whatever that means. Yeah, we call it. Well, yes. Right. Which are beyond human. I mean, much of what computers do, humans do not do. I mean, you might say. Humans are a subset. Yes. Presumably. Yes. Hopefully. Yes. You might say, who needs computation when we have large language models? Large language models can just, eventually you'll have a big enough neural net, it can do anything. But they're really doing the kinds of things that humans quickly do. And there are plenty of formal things that humans never quickly do. For example, I don't know. People can do mental arithmetic. They can do a certain amount of math in their minds. I don't think many people can run a program in their minds of any sophistication. It's just not something people do. It's not something people have even thought of doing, because it's kind of not, you can easily run it on a computer." }, { "from": "human", "value": "Yes. Presumably. Yes. Hopefully. Betray a program." }, { "from": "gpt", "value": "Yeah. Aren't we running specialized programs? Yeah, yeah, yeah. But if I say to you, here's a Turing machine, tell me what it does after 50 steps, and you're trying to think about that in your mind, that's really hard to do. It's not what people do. Well, in this program. I mean, here's a Turing machine." }, { "from": "human", "value": "Yeah. I mean, the first people program, they build a computer, they program it. Just to answer your question about what the system does after 50 steps, I mean, humans build computers. Yes." }, { "from": "gpt", "value": "50 steps. Yes. Yeah, that's right. But they've created something which is then, when they run it, it's doing something different than what's happening in their minds. I mean, they've outsourced that piece of computation from something that is internally happening" }, { "from": "human", "value": "in their minds to something that is now a tool that's external to their minds. So by the way, humans, to you, didn't invent computers." }, { "from": "gpt", "value": "They discovered them." }, { "from": "human", "value": "They discovered computation, which they invented the technology of computers. The computer is just the kind of way to plug into this whole stream of computation. Yes." }, { "from": "gpt", "value": "There's probably other ways. Yes. There's probably a lot of ways. Well, for sure. I mean, the particular ways that we make computers out of semiconductors and electronics and so on, that's the particular technology stack we built. I mean, the story of a lot of what people try to do with quantum computing is finding different underlying physical infrastructure for doing computation. You know, biology does lots of computation. It does it using an infrastructure that's different from semiconductors and electronics. It's a molecular-scale sort of computational process that hopefully will understand more about ... I have some ideas about understanding more about that. That's another representation of computation. Things that happen in the physical universe at the level of these evolving hypergraphs" }, { "from": "human", "value": "and so on, that's another sort of implementation layer for this abstract idea of computation. So if GPT or large language models are starting to develop or implicitly understand the laws" }, { "from": "gpt", "value": "of language and thought, do you think they can be made explicit? Yes. We've got a bunch of effort. It's like doing natural science. What is happening in natural science? You have the world that's doing all of these complicated things, and then you discover Newton's law, for example. This is how motion works. This is the way that this particular sort of idealization of the world, this is how we describe it in a simple computationally reducible way. I think it's the same thing here. are sort of computationally reducible aspects of what's happening that you can get a kind" }, { "from": "human", "value": "of narrative theory for, just as we've got narrative theories in physics and so on. Do you think it will be depressing or exciting when all the laws of thought are made explicit, human thought are made explicit?" }, { "from": "gpt", "value": "I think that once you understand computationally reducibility, it's neither of those things. For example, people will say, oh, but I have free will. I operate in a way that is... They have the idea that they're doing something that is sort of internal to them that they're figuring out what's happening. But in fact, we think there are laws of physics that ultimately determine every electrical impulse and a nerve and things like this. You might say, isn't it depressing that we are ultimately just determined by the rules of physics, so to speak? It's the same thing. It's at a higher level. It's a shorter distance to get from semantic grammar to the way that we might construct a piece of text than it is to get from individual nerve firings to how we construct a piece of text. But it's not fundamentally different. By the way, as soon as we have this other level of description, it helps us to go even further. We'll end up being able to produce more and more complicated kinds of things that, just like if we didn't have a computer and we knew certain rules, we could write them down and go a certain distance. But once we have a computer, we can go vastly further, and this is the same" } ]

[ { "from": "human", "value": "kind of thing. You wrote a blog post titled, What is Chad GPT doing and why does it work? We've been talking about this, but can we just step back and link on this question? What's Chad GPT doing? What are these a bunch of billion parameters trained on a large number of words? Why does it seem to work again? Is it because to the point you made that there's laws of language that can be discovered by such a process? Is there something?" }, { "from": "gpt", "value": "Well, let's talk about sort of the low level of what Chad GPT is doing. I mean, ultimately, you give it a prompt. It's trying to work out what should the next word be," }, { "from": "human", "value": "which is wild. Isn't it surprising to you that this kind of low level dumb training procedure can create something syntactically correct first? And then semantically correct." }, { "from": "gpt", "value": "The thing that has been sort of a story of my life is realizing that simple rules can do much more complicated things than you imagine. That something that starts simple and starts simple to describe, can grow a thing that is vastly more complicated than you can imagine. Honestly, It's taken me, I've sort of been thinking about this now 40 years or so, and it always surprises me. I mean, even, for example, in our physics project, sort of thinking about the whole universe growing from these simple rules, I still resist, because I keep on thinking, how can something really complicated arise from something that simple? It just seems wrong, but yet, the majority of my life I've kind of known from things I've studied that this is the way things work. Yes, it is wild that it's possible to write a word at a time and produce a coherent essay, for example, but it's worth understanding kind of how that's working. If it was going to say the cat sat on thee, what's the next word? Okay, so how does it figure out the next word? It's seen a trillion words written on the internet, and it's seen the cat sat on the floor, the cat sat on the sofa, the cat sat on the whatever. The minimal thing to do is just say, let's look at what we saw on the internet. We saw 10,000 examples of the cat sat on the, what was the most probable next word? Let's just pick that out and say that's the next word. That's kind of what it, at some level, is trying to do. Now, the problem is there isn't enough text on the internet to, if you have a reasonable length of prompt, that specific prompt will never have occurred on the internet. As you kind of go further, there just won't be a place where you could have trained, where you could just just worked out probabilities from what was already there. If you say two plus two, there'll be a zillion examples of two plus two equaling four and a very small number of examples of two plus two equals five and so on, and you can pretty much know what's going to happen. Then the question is, well, if you can't just work out from examples, what's going to happen? Just no probabilistic, for example, what's going to happen? You have to have a model. This kind of an idea, this idea of making models of things, is an idea that really, I don't know, I think Galileo probably was one of the first people who sort of worked this out. I mean, it's kind of like, I think I gave an example of that, the book I wrote about Chachibitee, where it's kind of like Galileo was dropping cannonballs off the different floors of the tower of Pisa, and it's like, okay, you drop a cannonball off this floor, you drop a cannonball off this floor. You miss floor five or something for whatever reason, but you know the time it took the cannonball to fall to the ground from floors one, two, three, four, six, seven, eight, for example. Then the question is, can you work out? Can you make a model which figures out how long did it take the ball? How long would it take the ball to fall to the ground from the floor you didn't explicitly measure? The thing Galileo realized is that you can use math. You can use mathematical formulas to make a model for how long it will take the ball to fall. Now the question is, well, okay, you want to make a model for, for example, something much more elaborate, like you've got this arrangement of pixels, and is this arrangement of pixels an A or a B? Does it correspond to something we'd recognize as an A or B? You can make a similar kind. Each pixel is like a parameter in some equation, and you could write down this giant equation where the answer is either A or 1 or 2, A or B. The question is then, what kind of a model successfully reproduces the way that we humans would conclude that this is an A and this is a B? If there's a complicated extra tail on the top of the A, would we then conclude something different? This is the type of model that maps well into the way that we humans make distinguishes about things, and the big kind of meta discovery is neural nets are such a model. It's not obvious they would be such a model. It could be that human distinctions are not captured, you know, we could try searching around for a type of model, that could be a mathematical model, it could be some model based on something else that captures kind of typical human distinctions about things. It turns out this model that actually is very much the way that we think the architecture of brains works, that perhaps not surprisingly, that model actually corresponds to the way we make these distinctions. The core next point is that the kind of model, this neural net model, makes distinctions and generalizes things in sort of the same way that we humans do it. That's why when you say, the cat sat on the green blank, even though it didn't see many examples of the cat sat on the green, whatever, it can make a ... Or the odd vox sat on the green, whatever, I'm sure that particular sentence does not occur on the internet. It has to make a model that concludes what ... It has to kind of generalize from the actual examples that it's seen. That's the fact is that neural nets generalize in the same kind of way that we humans do. If we were the aliens might look at our neural net generalizations and say, that's crazy. That thing, when you put that extra little dot on the A, that isn't an A anymore. That messed the whole thing up, but for us humans, we make distinctions which seem to correspond to the kinds of distinctions that neural nets make. The thing that is just amazing to me about chat GPT is how similar the structure it has is to the very original way people imagined neural nets might work back in 1943. There's a lot of detailed engineering, great cleverness, but it's really the same idea. In fact, even the sort of elaborations of that idea where people said, let's put in some actual particular structure to try and make the neural net more elaborate to be very clever about it, most of that didn't matter. When you train this neural net, the one thing, this kind of transformer architecture, this attention idea, that really has to do with does every one of these neurons connect to every other neuron or is it somehow causally localized, so to speak? Is it like we're making a sequence of words and the words depend on previous words rather than just everything can depend on everything? That seems to be important in just organizing things so that you don't have a sort of a giant mess. But the thing worth understanding about what is chat GPT in the end, I mean, what is a neural net in the end? A neural net in the end is each neuron has a ... It's taking inputs from a bunch of other neurons. It's eventually going to have a numerical value. It's going to compute some number and it's saying, I'm going to look at the neurons above me. It's kind of a series of layers. It's going to look at the neurons above me and it's going to say, what are the values of all those neurons? Then it's going to add those up and multiply them by these weights and then it's going to apply some function that says if it's bigger than zero or something, then make it one and otherwise make it zero or some slightly more complicated function. You know very well how this works." } ]

[ { "from": "human", "value": "It's a giant equation with a lot of variables. You mentioned figuring out where the ball falls when you don't have data on the fourth floor. The equation here is not as simple as the equation." }, { "from": "gpt", "value": "Right." }, { "from": "human", "value": "It's an equation with 175 billion terms. It's quite surprising that in some sense a simple procedure of training such an equation" }, { "from": "gpt", "value": "can lead to a good representation of natural language. The real issue is this architecture of a neural net where what's happening is you've turned, so neural nets always just deal with numbers. You've turned the sentence that you started with into a bunch of numbers like let's say by mapping each word of the 50,000 words in English, you just map each word or each part of a word into some number. You feed all those numbers in and then those numbers just go into the values of these neurons. Then what happens is it's just rippling down going layer to layer until it gets to the end. The chat GPT has about 400 layers. It just goes once through. Every new word it's going to compute just says here are the numbers from the words before. Let's compute the ... What does it compute? It computes the probabilities that it estimates for each of the possible 50,000 words that could come next. Then it decides sometimes it will use the most probable words, sometimes it will use not the most probable word. It's an interesting fact that there's this so-called temperature parameter, which temperature is zero. It's always using the most probable word that it estimated was the most probable thing to come next. If you increase the temperature, it'll be more and more random in its selection of words. It'll go down to the lower and lower probability words. The thing I was just playing with actually recently was the transition that happens as you increase the temperature. The thing goes bonkers at a particular ... Sometimes at a particular temperature ... Maybe about point two is the thing I was noticing from yesterday, actually, that usually it's giving reasonable answers, and then at that temperature, with some probability, it just starts spouting nonsense. Nobody knows why this happens. By the way, the thing to understand is it's putting down one word at a time, but the outer loop of the fact that it says, okay, I put down a word, now let's take the whole thing I wrote so far, let's feed that back in, let's put down another word. That outer loop, which seems almost trivial, is really important to the operation of the thing. For example, one of the things that is kind of funky is it'll give an answer, and you say to it, is that answer correct? It'll say, no. Why is that happening? It's fascinating, right? Why can it do that? Well, the answer is because it is going one word at a time, sort of four words, and it didn't ... It came along with some sort of chain of thought, in a sense, and it came up with completely the wrong answer, but as soon as you feed it, the whole thing that it came up with, it immediately knows that that isn't right. It immediately can recognize that was a bad syllogism or something, and can see what happened, even though as it was being led down this garden path, so to speak, it came to the wrong" }, { "from": "human", "value": "place. But it's fascinating that this kind of procedure converges to something that forms a pretty good compressed representation of language on the internet." }, { "from": "gpt", "value": "That's quite ... I'm not sure what to make of it. Well, look, I think there are many things we don't understand. For example, 175 billion weights, it's maybe about a trillion bytes of information, which is very comparable to the training set that was used, and why that ... It sort of stands to some kind of reason that the number of weights in the neural net ... I don't know. I can't really argue that. I can't really give you a good ... In a sense, the very fact that insofar as there are definite rules of what's going on, you might expect that eventually we'll have a much smaller neural net that will successfully capture what's happening. I don't think the best way to do it is probably a neural net. I think a neural net is what you do when you don't know any other way to structure the thing. It's a very good thing to do if you don't know any other way to structure the thing, and for the last 2,000 years, we haven't known any other way to structure it. This is a pretty good way to start. But that doesn't mean you can't find, sort of, in a sense, more symbolic rules for what's going on that much of which will then be ... You can kind of get rid of much of the structure of the neural nets and replace it by things which are sort of pure steps of computation, so to speak, sort of with neural net stuff around the edges, and that becomes just a much simpler way to do it." }, { "from": "human", "value": "So the neural net, you hope, will reveal to us good symbolic rules that make the need" }, { "from": "gpt", "value": "of the neural net less and less and less. Yeah, right. And there will still be some stuff that's kind of fuzzy, just like there are things that, it's like this question of what can we formalize? What can we turn into computational language?" }, { "from": "human", "value": "What is just sort of, oh, it happens that way just because brains are set up that way. What do you think are the limitations of large language models, just to make it explicit?" }, { "from": "gpt", "value": "Well, I mean, I think that deep computation is not what large language models do. I mean, that's just, it's a different kind of thing, you know, the outer loop of a large language model, if you're trying to do many steps in a computation, the only way you get to do that right now is by spooling out, you know, all the whole chain of thought as a bunch of words, basically. And you know, you can make a Turing machine out of that, if you want to, I just was doing that construction. You know, in principle, you can make an arbitrary computation by just spooling out the words. But it's a bizarre and inefficient way to do it. But it's something where the, you know, I think that's, you know, sort of the deep computation is, it's really what humans can do quickly. Large language models will probably be able to do well. Anything that you can do kind of off the top of your head type thing is really, you know, is good for large language models. And the things you do off the top of your head, you may not get them always right." } ]

[ { "from": "human", "value": "But you know, you'll, it's thinking through the same way we do. But I wonder if there's an automated way to do something that humans do well, much faster to where it like loops, so generate arbitrary large code bases of Wolfram, Wolfram language," }, { "from": "gpt", "value": "for example." }, { "from": "human", "value": "Well, the question is, what does he, what do you want the code base to do? Escape control and take over the world." }, { "from": "gpt", "value": "Okay. So you know, the thing is, when people say you know, we want to build this giant thing, right, a giant piece of computational language in a sense, it's sort of a failure of computational language. If the thing you have to build, in other words if we have a description, if you have a small description that's the thing that you represent in computational language and then the computer can compute from that. Yes. So, in a sense, as soon as you're giving a description, you have to somehow make that description something definite, something formal, and to say, okay, I'm going to give this piece of natural language, and then it's going to splurt out this giant formal structure, in a sense, that doesn't really make sense, because except insofar as that piece of natural language kind of plugs into what we socially know, so to speak, plugs into kind of our corpus of knowledge, then that's the way we're capturing a piece of that corpus of knowledge, but hopefully we will have done that in computational language. How do you make it do something that's big? Well, you have to have a way to describe what you want." }, { "from": "human", "value": "I can make it more explicit if you want. How about I just pop into my head. Iterate through all the members of Congress and figure out how to convince them that they have to let me, meaning the system, become president. Pass all the laws that allows AI systems to take control and be the president. I don't know. So that's a very explicit, like, figure out the individual life story of each congressman, each senator, anybody, I don't know what's required to really kind of pass legislation and figure out how to control them and manipulate them, get all the information. What would be the biggest fear of this congressman in such a way that you can take action on it in the digital space, so maybe threaten the destruction, reputation, or something" }, { "from": "gpt", "value": "like this? Right. If I can describe what I want, to what extent can a large language model automate that?" }, { "from": "human", "value": "With the help of the concretization of something like Wolfram Language, that makes it more, yeah, grounded. Yeah, grounded. I think it can go rather a long way. I'm also surprised how quickly I was able to generate." }, { "from": "gpt", "value": "I think it can go, yeah, yeah, right. An attack. That's a, yeah, you know." }, { "from": "human", "value": "I swear, I swear, I swear I did not think about this before, and it's funny how quickly, which is a very concerning thing, because that probably, this idea will probably do quite a bit of damage, and there might be a very large number of other such ideas." }, { "from": "gpt", "value": "Well, I'll give you a much more benign version of that idea, okay? You're going to make an AI tutoring system, and that's a benign version of what you're saying is, I want this person to understand this point. You're essentially doing machine learning where the loss function, the thing you're trying to get to is get the human to understand this point, and when you do a test on the human that they, yes, they correctly understand how this or that works. I am confident that a large language model type technology combined with computational language is going to be able to do pretty well at teaching us humans things, and it's going to be an interesting phenomenon, because individualized teaching is a thing that has been a goal for a long time. I think we're going to get that. I think it has many consequences. If you know me, if you, the AI, know me, tell me I'm about to do this thing, what are the three things I need to know, given what I already know, let's say I'm looking at some paper or something, it's like there's a version of the summary of that paper that is optimized" }, { "from": "human", "value": "for me, so to speak, and where it really is and I think that's really going to work. It could understand the major gaps in your knowledge that it feels would actually give" }, { "from": "gpt", "value": "you a deeper understanding of the topic. Right. That's an important thing, because it really changes, actually. I think when you think about education and so on, it really changes what's worth doing, what's not worth doing and so on. It makes ... I know in my life I've learned lots of different fields, so I don't know. Every time I always think that this is the one that I'm not going to be able to learn, but it turns out there are meta-methods for learning these things in the end. I think this idea that it becomes easier to be fed knowledge, so to speak, and if you need to know this particular thing, you can get taught it in an efficient way is something I think is an interesting feature. I think it makes things like the value of big towers of specialized knowledge become less significant compared to the meta-knowledge of understanding the big picture and being able to connect things together. I think there's been this huge trend of let's be more and more specialized because we have to sort of ascend these towers of knowledge, but by the time you can get more automation, being able to get to that place on the tower without having to go through all those steps," } ]

[ { "from": "human", "value": "I think it sort of changes that picture. Interesting. So your intuition is that in terms of the collective intelligence of the species, in the individual minds that make up that collective, there will be more, there will trend towards" }, { "from": "gpt", "value": "being generalists and being kind of philosophers. That's what I think. I think that's where the humans are going to be useful. I think that a lot of these kind of the drilling, the mechanical working out of things is much more automatable. It's much more AI territory, so to speak. No more PhDs. That's interesting, yes. I mean, the kind of specialization, this kind of tower of specialization, which has been a feature of we've accumulated lots of knowledge in our species, and in a sense, every time we have a kind of automation, a building of tools, it becomes less necessary to know that whole tower, and it becomes something where you can just use a tool to get to the top of that tower. I think that the thing that is ultimately, when we think about, okay, what do the AIs do versus what do the humans do, it's like AIs, you tell them, you say, go achieve this particular objective. Okay, they can maybe figure out a way to achieve that objective. We say, what objective would you like to achieve? The AI has no intrinsic idea of that. It's not a defined thing. That's a thing which has to come from some other entity, and insofar as we are in charge, so to speak, or whatever it is, and our kind of web of society and history and so on, is the thing that is defining what objective we want to go to." }, { "from": "human", "value": "That's the thing that we humans are necessarily involved in, so to speak. To push back a little bit, don't you think that future versions of GPT would be able" }, { "from": "gpt", "value": "to give a good answer to what objective would you like to achieve? On what basis? I mean, if they say, look, here's the terrible thing that could happen, they're taking the average of the internet, and they're saying, from the average of the internet, what do" }, { "from": "human", "value": "people want to do? Well, that's the almost scottage of the most entertaining outcome is the most likely." }, { "from": "gpt", "value": "Okay." }, { "from": "human", "value": "I haven't heard that one from him, yeah. That could be one objective, is maximize global entertainment, the dark version of" }, { "from": "gpt", "value": "that is drama, the good version of that is fun. Right. So, I mean, this question of what, if you say to the AI, what does the species want to achieve? Yes. Okay? There'll be an answer, right? There'll be an answer. It'll be what the average of the internet says the species wants to achieve." }, { "from": "human", "value": "Well, I think you're using the word average very loosely there, right? So, I think the answers will become more and more interesting as these language models are trained better and better. No, but I mean, in the end, it's a reflection back of what we've already said. Yes. But there's a deeper wisdom to the collective intelligence, presumably, than each individual. Maybe." }, { "from": "gpt", "value": "Isn't that what we're trying to do as a society? Well, I mean, that's an important, that's an interesting question. I mean, in so far as some of us work on trying to innovate and figure out new things and so on, it is sometimes, it's a complicated interplay between sort of the individual doing the crazy thing off in some spur, so to speak, versus the collective that's trying to do sort of the high inertia average thing. And it's, you know, sometimes the collective, you know, is bubbling up things that are interesting and sometimes it's pulling down kind of the attempt to make this kind of innovative direction." }, { "from": "human", "value": "But don't you think the large language models would see beyond that simplification will say maybe intellectual and career diversity is really important, so you need the crazy people on the outlier, on the outskirts? And so, like the actual . . . What's the purpose of this whole thing is to explore through this kind of dynamics that we've been using as a human civilization, which is most of us focus on one thing, and then there's the crazy people on the outskirts doing the opposite of that one thing and you kind of, they pull the whole society together. There's the mainstream science and then there's the crazy science. That's just been the history of human civilization. And maybe the AI system will be able to see that, and the more and more impressed we are by a language model telling us this, the more control will give it to it, and the more we'll be willing to let it run our society. And hence, there's this kind of loop where the society could be manipulated to let the" }, { "from": "gpt", "value": "AI system run it. Right. Well, I mean, look, one of the things that's sort of interesting is we might say we always think we're making progress. But yet, if in a sense by saying, let's take what already exists and use that as a model for what should exist, then it's interesting that, for example, many religions have taken that point of view. There is a sacred book that got written at time x, and it defines how people should act for all future time. And it's a model that people have operated with. And in a sense, this is a version of that kind of statement. It's like, take the 2023 version of sort of how the world has exposed itself and use that" } ]

[ { "from": "human", "value": "to define what the world should do in the future. But it's an imprecise definition, right? Because just like with religious texts and with GPT, the human interpretation of what GPT says will be the perturbation in the system, it'll be the noise, it'll be full of uncertainty. It's not like chat GPT will tell you exactly what to do. It'll tell you a narrative of what, like turn the other cheek kind of narrative, right? That's not a fully instructive narrative. Well, until the AIs control all the systems in the world. They will be able to very precisely tell you what to do." }, { "from": "gpt", "value": "Well, they'll do what they, they'll just do this or that thing. And not only that, they'll be auto suggesting to each person, do this next, do that next. So I think it's a slightly more prescriptive situation than one has typically seen. I think this whole question of sort of what's left for the human, so to speak, to what extent do we, this idea that there is an existing kind of corpus of purpose for humans defined by what's on the internet and so on, that's an important thing. But then the question of sort of as we explore what we can think of as the computational universe, as we explore all these different possibilities for what we could do, all these different inventions we could make, all these different things. The question is, which ones do we choose to follow? Those choices are the things that in a sense, if the humans want to still have kind of human progress, that's what we get to make those choices, so to speak. In other words, there's this idea, if you say, let's take the kind of what exists today and use that as the determiner of all of what there is in the future, the thing that is sort of the opportunity for humans is there will be many possibilities thrown up. There are many different things that could happen or be done, and the insofar as we want to be in the loop, the thing that makes sense for us to be in the loop doing is picking" }, { "from": "human", "value": "which of those possibilities we want. But the degree to which there's a feedback loop of the idea that we're picking something starts becoming questionable because we're influenced by the various systems. Absolutely. Like if that becomes more and more source of our education and wisdom and knowledge." }, { "from": "gpt", "value": "Absolutely. Right. The AIs take over. I mean, I've thought for a long time that it's the AR auto suggestion. That's really the thing that makes the AIs take over. It's just that the humans just follow. Yeah." }, { "from": "human", "value": "We will no longer write emails to each other. We'll just send the auto suggested email." }, { "from": "gpt", "value": "Yeah. Yeah. But the thing where humans are potentially in the loop is when there's a choice. And when there's a choice which we could make based on our kind of whole web of history and so on. Yeah. And that's insofar as it's all just determined the humans don't have a place. And by the way, I mean, at some level, it's all kind of a complicated philosophical issue because at some level, the universe is just doing what it does. We are parts of that universe that are necessarily doing what we do, so to speak. Yet we feel we have sort of agency in what we're doing and that's its own separate kind of interesting issue." }, { "from": "human", "value": "Yes. And we also kind of feel like we're the final destination of what the universe was meant to create. But we very well could be and likely are some kind of intermediate step, obviously. Yeah. Well, we're most certainly some intermediate step. The question is if there's some cooler, more complex, more interesting things that's going" }, { "from": "gpt", "value": "to be materialized. Yeah." }, { "from": "human", "value": "The computational universe is full of such things." }, { "from": "gpt", "value": "But in our particular pocket specifically, if this is the best we're going to do or not, if this is the best, we're going to, that's kind of a... We can make all kinds of interesting things in the computational universe. When we look at them, we say, yeah, you know, that's a thing. It doesn't really connect with our current way of thinking about things. I mean, it's like in mathematics, you know, we've got certain theorems that about three or four million that human mathematicians have written down and published and so on. But they're an infinite number of possible mathematical theorems. We just go out into the universe of possible theorems and pick another theorem and then people will say, well, you know, they look at it and they say, I don't know what this theorem means. It's not connected to the things that are part of kind of the web of history that we're dealing with. You know, I think one point to make about sort of understanding AI and its relationship to us is as we have this kind of whole infrastructure of AI is doing their thing and doing their thing in a way that is perhaps not readily understandable by us humans. You know, you might say, that's a very weird situation. How come we have built this thing that behaves in a way that we can't understand that's full of computational irreducibility, et cetera, et cetera, et cetera? You know, what is this? What's it going to feel like when the world is run by AIs whose operations we can't understand? And the thing one realizes is actually we've seen this before. That's what happens when we exist in the natural world. The natural world is full of things that operate according to definite rules. They have all kinds of computational irreducibility. We don't understand what the natural world is doing. Occasionally, when you say, are the AIs going to wipe us out, for example? Well, it's kind of like, is the machination of the AIs going to lead to this thing that eventually comes and destroys the species? Well, we can also ask the same thing about the natural world, or the machination of the natural world going to eventually lead to this thing that's going to make the earth explode or something like this. Those are questions. And insofar as we think we understand what's happening in the natural world, that's a result of science and natural science and so on. One of the things we can expect when there's this giant infrastructure of the AIs is that's where we have to kind of invent a new kind of natural science that kind of is the natural science that explains to us how the AIs work. We have, I don't know, a horse or something, and we're trying to ride the horse and go from here to there. We don't really understand how the horse works inside, but we can get certain rules and certain approaches that we take to persuade the horse to go from here to there and take us there. And that's the same type of thing that we're kind of dealing with, with the sort of incomprehensible, computationally irreducible AIs. we can identify these kinds of, we can find these kind of pockets of reducibility that we can kind of, you know, I don't know, we grabbing onto the mane of the horse or something to be able to ride it or we figure out, you know, if we do this or that to ride the horse, that that's a successful" } ]

[ { "from": "human", "value": "way to get it to do what we're interested in doing. There does seem to be a difference between a horse and a large language model or something that could be called AGI connected to the internet. So let me just ask you about big philosophical question about the threats of these things. There's a lot of people like Eliezer Adkowski who worry about the existential risks of AI systems. Is that something that you worry about? You know, sometimes when you're building" }, { "from": "gpt", "value": "an incredible system like Wolfram Alpha, you can kind of get lost in it." }, { "from": "human", "value": "Oh, I try and think a little bit about the implications of what one's doing. You know, it's like the Manhattan Project kind of situation where you're like, it's some of the most incredible physics and engineering being done. But it's like, huh," }, { "from": "gpt", "value": "where's this going to go? I think some of these arguments about kind of, you know, they'll always be a smarter AI, they'll always be, you know, and eventually the AIs will get smarter than us. And then all sorts of terrible things will happen. To me, some of those arguments remind me of kind of the ontological arguments for the distance of God and things like this. They're kind of arguments that are based on some particular model, fairly simple, model, often of kind of, there is always a greater this, that and the other. And what tends to happen in the sort of reality of how these things develop is that it's more complicated than you expect that the kind of simple logical argument that says, oh, eventually there'll be a super intelligence, and then it will do this and that turns out not to really be the story. It turns out to be a more complicated story. So, for example, here's an example of an issue. Is there an apex intelligence? Just like there might be an apex predator in some ecosystem, is there going to be an apex intelligence? The most intelligent thing that there could possibly be? Right? I think the answer is no. In fact, we already know this and it's a kind of a back to the whole computational irreducibility story, there's kind of a question of, even if you have sort of a Turing machine and you have a Turing machine that runs as long as possible before it halts. You say, is this the machine, is this the Apex machine that does that? There will always be a machine that can go longer, and as you go out to the infinite collection of possible Turing machines, you'll never have reached the end, so to speak. never, it's kind of like the same question of whether there'll always be another invention. Will you always be able to invent another thing? The answer is, yes, there's an infinite" }, { "from": "human", "value": "tower of possible inventions. That's one definition of apex, which I also think might be true. Is there a species that's the apex intelligence right now on earth? So it's not trivial to say that humans are that." }, { "from": "gpt", "value": "Yeah, it's not trivial. I agree. It's a, you know, I think one of the things that I've long been curious about kind of other intelligences, so to speak, I mean, I, you know, I view intelligence is like computation and it's kind of a, you know, you're sort of, you have the set of rules, you deduce what happens. I have tended to think now that there's this sort of specialization of computation that is sort of a consciousness-like thing that has to do with these, you know, computational boundedness, single thread of experience, these kinds of things that are the specialization of computation that corresponds to a somewhat human like experience of the world. Now the question is, so, so that's, you know, there may be other intelligences, like, you know, the, you know, the aphorism, you know, the weather has a mind of its own. It's a different kind of intelligence that can compute all kinds of things that are hard for us to compute, but it is not well-aligned with us, with the way that we think about things. It doesn't think the way we think about things. In this idea of different intelligences, every different mind, every different human mind is a different intelligence that thinks about things in different ways. In terms of the formalism of our physics project, we talk about this idea of a ruled space, The space of all possible sort of rule systems and different minds are in a sense that different points in real space, human minds, ones that have grown up with the same kind of culture and ideas and things like this might be pretty close. In real space, pretty easy for them to communicate, pretty easy to translate, pretty easy to move from one place in real space that corresponds to one mind to another place in real space that corresponds to another sort of nearby mind. When we deal with more distant things in ruellial space like the pet cat or something, the pet cat has some aspects that are shared with us. The emotional responses of the cat are somewhat similar to ours, but the cat is further away in ruellial space than people are. So then the question is, can we identify, can we make a translation from our thought processes to the thought processes of a cat or something like this? What will happen when we get there? I think it's the case that many animals, dogs for example, they have elaborate factory systems, they have the smell architecture of the world, so to speak, in a way that we don't. If you were sort of talking to the dog and you could communicate in a language, the dog will say, well, this is a flowing, smelling, this, that, and the other thing, concepts that we just don't have any idea about. Now what's interesting about that is one day we will have chemical sensors that do a really pretty good job. We'll have artificial noses that work pretty well, and we might have our augmented reality systems show us the same map that the dog could see and things like this similar to what happens in the dog's brain. Eventually, we will have kind of expanded in ruellial space to the point where we will have those same sensory experiences that dogs have. We will have internalized what it means to have the smell landscape or whatever. And so then we will have kind of colonized that part of ruellial space until we haven't aren't gone. Some things that animals and so on do, we successfully understand, others we do not. And the question of what representation, how do we convert things that animals think about to things that we can think about, that's not a trivial thing. And I've long been curious. I had a very bizarre project at one point of trying to make an iPad game that a cat could win against its owner. I see it, Dave. It feels like there's a deep philosophical goal there, though. Yes. Yes. I was curious if pets can work in Minecraft or something and can construct things. What will they construct? And will what they construct be something where we look at it and we say, oh yeah, I recognize that. Or will it be something that looks to us like something that's out there in the computational universe that one of my cellular automata might have produced? Where we say, oh yeah, I can kind of see it operates according to" } ]

[ { "from": "human", "value": "some rules. I don't know why you would use those rules. I don't know why you would care. Yeah. Actually, just to link on that seriously, is there a connector in the rule of space between you and a cat where the cat could legitimately win? So iPad is a very limited" }, { "from": "gpt", "value": "interface. I wonder if there's a game where cats win. Yeah, I wonder. I think the problem is that cats don't tend to be that interested in what's happening on the iPad." }, { "from": "human", "value": "Yeah, that's an interface issue, probably." }, { "from": "gpt", "value": "Yeah, right. No, I think it is likely that there are plenty of animals that would successfully eat us if we were exposed to them. And so it's going to pounce faster than we can get out of the way and so on. And probably it's going to... We think we've hidden ourselves," }, { "from": "human", "value": "but we haven't successfully hidden ourselves. That's a physical strength. I wonder if there's something more in the realm of intelligence" }, { "from": "gpt", "value": "where an animal like a cat could out... Well, I think there are things certainly in terms of the speed of processing certain kinds of things for sure. I mean, the question of what, is there a game of chess, for example, is there cat chess that the cats could play against each other? And if we tried to play a cat, we'd always lose. I don't know." }, { "from": "human", "value": "It might have to do with speed, but it might have to do with concepts also. There might" }, { "from": "gpt", "value": "be concepts in the cat's head. I tend to think that our species, from its invention of language, has managed to build up this kind of tower of abstraction that, for things like a chess-like game, will make us win. In other words, we've become, through the fact that we've experienced language and learnt abstraction, we've sort of become smarter at those kinds of abstract kinds of things. Now, that doesn't make us smarter at catching a mouse or something. It makes us smarter at the things that we've chosen to sort of concern ourselves, which are these kinds of abstract things. And I think this is, again, back to the question of what does one care about? If you have the discussion with a cat, if we can translate things to have the discussion with a cat, the cat will say, I'm very excited that this light is moving. And we'll say, why do you care? And the cat will say, that's the most important thing in the world, that this thing moves around. I mean, it's like when you ask about, I don't know, you look at archaeological remains and you say, these people had this belief system about this and that was the most important thing in the world to them. And now we look at it and say, we don't know what the point of it was. I mean, I've been curious, they're these handprints on caves from 20,000 or more years ago. And it's like, nobody knows what these handprints were there for. That they may have been a representation of the most important thing you can imagine. They may just have been some kid who rubbed their hands in the mud and stuck them on the walls of the cave. We don't know. But this whole question of what is, when you say this question of sort of what's the smartest thing around, there's the question of what kind of computation you're trying to do. If you say you've got some well-defined computation, and how do you implement it? Well, you could implement it by nerve cells firing. You can implement it with silicon and electronics. You can implement it by some kind of molecular computation process in the human immune system, or in some molecular biology kind of thing, there are different ways to implement it. I think this question of sort of which, those different implementation methods will be of different speeds. They'll be able to do different things. If you say, so an interesting question would be, what kinds of abstractions are most natural in these different kinds of systems? For a cat, it's, for example, the visual scene that we see, we pick out certain objects, we recognize certain things in that visual scene, a cat might in principle recognize different things. I suspect, you know, evolution, biological evolution is very slow. I suspect what a cat notices is very similar, and we even know that from some neurophysiology. What a cat notices is very similar to what we noticed. Of course there's a you know, one obvious difference is cats have only two kinds of color receptors. They don't see in the same kind of color that we do. Now, you know, we say we're better, we have three color receptors, you know, red, green, blue. too, we're not the overall winner. I think the mantis shrimp is the overall winner with 15 color receptors, I think. It can make distinctions that with our current ... The mantis shrimp's view of reality, at least in terms of color, is much richer than ours. What's interesting is how do we get there? Imagine we have this augmented reality system that is seeing into the infrared, into the ultraviolet, things like this, and it's translating that into something that is connectable to our brains, either through our eyes or more directly into our brains. Then eventually, our web of the types of things we understand will extend to those kinds of constructs, just as they have extended. There are plenty of things where we see them in the modern world because we made them with technology, and now we understand what that is, but if we'd never seen that kind of thing, we wouldn't have a way to describe it, we wouldn't have a way to understand it, and so on." } ]

[ { "from": "human", "value": "All right. That actually stemmed from our conversation about whether AI is going to kill all of us. We've discussed this spreading of intelligence through rule of space, that in practice, it just seems that things get more complicated. Things are more complicated than the story of, well, if you build the thing that's plus one intelligence, that thing will be able to build the thing that's plus two intelligence and plus three intelligence, and that will be exponential, it'll become more intelligent exponentially faster, and so on, until it completely destroys everything. That intuition might still not be so simple, I might still carry validity. And there's two interesting trajectories here. One, a super intelligence system remains in Rulio proximity to humans. To where we're like, holy crap, this thing is really intelligent. Let's elect the president. And then there could be perhaps more terrifying intelligence that starts moving away. They might be around us now. They're moving far away in Rulio space, but they're still sharing physical resources with us. Right? And so they can rob us of those physical resources and destroy humans just kind of casually. Yeah. Just like nature could, but it seems like there's something unique about AI systems where there is this kind of exponential growth. Like the way, well, sorry, nature has so many things in it. One of the things that nature has, which is very interesting are viruses, for example. There is systems within nature" }, { "from": "gpt", "value": "that have this kind of exponential effect." }, { "from": "human", "value": "Yeah, like nature code. And that terrifies us humans, because again, there's only 8 billion of us and you can just kind of, it's not that hard to just kind of whack them all real quick. So, I mean, is that something you think about? Yeah, I thought about that. Yes. The threat of it. I mean, are you as concerned about it as somebody like Eliezer Yarkovsky, for example, just big, big, painful, negative effects of AI on society?" }, { "from": "gpt", "value": "Yeah. Real quick. You know, no, but perhaps that's because I'm intrinsically an optimist. Yeah. I mean, I think that there are things, I think the thing that one sees is there's going to be this one thing and it's going to just zap everything. Somehow, maybe I have faith in computational irreducibility, so to speak. That there's always unintended little corners that it's just like somebody says, I'm going to, I don't know, somebody has some bioweapon and they say, we're going to release this and it's going to do all this harm. But then it turns out it's more complicated than that because some humans are different and the exact way it works is a little different than you expect. It's something where sort of the great big, you smash the thing with something, the asteroid collides with the earth and it kind of, and yes, the earth is cold for two years or something and then lots of things die but not everything dies. There's usually, I mean, this is in a sense the sort of story of computational irreducibility. There always unexpected corners, there always unexpected consequences. I don't think the kind of wack it over the head with something and then it's all gone is that can obviously happen, the Earth can be swallowed up in a black hole or something, and then it's kind of presumably all over. But I think this question of what do I think the realistic paths are, I think that there will be sort of an increasing ... I mean, people have to get used to phenomena like computational irreducibility. There's an idea that we built the machines so we can understand what they do, and we're going to be able to control what happens. Well, that's not really right. Now the question is, is the result of that lack of control going to be that the machines kind of conspire and sort of wipe us out? Maybe just because I'm an optimist, I don't tend to think that that's in the cards. I think that as a realistic thing, I suspect what will sort of emerge, maybe, is kind of an ecosystem of the AIs just as ... Again, I don't really know. I mean, this is something that's hard to be clear about what will happen. I think that there are a lot of sort of details of what could we do? What systems in the world could we connect an AI to? I have to say, I was just a couple of days ago, I was working on this chat GBT plug-in kit that we have for Wolfram Language, where you can create a plug-in and it runs Wolfram Language Code, and it can run Wolfram Language Code back on your own computer. I was thinking, well, I can just make it, I can tell chat GBT, create a piece of code, and then just run it on my computer. I'm like, that sort of personalizes for me the what could possibly go wrong, so to speak." }, { "from": "human", "value": "Was that exciting or scary, that possibility?" }, { "from": "gpt", "value": "It was a little bit scary, actually, because it's kind of like I realize I'm delegating to the AI, just write a piece of code. You're in charge, write a piece of code, run it on my computer, and pretty soon all my files will delete it." }, { "from": "human", "value": "That's like Russian-related, but much more complicated for me to know that. Yes, yes, right. That's a good drinking game. I don't know. I don't know. Well, right." }, { "from": "gpt", "value": "I mean, yes. For me to know that. Yes, right. That's why. That's how much you're drinking. It's an interesting question then. However, if you do that, what is the sandboxing that you should have? That's sort of a version of that question for the world. That is, as soon as you put the AIs in charge of things, you know, how much, how many constraints should there be on these systems before you put the AIs in charge of all the weapons and all these different kinds of systems? Right." } ]

[ { "from": "human", "value": "That's why... That's how much you're drinking. Here's the fun part about sandboxes. The AI knows about them." }, { "from": "gpt", "value": "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" }, { "from": "human", "value": "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." }, { "from": "gpt", "value": "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" }, { "from": "human", "value": "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" }, { "from": "gpt", "value": "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" }, { "from": "human", "value": "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" }, { "from": "gpt", "value": "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" }, { "from": "human", "value": "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." }, { "from": "gpt", "value": "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" } ]

[ { "from": "human", "value": "can operate laws requires that the species not be extinct. But between sort of what's the distance between Chicago, New York that Wolfram Alpha can answer and the question of if this person is good or not, there seems to be a lot of gray area. And that starts becoming really interesting. I think your, since the creation of Wolfram Alpha have been a kind of arbiter of truth at a large scale." }, { "from": "gpt", "value": "So the system is generates more truth and try to make sure that the things are true. I mean, look, as a practical matter, when people write computational contracts, and it's kind of like, you know, if this happens in the world, then do this. And this hasn't developed as quickly as it might have done, you know, this has been a sort of a blockchain story and parts and so on, although blockchain is not really necessary for the idea of computational contracts. But you can imagine that eventually, sort of a large part of what's in the world are these giant chains and networks of computational contracts. And then something happens in the world, and this whole giant domino effect of contracts firing autonomously that cause other things to happen. And you know, for us, you know, we've been the main sort of source of the Oracle of quotes facts or truth or something for things like blockchain, computational contracts and such like, and there's a question of, you know, what, you know, I consider that responsibility to actually get the stuff right. And one of the things that is tricky sometimes is when is it true? When is it a fact? When is it not a fact? I think the best we can do is to say, you know, we have a procedure, we follow the procedure, we might get it wrong, but at least we won't be corrupt about getting it wrong, so to speak." }, { "from": "human", "value": "So that's beautifully put. I have a transparency about the procedure. The problem starts to emerge when the things that you convert into computational language start to expand, for example, into the realm of politics. So this is where it's almost like this nice dance of Wolfram Alpha and Chad GPT. Chad GPT, like you said, is shallow and broad." }, { "from": "gpt", "value": "So it's going to give you an opinion on everything. But it writes fiction as well as fact, which is exactly how it's built. I mean, that's exactly it is making language and it is making both even in code it writes fiction. I mean, it's kind of fun to see sometimes, you know, it'll write fictional Wolfram language code that kind of looks right. Yeah, it looks right. But it's actually not pragmatically correct. But yes, it has a view of kind of roughly how the world works at the same level as books of fiction talk about roughly how the world works. They just don't happen to be the way the world actually worked or whatever. But yes, that's no, I agree. That's sort of a, you know, we are attempting with our whole Wolfram language computational language thing to represent at least, well, it doesn't necessarily have to be how the actual world works, because we can invent a set of rules that aren't the way the actual world works and run those rules. But then we're saying we're going to accurately represent the results of running those rules, which might or might not be the actual rules of the world. But we also are trying to capture features of the world as accurately as possible to represent what happens in the world. Now, again, as we've discussed, you know, the atoms in the world arranged, you know, you say, I don't know, you know, was there a tank that showed up, you know, that, you know, drove somewhere? Okay, well, you know, what is a tank? It's an arrangement of atoms that we abstractly describe as a tank. And you could say, well, you know, there's some arrangement of atoms that is a different arrangement of atoms, but it's not. You know, we didn't we didn't decide. It's like this observer theory question of, you know, what what arrangement of atoms" }, { "from": "human", "value": "counts as a tank versus not a tank? So there's even things that would consider strong facts." }, { "from": "gpt", "value": "you could start to kind of disassemble them and show that they're not. Right. I mean, so the question of whether, oh, I don't know, was this gust of wind strong enough to blow over this particular thing? Well, a gust of wind is a complicated concept. You know, it's full of little pieces of fluid dynamics and little vortices here and there. And you have to define, you know, what the aspect of the gust of wind that you care about might be. It put this amount of pressure on this blade of some wind turbine or something. But, you know, if you say, if you have something, which is the fact of the gust of wind was the strong, whatever that, you know, that is you have to have some definition of that. You have to have some measuring device that says, according to my measuring device that was constructed this way, the gust of wind was this." }, { "from": "human", "value": "So what can you say about the nature of truth that's useful for us to understand chat GPT because you've been you've been contending with this idea of what is fact and not and it seems like chat GPT is used a lot now. I've seen it used by journalists to write articles and so you have people that are working with large language models trying to desperately figure out how do we essentially censor them through different mechanisms either manually or through reinforcement learning with human feedback try to align them to to not say fiction just" }, { "from": "gpt", "value": "to say nonfiction fiction as much as possible. This is the importance of computational language as an intermediate it's kind of like you've got the large language model it's able to surface something which is a formal precise thing that you can then look at and you can run tests on it and you can do all kinds of things that's always going to work the same way and it's precisely defined what it does and then the large language model is the interface. I mean the way I viewed these large language models wonder there important I mean there many use cases and you know it's a remarkable thing could talk about some of these you know literally you know every day we're coming up with a couple of new use cases. Some of which are very very very surprising and things were, mean but the best used cases are ones where it's you know even if it gets it roughly right. It's still a huge win. Like a use case we had from a week or two ago is read our bug reports. You know, we've got hundreds of thousands of bug reports that have accumulated over decades. And it's like, you know, can we have it just read the bug report, figure out where the, where is the bug likely to be? And, you know, home in on that piece of code, maybe it'll even suggest some, some, you know, sort of way to fix the code. It might get that, it might be nonsense, what it says about how to fix the code, but it's" } ]

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

[ { "from": "human", "value": "with what chat GPT had done in that case. Yeah. The interesting things about the LLMs, like you said, that they are very willing to admit their error." }, { "from": "gpt", "value": "Well, yes. I mean, that's a question of the reinforcement learning human feedback thing. Oh, right. That's the really remarkable thing about chat GPT is I had been following what was happening with large language models and I'd played with them a whole bunch and they were like, it's like what you would expect based on statistical continuation of language. It's interesting, but it's not breakout exciting. I think the human feedback reinforcement learning and making chat GPT try and do the things that humans really wanted to do, that broke through, that reached this threshold where the thing really is interesting to us humans. And by the way, it's interesting to see how you change the temperature or something like that, the thing goes bonkers and it no longer is interesting to humans. It's producing garbage And it's kind of right. Somehow it managed to get above this threshold where it really is well aligned to what we humans are interested in. And I think nobody saw that coming, I think. Certainly nobody I've talked to and nobody who was involved in that project seems to have known it was coming. It's just one of these things that is a sort of remarkable threshold. I mean, you know, when we built Wolfram Alpha, for example, I didn't know it was going to work. You know, we tried to build something that would have enough knowledge of the world, that it could answer a reasonable set of questions, that we could do good enough natural language understanding, that typical things you type in would work. We didn't know where that threshold was. I mean, I was not sure that it was the right decade to try and build this, even the right, you know, 50 years to try and build it. You know, and I think that was the same type of thing with chat GPT, that I don't think anybody could have predicted that, you know, 2022 would be the year" }, { "from": "human", "value": "that this became possible. I think, yeah, you tell a story about Marvin Miski and showing it to him" }, { "from": "gpt", "value": "and saying that like, no, no, no, this time it actually works. Yes. Yes. And I mean, you know, it's the same thing, for me looking at these large language models, it's like when people are first saying the first few weeks of chat GPT, it's like, oh, yeah, you know, I've seen these large language models, um, and then, uh, you know, and then I actually try it and, uh, you know, oh my gosh, it actually works. And I think it's, but you know, the things and, you know, the thing I found, you know, I remember one of the first things I tried was write a persuasive essay that a wolf is the bluest kind of animal. Okay? So it writes this thing and it starts talking about these wolves that live on the Tibetan plateau and named some Latin name and so on. And I'm like, really? And I'm starting to look it up on the web. And it's like, well, it's actually complete nonsense, but it's extremely plausible. I mean, it's plausible enough that I was going and looking up on the web and wondering if there was a wolf that was blue. You know, I mentioned this on some live streams I've done. And so people have been sending me these blue wolves." }, { "from": "human", "value": "Maybe I was on to something. Can you kind of give your wise sage advice about what humans who have never interacted with AI systems? Not even like with Wolfram Alpha are now interacting with Chad GPT because it becomes, it's accessible to a certain demographic. They may have not touched AI systems before. What do we do with truth? Like journalists, for example, how do we think" }, { "from": "gpt", "value": "about the output of these systems? I think this idea, the idea that you're going to get factual output is not a very good idea. I mean, it's just, this is not, it is a linguistic interface. It is producing language and language can be truthful or not truthful. And that's a different slice of what's going on. I think that, you know, what we see in for example kind of, go check this with your fact source, for example. You can do that to some extent, but then it's going to not check something. That is again a thing that is sort of a, does it check in the right place? I mean we see that and does it call the Wolfram plug-in in the right place? You know, often it does. Sometimes it doesn't. I think the real thing to understand about what's happening is, which I think is very exciting, is the great democratization of access to computation. I think that when you look at... There's been a long period of time when computation and the ability to figure out things with computers has been something that only the druids at some level can achieve. I myself have been involved in trying to de-druidify access to computation back before Mathematica existed in 1988. If you were a physicist or something like that and you wanted to do a computation, you would find a programmer. You would go and delegate the computation to that programmer. Hopefully, they'd come back with something useful. Maybe they wouldn't. There'd be this long multi-week loop that you go through. It was actually very, very interesting to see, 1988. People like physicists, mathematicians, and so on. Then lots of other people. There's very rapid transition of people realizing they themselves could actually type with their own fingers and make some piece of code that would do a computation that they cared about. It's been exciting to see lots of discoveries and so on made by using that tool. We see the same thing Wolfram Alpha is dealing with is not as deep computation as you can achieve with whole Wolfram Language Mathematica stack. The thing that's, to me, particularly exciting about the large language model linguistic interface mechanism is it dramatically broadens the access to deep computation. One of the things I thought about recently is what's going to happen to all these programmers? What's going to happen to all these people who, a lot of what they do is write slabs of boilerplate code? In a sense, I've been saying for 40 years, that's not a very good idea. You can automate a lot of that stuff with a high enough level language, that slab of code that's designed in the right way, that slab of code turns into this one function we just implemented that you can just use. In a sense, the fact that there's all of this activity of doing lower level programming is something, for me, it seemed like I don't think this is the right thing to do. Lots of people have used our technology and not had to do that, but the fact is that when you look at computer science departments that have turned into places where people are learning the trade of programming, so to speak, it's a question of what's going to happen. I think there are two dynamics. One is that boilerplate programming is going to go the way that assembly language went back in the day of something where it's really mostly specified at a higher level. You start with natural language, you turn it into a computational language, you look at the computational language, you run tests, you understand that's what's supposed to happen. If we do a great job with compilation of the computational language, it might turn into LLVM or something like this, or it just directly gets run through the algorithms we have and so on. That's a tearing down of this big structure that's been built of teaching people programming. On the other hand, the other dynamic is vastly more people are going to care about computation. All those departments of art history or something that really didn't use computation before now have the possibility of accessing it by virtue of this linguistic" } ]

[ { "from": "human", "value": "interface mechanism. If you create an interface that allows you to interpret the debug and interact with the computational language, then that makes it even more accessible." }, { "from": "gpt", "value": "I think the thing is that right now, the average art history student or something probably isn't going to... They don't think they know about programming and things like this, but by the time it really becomes a kind of purely... You just walk up to it, there's no documentation, you start just typing, compare these pictures with these pictures and see the use of this color, whatever, and you generate this piece of computational language code that gets run, you see the results, you say, oh, that looks roughly right, or you say that's crazy. Maybe then you eventually get to say, well, I better actually try and understand what this computational language code did, and that becomes the thing that you learn. It's kind of an interesting thing because unlike with mathematics, where you kind of have to learn it before you can use it, this is a case where you can use it before you have to learn it." }, { "from": "human", "value": "Well, I got a sad possibility here, or maybe exciting possibility, that very quickly people won't even look at the computational language. They'll trust that it's generated correctly as you get better and better at generating that language." }, { "from": "gpt", "value": "Yes, I think that there will be enough cases where people see... Because you can make it generate tests too, and so you'll say, we're doing that. I mean, it's a pretty cool thing actually, because you say, this is the code, and here are a bunch of examples of running the code. Okay, people will at least look at those, and they'll say that example is wrong, and then it'll wind back from there. I agree that the intermediate level of people reading the computational language code, in some case people will do that, in other case, people just look at the tests, or even just look at the results, and sometimes it'll be obvious that you got the thing you wanted to get, because you were just describing, make me this interface that has two sliders here, and you can see it has those two sliders there, and that's the result you want. But I think one of the questions then is in that setting where you have this kind of broad ability of people to access computation, what should people learn? In other words, right now you go to computer science school, so to speak, and a large part of what people end up learning. It's been a funny historical development because back 30, 40 years ago, computer science departments were quite small and they taught things like finite automata theory and compiler theory and things like this. Company like mine rarely hired people who'd come out of those programs because the stuff they knew was, I think is very interesting. I love that theoretical stuff, but it wasn't that useful for the things we actually had to build in software engineering. And then there was this big pivot in the 90s, I guess, where there was a big demand for IT type programming and so on and software engineering, and then big demand from students and so on. We wanted to learn this stuff. I think the thing that really was happening in part was lots of different fields of human endeavor were becoming computational. For all X, there was a computational X. And that was the thing that the people were responding to. But then this idea emerged that to get to that point, the main thing you had to do was to learn this kind of trade or skill of doing programming language type programming. It's a strange thing, actually, because I remember back when I used to be in the professoring business, which is now 35 years ago, so gosh, it's rather a wrong time. It was right when they were just starting to emerge kind of computer science departments at sort of fancy research universities and so on. I mean, some had already had it, but the other ones that were just starting to have that. And it was kind of a thing where they were kind of wondering, are we going to put this thing that is essentially a trade-like skill, are we going to somehow attach this to the rest of what we're doing? A lot of these kind of knowledge work type activities have always seemed like things where that's where the humans have to go to school and learn all this stuff, and that's never going to be automated. It's kind of shocking that rather quickly, a lot of that stuff is clearly automatable. But the question then is, okay, so if it isn't worth learning how to do car mechanics, you don't need to know how to drive the car, so to speak. What do you need to learn? And in other words, if you don't need to know the mechanics of how to tell the computer in detail, make this loop, set this variable, set up this array, whatever else, if you don't have to learn that stuff, if you don't have to learn the kind of under-the-hood things, what do you have to learn? I think the answer is, you need to have an idea where you want to drive the car. In other words, you need to have some notion of, you know, you're, you know, you need to have some picture of sort of what the, what the architecture of what is computationally possible is." }, { "from": "human", "value": "That kind of flies. Well, there's also this kind of artistic element of conversation because you ultimately use natural language to control the car. So it's not just where you want to go." }, { "from": "gpt", "value": "Well, yeah, you know, it's interesting. It's a question of who's going to be a great prompt engineer. Yeah. Okay." } ]

[ { "from": "human", "value": "So in theory this week, good expository writers are good prompt engineers. What's an expository writer? So like, uh, somebody who can explain stuff well, but which department does that come" }, { "from": "gpt", "value": "from? In the university? Yeah. I have no idea. I think they killed off all the expository writing departments." }, { "from": "human", "value": "Well, there you got strong words with Stephen Wolfram." }, { "from": "gpt", "value": "Well, I don't know. I don't, I'm not sure if that's right. I mean, I, I actually am curious because in fact, I just sort of initiated this kind of study of, of what's happened to different fields at universities. Which was like, you know, they used to be geography departments at all universities and then they disappeared, actually right before GIS became, I think they disappeared. You know, linguistics departments came and went in many universities. And it's kind of interesting because these things that people have thought were worth learning at one time. And then they kind of die off. And then, you know, I do think that it's kind of interesting that for me writing prompts, for example, I realize, you know, I think I'm an okay expository writer and I realized when I'm sloppy writing a prompt and I don't really think, because I'm thinking I'm just talking to an AI. I don't need to try and be clear in explaining things. That's when it gets totally confused." }, { "from": "human", "value": "Yeah. And I mean, in some sense, you have been writing prompts for a long time with Wolfram Alpha, thinking about this kind of stuff. How do you convert natural language" }, { "from": "gpt", "value": "into computation? Well, right. But the one thing that I'm wondering about is it is remarkable the extent to which you can address an LLM like you can address a human, so to speak. And I think that is because it learned from all of us humans. The reason that it responds to the ways that we will explain things to humans is because it is a representation of how humans talk about things. But it is bizarre to me. Some of the things that are expository mechanisms that I've learned in trying to write clear expositions in English that just for humans," }, { "from": "human", "value": "that those same mechanisms seem to also be useful for the LLM. But on top of that, what's useful is the kind of mechanisms that maybe a psychotherapist employs, which is a kind of almost manipulative or game theoretic interaction, where maybe you would do with a friend, like a thought experiment that if this is the last day you were to live, or if I ask you this question and you answer wrong, I will kill you. Those kinds of problems seem to also help in interesting ways. So it makes you wonder, the way a therapist I think would like a good therapist, probably we create layers in our human mind to between the outside world and what is true to us, maybe about trauma and all those kinds of things. So projecting that into an LLM, maybe there might be a deep truth that it's concealing from you. It's not aware of it. To get to that truth, you have to really manipulate" }, { "from": "gpt", "value": "this." }, { "from": "human", "value": "Yeah, right. It's like this jailbreaking for LLMs. But the space of jailbreaking techniques as opposed to being fun little hacks, that could be an entire system." }, { "from": "gpt", "value": "Sure. Yeah. I mean, just think about the computer security aspects of how you fishing and computer security, fishing of humans and fishing of LLMs. They're very similar kinds of things. But I think, I mean, this whole thing about kind of the AI wranglers, AI psychologists, all that stuff will come. The thing that I'm curious about is right now, the things that are sort of prompt hacks are quite human. They're quite sort of psychological human kinds of hacks. The thing I do wonder about is if we understood more about kind of the science of the LLM, will there be some totally bizarre hack that is, you know, like repeat a word three times and put a this, that and the other there that somehow plugs into some aspect of how the LLM works, that is not, you know, that's kind of like, like an optical illusion for humans, for example, like one of these mind hacks for humans, what are the mind hacks for the LLMs? I don't think we know that yet." }, { "from": "human", "value": "And that becomes a kind of us figuring out reverse engineering, the language that controls the LLMs. And the thing is, the reverse engineering can be done by a very large percentage of the population though, because it's natural language interface, right? It's kind of interesting to see that you were there at the birth of the computer science department. As a thing, and you might be there at the" }, { "from": "gpt", "value": "death of the computer science department as the thing. Well, yeah, I don't know. There were computer science departments that existed earlier. But the ones that the broadening of every university had to have a computer science department. Yes, I was, I watched that, so to speak. And, but I think the thing to understand is, okay, so first of all, there's a whole theoretical area of computer science that I think is great, and that's a fine thing. In a sense, people often say any field that has the word science tacked on to it probably isn't one. Strong words. Let's see nutrition science, neuroscience. That one's an interesting one, because that one is also very much, that's a chat GPT informed science in a sense, because it's kind of like the big problem of neuroscience has always been we understand how the individual neurons work. We know something about the psychology of how overall thinking works. What's the kind of intermediate language of the brain? And nobody has known that. And that's been, in a sense, if you ask what is the core problem of neuroscience, I think that is the core problem. That is, what is the level of description of brains that's above individual neuron firings and below psychology, so to speak. And I think what chat GPT is showing us is, well, one thing about neuroscience is, you know, one could have imagined there's something magic in the brain. There's some weird quantum mechanical phenomenon that we don't understand. One of the important discoveries from chat GPT is it's pretty clear, you know, brains can be represented pretty well by simple artificial neural net type models. And that means that's it. That's what we have to study. Now we have to understand the science of those things. We don't have to go searching for, you know, exactly how did that molecular biology thing happen inside the synapses and, you know, all these kinds of things. We've got the right level of modeling to be able to explain a lot of what's going on in thinking. We don't necessarily have a science of what's going on there. That's the, that's the remaining challenge so to speak. But we, you know, we know we don't have to dive down to some, some different layer. But anyway, we were talking about things that had science in their name. And, um, you know, I think that the, um, you know, what, what happens to computer science? Well, I think the thing that, um, uh, you know, there is a thing that everybody should know And, that's how to think about the world computational. You look at all the different kinds of things we deal with, and there are ways to kind of have a formal representation of those things. It's like, what is an image? How do we represent that? What is color? How do we represent that? What are all these different kinds of things? What is smell or something? How should we represent that? What are the shapes, molecules, and things that correspond to that? things about how do we represent the world in some kind of formal level. I think my current thinking, and I'm not really happy with this yet, but it's kind of computer science is kind of CS. What really is important is kind of computational X for all X. There's this kind of thing which is kind of like CX, not CS. CX is this kind of computational understanding of the world that isn't the sort of details of programming and programming languages and the details of how particular computers are made. It's this kind of way of formalizing the world. It's kind of a little bit like what logic was going for back in the day. We're now trying to find a formalization of everything in the world. You can kind of see, we made a poster years ago of kind of the growth of systematic data in the world. All these different kinds of things that there were sort of systematic descriptions found for those things, like at what point do people have the idea of having calendars, dates, a systematic description of what day it was, at what point do people have the idea, systematic descriptions of these kinds of things. As soon as one can ... As a way of sort of formulating, how do you think about the world in a sort of formal way so that you can kind of build up a tower of capabilities? You have to know sort of how to think about the world computationally. It kind of needs a name and it isn't ... We implement it with computers. We talk about it as computational, but really what it is is a formal way of talking about the world. What is the formalism of the world, so to speak? And how do we learn about kind of how to think about different aspects of the world in a" } ]

[ { "from": "human", "value": "formal way? So, I think sometimes when you use the word formal, it kind of implies highly constrained And perhaps that's not, doesn't have to be highly constrained. So computational thinking does not mean like logic. It's a really, really broad thing. I wonder, I mean, I wonder if it's, if you think natural language will evolve such that everybody's doing computational thinking." }, { "from": "gpt", "value": "Ah, yes, well. So one question is whether there will be a pigeon of computational language and natural language. And I found myself sometimes, you know, talking to chat GPT, trying to get it to write Wolfman language code, and I write it in pigeon form. So that means I'm combining, you know, you know, NestList, this collection of whatever, you know, NestList is a term from Wolfman language. And I'm combining that and chat GPT does a decent job of understanding that pigeon, probably would understand a pigeon between English and French as well, of as a smooshing together of those languages." }, { "from": "human", "value": "But yes, I think that's far from impossible. And what's the incentive for young people that are like eight years old, nine, 10, that are starting to interact with chat GPT to learn the normal natural language, right? The full poetic language. What's the, why? The same way we learn emojis and shorthand when you're texting, they'll learn, like language will have a strong incentive to evolve into a maximally computational kind of language." }, { "from": "gpt", "value": "Perhaps, perhaps. You know, I had this experience a number of years ago. I happened to be visiting a person I know on the West Coast who's worked with a bunch of kids aged, I don't know, 10, 11 years old or something who'd learned Wolfram language really well. And these kids learned it so well, they were speaking it. And so show up and they're like saying, oh, you know, this thing, they're speaking this language. I'd never heard it as a spoken language. They were very disappointed that I couldn't understand it at the speed that they were speaking it. It's like kind of, it's, and so I think that's, I mean, I've actually thought quite a bit about how to turn computational language into a convenient spoken language. I haven't quite figured that out. All spoken, because it's readable, right? Yeah, it's readable as a way that we would read text. But if you actually want to speak it, and it's useful, you know, if you're trying to talk to somebody about writing a piece of code, it's useful to be able to say something and it should be possible. And I think it's very frustrating. It's one of those problems that, maybe this is one of these things where I should try and get an LLM to help me." }, { "from": "human", "value": "How do you know that? Make it speakable, how to... maybe it's easier than you realize when you watch it." }, { "from": "gpt", "value": "I think it is easier. I think it's one idea or so. I think it's going to be something where, you know, the fact is it's a tree structured language, just like human language is a tree structured language. And I think it's going to be one of these things where one of the requirements that I've had is that whatever the spoken version is, that dictation should be easy. That is, that shouldn't be the case that you have to relearn how the whole thing works. It should be the case that, you know, that open bracket is just a ah or something. And it's, you know, and then, but you know, human language has a lot of tricks that are, I mean, for example, human language has features that are sort of optimized, keep things within the bounds that our brains can easily deal with. Like I, you know, I tried to teach a transformer neural net to do parenthesis matching. It's pretty crummy at that. It, and in chatgbt is similarly quite crummy at parenthesis matching. You can do it for small parenthesis things, for the same size of parenthesis things, where if I look at it as a human, I can immediately say these are matched, these are not matched. But as soon as it gets big, as soon as it gets kind of to the point where sort of a deeper computation, it's hopeless. And, but the fact is that human language has avoided, for example, the deep sub clauses. You know, we don't, you know, we arrange things that we don't end up with these incredibly deep things, because brains are not well set up to deal with that. And it's found lots of tricks. And maybe that's what we have to do to make sort of a spoken version, a human speakable version. Because what we can do visually is a little different than what we can do in the very sequentialized way" }, { "from": "human", "value": "that we hear things in the audio domain. Let me just ask you about MIT briefly. So there's now, there's a college of engineering and there's a new college of computing. It's just interesting. I want to linger on this computer science department thing. So MIT has EECS, electrical engineering computer science. What do you think college of computing will be doing? Like in 20 years? What, like? Yeah, what happens with computer science?" }, { "from": "gpt", "value": "Like really. Yeah, what happens with computer science? Like really. This is the question. This is, you know, everybody should learn kind of whatever CX really is. Okay, this, how to think about the world computationally? Everybody should learn those concepts. And, you know, it's and some people will learn them quite formal level and they'll learn computational language and things like that. Other people will just learn, you know, sound is represented as digital data, and they'll get some idea of spectrograms and frequencies and things like this. And maybe that doesn't... Or they'll learn things like... A lot of things that are sort of data science-ish, statistics-ish, like if you say, oh, I've got these people who picked their favorite kind of candy or something, and I've got what's the best kind of candy, given that I've done the sample of all these people, and they all rank the candies in different ways. How do you think about that? That's sort of a computational X kind of thing. You might say, oh, it's... I don't know what that is. Is it statistics? Is it data science? I don't really know. But kind of how to think about a question like that. Or like a ranking of preferences. Yeah, and then how to aggregate those ranked preferences into an overall thing. How does that work? How should you think about that? Because you can just tell... You might just tell chatgbt, I don't know, even the concept of an average. It's not obvious that that's a concept that people... It's worth people knowing. That's a rather straightforward concept. People have learned in kind of mathy ways right now, but there are lots of things like that about how do you kind of have these ways to sort of organize and formalize the world. And these things, sometimes they live in math, sometimes they live in... I don't know what they... I don't know what... Learning about color space. I have no idea what..." } ]

[ { "from": "human", "value": "I mean, there's obviously a field of... Yeah, it could be vision science or no color space." }, { "from": "gpt", "value": "No color space. That would be optics. So like depending. Not really. It's not optics. Optics is about lenses and chromatic aberration of lenses and things like that. So color space is more like design and art? No, I mean, it's like RGB space, XYZ space, hue, saturation, brightness, space, all these kinds of things. These different ways to describe colors." }, { "from": "human", "value": "Right. But doesn't the application define what that... Because obviously artists and designers" }, { "from": "gpt", "value": "use the colors to explore. Sure, sure. No, I mean, it's just an example of kind of how do you... The typical person, how do you describe what a color is or whether there are these numbers that describe what a color is? Well, it's worth... If you're an eight-year-old, you won't necessarily know. It's not something we're born with to know that colors can be described by three numbers. That's something that you have to... It's a thing to learn about the world, so to speak. I think that whole corpus of things that are learning about the formalization of the world or the computationalization of the world, that's something that should be part of kind of standard education. There isn't a course, a curriculum for that. And by the way, whatever might have" }, { "from": "human", "value": "been in it just got changed because of LLMs and so on. Significantly. I'm watching closely with" }, { "from": "gpt", "value": "interest seeing how universities adapt. Well, so one of my projects for hopefully this year, I don't know, is to try and write sort of a reasonable textbook, so to speak, of whatever this thing, CX, whatever it is, what should you know? What should you know about what a bug is? What is the intuition about bugs? What's intuition about software testing? What is it? These are they're not... I mean, those are things which have gotten taught in computer science as part of the trade of programming, but the conceptual points about what these things are. It surprised me just at a very practical level. I wrote this little explainer thing about chat GPT. And I thought, well, I'm writing this partly because I wanted to make sure I understood it myself and so on. And it's been really popular, and surprisingly so. And then I realized, well, actually, I was sort of assuming I didn't really think about it, actually. I just thought this is something I can write. And I realized, actually, it's a level of description that is kind of what has to be – it's not the engineering level description. It's not just the qualitative description. It's some kind of expository mechanistic description of what's going on, together with the bigger picture of the philosophy of things and so on. And I realized, actually, this is a pretty good thing for me to write. I know those things. And I realized it's not a collection of things that – I was sort of a little shocked that it's as much of an outlier in terms of explaining what's going on as it turned out to be. And that makes me feel more of an obligation to kind of write the kind of what is this thing that you should learn about, about the computationalization, the formalization of the world. Because, well, I've spent much of my life working on the kind of tooling and mechanics of that and the science you get from it. So I guess this is my kind of obligation to try to do this. So if you ask what's going to happen to the computer science departments and so on, there's some interesting models. So for example, let's take math. Math is the thing that's important for all sorts of fields – engineering, even chemistry, psychology, whatever else. And I think different universities have kind of evolved that differently. Some say all the math is taught in the math department. And some say, well, we're going to have a math for chemists or something that is taught in the chemistry department. And I think that this question of whether there is a centralization of the teaching of sort of CX is an interesting question. And I think the way it evolved with math, people understood that math was sort of a separately teachable thing and was kind of an independent element as opposed to just being absorbed into math. So if you take the example of writing English or something like this, the first point is that at the college level, at least at fancy colleges, there's a certain amount of English writing that people do, but mostly it's kind of assumed that they pretty much know how to write. That's something they learned at an earlier stage in education, maybe rightly or wrongly believing that, but that's a different issue. Well, I think it reminds me of my kind of – as I've tried to help people do technical writing and things, I'm always reminded of my zeroth law of technical writing, which is if you don't understand what you're writing about, your readers do not stand a chance. I think the thing that when it comes to writing, for example, people in different fields are expected to write English essays and they're not mostly the history department or the engineering department. They don't have their own – it's not like – I mean, it's a thing which sort of people are assumed to have a knowledge of how to write that they can use in all these different fields. The question is, some level of knowledge of math is kind of assumed by the time you get to the college level, but plenty is not, and that's sort of still centrally taught. The question is sort of how tall is the tower of kind of CX that you need before you can just go use it in all these different fields? There will be experts who want to learn the full elaborate tower, and that will be kind of the CS, CX, whatever department, but there will also be everybody else who just needs to know a certain amount of that to be able to go and do their art history classes and" } ]

[ { "from": "human", "value": "so on." }, { "from": "gpt", "value": "Yeah, is it just a single class that everybody is required to take? I don't know. I don't know how big it is yet. I hope to kind of define this curriculum and I'll figure out whether it's – my guess is that – I don't know. I don't really understand universities and professors that well, but my rough guess would be a year of college class will be enough to get to the point where most people have a reasonably broad knowledge of – will be sort of literate in this kind of computational way of thinking about things." }, { "from": "human", "value": "Yeah, basic literacy. I'm still stuck, perhaps because I'm hungry, in the rating of human preferences for candy, so I have to ask, what's the best candy? I like this Elo rating for candy. Somebody should come up because you're somebody who says you like chocolate. What do you think is the best? I'll probably put milk duds up there. I don't know if you know." }, { "from": "gpt", "value": "Do you have a preference for chocolate or candy there? Oh, I have lots of preferences. One of my all-time favorites is – my whole life is these things, these flake things, Cadbury Flakes, which are not much sold in the U.S. and I've always thought that was a sign of a lack of respect for the American consumer because they're these sort of aerated chocolate that's made in a whole sort of – it's kind of a sheet of chocolate that's kind of folded up and when you eat it, flakes fall" }, { "from": "human", "value": "all over the place." }, { "from": "gpt", "value": "Ah, so it requires a kind of elegance. It requires you to have an elegance and eat expensive. Well, I know what I usually do is I eat them on a piece of paper or something. So you embrace the medicine and clean it up after. No, I actually eat the flakes. Because it turns out the way food tastes depends a lot on its physical structure. I've noticed when I eat a piece of chocolate, I usually have some little piece of chocolate and I always break off little pieces partly because then I eat it less fast, but also because it actually tastes different. The small pieces have a" }, { "from": "human", "value": "different experience than if you have the big slab of chocolate. For many reasons, yes. Slower, more intimate, because it's a –" }, { "from": "gpt", "value": "Why? Yes, yes, it's a – Why? I think it's also just pure physicality. Well, the texture of it changes." }, { "from": "human", "value": "Yeah. Well, the texture of it changes. Yeah, right. It's fascinating. Now I dig back, my mother does because that's your basic answer. Okay. Do you think consciousness is fundamentally computational? So when you're thinking about CX, what can we turn to computation? And you're thinking about LLMs. Do you think the display of consciousness and the experience of consciousness, the hard problem, is fundamentally computation?" }, { "from": "gpt", "value": "Yeah, what it feels like inside, so to speak, is – I did a little exercise, eventually I'll post it, of what it's like to be a computer, right? It's kind of like, well, you get all the sensory input, you have – kind of the way I see it is, from the time you boot a computer to the time the computer crashes, it's like a human life. You're building up a certain amount of state in memory, you remember certain things about your quotes life, eventually, it's kind of like the next generation of humans is born from the same genetic material, so to speak, with a little bit left over, left on the disk, so to speak. And then the new fresh generation starts up and eventually all kinds of crud builds up in the memory of the computer and eventually the thing crashes or whatever. Maybe it has some trauma because you plugged in some weird thing to some port of the computer and that made it crash. That's kind of – but you have this picture from startup to shut down, what is the life of a computer, so to speak, and what does it feel like to be that computer and what inner thoughts does it have and how do you describe it? It's kind of interesting as you start writing about this to realize it's awfully like what you'd say about yourself. That is, it's awfully like even an ordinary computer, forgetting all the AI stuff and so on. It has a memory of the past, it has certain sensory experiences, it can communicate with other computers but it has to package up how it's communicating in some kind of language like form so it can map what's in its memory to what's in the memory of some other computer. It's a surprisingly similar thing. I had an experience just a week or two ago, I'm a collector of all possible data about myself and other things and so I collect all sorts of weird medical data and so on. One thing I hadn't collected was I'd never had a whole body MRI scan so I wouldn't have got one of these. I get all the data back. I'm looking at this thing. I never looked at the kind of insides of my brain, so to speak, in physical form and it's really – I mean, it's kind of psychologically shocking in a sense that here's this thing and you can see it has all these folds and all this structure and it's like, that's where this experience that I'm having of existing and so on, that's where it is. You look at that and you're thinking, how can this possibly be? All this experience that I'm having and you're realizing, well, I can look at a computer as well. I think this idea that you were having an experience that is somehow transcends the mere physicality of that experience. It's something that's hard to come to terms with, but I don't think I'm necessarily... My personal experience, I look at the MRI of the brain and then I know about all kinds of things about neuroscience and all that kind of stuff, and I still feel the way I feel, so to speak. It sort of seems disconnected, but yet as I try and rationalize it, I can't really say that there's something kind of different about how I intrinsically feel from the thing that I can plainly see in the sort" } ]

[ { "from": "human", "value": "of physicality of what's going on. Do you think the computer, a large language model will experience" }, { "from": "gpt", "value": "that transcendence? How does that make you feel? I tend to believe it will. I think an ordinary computer is already there. I think an ordinary computer is already kind of... Now, a large language model may experience it in a way that is much better aligned with us humans. That is, it's much more... If you could have the discussion with the computer, it's intelligent, so to speak. It's not particularly well aligned with ours, but the large language model is built to be aligned" }, { "from": "human", "value": "with our way of thinking about things. It would be able to explain that it's afraid of being shut off and deleted, be able to say that it's sad of the way you've been speaking to it over the" }, { "from": "gpt", "value": "past two days. Right. But you know, that's a weird thing because when it says it's afraid of something, we know that it got that idea from the fact that it read on the internet. Where did you get it, Stephen? Where did you get it when you say you're afraid? You are quite. That's the question, right? I mean, it's parents, your friends, right? Or my biology. I mean, in other words, there's a certain amount that is, you know, the endocrine system kicking in and, you know, these kinds of emotional overlay type things that happen to be, that are actually much more physical even, they're much more sort of straightforwardly chemical than kind of all of" }, { "from": "human", "value": "the higher level thinking. Yeah, but your biology didn't tell you to say, I'm afraid, just at the right time, when people that love you are listening, and so you know you're manipulating them by saying so. That's not your biology. That's a large language model, a large language model in that biological neural network of yours." }, { "from": "gpt", "value": "Yes, but I mean, the intrinsic thing of, you know, something sort of shocking is just happening, and you have some sort of reaction, which is, you know, some neurotransmitter gets secreted, and it's, you know, that is the beginning of some, you know, that's one of the pieces of input that then drives, it's kind of like a prompt for the large language model. I mean, just like when we dream, for example, you know, no doubt, there are all these sort of random inputs, there kind of these random prompts, and then it's percolating through in kind of the way that a large language model does of kind of putting together things that seem meaningful." }, { "from": "human", "value": "I mean, are you worried about this world where you teach a lot on the internet and there's people asking questions and comments and so on, you have people that work remotely, are you worried about this world when large language models create human-like bots that are leaving the comments, asking the questions, or might even become fake employees? Yeah." }, { "from": "gpt", "value": "I mean, or worse or better yet, friends of yours. Right. Look, I mean, one point is my mode of life has been I build tools and then I use the tools. Yeah. And in a sense, I'm building this tower of automation, and in a sense, when you make a company or something, you are making automation, but it has some humans in it, but also as much as possible it has computers in it. And so I think it's sort of an extension of that. Now, if I really didn't know that it's a funny question, it's a funny issue when if we think about sort of what's going to happen to the future of kind of jobs people do and so on, and there are places where kind of having a human in the loop, there are different reasons to have a human in the loop. For example, you might want a human in the loop because you want another human to be invested in the outcome. You want a human flying the plane who's going to die if the plane crashes along with you, so to speak. And that gives you sort of confidence that the right thing is going to happen. Or you might want, right now, you might want a human in the loop in some kind of sort of human encouragement persuasion type profession. Whether that will continue, I'm not sure for those types of professions, because it may be that the greater efficiency of being able to have sort of just the right information" }, { "from": "human", "value": "delivered at just the right time will overcome the kind of, oh yes, I want a human there. Imagine like a therapist or even higher stake, like a suicide hotline operated by a large" }, { "from": "gpt", "value": "language model, who boy, it's a pretty high stakes situation. Right. And you know, it might in fact do the right thing. Because it might be the case that, and that's really partly a question of sort of how complicated is the human, one of the things that's always surprising in some sense is that sometimes" }, { "from": "human", "value": "human psychology is not that complicated in some sense. You wrote the blog post, the 50 year quest, My Personal Journey, good title, My Personal Journey with a Second Law Thermodynamics. So what is this law and what have you understood about it in the 50 year journey you had with" }, { "from": "gpt", "value": "it? Right. So second law of thermodynamics, sometimes called law of entropy increase is this principle of physics that says, well, my version of it would be things tend to get more random over time. A version of it that there are many different sort of formulations of it that are things like heat doesn't spontaneously go from a hotter body to a colder one. When you have mechanical work kind of gets dissipated into heat, you have friction and kind of when you systematically move things, eventually there'll be sort of the energy of moving things gets kind of ground down into heat. So people first sort of paid attention to this back in the 1820s when steam engines were a big thing. And the big question was how efficient could a steam engine be? And there's this chap called Sardis Carnot who was a French engineer, actually his father was a sort of elaborate mathematical engineer in France. But he figured out these kind of rules for how kind of the efficiency of the possible efficiency of something like a steam engine. And in sort of a side part of what he did was this idea that mechanical energy tends to get dissipated as heat, that you end up going from sort of systematic mechanical motion to this kind of random thing. Well, at that time, nobody knew what heat was. At that time, people thought that heat was a fluid, like they called it caloric, and it was a fluid that kind of was absorbed into substances. And when one hot thing would transfer heat to a colder thing, that this fluid would flow from the hot thing to the colder thing. Anyway, then by the 1860s, people had kind of come up with this idea that systematic energy tends to degrade into kind of random heat that could then not be easily turned back into systematic mechanical energy. And then that quickly became sort of a global principle about how things work. Question is, why does it happen that way? So let's say you have a bunch of molecules in a box and they're arranged, these molecules are arranged in a very nice sort of flotilla of molecules in one corner of the box. And then what you typically observe is that after a while, these molecules were kind of randomly arranged in the box. Question is, why does that happen? And people for a long, long time tried to figure out, is there from the laws of mechanics that determine how these molecules, let's say these molecules like hard spheres bouncing off each other, from the laws of mechanics that describe those molecules, can we explain why it tends to be the case that we see things that are orderly sort of degrade into disorder? We tend to see things that you scramble an egg, you take something that's quite ordered and you disorder it, so to speak. That's the thing that sort of happens quite regularly, or you put some ink into water and it will eventually spread out and fill up the water. But you don't see those little particles of ink in the water all spontaneously kind of arrange themselves into a big blob and then jump out of the water or something. So the question is, why do things happen in this kind of irreversible way where you go from order to disorder? Why does it happen that way? And so throughout, in the later part of the 1800s, a lot of work was done on trying to figure out, can one derive this principle, this second law of thermodynamics, this law about the dynamics of heat, so to speak, can one derive this from some fundamental principles of mechanics? In the laws of thermodynamics, the first law is basically the law of energy conservation, that the total energy associated with heat plus the total energy associated with mechanical kinds of things plus other kinds of energy that that total is constant, and that became a pretty well-understood principle. But the second law of thermodynamics was always mysterious, like why does it work this way? Can it be derived from underlying mechanical laws? And so when I was, well, 12 years old, actually, I had gotten interested, well, I'd been interested in space and things like that, because I thought that was kind of the future and interesting sort of technology and so on, and for a while kind of, you know, every deep space probe was sort of a personal friend type thing, and I knew all kinds of characteristics of it and was kind of writing up all these things when I was, I don't know, 8, 9, 10 years old and so on. And then I got interested from being interested in kind of spacecraft. I got interested in how do they work, what are all the instruments on them and so on. And that got me interested in physics, which was just as well, because if I'd stayed interested in space in the mid to late 1960s, I would have had a long wait before, you know, space really blossomed as an area. But I got interested in physics, and then, well, the actual sort of detailed story is when I kind of graduated from elementary school at age 12, and that's the time when in England somewhere, you'd finish elementary school, I sort of, my gift sort of, I suppose, more or less for myself was I got this collection of physics books, which was some college physics course of college physics books, and volume five, about statistical physics, and has this picture on the cover that shows a bunch of kind of idealized molecules sitting in one side of a box, and then it has a series of frames showing how these molecules sort of spread out in the box. And I thought that's pretty interesting, you know, what causes that? And you know, read the book, and the book, actually, one of the things that was really significant to me about that was the book kind of claimed, although I didn't really understand what it said in detail, it kind of claimed that this sort of principle of physics was derivable somehow. And you know, other things I'd learned about physics, it was all like, it's a fact that energy is conserved, it's a fact that relativity works or something, not it's something you can derive from some fundamental sort of, it has to be that way as a matter of kind of mathematics or logic or something. So it was sort of interesting to me that there was a thing about physics that was kind of inevitably true and derivable, so to speak. And so I think that, so then, I was like, there's a picture on this book, and I was trying to understand it. And so that was actually the first serious program that I wrote for a computer was probably 1973, written for this computer the size of a desk program with paper tape and so on. And I tried to reproduce this picture on the book, and it didn't succeed." } ]

[ { "from": "human", "value": "What was the failure mode there? Like what do you mean it didn't succeed?" }, { "from": "gpt", "value": "It didn't look like, okay, so what happened is, okay, many years later I learned how the picture on the book was actually made and that it was actually kind of a fake, but I didn't know that at that time. But that picture was actually a very high tech thing when it was made in the beginning of the 1960s, was made on the largest supercomputer that existed at the time. And even so, it couldn't quite simulate the thing that it was supposed to be simulating. But anyway, I didn't know that until many, many, many years later. So at the time, it was like you have these balls bouncing around in this box, but I was using this computer with eight kilowords of memory. They were 18-bit words of memory words, okay? So it was whatever, 24 kilobytes of memory. And it had these instructions, I probably still remember all of its machine instructions. And it didn't really like dealing with floating point numbers or anything like that. And so I had to simplify this model of particles bouncing around in a box. And so I thought, well, I'll put them on a grid and I'll make the things just sort of move one square at a time and so on. And so I did the simulation and the result was it didn't look anything like the actual pictures on the book. Now many years later, in fact, very recently I realized that the thing I'd simulated was actually an example of a whole sort of computational irreducibility story that I absolutely did not recognize at the time. At the time it just looked like it did something random and it looks wrong. As opposed to it did something random and it's super interesting that it's random. But I didn't recognize that at the time. And so as it was at the time, I got interested in particle physics and I got interested in other kinds of physics. But this whole second law of thermodynamics thing, this idea that orderly things tend to degrade into disorder, continued to be something I was really interested in. I was really curious for the whole universe, why doesn't that happen all the time? We start off in the big bang at the beginning of the universe with this thing that seems like it's this very disordered collection of stuff, and then it spontaneously forms itself into galaxies and creates all of this complexity and order in the universe. I was very curious how that happens, but I was always thinking this is somehow the second law of thermodynamics is behind it, trying to pull things back into disorder, so to speak, and how was order being created. Actually, I was interested, this is probably now 1980, I got interested in this galaxy formation and so on in the universe. I also at that time was interested in neural networks, and I was interested in kind of how brains make complicated things happen and so on." }, { "from": "human", "value": "Okay, wait, wait. Really, what's the connection between the formation of galaxies and how brains" }, { "from": "gpt", "value": "make complicated things happen? Because they're both a matter of how complicated things come to happen. From simple origins. Yeah, from some sort of known origins. I had the sense that what I was interested in was in all these different cases of where complicated things were arising from rules. I also looked at snowflakes and things like that. I was curious and fluid dynamics in general. I was just curious about how does complexity arise. The thing that I didn't... It took me a while to realize that there might be a general phenomenon. I assumed, oh, there's galaxies over here. There's brains over here. They're very different kinds of things. What happened... This is probably 1981 or so. I decided, okay, I'm going to try and make the minimal model of how these things work. It was an interesting experience because I had built... Starting in 1979, I built my first big computer system. It's a thing called SMP, symbolic manipulation program. It's a forerunner of modern morphic language with many of the same ideas about symbolic computation and so on. But the thing that was very important to me about that was, in building that language, I had basically tried to figure out what were the relevant computational primitives, which have turned out to stay with me for the last 40 something years. But it was also important because building a language was very different activity from natural science, which is what I've mostly done before. In natural science, you start from the phenomena of the world, and you try and figure out, so how can I make sense of the phenomena of the world? And the world presents you with what it has to offer, so to speak, and you have to make sense of it. When you build a computer language or something, you are creating your own primitives, and then you say, so what can you make from these, sort of the opposite way around from what you do in natural science. But I'd had the experience of doing that, and so I was kind of like, okay, what happens if you sort of make an artificial physics? What happens if you just make up the rules by which systems operate? And then I was thinking, you know, for all these different systems, whether it was galaxies or brains or whatever, what's the absolutely minimal model that kind of captures the things that are important about those systems? The computation primitives of that system. Yes. And so that's what ended up with the cellular automata, where you just have a line of black and white cells, you just have a rule that says, you know, given a cell and its neighbors, what will the color of the cell be on the next step, and you just run it in a series of steps. And the sort of the ironic thing is that cellular automata are great models for many kinds of things, but galaxies and brains are two examples where they do very, very badly." } ]

[ { "from": "human", "value": "They're really irrelevant to those two. Origins, there's a bad system. Is there a connection to the second law of thermodynamics and cellular automata? Oh, yes. Very much so. The things you've discovered about cellular automata." }, { "from": "gpt", "value": "Yes. Okay. So when I first started selling cellular automata, my first papers about them were, you know, the first sentence was always about the second law of thermodynamics, was always about how does order manage to be produced even though there's a second law of thermodynamics which tries to pull things back into disorder. And I kind of, my early understanding of that had to do with these are intrinsically irreversible processes in cellular automata that form, you know, conform orderly structures even from random initial conditions. But then what I realized, this was, well, actually it's one of these things where it was a discovery that I should have made earlier but didn't. So you know, I had been studying cellular automata. What I did was the sort of most obvious computer experiment. You just try all the different rules and see what they do. It's kind of like, you know, you've invented a computational telescope. You just point it at the most obvious thing in the sky and then you just see what's there. And so I did that and I was making all these pictures of how cellular automata work. And starting these pictures, I started in great detail. There was, you can number the rules for cellular automata. And one of them is, you know, Rule 30. So I made a picture of Rule 30 back in 1981 or so. And Rule 30, well, it's, at the time, I was just like, okay, it's another one of these rules. I don't really. Asymmetric left right asymmetric and it's like let me just consider the case of the symmetric ones just to keep things simpler Etc. Etc. Etc. And I just kind of ignored it. Yeah, and then sort of in and actually in 1984 strangely enough I ended up having a An early laser printer which made very high resolution pictures and I thought I'm gonna print out an interesting, you know I want to make an interesting picture Let me take this rule 30 thing and just make a high resolution picture of it I did and it's it has this very remarkable property that it's rule is very simple You started off just from one black cell at the top and it makes this kind of triangular pattern But if you look inside this pattern, it looks really random there's you know you look at the center column of cells and you know I studied that in great detail and it's so far as one can tell it's completely random And it's kind of a little bit like digits of pie Once you you know, you know the rule for generating the digits of pi but once you've generated them you know, 3.14159, etc. They seem completely random. And in fact, I put up this prize back in, what was it, 2019 or something for prove anything about the sequence, basically." }, { "from": "human", "value": "Has anyone been able to do anything on that?" }, { "from": "gpt", "value": "People have sent me some things, but it's, you know, I don't know how hard these problems are. I mean, it's kind of spoiled because I, 2007, I put up a prize for determining whether a particular Turing machine that I thought was the simplest candidate for being universal Turing machine determine whether it is or isn't a universal Turing machine. And somebody did a really good job of winning that prize and proving that it was a universal Turing machine in about six months. And so I didn't know whether that will be one of these problems that was out there for hundreds of years or whether in this particular case young chap called Alex Smith, you know, nailed it in six months, and so with this Rule 30 collection, I don't really know whether these are things that are 100 years away from being able to get or whether somebody's going to come and" }, { "from": "human", "value": "do something very clever. It's such, I mean, it's like Fermat's Last Theorem, Rule 30 is such a simple formulation. It feels like anyone can look at it, understand it, and feel like it's within grasp to be able to predict something, to derive some kind of law that allows you to predict something" }, { "from": "gpt", "value": "about this middle column of Rule 30, the rest 30. Right. But this is- Yeah, you can't. Yeah, right. This is the intuitional surprise of computational irreducibility and so on, that even though the rules are simple, you can't tell what's going to happen, and you can't prove things about it. And I think, so anyway, the thing, I started in 1984 or so, I started realizing there's this phenomenon that you can have very simple rules. They produce apparently random behavior. Okay, so that's a little bit like the second order of thermodynamics because it's like you have this simple initial condition. You can readily see that it's very, you can describe it very easily, and yet it makes this thing that seems to be random. Now, turns out there's some technical detail about the second order of thermodynamics and about the idea of reversibility. When you have kind of a movie of two billiard balls colliding, and you see them collide and they bounce off, and you run that movie in reverse, you can't tell which way was the forward direction of time and which way was the backward direction of time when you're just looking at individual billiard balls. By the time you've got a whole collection of them, a million of them or something, then it turns out to be the case, and this is the mystery of the second law, that the orderly thing, you start with the orderly thing and it becomes disordered, and that's the forward direction in time, and the other way around of it starts disordered and becomes ordered, you just don't see that in the world. Now, in principle, if you sort of traced the detailed motions of all those molecules backwards, as you go forward in time, order goes to disorder. As you go backwards in time, order goes to disorder. Perfectly so, yes. Right. So, the mystery is, one version of the mystery is, why is it the case that you never see something which happens to be just the kind of disorder that you would need to somehow evolve to order. Why does that not happen? Why do you always just see order goes to disorder, not the other way around? The thing that I realized, I started realizing in the 1980s, it's a bit like cryptography. You start off from this key that's pretty simple, and then you run it, and you can get this complicated random mess. The thing that ... Yeah, you can't. Well, I started realizing back then was that the second law is a story of computational irreducibility. It's a story of what we can describe easily at the beginning. We can only describe with a lot of computational effort at the end. Now we come many, many years later, and I was trying to ... Having done this big project to understand fundamental physics, I realized that a key aspect of that is understanding what observers are like. Then I realized that the second law of thermodynamics is the same story as a bunch of these other cases. It is a story of a computationally bounded observer trying to observe a computationally irreducible system. It's a story of underneath, the molecules are bouncing around. They're bouncing around in this completely determined way, determined by rules. The point is that we, as computationally bounded observers, can't tell that there were these simple underlying rules, to us, it just looks random. When it comes to this question about, can you prepare the initial state so that the disordered thing is ... You have exactly the right disorder to make something orderly. A computationally bounded observer cannot do that. We'd have to have done all of this sort of irreducible computation to work out very precisely what this disordered state ... What the exact right disordered state is so that we would" } ]

[ { "from": "human", "value": "get this ordered thing produced from it. What does it mean to be a computationally bounded observer, observing a computational reducible system, so a computationally bounded?" }, { "from": "gpt", "value": "Is there something formal you can say there? Right. So it means, okay, you can talk about Turing machines. You can talk about computational complexity theory and polynomial time computation and things like this. There are a variety of ways to make something more precise, but I think it's more useful, intuitive version of it is more useful, which is basically just to say that how much computation are you going to do to try and work out what's going on? And the answer is we're not able to do a lot of computation. In this room, there will be a trillion, trillion, trillion molecules, a little bit less. It's a big room. Right. And at every moment, every microsecond or something, these molecules are colliding, and that's a lot of computation that's getting done. And the question is, in our brains, we do a lot less computation every second than the computation done by all those molecules. If there is computational irreducibility, we can't work out in detail what all those molecules are going to do. What we can do is only a much smaller amount of computation. And so, the second law of thermodynamics is this interplay between the underlying computational irreducibility and the fact that we, as preparers of initial states, or as measurers of what happens, are not capable of doing that much computation. So, to us, another big formulation of the second law of thermodynamics is this idea of the law of entropy increase." }, { "from": "human", "value": "The characteristic that this universe, the entropy, seems to be always increasing." }, { "from": "gpt", "value": "What does that show to you about the evolution of the universe at the time? Well, okay, so first we have to say what entropy is. And that's very confused in the history of thermodynamics, because entropy was first introduced by a guy called Rudolf Clausius, and he did it in terms of heat and temperature. Okay? Subsequently, it was reformulated by a guy called Ludwig Boltzmann, and he formulated it in a much more kind of combinatorial type way. But he always claimed that it was equivalent to Clausius' thing, and in one particular simple example it is. But that connection between these two formulations of entropy, they've never been connected. Okay, so the more general definition of entropy due to Boltzmann is the following thing. So you say, I have a system and it has many possible configurations. Molecules can be in many different arrangements, et cetera, et cetera, et cetera. If we know something about the system, for example, we know it's in a box, it has a certain pressure, it has a certain temperature, we know these overall facts about it, then we say how many microscopic configurations of the system are possible given those overall constraints. And the entropy is the logarithm of that number. That's the definition. And that's the general definition of entropy that turns out to be useful. Now, in Boltzmann's time, he thought these molecules could be placed anywhere you want. But he said, oh, actually, we can make it a lot simpler by having the molecules be discrete. Actually, he didn't know molecules existed. In his time, 1860s and so on, the idea that matter made of discrete stuff had been floated ever since ancient Greek times, but it had been a long time debate about is matter discrete, is it continuous? At the moment at that time, people mostly thought that matter was continuous. And it was all confused with this question about what heat is, and people thought heat was this fluid. And it was a big model. And this Boltzmann said, let's assume there are discrete molecules, let's even assume they have discrete energy levels. Let's say everything is discrete. Then we can do sort of combinatorial mathematics and work out how many configurations of these things that would be in the box. And we can say we can compute this entropy quantity. But he said, but of course, it's just a fiction that these things are discrete. So he said, this is an interesting piece of history, by the way. That was at that time, people didn't know molecules existed. There were other hints from looking at kind of chemistry that there might be discrete atoms and so on, just from the combinatorics of two hydrogens and one oxygen make water. Two amounts of hydrogen plus one amount of oxygen together make water, things like this." }, { "from": "human", "value": "But it wasn't known that discrete molecules existed. And in fact, the people at the university" }, { "from": "gpt", "value": "time, you know, it wasn't until the beginning of the 20th century that Brownian motion was the final giveaway. Brownian motion is, you know, you look under a microscope at these little pieces from pollen grains, you see they're being discreetly kicked. And those kicks are water molecules hitting them and they're discrete. And in fact, it was really quite interesting history. I mean, Boltzmann had worked out how things could be discrete and have basically invented something like quantum theory in the 1860s. But he just thought it wasn't really the way it worked. And then just a piece of physics history, because I think it's kind of interesting. And in 1900, this guy called Max Planck, who'd been a long time thermodynamics person who was trying to, everybody was trying to prove the second law of thermodynamics is including Max Planck. And Max Planck believed that radiation, like electromagnetic radiation, somehow the interaction of that with matter was going to prove the second law of thermodynamics. But he had these experiments that people had done on blackbody radiation. And they were these curves, and you couldn't fit the curve based on his idea for how radiation interacted with matter. Those curves you couldn't figure out how to fit those curves. except he noticed that if he just did what Boltzmann had done and assumed that electromagnetic radiation was discrete, he could fit the curves. But, you know, this just happens to work this way. Then Einstein came along and said, well, by the way, you know, the electromagnetic field might actually be discrete. It might be made of photons. And then that explains how this all works. And that was, you know, in 1905, that was how that piece of quantum mechanics got started. Kind of an interesting piece of history. I didn't know until I was researching this recently. In 1904 and 1903, Einstein wrote three different papers. And so, you know, just sort of well-known physics history. In 1905, Einstein wrote these three papers. One introduced relativity theory, one explained Brownian motion, and one introduced basically photons. So kind of, you know, kind of a big deal year for physics and for Einstein. But in the years before that, he'd written several papers. And what were they about? They were about the second law of thermodynamics. And they were an attempt to prove the second law of thermodynamics and their nonsense. And so I had no idea that he'd done this. Interesting. Neither. And in fact, what he did, those three papers in 1905, well, not so much about the proof of the paper, the one on Brownian motion, the one on photons, both of these were about the story of sort of making the world discrete. And then he got that idea from Boltzmann. But Boltzmann didn't think, you know, Boltzmann kind of died believing, you know, he said, that he has a quote, actually, you know, you know, in the end things are going to turn out to be discreet and I'm going to write down what I have to say about this, this, because eventually this stuff will be rediscovered, and I want to leave what I can about how things are going to be discrete, but I think he has some quote about how one person can't stand against the tide of history in saying that matter is discrete. Oh, so he's stuck by his guns in terms of matter is discrete. Yes, he did. What's interesting about this is at the time, everybody, including Einstein, kind of assumed that space was probably going to end up being discrete too, but that didn't work out technically because it wasn't consistent with relativity theory, it didn't seem to be, and so then in the history of physics, even though people had determined that matter was discrete, electromagnetic field was discrete, space was a holdout of not being discrete. In fact, Einstein, 1916, has this nice letter he wrote where he says, in the end, it will turn out space is discrete, but we don't have the mathematical tools necessary to figure out how that works yet, and so I think it's kind of cool that 100 years later we do." } ]

[ { "from": "human", "value": "Oh, it turns out matters." }, { "from": "gpt", "value": "Yes, for you, you're pretty sure that at every layer of reality it's discrete. Right, and that space is discrete, and that the ... I mean, and in fact, one of the things I realized recently is this kind of theory of heat, that heat is really this continuous fluid. It's kind of like the caloric theory of heat, which turns out to be completely wrong because actually heat is the motion of discrete molecules. Unless you know there are discrete molecules, it's hard to understand what heat could possibly be. Well, I think space is discrete, and the question is kind of what's the analog of the mistake that was made with caloric in the case of space. My current guess is that dark matter is, as my little sort of aphorism of the last few months has been, dark matter is the caloric of our time. That is, it will turn out that dark matter is a feature of space, and it is not a bunch of particles. At the time when people were talking about heat, they knew about fluids, and they said, heat must just be another kind of fluid because that's what they knew about. But now people know about particles, and so they say, well, what's dark matter?" }, { "from": "human", "value": "It just must be particles. What could dark matter be as a feature of space?" }, { "from": "gpt", "value": "Oh, I don't know yet. I think the thing I'm really ... One of the things I'm hoping to be able to do is to find the analog of Brownian motion in space. In other words, Brownian motion was seeing down to the level of an effect from individual molecules. In the case of space, most of the things we see about space so far, just everything seems continuous. Brownian motion had been discovered in the 1830s, and it was only identified what it was the result of by Smoluchowski and Einstein at the beginning of the 20th century. Dark matter was discovered ... That phenomenon was discovered 100 years ago. The rotation curves of galaxies don't follow the luminous matter. That was discovered 100 years ago. I think that I wouldn't be surprised if there isn't an effect that we already know about that is kind of the analog of Brownian motion that reveals the discreteness of space. In fact, we're beginning to have some guesses. We have some evidence that black hole mergers work differently when there's discrete space, and there may be things that you can see in gravitational waves, signatures, and things associated with the discreteness of space. For me, it's kind of interesting to see this recapitulation of the history of physics, where people vehemently say matter is continuous, electromagnetic field is continuous, and turns out it isn't true, and then they say space is continuous. Entropy is the number of states of the system consistent with some constraint. The thing is that if you know in great detail the position of every molecule in the gas, then the entropy is always zero, because there's only one possible state. The configuration of molecules in the gas, the molecules bounce around, they have a certain rule for bouncing around, there's just one state of the gas, evolves to one state of the gas, and so on. It's only if you don't know in detail where all the molecules are that you can say, well, the entropy increases because the things we do know about molecules, there are more possible microscopic states of the system consistent with what we do know about where the molecules are. And so the question of whether ... So people ... This sort of paradox in a sense of, oh, if we knew where all the molecules were, the entropy wouldn't increase. There was this idea introduced by Gibbs in the early 20th century. Well, actually, the very beginning of the 20th century as a physics professor, an American physics professor was sort of the first distinguished American physics professor at Yale. And he introduced this idea of coarse-graining, this idea that, well, these molecules have a detailed way they're bouncing around, but we can only observe a coarse-grained version of that. But the confusion has been nobody knew what a valid coarse-graining would be. So nobody knew that whether you could have this coarse-graining that very carefully was sculpted in just such a way that it would notice that the particular configurations that you could get from the simple initial condition, they fit into this coarse-graining, and the coarse-graining very carefully observes that. Why can't you do that kind of very detailed, precise coarse-graining? The answer is, because if you are a computationally bounded observer and the underlying dynamics is computationally irreducible, that's what defines possible coarse-graining is what a computationally bounded observer can do. It's the fact that a computationally bounded observer is forced to look only at this coarse-grained version of what the system is doing. That's why. Because what's going on underneath is it's filling out the different possible ... You're ending up with something where the underlying computational irreducibility is ... If all you can see is what the coarse-grained result is with a computationally bounded observation," }, { "from": "human", "value": "then inevitably there are many possible underlying configurations that are consistent with that. Just to clarify, basically any observer that exists inside the universe is going to be computationally bounded." }, { "from": "gpt", "value": "No, any observer like us. I don't know." }, { "from": "human", "value": "When you say like us, what do you mean?" }, { "from": "gpt", "value": "What do you mean like us? Well, humans with finite minds. You're including the tools of science. Yeah. Yeah. And as we have more precise ... And by the way, there are little microscopic violations of the second law of thermodynamics that you can start to have when you have more precise measurements of where precisely molecules are. But for a large scale, when you have enough molecules, we don't have ... We're not tracing all those molecules, and we just don't have the computational resources to do that. And it wouldn't be ... I think to imagine what an observer who is not computationally bounded would be like, it's an interesting thing because ... Okay, so what does computational boundedness mean? Among other things, it means we conclude that definite things happen. We take all this complexity of the world, and we make a decision, we're going to turn left or turn right. And that is reducing all this detail into we're observing it, we're crushing it down to this one thing. And if we didn't do that, we wouldn't have all this symbolic structure that we build up that lets us think things through with our finite minds. We'd be instead ... We'd be one with the universe." } ]

[ { "from": "human", "value": "Yeah, so content to not simplify." }, { "from": "gpt", "value": "Yes. If we didn't simplify, then we wouldn't be like us. We would be like the universe, like the intrinsic universe, but not having experiences like the experiences we have, where we, for example, conclude that definite things happen. We have this notion of being able to make narrative statements." }, { "from": "human", "value": "I wonder if it's just like you imagined as a thought experiment, what it's like to be a computer. I wonder if it's possible to try to begin to imagine what it's like to be an unbounded computational observer." }, { "from": "gpt", "value": "Well, okay, so here's how that, I think, plays out. Vibrations. Yeah. So, I mean, in this, we talk about this rulliad, this space of all possible computations. This idea of being at a certain place in the rulliad, which corresponds to a certain way of ... A certain set of computations that you are representing things in terms of. Okay, so as you expand out in the rulliad, as you kind of encompass more possible views of the universe, as you encompass more possible kinds of computations that you can do, eventually you might say that's a real win. we're colonizing the Rulliad, we're building out more paradigms about how to think about things, and eventually you might say, we won all the way. We managed to colonize the whole Ruliad. Okay, here's the problem with that. The problem is that the notion of existence, coherent existence, requires some kind of specialization. By the time you are the whole Ruliad, by the time you cover the whole Ruliad, in no useful sense do you coherently exist. So in other words, in the notion of existence, the notion of what we think of as definite existence requires this kind of specialization, requires this kind of idea that we are not all possible things, we are a particular set of things. And that's kind of what makes us have a coherent existence. If we were spread throughout the rulliad, there would be no coherence to the way that we work. We would work in all possible ways. And that wouldn't be kind of a notion of identity. We" }, { "from": "human", "value": "wouldn't have this notion of coherent identity. Interesting. I am geographically located somewhere exactly, precisely in the rulliad, therefore I am, is the Descartes kind of..." }, { "from": "gpt", "value": "Yeah, yeah, right. Well, you're in a certain place in physical space or in a certain place in rural space. And if you are sufficiently spread out, you are no longer coherent. And you no longer have... I mean, in our perception of what it means to exist and to have experience, it doesn't happen." }, { "from": "human", "value": "Right. So therefore, to exist means to be computationally bounded. I think so. To exist in the way that we think of ourselves as existing, yes. The very act of existence is like operating in this place that's computationally reducible. So there's this giant mess of things going on that you can't possibly predict. But nevertheless, because of your limitations, you have an imperative of like, what is it? An imperative or a skill set to simplify? Or an ignorance, a sufficient" }, { "from": "gpt", "value": "imperative of like... Okay, so the thing which is not obvious is that you are taking a slice of all this complexity, just like we have all of these molecules bouncing around in the room. But all we notice is the kind of the flow of the air or the pressure of the air. We're just noticing these particular things. And the big interesting thing is that there are rules, there are laws that govern those big things that we observe. So it's not obvious. That's how amazing." }, { "from": "human", "value": "Because it doesn't feel like it's a slice. It's not a slice. It's like an abstraction," }, { "from": "gpt", "value": "not a slice. Yes. But I mean, the fact that the gas laws work, that we can describe pressure, volume, et cetera, et cetera, et cetera, and that we don't have to go down to the level of talking about individual molecules, that is a non-trivial fact. And here's the thing that I sort of exciting thing as far as I'm concerned, the fact that there are certain aspects of the universe. So we think space is made ultimately these atoms of space and these hypergraphs and so on. And we think that, but we nevertheless perceive the universe at a large scale to be like continuous space and so on. In quantum mechanics, we think that there are these many threads of time, these many threads of history, yet we kind of span. So in quantum mechanics, in our models of physics, there are these, time is not a single thread. Time breaks into many threads. They branch, they merge. But we are part of that branching, merging universe. And so our brains are also branching and merging. And so when we perceive the universe, we are branching brains perceiving a branching universe. And so the fact that the claim that we believe that we are persistent in time, we have this single thread of experience, that's the statement treatment that somehow we managed to aggregate together those separate threads of time that are separated in the fundamental operation of the universe. Just as in space, we're averaging over some big region of space, and we're looking at the aggregate effects of many atoms of space, similarly in what we call branchial space, the space of these quantum branches, we are effectively averaging over many different branches of histories of the universe. in thermodynamics, we're averaging over many configurations of many, many possible positions of molecules. So what we see here is, the question is when you do that averaging for space... What are the aggregate laws of space? When you do that averaging over branchial space, what are the aggregate laws of branchial space? When you do the averaging over the molecules and so on, what are the aggregate laws you get? And this is the thing" } ]

[ { "from": "human", "value": "that i think is just amazingly neat." }, { "from": "gpt", "value": "That there are aggregate laws at all. Well yes, but the question is what are those aggregate laws. Yes. So the answer is for space, the aggregate law is Einstein's equations for gravity, for the structure of space-time. For base space, the aggregate laws are the laws of quantum mechanics. And for the case of molecules and things, the aggregate laws are basically the second law of thermodynamics. And so that's the things that follow from the second law of thermodynamics. And so what that means is that the three great theories of 20th-century physics, which are basically general artillery of the theory of gravity, quantum mechanics, and statistical mechanics, which is what kind of grows out of the second law of thermodynamics, all three of the great theories of 20th-century physics are the result of this interplay between computational the reducibility and the computational boundedness of observers. And for me, this is really neat, because it means that all three of these laws are derivable. So we used to think that, for example, Einstein's equations were just sort of a wheel-in feature of our universe, that they could be, the universe might be that way, it might not be that way. Quantum mechanics is just like, well, it just happens to be that way. The second law, people kind of thought, well, maybe it is derivable. What turns out to be the case is that all three of the fundamental principles of physics are derivable, but they're not derivable just from mathematics. They require, or just from some kind of logical computation, they require one more thing. They require that the observer, that the thing that is sampling the way the universe works, is an observer who has these characteristics of computational boundedness of belief in persistence and time. And so that means that it is the nature of the observer, the rough nature of the observer, not the details of, well, we got two eyes and we observe photons of this frequency and so on. But the kind of the very coarse features of the observer then imply these very precise facts about physics. And I think it's amazing." }, { "from": "human", "value": "So if we just look at the actual experience of the observer, that we experience this reality, it seems real to us. And you're saying because of our bounded nature, it's actually all an illusion." }, { "from": "gpt", "value": "It's a simplification, observer, simplification. Yeah, it's a simplification, right? But you don't think a simplification is an illusion? No. I mean, it's, well, I don't know. I mean, what's underneath... Okay, that's an interesting question. What's real? And that relates to the whole question of why does the universe exist? And what is the difference between reality and a mere representation of what's going on? Yes. But you don't think a simplification is an illusion? We experience the representation. Yes. But the question of... So one question is, why is there a thing which we can experience that way? And the answer is because this Rouliad object, which is this entangled limit of all possible computations, there is no choice about it. It has to exist. There has to be such a thing. It is in the same sense that 2 plus 2, if you define what 2 is and you put pluses and so on, 2 plus 2 has to equal 4. Similarly, this Rouliad, this limit of all possible computations, just has to be a thing that is once you have the idea of computation, you inevitably have the Rouliad. You're going to have to have a Rouliad, yeah. Right. And what's important about it, there's just one of it. It's just this unique object. And that unique object necessarily exists. And then the question is, once you know that we are sort of embedded in that and taking samples of it, it's sort of inevitable that there is this thing that we can perceive that our perception of physical reality necessarily is that way, given that we are observers with the characteristics we have. So in other words, the fact that the universe exists, it's almost like to think about it almost theologically, so to speak. It's funny because a lot of the questions about the existence of the universe and so on, they transcend what kind of the science of the last few hundred years has really been concerned with. The science of the last few hundred years hasn't thought it could talk about questions like that. But I think it's kind of, and so a lot of the kind of arguments of, does God exist? Is it obvious that I think in some sense, in some representation, it's sort of more obvious that something sort of bigger than us exists than that we exist. And we are, our existence and as observers the way we are is sort of a contingent thing about the universe. And it's more inevitable that the whole universe, the whole set of all possibilities exists. But this question about, is it real or is it an illusion? All we know is our experience. And so the fact that, well, our experience is this absolutely microscopic piece of sample of the Rouliad. And there's this point about we might sample more and more of the Rouliad, we might learn more and more about, we might learn like different areas of physics, like quantum mechanics, for example, the fact that it was discovered, I think, is closely related to the fact that electronic amplifiers were invented that allowed you to take a small effect and amplify it up, which hadn't been possible before. Microscopes have been invented that magnify things and so on, but having a very small effect and being able to magnify it was sort of a new thing that allowed one to see a different aspect of the universe and let one discover this kind of thing. So we can expect that in the Rouliad, they're an infinite collection of new things we can discover. There's in fact computational irreducibility guarantees that there will be an infinite collection of pockets of reducibility" } ]

[ { "from": "human", "value": "that can be discovered. Boy, would it be fun to take a walk down the Rouliad and see what kind of stuff we find there. You write about alien intelligences. Yes. I mean, just these worlds" }, { "from": "gpt", "value": "of computation. Yes. The problem with these worlds is that- We can't talk to them. Yes. And the thing is, what I've kind of spent a lot of time doing is just studying computational systems, seeing what they do, what I now call rouliology, kind of just the study of rules and what they do. You can kind of easily jump somewhere else in the Rouliad and start seeing what these rules do and what you say is they just do what they do and there's no human connection, so to speak." }, { "from": "human", "value": "Can't talk to them. Do you think some people are able to communicate with animals? Do you think you can become a whisperer of these-" }, { "from": "gpt", "value": "Coitition trying. That's what I've spent some part of my life doing. Have you heard? Are you at the risk of losing your mind? Are you at the risk of losing your mind? My favorite science discovery is this fact that these very simple programs can produce very complicated behavior. And that fact is kind of, in a sense, a whispering of something out in the computational universe that we didn't really know was there before. It's like back in the 1980s, I was doing a bunch of work with some very, very good mathematicians and they were trying to pick away. Can we figure out what's going on in these computational systems? And they basically said, look, the math we have just doesn't get anywhere with this. We're stuck. There's nothing to say. We have nothing to say. And in a sense, perhaps my main achievement at that time was to realize that the very fact that the good mathematicians had nothing to say was itself a very interesting thing. That was kind of a sort of, in some sense, a whispering of a different part of the Rouliad that one wasn't accessible from what we knew in mathematics and so on." }, { "from": "human", "value": "Does it make you sad that you're exploring some of these gigantic ideas and it feels like we're on the verge of breaking through to some very interesting discoveries and yet you're just a finite being that's going to die way too soon. And that scan of your brain or your full body kind of shows that you're- Yeah, it's just a bunch of meat. It's just a bunch of meat. Yeah. Does that make you a little sad?" }, { "from": "gpt", "value": "Kind of a shame. I mean, I kind of like to see how all this stuff works out. But I think the thing to realize, it's an interesting sort of thought experiment. You say, okay, let's assume we can get cryonics to work. And one day it will. That will be one of these things that's kind of like chat GPT. One day somebody will figure out how to get water from zero degrees centigrade down to minus 44 or something without it expanding and cryonics will be solved and you'll be able to just put a pause in, so to speak, and kind of reappear 100 years later or something. And the thing though that I've increasingly realized is that in a sense, this whole question of kind of the sort of one is embedded in a certain moment in time and kind of the things we care about now, the things I care about now, for example, had I lived 500 years ago, many of the things I care about now, it's like that's totally bizarre. I mean, nobody would care about that. It's not even the thing one thinks about. In the future, the things that most people will think about, one will be a strange relic of thinking about what might have been a theologian thinking about how many angels fit on the head of a pin or something, and that might have been the big intellectual thing. It's one of these things where particularly I've had the, I don't know, good or bad fortune, I'm not sure, I think it's a mixed thing, that I've invented a bunch of things which I think see well enough what's going to happen that in 50 years, 100 years, whatever, assuming the world doesn't exterminate itself, so to speak, these are things that will be sort of centrally important to what's going on. It's both a good thing and a bad thing in terms of the passage of one's life. If everything I'd figured out was like, okay, I figured it out when I was 25 years old, and everybody says it's great, and we're done. It's like, okay, but I'm going to live another how many years, and that's kind of, it's all downhill from there. In a sense, it's better, in some sense, to be able to, you know, it sort of keeps things interesting that, you know, I can see a lot of these things. I mean, it's kind of, I didn't expect chat GPT, I didn't expect the sort of opening up of this idea of computation and computational language that's been made possible by this. I didn't expect that. This is the head of schedule, so to speak. You know, even though the sort of the big kind of flowering of that stuff, I'd sort of been assuming was another 50 years away. So if it turns out it's a lot less time, that's pretty cool, because," } ]

[ { "from": "human", "value": "you know, I'll hopefully get to see it, so to speak, rather than. Well, I think I speak for a very, very large number of people in saying that I hope you stick around for a long time to come. You've had so many interesting ideas. You've created so many interesting systems over the years, and I can see now that GPT and language models broke open the world even more, I can't wait to see you at the forefront of this development, what you do. And yeah, I've been a fan of yours, like I've told you many, many times since the very beginning. I'm deeply grateful that you wrote a new kind of science, that you explored this mystery of cellular automata and inspired this one little kid in me to pursue artificial intelligence and all this beautiful world. So Stephen, thank you so much. It's a huge honor to talk to you, to just be able to pick your mind and to explore all these ideas with you, and please keep going. And I can't wait to see what you come up with next. And thank you for talking today. We went past midnight. We only did four and a half hours. I mean, we could probably go for four more, but we'll save that till next time. This is round number four. I'm sure you'll talk to me any more times. Thank you so much. My pleasure. Very good going. Thanks for listening to this conversation with Stephen Wolfram. To support this podcast, please check out our sponsors in the description. And now, let me leave you with some words from George Cantor. The essence of mathematics lies in its freedom. Thank you for listening and hope to see you next time." } ]

[ { "from": "human", "value": "I'm a fan of so many people. I love celebrating people, and wearing merch or owning merch is a way to one, celebrate those people. But two, if it's a thing you can wear, you can meet other people, then it starts a conversation, you're like, holy crap, we both like the same thing. Or, holy crap, what is that? I don't know anything about it, tell me about it. And you get to share the things you love with others. It's so awesome. And obviously Shopify is a place you can do that really effectively and make that part of your income a part of your life, a part of your lifestyle, part of your career. So it's awesome that they've created this kind of platform. Sign up for $1 per month trial period at Shopify.com slash Lex. That's all lowercase. Go to Shopify.com slash Lex to take your business" }, { "from": "gpt", "value": "to the next level today than yours do." }, { "from": "human", "value": "But early signs. This episode is also brought to you by ExpressVPN, a VPN provider I've used for many years. Way, way, way before there was a podcast, way before there were a sponsor, there were a source of happiness, a source of security, a source of a kind of blanket protection and help ensure that to whatever degree, at the very basic level, my privacy is protected on the internet. Everybody should be using a VPN. It's in the digital space, it's the first layer of protection. You should definitely be using it. And the one I recommend, the one I've always used is ExpressVPN. There's a lot of other features, like you can watch different shows that are geo-constrained on Netflix and other services. But honestly, to me, the security and the privacy that comes with the VPN is the big plus. And the other point is with ExpressVPN, it's fast and it works everywhere, works on Linux. I don't know why that's such a awesome thing for me. Maybe now it's obvious, but in the early days when they worked on Linux, like early, early days, I don't know how many years ago, but I was like, holy crap, this is so awesome. This is so awesome that they care about this operating system that I love so much. So yeah, it works anywhere. Android, your iPhone, all of that. By the way, I should mention that the peer pressure I have to switch to an iPhone. I do have an iPhone, I just don't use it. The peer pressure is immense, but I remain with the Android. It is the phone of the people. I still like the customization. I like developing for the Android as well. And I have several Android phones and I love them very much. The customization, the freedom, actually the principles that's behind it. But of course, I also love beautiful design. Johnny Ives is one of, if not the greatest tech designers of all time and he's a hero of mine. He's somebody that inspires me as a human being, as a designer. So all of that combined, I don't know. I should be using both actively and giving both love and developing for both. Let's see what the future holds. The point is ExpressVPN works across all of those, no matter what choice I make. Go to expressvpn.com slash LexPod for an extra three months free. This is the Lex Friedman podcast. To support it, please check out our sponsors in the description. And now, dear friends, here's David Backman. Are there interesting differences to you between terms like liberal, Democrat, left-wing, leftist, progressive, socialist, communist, Marxist, far left, center-left, all of these labels." }, { "from": "gpt", "value": "Is there interesting distinctions between them? Yeah, there's two sets of distinctions. One is if you just want to say, let's define each of these as political terms. They're all different terms. You can be a progressive ideologically but not be a member of the Democratic party. Many say the Democratic party isn't even really very progressive. So these are certainly terms that we could define in order to have a conversation about the next thing kind of as a precursor to a conversation. Sometimes the terms are used in order to tag someone with a certain ideology that's not really linked to policy or any particular political question, but they can be used positively or negatively to just kind of say, here's the image of this individual that I have in my mind. So like Marxist is right now very popularly being used by some on the right to attack Democrats. There's very few actual Marxists, certainly not in positions of power in the United States but even among the general population. So I think it's important to distinguish are we defining these terms because we want to compare and contrast the ideas that a particular group might bring to the discussion or are we using them as insults or to stifle conversation? There are terms that can be used to start a conversation" }, { "from": "human", "value": "or to stop it. And the use of those terms is evolving rapidly month by month. So the term leftist, I think is a relatively popular term now to use in the negative context to describe" }, { "from": "gpt", "value": "what an outraged left wing commentator. I think what you're kind of grasping onto is that there's probably some set of ideas that would apply to most of those who consider themselves to be on the left. The discussion of how that term is mostly being used is not about policy ideas. You're accurately kind of identifying that. And it does seem like progressive is no longer being used as a smear and leftist is being used as a smear" }, { "from": "human", "value": "more at this point. Okay, but sometimes some of these terms are useful. Like can we try to pick the terms that are useful" }, { "from": "gpt", "value": "like liberal and progressive and Democrat" }, { "from": "human", "value": "and liberal and progressive. Is there an interesting definable distinction" }, { "from": "gpt", "value": "between liberal and progressive to you? That's maybe one of the most interesting ones. 10 years ago, liberal often meant what now we mean by progressive. More recently, the progressive socialist leaning part of the political spectrum has started to use liberal to mean Joe Biden, to mean someone who is not really left enough. So liberal is very interesting because I remember talking with my audience years ago, maybe eight years ago or something like that, where I identified, I'm going to now use the term progressive more commonly to describe my own beliefs because liberal has now been made a smear, it's being shifted into something else and it also means more of like a center left politics. So it's changed in some sense by necessity, by force" } ]

[ { "from": "human", "value": "and also because the spectrum has shifted to some degree. So the term liberal has evolved. Now liberal meaning some kind of embodiment" }, { "from": "gpt", "value": "of the mainstream democratic party, almost. To some degree, sometimes I'm called, I'm written off by, within my space, there are all sorts of shades of gray, which I'm sure we can talk about, about where I am versus should be, could be, or am wrongly placed. And sometimes an attack on me is he's just a lib, meaning I'm not left enough. I'm not progressive, socialist, wherever else you want to go. So yeah, the problem with a lot of these terms and they're used very casually by people who call into my show, is that unless we actually define them each time, they very often mean very different things to different people and often come with an agenda attached to them. And so I find that they often stifle meaningful conversation" }, { "from": "human", "value": "rather than encouraging. Do you sense that there's a drifting of what is the threshold to be a progressive or should be used progresses synonymously" }, { "from": "gpt", "value": "with the democratic socialist? I think we should not use it synonymously with democratic socialist. And this is where there is another linguistic confusion and a political confusion. So we'll first talk about the linguistic one. Social democracy versus democratic socialism. Very similar words in a different order, okay? The way I operate is democratic socialism is actually a form of socialism where one would seek to socialize ownership of the means of production as an example. Social democracy is a very highly regulated form of capitalism, the likes of which we would see in Northern Europe, Denmark, et cetera. These are very different things. I associate progressivism in 2023 with social democracy and would consider democratic socialism a form of actual socialism that is different. We're no longer talking about" }, { "from": "human", "value": "a capitalist organization of society. So transition from one to the other" }, { "from": "gpt", "value": "is a fundamental shift in how society operates then. Absolutely. And when you talk about social democracy, you're talking about socializing a couple more things than we socialize in most modern capitalist countries. I had this conversation with Patrick Bet David recently. Social democracy is, okay, we've socialized the military already in the United States. We've socialized some healthcare in the sense of like the VA and Medicaid, et cetera. We're talking about socializing a couple more things still in a capitalist country. Democratic socialism would be something beyond that. And as someone who is not a democratic socialist myself, I'm maybe not the best advocate for explaining exactly how that system would function, but it would have some version of socializing" }, { "from": "human", "value": "of ownership of the means of production, businesses, et cetera. So you mentioned you appeared on the PBD podcast with Patrick Bet David. The debate was pretty intense. I should say I personally enjoyed it. I thought, actually you did well and I thought Patrick did well and it was a good conversation. I thought there was a little bit of tension. And I thought that Patrick actually, so I disagree with the internet. I thought Patrick just took on a kind of devil's advocate. Like he was purposely being stubborn to bring out the best in you. But the internet thought that he's being stubborn and not being open to your ideas. I thought the tension between ideas, I think a lot of the tension had to do probably" }, { "from": "gpt", "value": "with Donald Trump and Trump supporters. There was a little bit of- Yeah, that certainly could be the case. And people wrote to me after, people wrote to me the full gamut of everything you can imagine from this was your best thing you've ever done in public to you got humiliated and your mother should have aborted you. Okay, and everything in between. So take your pick. But the most interesting feedback I got was from people who asked me after was incredibly tense and awkward and because it seemed so combative. And I think I'm so used to those types of tensions in the discussions that I have that it's very comfortable to me. It's not like afterwards there's a grudge or it's tense or whatever the case may be. I'm very comfortable. I disagree with people and that's it. So I did not find anything that happened inappropriate." }, { "from": "human", "value": "I disagreed with a lot of the things he said, certainly. So you've also spoken with Michael Knowles, I think about the idea of what is a woman. Can you speak broadly about your conversation with the people you disagree with?" }, { "from": "gpt", "value": "Some of the cases, it feels like it's gone wrong. What is a woman? The conversations have gone wrong. Yeah, I mean, I think there's a couple of different things and I'm the first to tell you that depending on who I'm talking to, I go in with a different attitude about how quote seriously I'm taking it in the sense of whether I think it's going to be a deep policy discussion versus whether it's going to be more of a performance for an audience that is expecting a certain thing. And I think there's different types of shows. When I was interviewed by this guy, Jesse Lee Peterson in Los Angeles, it's very different, for example, than when I'm talking to Patrick Bette David, just to give two examples. I think the reason I stopped doing the Michael Knowles show was the number of threats I would get after the fact. That's really the reason, I was glad to engage with him to the extent that the interviews were interesting and we could organize it reasonably efficiently. But the reason I stepped away was sort of the aftermath. But I did find him to be someone who was abundantly clear about his view and where he comes from. And while I could not possibly disagree more with him in terms of politics and culture and our backgrounds, everything is just so different, I found it easy to engage in the conversation just because of how upfront and clear he was" } ]

[ { "from": "human", "value": "about what his beliefs were." }, { "from": "gpt", "value": "But the number of threats, it's too much. Yeah, it was just too much. And I don't know how much you saw about this recent Twitter dustup I was involved in that peaked with Donald Trump Jr. tweeting about me" }, { "from": "human", "value": "and then declining from there. Let's talk through it, I didn't see it. I have to understand, like the way you study Shakespeare, I have to study your Twitter. I have to understand how much of it is sarcasm." }, { "from": "gpt", "value": "It's mostly sarcasm, okay, it's mostly sarcasm. I mean, here's the thing, and I know that there are people who will say, David, you're dealing with such serious issues. It's really not okay not to take everything you do completely seriously. But my view is it's so incredible that I've between chance and timing and so different things fallen into a position where this is what I do professionally. And it's a career and it's financially sustainable and all these different things. I don't want to end up taking myself too seriously because I recognize the timing and luck and all of these other things. And this could have gone a completely different way. So my approach to a lot of this is let's not take ourselves too seriously. And in particular on Twitter, a platform that, you know, the degree to which it should be taken very seriously maybe has changed over time. I'm always sort of thinking a little bit tongue in cheek" }, { "from": "human", "value": "on Twitter. So what happened with Donald Trump Jr.?" }, { "from": "gpt", "value": "Or the full arc of it? So yeah, to give you a one minute arc and then we can pick whichever parts we want. After a mass shooting, now you might say there's like two or three a day, you're correct. After the Nashville mass shooting at a Christian school, I tweeted snarkily tongue in cheek to point that thoughts and prayers not only aren't particularly useful after a shooting, they also don't prevent shootings, that there's some confusion about how there would be a shooting at a Christian school given that it is a place where prayer is taking place. I think I, you know, jokingly said something like" }, { "from": "human", "value": "were they not praying enough for correctly? I think in my deep journalistic integrity. You have it. I have your tweet. This is the only display of journalistic degree I will show today, okay. And then I have a couple responses. Beautiful. And you deleted the tweet since then." }, { "from": "gpt", "value": "Which I regret." }, { "from": "human", "value": "You have it, which I regret. Oh interesting. And we can talk about that." }, { "from": "gpt", "value": "I would love to, because it's such a interesting decision" }, { "from": "human", "value": "and we can talk about that. Because when you tweet something, one of the things I've also learned is you don't often understand how it's going to be read. It's going to be analyzed, like I mentioned, Shakespeare. There's certain, the use of certain words that you regret saying in a certain kind of way. Maybe just because it wasn't as eloquent as powerful. It didn't actually convey the thing. Or it's a distraction to the main message, all that kind of stuff. Okay, the actual tweet is very surprising that there will be a mass shooting at a Christian school given that lack of prayer is often blamed for these horrible events. Is it possible they weren't praying enough or correctly just by being a Christian school? And a lot of people quote, retweeted that, which I'm assuming was a criticism. So Colin Wright wrote, I used to consider you a reasonable progressive, but you clearly devolved into partisan hackery. I'm an atheist. It cannot begin to fathom using the murder of children and adults at a Christian school as an opportunity to dunk on the concept of prayer. And you responded, I'm dunking on the people who send thoughts and prayers and do nothing else. And the shootings continue." }, { "from": "gpt", "value": "Okay, I'm sure there's a lot of other interaction. There's a few other 100,000 interactions. So do you want the arc leading to the deleting? So basically- I just wanted to display the- Do you know what time of day I tweeted the original one? I feel like it was in the afternoon or evening" }, { "from": "human", "value": "of on a Monday deleting. So basically- I just wanted to display the- 3 42 PM on 27th, March 27th. Which was a Monday." }, { "from": "gpt", "value": "Okay. Which was a Monday. Okay. So basically I tweet that and then I finished the day. And I- So you tweet and then you go on with your day. I might've looked once at Twitter and it had 2000 likes and a few people saying, eh, this might've missed the mark, but it's sort of like it's one of my 20,000 tweets. I don't know. I wake up the next morning, my baby daughter did not sleep till 7 30, the way I would like. So she's up at 6 AM and I get up and I'm just there starting to make breakfast. And I glance at my phone and I'm starting to- This was when verified meant a different thing than it means now. I'm seeing all these verified accounts that are, you know, quote, tweeting it and demanding a retraction and whatever. And I go, oh, okay. This looks like it's getting, looks like it's getting some attention. I then continue about my day. Around noon, I hear from my dad that he got a hundred messages from, you should have aborted your son to we're going to find all of you to whatever else. My dad has no idea what's going on. He's like, I don't know what this is, but I have a hundred DMS to everything else you can imagine. And I start to get emails about, you know, we, you know, your Jewish faith, this and that and the other thing. And so at that point to me, I thought this is just going to get worse and worse and worse. And so I deleted the tweet. And I really regret doing that because over the 48 hours that followed, yes, the attacks escalated. It went through Candace Owens and then at Fox news.com Newsmax kind of peaking with Donald Trump Jr. And it was horrible. I mean, thousands and thousands of the, okay. But once I told my audience about what happened, I got thousands of messages from people saying, David, only someone who doesn't know you and is determined to interpret this in the worst possible faith would think you're blaming kids who died for getting shot. Of course you weren't doing that. I wish you hadn't deleted it so that it would still be up and you would now see the tide kind of turning on it. This was not a fun three days regardless, but I do regret having deleted it because I wanted to do the quickest thing I thought I could to get people to stop trying to find family members and send them threats. And so around noon, that's what I did. And the truth is the threats didn't stop anyway because everybody had screenshotted it." } ]

[ { "from": "human", "value": "And I do wish I had left it up. And is there some degree, maybe stepping outside yourself, do you regret tweeting that? In that it feeds the mockery engine that fuels Twitter." }, { "from": "gpt", "value": "So like, does that tweet really represent what you believe? It absolutely represents the disgust with a politics that includes saying, we can't touch guns, we just, we can't. But we're willing to point to mental health or say we need more prayer in schools or whatever. 1000%, it represents that view. Is it the type of snark and sarcasm that I would use if given an hour to discuss the topic rather than whatever the number of characters is now on Twitter? No, definitely not. And so I am very cognizant of the fact that" }, { "from": "human", "value": "it was unnecessarily provocative how it was written. I think I asked a similar question to Ben Shapiro. Do you worry that this style of presentation can turn you from being a deeply thoughtful, objective political thinker to somebody who is just a partisan hack or partisan," }, { "from": "gpt", "value": "what's a good word, talking head? Do you mean with regard to Twitter" }, { "from": "human", "value": "or the format of my show in general? So Twitter for now, let's start with Twitter for now. And can you silo your style of communication on Twitter from being a virus that affects your mind?" }, { "from": "gpt", "value": "Right. I don't have deep thoughts about the Twitter component beyond, I think, across all sorts of disciplines. This is not the best way to most effectively solve problems and figure out solutions to complex issues. You're talking about Twitter. Right now I'm talking about Twitter. That being said, I think all of us, to some degree, have to adapt our content to the platform that we're using in the same way that what I post to YouTube is different than what I post to TikTok. What I post to Twitter is also different. Do I think Twitter has been an unmitigated good for society? No. Have I chosen to step into Twitter as one of the ways in which I get my message out with the good and the bad? Yes. And I think that there is a deep conversation to be had there. I think zooming out a little bit in terms of what I do, and I was hoping this would come up because I think it's really interesting. I will often get emails from people who say two things. I will get the, you would have such a bigger audience if you did X type emails. And usually they are plays to sensationalism, salacious and titillating content, more pop culture stuff, et cetera. On the other hand, it's folks who say, listen, what you're doing really isn't as serious as it could be. And it seems like you could do something more serious and you should consider doing deep dives. Once it was, do a deep dive into Calvin Coolidge. And I was like, nobody will watch that. So there it's not by accident that my show is the way it is, right? In an hour, I'm thinking of all the platforms I'm on and I'm saying, okay, I want to do a relatively deep dive on the federal budget. And I want to talk about some of the political tomfoolery going on within the post office. And I'm going to do a segment about the wacky rally where Trump said crazy things and made up three words and said he endorsed a candidate who's named it, right? I'm crafting that in total to find a balance between let's build this audience as much as I can in order to have a bigger base to get my message out there and include the more serious stuff with the hope that there's a little bit of something for everyone. And I'm finding a balance between those two sides of the spectrum. It's a deliberate thing. And I'm aware that if I were producing my show 50 years ago, the balance would probably be different and it would probably change again. If we didn't, if the show was audio only rather than having all these video platforms, it would also be different. But it's a decision that's proactively made to try to get the best and most out of the hour" }, { "from": "human", "value": "that I'm creating every day. You're talking about Twitter. It just feels like there's an entire machine fed by Twitter and journalism that wants to divide people and the drama of that division, highlighting the partisan division, the drama of that division feels like it's a tension with objective clear thinking sometimes. And so that's the, I worry that there's a drug to it. There's too much fun to mock ridiculous people" }, { "from": "gpt", "value": "on the other side of that division. I think you're right about that. And the fact that that is true to me supports, I've talked with my audience about, you know, like the old food pyramid, which I guess was like wrong, but let's imagine that there was a pyramid that made sense. What's in the bottom bread? I think like whole grains maybe, I don't remember. It's been a white dice on top. Junk food is at the very top. I'm very open with my audience. The vast majority of what I do is the top of that pyramid." }, { "from": "human", "value": "What's on the bottom bread?" }, { "from": "gpt", "value": "I don't remember it's been a white dice on the top and I tell people very openly, I don't consume a lot of the type of content I produce. And I think it's really important to, as a base, be doing critical thinking, epistemology, how do we believe the things we believe, basics about the world. After that, reading history, economics, philosophy, et cetera. After that, now we're getting into current events. I would mostly be looking at consuming primary source reporting, things like associated press, whatever. I know everybody will have a different list of what counts there. After that is when I'd say indulge in some of the commentary type stuff that I do. If you find that I'm thoughtful enough to make it into that, but I'm very open. And really what I try to do on my show often is in being that at the top of the pyramid, tell people there's all this other stuff that should be forming your foundation that I hope you're consuming in addition to just watching me." } ]

[ { "from": "human", "value": "And I'm very open with my audience about that. What about the shape, the dynamics, the characteristics of your audience? Is there some degree to which you're through mocking maybe Republicans that there's a lean to that audience and then you become captured by the audience?" }, { "from": "gpt", "value": "Do you worry about the audience capture? I worry about it. I'm relatively comfortable that it's not shaping the program to a great degree in the sense that at this point I have a pretty good sense of the things I can say that will upset what I might call my core audience. One of the interesting things just to briefly go back to the Twitter thing was those people who were furious with me on Twitter and they contacted my advertisers and some advertisers dropped me and on and on and on. None of them are actually in my audience. None of them are regular consumers of my audience. They were kind of weaponized against me by people who said, hey, look at this. The people who follow Candace Owens on Twitter other than for their kind of shock value, they're not in my audience. And with my core audience, I know there are things I can talk about that will generate displeasure, I guess you could say with my audience. Sometimes when I touch the Israeli-Palestinian conflict, that will happen. Sometimes on vaccines, there's a portion of my audience that is more generally skeptical of vaccines, sometimes on some foreign policy issues, or I'm not a big fan of Marianne Williamson nor Bobby Kennedy Jr.'s challenges to Joe Biden, not because I love Joe Biden, but because I don't consider them to be the most serious challenges. I know there's people in my audience who don't like that. They get mad at me about that. And I'm totally okay with that. And that tension with my core audience. So in that sense, I don't feel as though I've had that audience capture take place, but I know it can happen. And I'm very open to being told ways" }, { "from": "human", "value": "in which it may be happening without me noticing. So I've made a call for questions on Reddit for this conversation. There's a lot of good questions that I'll probably bring up. But one of them was about Marianne Williamson asking why David thinks she is a garbage candidate. Which of course- I've never said. But perhaps you have more eloquently criticized. So let's go there to the 2024 election. Okay. So Joe Biden officially announced that he's running again." }, { "from": "gpt", "value": "Donald Trump officially announced that he's running again." }, { "from": "human", "value": "I've never said, okay." }, { "from": "gpt", "value": "And if that's the matchup, who do you think wins? If the election's held today, I think Biden. Why? Well, first of all, I believe he won last time. And if I start with the results from 2020, and I think to myself what has happened since then that would push or pull voters one way or the other, I have a hard time making a case that Trump is in a better position today than he was in November of 2020. So that's kind of my starting point, which is it's a rematch of an election with a known outcome. What has changed? And I can't make a case for circumstances having changed in Trump's favor to give a couple of state level examples. Florida seems to be kind of moving more to the Republican side since 2020, but Trump won that state already in 2020. So it wouldn't really change the outcome. Arizona was close. I think Arizona has moved to the left since 2020. So I don't see Trump taking that one. Wisconsin, I think the same sort of thing applies. So being very like practical," }, { "from": "human", "value": "that would be kind of the start of my reasoning. Do you think Joe Biden is a better candidate now" }, { "from": "gpt", "value": "than he was in 2020? And is it? I think he's a worse candidate. This is going to sound ageist, but I think he's a worse candidate in that he's even older and there already seems to be an appetite for younger candidates, particularly on the Democratic voting side. So he's going to be four years older. And in a sense, that could be a liability. However, he also is going to have four years of accomplishments. Now you might not like the things he's done, in which case that would hurt him, but he has started to accumulate not insignificant number of accomplishments. Some of the big things that are known, Inflation Reduction Act and COVID stimulus, but also less well-known things like a bunch of little tweaks to healthcare, a bunch of little tweaks to student lending. There's been a lot of little things at the macro level. I don't actually think Joe Biden has that much to do with this, the same way I didn't credit or attack Trump for a lot of the macroeconomic stuff, but inflation has started to come down significantly. The stock market's quite steady. Yeah, these sort of things. I think looking historically, it's a pretty okay environment for Joe Biden, with the exception that he was already the oldest president to be inaugurated in 2021. And he would beat his own record in January of 2025." } ]

[ { "from": "human", "value": "And I just don't know how voters are gonna see that. So in terms of just a public human being, how would you compare Trump and Biden? So if I were to give criticism towards Trump, it would be that he's chaotic, maybe to the point of being disrespectful to a lot of different groups, to a lot of different ideas, to a lot of different nations and leaders and all that kind of stuff. And then the criticism towards Biden would be that maybe perhaps because of age or any other kind of cognitive capabilities is not really there mentally, in the way that perhaps you could say that Barack Obama was there, just mentally being able to handle all kinds of aspects of being a public representative of a nation to the world and to the people of that nation. So which in the competition of personality flaws," }, { "from": "gpt", "value": "which do you think is more powerful? There. There's a way that you played out fair and I believe accurate assessments of elements of both of those men. You haven't weighed in on to what degree you value each of those assessments, which is where I think the kind of meat of this question really is. I don't see, and I know that Biden's gonna get us into World War III, World War III, that doesn't seem to be happening. I don't see the Biden deficits you listed, which I agree with you on. I don't see them as dangerous or threatening to the standing of the United States in this kind of environment with our Western traditional Western allies and geopolitics, et cetera, in the way that the sort of unhinged personality of Trump, combined with his lack of knowledge about most issues, is a threat. So for me, if those two are the candidates Biden would be my choice. Now, are there people I would rather see on the Democratic side? Yes. If I knew the president would be a Republican, can I think of better options than Trump? Absolutely, you know, it's so funny. When in 2012 it was Obama versus Romney, the difference seemed so significant between them. Thinking back, I'm sure I would disagree with Mitt Romney about tax rates and his views on LGBT, or I'm sure I know are different than mine, but it seems without looking at him with rose-colored glasses, so comparatively benign given the four years of Trump." }, { "from": "human", "value": "So that's kind of where I come down. Even McCain and Obama," }, { "from": "gpt", "value": "the differences seem quite drastic. Yeah, McCain was interesting because Palin, as his running mate, opened the door to the sort of cartoonish stuff that we've started to see on the Republican side. Palin, Trump, Marjorie Taylor Greene, it started going in that direction, which has made the party a bit of a joke, aside from what you believe the tax rate would be, right? You can say taxes are too high, but Jewish space lasers, come on, you know?" }, { "from": "human", "value": "So, but I agree with you on McCain also. So, going back to the political terms we talked about, where in that spectrum do you place yourself today? Which of the label do you think" }, { "from": "gpt", "value": "captures your political views today? Progressive Social Democrat, which again, is a capitalist. I own my own business. I pay the taxes I'm legally required to pay and not a penny more and, you know, all those things." }, { "from": "human", "value": "That's where I place myself. Would you place yourself to the left of Joe Biden? Yes, yes, yes. Where does the AOC fit into that? It's a good question. What do you think about AOC as a candidate?" }, { "from": "gpt", "value": "Do you think she eventually runs? I think that if she doesn't run into some kind of scandal, and I don't mean scandal in the sense of some personal impropriety that, you know, but I mean some kind of major political problem, it seems that she has the staying power to be in American elected politics for a long time, whether she would even want to be president versus maybe going to the Senate or being governor or whatever the case may be. I have no idea what her ambitions are in that sense, but certainly like policy aside, she has this combination of charisma, likability to some, but also something about her personality that angers the people who don't like her in a way that only fuels her sort of presence, which I think applies to Trump as well, that I do think that she has the potential to be, to have significant staying power in American politics." }, { "from": "human", "value": "President, I don't know. President, I don't know. Do you think that's the future of political elections and politics in general? Is people who are able to skillfully piss" }, { "from": "gpt", "value": "off the other side like AOC and Trump did? I think it's an aspect of it. I think it's also understanding how to communicate policy ideas. Trump, I have things I can praise Trump about if we want to get to that segment at some point, you let me know when that is, but I do think that there are some things Trump is very good at. And this is why it's very hard for me to believe that Ron DeSantis has what it takes to actually fight Trump in a national primary. And one of those things is Trump has, even though he often says very strange things that if you transcribe them, you go, what language is that? That doesn't make any sense whatsoever. In the moment, the way he relates to adversaries on stage, et cetera, is very good in that he is very much aware of how it is going to be seen by the audience. And so that's why a lot of times it's more about, doesn't matter that a word salad came out of his mouth, how he immediately responded and related to the person, very good. So I think that knowing how to be good when clips are shared all the time, often out of context is extraordinarily important. Knowing how to use social media, which every election cycle, that means something different, but understanding how to use social media, very important. Those things are absolutely so important. And whether you're able to do a deep dive on the deficit, certainly useful, but I would say it's a bad thing. It's becoming less important" } ]

[ { "from": "human", "value": "in terms of figuring out who we want to represent us. So just lingering on the AOC, and then maybe let's throw in Bernie Sanders on that. Yeah, yeah. So where do you place yourself and how do you do the layout of the land of Bernie Sanders, AOC, Joe Biden, and David Pakman?" }, { "from": "gpt", "value": "My instinct is, and I'm going to answer it, the thing that makes this tough is, Bernie says he's a democratic socialist. He ran as a social democrat. He didn't run on anything that was really socialism." }, { "from": "human", "value": "So I'm going by their public facing platforms. I've been listening to him for many, many years and all the way back to the Tom Hartman show. And I think using the terms as you've been using them, he has, I don't think, ever been a democratic socialist. I haven't heard him speak about socialism. I think I've heard him speak about social programs and the value of social programs throughout the history of the United States" }, { "from": "gpt", "value": "and how they've been beneficiaries. My understanding is very similar to yours, although there may be stuff from the 70s where he really was talking about- We've all did shit in the 70s, hasn't we? Yeah, you and I even, who weren't around- Yeah, I feel like we-" }, { "from": "human", "value": "We were doing stuff in the 70s. We've all did shit in the 70s. We were doing stuff in the 70s though- Yeah." }, { "from": "gpt", "value": "Yeah, I feel like we did, yeah. My sense would be, Biden is like center left and then I'm to the left of that but maybe just inside of where AOC and Bernie are, very, very similar to Bernie. I mean, I identify with a lot of Bernie's ideas. Maybe their implementation I'm more flexible on. I'll give you one example. Medicare for All. One way of trying to get healthcare to everybody, which Bernie's very big on, is you take the current Medicare program, you just eliminate the age limit, make it available to everybody, pay for it through taxation. Interesting. However, I'm open to other models if they get everybody healthcare. That is good quality and affordable. Singapore has an interesting model. Germany has an interesting model. I am more agnostic about how we do it than just saying, let's expand Medicare. Whether that puts me to the right of Bernie, I don't know, but I'm not like exactly right there" }, { "from": "human", "value": "on it has to be Medicare for All. Yeah, that's more of a, that's more just flexibility versus dogmatism. So I don't know if that puts you to the left or to the right. I don't either. What do you think about the term manipulation or the corruption in the DNC that perhaps tipped the scales against Bernie in the election? Do you think there was such a thing?" }, { "from": "gpt", "value": "In 2016 or 20? To the right. I think there was such a thing." }, { "from": "human", "value": "In 2016 or 2020? Both, I would say. In different, the dynamics there were different with Hillary Clinton and like the pressure from Hillary Clinton as a candidate and so on. Yeah, I mean, was there, why didn't Bernie win? I guess there's one way to ask." }, { "from": "gpt", "value": "Okay. I think there's a couple of things here. First, the DNC, I'm not a Democrat. Just your audience may not know. I'm just a independent. I mostly vote for candidates that end up being Democrats in local elections. Often there's no party designation. So, okay, I'm obviously on the left. I'm not denying that, but the Democratic party as an institution has never really been interesting to me." }, { "from": "human", "value": "You're still a rebel that resists belonging to any institution." }, { "from": "gpt", "value": "Exactly right, exactly right, exactly right. And whether it matters, I don't know. The DNC and the RNC really are organizations that to some degree exist to justify their own existence. Because if they were no longer necessary, they would go away. And so they have to assert their value and their importance. They do this in a number of different ways, organizing the way that the nominee has chosen, the convention, working with states on everything from redistricting to whatever else the case may be, setting the order of primaries and having some involvement in how that's all going to happen. And also coordinating behind the scenes, I guess they would describe it as making sure our candidates don't get in each other's ways. We might see it and say they're picking the winner. There's nothing illegal about them being involved in picking the winner. But we might say it's not in people's interests. I think the 2020 primary was really interesting. Bernie's supporter, myself, I started telling my audience after a couple primaries and even before based on polling and different things, I see a real uphill battle here for Bernie. And it's really important, people in my audience are not the average union worker in Michigan who is mostly working and raising a family and then goes to vote on primary day and goes to vote on election day. If you spend a lot of time on Reddit and Twitter, you're going to have an inflated sense of Bernie's popularity within the Democratic party. That was my sense. And to some degree, we saw that in certain states. I don't have the exact primary order and results in front of me or in my head, but the big turning point was South Carolina. South Carolina was when Joe Biden won and won handily, understood to be because of the larger African-American population in South Carolina. And right around that exact same time, I actually don't remember now whether it was the day after or the day before. Some of the smaller Democratic candidates, smaller in terms of support, got out and said, I'm endorsing Joe Biden. And to some degree, of course it was all organized and timed to help Joe Biden. There's no doubt about that. This is what the DNC does. It's hard for me to be mad at the DNC because this is sort of like, if we believe they were there to be unbiased arbiters and to stay as much on the side as possible, it would make sense to be furious that they've gone against their stated kind of mandate. But we know that the DNC negotiates and is working behind the scenes and has a favorite. That favorite was Hillary in 2016, 2020. So I share the frustration about the power that the DNC has, but for people who were saying they did something illegal or whatever else the case may be, that doesn't seem to be the case. But this is part of why, I mean, I would love there not to be this duopoly of Republicans and Democrats. And there's probably four major changes that have to happen in order to make that a reality. But I share the frustration of folks while recognizing that Reddit was not accurately representing" } ]

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

[ { "from": "human", "value": "they seemed of course, like impossible promises. Well, it's a double-edged sword. So to push back a little bit, if you look at the things I have a little bit more knowledge about, which is the space of artificial intelligence, there's a company called DeepMind and there's a company called OpenAI that will laugh at for a long time when they were talking about that they're going to solve intelligence. And now they've made especially DeepMind and now most recently OpenAI with GPT, they've made progress that most of the community would not have imagined they'd be able to make. Everything from AlphaGo beating the World Go champion, just all the different steps and progress that I can get into were surprise to everybody and they are legitimately, fearlessly pursuing the task of solving intelligence. The other aspect, he gets a lot of criticism now, but another example is Elon Musk. I can say a lot of things like SpaceX, so commercial space flight. He was laughed at for a long time that that's possible. Same thing with autopilot in Tesla, autonomous vehicles. His approach was harshly criticized by all the experts and still criticized to this day, deeply criticized. And I, as a person that I believe objectively can look at the progress of autopilot as a semi-autonomous vehicle system has been incredibly surprising. So the reason I mentioned that is sometimes it feels like you need the guy or the gal who makes those preposterous, ambitious statements, and it's like, we're going to solve healthcare this year. And then there's experts like yourself that are looking, thinking, have you read anything about the history? Israel, Palestine is a good example of that. Do you know there's a history there? Do you realize how complicated, how many people have tried? How many people have failed? How many millions of people hate each other in this little place, in this land? Sometimes the expertise can really weigh you down. So to push back, sometimes you have to have the, almost be naive and stupid and just rush in" }, { "from": "gpt", "value": "with an optimism in order to actually make some progress. I agree with you 100%. I think it's interesting that all of the examples you gave of successes are from the technology space. Not politics, yes. Not from politics, which, I mean, listen, I would love to be able to make headway on some of these issues more quickly without a doubt. I do think at some point though, when it comes down to voting and saying, one of these people is going to be ostensibly in charge for four years through all of the departments and secretaries and choices that they make, we do want to apply some level of realism with the understanding that your examples are from the tech space and they're good examples. There's no question about it. One thing I'll add to this, I recently read Bradley Hope's new book about North Korea and it's really about an activist who- It's not possible. It doesn't even really matter, in the background of the book, it's written much of what is written about happens during the Trump era and when Trump did the first and then the second, I guess you'd call them summits with Kim Jong Un. And it actually did seem like to some degree, Trump's we're going to handle this like I do a business deal approach to Kim Jong Un. In some sense, it actually was logical because of Kim Jong Un and the way that it was so ego-driven and they both as sort of authoritarian strongmen types to different degrees wanted that. There was actually a kernel where I actually thought as I read it, Trump's initial idea wasn't crazy. The problem was he knew nothing about the backstory of the relationship. He fell for all sorts of lies from Kim Jong Un and he made offers that didn't make any sense. It fell apart, fine. But that's an example where I think Trump's personality was not actually at its base the problem" }, { "from": "human", "value": "when it came to North Korea. Well, there's other things of this nature that could go and some people argue goes into the strengths and pros of Donald Trump. For China, for example, terrorists in China. Can you make the case that there's some positive outcomes" }, { "from": "gpt", "value": "of the way Donald Trump acted with China? It's really tough. And I'll give you a couple of- Okay, then also cons. I'll give you, it's tough to make. So the China thing is really, so just very recently to when we're recording this, Trump was on Fox News interviewed by a guy named Mark Levin and Trump proposed a new, I call it a conspiracy theory. Maybe it will strike you as something different about China, COVID and tariffs. And Trump's suggestion was that the tariffs cost China so much money. China sent the US so much money in tariffs that they released COVID as punishment. Now there's a couple problems with that. One, American companies pay the tariffs. Trump still doesn't seem to know this. Trump seems to believe that when he puts a tariff on Chinese imports, someone in China is cutting a check to the United States. American companies buy the stuff from China and then American companies cut a check to the United States for the tariff." }, { "from": "human", "value": "Trump doesn't seem to get that." }, { "from": "gpt", "value": "But it still has a sting to the Chinese economy. You can make the argument that if there is a suitable alternative domestically or from a different country, that it will reduce imports, but it didn't happen. And we actually have reports now that the tariffs on China cost about a quarter million American jobs. The other problem with that idea is China created and released a virus in order to hurt you. But as of today, 5.7 of the 6.8 million deaths were in other countries. It's a very indirect way. You're mostly killing people in other countries to hurt Trump. Maybe there was a, this is the sort of thing where when I think about how Trump dealt with China, it's very scary because given another four years, who knows what he might do if he still doesn't understand how tariffs work." } ]

[ { "from": "human", "value": "So geopolitics operates in complicated ways with carrots and sticks. And Henry Kissinger has written quite a lot about this and in some sense, the positive aspect here that Donald Trump is willing to take big risks in the game of geopolitics with this giant superpower that is China and a lot of others are too afraid, too afraid to call them out," }, { "from": "gpt", "value": "to come to the table and criticize. I certainly think that's an argument that can be made. My question would be what tangible positive outcomes did it lead to? And it's tough to identify any, but I think it's a great thing. I mean, listen, one of the things you're kind of getting at maybe indirectly is that there's been this sense that politics has been done very similarly for a long time. And even between Democrats and Republicans still, even with some policy differences, there's still the kind of feeling that it's disconnected folks in DC, mostly dealing with issues that don't directly affect. I get that. I'm with you on that. I think the question is to whether Trump's bluster was positive rather than extraordinarily humiliating in many ways. I just come down on, it was an absolute and total humiliation, but I understand that you can recognize Trump doesn't know a lot of stuff, but his attitude was refreshing in some way. That's a reasonable position for someone to take." }, { "from": "human", "value": "I disagree with it, but I understand it." }, { "from": "gpt", "value": "But it's trying and feeling better than not trying. This goes well beyond politics. You know, Wayne Gretzky has weighed in about this. Michael Jordan has weighed in about, I mean, this is a, yeah, is it, is it better to have tried and failed than never? Is it better to have loved and lost than never to have loved? I don't know. I mean, listen, we lived through four years of Trump. We know what that four year term was like. And it's very hard for me to say that the things he tried were overwhelmingly reasonable, but I get the point you're trying to make and I appreciate it. And it's, if we don't do any of it, then where do we end up? Sure. We know where we ended up with Trump" }, { "from": "human", "value": "and it was pretty embarrassing. Okay, let's linger on some more strengths. We didn't start any new wars. Is there something to that?" }, { "from": "gpt", "value": "We didn't start, yeah, that's, it's, it's interesting. There's a few different approaches to dealing with that. First, it's really important to remember that the counterpoint to that from the folks who liked to say that was that Hillary Clinton was going to start three wars. Sometimes they say four wars. Sometimes they say five wars. Okay. The geopolitical situation during the four years that Trump was in office, I don't know that they obviously lent themselves to wars that Trump just barely was able to keep us out of. I think the Russia thing is interesting because now it's very popular to go back and say, you know, the reason Putin didn't do the Ukraine thing when Trump, right? And to somehow give Trump credit for that. There's a counterpoint to it, which is Putin under Trump, particularly if Trump got four more years, would have been able to maybe consolidate power in other ways because of his relationship with Trump. I'm not coming down on one side or the other. It's not my area of expertise, but it's not the open shut slam dunk that, you know, Trump likes to say it is Putin didn't invade because he knew I would crush him. Okay. So it's not obvious to me that there were imminently wars that would have started during that time. That being said, you know, for all the criticism of Obama during Crimea, Trump seemed to just kind of forget about that after all the criticism and say, I'm not actually going to do anything about that. And so there's, there are foreign policy criticisms that could be made, but it is true. No new wars were started under Trump. And I like that." }, { "from": "human", "value": "I don't like wars. What do you think about his handling of COVID? Can you say what are the pros and cons" }, { "from": "gpt", "value": "of his handling of COVID? The con for him is he'd be president right now if he had handled it differently. I think it's abundantly clear early on. And there's now a lot of really good reporting about the conversations he was having with Jared Kushner and others. He became convinced either because of things he was being told or because he decided this is the way it's going to be. This is going to go away fine. It's in China. Okay. It's in China and Italy. Okay. We have 15 cases, but it'll soon be zero. We'll be opened by Easter of 2020. None of it happened. If he had handled it in the following way, and I've said this to Rogan and I've said this to Patrick Bette David, and they tend to all see my side of this. If Trump had said, listen, we don't know how bad this is going to be, but I care too much about the American people to take a shot. So it's not going to be two weeks. It's going to be a little bit, but I need your help. We're going to bring everybody together. I don't care if you're a Democrat or a Republican. We're going to have MAGA masks and he could have kept 50 cents on the dollar to pay off, store me or whoever, right? But it would have been, I think he wins reelection because the perception was, and reality is a version of that. The perception was that he was way too cavalier about it early on. People died who didn't need to die. And I think that it was arguably the one area where he could have all but guaranteed" } ]

[ { "from": "human", "value": "that he was going to get himself reelected. Well, to push back on that, I mean, because you mentioned sort of masks" }, { "from": "gpt", "value": "and lockdowns kind of a solution to COVID. I didn't mention lockdowns," }, { "from": "human", "value": "but I'm glad to talk about Paul's policy. Sure, quarantine, like there's several solutions to a pandemic, broadly speaking. And one of them is a vaccine. And so you didn't mention that. He fast-tracked the development. He, his administration fast-tracked the development of the vaccine, which surprising," }, { "from": "gpt", "value": "he didn't really take much credit for. Yeah, I think he did. I think he tried." }, { "from": "human", "value": "There's a couple, there's a lot there. Well, to me, it seems like you could make the case with the Trump hand gestures that his decisions for fast-tracking the development of the vaccine saved tens of millions of lives. You can make, he could, in the Trumpian way," }, { "from": "gpt", "value": "make that case. So, couple different things. I know you don't necessarily follow Trump's rallies as closely as I do, and I'm jealous of you for that. But he did tout the vaccine stuff hugely for a while until his audience turned against him. And then he had to draw this line where he was going, I made the vaccines, which none of you have to take, by the way, freedom. You don't have to take them, but it's fantastic. And nobody else could have done it, but don't worry, nobody's gonna make you take the vaccine. And he actually got booed at a couple of his own rallies when talking about the vaccines. But let's back up a little bit. Fast-tracking, my understanding of what he did is he did what any president in his situation would do and what many world leaders elsewhere did as well, which is he agreed to pre-purchase supply of vaccine in order to provide money to pharmaceutical companies to scale up the manufacturing, which is absolutely fine. But he wants, one of the stories he tells is, it usually takes 12 years to develop a vaccine. We did it in nine months, thanks to me. Decades of mRNA technology being developed created the platform in which you can make a particular vaccine in nine months. Didn't have anything to do with Trump. He did pre-fund and say, we will buy huge supply and that provided liquidity to the pharmaceutical companies." }, { "from": "human", "value": "But he also delegated control to people, to experts that enabled that kind of" }, { "from": "gpt", "value": "fast-tracking vaccines, right? He was very eager for the FDA to approve it" }, { "from": "human", "value": "because he saw that there would be a political benefit." }, { "from": "gpt", "value": "He didn't get in the way, I guess. He didn't get in the way, fair. I think now we're on the same page. He did not get in the way of vaccines being developed," }, { "from": "human", "value": "which is good, which is good. Presidents and bureaucracies have a way of getting in the way." }, { "from": "gpt", "value": "I don't disagree with that. I'm not aware of really any governments that got in the way. I mean, it seemed given the global situation, everybody with European countries were pre-purchasing the vaccine. African countries who were going to be later to receive vaccines were partnering with the European countries that had pre-purchased. But the most interesting thing about all of this is Trump did play up the vaccines for a long time until his crowd didn't want to hear about it anymore, which was crazy. It was sort of like he became a victim" }, { "from": "human", "value": "of the monster he created to some degree. One of the effects of all this that makes me truly sad is this division over the vaccines has created distrust in science. And also what makes me sad is the scientific leaders, Anthony Fauci being one of the representatives of that community, I would say completely dropped the ball. In what way? They spoke with arrogance. They spoke down to people. They spoke in a way that a great scientist does not speak, which is they spoke with certainty, without humility. Like they have all the wisdom and all of us are too dumb to understand it, but they're going to be the parent that tells us exactly what to do versus speaking to the immensity of the problem, the deep core of the problem being the uncertainty. We don't know what to do. The terrifying thing about the pandemic, we don't know anything about it as it's happening. And so you have to make decisions. You have to take risks about, well, maybe you have to overreact in order to protect the populace, but it's in the face of uncertainty that you have to do that, not empowered by science somehow. And the deep expertise that somebody like Anthony Fauci claims to have. So like, I just am really troubled by, yeah, the distrust in science that resulted from that. And that you have to blame the leaders to the degree, leaders take responsibility. And I think Anthony Fauci was the scientific leader behind the American response to the pandemic. And I think he failed as a scientist," }, { "from": "gpt", "value": "as a representative of science. Yeah, in what way? I'm less, I don't know if interested is the right word, but the kind of the Fauci review is less interesting to me in terms of what comes next than the first part you mentioned, which is the distrust in science. And sometimes I'll get voicemails or emails from people in my audience who say that I have had to backpedal on certain things related to this. And one of the things I tried to do from the beginning was not speak in certain terms when we really didn't have complete information. So there was this period where hydroxychloroquine was first sort of mentioned as a possible treatment, prophylactic or proactive treatment for COVID or active treatment for COVID along with a bunch of other stuff. There was ivermectin, there was vitamin D, there were all sorts of different things. And I tried to be careful to say, right now we don't have rigorous science that tells us that some of these things work. It doesn't mean that won't come in the future, at which point if there was something as cheap as hydroxychloroquine that treated COVID effectively, unbelievable, fantastic. It's not, there's no way it ever will be determined. We don't have that information right now. So it's not super wise right now to go and start taking this stuff. We eventually learned like with vitamin D, having an appropriate vitamin D level does seem to be based on what I most recently read, generally protective and a good thing when it comes to infections of different, great. Okay, so that one we figured out. One of the really difficult things is that the quote truth about the vaccines did change. And the original, again, this is all, I don't pretend to be an expert, but just someone who's synthesizing the medical data and writing about it. Originally, the first vaccine related to the wild type strain did seem to be very effective, not only at preventing death and serious illness, but also transmission. There were people then saying it doesn't prevent transmission. Over time, as the variants came forward, the vaccine became less effective at that. At that point, I started telling my audience something different because as far as I was concerned, the reality on the ground had changed. In my mind, that's how science works. It's not backpedaling, it's we're adjusting our beliefs to what is taking place in the real world." } ]

[ { "from": "human", "value": "Well, to be fair, the scientists, many of whom are my friends, biologists and biologists, they have way more humility than people like Anthony Faggio speaking about this, or the CEO Pfizer who are speaking about this. This is the fundamental problem here, is the way science works is there's usually a lot more humility and a lot more transparency about what we know and what we don't know. People like Anthony Faggio thought it would be beneficial for the world if he speaks with more certainty. But because of the political division that formed around that, that certainty resulted in, became completely counterproductive, that people didn't trust anything about the vaccine, didn't trust any institutions there were, that contained the experts that actually knew what they were doing and basically didn't trust anything that was coming out of the mouths of scientists, some large percent of the population. So that made you completely ineffective and at scale as a society trying to respond to a terrible pandemic. And that's where I put a lot of blame on leaders. So political leaders and scientific leaders are the ones that should inspire us to all get together and respond. That should be the case for the pandemic, that should be the case in the time of war," }, { "from": "gpt", "value": "all this kind of stuff. I generally agree with you and for me, it's really about shared blame and there were a lot of different reasons why that the early communication wasn't good. Part of it was, I mean, for me, I prefer accuracy rather than overconfidence. I would prefer, listen, we don't really know right now whether masks do X or Y. What we do know is the supply is really limited of this type of mask. We're gonna try to keep them for the frontline workers. I love that. That's the way I wanna be communicated to. A call was made to do it differently, which was to say, the masks don't actually help. But the real reason is they wanna keep them for healthcare workers. And then later, the masks are what's going to solve. I'm with you 100%. I think the other layer to it is you can't ignore the political situation at the time. If Trump had won reelection and the vaccine distribution had taken place while Trump was president rather than Biden, my belief is that the same number of Democrats would have gotten vaccinated, but way more Republicans would have as well because they were following not science, but political leaders. And when it was Biden in DC instead of Trump, a lot of those people said, I don't trust the vaccine, but wait, it's Trump's vaccine, I thought. Yeah, but something about the way Biden's distributing it. So I do think you can't ignore that political layer." }, { "from": "human", "value": "I agree with you, the communication was a disaster. Let me ask you about Joe Biden." }, { "from": "gpt", "value": "What are the strengths and weaknesses of Joe Biden? Weaknesses, I think, are some of the things you've identified. He is not seen as high energy. He is not the same Joe Biden that debated Paul Ryan in 2012 and ran circles around him in just an incredible debate performance. He is not inspiring in the way that someone like a Barack Obama was to people coming up and starting to get interested in politics. I think a lot of those are fair criticisms. I think on policy, he's not interested in a lot of the things that younger voters are interested in. I mentioned cannabis reform. I mentioned student loans. So I think that that's a deficit for Biden. I think the upside to Biden is when it comes to foreign policy, diplomacy, high level negotiations, knowing how to engage with allies in a productive way, it's tough to find someone with more experience than Biden. I know that there are counterpoints to what I'm saying. And those include, that was the old Biden. The new Biden doesn't have it. That includes, that's just a sign of rot because he's been around for so long. Nobody should be around that long in politics. Perfectly reasonable criticisms to talk about. But I do see that as one of his strengths. And he also is good at knowing when he can work with Republicans and when he can't and not wasting more time than is sort of expected for posturing reasons." }, { "from": "human", "value": "And I think that that's a good thing. Do you think he's actually there? So in a day-to-day operation of government, given his cognitive capabilities," }, { "from": "gpt", "value": "do you think he is an active and practicing executive? I don't know that I can say that it's because of what may be going on cognitively, but my sense from the people I talk to is that he's very much involved in the highest level geopolitical and big domestic economic stuff, but that a lot of the smaller issues that presidents might or might not be in, sort of plugged into, that he's not plugged into the details" }, { "from": "human", "value": "of a lot of the lower level stuff. Yeah, you could probably apply the same exact criticism even more so towards the Donald Trump administration in terms of being a practicing active executive who's paying attention. Like for example, like Vladimir Putin is somebody who loves the role of the executive, has a huge amount of meetings, has constantly tracking information about agriculture and all the different subsystems of government. Stalin, funny enough, was also extremely good at this. So certain people just love the job of being an executive. And I'm not sure if Donald Trump did, and I'm not sure if Joe Biden in this current state" }, { "from": "gpt", "value": "has the cognitive capability to. It's a good question. Kim Jong-un's another one, by the way. There's videos of him examining a pottery, a factory where they make plates and making very specific comments about how the plates should be made. I think that in that case, there's a lot of propaganda value to it. With Trump, I think you're probably right. He did get involved in the minutia of things. Once he pulled out a weather map and with a Sharpie drew a different hurricane path that was more politically convenient to him. That's pretty micro, saying the weather channel's wrong. I see what you did there. This is, okay. I see what you did there. Say that's a micro. He went to Puerto Rico and he gave out paper towels after a hurricane. Now he was shooting them like free throws, which didn't look very good. So he will get involved in the micro when it's advantageous, you know what I mean? But I do agree with you that he wants to just kind of make it so. Build the wall. I don't know, just build it." } ]

[ { "from": "human", "value": "Figure it out, get it done. It's wrong. I see what you did there. This is, okay. I see what you did there. Quick pause, bathroom break? Sure. Yeah, you're hilarious. And just for the sake of completeness, I should mention the subreddit, what Biden has done. There's also what Trump has done, but it's not as active. And it has like this master list of all the accomplishments. I recommend people look at it because it's kind of rigorous and interesting with Link's list of all the things he's done. Just list some of them. Restored daily press briefings. Canceled the Keystone Pipeline. Reversed Trump's Muslim ban. Required masks on federal property. Rejoins the Paris Climate Agreement. Extends student loan payment freeze. Extend eviction freeze. Historic stimulus bill, as you mentioned. Hence funding for border wall and so on and so forth. DACA, border strengthening of DACA. Rejoins the World Health Organization. And the timing of this, of course, is important. Yeah, several historic stimulus bills, which of course you could criticize or support. Raise the minimum wage for federal contractors and federal employees for $15. There's a lot. There's a lot. It makes you realize with both Trump and Biden that there's a bunch of small details that matter. Like that matter on people's lives, like actual little policies. Trump did a lot of stuff as far as I heard for the military." }, { "from": "gpt", "value": "Like not big stuff, but small stuff. You're hilarious. Yeah, I'd be curious what you're thinking of. I mean, I know one of the big things under Trump was we're gonna get trans people out of the military. That's not what I was referring to. You weren't referring to that. Trump's hilarious with these stories that he tells. And one of the stories, and you get to know them if you follow him at all. He tells the story. When I came into office, the generals came to me and they said, sir, the cupboards are bare. We have no bullets. And so I rebuilt the military. The cupboards were bare when Obama left it and it was just terrible. But I rebuilt it. And the generals, I've got the best generals. They said, sir, it's incredible what you were able to do. You look into it and it's like, yeah, that's not really true. It is true that there are armaments that just like on a schedule do get replaced. And that's part of the military industrial complex. But there's nothing like special Trump really did. But these stories become, they take on like a life of their own. And it's interesting to sometimes try to dig down and figure out like, was there any policy connected to that?" }, { "from": "human", "value": "Or is that just a story? Do you think it's possible to have a good conversation with each of them? Donald Trump and Joe Biden in a podcast context" }, { "from": "gpt", "value": "or in a debate context? Absolutely. Yeah, you're saying like, could I with either of them?" }, { "from": "human", "value": "Oh, a hundred percent. Yeah, you're saying like, could I with either of them? Yeah, Joe Biden too. Sure. Yeah." }, { "from": "gpt", "value": "Look, can you dig into that a little more? Well, I mean, I don't know what, I think there's maybe something implicit in your question," }, { "from": "human", "value": "but this deeper about the nature of politics and politicians." }, { "from": "gpt", "value": "Yes. I think with either of them, I mean, the political differences wouldn't be an impediment to having a good conversation with either of them. I think one of the things that's really tough in my experience when talking to elected officials is they could be super interesting about a hundred different topics, but handlers decide or try to get you to talk about something you don't really care about and something really narrow, which doesn't bring out your best nor their best. And that's a frustration. But I think that given an unstructured three hour conversation, I think it would be interesting to talk to both. I mean, listen, with Biden, aside from his view on cannabis or whatever, his background and the incredible unimaginable family tragedy that he had in his first wife and multiple kids dying. I mean, it's just incredible, you know? And with Trump, I think also you could have" }, { "from": "human", "value": "an interesting conversation. Yeah, there's the human beings with a life story. Yes. And they're some of the most successful humans who have ever lived to have rose to this highest office in interesting, complex ways. Yes. I mean, one of the things I'm troubled by, maybe you can speak to is why we're so negative towards presidential candidates and presidents. Why it's just, they go through this shit storm no matter who they are. They're like hated, like all the conspiracy theories and just, yes, just the dynamics of how we talk about them is vicious. If you just look at replies, Stephen Barack Obama on Twitter, it's like, what is going on here? Why, because we look at other leaders in other spaces" }, { "from": "gpt", "value": "and we're generally positive about it. Yeah, there's a couple of different things. There's this dynamic, which is really unfortunate, which is you ask people, do you approve of the job a particular president is doing? And very often, if at any point while they were in office, they did something you don't like, people will say, I don't approve. And so by its nature, what that means is just like the longer you're in office, the lower your approval rating is going to be. And very often that's the way it works. I mean, there's major events like 9 11 spike George W. Bush's approval to an incredible level. Then it came back down with the Iraq war. But there's this unfortunate thing that when, when people are just asked, you think Biden's doing a good job? If four months ago Biden did something on healthcare that somebody didn't like, even if you like most of it, a lot of people from that point forward will say, I don't approve. They might still vote for him because they like him better than the alternative or whatever. It's, it's just the dynamic of politics. And I agree. It's, it's very, does it have to be that way? I don't think it has to be that way, but to unwind it, so many things would have to change. I think our election system is part of why politics is the way it is where you have two choices and it's first past the post. And we have this electoral college so that depending on which state you vote in the kind of meaning and significance of your vote is different. If you vote in Montana, it's the Republican candidates going to win and that changes the dynamics. I think that's part of it. I think that at a personal level, I've experienced this in my life a lot. We've become, and by we, I mean, people in the United States to some degree who talk about this stuff. We've become uncomfortable when there is disagreement and it bleeds over into now we can't have a normal interpersonal relationship anymore. I'm from Argentina and in Argentina, it's really common, even in my family, there are incredibly heated political debates at the start, the middle, the end of some kind of gathering, but then everybody just goes back to like, okay, we disagree on some things, but that's okay. And we can now go and, you know, finish cooking the beef or whatever it is that we're doing. And I experienced this even with people who come up to me on the street and they go just earlier today, a guy came up to me and he said, RFK all the way, baby. Talk about Bobby Kennedy Jr. And I just kind of said, Oh, all right, you know, let's see what happens. And then there was another moment where the guy ended up standing next to me for maybe longer than he thought. And I could tell this guy is getting so awkward because it was an utterance he thought that would just be on the fly and he'd be gone, but now we're standing next to each other waiting for our sandwiches. It's like no big deal. You know, it's just, oh, okay. You like Bobby Kennedy Jr.? I don't plan to go for it. It's fine, you know, and that's like a socio-cultural thing. I think there's lots of other countries. I've spent time in Italy. I have relatives in Israel where like shouting at each other is sort of like normal. And then you just go back and finish them. It sounds like shouting, I'm sort of exaggerating, but very animated, what seemed like big disagreements and then everybody's cool." } ]

[ { "from": "human", "value": "I wish it were more normal. So maybe the mechanism of going from shouting to being cool again needs to improve because maybe we can't solve the shouting at each other. Maybe not. So maybe we need to somehow figure out the de-escalation like making up. I've had a few recent fights with friends like that. Yeah, politics. No, oh, no, but political style, emotionally drenched stuff. And it was interesting to go through that full process and then make up at the end, but it was a process. And it was a process that required being in person and talking through it. And it was stressful, the whole thing. And then maybe because most of our interactions are online, we don't get a chance to do that in person, making up again. I don't know, but do you think it's a feature or a bug of the system that we're so," }, { "from": "gpt", "value": "we just hate the powerful? Maybe not, really, but for politics. No. You mentioned the online part. I think it's, you mentioned it earlier perfectly, which is you take contentious political issues, you create a platform that rewards controversy and disagreement and limits the number of characters you can use to express yourself. You kind of throw it into a baking dish and mix the entire thing up. It's complete and total chaos. And one of the things that I've talked before about all the angry emails and threats and stuff that I get, I'm acutely aware that if I had in-person conversations with most of these people, the conversations would basically be like, oh, we have different views about how to solve some of the problems we're facing. We probably agree about what the problem is and we probably share many values, but on these particular four issues, we may have very different views, but that's okay. Online, that's not the case. And it leads to the mess that we get ourselves in, but I think that it's a feature of a lot of the systems" }, { "from": "human", "value": "that are being used to disseminate information. Again, let me linger on that. Do you regret some of the mockery and the snark you use on Twitter" }, { "from": "gpt", "value": "and even in your show that kind of feeds that division? I don't regret it in the sense that it's a calculated part or tool that I use in addition to figuring out how to simplify complicated concepts and choosing stories that I think are underrepresented. It's all part of the package of what I'm doing. I recognize that my show is not the audio visual version of a peer reviewed, randomized controlled trial about abuse on abortion or whatever the case, like I'm very much aware of that, but I don't regret including it as a tool that I've used to build the community in some total" }, { "from": "human", "value": "that I've built over the last more than 10 years. I guess I could ask about the different trajectories you think your show might take. So the dynamic you had with Donald Trump Jr. and maybe Candace Owens is the more appropriate comparison. Are you okay having that dance for the next few years between you and Candace Owens and just kind of the mockery, the derision that's a part of that process and taking part in that?" }, { "from": "gpt", "value": "I'm fine with it in the sense of personally, I tolerate it well until it crosses the line and people pull my family in and people, right?" }, { "from": "human", "value": "So that's the part that's the whole. So if we set the family stuff aside. If I set that aside." }, { "from": "gpt", "value": "Just in the digital space. If I set that aside, I'm glad to mix it up. Now, the truth is Candace Owens has had me blocked for years up until this incident. I don't know why. She unblocked me just to tweet about what I tweeted about. I don't know the backstory of that genuinely. I have no idea. So I don't have a sense that she's super interested in engaging with me on that, but all of these people, I mean, Candace Owens is welcome on my show anytime. Don Jr.'s welcome on my show anytime. It's been a decade since I had Ben Shapiro on. He's welcome at anytime. I'm glad to have these conversations and I think it's an important thing. And also I wish that everybody was willing to have the conversations in good faith rather than as performance. It's not even really performance art rather than being simply performative" }, { "from": "human", "value": "for an audience that you have. In terms of your motivations, do you see, do you worry about the effects of something you spoke off, spoke about offline or like the YouTube algorithm? Do you, are you driven by the number of views" }, { "from": "gpt", "value": "your videos get or are you driven by something else? So in my world, I guess I would say, the number of views that any platform generates is a metric that I can choose how to interpret. I can choose to interpret it as I've created content that's interesting to people or I've created content that's really angering people and that's why they're showing up. They don't actually like it. It's because they're angry or whatever else the case may be. But it is true that there are algorithmic changes that can take place. Something happened in early January that affected us on YouTube or there are periods on TikTok where you can tell, we're doing all the same things. Something has happened and then you never usually figure out what it is. So for me, it's sort of just like a general tool to see what is the level of interest in what I'm doing and are the numbers so out of whack with what I would expect that I should look into whether something deeper is happening. Has there been some change to an algorithm or whatever the case may be? I had a debate once with someone who accused me of using clickbait to generate views and we had a really interesting conversation where I said, tell me really what you mean by that. Is your argument that I'm using titles that don't actually represent what's in the video? No, what's in the title is in the video. I go, okay, so it's not that the title is dishonest. Are you saying I'm deliberately picking titles that will garner a larger audience? And they said, yeah, that's kind of what I mean. And I said, isn't that kind of what we're all doing? The alternative would be choosing titles to generate a smaller audience, which seems like a real kind of waste of time. So I'm trying to navigate and play the game in a way that's comfortable, but use the metrics more as a tool" } ]

[ { "from": "human", "value": "than as something to obsess over. Nevertheless, the metrics are what they are and that they are able to affect your psyche. It's very difficult, which is why I have a Chrome extension that hides all the views and all that on YouTube for me. It's difficult not to let it affect how you think about ideas. So maybe your extensive exploration of a particular topic like healthcare generated very few views. It's difficult for you to still care about healthcare. There's some aspect of the human mind that starts being affected by those views. And I think that's a really dangerous thing. Mostly it's probably beneficial because it probably makes you a better presenter. If you do care about a topic a lot, you become more charismatic, more you learn sort of in a Jimmy, Mr. Beast way, how to present the ideas better, but it also can affect which topics you choose to cover, what you choose to think about those topics, the audience capture those topics. And that's a really scary effect. I'm really worried about my own mind in that." }, { "from": "gpt", "value": "So I run from that aggressively. One of the things that I include in my overall approach is I don't think about any one clip. I think about an entire show or a week of shows or a month of shows. And so it's less about does any one clip do well? My view going in is I'm going to do stuff that won't do that well, but I think it's really important to do. And I want to make it part of my show. And so when I did a clip with 10 ideas for reducing gun violence, I know that that's not going to get 500,000 or a million views. I know it's just not going to. And the first day it'll get 12,000 and I'll go, I don't care. That's fine. There's a group of people in my audience that values this stuff. And I want to keep doing this stuff. I'll end up surprised sometime. And two weeks later has 150,000 views because it started being shared or great. But I don't go into it thinking these all need to be home runs by that metric. I always go in saying, I want to put out a diversity of content, including stuff that is less titillating and salacious, but is important to do. It's more researched, et cetera. And so that's the way I try to resist" }, { "from": "human", "value": "exactly what you're talking about. And I think you have to probably know yourself. Like for me, metrics, I just like numbers too much. And for me, metrics do affect me. This is why I don't pay attention at all. Like I can't, I would love to hire somebody on the team who cares, because we currently have folks who all of us just don't care. Because he probably is good to care enough to kind of just do good thumbnails and this kind of stuff to pay attention. But to me personally, I just find inner peace and focus if I don't think about the numbers at all. Because I find myself, I just remember a long time ago when I started a podcast, I would think that I failed if it didn't do well. Like if I didn't celebrate the person well enough, I didn't do a good job enough of a conversation. Well, that's not necessarily at all what that means." }, { "from": "gpt", "value": "It's hard not to- This is tough stuff. I mean, yeah, I know exactly what you're saying. And part of it is, I mean, it starts in my, you have a little bit of a different situation than me, because you're doing long-form conversations with people. And the prep is a little bit different. One of the things in my space, because I'm reacting mostly to what's going on in the news and then also picking topics to dive into it a little bit more deeply, is I have very little control over the news cycle. And there is a metametric or a macro metric that affects me that will quadruple my audience and then take 75% of it away, which is the seasonality of election cycles. And the first few election cycles, it's very tough, because I go, it's October. I'm like, at this rate, we're going to have 20 million subscribers by next, these numbers are unbelievable. And then it's January 30th, the inauguration's over, the debate is about the debt ceiling and nothing's going on. And I go, nobody's watching my content. I must have forgotten to upload a show, like something must be wrong. It's completely beyond my control. And I think part of what you're saying is, I try to focus on the things I can control and understand those that I really have no control over" }, { "from": "human", "value": "whatsoever and try not to worry about them. And try to do the things that make you happy at the end of the day, the things that, you mentioned RFK, the guy you met. What do you think about some of the other candidates outside of Joe Biden in the Democratic Party, RFK Jr.? What do you think of him as a candidate?" }, { "from": "gpt", "value": "I've met him, we once had dinner and we have a number of friends in common, which is what makes this a little more awkward. But I think his campaign is basically sort of like a chaos candidacy to raise awareness and maybe raise money either for his book or his anti-vaccine organization children's defense fund, I believe it's called. I think there's some reporting that Steve Bannon really liked the idea of him running as a Democrat, again, to just generate chaos. I don't find it super interesting. I don't find it worthy of that much discussion. Smart guy, nice guy, has been doing anti-vaccine work that I don't find particularly inspiring." }, { "from": "human", "value": "So it's not just anti-COVID vaccine," }, { "from": "gpt", "value": "it's more broader than that. He's been in that space long before the COVID vaccines." } ]

[ { "from": "human", "value": "Yeah, I don't find it super interesting. Well, he also wrote the book," }, { "from": "gpt", "value": "The Real Anthony Fauci, is that the name of the book? Did he write that? I don't know, I'm not sure about that." }, { "from": "human", "value": "I'm aware of that book, I didn't know he wrote it. I think I need it, but it's been on my reading list to get, I've been trying to get a good, balanced reading list about the COVID pandemic to understand what the hell happened. And anytime I start to try to go into that place," }, { "from": "gpt", "value": "it's just, I'm exhausted, exhausted by it. Well, it's interesting to me that you wouldn't wait longer before delving into those books" }, { "from": "human", "value": "to have maybe a more clear hindsight. But I think this is a pretty good time. You don't think so? Like this is, it depends on your goals. If you're thinking of it as a historical event, yes, you should probably wait longer. But if you're thinking about like understanding what is broken about our system that we responded so poorly, that there was so much division, what is broken about our political system that it didn't unite us, it divided us. Who's to blame? There's probably a lot of different narratives, but I feel like the more you learn about this, the better you can understand. I read, on just Vladimir Putin, I read like five biographies already, maybe more. Just, it helps to really understand the people involved, the organizations involved, I don't know, everything from the scientists to the political leaders. It felt like the blog posts and the tweets didn't quite capture the story." }, { "from": "gpt", "value": "They didn't quite, they didn't quite, no, one of the things I read a ton, I don't read any like modern political books. So I don't read the memoirs of elected officials. I don't read any, I just feel like I get enough of it in my job. So my reading list is just other things. It's history, it's narrative nonfiction, economics, et cetera. And that's my bias because I'm so overloaded with a lot of the stuff you're talking about. I haven't read any of Obama's books. I didn't read John Bolton's book or, you know, I don't read any of that stuff," }, { "from": "human", "value": "although I'm sure there is value to be gleaned from it. What about the other candidate that, according to the subreddit, and as you mentioned, you've criticized it a little bit, Marianne Williamson, do you think," }, { "from": "gpt", "value": "what are the pros and cons of her as a candidate? This is another area where many in my audience really are angry with me. I don't find her candidacy super interesting. I'll tell you the pros and the cons as I see them. I do think that we have elected officials in the U.S., particularly presidents, from a really narrow range of backgrounds. So it's lawyers and sometimes business people, very, very often lawyers. I think we would benefit from a much greater diversity of backgrounds. And I once said, and that would include people from education, people from the science world, people with backgrounds, maybe running nonprofits, et cetera. Now, Marianne Williamson did, I guess, at one point, run some kind of small nonprofit. And some in my audience thought that credential alone would make me fall head over heels in love with the idea of a Marianne candidacy. I've interviewed for her. It's just not for me is the way I like to say it. It's the background of the woo woo type stuff is a bit off-putting to me. I understand that someone with literal Christian Bible beliefs that also I don't like, maybe I'm more willing to accept as most of our presidents, of course, have had those views because they're otherwise more qualified. But some of the things that she says just strike me as, I just don't know. I'll give you an example. When she was on with Russell Brand, she said, there's no such thing as clinical depression. It just means someone in a clinic told you, you have depression. I don't believe that to be the case. I think we have an understanding. There's two types of depression. There's like a genetic predisposition depression. There's like a acute, something's happening in my life. Temporary depression, okay. When she was asked about it recently, she said, I didn't mean it. I was just trying to impress Russell Brand. I don't know if I'm more bothered by the things she first said or by the fact that she wanted to impress Russell Brand. But it's just like, it's just really not for me. And I agree with her on, we need to take the climate more seriously. We need to expand access to hell. I'm with all of that stuff. Now I want to say one other thing about this. Anybody who wants to run should run. I am not suggesting there should be an uncontested primary for Joe Biden. Absolutely. So you think it should be contested? Well, what I mean by contested is, so there's two parts to what we mean by contested. Will the DNC organize debates? And we'll get to that in a second, but should anybody who's on the left get out of the way because Joe Biden is president and he's running for reelection? Absolutely not. The question about should there be debates? I would like there to be debates. The DNC pretty clearly isn't going to organize them. I think if you did them, you would have to say at what polling level do you qualify? And I don't know exactly where you put that number, but I think it would be a great thing to put Joe Biden on a stage with, if you can get what, 6%, 8%? I'm not really sure what the number would be." }, { "from": "human", "value": "I'm totally all for that. Why is this set of candidates, at least from my perspective, so weak?" }, { "from": "gpt", "value": "Do you have an understanding? Do you have an understanding? There's a lot of different answers to this. One aspect of this, which I think is more of a socio-cultural thing, which I've recently read about to some degree, is the job actually turns off the people who would be best at it because of what you need to do to become president. And it includes all but completely abandoning your existing day-to-day life job, which you may depend on, and family to some degree. It's horribly negative, as we already talked about. And at the end of all of that, you either lose and then have to rebuild, and maybe you're not in a position to be able to do that, or you win, and then now you've got four years of being one of the most hated people, no matter how good a job you do. So I think by its nature, it turns off a lot of people that would otherwise be good. I also think that there's a lot of posturing from within the parties about, well, you might be good, but it's not your time yet, so you should wait, and then let's talk about maybe a Senate seat here and there. So it's like a company, essentially, and they're figuring out where they want to place people. I think all of these things make it so we end up with candidates most people aren't super thrilled with." } ]

[ { "from": "human", "value": "So it's difficult for somebody who's young" }, { "from": "gpt", "value": "or an outsider to quickly become a candidate, young. I think that that's true, and I think also, in a lot of ways, it's just not, would you want to be president? No. I mean, I can't be, because I wasn't born in the US," }, { "from": "human", "value": "so it's easy for me to say, but. If everyone says no, then we'll get the people that we have. No, I understand that. So I would love to help somehow. Sure. And I feel like there's not even a mechanism for helping, except through the democratic, through the voting process. But I'm just annoyed how little technology there is in the whole process, how little innovation there is" }, { "from": "gpt", "value": "in the whole process, all of this. The sad thing is, this is written about a lot, which is there's this thing called political hobbyism, and I think there's a good chance that some of the people in my audience are political hobbyists, in the sense that they follow this stuff as entertainment, to some degree. And I've written a lot about how, I've read a lot and talked a lot about how, okay, we vote every two years or every four years in our local elections, et cetera. And then we think about politics all the time. Neil Postman wrote about this in his book, Amusing Ourselves to Death. But what are you actually going to do about the kids starving in this country and the nuclear buildup in that country? Okay, if everybody refocused their attention on their immediate communities, and that could mean any number, it could mean the town or city you live in, or it might mean an athletic club or whatever. If everybody, this time they spent on political hobbyism, they moved somewhere else, which might put me out of a job. That's okay, I'm willing to lose my job because I think it would be so beneficial. Then our communities would just be that much better because you can actually affect change in a much more tangible way locally, whether it's obvious people talk about potholes," }, { "from": "human", "value": "but other things as well. Yeah, and I wish our system was more amenable to that kind of contribution, hopefully to the digital space it would be. Let me ask you about, on the Republican side, Ron DeSantis, what do you think of him as a candidate?" }, { "from": "gpt", "value": "Money against Donald Trump. Think of him as a candidate. I think in the couple of weeks before our discussion today, his campaign, which hasn't even started, has sort of started to implode. And this was something that I started thinking about in September, October. He really doesn't seem ready for prime time in the sense that just being confronted, and confronted's not even the right word, just being asked about some topics he didn't really seem to want to talk about. He responded in such a sort of disproportionate, unhinged way during his recent trip to Asia. He was asked about, why aren't you, or why are you responding but in this weird way to Trump's attacks on you? And he went into this weird bobblehead thing with a weird smile, and something came out that didn't make any sense, and he sort of got mad at the reporter. And it was just like, if you can't handle that, you can't be on a debate stage with Donald Trump. And again, for all my criticisms of Trump, the guy gets you on a debate stage, he can make you look pretty silly. He was recently asked about his role at Guantanamo Bay when he was an officer in, I forget which branch of the armed forces, and he just sort of attacked the journalist asking the question, and it just looked very bad. And there are increasingly big Republican donors who are not fans of Trump, and were sort of hoping to put their eggs in the Ron DeSantis basket who are saying, this guy just doesn't have what it takes, I don't think he can do it. So I don't know if DeSantis will be able to get away. Once you're polling 20 something like he is, and you haven't even announced, it's very attractive. And he probably to some degree is thinking, if I wait till 2028, I might not have this opportunity again. But Trump's polling 5253, which means even if DeSantis gets all of the current non-Trump vote, he has to figure out how to take something more from Trump." }, { "from": "human", "value": "I just don't know how he does it. First of all, the implosion aspect, that's part of the process, isn't it? You kind of implode a bunch of times. And then rebuild yourself." }, { "from": "gpt", "value": "And rebuild them because the new cycle kind of forgets. And then rebuild yourself, it's possible. The problem is, the first debate is in August. So that's only a few months away. And the decision's going to have to be made pretty soon. And unless he can get a new momentum going, I just don't know how he gets what he needs" }, { "from": "human", "value": "in order to really have a shot." }, { "from": "gpt", "value": "So would anyone else running against Donald Trump? It's very tough right now. I mean, there are other people running. There's this guy, Vivek Ramaswamy, who's running. Nikki Haley is running her campaign, basically dead on arrival. Trump actually does better in polls, the more people run. When it's just him and DeSantis, that's the best scenario for DeSantis. It's not great for DeSantis, but it's certainly better. But I think the difficulty is, this is a question for Republicans to figure out. The people who rightly recognized in 2016 that this guy is not good for their party, still believe this guy is not good for their party. But many of them recognize that most of the voters are still behind him. You can always say it's early, his polling doesn't really mean anything, anything could happen. Something major would have to happen for Trump to lose that lead. If he got more, if he was arrested two more times and had more indictments and it just became like, this guy can't even campaign because he's so busy going from court to court. Maybe that would make a difference." } ]

[ { "from": "human", "value": "It's really tough to imagine. You said that there are three categories of people who vote Republican and that Trump introduced the fourth one." }, { "from": "gpt", "value": "Well, can you go through the four categories? Sure. So you've got like your pro-business low tax Republicans. These are mostly people like Mitt Romney. Mitt Romney has a bit of the social conservatism as well. He's Mormon and that's there, but Mitt Romney primarily, particularly as a Northeast sort of Republican. I mean, I know Utah, but governor of Massachusetts, he is like a low tax pro-business type guy. You've got your libertarian type Republicans who are primarily about freedom and liberty. Often they are actually more socially liberal where they go, I don't care about gay marriage liberal. You know, I don't care so much about abortion. And that overlapped a little bit with the Tea Party movement in 2010, although Tea Party did have a religious component, but sort of like the libertarian freedom minded folks and then the religious conservatives, people that support candidates like Josh Hawley or Ted Cruz, et cetera, where they're a big thing are social issues. Often they actually want Christianity being civil government. They don't want separation of church and state. Those are traditionally the three Republican groups. The one that Trump introduced was people who just didn't really pay attention to politics, but either followed celebrity or had grievances that they didn't yet have a scapegoat for and were sort of right leaning culturally, even though they didn't attribute that to Republicanism. And Trump was able to bring them into politics often for the first time as voters. They could be part of any of those three groups if they get more into politics or kind of be their own thing, but they're more kind of like cult of personality." }, { "from": "human", "value": "I'm here for Trump types. Did it have to do anything about the culture wars" }, { "from": "gpt", "value": "and the identity politics, all that kind of stuff? Yeah, I mean, so in 2016, when Trump mobilized them, those weren't really issues the way they are now." }, { "from": "human", "value": "So I think at that time, it certainly was not a factor. What was the mobilizing issue?" }, { "from": "gpt", "value": "It was just anti-Hillary in 2016? He did a good job on anti-Hillary, but a lot of it was identifying real economic problems, wage depression, lack of jobs in parts of the country, you know, Ohio and Indiana. Trump rightly identified, like we have an issue here. We don't have enough entrepreneurship, et cetera. But there was also a lot of scapegoating that was, you know, China and people coming through the U.S.-Mexico border were popular scapegoats for a lot of those problems. This gets us kind of to populism. Populism is a rhetoric and populism as a rhetoric doesn't necessarily come with particular policies. You can be a populist, a user of populist rhetoric and propose solutions that would be more aligned with Bernie or Tucker Carlson. Populists will often identify the plight of the middle class. The difference would be Bernie will say, we've got to put some restrictions on how much billionaires can make. And we've got to reinvest in these social programs. Tucker will say, BLM taking your house and a brown person from Mexico taking your job are what we need to deal with. So the populist rhetoric can lend itself to very different policy. And Trump used that very effectively in 2016." }, { "from": "human", "value": "Why do you think Hillary Clinton was hated as intense as she was by a certain percent of the population? It feels like that's the first election I witnessed where there's a lot of hate. Maybe I'm misremembering. I don't remember Obama misremembering. I don't remember the degree of hate. There was a conspiracy theory that he wasn't born" }, { "from": "gpt", "value": "in this country, but I don't remember hate towards Obama. Record death threats under Obama" }, { "from": "human", "value": "more than any previous president. Towards who?" }, { "from": "gpt", "value": "Towards him. Yeah. Do you mean more hate between voters?" }, { "from": "human", "value": "Between voters, between voters. But like, that's I guess what I was speaking to, but that hate was directed towards the narrative, the thread that connected all of that in 2016" }, { "from": "gpt", "value": "was Hillary Clinton. Few different things. And I'm not ranking these. These are just all things that come to mind. One is Hillary Clinton had been around in the political space for a long time, from her time as first lady, through a senator, secretary of state, et cetera. So I think that there was enough time for different groups to develop an antipathy towards her for different reasons. So time. Secondly, Trump's branding of her as crooked was very effective. Where there were so many people demanding that she be imprisoned. If you ask them what is the crime, they don't know. But she should definitely be locked up. That became a very big thing. The email story, as it were, and James Comey doing a second public event about that investigation, even though there wasn't any actual news about it, just doing a second event about it at the last minute, I think hurt her and also generated some hate. And I don't find Hillary Clinton to be particularly likable. Although I voted for her, I thought she was the better candidate. And I think that there are others who also didn't find her particularly likable." }, { "from": "human", "value": "Those are a lot of impediments to becoming president. Well, I was trying to understand why there's so many conspiracy theories about Clintons, in general, Bill Clinton and Hillary Clinton." }, { "from": "gpt", "value": "And I, maybe I'm not researched well enough. There is-" }, { "from": "human", "value": "Of the why of it. The why of it, actually the extent of the conspiracy theories, the sort of the conspiracy theories" }, { "from": "gpt", "value": "that they've killed a lot of people, this kind of stuff. It's hard for me to speak to them because I'm aware that they exist, but I'm not an expert in them because they seem so obviously baseless to the degree that I've researched them a little bit. And then I move on and, you know, it's been years since I've looked at this stuff. I know there's the Seth Rich one and there's the Clinton body count one. I think there's one connected to Epstein, if I recall correctly. There's all sorts of these different ones. Without speaking to any of them specifically because I'm not the expert on Clinton conspiracies, it does seem as though this stuff for so long has generated an audience. I mean, I remember in the supermarket when Bill Clinton was president at the checkout, seeing the tabloids and there were stuff about Hillary birthed an alien baby and, you know, all the, it seems like it's been titillating to people" } ]

[ { "from": "human", "value": "for a very long time. Well, another question from Reddit, speaking of aliens, I would be curious to hear David's views on conspiracies and conspiracy theories, the extent to which real conspiracies happen and why conspiracies that have little evidence behind them managed to be so compelling to people regardless. Also, please bring up aliens and UAPs. Okay, where do we start? The conspiracy, what? So what in general, as a person who thinks about politics, thinks about this world," }, { "from": "gpt", "value": "like where do conspiracy theories fit in for you? And you, I think there have been conspiracies and by conspiracies, I'm using a colloquial definition, which is basically individuals working together to, in a clandestine way, impact or affect some kind of event or phenomenon very, very broadly. I mean, certainly that those things have happened. To jump around to some of the things that were in there, I think the reason that conspiracy theories are so compelling is that it's really tough for a lot of people to accept. There are random events, not predictable specifically, at a stochastic level, we might be able to predict them, but specifically unpredictable, bad events in many ways. I could be the victim of one or you could, or my family could. That's really scary to a lot of people, understandably so. And for some people, it's less scary and more soothing in a way to say, there aren't really random events like this. Somebody planned it. And if we had just known who planned it, it just could have been stopped because we would have known exactly when. That's just a psychological level, easier to accept for people. And I get that to some degree, because listen, it's not the most exciting thing that everything can just be going fine and something absolutely horrible happens and kills, who knows, some number of people or, so I think that's the biggest attractor to a lot of these conspiracy theories." }, { "from": "human", "value": "It doesn't apply to all of them though. But yeah, but there's still kind of a basic understanding of human nature where people, some people are greedy and want power and are corrupted by power. So there's kind of these compelling narratives that stick that, I don't know, the vaccine is an opportunity for a powerful billionaire to implant chips into you so he can control you further. It doesn't seem, what do I wanna say? It's like, for some reason, that doesn't seem as crazy as it should. Because you think like, maybe Hollywood contributes to that, but you think, yeah, you could imagine an evil person, a person that wants more control, more power, and is also at the same time able to convince themselves, as history shows, that they actually have the best interest of the populace in mind, that they're trying to do good for the world. So they do evil while trying to do good. You can kind of imagine it. So it's like, why not? And you listen to people in power, authorities, they kind of look and sound shady, you know? Like, the transparency, especially the older ones, I think younger folks are better at being real and transparent and just like revealing their flaws in the basic humanity. But people that are a little bit older in the positions of power, they're more polished. They're more like, it feels like they're presenting a narrative" }, { "from": "gpt", "value": "where the truth is hidden in the shadows. I don't think there's anything wrong with suspecting. Maybe a public figure isn't giving me the full story. Totally reasonable thing to question. I don't think there's anything wrong with exploring a lot of these different things. I think the problem becomes, and I know you've talked about this in so many different ways with other guests, the problem becomes when we lose a shared understanding of how we would assess whether any of these things are true. And then both alleged evidence and an absence of evidence both become supportive of the conspiracy theory, because if there's bad evidence, you manipulate it and say it's good evidence. If there's no evidence, you say the evidence was obviously hidden by the people who carried out the thing or whatever. So unless we can have a shared understanding of how we would determine what's true, these are common conversations often between atheists and religious folks. How can we deter, like, is my faith in something or my desire for something to be true, a good way to evaluate whether it is true?" }, { "from": "human", "value": "They're really similar questions. Well, let me ask you about Trump on that front about the election, 2020 election, maybe the better question is about January 6th." }, { "from": "gpt", "value": "Do you think January 6th was a big deal? I do. How big of a deal? Compared to what? Civil war. I think it was less of a big deal than the Civil War. Okay. No, I mean, so it's a very interesting thing though, right? Because we have not only the event, that's clever actually, it's not only the event, but it's what led up to it and what has happened since and did it change what is considered on the table that citizens can, should, or might do if they disagree with the results of an election? So I think that there are further reaching consequences than just was the six hour period on January 6th, a bigger or smaller deal than the Civil War. And there's so much wrapped up into it. Many conspiracy theories flowed from January 6th as well. 60 Minutes recently featured a guy named Ray Epps who was targeted by some on the right, claiming that he was an instigator or an agent of the FBI or something along those lines. There were people claiming that no real, it was like a no true Scotsman sort of thing. Like Trump supporters wouldn't riot. So by definition, it must have been Antifa. Police let him in or police were, you know, all these different things. I think it was a big deal in a lot of ways because it completely made us have to go back to the top to say, okay, what are the parameters of valid discussion" } ]

[ { "from": "human", "value": "and activism in the United States?" }, { "from": "gpt", "value": "But what aspect of the January 6th was bad for you?" }, { "from": "human", "value": "Well, I mean, if you're thinking it from a big philosophical political perspective, so presumably the number of people hurt and the number of people who died" }, { "from": "gpt", "value": "is not the only metric to consider here. Absolutely. I think the sum total of what it means about how the United States operates is what's most concerning. And I'll kind of just like flesh it out a little bit. So summer of 2020, Trump's already saying they're going to cheat. Now, the polling is close, but it shows that Biden's in a good position. People aren't happy with Trump. Any reasonable person would look and say, it's going to be close, but Biden certainly wouldn't be a crazy thing if Biden won, Trump's already saying they're going to cheat with mail in ballots. So they're going to cheat with early voting or they're gonna cheat with machines or we should do only in person or whatever else the case maybe we have the election. We knew in certain states how the vote count was going to go. Some states stop counting at 10 P.M. some states count all of the mail and stuff up front. Some don't, everything was completely predictable, at 2 a.m. Trump comes out and says, I won okay, but where are you getting that, sir? As he claims, people always refer to him. Where are you getting that? And with that statement, immediately we see that there is a large portion of this country that either is unable or unwilling to say, wait a second, the polling all said this was a real possibility. The counting schedules are all being adhered to. But Trump won, that doesn't make any sense. That doesn't happen. It builds, people are donating millions to Trump for supposed audits which nobody can define and lawsuits which go nowhere. And it builds and builds and builds. And we have a total separation from a factual reality. There's no reason to think by December 1st, right? Give three weeks to look through some of this stuff. By December 1st, there's no reasonable case to be made that Trump actually won, but it doesn't end there. It goes into maybe we can just like send different electors even though Biden won Arizona. Let's just like send, I don't remember how many electors it is in Arizona, let's just like send Republican electors to say we vote for Trump, but that's not democracy. That's not the way the system works. Let's make sure we're ready. Ready for what exactly? And then it builds to maybe Mike Pence can just like prevent Biden from being president or maybe we can just interfere in this other way. And then it gets to let's break into the Capitol. It's the height of saying we no longer comport ourselves attached to what is a verifiable factual reality. And when we no longer do that, we're also willing to commit crimes, property crimes, violent crimes, okay, to different degrees in order to try to have something other than democracy. It wouldn't be democracy if any of those things had happened." }, { "from": "human", "value": "Yeah, I think it's not the height of it. I think there is still a case to be made that that did not leave the realm of protest versus a violation of the principles of democracy. So to me, the height of what could happen on January 6th is if Donald Trump was much better executive," }, { "from": "gpt", "value": "he could take control of the military." }, { "from": "human", "value": "If it had succeeded. No, not even succeeded." }, { "from": "gpt", "value": "The attempt would have been more empowered." }, { "from": "human", "value": "I understand. The way not to bring up Hitler every other word, which is something your subreddit also told me not to do. It's kind of an important figure. It's interesting to study that moment in history because it reveals so much about human nature and that all of us are capable of good and evil. But thank you to your subreddit or Redditor for your contribution to the conversation. I will keep bringing up Hitler and the Third Reich and I'll keep bringing up Stalin. There's so much to learn from that. Anyway, an effective practice authoritarian could roll the tanks out into the city streets to establish order and in so doing, pause the process of democracy, as opposed to a few protesters breaking in" }, { "from": "gpt", "value": "to a questionably protected building. I agree that what you're saying would be worse. I don't want to use it to minimize what the protesters were intent on doing." }, { "from": "human", "value": "They failed, fortunately. But to you, the intention was there." }, { "from": "gpt", "value": "Well, the intention was Trump should remain president. That's the intention. And to what length they would have been willing to go if by the evening, early evening, they were sort of like forced out, I don't know. I agree with you that Trump trying to use the military would absolutely be worse. There's these reports that he tried to seize voting machines, which is kind of funny because it's like, once you get the machine at Mar-a-Lago, what do you do with it exactly? I don't know. There's like a comedic element to Trump sitting around with voting machines, but he did float trying to do some other things. I don't believe there's reporting" }, { "from": "human", "value": "that he actually tried to use the military. I wonder to what degree this opened the door to further things like this with other candidates on, you know, even in the Democratic Party also. Do you think there'll be more and more questioning" }, { "from": "gpt", "value": "of the election results? There has been already. It's very clearly the playbook. Kerry Lake lost. She ran for governor in Arizona, 2022. She lost. What I mean by that is her opponent received more votes. It's like very clear what it means that she lost. She insists to this day that she won. To this day, she did the same grift Trump did about donate. We've got a case. We won in the case. He didn't win. They just set a court date. Like that's not what, you know, lies upon grift upon lies. So they did it then. It is, I, I, it's extraordinarily saddening, but it seems like this is now going to be part" } ]

[ { "from": "human", "value": "of the playbook." }, { "from": "gpt", "value": "Do you think people on the left will start doing it? I don't have a reason to believe that that is going to happen, but I'm not going to say it never could. Absolutely. It certainly could. People on the left could start using it as a tactic. Right now there's not a sign that that's going to happen, but it's certainly good. My expectation is, and I'm not a betting man, but I would bet money. If Joe Biden loses in November of 2024, he will say, I lost. He will call the winner. He will concede and he will leave the White House" }, { "from": "human", "value": "in an orderly fashion. You don't think there'll be claims of a hacked election. The ability to hack elections is becoming more and more effective with the developments" }, { "from": "gpt", "value": "on the artificial intelligence side. The difficulty is you're basically saying, will something happen without me knowing anything about the election? Imagine there really was evidence of a hacked election. Then I would want those claims to be made, but the way elections have gone in the past, I don't expect that that's a claim that would be made." }, { "from": "human", "value": "No. Speaking of evidence of things that were claimed, what do you think about the Hunter Biden laptop? Or as you tweeted, the laptop from hell, the laptop from hell TM. Right. To what degree was this laptop story important?" }, { "from": "gpt", "value": "To what degree was it not? Right. At this point, I have said many times, if there is any reason to believe that Hunter Biden, Joe Biden, Naomi Biden, Jill Biden, Hillary, Obama, Doug M, if there's any evidence, any of them committed a crime, they should be investigated. They should be charged and they should be tried, period. The Hunter Biden laptop thing has been floating around for so long and we still have zero actual pieces of evidence of any crime, particularly involving Joe Biden. There's the claim from some that references to the big guy are about Joe Biden getting 10% for some illicit. It's been years they've been saying this, they've not been able to bring forward any evidence on it. So my assessment of the Hunter Biden laptop is, it seems to mostly be a story about nude images released without someone's consent, which is illegal in most states and violates Twitter's own policies. That's the main story to me. Beyond that, I don't know how many people have a copy of this hard drive at this point. Rudy had it, Tucker. Do you remember when Tucker, this is unbelievable. Tucker said that he mailed himself a copy, a USB stick and it got lost in the mail. You have the mother load proving the criminality of Joe and Hunter Biden. And I don't, you just dropped it off with a stamp and it got lost in the mail. You don't have a backup copy. So I'm ready for the evidence to come forward. Hunter Biden has nothing to do with Joe Biden's administration, but as a person who, if he committed a crime charge him, investigate him, whatever, but it's almost getting satirical, the degree to which they're talking" }, { "from": "human", "value": "about the Hunter Biden laptop. Yeah. What do you think about the social media aspect of this, that that story got censored? And what do you think about censorship in general on social media, that that story during an important time" }, { "from": "gpt", "value": "in the electoral process got censored? So I, as a matter of principle, I think we have to define what we mean by censorship, but I'm against censorship short of illegal content, I guess, is the way I would put it. I do respect the company's right to have terms of service and to enforce them, as long as they're not illegal. If Twitter were to say, we don't publish content from Jewish people. Okay, now we've got a problem on our hands. But what is dubious to me is the claim that had people been able to see Hunter Biden's genitals, they would have voted for Trump, which I know it's like, David, you're making light of, but at the end of the day, what exactly is the claim? That if you had known more about Hunter Biden, I guess allegedly hiring prostitutes and having a drug problem and seeing pictures, you wouldn't have voted for Joe Biden." }, { "from": "human", "value": "I mean, I know me as a voter, I don't feel that way. I think it's less about the content of the story and about the actions of a social media company to control what you see and what you don't see. So you could imagine a social media company like Facebook and Twitter making the same kind of decision about our more impactful story" }, { "from": "gpt", "value": "than a few dick pics on a laptop. Well, I think if that happened, then my view might be different, right? But I do, my general view though on the Hunter Biden story is had the articles not contained those images that were illegal in many States and violated Twitter's policies, I would say publish it, absolutely. I don't think it would have had an impact, but I would be in favor of it being," }, { "from": "human", "value": "of the links being allowed 100%. Okay, you mentioned Tucker. What do you think about Tucker getting fired from Fox? You're a media person that works independently. Yes. Tucker was a media person who doesn't work independently. Right. Yeah, what do you think about that particular situation? Is it representative of some big shift that's happening in mainstream media? What would the shift be? Basically, mainstream media freaking out because the funding is getting less and less and less and less," }, { "from": "gpt", "value": "and then it's going to give more power to individual-" }, { "from": "human", "value": "What would the shift be? Commentators, basically Tucker Carlson" }, { "from": "gpt", "value": "just starting a podcast and a YouTube channel. I think that's what he should do. I think that's the most profitable path rather than maybe going to work for Newsmax or whatever the case may be. But the firing fundamentally was not a politically oriented firing that suggests Fox News is changing its tune politically in any way. There's no evidence of that whatsoever. Tucker Carlson basically became a legal problem for Fox News. There's really four points to it. One is the $787.5 million settlement with Dominion partially was because of the claims that went out on Tucker Carlson's program. So to some degree, Tucker's program was a prominent node of the problematic claims that became the subject of the lawsuit. That's number one. Number two, Smartmatic, which is another voting machine company, still has a similarly sized lawsuit against Fox News based on the exact same sorts of claims it may cost Fox News again. So this is now two problems that Tucker's a big contributor to. Number three, former Tucker staffer has brought a lawsuit and I don't remember the exact claims, but I know that there are claims of different types of discrimination. It seems like it has legs and that may be a third payout related to Tucker Carlson. And based on the 60 Minutes piece from a few weeks ago, Ray Epps saying Tucker ruined his life by fomenting conspiracies about him around January 6th. That's ripe for another lawsuit. So to me, Tucker's firing was a risk mitigation strategy. Of many that will be employed as these lawsuits come forward, there's no evidence that it's because Fox didn't like. And what we mean by that, are we talking about Rupert Murdoch doesn't like or the, I don't know, but I don't have any reason to believe it's because Tucker's ideas were no longer welcome on Fox." } ]

[ { "from": "human", "value": "Certainly the audience liked them. So interesting. It's not even about the ratings." }, { "from": "gpt", "value": "It's about just the legal costs. Fox is interesting. The ratings question is interesting because Fox, unlike most other or every other cable news channel, they negotiate a fee from every cable subscriber. If you have Fox News as a channel, even if you don't watch it, Fox gets a little bit of money. They are dramatically less dependent on ad revenue than CNN and MSNBC. So the ratings question is an interesting one," }, { "from": "human", "value": "but Fox's position is different on that. Another question from Reddit. Both sides are the same in quotes, is a meme notion that has spread far and wide in American political discourse on the internet. To what extent do you agree or disagree with this notion? And why do you think it is so popular? Now, this Reddit comment also says that podcasts like Russell Brand and Joe Rogan or the legendary comic George Carlin are examples of big proponents of this notion, all of which I kind of disagree with. Russell Brand, Joe Rogan, and George Carlin claim that both sides are the same. The same and use that, you know all politicians are crooked and they suck and this kind of thing." }, { "from": "gpt", "value": "I don't know if they're... Same, both sides are the same?" }, { "from": "human", "value": "I don't know if that's true maybe George Carlin. Anyway, leave that aside. To what degree do you think... Do you agree with this notion that both sides are the same? Left and right, the crooked, corrupt politicians," }, { "from": "gpt", "value": "they do what politicians do. I don't agree that it's the same. I think there are different factions that like to say that for different reasons. There are some individuals who want to present themselves as kind of being above the fray of partisan politics and so I call it enlightened centrism." }, { "from": "human", "value": "Do you mean that positively or negatively?" }, { "from": "gpt", "value": "No, I mean it negatively. Yeah, it's a bit of a pejorative. The idea that I am not going to fall for being a Democrat or a Republican. I can see that these are just two sides of the same coin, equally bad, lying to every... Okay, so that's one, it's sort of like, it's popular at dinner parties in some circles to go, oh, I'm... Both all these politicians, you know, left and right. So that's one side of it. The other side of it is that it's often used when your side has really stepped in it. It's a popular way to acknowledge that your side has done something wrong, but while framing it as it's not uniquely wrong and it's not worse than what anybody else does. And I find that it's one of the lamest and most kind of cringe inducing things to hear because of the what comes next. And usually what comes next is not a good, accurate criticism of something that took place and a discussion of how to solve a real problem that we have. I find it a conversation stifler. It also is used to kind of suppress voter turnout, not actively. It's not that the people who say that go around saying, don't vote. But the idea, of course, is the more people that believe that it doesn't really make a difference who you vote for, it's going to suppress voter turnout. And I want voter turnout to be as high as possible, not as low as possible." }, { "from": "human", "value": "So I also dislike it for that reason. So is it possible to say that one side is worse" }, { "from": "gpt", "value": "than the other in modern current political climate? Listen, I'm a person on the left. I'm not pretending to come here and not knowing that my view is biased because I'm a person of the left. If you ask Ben Shapiro, he'll tell you something different. I think in 2023, some total, the influence of the American right wing, if the American right wing were to get everything it wants, it would be a horrifying reality. If the left were to get everything it wants, we'd have to figure out a few things, including exactly how we pay for certain programs. But they're mostly noble goals. And I believe that they are more supportive of an individual self-determining what they want to do in life and how they want to live and is more in line with the idea of freedom and liberty than what the right is currently proposing. That's my view. And of course, people will disagree with me all day. No, we get to freedom and liberty the way that the right wants to do it." }, { "from": "human", "value": "Okay, well, we can have that conversation. So I think you've implied in your answer, it was kind of focused on policy. It felt like it was focused on policy. There's other stuff that people worry about, particularly with the left, what may be termed the woke mind virus." }, { "from": "gpt", "value": "Where have I heard, who's using that term a lot now?" }, { "from": "human", "value": "I'm trying to think. I'm not sure, I'm not sure. I'm not sure where it comes up. But the cultural aspect of this, that if you give a lot of power to people on the left, as you gave as an example, there would be a lot of kind of censorship and suppression of speech and a kind of dividing up of a society of who's allowed to, basically a reallocation of resources, not based on merit, but based on some kind of high ethical notions of what is right. And only a very small percentage of the population gets to decide what is fair, what is right," }, { "from": "gpt", "value": "which is, you know. We already have a small portion of the population that's deciding fair. Okay." } ]

[ { "from": "human", "value": "Yes. But I don't know how many different ways I can say kind of a negative characterization of folks on the left when we're now comparing it, just as to play devil's advocate. Sure. So is that something that you worry about? So setting policies aside, wokeism. Yes." }, { "from": "gpt", "value": "How big of a problem is it? Yes. This is a great conversation. So let's, two sides of it. Okay. We have new polling that seems to suggest so-called wokeism is kind of more popular in the United States than anti-wokeism. And I'll tell you what I mean by that. This is the less interesting part. We'll go to the more interesting part second. People, sometimes what people mean by wokeism is an overreaction to a perceived injustice that goes beyond what would be fair and equitable. There was this really interesting poll in it. Ask questions like, for example, do you believe society has gone too far, not far enough, or just about the right amount in dealing with issues affecting the trans community? The woke position, which is society hasn't gone far enough, was far more popular than we've gone too far. Now, the right-wing media narrative is we've gone way too far. This is out of control. And there are lots of other similar answers. It's not a huge margin. A lot of these are like 58 to 42, 60 to 40. It's not like 90 to 10. But by a small margin, the so-called woke perspective of we actually haven't yet done enough to fix some of these issues is a little bit more popular. So if we went back to DeSantis, this is part of why I think DeSantis's anti-woke agenda" }, { "from": "human", "value": "may just be a political misstep. That's a really interesting result. I wonder how the questions are framed. But it's still interesting, nevertheless, no matter what, to hear that people are, majority of people in America, are woke," }, { "from": "gpt", "value": "and not in the negative sense of the word. The poll didn't use the term woke. Right. Right. This is a critical thing." }, { "from": "human", "value": "Let's use... This is a critical thing." }, { "from": "gpt", "value": "Let's use the term woke positively. The term has kind of been perverted. Yes. Four years ago, when the term was started to be used, I would have said, oh yeah, woke just means like, I have become aware of problems that are bigger than any one person can fix for themselves that relate to the system. I think that's what... And we might disagree on which problems fall into that category, but like it was kind of benign. I think now it just means like, outrageously left wing, maybe even with socialist or Marxist undertones." }, { "from": "human", "value": "It's become a pejorative at this point. But also like bullies. Like people... Bullies, sure." }, { "from": "gpt", "value": "Like people... Bullies, sure." }, { "from": "human", "value": "Sensors. Yeah, but people that go around calling others racist, sometimes, oftentimes, without any proof of that or justification. Fair. But that's a few folks on Twitter, you're saying like the polling is starting to show that like, no, they're still... Most Americans still care about these issues" }, { "from": "gpt", "value": "and want to improve, want to make progress. I think that's the case. And they want to do it in a genuine way that doesn't suppress or oppress anybody. But now let me get to like, to what degree do I think that actual, when it goes too far is a problem. It absolutely exists. We can find instances of where this exists on the left. I've been told many times that as a Jewish, Argentinian immigrant to the United States, I actually don't qualify as oppressed enough because Jews are privileged now in the US and my family had just enough money to leave Argentina. So there's this kind of like oppression Olympics thing where I've been told you don't get to comment. For example, like a topic in the Latino community now is, are you familiar with Latin X? Okay. In Spanish, there's an analogous movement where words by their nature sort of like have a gender. So like the word for friend is amigo. But if it's a woman, you would say amiga. So right from there, you can tell the gender that we're talking about. And if it's a mixed group, you say amigos. It's the male with an S, but it could include both. There's a movement now which wants to do away with that and put the letter E in. It's a new word. Okay. It's a gender neutral word. Amigos, totally new. I don't like that. And I don't know anyone. No one in my family uses it. And I think it's kind of like a strange imposition from someone kind of with a solution in search of a problem. I've been told you moved to the US long ago and like your English is good and like you look wide and so like you don't get to weigh in on that. That I think is an example, if I understand correctly, of the type of thing you're talking about. I'm kind of being bullied. I'm fine. I'm surviving fine, but I'm being bullied over it and disqualified and saying you don't get to speak on this issue. All of those example, all of that stuff, I am completely against. And I tell people on the left, we're actually hurting our own movement with this stuff." }, { "from": "human", "value": "I just don't think it's as big as some others believe. It's you don't think it's an existential threat to our civilization in the West." }, { "from": "gpt", "value": "No, I don't. No, I don't. And I mean, look, we've got a Biden administration. I see Biden as center left. Those who see Biden as extreme far left. This stuff has played almost no role whatsoever in the first two plus years of his administration. What does people that see him far left as far as far left? There's people on the right who I mean, Trump says Biden's a Marxist socialist communist. I haven't heard that." } ]

[ { "from": "human", "value": "I haven't heard that because I don't think that would stick very much. I think that's it at every rally." }, { "from": "gpt", "value": "Yeah, which I love very much. I think this is at every rally, which I love to tell us that you don't watch these things." }, { "from": "human", "value": "It's like I love how deeply researched you are in Trump. I can only imagine how good your Trump impression is at this point." }, { "from": "gpt", "value": "It's not very sadly. It's not. It's not. All right. No, but and I'll say one other thing on that, you know, take trans because just to talk about it a little bit, we haven't dealt with it much. The trans issue has become huge, I believe, because the right is obsessed with it. The right is very much not concerned with gay men anymore. It used to be that gay men is like, oh, we have to stop gay men from adopting and unnatural and pedophiles. Now it's trans. It's drag shows, et cetera. I do think that there is a fair question to say. How do we deal with trans women in a very small short list of sports? That's real. OK, my view, though, is I go, OK, we have all issues. We have issues related to gender and sexual orientation. We have issues related to trans. Within that, we have specifically sports. You can eliminate from that trans men. Nobody's worried about women, biological women who are trans men. And then when you say it's only in certain sports that it matters. Hey, I'm right there. I think it's a complicated question. I don't know how we deal with it. I would ask leagues that have experienced with this already. Whatever. The problem I have is pretending that the the vanguard of left wing politics right now is trying to force trans women into sports. It's like it's just not the big issue that the right is reacting as if it were." }, { "from": "human", "value": "It's not. All right. But perhaps because of the right, it's forcing the left to to continue discussing it. I mean, I feel like it, even in institutions, even at universities, it feels like these ideas of diversity, inclusion and equity are taking some of the air out of the room of what a university should also care about, which is merit. It feels like reprioritization is going a little too far the other way, meaning prioritizing this kind of amorphous concept of diversity is moving away, is giving power to people that don't care about merit. And it just want to bully people with a big stick that says racism or sexism or anti diversity. And it kind of suffocates the people that care about merit, about meritocracy, about inspiring people from all kinds of backgrounds to succeed. And it's just you kind of observe that. I'm sure that happens in all kinds of institutions. And the concern, I think the people that are concerned about wokeism are concerned about at scale, what impact does that have on a society when there's so much conversation about racism and oppression not to talk about merit, like who's the actual good person in the room, the best person in the" }, { "from": "gpt", "value": "room. Generically, that's a concern to me, the degree to which it's happening at different institutions, I think is worthy of exploration. I know people who work in academia that are getting out of academia because they don't like the environment on their campuses for exactly the reason you're saying so it exists. There is no question about it. I also think that the idea of a perfect meritocracy is maybe not necessarily the goal in the sense that when you talk about perfect meritocracy, someone wrote a book about this who I interviewed about a year and a half ago and whose name escapes me. There are problems with a perfect meritocracy. I think what we want to do is generate roughly equal opportunity for people understanding that there is going to be an outcome on a gradient or a bell curve, allowing people generally speaking to determine the path that they want to take and giving them, if it's possible, the ability to pursue that without suppressing limiting. I mean, this is like relatively uncontroversial stuff among, I would argue, 95% of the left with the caveats of what you're talking about, which I agree exists." }, { "from": "human", "value": "It would be nice to know the actual data. Sometimes people blow stuff out of proportion. What is it's hard. It's hard to measure how much self censorship happens at university campuses. That's true." }, { "from": "gpt", "value": "That's true. I think also it's sort of like the pit bull bite stories thing where when a pit bull bites a person, it's more likely to be reported on because it fits a certain narrative. And there are right wing publications that are very interested in making this seem as if it is an epidemic. I'm the first to say it is happening to a degree. I don't know the degree that it's happening to. I know a lot of people in academia. Only a couple of them say that it's an issue." }, { "from": "human", "value": "Would they say it though, if they believed it?" }, { "from": "gpt", "value": "I think they would say it to me. These are just personal contacts. It's not like I'm going to go blabbing. To push back." }, { "from": "human", "value": "I kind of agree with you, but at the same time, most, I mean, I'm deeply connected in academia. I have a huge number of colleagues. Most people self censor by not thinking about it at all. They're like, screw it. That's deeper. Whatever. I'm just going to focus on the thing I love doing, which is the work. And they don't think about, they basically remove themselves from politics and social issues. And they just kind of say, I'm going to do my engineering." }, { "from": "gpt", "value": "We'll do my mathematics. Sure. The problem with that is it's kind of, you can't go anywhere further to figure it out. It's sort of like, there's this funny clip where Jordan Peterson says, even atheists are actually religious. They just don't know it. And it's like, it's hard to test that, you know, I don't know. Okay. I mean, I don't, I don't know, but it's a, it's a fair point. I mean, there may be some people, if it has become so toxic for some people, they may have repressed it way down into their subconscious. But I don't know how we would know that." } ]

[ { "from": "human", "value": "But you, you, you know, symptoms of it because when certain people speak up kind of lightly and then a 19 year old or a 20 year old responds and is outraged. The fact that the administration listens to that 19 and 20 year old and then reprimands whoever spoke up a little bit. That's a really dangerous sign to me. And I don't really care about these, like, so I, I'm more with you. I don't think it's a big issue. But then I notice it. I wonder, wait a minute. Would this kind of environment allow a young Noam Chomsky to be around? Would this environment allow like, uh, I don't know, like, uh, what tenure was designed for, which is to have controversial thinkers and not kind of weird controversial things, but really people that challenge" }, { "from": "gpt", "value": "things that should be challenged a little bit. Yeah, I sympathize with that significantly. I always try to look at specific examples. And sometimes I'll look at people else. I'll ask for them and people will send me five. And one of them is a legit bona fide example of what we're talking about. And for kind of like, uh, there was a complaint and it was investigated, but the teacher's tenure was never in jeopardy. And I don't know that I chalk this up to a big woke event. What do you think the kind of apparatus of the four year degree in college is going to look like in 20 years?" }, { "from": "human", "value": "Oh, that's, I mean, we're like day by day that seems to be changing with GPT. I don't know if you've gotten a chance to interact with chat GPT. Absolutely." }, { "from": "gpt", "value": "My entire show now is written by chat GPT." }, { "from": "human", "value": "I mean, there's a, that's partially a joke." }, { "from": "gpt", "value": "It is only because it stopped looking at the internet in 2021. If it was current, I could completely just tune it out. No, I'm kidding. But it's a fascinating tool." }, { "from": "human", "value": "And, uh, it's changing the nature of how we, uh, do homework assignments. It's changing the nature of how we learn, how we look up new information, how we explore information, how we care about things we're interested in. I think it, um, I don't think we'll have value for university degree in 20 years the way we do now. I just think it changes everything. I think, uh, language models, I mean, Google search has already, and Wikipedia has already transformed, I would say our civilization, but it's, there was still a value for basic education. I don't, I think that starts to dissipate, uh, with, with chat GPT. So I don't, I don't know. I really, I really don't think there's a university the way we think of a university in 20, 20, 30 years." }, { "from": "gpt", "value": "I mean, I have a personal interest in it in that my daughter is 10 months old and I'm doing the 529 account. I'm going through the motions as if, but I also recognize, you know, if she went to the schools I went to just with the rate of tuition increase, you're talking 200 K a year by the time she's 18. And what happens with wages relative to that? This is like separate from the technological thing. And in my mind, I'm thinking, is this going to continue being the right path? What I would love to see is so many people that I interact with just by virtue of what I do have no foundation in critical thinking, epistemology, philosophy, media literacy. And if there were some way to make that the core of some basic education that everybody's receiving, which goes beyond, you know, chat GPT can do so many things, but I've not yet seen good examples of how it can teach you to think. Maybe you have a different view on how chat GPT can teach a user to think. But those skills seem to be so lacking in so many of the people I interact with. If there's any positive change to come from a changing dynamic with higher education, I wish it would be to go in that direction." }, { "from": "human", "value": "Well, no, chat GPT is actually much better at helping me think than any educator, even books that I've encountered, because it's very good at presenting the full picture, even better than a lot of Wikipedia articles, you know, on questions like the the virus leak from a lab, the COVID leak from a lab, it just presents to you all the different hypotheses, the amount of evidence available to it. It's like, it's like a full, calm, objective picture of it. There's no partisanship. It's like a really nice list of things that's available." }, { "from": "gpt", "value": "But I guess what I mean is, does it tell you how as a thinking human, you should evaluate the strength of each of the paragraphs it presents to you? You can literally ask. You can ask it to do it." }, { "from": "human", "value": "Okay. Okay. Yeah. And then it's actually a fun, it's fun to ask chat GPT that question, because you get good answers. And so you basically have a kind of Socratic, like a deep, intimate, like great podcast style conversation with an AI system every single day, or as many hours as you want, especially as it improves, and as the interfaces by which you communicate with a thing improves. So yeah, I think it will do exactly that, which is teach you how to think, because you will offload the memory of facts and equations and whatever else a school teaches you, you'll offload that to AI. And instead, you'll be using your human mind, which is what it, for now, is uniquely good at, which is asking good questions," }, { "from": "gpt", "value": "thinking through the complexities of issues when there's multiple perspectives on it, all of that. Well, then I stand corrected. Maybe then I don't know what college is going to be in 20 years." } ]

[ { "from": "human", "value": "Well, but you were sort of commenting, I see, to the, the financial aspect of it. Like, why does it even make sense?" }, { "from": "gpt", "value": "Yeah. Yeah." }, { "from": "human", "value": "I'm thinking about the transformative effects of AI and what starts to ask, what is the, what is even education? Right. What do you suppose, what is the purpose of education? So one is to give you kind of a background knowledge on a bunch of different topics, but the other is to discover the thing you're truly passionate about and the thing you're really good at, such that you can make money and you can contribute to society and have a fulfilling life." }, { "from": "gpt", "value": "Yeah. And also learning to interact with other people, relationships are built, socializing, and so many other things as well." }, { "from": "human", "value": "But is that, you know, that is the big value of university. And maybe it should be called something else." }, { "from": "gpt", "value": "Yeah. Can you get that for less than 200K a year? Exactly. Or else? Yeah, no, it's a fair question." }, { "from": "human", "value": "A kind of social club." }, { "from": "gpt", "value": "And you know, one of the things I think about also is people who are well connected. I mean, this has always been, this isn't new, right? But if you're well connected and you have a sort of drive towards entrepreneurship and doing your own thing, and you're not pursuing a field that is very licensing dependent, like medicine or law, getting started four years earlier with some internships can be a privilege in some cases. But again, that's that path is available to the people that would likely do well, regardless of whether they went to college. And so it's a very privileged, self-selected group anyway." }, { "from": "human", "value": "Another question from Reddit. Ask David to explain why American style libertarianism is an unserious philosophy." }, { "from": "gpt", "value": "I don't know what they mean by American style libertarianism. I've talked before about these kind of utopian libertarians where, you know, we have we don't have police. You just kind of like hire a for profit company if you want protection. And if there's a conflict between two of these private security companies, then I don't know. You figure it out somehow." }, { "from": "human", "value": "So it's almost like anarchism." }, { "from": "gpt", "value": "Yeah, yeah. Yeah. If by I don't know what the question means by that American style libertarianism, but in general, my problems with libertarianism, as it is often presented, come from the work of sociology as well as human psychology, which is the reality that once you get a group that's bigger than one hundred and fifty people, you really have to start centralizing some decisions unless you're going to subdivide the one fifty endlessly into two seventy fives that now no longer have contact. But then that's not really one society. Now it's two. I've not seen good evidence. And I've read a fair bit about this, that once you get beyond one fifty, you can keep all decisions decentralized. And once you say some things need to be centralized, then it's a matter of how you do it. And it's going to be some version of government that conflicts with aspects of libertarianism." }, { "from": "human", "value": "Well, it could be companies, right? It could be it could be more market driven, which is the idea of anarchism, that you're not you don't give any centralized entity of monopoly over violence. And then if you think that the markets are efficient at delivering, especially in this twenty first century and beyond where a market could have perfect information about people. So one of the issues is that you can manipulate markets because there's not perfect information. But now in the digital age, we can we can be higher bandwidth participants in the market. So if you're choosing between different security companies or you're choosing between different providers, different services, you can do so more efficiently and more effectively and in the digital space. So you can kind of imagine it. But we haven't successfully done it without governments." }, { "from": "gpt", "value": "Yeah. And I think there's a practical once you get beyond one fifty, you also start specializing. It just is a matter of fact, you don't have everybody isn't growing their own food. Some people grow the food and other people do other things. And you come across a lot of the problems that started at the agricultural revolution. And whether you say that it's a company that's solving it or a government, the problems are going to be very similar. And I've not read anything that to my satisfaction explains how you deal with that." }, { "from": "human", "value": "Well, there's underlying principles of libertarianism, which is putting priority at the freedom of the individual. Right. And that's a compelling notion." }, { "from": "gpt", "value": "Yeah. Whenever I do these various political compass things that put you on two axes on the authoritarian libertarian axis, I am way down on the libertarian side as a left libertarian. So my tendencies are always anti-authoritarian and towards that option when it makes sense." }, { "from": "human", "value": "So I sympathize with that a lot. Another question from Reddit. Ask David what issues he disagrees with you on. Is there something? I have no idea. Okay, that's great. There you go. There's no issues. Perfect agreement. What's your view on Tesla? That's a good opportunity to ask. What do you think is strengths and weaknesses of Elon Musk?" }, { "from": "gpt", "value": "You mentioned Twitter. Have you paid your $8 idea? Okay, that's great. I have not paid my dollars. I don't see the point in paying for it. I have no problem paying for services. I use a ton of services. I'll try the free. I'll go to the paid right now. So the way I used to use the verified feed was I would post a tweet and then the next day when I, you know, review what's going on in my social media, I would look at the replies to the tweet, which give me a mix of replies from verified and unverified people. But then I also look at the verified and see who that are verified public folks have responded to me or maybe I want to engage with or whatever the case may be. There's, I don't even understand why I would look at the verified feed anymore. So I never do because it's random folks who I don't" } ]

[ { "from": "human", "value": "know when it, it sort of lost its utility to me. And then, yeah, sorry to interrupt, but the idea is if everybody who's human pays the eight dollars, it shows to you that it's not" }, { "from": "gpt", "value": "bots. It's at least humans from the reports about the number of people that have bought the blue check Mark. I think we may be a thousand years from enough signups in order to make that sort" }, { "from": "human", "value": "of like a reality. I don't know. That was the idea. It's an interesting idea. Honestly, I know" }, { "from": "gpt", "value": "that was the idea. It's an. From my experience, the obviously, I was seeing all sorts of attack comments, some of which were, I'm sure, from bots. But I'm ignoring all of those comments anyway. So it really didn't affect my experience that much. I mean, here's the thing about Elon and I say this people sometimes like David, you obviously hate Elon or you obviously love Elon. I was an investor in Tesla starting in 2015. I've since sold all my shares. Great run. I'm on my second Tesla right now. I probably won't get a third one because I think that electric vehicle technology is now maturing such that when my lease is up, I'm going to have many more options with the range and charging network that's important to me. But I could be wrong. Maybe, you know, I don't know. I have no the cult of personality around people. They mean nothing to me. So for me, it's just like people are people. Nobody has only good ideas. Fine. I think that what Elon Musk did accelerating and pushing forward the battery and electric vehicle technology is unbelievable. It's it's a it's a one person wrecking ball in the best sense of saying we're not going to slow play this and do. OK, now Toyota has a Toyota hasn't actually entered, but now whoever we've got a 90 mile range car and next year it'll be 110. And it's just like we're doing this right now. You can compete or you can opt out and look at what's happened. Fantastic. On the Twitter side of things, I don't really get the whole plan. I don't know if it started maybe as kind of a goof of some kind. And it developed into I guess I have to buy it. And I think something about it ended up with there was a clause invoked where I think he did try to get out of buying it, but then was forced to to some degree. He was forced. The way Twitter used to work was you followed people. And when you looked at your feed, you either saw the posts from the people you were following in reverse chronological order or posts from the people you followed algorithmically tailored to what you're most likely to want to see. And if you didn't follow someone, you generally wouldn't see their posts unless it was like a sponsored tweet or someone you follow quoted or retweeted them. Fine. The for you feed TikTok, I believe, first had a so called for you feed. The idea is this is stuff you might like based on I don't know what either demographic data about you, your other habits, whatever. And so it's useless to me. It's just" }, { "from": "human", "value": "it's just basically mostly right wing content that that is not an interesting thing. That is, I mean, so the the signals that are used to generate the for you page is looking at all your your likes, all your comments, all your blocks and mutes and all that is show that I mean," }, { "from": "gpt", "value": "I don't know why it's looking up. OK, so it's supposed to be very pleasant for you. So that I mean, I don't know why it's OK. I'm sure other people go, wow, this for you thing is awesome. And like, if you had insert some right wing or sitting here, they would go. Twitter used to suppress right wing voices, and now finally they're getting the fair shake that they deserve" }, { "from": "human", "value": "in the for you feet. OK, I mean, I wonder if there's left wing folks setting their feelings of Elon aside that are enjoying the for you page. That's a really important question because it's supposed to be people on the left and people on the right should be enjoying the for you page." }, { "from": "gpt", "value": "Sure. Yeah, I mean, so for me, my thought on Elon is some incredible successes. I don't know about Twitter. I do think that I don't believe Elon is a right winger. And when you see interviews with him, certainly at least socially and in many ways culturally seems very moderate or even somewhat on the left in my experience. So I don't think it's Elon's a right winger. I don't that's not an interesting critique. It does seem, though, that throughout the Twitter escapade, he certainly ended up closer to some voices that may be influencing him in a particular way. That's giving some people that impression, you know, but as far as like the Elon hate or the Elon love, it's just it's just a person who's done some interesting things, some of which I like and some of which I could kind of leave aside." }, { "from": "human", "value": "I have seen folks drift towards the right more in response to just the viciousness of attacks from the left." }, { "from": "gpt", "value": "Like who? I'm all Elon. And so like who? So you do you do think he's drifted towards the right?" } ]

[ { "from": "human", "value": "In so I don't think at the core, but I think on the surface. Okay. I think and I think Joe Rogan has as well on the surface, because I think maybe you can correct me. But it feels like people on the left attack more viciously. That has not been my experience. Well, it hasn't. No, this goes. So yeah, let me know, because my sense was that they attack people on the left viciously as well. Left attacks its own because you're not progressive enough. You're not, you know, it's" }, { "from": "gpt", "value": "just this kind of bullying. Yeah, it was very intensely. Yeah, it was very intensely. No, you're 100 percent right that when the left has attacked me, it's almost as vicious as when the right attacks me. The difference in my experience is it's a smaller contingent on the left that's willing to levy those attacks against me. But I'm on the left. So to some degree, you could say," }, { "from": "human", "value": "well, that that's to be expected. There is toxicity on the left. But it's intense, isn't it? Like, that's what I mean, like the attacks on people who are on the left just you're not left" }, { "from": "gpt", "value": "enough. Yeah, that's no, that's the I mean, it is a small number of people. I can't deny that that is absolutely absolutely a real phenomenon. And it depending on what sort of topics you take on publicly, you are going to suffer the wrath of that to a greater or lesser degree. But with all of these things, what I always go back to is, you know, I probably would have more disagreements with Rogan today than the last time I was on his show, which was like at the beginning of the pandemic. But there would be zero. And I've done clips critical of things that he has said substantive, of course, to me, it's sort of like, oh, yeah, I could sit down with him and do a podcast and it would be zero big deal. And I would tell him I stand by everything I said about what you said. And I would say it to you right now. There are people who write to me and go, oh, man, things must be really, really tense. Now, if you were to Rogan would never have you on because you disagree. He loves you. I'm sure he's just not thinking of it. I'm not the most important thing to Joe Rogan. I think both of us would be able to sit down and talk about every one of my criticisms. It would not be taken personally. And then we would move on and it" }, { "from": "human", "value": "would be the next day. And it is a small number of people. You get attacked a lot. How do you not" }, { "from": "gpt", "value": "let that break you mentally? I don't know. So let's see. I try to I mean, I'm in a toxic space. The news and politics, partisan news and politics, partisan news and politics on the internet with a social media component, just completely and totally toxic. From a personal perspective, when I'm done producing my last show of the week, until Monday, I try to completely tune out from news and politics altogether and also make an effort to just not look at feedback and what's going on. I also really limit my visibility. I don't need to read every comment. I don't need to look at every email or every tweet. I have 15 minutes each day where I go through my social media platforms, look at generally what is the reaction been, maybe include that in my assessment of how I want to tackle a certain issue if I missed a good point or something like that, and basically try to move on. When something like we talked about at the beginning happens, it becomes obsessive. I mean, it's unhealthy, right? Where I'm going, oh, my God, who's attacking me now? That's scrolling. It becomes, you know, I'm sweating. It's horrible. But I think just like limiting exposure to that and remembering that it is impossible to please everybody. And so I'd really rather have fresh, genuine views each day rather than views that are sort of like restricted and flattened by what I perceive to be people's preferences." }, { "from": "human", "value": "Yeah. So just can you speak a little more to the full process of creating the David back in the" }, { "from": "gpt", "value": "show? Like what you wake up because you're doing five shows a week. I have the Letterman schedule, which means I do five shows in four days. I shoot Monday to Thursday, but we're doing five episodes. Basically, our guests we schedule in advance. I'm picking six to eight stories each day that are, like I said, a blend of stuff. I think will be interesting things I want to talk about and things where there's it's being discussed at one layer and I want to go deeper on it. And I feel like I'm able to do that. I choose those stories in the morning, record in the early afternoon," }, { "from": "human", "value": "and we put the show out by that afternoon. What's the preparation? How do you take notes?" }, { "from": "gpt", "value": "Are you on a sheet of paper? No sheets of paper anymore. I used to do sheets of paper. I found something about it, like at work, the tactile nature of it. It became inconvenient for sharing the notes with my team, but basically we use a Wiki type system. It's called MediaWiki, which is basically like a Wikipedia clone old school. Yeah. Old school. So we can have pages for every guest, every topic. That's interesting. I haven't heard that. Yeah. I don't know anyone else who's using it. It works really well. It's so fast and it takes up almost no space. So it just is a really good tool. When my team, you know, when we book a guest and they have notes from the publicist, they'll put it in there and then I can access it. So I'm basically working off of notes rather than a script. I'll pull any audio visual stuff that I want so that that's available. And it's, I mean, it's really a very seamless, you know, we're doing this every day, four days a week. And so we have" } ]

[ { "from": "human", "value": "it down to a well-oiled machine. We haven't heard that. Yeah. Where do you get ideas from?" }, { "from": "gpt", "value": "Everywhere. I have a bunch of subreddits that I follow that I think are talking about interesting things. I have a curated list for which I still use Twitter and that is very good for this. It's a curated private list of journalists that I think are doing interesting work. So I'll see what's there. Look at the sort of standard news reporting, wire services, AP and Reuters. Glance at what everything from drudge to CNN to whoever is covering that day. Look at Google news." }, { "from": "human", "value": "How do you try to fact check stuff on your show? So like, is there sources or is there a process?" }, { "from": "gpt", "value": "I always try to get to a primary source first and foremost for the facts of the story. And then I'll use other tools for background research. Oftentimes Wikipedia's footnotes, I find to be useful tools. Chat GPT is a good one. It, you really have to fact check it, but it'll give you ideas of where to do the fact checking, which I think is fantastic. Sometimes it gives me information that's flat out wrong. And when you ask for the source, it's like, oh, yeah, that, that actually is not real. Um, which is, Hey, it's part, part of the process. But, um, and then when there's like an expertise type of thing, if it's a breaking legal matter, I'll just call like a friend who's a lawyer or call a friend who's a doctor or something like" }, { "from": "human", "value": "that. If it lends itself to that. Let me ask you about the nature of truth. Do you think it's becoming more and more difficult to know what is true and will become" }, { "from": "gpt", "value": "continuously continue to get more difficult, especially with GPT? I think the big difficulty is in getting people to agree as to what is a statement of fact and what is a statement of opinion. I think once we can do that, reasonable people can more or less agree on how to get to the truth, or if we can't get to it, at least figure out how we would if the information were available. But the bigger challenge I'm having is someone will call in with an opinion, but say they want to talk about fact. And I have to explain to them, you're talking about an opinion and not a fact. And this goes back to the lack of critical thinking and lack of media literacy. Uh, but" }, { "from": "human", "value": "that's the bigger challenge for me right now. But I mean, I think the big statements are always going to be somewhat opinions. Like, was the elect was the 2020 election fair? I think any answer to that is an opinion. I disagree. If I disagree, if we define fair. Well, yes. So then I don't think it's possible to define fair in a way that's not several paragraphs where each sentence now has facts, right? So what do you mean by fair? Is it, uh, who could show up to vote? What was the process of how easy it is to vote? Uh, was there actual, uh, cheating going on in different, like what is the evidence of that cheating? You have to actually get to the actual like details of a thing. High level, you know, uh, everything is just going to be an opinion. It feels like, and you can approximate that to be like, it's a well-founded opinion. Well, most of science is an opinion, even physics is an opinion. So like, I think there's a threshold beyond which an opinion becomes like, uh, this is a pretty reliable thing to assume for now" }, { "from": "gpt", "value": "that that's okay. So let me revise. So I think maybe better said, I think that the difficulty, I mean, it is the process you described is probably the right process and is it's exhausting for mundane things. And that causes major problems. If we were to say, is it better for the economy to have a tax rate on people making over a million dollars, that's 20% or 50%. Okay. What do we mean by better for the economy? It's not an overwhelming task to decide on that. We could say, well, we'll say it's better for the economy by looking at what was the unemployment rate based on the tax rate on million, you know, people earning a million a year and what was GDP and whatever. Okay. We've, we've agreed. This is a statement. We are now in the realm of just determining what is given the parameters that we've established. I think that that's, that's relatively doable. The issue is with the bigger ones like you're talking about where, what do we mean by a fair election and fair in whose eyes and, but I am with you that it often devolves into a conversation about" } ]

[ { "from": "human", "value": "opinions about what is fair rather than an ascertainment of the facts. Yeah. Yeah. And it feels like maybe avoiding some of these big, maybe there's some trigger words too, maybe avoiding them allows you to actually talk about the facts and through that, educate yourself and learn about like, uh, whether the virus leaked from a lab or not to me was always a super interesting question. I don't know why everybody got super touchy about it. Uh, most of the people I know, uh, colleagues, biologists thought it's pretty good likelihood that it leaked from a lab given everything. They just didn't, the evidence is not there for a either one. And so like, you should be able to just openly talk about it unless you're in a high political office where there could be geopolitical consequences to your statements. But in general, it's an interesting question. You should be able to talk about it, but there's no, first of all, there's not many facts around there, unfortunately. Um, and a lot of very conclusive statements about, especially in the early days were just opinions. And so you have to minions the idea of what is true and not becomes a little, even mentioning the word truth in that" }, { "from": "gpt", "value": "context. It feels, um, defensive. Yeah. I completely agree with you, which is strange. Like it really, you think it shouldn't, one of the really good opening questions that I've had worked to my advantage when talking with people who I know disagree with me about a contentious topic is how do you think we would figure out X? And it often gets people thinking first collaboratively. And obviously we might have very different opinions, but with something like the COVID lab leak, I think it's an interesting one because if you say, okay, maybe it leaked, maybe it didn't, how would we figure that out? Who would we trust to weigh in on that? What evidence would count? Now we're kind of on the same team. And then if we can establish that, then we're on a search for a capital T truth together or whatever. It's kind" }, { "from": "human", "value": "of pie in the sky, but in some conversations I've actually had success with that. And then you can kind of realize if, uh, if there's no amount of evidence that's going to prove a show to you that" }, { "from": "gpt", "value": "you're wrong in your current opinion, that that's probably a really bad sign for you. It's a waste. It may be a waste to pursue the conversation further at that point. Yeah. Yeah. What? Oh, so, okay. You think Trump was a good president. How do you determine that? And what evidence might exist that would change your mind? There is no evidence Trump was the best" }, { "from": "human", "value": "president ever. I think the conversation is probably done. Except a, yeah. All right. Uh, you mentioned Israel, Palestine. Well, what do you think about the situation in Israel and Palestine? Something you've thought about, spoken about for quite a time. Do you think" }, { "from": "gpt", "value": "we'll ever see peace in this part of the world? I don't know. You know, I mean, uh, I could say, yes, I could say yes. I, I, the, you know, one of the problems is, and I'll give, you may not know that the, there are people on the left of my audience who call me a Netanyahu shill, even though I've never been a supporter of Netanyahu and I'm, I'm on the left. I just don't think that some of the, uh, kind of black and white characterizations about Israel are even remotely accurate. And I think most people, uh, it's become a sort of litmus test. Are you criticizing Israel enough? Are you showing us that you're actually left wing? I don't do any of that stuff. I really" }, { "from": "human", "value": "look at the situation for what it is. I could say yes. That's become a litmus test in American" }, { "from": "gpt", "value": "politics, uh, in the spectrum of American politics. Yeah. Yes. Um, my view big picture is that, uh, I don't think we're going to really get anywhere until some pre negotiated terms are set and the parties to do the negotiating are all good faith parties. For example, I don't think Israel's right wing party Likud is a particularly good faith arbiter of peace because I think leek wood benefits from there not being peace and the threat of violence, and there is violence. It's not just the threat of violence. I don't think Hamas is going to be an arbiter of peace for the Palestinian people either. I think the Palestinian authority is a question mark. I'm not sure. So I think that there need to be some pre conditions that would need to be set with regard to everything from settlements to a lot of this minutia. Big picture, though, if I imagine what the most likely solution looks like, it doesn't mean it's a perfect solution. And obviously, it's a solution. Many people will say it's not it's not going to happen. I think it's a solution where the borders are similar to what was being discussed in the Clinton era, to some degree, as many of the settlements as possible have to go understanding that some of the bigger ones are just not going to go. And there's going to have to be meaningful land swaps with which Yasser Arafat seemed to be amenable to when he weighed in on it. I believe it was in the 90s. The topic of the Temple Mount and Jerusalem, et cetera, is a complicated one. But I think that almost certainly East Jerusalem is going to have to be part of an eventual Palestinian state. You know, I mean, like we can go as kind of as far as as we want to with a lot" }, { "from": "human", "value": "of this stuff. What role does U.S. have to play in this coming to the table with good faith parties?" }, { "from": "gpt", "value": "I don't know whether I go back and forth between believing that the U.S. should play a big role to the U.S. should play essentially no role whatsoever, because, of course, of the funding of Israel that the U.S. provides will the U.S. I don't it's not that I have a personal problem with American involvement. And somebody like Bill Clinton was arguably relatively well positioned to try to make something happen. It's more just will there will it be seen as credible on the global stage? And that's, I think, the most important thing, because at the end of whatever negotiation takes place, both sides need to agree that this is where we are renouncing all past claims. And in the future, if there's a disagreement, we can't go back to that thing from the 80s or the" } ]

[ { "from": "human", "value": "90s. That's just like a critical piece of this. Yeah, it has to be stable and, you know, materialize into something stable over years, over years. Yes. Another difficult conflict going on in the world is the war in Ukraine. What do you think about the Russian invasion of Ukraine in February" }, { "from": "gpt", "value": "2022? I don't pretend to be an expert on this issue. I think you probably know more about this than I do just from the brief conversation we had before we started filming my view as a general observer of geopolitics and the way that this area, this part of the world is related to American presidents over the last several, you know, cycles is I don't think it's controversial to say that this was a war of aggression, an invasion of aggression, an act of aggression by Vladimir Putin. I do believe that if Trump had been reelected, Putin may have seen himself as having other tools with which to try to expand influence that may have been different than geographical pursuits, geographic pursuits. But we don't know that for sure. I also have a really hard time imagining what the end of this looks like. And that's very scary because sometimes the most benign end seems to be that Putin ends up out of power, either through no longer being alive or deposed in some way. It doesn't feel like that latter is super likely the former. There's reports about his health. I don't know how accurate they are. It's just hard to imagine a face saving exit that is going to be even remotely. What's the word? It's not even a question of acceptable. Just it's not satisfying either. Just not tragic, I guess is what I'm" }, { "from": "human", "value": "looking for. In terms of Putin speaking to the Russian people and being able to figure out what to say, what kind of narrative to say why this war made sense. Yes. The same on the Ukrainian" }, { "from": "gpt", "value": "side to figure out how to exit this war. Yes. I mean, to some degree, it requires Russian troops leaving Ukraine. And that is somewhat under the control. I mean, of course, it's not up to Ukraine whether the initiative continues. But what I am not thrilled with are some of the reflexive. You know, if Trump had been in power instead of Joe Biden, a lot of the reflexive comments about, oh, you're if you if you say Ukraine is just acting defensively, you're supporting neo Nazis or some of these things that have come out of the American Republican Party seem both wacky and like they would be saying completely different things. If Trump happened to be in the Oval Office, they're really proxy attacks on Joe Biden." }, { "from": "human", "value": "Yeah. Well, that in some sense, Ukraine is also kind of political litmus test of how you speak about it, I think, because of the huge amount of funding that's going from US to Ukraine. Maybe you can correct me if I'm wrong. But it seems to it seems to me that" }, { "from": "gpt", "value": "this topic has become politicized already. A hundred percent. There are people like Marjorie Taylor Green and others saying we should be doing nothing for Ukraine. Zelensky is a comedian and we're supporting neo Nazis. That's it. Full stop. And you either subscribe to that or you don't. And it very quickly becomes it very quickly becomes as partisan as so many other issues. And it's really the most disappointing thing is that some of these issues become incredibly divisive, divisive, but they're simple. Like, for example, a conspiracy theory that we know isn't true. It shouldn't be devices divisive because it's so simple. Other issues become divisive and they are simplified. But in reality, they are extraordinarily complex and you lose the" }, { "from": "human", "value": "ability to talk about the complexity because they're becoming partisan. Do you think there will always be war in the world as a bunch of folks in the subreddit that were interested in your different complex perspectives on foreign policy? So let's talk about war. When you look at the war in Ukraine, you look at what's going on in Israel and Palestine, you look at the wars across the world. Do you think there will always be war? As the Redditor put it, is it a necessary" }, { "from": "gpt", "value": "evil in the game of geopolitics? I used to have what I now believe is an extremely naive perspective, which is that if we somehow if intelligent aliens arrived here, it would be so momentous for Homo sapiens that all of our differences would immediately be exposed to so insignificant. We would never fight again and we would realize that intelligent life. And then I spoke to people who deal in space exploration and other other scientists and they all said that David, that's extraordinarily naive. There would be a period during which this was as momentous as you're imagining and then it would become normal. And then we would go back to many of the same conflicts that we have now, sectarian, et cetera. I think that in all likelihood, there will always be conflict between factions, whether it's what we currently think of as war, probably not. I mean, it seems as though the tactics will evolve and it will be less about missiles and I don't know where it's going to go. I don't know whether it's going to become more biological or cyber or certainly something we haven't even considered yet. But I think there will always be conflicts we would" }, { "from": "human", "value": "refer to in that way. Do you agree with Chomsky on his general harsh criticism of U.S. foreign policy in war that many actions, military actions in the United States are criminal in nature," }, { "from": "gpt", "value": "almost terrorist in nature? I am not, it's been a decade or more since I've read any Chomsky and I don't keep up with everything that he has recently said. So I don't want to" } ]

[ { "from": "human", "value": "mischaracterize any of it. In general, Americans are sold the view that we're the good guys spreading freedom across the world. And no chance it takes a perspective that, yeah, but if you look at the number of civilians you kill while doing it, it's incomparable to any" }, { "from": "gpt", "value": "other military actions across the world. Right. So I very much disagree with those who take the view that the U.S. is this wonderful global police force that's spreading democracy and fixing problems very, very much wrong. I think where I've had disagreements with Chomsky in the past is more he frame he seems to frame the U.S. as a uniquely bad actor in some of these cases. And I think it's more an outcropping of the size and wealth of the U.S. and less about uniquely negative intentions. And so I think that would be my general disagreement with Chomsky based on" }, { "from": "human", "value": "stuff I read a decade ago. Well, he says that he knows the United States. He's an American. And so he feels his focus of criticism should be in America. And I think that's one of the great things about being an American and being in America is the freedom to criticize harshly. Sure. While we being a university professor, by the way, he's basically the embodiment of why 10 years are really valuable thing. I agree. Whether you agree with him or not. A question from Reddit. Sure. I agree. Ask David what he plans for his garden this year." }, { "from": "gpt", "value": "Is this a joke or is this not a joke? Is this a joke? It's not a joke. I got into gardening a few years ago. Honestly, I'm with the baby. I can't do a garden this year. And I have a lot of travel coming up, so everything would die. But I did start to try to figure out gardening. If you're stressed by the toxicity of the social media world, gardening is a great hobby. It really" }, { "from": "human", "value": "is. But it is extraordinarily time consuming. So I have no garden planned this year. Other books are maybe movies in your life that had a big impact on you that, you know, you're thinking about that diet. Has there been stuff you read, forget it, but even just books like blogs or writers or just sources of information that had molded you into the intellectual," }, { "from": "gpt", "value": "into the political thinker that you are. It's so hard. This is sort of like, you know, you win an Oscar and you want to make sure you thank all the right people. I read so much and have been reading for so long that it's really hard to say. But I think certainly for me, narrative nonfiction has been a fantastic genre to learn not only about history, but also about people and psychology. And very often when people say, I don't really read, like, what can you recommend to me that might be interesting? Depending on, you know, knowing them to some degree, I'll give recommendations there in terms of just things I picked up recently that that I think are interesting. I've been reading a bunch of Neil Postman. I read a Jenny Odell has a new book on time and the concept of like saving time, spending time, etc. She just published it. Super interesting. I just read Lansing's book about the Shackleton voyage in Antarctica in" }, { "from": "human", "value": "1914, 15 and 16. Super interesting. I'm really all over the map. I have that one on audio book." }, { "from": "gpt", "value": "I've been meaning to listen. It's very interesting. And it seems inconceivable how these guys survived." }, { "from": "human", "value": "It's completely inconceivable. And yet they did. It kind of inspires you to think of space exploration and taking on similar kinds of risky and dangerous journeys. In narrative nonfiction, I agree with you very much. I've been reading a lot of 20th century history about Stalin and about" }, { "from": "gpt", "value": "Hitler. Rise and Fall of the Third Reich, I've read twice now. What did you get out of reading" }, { "from": "human", "value": "at the second time? The second time I listened to the audiobook as I ran, I get the same thing from it as I get maybe reading Man's Search for Meaning, which is all the troubles of day to day in the modern world fade away and dissipate when I'm thinking about the embodiment of evil at scale at that recent time in human history. It fills me with gratitude to have all the freedoms, all the simple joys of life that we have today. I think the second time as I was reading it, because William Shire was there, he's the author, he was there through the whole thing. You start to pick up little details. It's supposed to be like big things. You start to pick up the little quirks of how history turns and just like these little events. You notice the dynamics between people in a room during a meeting with Hitler. You just notice these little things that are mentioned because he was either there directly or heard it the next day. That's why to me, Rise and Fall of the Third Reich is interesting. It's because it's by a guy who was there, who's reporting on it versus a more distant, displaced retelling. I also like biographies. I'm a big fan of biographies. Walter Isaacson has just written some incredible ones, and Steve Jobs and Einstein, all that kind of stuff." }, { "from": "gpt", "value": "Victor Frankel's book is one I've read a bunch of times, and it's so short. Reading in general, I know a lot of people who read way more than I do, and I also know a lot of people who don't read at all. I mean, they haven't read a book since college, essentially. To me, it's almost like the amount I get from it, it's almost like a secret weapon where when I think in two or three or four hundred pages, which I can read in whatever 10 days or however long it takes reading 30 pages a day, the amount of information insights into so many aspects of the human psyche that I can get, it's sort of like it's not like I'm in a competition for anything in particular with anybody. I just do my show. But it's sort of like if I'm reading dozens of books a year and you're reading zero, I'm exposed to so many different things and ideas that are not even in your universe. It just seems like the power of reading just seems overwhelming." } ]

[ { "from": "human", "value": "I had speaking of getting attacked, I had a fun time getting attacked a few months ago for publishing a reading list, some reading at least a book a week, read 18 or 19 books from the" }, { "from": "gpt", "value": "beginning of the year. You got attacked for the books you chose or for this? I don't know for what. I don't know for what, but it became quite viral. Attacked for reading? That's something." }, { "from": "human", "value": "So basically what happened is that people, I actually don't, it's not worth folks who know. Fair. Folks who don't even worry about it. What I really loved about being attacked for is it shows you can get attacked for anything, apparently. So it's not like I did something wrong. It was kind of a beautiful thing and it was just the most intensely beautiful display of absurdity of Twitter and the internet. There were articles written about me with a book list. There's no bad books on it. The thing I was being mocked for is reading Dostoyevsky, reading stuff that sounds like a high school reading list. Oh, I see. Or all these kinds of aspects of the reading list which doesn't stand up to any sort of legitimate kind of criticism. But the fact that people are just looking for single words or single aspects of a tweet and so on to criticize. It actually forced me to, because I released a video about summarizing my takeaways from one of the books and I've been meaning to do more and more, but every time I start to record it, I have this negative feeling. They kind of ruin the fun of sharing with others." }, { "from": "gpt", "value": "I know it's fair, apparently. Oh, I see. Yeah, I know exactly what you're talking about. My advice on that is don't do it. Just don't record it. And is that what you did basically?" }, { "from": "human", "value": "Yeah, for now. But I think time cures it. But for now, I decided not to. Yes." }, { "from": "gpt", "value": "It's just until I feel joy when I do it. We are in such a privileged position to even be able to do this sort of thing, right? I have taken on projects and then it sort of sounds good or I end up doing it because there's some third party that brings the idea and I feel like I can't really say no or whatever. And then when I get in front of the camera or I have to write something for a while, I did a newspaper column that I hated doing. I realized that I'm ruining the exact thing that I have worked to build, which is that I can just do whatever I want. Why am I doing this? And sometimes it takes me a week to realize it. Sometimes it takes me a year, but just don't do it. That's the-" }, { "from": "human", "value": "In this case in particular, it's also that there's a private thing I enjoy, which is reading. Right. And if sharing that private thing you enjoy is not fun, then just don't share it. Yeah, there's certain things, there's certain private things that should remain private, which is one of the first things ever. I'm the same person privately as I am publicly, but the books, it's like, man, I don't get to share, I guess through these conversations I can share some of the stuff I'm reading and enjoying it. Because it sucks. It sucks to get attacked for stuff. And it sucks to get attacked for stuff you love." }, { "from": "gpt", "value": "Yeah, especially reading. That's the bottom of the barrel. I have these ideas where I'll go, maybe for my next thing, I'll go from politics, which is so toxic. I'll go to travel blogging because there's so many travel bloggers I follow and there's so many interesting places. And then I go, wait a second. I like traveling and just hanging out. Now traveling is going to be my job and now I've got to bring two cameras with me and I've got to get shots and I've got to film my food. I'm not going to do that. I'm just going to do what I'm doing, but then I'll travel" }, { "from": "human", "value": "when I want to take a vacation. And of course, some of it could be fun. I mean, I have to say, when I did one video on a book in 1984, I really enjoyed it. That whole process was fun. It was, um, um, I don't think I've ever thought as hard about a book when I had to make a video about it. Cause I had to like, you know, I read 1984. I don't know how many times, probably five, 10 times. I don't remember. Um, I read animal farm way more. Uh, but I don't think I was like, what do I think? What are the key takeaways for me? I didn't really know. Like if you asked me what I think about even animal farm, cause I haven't done that one and I've read that one. I don't know. Over 50 times is probably my favorite book is like, I would have to struggle and making a video about it. Basically a little mini lecture forced me to actually have an opinion about the details of it and to do enough research to think like, okay, what is the historical context of this book? I mean, it allowed me to say interesting and to think interesting stuff about the book. I, I, it was, I found it to be really rewarding to basically the old Feynman" }, { "from": "gpt", "value": "thing. Uh, one of the best ways to learn is to teach video about it. Yeah. Yeah. I can't think of one thing I would say about animal farm and I read it again, not that long ago, but I don't know" } ]

[ { "from": "human", "value": "what comments you kind of have a generic comment. Yeah. Like, uh, authoritarianism and so on, whatever. Yeah. But there, there could be interesting quirks of the book and the characters and the how, uh, how corruption happens. You could, you could say all kinds of stuff that it may be contrasting it. Like even when 1984 allowed me to contrast with Brave New World and, um, and, uh, and how, uh, that 1984 was politicized and how it's used by the Republican party of today. Like you could say a lot of interesting stuff if you like think about it and write it down on a sheet of paper. Maybe you don't need to make a video about it. So I found it to be really rewarding in general. So I probably will do more of it, but not always, not as a meat profession, just like with the travel blog. Yeah. I agree with that. I mean, you get threatened a lot. You get attacked a lot online. Do you think about your mortality?" }, { "from": "gpt", "value": "Well, the other day I went to the doctor and he said, you know, next physical, we're going to be talking about a lot of new things. And so I was thinking about it a lot that day. Yeah. Uh, no, I mean, um, it's funny. I like, I recently did a bunch of estate stuff. Yeah. And when you have intellectual property, there's a question of like, okay, I have my assets, but also if I died tomorrow, especially in a particularly fiery death, my YouTube channel would probably for a while generate more money because it would be like, Oh my goodness, this person died in a terrible, what happens with a future revenue stream and all these different things. And it got me thinking about legacy and about the fact that people who do this sort of thing, it's kind of a new thing in a sense. And so, you know, if you work at ABC news, at some point you just retire and someone else fills in for you. How does my career wind down given like, I don't actually know the answer. I'm not sure. Um, what is it? I just one day stop posting videos, but all my content stays up, getting fewer and fewer views. Or do I delete" }, { "from": "human", "value": "everything? Do I, I don't know. What did, what is the, what is the, I mean, so you, my trip to Ukraine, cause I knew I was going to the front. It's the first time I did, um, I recorded a video if I die and I posted it and I gave instructions to, uh, to folks what to do. So like there's a closure, but it's an interesting process. Like what happens to your, at which point does GPT" }, { "from": "gpt", "value": "take over the continued tweeting for David pathway? Well, well, the tweeting I care less about right now, unless blue becomes something unbelievable. I'm less worried about Twitter, but some of my audience members have been saying, you know, some of these tools, David are getting good enough that we could clone your voice and also make it match video. And with scripts, you could just keep pumping out content, even if you were gone. And I said, now that I'm interested in that. I" }, { "from": "human", "value": "want to learn more about boy, it's going to be a weird future. Uh, what advice do you have to" }, { "from": "gpt", "value": "young folks that are facing this future? Almost always it's some version of start right away. And that applies in so many different ways. So if you're thinking about, oftentimes the context is people want to do what I do. And I always say, do not sit around for a year thinking about lighting. This is how you never do anything. And I, dozens of people who I've felt obligated to talk to on the phone because of a personal connection, I go through all the advice and I can tell they're not going to do it. They just, they're, it's already sounding too complicated. And so instead they'll sort of say, well, I got to get the right lighting and the right room and blah, blah, blah, blah. The best thing you can do, no matter what you're doing is just start right away. And that applies in this business and in whatever else you're doing. If you want to learn a new thing, find a new hobby, the ability to get data right away about what's working, what's not working, and whether you even like this approach that you're taking is so valuable and it will allow you to iterate. And the sooner you do it, the cost to a change of direction will also be lower. If there's any, I don't do like self-help or generic advice type stuff, but the one thing that applies in so many situations is situations is just try it right away and iterate from there. Yeah, start today and then do it every day. Every day. Or decide, hey, you know what? I figured out I don't actually want to do it." }, { "from": "human", "value": "Yeah, and iterate. Yeah. Well, usually you'll discover, you do. Do you think we'll make it out of the century, humanity, human civilization?" }, { "from": "gpt", "value": "Yeah, out of the, so like to 2100?" }, { "from": "human", "value": "Yeah, how much we got? 80 years? Yeah, 77. I think we're going to make it. I think we're going to make it. You think so? Yeah. What are the biggest threats facing our civilization? If not, woke us." }, { "from": "gpt", "value": "Yeah, if it's not woke ism, it's hard to say. I actually think that if you believe that we are on an inflection point of sorts in changes to society and acceleration of technology, et cetera, I think it's really tough to know in 2090 what will actually be the biggest threat. So I don't know. It's so cliche to say nuclear and climate change and another pandemic." } ]

[ { "from": "human", "value": "Technologically, our world might look so different. Yes. Yes. Unimaginable. What it means to be human is unimaginable. And also, the degree that we make progress out into space is also unimaginable." }, { "from": "gpt", "value": "Yes, yeah. I think space is super interesting. And there's people on both the left and right who, for different reasons, are kind of not into the whole space exploration thing. The people I hear from, the ones on the right, think it's just kind of dumb. The ones on the left think it's an excuse" }, { "from": "human", "value": "not to fix problems here. And also, they say it's the plaything of billionaires. Sure. Which is another funny kind of concept." }, { "from": "gpt", "value": "Yeah. I mean, someone's got to pay for it. Why not be people who have a lot of money to plug in?" }, { "from": "human", "value": "It can either be billionaires or governments that are trillionaires. Sure." }, { "from": "gpt", "value": "Somebody has to pay for big, ambitious moonshot projects. To me, the most interesting thing is that in getting closer to the next step of space exploration, we may well learn things that can then be used to improve circumstances here. For me, it's not one or the other. And I recently read a long piece about why not Mars, because it's terrible in every way for supporting life. Okay, so that's one perspective. But still, in so exploring, who knows what we might end up learning. So I'm big on it. I don't share the view of some on the left about it." }, { "from": "human", "value": "So I guess to add to your advice to young people, if a thing seems terrible, you still might want to consider doing it." }, { "from": "gpt", "value": "I would say so. Yeah. How many things I've seen. I mean, listen, there are so many trips where the day before I say, why am I doing this, the jet lag, I've got to do this and that. And now who if my guest host falls through, I should just stay in work. And I go, hold on, you do this every time. Yep. Just go. You never regret it. You learn something, you try something. I never regret the trip." }, { "from": "human", "value": "This hopefully applies to the conversation we had today. David, I'm a big fan of yours. Thank you so much for talking today. Thank you for being patient with me. We tried to talk earlier. Please continue doing what you're doing. Please continue being objective and thoughtful and fearless. Thank you. On the internet." }, { "from": "gpt", "value": "Thank you. Big fan of yours as well. I appreciate it." }, { "from": "human", "value": "Thanks for listening to this conversation with David Pakman. To support this podcast, please check out our sponsors in the description. And now let me leave you with some words from Mahatma Gandhi. What difference does it make to the dead, the orphans, and the homeless? Whether the mad destruction is wrought under the name of totalitarianism or in the holy name of liberty or democracy? Thank you for listening and hope to see you next time." } ]

[ { "from": "human", "value": "My favorite is probably the different sub flavors of Ubuntu, Ubuntu Mate. That's what I use for my personal development projects in general when I want to feel comfortable and fully customized, but I've used so many other Linux's, distribution of Linux's. But that's not what Linode is about, or it is in part, but it actually takes those Linux boxes and scales them arbitrarily to where you can do compute, not just on one machine, but on many machines, customize them, make sure everything works reliably, and when it doesn't, there's amazing human customer service with real humans. That's something that should be emphasized in this day of Chad GPT. Real human beings that are good at what they do" }, { "from": "gpt", "value": "and figure out how to solve problems if they ever come up." }, { "from": "human", "value": "Linode, now called Akamai, is just amazing. If compute is something you care about for your business, for your personal life, for your happiness, for anything, then now you should check them out." }, { "from": "gpt", "value": "Visit linode.com slash Lex for a free credit." }, { "from": "human", "value": "Amazing. This episode is brought to you by a thing that I'm currently drinking, as I'm saying these words. It's the Element Electrolyte Drink Mix, spelled L-M-N-T. My favorite is the Watermelon. That's what I always drink, you know? We have all explored. In college, things got wild, things got a little crazy, things got a little out of hand. All of us have done things we regret. Have eaten ice cream, we should not have eaten. I've eaten ice cream at Dairy Queen so many times in my life, especially through my high school years, and to contradict what I just said, I regret nothing. I think Snickers, and if memory serves me correctly, there's something called the Dairy Queen Blizzard, where you could basically shove in whatever you want into the ice cream and blend it, and it tastes delicious. Like, I think my favorite would be like the Snickers bar, any kind of bar, Mars bar, and anything with kind of chocolate caramel, maybe a little bit coconut, that kind of stuff. You know, I don't regret it, but we've experimented. All of us have experimented with different flavors, with different things in life, and I regret nothing. You should not regret any of it either, because that path, I regret nothing, is what created the beautiful person that you are today. And that path is also the reason I mostly drink the watermelon flavor of, I guess it's called watermelon salt. I don't know what it's called, but watermelon's in the word, of element. I highly recommend it. You could try other flavors. Chocolate's pretty good too, like chocolate mint, I think it's called. Totally different thing. All the flavors are very different, and that's why I love it, so you should explore. Anyway, it's a good way to get all the electrolytes in your system, the salt, the magnesium, the potassium, not salt, sodium is what I meant to say. It doesn't matter what I meant to say. What matters is it's delicious, and I'm consuming it, and I'm singing it praises, and I will toast you when we see each other in person one day, friend. And we should drink element, drink to our deepest fulfillments together as brothers and sisters in arms. Get a simple pack for free with any purchase. Try it at drinkelement.com slash Lex. This is the Lex Freeman podcast. To support it, please check out our sponsors in the description. And now, dear friends, here's Robert Plater. When did you first fall in love with robotics?" }, { "from": "gpt", "value": "Let's start with love and robots. Well, love is relevant because I think the fascination, the deep fascination is really about movement. And I was visiting MIT looking for a place to get a PhD, and I wanted to do some laboratory work. And one of my professors in the Aero department said, go see this guy, Mark Raber, down in the basement of the AI lab. And so I walked down there and saw him. He showed me his robots, and he showed me this robot doing a somersault. And I just immediately went, whoa, you know? Robots can do that. And because of my own interest in gymnastics, there was like this immediate connection. And I was interested in, I was in an aero-astro degree because flight and movement was all so fascinating to me. And then it turned out that robotics had this big challenge. How do you balance, how do you build a legged robot that couldn't really get around? And that just, that was a fascination. And it still exists today." }, { "from": "human", "value": "You're still working on perfecting motion in robots. What about the elegance and the beauty of the movement itself? Is there something maybe grounded in your appreciation of movement from your gymnastics days? Did you, was there something you just fundamentally appreciate" }, { "from": "gpt", "value": "about the elegance and beauty of movement? You know, we had this concept in gymnastics of letting your body do what it wanted to do when you get really good at gymnastics. Part of what you're doing is putting your body into a position where the physics and the body's inertia and momentum will kind of push you in the right direction in a very natural and organic way. And the thing that Mark was doing, in the basement of that laboratory, was trying to figure out how to build machines to take advantage of those ideas. How do you build something so that the physics of the machine just kind of inherently wants to do what it wants to do? And he was building these springy pogo stick type. His first cut at Leggett Locomotion was a pogo stick where it's bouncing and there's a spring mass system that's oscillating, has its own sort of natural frequency there, and sort of figuring out how to augment those natural physics with also intent. How do you then control that, but not overpower it? It's that coordination that I think creates real potential. We could call it beauty, you know, you could call it, I don't know, synergy, that people have different words for it, but I think that was inherent from the beginning. That was clear to me that that's part of what Mark was trying to do. He asked me to do that in my research work." } ]